| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062106310641065106610671068106910701071107210731074107510761077107810791080108110821083108410851086108710881089109010911092109310941095109610971098109911001101110211031104110511061107110811091110111111121113111411151116111711181119112011211122112311241125112611271128112911301131113211331134113511361137113811391140114111421143114411451146114711481149115011511152115311541155115611571158115911601161116211631164116511661167116811691170117111721173117411751176117711781179118011811182118311841185118611871188118911901191119211931194119511961197119811991200120112021203120412051206120712081209121012111212121312141215121612171218121912201221122212231224122512261227122812291230123112321233123412351236123712381239124012411242124312441245124612471248124912501251125212531254125512561257125812591260126112621263126412651266126712681269127012711272127312741275127612771278127912801281128212831284128512861287128812891290129112921293129412951296129712981299130013011302130313041305130613071308130913101311131213131314131513161317131813191320132113221323132413251326132713281329133013311332133313341335133613371338133913401341134213431344134513461347134813491350135113521353135413551356135713581359136013611362136313641365136613671368136913701371137213731374137513761377137813791380138113821383138413851386138713881389139013911392139313941395139613971398139914001401140214031404140514061407140814091410141114121413141414151416141714181419142014211422142314241425142614271428142914301431143214331434143514361437143814391440144114421443144414451446144714481449145014511452145314541455145614571458145914601461146214631464146514661467146814691470147114721473147414751476147714781479148014811482148314841485148614871488148914901491149214931494149514961497149814991500150115021503150415051506150715081509151015111512151315141515151615171518151915201521152215231524152515261527152815291530153115321533153415351536153715381539154015411542154315441545154615471548154915501551155215531554155515561557155815591560156115621563156415651566156715681569157015711572157315741575157615771578157915801581158215831584158515861587158815891590159115921593159415951596159715981599160016011602160316041605160616071608160916101611161216131614161516161617161816191620162116221623162416251626162716281629163016311632163316341635163616371638163916401641164216431644164516461647164816491650165116521653165416551656165716581659166016611662166316641665166616671668166916701671167216731674167516761677167816791680168116821683168416851686168716881689169016911692169316941695169616971698169917001701170217031704170517061707170817091710171117121713171417151716171717181719172017211722172317241725172617271728172917301731173217331734173517361737173817391740174117421743174417451746174717481749175017511752175317541755175617571758175917601761176217631764176517661767176817691770177117721773177417751776177717781779178017811782178317841785178617871788178917901791179217931794179517961797179817991800180118021803180418051806180718081809181018111812181318141815181618171818181918201821182218231824182518261827182818291830183118321833183418351836183718381839184018411842184318441845184618471848184918501851185218531854185518561857185818591860186118621863186418651866186718681869187018711872187318741875187618771878187918801881188218831884188518861887188818891890189118921893189418951896189718981899190019011902190319041905190619071908190919101911191219131914191519161917191819191920192119221923192419251926192719281929193019311932193319341935193619371938193919401941194219431944194519461947194819491950195119521953195419551956195719581959196019611962196319641965196619671968196919701971197219731974197519761977197819791980198119821983198419851986198719881989199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022202320242025202620272028202920302031203220332034203520362037203820392040204120422043204420452046204720482049205020512052205320542055205620572058205920602061206220632064206520662067206820692070207120722073207420752076207720782079208020812082208320842085208620872088208920902091209220932094209520962097209820992100210121022103210421052106210721082109211021112112211321142115211621172118211921202121212221232124212521262127212821292130213121322133213421352136213721382139214021412142214321442145214621472148214921502151215221532154215521562157215821592160216121622163216421652166216721682169217021712172217321742175217621772178217921802181218221832184218521862187218821892190219121922193219421952196219721982199220022012202220322042205220622072208220922102211221222132214221522162217221822192220222122222223222422252226222722282229223022312232223322342235223622372238223922402241224222432244224522462247224822492250225122522253225422552256225722582259226022612262226322642265226622672268226922702271227222732274227522762277227822792280228122822283228422852286228722882289229022912292229322942295229622972298229923002301230223032304230523062307230823092310231123122313231423152316231723182319232023212322232323242325232623272328232923302331233223332334233523362337233823392340234123422343234423452346234723482349235023512352235323542355235623572358235923602361236223632364236523662367236823692370237123722373237423752376237723782379238023812382238323842385238623872388238923902391239223932394239523962397239823992400240124022403240424052406240724082409241024112412241324142415241624172418241924202421242224232424242524262427242824292430243124322433243424352436243724382439244024412442244324442445244624472448244924502451245224532454245524562457245824592460246124622463246424652466246724682469247024712472247324742475247624772478247924802481248224832484248524862487248824892490249124922493249424952496249724982499250025012502250325042505250625072508250925102511251225132514251525162517251825192520252125222523252425252526252725282529253025312532253325342535253625372538253925402541254225432544254525462547254825492550255125522553255425552556255725582559256025612562256325642565256625672568256925702571257225732574257525762577257825792580258125822583258425852586258725882589259025912592259325942595259625972598259926002601260226032604260526062607260826092610261126122613261426152616261726182619262026212622262326242625262626272628262926302631263226332634263526362637263826392640264126422643264426452646264726482649265026512652265326542655265626572658265926602661266226632664266526662667266826692670267126722673267426752676267726782679268026812682268326842685268626872688268926902691269226932694269526962697269826992700270127022703270427052706270727082709271027112712271327142715271627172718271927202721272227232724272527262727272827292730273127322733273427352736273727382739274027412742274327442745274627472748274927502751275227532754275527562757275827592760276127622763276427652766276727682769277027712772277327742775277627772778277927802781278227832784278527862787278827892790279127922793279427952796279727982799280028012802280328042805280628072808280928102811281228132814281528162817281828192820282128222823282428252826282728282829283028312832283328342835283628372838283928402841284228432844284528462847284828492850285128522853285428552856285728582859286028612862286328642865286628672868286928702871287228732874287528762877287828792880288128822883288428852886288728882889289028912892289328942895289628972898289929002901290229032904290529062907290829092910291129122913291429152916291729182919292029212922292329242925292629272928292929302931293229332934293529362937293829392940294129422943294429452946294729482949295029512952295329542955295629572958295929602961296229632964296529662967296829692970297129722973297429752976297729782979298029812982298329842985298629872988298929902991299229932994299529962997299829993000300130023003300430053006300730083009301030113012301330143015301630173018301930203021302230233024302530263027302830293030303130323033303430353036303730383039304030413042304330443045304630473048304930503051305230533054305530563057305830593060306130623063306430653066306730683069307030713072307330743075307630773078307930803081308230833084308530863087308830893090309130923093309430953096309730983099310031013102310331043105310631073108310931103111311231133114311531163117311831193120312131223123312431253126312731283129313031313132313331343135313631373138313931403141314231433144314531463147314831493150315131523153315431553156315731583159316031613162316331643165316631673168316931703171317231733174317531763177317831793180318131823183318431853186318731883189319031913192319331943195319631973198319932003201320232033204320532063207320832093210321132123213321432153216321732183219322032213222322332243225322632273228322932303231323232333234323532363237323832393240324132423243324432453246324732483249325032513252325332543255325632573258325932603261326232633264326532663267326832693270327132723273327432753276327732783279328032813282328332843285328632873288328932903291329232933294329532963297329832993300330133023303330433053306330733083309331033113312331333143315331633173318331933203321332233233324332533263327332833293330333133323333333433353336333733383339334033413342334333443345334633473348334933503351335233533354335533563357335833593360336133623363336433653366336733683369337033713372337333743375337633773378337933803381338233833384338533863387338833893390339133923393339433953396339733983399340034013402340334043405340634073408340934103411341234133414341534163417341834193420342134223423342434253426342734283429343034313432343334343435343634373438343934403441344234433444344534463447344834493450345134523453345434553456345734583459346034613462346334643465346634673468346934703471347234733474347534763477347834793480348134823483348434853486348734883489349034913492349334943495349634973498349935003501350235033504350535063507350835093510351135123513351435153516351735183519352035213522352335243525352635273528352935303531353235333534353535363537353835393540354135423543354435453546354735483549355035513552355335543555355635573558355935603561356235633564356535663567356835693570357135723573357435753576357735783579358035813582358335843585358635873588358935903591359235933594359535963597359835993600360136023603360436053606360736083609361036113612361336143615361636173618361936203621362236233624362536263627362836293630363136323633363436353636363736383639364036413642364336443645364636473648364936503651365236533654365536563657365836593660366136623663366436653666366736683669367036713672367336743675367636773678367936803681368236833684368536863687368836893690369136923693369436953696369736983699370037013702370337043705370637073708370937103711371237133714371537163717371837193720372137223723372437253726372737283729373037313732373337343735373637373738373937403741374237433744374537463747374837493750375137523753375437553756375737583759376037613762376337643765376637673768376937703771377237733774377537763777377837793780378137823783378437853786378737883789379037913792379337943795379637973798379938003801380238033804380538063807380838093810381138123813381438153816381738183819382038213822382338243825382638273828382938303831383238333834383538363837383838393840384138423843384438453846384738483849385038513852385338543855385638573858385938603861386238633864386538663867386838693870387138723873387438753876387738783879388038813882388338843885388638873888388938903891389238933894389538963897389838993900390139023903390439053906390739083909391039113912391339143915391639173918391939203921392239233924392539263927392839293930393139323933393439353936393739383939394039413942394339443945394639473948394939503951395239533954395539563957395839593960396139623963396439653966396739683969397039713972397339743975397639773978397939803981398239833984398539863987398839893990399139923993399439953996399739983999400040014002400340044005400640074008400940104011401240134014401540164017401840194020402140224023402440254026402740284029403040314032403340344035403640374038403940404041404240434044404540464047404840494050405140524053405440554056405740584059406040614062406340644065406640674068406940704071407240734074407540764077407840794080408140824083408440854086408740884089409040914092409340944095409640974098409941004101410241034104410541064107410841094110411141124113411441154116411741184119412041214122412341244125412641274128412941304131413241334134413541364137413841394140414141424143414441454146414741484149415041514152415341544155415641574158415941604161416241634164416541664167416841694170417141724173417441754176417741784179418041814182418341844185418641874188418941904191419241934194419541964197419841994200420142024203420442054206420742084209421042114212421342144215421642174218421942204221422242234224422542264227422842294230423142324233423442354236423742384239424042414242424342444245424642474248424942504251425242534254425542564257425842594260426142624263426442654266426742684269427042714272427342744275427642774278427942804281428242834284428542864287428842894290429142924293429442954296429742984299430043014302430343044305430643074308430943104311431243134314431543164317431843194320432143224323432443254326432743284329433043314332433343344335433643374338433943404341434243434344434543464347434843494350435143524353435443554356435743584359436043614362436343644365436643674368436943704371437243734374437543764377437843794380438143824383438443854386438743884389439043914392439343944395439643974398439944004401440244034404440544064407440844094410441144124413441444154416441744184419442044214422442344244425442644274428442944304431443244334434443544364437443844394440444144424443444444454446444744484449445044514452445344544455445644574458445944604461446244634464446544664467446844694470447144724473447444754476447744784479448044814482448344844485448644874488448944904491449244934494449544964497449844994500450145024503450445054506450745084509451045114512451345144515451645174518451945204521452245234524452545264527452845294530453145324533453445354536453745384539454045414542454345444545454645474548454945504551455245534554455545564557455845594560456145624563456445654566456745684569457045714572457345744575457645774578457945804581458245834584458545864587458845894590459145924593459445954596459745984599460046014602460346044605460646074608460946104611461246134614461546164617461846194620462146224623462446254626462746284629463046314632463346344635463646374638463946404641464246434644464546464647464846494650465146524653465446554656465746584659466046614662466346644665466646674668466946704671467246734674467546764677467846794680468146824683468446854686468746884689469046914692469346944695469646974698469947004701470247034704470547064707470847094710471147124713471447154716471747184719472047214722472347244725472647274728472947304731473247334734473547364737473847394740474147424743474447454746474747484749475047514752475347544755475647574758475947604761476247634764476547664767476847694770477147724773477447754776477747784779478047814782478347844785478647874788478947904791479247934794479547964797479847994800480148024803480448054806480748084809481048114812481348144815481648174818481948204821482248234824482548264827482848294830483148324833483448354836483748384839484048414842484348444845484648474848484948504851485248534854485548564857485848594860486148624863486448654866486748684869487048714872487348744875487648774878487948804881488248834884488548864887488848894890489148924893489448954896489748984899490049014902490349044905490649074908490949104911491249134914491549164917491849194920492149224923492449254926492749284929493049314932493349344935493649374938493949404941494249434944494549464947494849494950495149524953495449554956495749584959496049614962496349644965496649674968496949704971497249734974497549764977497849794980498149824983498449854986498749884989499049914992499349944995499649974998499950005001500250035004500550065007500850095010501150125013501450155016501750185019502050215022502350245025502650275028502950305031503250335034503550365037503850395040504150425043504450455046504750485049505050515052505350545055505650575058505950605061506250635064506550665067506850695070507150725073507450755076507750785079508050815082508350845085508650875088508950905091509250935094509550965097509850995100510151025103510451055106510751085109511051115112511351145115511651175118511951205121512251235124512551265127512851295130513151325133513451355136513751385139514051415142514351445145514651475148514951505151515251535154515551565157515851595160516151625163516451655166516751685169517051715172517351745175517651775178517951805181518251835184518551865187518851895190519151925193519451955196519751985199520052015202520352045205520652075208520952105211521252135214521552165217521852195220522152225223522452255226522752285229523052315232523352345235523652375238523952405241524252435244524552465247524852495250525152525253525452555256525752585259526052615262526352645265526652675268526952705271527252735274527552765277527852795280528152825283528452855286528752885289529052915292529352945295529652975298529953005301530253035304530553065307530853095310531153125313531453155316531753185319532053215322532353245325532653275328532953305331533253335334533553365337533853395340534153425343534453455346534753485349535053515352535353545355535653575358535953605361536253635364536553665367536853695370537153725373537453755376537753785379538053815382538353845385538653875388538953905391539253935394539553965397539853995400540154025403540454055406540754085409541054115412541354145415541654175418541954205421542254235424542554265427542854295430543154325433543454355436543754385439544054415442544354445445544654475448544954505451545254535454545554565457545854595460546154625463546454655466546754685469547054715472547354745475547654775478547954805481548254835484548554865487548854895490549154925493549454955496549754985499550055015502550355045505550655075508550955105511551255135514551555165517551855195520552155225523552455255526552755285529553055315532553355345535553655375538553955405541554255435544554555465547554855495550555155525553555455555556555755585559556055615562556355645565556655675568556955705571557255735574557555765577557855795580558155825583558455855586558755885589559055915592559355945595559655975598559956005601560256035604560556065607560856095610561156125613561456155616561756185619562056215622562356245625562656275628562956305631563256335634563556365637563856395640564156425643564456455646564756485649565056515652565356545655565656575658565956605661566256635664566556665667566856695670567156725673567456755676567756785679568056815682568356845685568656875688568956905691569256935694569556965697569856995700570157025703570457055706570757085709571057115712571357145715571657175718571957205721572257235724572557265727572857295730573157325733573457355736573757385739574057415742574357445745574657475748574957505751575257535754575557565757575857595760576157625763576457655766576757685769577057715772577357745775577657775778577957805781578257835784578557865787578857895790579157925793579457955796579757985799580058015802580358045805580658075808580958105811581258135814581558165817581858195820582158225823582458255826582758285829583058315832583358345835583658375838583958405841584258435844584558465847584858495850585158525853585458555856585758585859586058615862586358645865586658675868586958705871587258735874587558765877587858795880588158825883588458855886588758885889589058915892589358945895589658975898589959005901590259035904590559065907590859095910591159125913591459155916591759185919592059215922592359245925592659275928592959305931593259335934593559365937593859395940594159425943594459455946594759485949595059515952595359545955595659575958595959605961596259635964596559665967596859695970597159725973597459755976597759785979598059815982598359845985598659875988598959905991599259935994599559965997599859996000600160026003600460056006600760086009601060116012601360146015601660176018601960206021602260236024602560266027602860296030603160326033603460356036603760386039604060416042604360446045604660476048604960506051605260536054605560566057605860596060606160626063606460656066606760686069607060716072607360746075607660776078607960806081608260836084608560866087608860896090609160926093609460956096609760986099610061016102610361046105610661076108610961106111611261136114611561166117611861196120612161226123612461256126612761286129613061316132613361346135613661376138613961406141614261436144614561466147614861496150615161526153615461556156615761586159616061616162616361646165616661676168616961706171617261736174617561766177617861796180618161826183618461856186618761886189619061916192619361946195619661976198619962006201620262036204620562066207620862096210621162126213621462156216621762186219622062216222622362246225622662276228622962306231623262336234623562366237623862396240624162426243624462456246624762486249625062516252625362546255625662576258625962606261626262636264626562666267626862696270627162726273627462756276627762786279628062816282628362846285628662876288628962906291629262936294629562966297629862996300630163026303630463056306630763086309631063116312631363146315631663176318631963206321632263236324632563266327632863296330633163326333633463356336633763386339634063416342634363446345634663476348634963506351635263536354635563566357635863596360636163626363636463656366636763686369637063716372637363746375637663776378637963806381638263836384638563866387638863896390639163926393639463956396639763986399640064016402640364046405640664076408640964106411641264136414641564166417641864196420642164226423642464256426642764286429643064316432643364346435643664376438643964406441644264436444644564466447644864496450645164526453645464556456645764586459646064616462646364646465646664676468646964706471647264736474647564766477647864796480648164826483648464856486648764886489649064916492649364946495649664976498649965006501650265036504650565066507650865096510651165126513651465156516651765186519652065216522652365246525652665276528652965306531653265336534653565366537653865396540654165426543654465456546654765486549655065516552655365546555655665576558655965606561656265636564656565666567656865696570657165726573657465756576657765786579658065816582658365846585658665876588658965906591659265936594659565966597659865996600660166026603660466056606660766086609661066116612661366146615661666176618661966206621662266236624662566266627662866296630663166326633663466356636663766386639664066416642664366446645664666476648664966506651665266536654665566566657665866596660666166626663666466656666666766686669667066716672667366746675667666776678667966806681668266836684668566866687668866896690669166926693669466956696669766986699670067016702670367046705670667076708670967106711671267136714671567166717671867196720672167226723672467256726672767286729673067316732673367346735673667376738673967406741674267436744674567466747674867496750675167526753675467556756675767586759676067616762676367646765676667676768676967706771677267736774677567766777677867796780678167826783678467856786678767886789679067916792679367946795679667976798679968006801680268036804680568066807680868096810681168126813681468156816681768186819682068216822682368246825682668276828682968306831683268336834683568366837683868396840684168426843684468456846684768486849685068516852685368546855685668576858685968606861686268636864686568666867686868696870687168726873687468756876687768786879688068816882688368846885688668876888688968906891689268936894689568966897689868996900690169026903690469056906690769086909691069116912691369146915691669176918691969206921692269236924692569266927692869296930693169326933693469356936693769386939694069416942694369446945694669476948694969506951695269536954695569566957695869596960696169626963696469656966696769686969697069716972697369746975697669776978697969806981698269836984698569866987698869896990699169926993699469956996699769986999700070017002700370047005700670077008700970107011701270137014701570167017701870197020702170227023702470257026702770287029703070317032703370347035703670377038703970407041704270437044704570467047704870497050705170527053705470557056705770587059706070617062706370647065706670677068706970707071707270737074707570767077707870797080708170827083708470857086708770887089709070917092709370947095709670977098709971007101710271037104710571067107710871097110711171127113711471157116711771187119712071217122712371247125712671277128712971307131713271337134713571367137713871397140714171427143714471457146714771487149715071517152715371547155715671577158715971607161716271637164716571667167716871697170717171727173717471757176717771787179718071817182718371847185718671877188718971907191719271937194719571967197719871997200720172027203720472057206720772087209721072117212721372147215721672177218721972207221722272237224722572267227722872297230723172327233723472357236723772387239724072417242724372447245724672477248724972507251725272537254725572567257725872597260726172627263726472657266726772687269727072717272727372747275727672777278727972807281728272837284728572867287728872897290729172927293729472957296729772987299730073017302730373047305730673077308730973107311731273137314731573167317731873197320732173227323732473257326732773287329733073317332733373347335733673377338733973407341734273437344734573467347734873497350735173527353735473557356735773587359736073617362736373647365736673677368736973707371737273737374737573767377737873797380738173827383738473857386738773887389739073917392739373947395739673977398739974007401740274037404740574067407740874097410741174127413741474157416741774187419742074217422742374247425742674277428742974307431743274337434743574367437743874397440744174427443744474457446744774487449745074517452745374547455745674577458745974607461746274637464746574667467746874697470747174727473747474757476747774787479748074817482748374847485748674877488748974907491749274937494749574967497749874997500750175027503750475057506750775087509751075117512751375147515751675177518751975207521752275237524752575267527752875297530753175327533753475357536753775387539754075417542754375447545754675477548754975507551755275537554755575567557755875597560756175627563756475657566756775687569757075717572757375747575757675777578757975807581758275837584758575867587758875897590759175927593759475957596759775987599760076017602760376047605760676077608760976107611761276137614761576167617761876197620762176227623762476257626762776287629763076317632763376347635763676377638763976407641764276437644764576467647764876497650765176527653765476557656765776587659766076617662766376647665766676677668766976707671767276737674767576767677767876797680768176827683768476857686768776887689769076917692769376947695769676977698769977007701770277037704770577067707770877097710771177127713771477157716771777187719772077217722772377247725772677277728772977307731773277337734773577367737773877397740774177427743774477457746774777487749775077517752775377547755775677577758775977607761776277637764776577667767776877697770777177727773777477757776777777787779778077817782778377847785778677877788778977907791779277937794779577967797779877997800780178027803780478057806780778087809781078117812781378147815781678177818781978207821782278237824782578267827782878297830783178327833783478357836783778387839784078417842784378447845784678477848784978507851785278537854785578567857785878597860786178627863786478657866786778687869787078717872787378747875787678777878787978807881788278837884788578867887788878897890789178927893789478957896789778987899790079017902790379047905790679077908790979107911791279137914791579167917791879197920792179227923792479257926792779287929793079317932793379347935793679377938793979407941794279437944794579467947794879497950795179527953795479557956795779587959796079617962796379647965796679677968796979707971797279737974797579767977797879797980798179827983798479857986798779887989799079917992799379947995799679977998799980008001800280038004800580068007800880098010801180128013801480158016801780188019802080218022802380248025802680278028802980308031803280338034803580368037803880398040804180428043804480458046804780488049805080518052805380548055805680578058805980608061806280638064806580668067806880698070807180728073807480758076807780788079808080818082808380848085808680878088808980908091809280938094809580968097809880998100810181028103810481058106810781088109811081118112811381148115811681178118811981208121812281238124812581268127812881298130813181328133813481358136813781388139814081418142814381448145814681478148814981508151815281538154815581568157815881598160816181628163816481658166816781688169817081718172817381748175817681778178817981808181818281838184818581868187818881898190819181928193819481958196819781988199820082018202820382048205820682078208820982108211821282138214821582168217821882198220822182228223822482258226822782288229823082318232823382348235823682378238823982408241824282438244824582468247824882498250825182528253825482558256825782588259826082618262826382648265826682678268826982708271827282738274827582768277827882798280828182828283828482858286828782888289829082918292829382948295829682978298829983008301830283038304830583068307830883098310831183128313831483158316831783188319832083218322832383248325832683278328832983308331833283338334833583368337833883398340834183428343834483458346834783488349835083518352835383548355835683578358835983608361836283638364836583668367836883698370837183728373837483758376837783788379838083818382838383848385838683878388838983908391839283938394839583968397839883998400840184028403840484058406840784088409841084118412841384148415841684178418841984208421842284238424842584268427842884298430843184328433843484358436843784388439844084418442844384448445844684478448844984508451845284538454845584568457845884598460846184628463846484658466846784688469847084718472847384748475847684778478847984808481848284838484848584868487848884898490849184928493849484958496849784988499850085018502850385048505850685078508850985108511851285138514851585168517851885198520852185228523852485258526852785288529853085318532853385348535853685378538853985408541854285438544854585468547854885498550855185528553855485558556855785588559856085618562856385648565856685678568856985708571857285738574857585768577857885798580858185828583858485858586858785888589859085918592859385948595859685978598859986008601860286038604860586068607860886098610861186128613861486158616861786188619862086218622862386248625862686278628862986308631863286338634863586368637863886398640864186428643864486458646864786488649865086518652865386548655865686578658865986608661866286638664866586668667866886698670867186728673867486758676867786788679868086818682868386848685868686878688868986908691869286938694869586968697869886998700870187028703870487058706870787088709871087118712871387148715871687178718871987208721872287238724872587268727872887298730873187328733873487358736873787388739874087418742874387448745874687478748874987508751875287538754875587568757875887598760876187628763876487658766876787688769877087718772877387748775877687778778877987808781878287838784878587868787878887898790879187928793879487958796879787988799880088018802880388048805880688078808880988108811881288138814881588168817881888198820882188228823882488258826882788288829883088318832883388348835883688378838883988408841884288438844884588468847884888498850885188528853885488558856885788588859886088618862886388648865886688678868886988708871887288738874887588768877887888798880888188828883888488858886888788888889889088918892889388948895889688978898889989008901890289038904890589068907890889098910891189128913891489158916891789188919892089218922892389248925892689278928892989308931893289338934893589368937893889398940894189428943894489458946894789488949895089518952895389548955895689578958895989608961896289638964896589668967896889698970897189728973897489758976897789788979898089818982898389848985898689878988898989908991899289938994899589968997899889999000900190029003900490059006900790089009901090119012901390149015901690179018901990209021902290239024902590269027902890299030903190329033903490359036903790389039904090419042904390449045904690479048904990509051905290539054905590569057905890599060906190629063906490659066906790689069907090719072907390749075907690779078907990809081908290839084908590869087908890899090909190929093909490959096909790989099910091019102910391049105910691079108910991109111911291139114911591169117911891199120912191229123912491259126912791289129913091319132913391349135913691379138913991409141914291439144914591469147914891499150915191529153915491559156915791589159916091619162916391649165916691679168916991709171917291739174917591769177917891799180918191829183918491859186918791889189919091919192919391949195919691979198919992009201920292039204920592069207920892099210921192129213921492159216921792189219922092219222922392249225922692279228922992309231923292339234923592369237923892399240924192429243924492459246924792489249925092519252925392549255925692579258925992609261926292639264926592669267926892699270927192729273927492759276927792789279928092819282928392849285928692879288928992909291929292939294929592969297929892999300930193029303930493059306930793089309931093119312931393149315931693179318931993209321932293239324932593269327932893299330933193329333933493359336933793389339934093419342934393449345934693479348934993509351935293539354935593569357935893599360936193629363936493659366936793689369937093719372937393749375937693779378937993809381938293839384938593869387938893899390939193929393939493959396939793989399940094019402940394049405940694079408940994109411941294139414941594169417941894199420942194229423942494259426942794289429943094319432943394349435943694379438943994409441944294439444944594469447944894499450945194529453945494559456945794589459946094619462946394649465946694679468946994709471947294739474947594769477947894799480948194829483948494859486948794889489949094919492949394949495949694979498949995009501950295039504950595069507950895099510951195129513951495159516951795189519952095219522952395249525952695279528952995309531953295339534953595369537953895399540954195429543954495459546954795489549955095519552955395549555955695579558955995609561956295639564956595669567956895699570957195729573957495759576957795789579958095819582958395849585958695879588958995909591959295939594959595969597959895999600960196029603960496059606960796089609961096119612961396149615961696179618961996209621962296239624962596269627962896299630963196329633963496359636963796389639964096419642964396449645964696479648964996509651965296539654965596569657965896599660966196629663966496659666966796689669967096719672967396749675967696779678967996809681968296839684968596869687968896899690969196929693969496959696969796989699970097019702970397049705970697079708970997109711971297139714971597169717971897199720972197229723972497259726972797289729973097319732973397349735973697379738973997409741974297439744974597469747974897499750975197529753975497559756975797589759976097619762976397649765976697679768976997709771977297739774977597769777977897799780978197829783978497859786978797889789979097919792979397949795979697979798979998009801980298039804980598069807980898099810981198129813981498159816981798189819982098219822982398249825982698279828982998309831983298339834983598369837983898399840984198429843984498459846984798489849985098519852985398549855985698579858985998609861986298639864986598669867986898699870987198729873987498759876987798789879988098819882988398849885988698879888988998909891989298939894989598969897989898999900990199029903990499059906990799089909991099119912991399149915991699179918991999209921992299239924992599269927992899299930993199329933993499359936993799389939994099419942994399449945994699479948994999509951995299539954995599569957995899599960996199629963996499659966996799689969997099719972997399749975997699779978997999809981998299839984998599869987998899899990999199929993999499959996999799989999100001000110002100031000410005100061000710008100091001010011100121001310014100151001610017100181001910020100211002210023100241002510026100271002810029100301003110032100331003410035100361003710038100391004010041100421004310044100451004610047100481004910050100511005210053100541005510056100571005810059100601006110062100631006410065100661006710068100691007010071100721007310074100751007610077100781007910080100811008210083100841008510086100871008810089100901009110092100931009410095100961009710098100991010010101101021010310104101051010610107101081010910110101111011210113101141011510116101171011810119101201012110122101231012410125101261012710128101291013010131101321013310134101351013610137101381013910140101411014210143101441014510146101471014810149101501015110152101531015410155101561015710158101591016010161101621016310164101651016610167101681016910170101711017210173101741017510176101771017810179101801018110182101831018410185101861018710188101891019010191101921019310194101951019610197101981019910200102011020210203102041020510206102071020810209102101021110212102131021410215102161021710218102191022010221102221022310224102251022610227102281022910230102311023210233102341023510236102371023810239102401024110242102431024410245102461024710248102491025010251102521025310254102551025610257102581025910260102611026210263102641026510266102671026810269102701027110272102731027410275102761027710278102791028010281102821028310284102851028610287102881028910290102911029210293102941029510296102971029810299103001030110302103031030410305103061030710308103091031010311103121031310314103151031610317103181031910320103211032210323103241032510326103271032810329103301033110332103331033410335103361033710338103391034010341103421034310344103451034610347103481034910350103511035210353103541035510356103571035810359103601036110362103631036410365103661036710368103691037010371103721037310374103751037610377103781037910380103811038210383103841038510386103871038810389103901039110392103931039410395103961039710398103991040010401104021040310404104051040610407104081040910410104111041210413104141041510416104171041810419104201042110422104231042410425104261042710428104291043010431104321043310434104351043610437104381043910440104411044210443104441044510446104471044810449104501045110452104531045410455104561045710458104591046010461104621046310464104651046610467104681046910470104711047210473104741047510476104771047810479104801048110482104831048410485104861048710488104891049010491104921049310494104951049610497104981049910500105011050210503105041050510506105071050810509105101051110512105131051410515105161051710518105191052010521105221052310524105251052610527105281052910530105311053210533105341053510536105371053810539105401054110542105431054410545105461054710548105491055010551105521055310554105551055610557105581055910560105611056210563105641056510566105671056810569105701057110572105731057410575105761057710578105791058010581105821058310584105851058610587105881058910590105911059210593105941059510596105971059810599106001060110602106031060410605106061060710608106091061010611106121061310614106151061610617106181061910620106211062210623106241062510626106271062810629106301063110632106331063410635106361063710638106391064010641106421064310644106451064610647106481064910650106511065210653106541065510656106571065810659106601066110662106631066410665106661066710668106691067010671106721067310674106751067610677106781067910680106811068210683106841068510686106871068810689106901069110692106931069410695106961069710698106991070010701107021070310704107051070610707107081070910710107111071210713107141071510716107171071810719107201072110722107231072410725107261072710728107291073010731107321073310734107351073610737107381073910740107411074210743107441074510746107471074810749107501075110752107531075410755107561075710758107591076010761107621076310764107651076610767107681076910770107711077210773107741077510776107771077810779107801078110782107831078410785107861078710788107891079010791107921079310794107951079610797107981079910800108011080210803108041080510806108071080810809108101081110812108131081410815108161081710818108191082010821108221082310824108251082610827108281082910830108311083210833108341083510836108371083810839108401084110842108431084410845108461084710848108491085010851108521085310854108551085610857108581085910860108611086210863108641086510866108671086810869108701087110872108731087410875108761087710878108791088010881108821088310884108851088610887108881088910890108911089210893108941089510896108971089810899109001090110902109031090410905109061090710908109091091010911109121091310914109151091610917109181091910920109211092210923109241092510926109271092810929109301093110932109331093410935109361093710938109391094010941109421094310944109451094610947109481094910950109511095210953109541095510956109571095810959109601096110962109631096410965109661096710968109691097010971109721097310974109751097610977109781097910980109811098210983109841098510986109871098810989109901099110992109931099410995109961099710998109991100011001110021100311004110051100611007110081100911010110111101211013110141101511016110171101811019110201102111022110231102411025110261102711028110291103011031110321103311034110351103611037110381103911040110411104211043110441104511046110471104811049110501105111052110531105411055110561105711058110591106011061110621106311064110651106611067110681106911070110711107211073110741107511076110771107811079110801108111082110831108411085110861108711088110891109011091110921109311094110951109611097110981109911100111011110211103111041110511106111071110811109111101111111112111131111411115111161111711118111191112011121111221112311124111251112611127111281112911130111311113211133111341113511136111371113811139111401114111142111431114411145111461114711148111491115011151111521115311154111551115611157111581115911160111611116211163111641116511166111671116811169111701117111172111731117411175111761117711178111791118011181111821118311184111851118611187111881118911190111911119211193111941119511196111971119811199112001120111202112031120411205112061120711208112091121011211112121121311214112151121611217112181121911220112211122211223112241122511226112271122811229112301123111232112331123411235112361123711238112391124011241112421124311244112451124611247112481124911250112511125211253112541125511256112571125811259112601126111262112631126411265112661126711268112691127011271112721127311274112751127611277112781127911280112811128211283112841128511286112871128811289112901129111292112931129411295112961129711298112991130011301113021130311304113051130611307113081130911310113111131211313113141131511316113171131811319113201132111322113231132411325113261132711328113291133011331113321133311334113351133611337113381133911340113411134211343113441134511346113471134811349113501135111352113531135411355113561135711358113591136011361113621136311364113651136611367113681136911370113711137211373113741137511376113771137811379113801138111382113831138411385113861138711388113891139011391113921139311394113951139611397113981139911400114011140211403114041140511406114071140811409114101141111412114131141411415114161141711418114191142011421114221142311424114251142611427114281142911430114311143211433114341143511436114371143811439114401144111442114431144411445114461144711448114491145011451114521145311454114551145611457114581145911460114611146211463114641146511466114671146811469114701147111472114731147411475114761147711478114791148011481114821148311484114851148611487114881148911490114911149211493114941149511496114971149811499115001150111502115031150411505115061150711508115091151011511115121151311514115151151611517115181151911520115211152211523115241152511526115271152811529115301153111532115331153411535115361153711538115391154011541115421154311544115451154611547115481154911550115511155211553115541155511556115571155811559115601156111562115631156411565115661156711568115691157011571115721157311574115751157611577115781157911580115811158211583115841158511586115871158811589115901159111592115931159411595115961159711598115991160011601116021160311604116051160611607116081160911610116111161211613116141161511616116171161811619116201162111622116231162411625116261162711628116291163011631116321163311634116351163611637116381163911640116411164211643116441164511646116471164811649116501165111652116531165411655116561165711658116591166011661116621166311664116651166611667116681166911670116711167211673116741167511676116771167811679116801168111682116831168411685116861168711688116891169011691116921169311694116951169611697116981169911700117011170211703117041170511706117071170811709117101171111712117131171411715117161171711718117191172011721117221172311724117251172611727117281172911730117311173211733117341173511736117371173811739117401174111742117431174411745117461174711748117491175011751117521175311754117551175611757117581175911760117611176211763117641176511766117671176811769117701177111772117731177411775117761177711778117791178011781117821178311784117851178611787117881178911790117911179211793117941179511796117971179811799118001180111802118031180411805118061180711808118091181011811118121181311814118151181611817118181181911820118211182211823118241182511826118271182811829118301183111832118331183411835118361183711838118391184011841118421184311844118451184611847118481184911850118511185211853118541185511856118571185811859118601186111862118631186411865118661186711868118691187011871118721187311874118751187611877118781187911880118811188211883118841188511886118871188811889118901189111892118931189411895118961189711898118991190011901119021190311904119051190611907119081190911910119111191211913119141191511916119171191811919119201192111922119231192411925119261192711928119291193011931119321193311934119351193611937119381193911940119411194211943119441194511946119471194811949119501195111952119531195411955119561195711958119591196011961119621196311964119651196611967119681196911970119711197211973119741197511976119771197811979119801198111982119831198411985119861198711988119891199011991119921199311994119951199611997119981199912000120011200212003120041200512006120071200812009120101201112012120131201412015120161201712018120191202012021120221202312024120251202612027120281202912030120311203212033120341203512036120371203812039120401204112042120431204412045120461204712048120491205012051120521205312054120551205612057120581205912060120611206212063120641206512066120671206812069120701207112072120731207412075120761207712078120791208012081120821208312084120851208612087120881208912090120911209212093120941209512096120971209812099121001210112102121031210412105121061210712108121091211012111121121211312114121151211612117121181211912120121211212212123121241212512126121271212812129121301213112132121331213412135121361213712138121391214012141121421214312144121451214612147121481214912150121511215212153121541215512156121571215812159121601216112162121631216412165121661216712168121691217012171121721217312174121751217612177121781217912180121811218212183121841218512186121871218812189121901219112192121931219412195121961219712198121991220012201122021220312204122051220612207122081220912210122111221212213122141221512216122171221812219122201222112222122231222412225122261222712228122291223012231122321223312234122351223612237122381223912240122411224212243122441224512246122471224812249122501225112252122531225412255122561225712258122591226012261122621226312264122651226612267122681226912270122711227212273122741227512276122771227812279122801228112282122831228412285122861228712288122891229012291122921229312294122951229612297122981229912300123011230212303123041230512306123071230812309123101231112312123131231412315123161231712318123191232012321123221232312324123251232612327123281232912330123311233212333123341233512336123371233812339123401234112342123431234412345123461234712348123491235012351123521235312354123551235612357123581235912360123611236212363123641236512366123671236812369123701237112372123731237412375123761237712378123791238012381123821238312384123851238612387123881238912390123911239212393123941239512396123971239812399124001240112402124031240412405124061240712408124091241012411124121241312414124151241612417124181241912420124211242212423124241242512426124271242812429124301243112432124331243412435124361243712438124391244012441124421244312444124451244612447124481244912450124511245212453124541245512456124571245812459124601246112462124631246412465124661246712468124691247012471124721247312474124751247612477124781247912480124811248212483124841248512486124871248812489124901249112492124931249412495124961249712498124991250012501125021250312504125051250612507125081250912510125111251212513125141251512516125171251812519125201252112522125231252412525125261252712528125291253012531125321253312534125351253612537125381253912540125411254212543125441254512546125471254812549125501255112552125531255412555125561255712558125591256012561125621256312564125651256612567125681256912570125711257212573125741257512576125771257812579125801258112582125831258412585125861258712588125891259012591125921259312594125951259612597125981259912600126011260212603126041260512606126071260812609126101261112612126131261412615126161261712618126191262012621126221262312624126251262612627126281262912630126311263212633126341263512636126371263812639126401264112642126431264412645126461264712648126491265012651126521265312654126551265612657126581265912660126611266212663126641266512666126671266812669126701267112672126731267412675126761267712678126791268012681126821268312684126851268612687126881268912690126911269212693126941269512696126971269812699127001270112702127031270412705127061270712708127091271012711127121271312714127151271612717127181271912720127211272212723127241272512726127271272812729127301273112732127331273412735127361273712738127391274012741127421274312744127451274612747127481274912750127511275212753127541275512756127571275812759127601276112762127631276412765127661276712768127691277012771127721277312774127751277612777127781277912780127811278212783127841278512786127871278812789127901279112792127931279412795127961279712798127991280012801128021280312804128051280612807128081280912810128111281212813128141281512816128171281812819128201282112822128231282412825128261282712828128291283012831128321283312834128351283612837128381283912840128411284212843128441284512846128471284812849128501285112852128531285412855128561285712858128591286012861128621286312864128651286612867128681286912870128711287212873128741287512876128771287812879128801288112882128831288412885128861288712888128891289012891128921289312894128951289612897128981289912900129011290212903129041290512906129071290812909129101291112912129131291412915129161291712918129191292012921129221292312924129251292612927129281292912930129311293212933129341293512936129371293812939129401294112942129431294412945129461294712948129491295012951129521295312954129551295612957129581295912960129611296212963129641296512966129671296812969129701297112972129731297412975129761297712978129791298012981129821298312984129851298612987129881298912990129911299212993129941299512996129971299812999130001300113002130031300413005130061300713008130091301013011130121301313014130151301613017130181301913020130211302213023130241302513026130271302813029130301303113032130331303413035130361303713038130391304013041130421304313044130451304613047130481304913050130511305213053130541305513056130571305813059130601306113062130631306413065130661306713068130691307013071130721307313074130751307613077130781307913080130811308213083130841308513086130871308813089130901309113092130931309413095130961309713098130991310013101131021310313104131051310613107131081310913110131111311213113131141311513116131171311813119131201312113122131231312413125131261312713128131291313013131131321313313134131351313613137131381313913140131411314213143131441314513146131471314813149131501315113152131531315413155131561315713158131591316013161131621316313164131651316613167131681316913170131711317213173131741317513176131771317813179131801318113182131831318413185131861318713188131891319013191131921319313194131951319613197131981319913200132011320213203132041320513206132071320813209132101321113212132131321413215132161321713218132191322013221132221322313224132251322613227132281322913230132311323213233132341323513236132371323813239132401324113242132431324413245132461324713248132491325013251132521325313254132551325613257132581325913260132611326213263132641326513266132671326813269132701327113272132731327413275132761327713278132791328013281132821328313284132851328613287132881328913290132911329213293132941329513296132971329813299133001330113302133031330413305133061330713308133091331013311133121331313314133151331613317133181331913320133211332213323133241332513326133271332813329133301333113332133331333413335133361333713338133391334013341133421334313344133451334613347133481334913350133511335213353133541335513356133571335813359133601336113362133631336413365133661336713368133691337013371133721337313374133751337613377133781337913380133811338213383133841338513386133871338813389133901339113392133931339413395133961339713398133991340013401134021340313404134051340613407134081340913410134111341213413134141341513416134171341813419134201342113422134231342413425134261342713428134291343013431134321343313434134351343613437134381343913440134411344213443134441344513446134471344813449134501345113452134531345413455134561345713458134591346013461134621346313464134651346613467134681346913470134711347213473134741347513476134771347813479134801348113482134831348413485134861348713488134891349013491134921349313494134951349613497134981349913500135011350213503135041350513506135071350813509135101351113512135131351413515135161351713518135191352013521135221352313524135251352613527135281352913530135311353213533135341353513536135371353813539135401354113542135431354413545135461354713548135491355013551135521355313554135551355613557135581355913560135611356213563135641356513566135671356813569135701357113572135731357413575135761357713578135791358013581135821358313584135851358613587135881358913590135911359213593135941359513596135971359813599136001360113602136031360413605136061360713608136091361013611136121361313614136151361613617136181361913620136211362213623136241362513626136271362813629136301363113632136331363413635136361363713638136391364013641136421364313644136451364613647136481364913650136511365213653136541365513656136571365813659136601366113662136631366413665136661366713668136691367013671136721367313674136751367613677136781367913680136811368213683136841368513686136871368813689136901369113692136931369413695136961369713698136991370013701137021370313704137051370613707137081370913710137111371213713137141371513716137171371813719137201372113722137231372413725137261372713728137291373013731137321373313734137351373613737137381373913740137411374213743137441374513746137471374813749137501375113752137531375413755137561375713758137591376013761137621376313764137651376613767137681376913770137711377213773137741377513776137771377813779137801378113782137831378413785137861378713788137891379013791137921379313794137951379613797137981379913800138011380213803138041380513806138071380813809138101381113812138131381413815138161381713818138191382013821138221382313824138251382613827138281382913830138311383213833138341383513836138371383813839138401384113842138431384413845138461384713848138491385013851138521385313854138551385613857138581385913860138611386213863138641386513866138671386813869138701387113872138731387413875138761387713878138791388013881138821388313884138851388613887138881388913890138911389213893138941389513896138971389813899139001390113902139031390413905139061390713908139091391013911139121391313914139151391613917139181391913920139211392213923139241392513926139271392813929139301393113932139331393413935139361393713938139391394013941139421394313944139451394613947139481394913950139511395213953139541395513956139571395813959139601396113962139631396413965139661396713968139691397013971139721397313974139751397613977139781397913980139811398213983139841398513986139871398813989139901399113992139931399413995139961399713998139991400014001140021400314004140051400614007140081400914010140111401214013140141401514016140171401814019140201402114022140231402414025140261402714028140291403014031140321403314034140351403614037140381403914040140411404214043140441404514046140471404814049140501405114052140531405414055140561405714058140591406014061140621406314064140651406614067140681406914070140711407214073140741407514076140771407814079140801408114082140831408414085140861408714088140891409014091140921409314094140951409614097140981409914100141011410214103141041410514106141071410814109141101411114112141131411414115141161411714118141191412014121141221412314124141251412614127141281412914130141311413214133141341413514136141371413814139141401414114142141431414414145141461414714148141491415014151141521415314154141551415614157141581415914160141611416214163141641416514166141671416814169141701417114172141731417414175141761417714178141791418014181141821418314184141851418614187141881418914190141911419214193141941419514196141971419814199142001420114202142031420414205142061420714208142091421014211142121421314214142151421614217142181421914220142211422214223142241422514226142271422814229142301423114232142331423414235142361423714238142391424014241142421424314244142451424614247142481424914250142511425214253142541425514256142571425814259142601426114262142631426414265142661426714268142691427014271142721427314274142751427614277142781427914280142811428214283142841428514286142871428814289142901429114292142931429414295142961429714298142991430014301143021430314304143051430614307143081430914310143111431214313143141431514316143171431814319143201432114322143231432414325143261432714328143291433014331143321433314334143351433614337143381433914340143411434214343143441434514346143471434814349143501435114352143531435414355143561435714358143591436014361143621436314364143651436614367143681436914370143711437214373143741437514376143771437814379143801438114382143831438414385143861438714388143891439014391143921439314394143951439614397143981439914400144011440214403144041440514406144071440814409144101441114412144131441414415144161441714418144191442014421144221442314424144251442614427144281442914430144311443214433144341443514436144371443814439144401444114442144431444414445144461444714448144491445014451144521445314454144551445614457144581445914460144611446214463144641446514466144671446814469144701447114472144731447414475144761447714478144791448014481144821448314484144851448614487144881448914490144911449214493144941449514496144971449814499145001450114502145031450414505145061450714508145091451014511145121451314514145151451614517145181451914520145211452214523145241452514526145271452814529145301453114532145331453414535145361453714538145391454014541145421454314544145451454614547145481454914550145511455214553145541455514556145571455814559145601456114562145631456414565145661456714568145691457014571145721457314574145751457614577145781457914580145811458214583145841458514586145871458814589145901459114592145931459414595145961459714598145991460014601146021460314604146051460614607146081460914610146111461214613146141461514616146171461814619146201462114622146231462414625146261462714628146291463014631146321463314634146351463614637146381463914640146411464214643146441464514646146471464814649146501465114652146531465414655146561465714658146591466014661146621466314664146651466614667146681466914670146711467214673146741467514676146771467814679146801468114682146831468414685146861468714688146891469014691146921469314694146951469614697146981469914700147011470214703147041470514706147071470814709147101471114712147131471414715147161471714718147191472014721147221472314724147251472614727147281472914730147311473214733147341473514736147371473814739147401474114742147431474414745147461474714748147491475014751147521475314754147551475614757147581475914760147611476214763147641476514766147671476814769147701477114772147731477414775147761477714778147791478014781147821478314784147851478614787147881478914790147911479214793147941479514796147971479814799148001480114802148031480414805148061480714808148091481014811148121481314814148151481614817148181481914820148211482214823148241482514826148271482814829148301483114832148331483414835148361483714838148391484014841148421484314844148451484614847148481484914850148511485214853148541485514856148571485814859148601486114862148631486414865148661486714868148691487014871148721487314874148751487614877148781487914880148811488214883148841488514886148871488814889148901489114892148931489414895148961489714898148991490014901149021490314904149051490614907149081490914910149111491214913149141491514916149171491814919149201492114922149231492414925149261492714928149291493014931149321493314934149351493614937149381493914940149411494214943149441494514946149471494814949149501495114952149531495414955149561495714958149591496014961149621496314964149651496614967149681496914970149711497214973149741497514976149771497814979149801498114982149831498414985149861498714988149891499014991149921499314994149951499614997149981499915000150011500215003150041500515006150071500815009150101501115012150131501415015150161501715018150191502015021150221502315024150251502615027150281502915030150311503215033150341503515036150371503815039150401504115042150431504415045150461504715048150491505015051150521505315054150551505615057150581505915060150611506215063150641506515066150671506815069150701507115072150731507415075150761507715078150791508015081150821508315084150851508615087150881508915090150911509215093150941509515096150971509815099151001510115102151031510415105151061510715108151091511015111151121511315114151151511615117151181511915120151211512215123151241512515126151271512815129151301513115132151331513415135151361513715138151391514015141151421514315144151451514615147151481514915150151511515215153151541515515156151571515815159151601516115162151631516415165151661516715168151691517015171151721517315174151751517615177151781517915180151811518215183151841518515186151871518815189151901519115192151931519415195151961519715198151991520015201152021520315204152051520615207152081520915210152111521215213152141521515216152171521815219152201522115222152231522415225152261522715228152291523015231152321523315234152351523615237152381523915240152411524215243152441524515246152471524815249152501525115252152531525415255152561525715258152591526015261152621526315264152651526615267152681526915270152711527215273152741527515276152771527815279152801528115282152831528415285152861528715288152891529015291152921529315294152951529615297152981529915300153011530215303153041530515306153071530815309153101531115312153131531415315153161531715318153191532015321153221532315324153251532615327153281532915330153311533215333153341533515336153371533815339153401534115342153431534415345153461534715348153491535015351153521535315354153551535615357153581535915360153611536215363153641536515366153671536815369153701537115372153731537415375153761537715378153791538015381153821538315384153851538615387153881538915390153911539215393153941539515396153971539815399154001540115402154031540415405154061540715408154091541015411154121541315414154151541615417154181541915420154211542215423154241542515426154271542815429154301543115432154331543415435154361543715438154391544015441154421544315444154451544615447154481544915450154511545215453154541545515456154571545815459154601546115462154631546415465154661546715468154691547015471154721547315474154751547615477154781547915480154811548215483154841548515486154871548815489154901549115492154931549415495154961549715498154991550015501155021550315504155051550615507155081550915510155111551215513155141551515516155171551815519155201552115522155231552415525155261552715528155291553015531155321553315534155351553615537155381553915540155411554215543155441554515546155471554815549155501555115552155531555415555155561555715558155591556015561155621556315564155651556615567155681556915570155711557215573155741557515576155771557815579155801558115582155831558415585155861558715588155891559015591155921559315594155951559615597155981559915600156011560215603156041560515606156071560815609156101561115612156131561415615156161561715618156191562015621156221562315624156251562615627156281562915630156311563215633156341563515636156371563815639156401564115642156431564415645156461564715648156491565015651156521565315654156551565615657156581565915660156611566215663156641566515666156671566815669156701567115672156731567415675156761567715678156791568015681156821568315684156851568615687156881568915690156911569215693156941569515696156971569815699157001570115702157031570415705157061570715708157091571015711157121571315714157151571615717157181571915720157211572215723157241572515726157271572815729157301573115732157331573415735157361573715738157391574015741157421574315744157451574615747157481574915750157511575215753157541575515756157571575815759157601576115762157631576415765157661576715768157691577015771157721577315774157751577615777157781577915780157811578215783157841578515786157871578815789157901579115792157931579415795157961579715798157991580015801158021580315804158051580615807158081580915810158111581215813158141581515816158171581815819158201582115822158231582415825158261582715828158291583015831158321583315834158351583615837158381583915840158411584215843158441584515846158471584815849158501585115852158531585415855158561585715858158591586015861158621586315864158651586615867158681586915870158711587215873158741587515876158771587815879158801588115882158831588415885158861588715888158891589015891158921589315894158951589615897158981589915900159011590215903159041590515906159071590815909159101591115912159131591415915159161591715918159191592015921159221592315924159251592615927159281592915930159311593215933159341593515936159371593815939159401594115942159431594415945159461594715948159491595015951159521595315954159551595615957159581595915960159611596215963159641596515966159671596815969159701597115972159731597415975159761597715978159791598015981159821598315984159851598615987159881598915990159911599215993159941599515996159971599815999160001600116002160031600416005160061600716008160091601016011160121601316014160151601616017160181601916020160211602216023160241602516026160271602816029160301603116032160331603416035160361603716038160391604016041160421604316044160451604616047160481604916050160511605216053160541605516056160571605816059160601606116062160631606416065160661606716068160691607016071160721607316074160751607616077160781607916080160811608216083160841608516086160871608816089160901609116092160931609416095160961609716098160991610016101161021610316104161051610616107161081610916110161111611216113161141611516116161171611816119161201612116122161231612416125161261612716128161291613016131161321613316134161351613616137161381613916140161411614216143161441614516146161471614816149161501615116152161531615416155161561615716158161591616016161161621616316164161651616616167161681616916170161711617216173161741617516176161771617816179161801618116182161831618416185161861618716188161891619016191161921619316194161951619616197161981619916200162011620216203162041620516206162071620816209162101621116212162131621416215162161621716218162191622016221162221622316224162251622616227162281622916230162311623216233162341623516236162371623816239162401624116242162431624416245162461624716248162491625016251162521625316254162551625616257162581625916260162611626216263162641626516266162671626816269162701627116272162731627416275162761627716278162791628016281162821628316284162851628616287162881628916290162911629216293162941629516296162971629816299163001630116302163031630416305163061630716308163091631016311163121631316314163151631616317163181631916320163211632216323163241632516326163271632816329163301633116332163331633416335163361633716338163391634016341163421634316344163451634616347163481634916350163511635216353163541635516356163571635816359163601636116362163631636416365163661636716368163691637016371163721637316374163751637616377163781637916380163811638216383163841638516386163871638816389163901639116392163931639416395163961639716398163991640016401164021640316404164051640616407164081640916410164111641216413164141641516416164171641816419164201642116422164231642416425164261642716428164291643016431164321643316434164351643616437164381643916440164411644216443164441644516446164471644816449164501645116452164531645416455164561645716458164591646016461164621646316464164651646616467164681646916470164711647216473164741647516476164771647816479164801648116482164831648416485164861648716488164891649016491164921649316494164951649616497164981649916500165011650216503165041650516506165071650816509165101651116512165131651416515165161651716518165191652016521165221652316524165251652616527165281652916530165311653216533165341653516536165371653816539165401654116542165431654416545165461654716548165491655016551165521655316554165551655616557165581655916560165611656216563165641656516566165671656816569165701657116572165731657416575165761657716578165791658016581165821658316584165851658616587165881658916590165911659216593165941659516596165971659816599166001660116602166031660416605166061660716608166091661016611166121661316614166151661616617166181661916620166211662216623166241662516626166271662816629166301663116632166331663416635166361663716638166391664016641166421664316644166451664616647166481664916650166511665216653166541665516656166571665816659166601666116662166631666416665166661666716668166691667016671166721667316674166751667616677166781667916680166811668216683166841668516686166871668816689166901669116692166931669416695166961669716698166991670016701167021670316704167051670616707167081670916710167111671216713167141671516716167171671816719167201672116722167231672416725167261672716728167291673016731167321673316734167351673616737167381673916740167411674216743167441674516746167471674816749167501675116752167531675416755167561675716758167591676016761167621676316764167651676616767167681676916770167711677216773167741677516776167771677816779167801678116782167831678416785167861678716788167891679016791167921679316794167951679616797167981679916800168011680216803168041680516806168071680816809168101681116812168131681416815168161681716818168191682016821168221682316824168251682616827168281682916830168311683216833168341683516836168371683816839168401684116842168431684416845168461684716848168491685016851168521685316854168551685616857168581685916860168611686216863168641686516866168671686816869168701687116872168731687416875168761687716878168791688016881168821688316884168851688616887168881688916890168911689216893168941689516896168971689816899169001690116902169031690416905169061690716908169091691016911169121691316914169151691616917169181691916920169211692216923169241692516926169271692816929169301693116932169331693416935169361693716938169391694016941169421694316944169451694616947169481694916950169511695216953169541695516956169571695816959169601696116962169631696416965169661696716968169691697016971169721697316974169751697616977169781697916980169811698216983169841698516986169871698816989169901699116992169931699416995169961699716998169991700017001170021700317004170051700617007170081700917010170111701217013170141701517016170171701817019170201702117022170231702417025170261702717028170291703017031170321703317034170351703617037170381703917040170411704217043170441704517046170471704817049170501705117052170531705417055170561705717058170591706017061170621706317064170651706617067170681706917070170711707217073170741707517076170771707817079170801708117082170831708417085170861708717088170891709017091170921709317094170951709617097170981709917100171011710217103171041710517106171071710817109171101711117112171131711417115171161711717118171191712017121171221712317124171251712617127171281712917130171311713217133171341713517136171371713817139171401714117142171431714417145171461714717148171491715017151171521715317154171551715617157171581715917160171611716217163171641716517166171671716817169171701717117172171731717417175171761717717178171791718017181171821718317184171851718617187171881718917190171911719217193171941719517196171971719817199172001720117202172031720417205172061720717208172091721017211172121721317214172151721617217172181721917220172211722217223172241722517226172271722817229172301723117232172331723417235172361723717238172391724017241172421724317244172451724617247172481724917250172511725217253172541725517256172571725817259172601726117262172631726417265172661726717268172691727017271172721727317274172751727617277172781727917280172811728217283172841728517286172871728817289172901729117292172931729417295172961729717298172991730017301173021730317304173051730617307173081730917310173111731217313173141731517316173171731817319173201732117322173231732417325173261732717328173291733017331173321733317334173351733617337173381733917340173411734217343173441734517346173471734817349173501735117352173531735417355173561735717358173591736017361173621736317364173651736617367173681736917370173711737217373173741737517376173771737817379173801738117382173831738417385173861738717388173891739017391173921739317394173951739617397173981739917400174011740217403174041740517406174071740817409174101741117412174131741417415174161741717418174191742017421174221742317424174251742617427174281742917430174311743217433174341743517436174371743817439174401744117442174431744417445174461744717448174491745017451174521745317454174551745617457174581745917460174611746217463174641746517466174671746817469174701747117472174731747417475174761747717478174791748017481174821748317484174851748617487174881748917490174911749217493174941749517496174971749817499175001750117502175031750417505175061750717508175091751017511175121751317514175151751617517175181751917520175211752217523175241752517526175271752817529175301753117532175331753417535175361753717538175391754017541175421754317544175451754617547175481754917550175511755217553175541755517556175571755817559175601756117562175631756417565175661756717568175691757017571175721757317574175751757617577175781757917580175811758217583175841758517586175871758817589175901759117592175931759417595175961759717598175991760017601176021760317604176051760617607176081760917610176111761217613176141761517616176171761817619176201762117622176231762417625176261762717628176291763017631176321763317634176351763617637176381763917640176411764217643176441764517646176471764817649176501765117652176531765417655176561765717658176591766017661176621766317664176651766617667176681766917670176711767217673176741767517676176771767817679176801768117682176831768417685176861768717688176891769017691176921769317694176951769617697176981769917700177011770217703177041770517706177071770817709177101771117712177131771417715177161771717718177191772017721177221772317724177251772617727177281772917730177311773217733177341773517736177371773817739177401774117742177431774417745177461774717748177491775017751177521775317754177551775617757177581775917760177611776217763177641776517766177671776817769177701777117772177731777417775177761777717778177791778017781177821778317784177851778617787177881778917790177911779217793177941779517796177971779817799178001780117802178031780417805178061780717808178091781017811178121781317814178151781617817178181781917820178211782217823178241782517826178271782817829178301783117832178331783417835178361783717838178391784017841178421784317844178451784617847178481784917850178511785217853178541785517856178571785817859178601786117862178631786417865178661786717868178691787017871178721787317874178751787617877178781787917880178811788217883178841788517886178871788817889178901789117892178931789417895178961789717898178991790017901179021790317904179051790617907179081790917910179111791217913179141791517916179171791817919179201792117922179231792417925179261792717928179291793017931179321793317934179351793617937179381793917940179411794217943179441794517946179471794817949179501795117952179531795417955179561795717958179591796017961179621796317964179651796617967179681796917970179711797217973179741797517976179771797817979179801798117982179831798417985179861798717988179891799017991179921799317994179951799617997179981799918000180011800218003180041800518006180071800818009180101801118012180131801418015180161801718018180191802018021180221802318024180251802618027180281802918030180311803218033180341803518036180371803818039180401804118042180431804418045180461804718048180491805018051180521805318054180551805618057180581805918060180611806218063180641806518066180671806818069180701807118072180731807418075180761807718078180791808018081180821808318084180851808618087180881808918090180911809218093180941809518096180971809818099181001810118102181031810418105181061810718108181091811018111181121811318114181151811618117181181811918120181211812218123181241812518126181271812818129181301813118132181331813418135181361813718138181391814018141181421814318144181451814618147181481814918150181511815218153181541815518156181571815818159181601816118162181631816418165181661816718168181691817018171181721817318174181751817618177181781817918180181811818218183181841818518186181871818818189181901819118192181931819418195181961819718198181991820018201182021820318204182051820618207182081820918210182111821218213182141821518216182171821818219182201822118222182231822418225182261822718228182291823018231182321823318234182351823618237182381823918240182411824218243182441824518246182471824818249182501825118252182531825418255182561825718258182591826018261182621826318264182651826618267182681826918270182711827218273182741827518276182771827818279182801828118282182831828418285182861828718288182891829018291182921829318294182951829618297182981829918300183011830218303183041830518306183071830818309183101831118312183131831418315183161831718318183191832018321183221832318324183251832618327183281832918330183311833218333183341833518336183371833818339183401834118342183431834418345183461834718348183491835018351183521835318354183551835618357183581835918360183611836218363183641836518366183671836818369183701837118372183731837418375183761837718378183791838018381183821838318384183851838618387183881838918390183911839218393183941839518396183971839818399184001840118402184031840418405184061840718408184091841018411184121841318414184151841618417184181841918420184211842218423184241842518426184271842818429184301843118432184331843418435184361843718438184391844018441184421844318444184451844618447184481844918450184511845218453184541845518456184571845818459184601846118462184631846418465184661846718468184691847018471184721847318474184751847618477184781847918480184811848218483184841848518486184871848818489184901849118492184931849418495184961849718498184991850018501185021850318504185051850618507185081850918510185111851218513185141851518516185171851818519185201852118522185231852418525185261852718528185291853018531185321853318534185351853618537185381853918540185411854218543185441854518546185471854818549185501855118552185531855418555185561855718558185591856018561185621856318564185651856618567185681856918570185711857218573185741857518576185771857818579185801858118582185831858418585185861858718588185891859018591185921859318594185951859618597185981859918600186011860218603186041860518606186071860818609186101861118612186131861418615186161861718618186191862018621186221862318624186251862618627186281862918630186311863218633186341863518636186371863818639186401864118642186431864418645186461864718648186491865018651186521865318654186551865618657186581865918660186611866218663186641866518666186671866818669186701867118672186731867418675186761867718678186791868018681186821868318684186851868618687186881868918690186911869218693186941869518696186971869818699187001870118702187031870418705187061870718708187091871018711187121871318714187151871618717187181871918720187211872218723187241872518726187271872818729187301873118732187331873418735187361873718738187391874018741187421874318744187451874618747187481874918750187511875218753187541875518756187571875818759187601876118762187631876418765187661876718768187691877018771187721877318774187751877618777187781877918780187811878218783187841878518786187871878818789187901879118792187931879418795187961879718798187991880018801188021880318804188051880618807188081880918810188111881218813188141881518816188171881818819188201882118822188231882418825188261882718828188291883018831188321883318834188351883618837188381883918840188411884218843188441884518846188471884818849188501885118852188531885418855188561885718858188591886018861188621886318864188651886618867188681886918870188711887218873188741887518876188771887818879188801888118882188831888418885188861888718888188891889018891188921889318894188951889618897188981889918900189011890218903189041890518906189071890818909189101891118912189131891418915189161891718918189191892018921189221892318924189251892618927189281892918930189311893218933189341893518936189371893818939189401894118942189431894418945189461894718948189491895018951189521895318954189551895618957189581895918960189611896218963189641896518966189671896818969189701897118972189731897418975189761897718978189791898018981189821898318984189851898618987189881898918990189911899218993189941899518996189971899818999190001900119002190031900419005190061900719008190091901019011190121901319014190151901619017190181901919020190211902219023190241902519026190271902819029190301903119032190331903419035190361903719038190391904019041190421904319044190451904619047190481904919050190511905219053190541905519056190571905819059190601906119062190631906419065190661906719068190691907019071190721907319074190751907619077190781907919080190811908219083190841908519086190871908819089190901909119092190931909419095190961909719098190991910019101191021910319104191051910619107191081910919110191111911219113191141911519116191171911819119191201912119122191231912419125191261912719128191291913019131191321913319134191351913619137191381913919140191411914219143191441914519146191471914819149191501915119152191531915419155191561915719158191591916019161191621916319164191651916619167191681916919170191711917219173191741917519176191771917819179191801918119182191831918419185191861918719188191891919019191191921919319194191951919619197191981919919200192011920219203192041920519206192071920819209192101921119212192131921419215192161921719218192191922019221192221922319224192251922619227192281922919230192311923219233192341923519236192371923819239192401924119242192431924419245192461924719248192491925019251192521925319254192551925619257192581925919260192611926219263192641926519266192671926819269192701927119272192731927419275192761927719278192791928019281192821928319284192851928619287192881928919290192911929219293192941929519296192971929819299193001930119302193031930419305193061930719308193091931019311193121931319314193151931619317193181931919320193211932219323193241932519326193271932819329193301933119332193331933419335193361933719338193391934019341193421934319344193451934619347193481934919350193511935219353193541935519356193571935819359193601936119362193631936419365193661936719368193691937019371193721937319374193751937619377193781937919380193811938219383193841938519386193871938819389193901939119392193931939419395193961939719398193991940019401194021940319404194051940619407194081940919410194111941219413194141941519416194171941819419194201942119422194231942419425194261942719428194291943019431194321943319434194351943619437194381943919440194411944219443194441944519446194471944819449194501945119452194531945419455194561945719458194591946019461194621946319464194651946619467194681946919470194711947219473194741947519476194771947819479194801948119482194831948419485194861948719488194891949019491194921949319494194951949619497194981949919500195011950219503195041950519506195071950819509195101951119512195131951419515195161951719518195191952019521195221952319524195251952619527195281952919530195311953219533195341953519536195371953819539195401954119542195431954419545195461954719548195491955019551195521955319554195551955619557195581955919560195611956219563195641956519566195671956819569195701957119572195731957419575195761957719578195791958019581195821958319584195851958619587195881958919590195911959219593195941959519596195971959819599196001960119602196031960419605196061960719608196091961019611196121961319614196151961619617196181961919620196211962219623196241962519626196271962819629196301963119632196331963419635196361963719638196391964019641196421964319644196451964619647196481964919650196511965219653196541965519656196571965819659196601966119662196631966419665196661966719668196691967019671196721967319674196751967619677196781967919680196811968219683196841968519686196871968819689196901969119692196931969419695196961969719698196991970019701197021970319704197051970619707197081970919710197111971219713197141971519716197171971819719197201972119722197231972419725197261972719728197291973019731197321973319734197351973619737197381973919740197411974219743197441974519746197471974819749197501975119752197531975419755197561975719758197591976019761197621976319764197651976619767197681976919770197711977219773197741977519776197771977819779197801978119782197831978419785197861978719788197891979019791197921979319794197951979619797197981979919800198011980219803198041980519806198071980819809198101981119812198131981419815198161981719818198191982019821198221982319824198251982619827198281982919830198311983219833198341983519836198371983819839198401984119842198431984419845198461984719848198491985019851198521985319854198551985619857198581985919860198611986219863198641986519866198671986819869198701987119872198731987419875198761987719878198791988019881198821988319884198851988619887198881988919890198911989219893198941989519896198971989819899199001990119902199031990419905199061990719908199091991019911199121991319914199151991619917199181991919920199211992219923199241992519926199271992819929199301993119932199331993419935199361993719938199391994019941199421994319944199451994619947199481994919950199511995219953199541995519956199571995819959199601996119962199631996419965199661996719968199691997019971199721997319974199751997619977199781997919980199811998219983199841998519986199871998819989199901999119992199931999419995199961999719998199992000020001200022000320004200052000620007200082000920010200112001220013200142001520016200172001820019200202002120022200232002420025200262002720028200292003020031200322003320034200352003620037200382003920040200412004220043200442004520046200472004820049200502005120052200532005420055200562005720058200592006020061200622006320064200652006620067200682006920070200712007220073200742007520076200772007820079200802008120082200832008420085200862008720088200892009020091200922009320094200952009620097200982009920100201012010220103201042010520106201072010820109201102011120112201132011420115201162011720118201192012020121201222012320124201252012620127201282012920130201312013220133201342013520136201372013820139201402014120142201432014420145201462014720148201492015020151201522015320154201552015620157201582015920160201612016220163201642016520166201672016820169201702017120172201732017420175201762017720178201792018020181201822018320184201852018620187201882018920190201912019220193201942019520196201972019820199202002020120202202032020420205202062020720208202092021020211202122021320214202152021620217202182021920220202212022220223202242022520226202272022820229202302023120232202332023420235202362023720238202392024020241202422024320244202452024620247202482024920250202512025220253202542025520256202572025820259202602026120262202632026420265202662026720268202692027020271202722027320274202752027620277202782027920280202812028220283202842028520286202872028820289202902029120292202932029420295202962029720298202992030020301203022030320304203052030620307203082030920310203112031220313203142031520316203172031820319203202032120322203232032420325203262032720328203292033020331203322033320334203352033620337203382033920340203412034220343203442034520346203472034820349203502035120352203532035420355203562035720358203592036020361203622036320364203652036620367203682036920370203712037220373203742037520376203772037820379203802038120382203832038420385203862038720388203892039020391203922039320394203952039620397203982039920400204012040220403204042040520406204072040820409204102041120412204132041420415204162041720418204192042020421204222042320424204252042620427204282042920430204312043220433204342043520436204372043820439204402044120442204432044420445204462044720448204492045020451204522045320454204552045620457204582045920460204612046220463204642046520466204672046820469204702047120472204732047420475204762047720478204792048020481204822048320484204852048620487204882048920490204912049220493204942049520496204972049820499205002050120502205032050420505205062050720508205092051020511205122051320514205152051620517205182051920520205212052220523205242052520526205272052820529205302053120532205332053420535205362053720538205392054020541205422054320544205452054620547205482054920550205512055220553205542055520556205572055820559205602056120562205632056420565205662056720568205692057020571205722057320574205752057620577205782057920580205812058220583205842058520586205872058820589205902059120592205932059420595205962059720598205992060020601206022060320604206052060620607206082060920610206112061220613206142061520616206172061820619206202062120622206232062420625206262062720628206292063020631206322063320634206352063620637206382063920640206412064220643206442064520646206472064820649206502065120652206532065420655206562065720658206592066020661206622066320664206652066620667206682066920670206712067220673206742067520676206772067820679206802068120682206832068420685206862068720688206892069020691206922069320694206952069620697206982069920700207012070220703207042070520706207072070820709207102071120712207132071420715207162071720718207192072020721207222072320724207252072620727207282072920730207312073220733207342073520736207372073820739207402074120742207432074420745207462074720748207492075020751207522075320754207552075620757207582075920760207612076220763207642076520766207672076820769207702077120772207732077420775207762077720778207792078020781207822078320784207852078620787207882078920790207912079220793207942079520796207972079820799208002080120802208032080420805208062080720808208092081020811208122081320814208152081620817208182081920820208212082220823208242082520826208272082820829208302083120832208332083420835208362083720838208392084020841208422084320844208452084620847208482084920850208512085220853208542085520856208572085820859208602086120862208632086420865208662086720868208692087020871208722087320874208752087620877208782087920880208812088220883208842088520886208872088820889208902089120892208932089420895208962089720898208992090020901209022090320904209052090620907209082090920910209112091220913209142091520916209172091820919209202092120922209232092420925209262092720928209292093020931209322093320934209352093620937209382093920940209412094220943209442094520946209472094820949209502095120952209532095420955209562095720958209592096020961209622096320964209652096620967209682096920970209712097220973209742097520976209772097820979209802098120982209832098420985209862098720988209892099020991209922099320994209952099620997209982099921000210012100221003210042100521006210072100821009210102101121012210132101421015210162101721018210192102021021210222102321024210252102621027210282102921030210312103221033210342103521036210372103821039210402104121042210432104421045210462104721048210492105021051210522105321054210552105621057210582105921060210612106221063210642106521066210672106821069210702107121072210732107421075210762107721078210792108021081210822108321084210852108621087210882108921090210912109221093210942109521096210972109821099211002110121102211032110421105211062110721108211092111021111211122111321114211152111621117211182111921120211212112221123211242112521126211272112821129211302113121132211332113421135211362113721138211392114021141211422114321144211452114621147211482114921150211512115221153211542115521156211572115821159211602116121162211632116421165211662116721168211692117021171211722117321174211752117621177211782117921180211812118221183211842118521186211872118821189211902119121192211932119421195211962119721198211992120021201212022120321204212052120621207212082120921210212112121221213212142121521216212172121821219212202122121222212232122421225212262122721228212292123021231212322123321234212352123621237212382123921240212412124221243212442124521246212472124821249212502125121252212532125421255212562125721258212592126021261212622126321264212652126621267212682126921270212712127221273212742127521276212772127821279212802128121282212832128421285212862128721288212892129021291212922129321294212952129621297212982129921300213012130221303213042130521306213072130821309213102131121312213132131421315213162131721318213192132021321213222132321324213252132621327213282132921330213312133221333213342133521336213372133821339213402134121342213432134421345213462134721348213492135021351213522135321354213552135621357213582135921360213612136221363213642136521366213672136821369213702137121372213732137421375213762137721378213792138021381213822138321384213852138621387213882138921390213912139221393213942139521396213972139821399214002140121402214032140421405214062140721408214092141021411214122141321414214152141621417214182141921420214212142221423214242142521426214272142821429214302143121432214332143421435214362143721438214392144021441214422144321444214452144621447214482144921450214512145221453214542145521456214572145821459214602146121462214632146421465214662146721468214692147021471214722147321474214752147621477214782147921480214812148221483214842148521486214872148821489214902149121492214932149421495214962149721498214992150021501215022150321504215052150621507215082150921510215112151221513215142151521516215172151821519215202152121522215232152421525215262152721528215292153021531215322153321534215352153621537215382153921540215412154221543215442154521546215472154821549215502155121552215532155421555215562155721558215592156021561215622156321564215652156621567215682156921570215712157221573215742157521576215772157821579215802158121582215832158421585215862158721588215892159021591215922159321594215952159621597215982159921600216012160221603216042160521606216072160821609216102161121612216132161421615216162161721618216192162021621216222162321624216252162621627216282162921630216312163221633216342163521636216372163821639216402164121642216432164421645216462164721648216492165021651216522165321654216552165621657216582165921660216612166221663216642166521666216672166821669216702167121672216732167421675216762167721678216792168021681216822168321684216852168621687216882168921690216912169221693216942169521696216972169821699217002170121702217032170421705217062170721708217092171021711217122171321714217152171621717217182171921720217212172221723217242172521726217272172821729217302173121732217332173421735217362173721738217392174021741217422174321744217452174621747217482174921750217512175221753217542175521756217572175821759217602176121762217632176421765217662176721768217692177021771217722177321774217752177621777217782177921780217812178221783217842178521786217872178821789217902179121792217932179421795217962179721798217992180021801218022180321804218052180621807218082180921810218112181221813218142181521816218172181821819218202182121822218232182421825218262182721828218292183021831218322183321834218352183621837218382183921840218412184221843218442184521846218472184821849218502185121852218532185421855218562185721858218592186021861218622186321864218652186621867218682186921870218712187221873218742187521876218772187821879218802188121882218832188421885218862188721888218892189021891218922189321894218952189621897218982189921900219012190221903219042190521906219072190821909219102191121912219132191421915219162191721918219192192021921219222192321924219252192621927219282192921930219312193221933219342193521936219372193821939219402194121942219432194421945219462194721948219492195021951219522195321954219552195621957219582195921960219612196221963219642196521966219672196821969219702197121972219732197421975219762197721978219792198021981219822198321984219852198621987219882198921990219912199221993219942199521996219972199821999220002200122002220032200422005220062200722008220092201022011220122201322014220152201622017220182201922020220212202222023220242202522026220272202822029220302203122032220332203422035220362203722038220392204022041220422204322044220452204622047220482204922050220512205222053220542205522056220572205822059220602206122062220632206422065220662206722068220692207022071220722207322074220752207622077220782207922080220812208222083220842208522086220872208822089220902209122092220932209422095220962209722098220992210022101221022210322104221052210622107221082210922110221112211222113221142211522116221172211822119221202212122122221232212422125221262212722128221292213022131221322213322134221352213622137221382213922140221412214222143221442214522146221472214822149221502215122152221532215422155221562215722158221592216022161221622216322164221652216622167221682216922170221712217222173221742217522176221772217822179221802218122182221832218422185221862218722188221892219022191221922219322194221952219622197221982219922200222012220222203222042220522206222072220822209222102221122212222132221422215222162221722218222192222022221222222222322224222252222622227222282222922230222312223222233222342223522236222372223822239222402224122242222432224422245222462224722248222492225022251222522225322254222552225622257222582225922260222612226222263222642226522266222672226822269222702227122272222732227422275222762227722278222792228022281222822228322284222852228622287222882228922290222912229222293222942229522296222972229822299223002230122302223032230422305223062230722308223092231022311223122231322314223152231622317223182231922320223212232222323223242232522326223272232822329223302233122332223332233422335223362233722338223392234022341223422234322344223452234622347223482234922350223512235222353223542235522356223572235822359223602236122362223632236422365223662236722368223692237022371223722237322374223752237622377223782237922380223812238222383223842238522386223872238822389223902239122392223932239422395223962239722398223992240022401224022240322404224052240622407224082240922410224112241222413224142241522416224172241822419224202242122422224232242422425224262242722428224292243022431224322243322434224352243622437224382243922440224412244222443224442244522446224472244822449224502245122452224532245422455224562245722458224592246022461224622246322464224652246622467224682246922470224712247222473224742247522476224772247822479224802248122482224832248422485224862248722488224892249022491224922249322494224952249622497224982249922500225012250222503225042250522506225072250822509225102251122512225132251422515225162251722518225192252022521225222252322524225252252622527225282252922530225312253222533225342253522536225372253822539225402254122542225432254422545225462254722548225492255022551225522255322554225552255622557225582255922560225612256222563225642256522566225672256822569225702257122572225732257422575225762257722578225792258022581225822258322584225852258622587225882258922590225912259222593225942259522596225972259822599226002260122602226032260422605226062260722608226092261022611226122261322614226152261622617226182261922620226212262222623226242262522626226272262822629226302263122632226332263422635226362263722638226392264022641226422264322644226452264622647226482264922650226512265222653226542265522656226572265822659226602266122662226632266422665226662266722668226692267022671226722267322674226752267622677226782267922680226812268222683226842268522686226872268822689226902269122692226932269422695226962269722698226992270022701227022270322704227052270622707227082270922710227112271222713227142271522716227172271822719227202272122722227232272422725227262272722728227292273022731227322273322734227352273622737227382273922740227412274222743227442274522746227472274822749227502275122752227532275422755227562275722758227592276022761227622276322764227652276622767227682276922770227712277222773227742277522776227772277822779227802278122782227832278422785227862278722788227892279022791227922279322794227952279622797227982279922800228012280222803228042280522806228072280822809228102281122812228132281422815228162281722818228192282022821228222282322824228252282622827228282282922830228312283222833228342283522836228372283822839228402284122842228432284422845228462284722848228492285022851228522285322854228552285622857228582285922860228612286222863228642286522866228672286822869228702287122872228732287422875228762287722878228792288022881228822288322884228852288622887228882288922890228912289222893228942289522896228972289822899229002290122902229032290422905229062290722908229092291022911229122291322914229152291622917229182291922920229212292222923229242292522926229272292822929229302293122932229332293422935229362293722938229392294022941229422294322944229452294622947229482294922950229512295222953229542295522956229572295822959229602296122962229632296422965229662296722968229692297022971229722297322974229752297622977229782297922980229812298222983229842298522986229872298822989229902299122992229932299422995229962299722998229992300023001230022300323004230052300623007230082300923010230112301223013230142301523016230172301823019230202302123022230232302423025230262302723028230292303023031230322303323034230352303623037230382303923040230412304223043230442304523046230472304823049230502305123052230532305423055230562305723058230592306023061230622306323064230652306623067230682306923070230712307223073230742307523076230772307823079230802308123082230832308423085230862308723088230892309023091230922309323094230952309623097230982309923100231012310223103231042310523106231072310823109231102311123112231132311423115231162311723118231192312023121231222312323124231252312623127231282312923130231312313223133231342313523136231372313823139231402314123142231432314423145231462314723148231492315023151231522315323154231552315623157231582315923160231612316223163231642316523166231672316823169231702317123172231732317423175231762317723178231792318023181231822318323184231852318623187231882318923190231912319223193231942319523196231972319823199232002320123202232032320423205232062320723208232092321023211232122321323214232152321623217232182321923220232212322223223232242322523226232272322823229232302323123232232332323423235232362323723238232392324023241232422324323244232452324623247232482324923250232512325223253232542325523256232572325823259232602326123262232632326423265232662326723268232692327023271232722327323274232752327623277232782327923280232812328223283232842328523286232872328823289232902329123292232932329423295232962329723298232992330023301233022330323304233052330623307233082330923310233112331223313233142331523316233172331823319233202332123322233232332423325233262332723328233292333023331233322333323334233352333623337233382333923340233412334223343233442334523346233472334823349233502335123352233532335423355233562335723358233592336023361233622336323364233652336623367233682336923370233712337223373233742337523376233772337823379233802338123382233832338423385233862338723388233892339023391233922339323394233952339623397233982339923400234012340223403234042340523406234072340823409234102341123412234132341423415234162341723418234192342023421234222342323424234252342623427234282342923430234312343223433234342343523436234372343823439234402344123442234432344423445234462344723448234492345023451234522345323454234552345623457234582345923460234612346223463234642346523466234672346823469234702347123472234732347423475234762347723478234792348023481234822348323484234852348623487234882348923490234912349223493234942349523496234972349823499235002350123502235032350423505235062350723508235092351023511235122351323514235152351623517235182351923520235212352223523235242352523526235272352823529235302353123532235332353423535235362353723538235392354023541235422354323544235452354623547235482354923550235512355223553235542355523556235572355823559235602356123562235632356423565235662356723568235692357023571235722357323574235752357623577235782357923580235812358223583235842358523586235872358823589235902359123592235932359423595235962359723598235992360023601236022360323604236052360623607236082360923610236112361223613236142361523616236172361823619236202362123622236232362423625236262362723628236292363023631236322363323634236352363623637236382363923640236412364223643236442364523646236472364823649236502365123652236532365423655236562365723658236592366023661236622366323664236652366623667236682366923670236712367223673236742367523676236772367823679236802368123682236832368423685236862368723688236892369023691236922369323694236952369623697236982369923700237012370223703237042370523706237072370823709237102371123712237132371423715237162371723718237192372023721237222372323724237252372623727237282372923730237312373223733237342373523736237372373823739237402374123742237432374423745237462374723748237492375023751237522375323754237552375623757237582375923760237612376223763237642376523766237672376823769237702377123772237732377423775237762377723778237792378023781237822378323784237852378623787237882378923790237912379223793237942379523796237972379823799238002380123802238032380423805238062380723808238092381023811238122381323814238152381623817238182381923820238212382223823238242382523826238272382823829238302383123832238332383423835238362383723838238392384023841238422384323844238452384623847238482384923850238512385223853238542385523856238572385823859238602386123862238632386423865238662386723868238692387023871238722387323874238752387623877238782387923880238812388223883238842388523886238872388823889238902389123892238932389423895238962389723898238992390023901239022390323904239052390623907239082390923910239112391223913239142391523916239172391823919239202392123922239232392423925239262392723928239292393023931239322393323934239352393623937239382393923940239412394223943239442394523946239472394823949239502395123952239532395423955239562395723958239592396023961239622396323964239652396623967239682396923970239712397223973239742397523976239772397823979239802398123982239832398423985239862398723988239892399023991239922399323994239952399623997239982399924000240012400224003240042400524006240072400824009240102401124012240132401424015240162401724018240192402024021240222402324024240252402624027240282402924030240312403224033240342403524036240372403824039240402404124042240432404424045240462404724048240492405024051240522405324054240552405624057240582405924060240612406224063240642406524066240672406824069240702407124072240732407424075240762407724078240792408024081240822408324084240852408624087240882408924090240912409224093240942409524096240972409824099241002410124102241032410424105241062410724108241092411024111241122411324114241152411624117241182411924120241212412224123241242412524126241272412824129241302413124132241332413424135241362413724138241392414024141241422414324144241452414624147241482414924150241512415224153241542415524156241572415824159241602416124162241632416424165241662416724168241692417024171241722417324174241752417624177241782417924180241812418224183241842418524186241872418824189241902419124192241932419424195241962419724198241992420024201242022420324204242052420624207242082420924210242112421224213242142421524216242172421824219242202422124222242232422424225242262422724228242292423024231242322423324234242352423624237242382423924240242412424224243242442424524246242472424824249242502425124252242532425424255242562425724258242592426024261242622426324264242652426624267242682426924270242712427224273242742427524276242772427824279242802428124282242832428424285242862428724288242892429024291242922429324294242952429624297242982429924300243012430224303243042430524306243072430824309243102431124312243132431424315243162431724318243192432024321243222432324324243252432624327243282432924330243312433224333243342433524336243372433824339243402434124342243432434424345243462434724348243492435024351243522435324354243552435624357243582435924360243612436224363243642436524366243672436824369243702437124372243732437424375243762437724378243792438024381243822438324384243852438624387243882438924390243912439224393243942439524396243972439824399244002440124402244032440424405244062440724408244092441024411244122441324414244152441624417244182441924420244212442224423244242442524426244272442824429244302443124432244332443424435244362443724438244392444024441244422444324444244452444624447244482444924450244512445224453244542445524456244572445824459244602446124462244632446424465244662446724468244692447024471244722447324474244752447624477244782447924480244812448224483244842448524486244872448824489244902449124492244932449424495244962449724498244992450024501245022450324504245052450624507245082450924510245112451224513245142451524516245172451824519245202452124522245232452424525245262452724528245292453024531245322453324534245352453624537245382453924540245412454224543245442454524546245472454824549245502455124552245532455424555245562455724558245592456024561245622456324564245652456624567245682456924570245712457224573245742457524576245772457824579245802458124582245832458424585245862458724588245892459024591245922459324594245952459624597245982459924600246012460224603246042460524606246072460824609246102461124612246132461424615246162461724618246192462024621246222462324624246252462624627246282462924630246312463224633246342463524636246372463824639246402464124642246432464424645246462464724648246492465024651246522465324654246552465624657246582465924660246612466224663246642466524666246672466824669246702467124672246732467424675246762467724678246792468024681246822468324684246852468624687246882468924690246912469224693246942469524696246972469824699247002470124702247032470424705247062470724708247092471024711247122471324714247152471624717247182471924720247212472224723247242472524726247272472824729247302473124732247332473424735247362473724738247392474024741247422474324744247452474624747247482474924750247512475224753247542475524756247572475824759247602476124762247632476424765247662476724768247692477024771247722477324774247752477624777247782477924780247812478224783247842478524786247872478824789247902479124792247932479424795247962479724798247992480024801248022480324804248052480624807248082480924810248112481224813248142481524816248172481824819248202482124822248232482424825248262482724828248292483024831248322483324834248352483624837248382483924840248412484224843248442484524846248472484824849248502485124852248532485424855248562485724858248592486024861248622486324864248652486624867248682486924870248712487224873248742487524876248772487824879248802488124882248832488424885248862488724888248892489024891248922489324894248952489624897248982489924900249012490224903249042490524906249072490824909249102491124912249132491424915249162491724918249192492024921249222492324924249252492624927249282492924930249312493224933249342493524936249372493824939249402494124942249432494424945249462494724948249492495024951249522495324954249552495624957249582495924960249612496224963249642496524966249672496824969249702497124972249732497424975249762497724978249792498024981249822498324984249852498624987249882498924990249912499224993249942499524996249972499824999250002500125002250032500425005250062500725008250092501025011250122501325014250152501625017250182501925020250212502225023250242502525026250272502825029250302503125032250332503425035250362503725038250392504025041250422504325044250452504625047250482504925050250512505225053250542505525056250572505825059250602506125062250632506425065250662506725068250692507025071250722507325074250752507625077250782507925080250812508225083250842508525086250872508825089250902509125092250932509425095250962509725098250992510025101251022510325104251052510625107251082510925110251112511225113251142511525116251172511825119251202512125122251232512425125251262512725128251292513025131251322513325134251352513625137251382513925140251412514225143251442514525146251472514825149251502515125152251532515425155251562515725158251592516025161251622516325164251652516625167251682516925170251712517225173251742517525176251772517825179251802518125182251832518425185251862518725188251892519025191251922519325194251952519625197251982519925200252012520225203252042520525206252072520825209252102521125212252132521425215252162521725218252192522025221252222522325224252252522625227252282522925230252312523225233252342523525236252372523825239252402524125242252432524425245252462524725248252492525025251252522525325254252552525625257252582525925260252612526225263252642526525266252672526825269252702527125272252732527425275252762527725278252792528025281252822528325284252852528625287252882528925290252912529225293252942529525296252972529825299253002530125302253032530425305253062530725308253092531025311253122531325314253152531625317253182531925320253212532225323253242532525326253272532825329253302533125332253332533425335253362533725338253392534025341253422534325344253452534625347253482534925350253512535225353253542535525356253572535825359253602536125362253632536425365253662536725368253692537025371253722537325374253752537625377253782537925380253812538225383253842538525386253872538825389253902539125392253932539425395253962539725398253992540025401254022540325404254052540625407254082540925410254112541225413254142541525416254172541825419254202542125422254232542425425254262542725428254292543025431254322543325434254352543625437254382543925440254412544225443254442544525446254472544825449254502545125452254532545425455254562545725458254592546025461254622546325464254652546625467254682546925470254712547225473254742547525476254772547825479254802548125482254832548425485254862548725488254892549025491254922549325494254952549625497254982549925500255012550225503255042550525506255072550825509255102551125512255132551425515255162551725518255192552025521255222552325524255252552625527255282552925530255312553225533255342553525536255372553825539255402554125542255432554425545255462554725548255492555025551255522555325554255552555625557255582555925560255612556225563255642556525566255672556825569255702557125572255732557425575255762557725578255792558025581255822558325584255852558625587255882558925590255912559225593255942559525596255972559825599256002560125602256032560425605256062560725608256092561025611256122561325614256152561625617256182561925620256212562225623256242562525626256272562825629256302563125632256332563425635256362563725638256392564025641256422564325644256452564625647256482564925650256512565225653256542565525656256572565825659256602566125662256632566425665256662566725668256692567025671256722567325674256752567625677256782567925680256812568225683256842568525686256872568825689256902569125692256932569425695256962569725698256992570025701257022570325704257052570625707257082570925710257112571225713257142571525716257172571825719257202572125722257232572425725257262572725728257292573025731257322573325734257352573625737257382573925740257412574225743257442574525746257472574825749257502575125752257532575425755257562575725758257592576025761257622576325764257652576625767257682576925770257712577225773257742577525776257772577825779257802578125782257832578425785257862578725788257892579025791257922579325794257952579625797257982579925800258012580225803258042580525806258072580825809258102581125812258132581425815258162581725818258192582025821258222582325824258252582625827258282582925830258312583225833258342583525836258372583825839258402584125842258432584425845258462584725848258492585025851258522585325854258552585625857258582585925860258612586225863258642586525866258672586825869258702587125872258732587425875258762587725878258792588025881258822588325884258852588625887258882588925890258912589225893258942589525896258972589825899259002590125902259032590425905259062590725908259092591025911259122591325914259152591625917259182591925920259212592225923259242592525926259272592825929259302593125932259332593425935259362593725938259392594025941259422594325944259452594625947259482594925950259512595225953259542595525956259572595825959259602596125962259632596425965259662596725968259692597025971259722597325974259752597625977259782597925980259812598225983259842598525986259872598825989259902599125992259932599425995259962599725998259992600026001260022600326004260052600626007260082600926010260112601226013260142601526016260172601826019260202602126022260232602426025260262602726028260292603026031260322603326034260352603626037260382603926040260412604226043260442604526046260472604826049260502605126052260532605426055260562605726058260592606026061260622606326064260652606626067260682606926070260712607226073260742607526076260772607826079260802608126082260832608426085260862608726088260892609026091260922609326094260952609626097260982609926100261012610226103261042610526106261072610826109261102611126112261132611426115261162611726118261192612026121261222612326124261252612626127261282612926130261312613226133261342613526136261372613826139261402614126142261432614426145261462614726148261492615026151261522615326154261552615626157261582615926160261612616226163261642616526166261672616826169261702617126172261732617426175261762617726178261792618026181261822618326184261852618626187261882618926190261912619226193261942619526196261972619826199262002620126202262032620426205262062620726208262092621026211262122621326214262152621626217262182621926220262212622226223262242622526226262272622826229262302623126232262332623426235262362623726238262392624026241262422624326244262452624626247262482624926250262512625226253262542625526256262572625826259262602626126262262632626426265262662626726268262692627026271262722627326274262752627626277262782627926280262812628226283262842628526286262872628826289262902629126292262932629426295262962629726298262992630026301263022630326304263052630626307263082630926310263112631226313263142631526316263172631826319263202632126322263232632426325263262632726328263292633026331263322633326334263352633626337263382633926340263412634226343263442634526346263472634826349263502635126352263532635426355263562635726358263592636026361263622636326364263652636626367263682636926370263712637226373263742637526376263772637826379263802638126382263832638426385263862638726388263892639026391263922639326394263952639626397263982639926400264012640226403264042640526406264072640826409264102641126412264132641426415264162641726418264192642026421264222642326424264252642626427264282642926430264312643226433264342643526436264372643826439264402644126442264432644426445264462644726448264492645026451264522645326454264552645626457264582645926460264612646226463264642646526466264672646826469264702647126472264732647426475264762647726478264792648026481264822648326484264852648626487264882648926490264912649226493264942649526496264972649826499265002650126502265032650426505265062650726508265092651026511265122651326514265152651626517265182651926520265212652226523265242652526526265272652826529265302653126532265332653426535265362653726538265392654026541265422654326544265452654626547265482654926550265512655226553265542655526556265572655826559265602656126562265632656426565265662656726568265692657026571265722657326574265752657626577265782657926580265812658226583265842658526586265872658826589265902659126592265932659426595265962659726598265992660026601266022660326604266052660626607266082660926610266112661226613266142661526616266172661826619266202662126622266232662426625266262662726628266292663026631266322663326634266352663626637266382663926640266412664226643266442664526646266472664826649266502665126652266532665426655266562665726658266592666026661266622666326664266652666626667266682666926670266712667226673266742667526676266772667826679266802668126682266832668426685266862668726688266892669026691266922669326694266952669626697266982669926700267012670226703267042670526706267072670826709267102671126712267132671426715267162671726718267192672026721267222672326724267252672626727267282672926730267312673226733267342673526736267372673826739267402674126742267432674426745267462674726748267492675026751267522675326754267552675626757267582675926760267612676226763267642676526766267672676826769267702677126772267732677426775267762677726778267792678026781267822678326784267852678626787267882678926790267912679226793267942679526796267972679826799268002680126802268032680426805268062680726808268092681026811268122681326814268152681626817268182681926820268212682226823268242682526826268272682826829268302683126832268332683426835268362683726838268392684026841268422684326844268452684626847268482684926850268512685226853268542685526856268572685826859268602686126862268632686426865268662686726868268692687026871268722687326874268752687626877268782687926880268812688226883268842688526886268872688826889268902689126892268932689426895268962689726898268992690026901269022690326904269052690626907269082690926910269112691226913269142691526916269172691826919269202692126922269232692426925269262692726928269292693026931269322693326934269352693626937269382693926940269412694226943269442694526946269472694826949269502695126952269532695426955269562695726958269592696026961269622696326964269652696626967269682696926970269712697226973269742697526976269772697826979269802698126982269832698426985269862698726988269892699026991269922699326994269952699626997269982699927000270012700227003270042700527006270072700827009270102701127012270132701427015270162701727018270192702027021270222702327024270252702627027270282702927030270312703227033270342703527036270372703827039270402704127042270432704427045270462704727048270492705027051270522705327054270552705627057270582705927060270612706227063270642706527066270672706827069270702707127072270732707427075270762707727078270792708027081270822708327084270852708627087270882708927090270912709227093270942709527096270972709827099271002710127102271032710427105271062710727108271092711027111271122711327114271152711627117271182711927120271212712227123271242712527126271272712827129271302713127132271332713427135271362713727138271392714027141271422714327144271452714627147271482714927150271512715227153271542715527156271572715827159271602716127162271632716427165271662716727168271692717027171271722717327174271752717627177271782717927180271812718227183271842718527186271872718827189271902719127192271932719427195271962719727198271992720027201272022720327204272052720627207272082720927210272112721227213272142721527216272172721827219272202722127222272232722427225272262722727228272292723027231272322723327234272352723627237272382723927240272412724227243272442724527246272472724827249272502725127252272532725427255272562725727258272592726027261272622726327264272652726627267272682726927270272712727227273272742727527276272772727827279272802728127282272832728427285272862728727288272892729027291272922729327294272952729627297272982729927300273012730227303273042730527306273072730827309273102731127312273132731427315273162731727318273192732027321273222732327324273252732627327273282732927330273312733227333273342733527336273372733827339273402734127342273432734427345273462734727348273492735027351273522735327354273552735627357273582735927360273612736227363273642736527366273672736827369273702737127372273732737427375273762737727378273792738027381273822738327384273852738627387273882738927390273912739227393273942739527396273972739827399274002740127402274032740427405274062740727408274092741027411274122741327414274152741627417274182741927420274212742227423274242742527426274272742827429274302743127432274332743427435274362743727438274392744027441274422744327444274452744627447274482744927450274512745227453274542745527456274572745827459274602746127462274632746427465274662746727468274692747027471274722747327474274752747627477274782747927480274812748227483274842748527486274872748827489274902749127492274932749427495274962749727498274992750027501275022750327504275052750627507275082750927510275112751227513275142751527516275172751827519275202752127522275232752427525275262752727528275292753027531275322753327534275352753627537275382753927540275412754227543275442754527546275472754827549275502755127552275532755427555275562755727558275592756027561275622756327564275652756627567275682756927570275712757227573275742757527576275772757827579275802758127582275832758427585275862758727588275892759027591275922759327594275952759627597275982759927600276012760227603276042760527606276072760827609276102761127612276132761427615276162761727618276192762027621276222762327624276252762627627276282762927630276312763227633276342763527636276372763827639276402764127642276432764427645276462764727648276492765027651276522765327654276552765627657276582765927660276612766227663276642766527666276672766827669276702767127672276732767427675276762767727678276792768027681276822768327684276852768627687276882768927690276912769227693276942769527696276972769827699277002770127702277032770427705277062770727708277092771027711277122771327714277152771627717277182771927720277212772227723277242772527726277272772827729277302773127732277332773427735277362773727738277392774027741277422774327744277452774627747277482774927750277512775227753277542775527756277572775827759277602776127762277632776427765277662776727768277692777027771277722777327774277752777627777277782777927780277812778227783277842778527786277872778827789277902779127792277932779427795277962779727798277992780027801278022780327804278052780627807278082780927810278112781227813278142781527816278172781827819278202782127822278232782427825278262782727828278292783027831278322783327834278352783627837278382783927840278412784227843278442784527846278472784827849278502785127852278532785427855278562785727858278592786027861278622786327864278652786627867278682786927870278712787227873278742787527876278772787827879278802788127882278832788427885278862788727888278892789027891278922789327894278952789627897278982789927900279012790227903279042790527906279072790827909279102791127912279132791427915279162791727918279192792027921279222792327924279252792627927279282792927930279312793227933279342793527936279372793827939279402794127942279432794427945279462794727948279492795027951279522795327954279552795627957279582795927960279612796227963279642796527966279672796827969279702797127972279732797427975279762797727978279792798027981279822798327984279852798627987279882798927990279912799227993279942799527996279972799827999280002800128002280032800428005280062800728008280092801028011280122801328014280152801628017280182801928020280212802228023280242802528026280272802828029280302803128032280332803428035280362803728038280392804028041280422804328044280452804628047280482804928050280512805228053280542805528056280572805828059280602806128062280632806428065280662806728068280692807028071280722807328074280752807628077280782807928080280812808228083280842808528086280872808828089280902809128092280932809428095280962809728098280992810028101281022810328104281052810628107281082810928110281112811228113281142811528116281172811828119281202812128122281232812428125281262812728128281292813028131281322813328134281352813628137281382813928140281412814228143281442814528146281472814828149281502815128152281532815428155281562815728158281592816028161281622816328164281652816628167281682816928170281712817228173281742817528176281772817828179281802818128182281832818428185281862818728188281892819028191281922819328194281952819628197281982819928200282012820228203282042820528206282072820828209282102821128212282132821428215282162821728218282192822028221282222822328224282252822628227282282822928230282312823228233282342823528236282372823828239282402824128242282432824428245282462824728248282492825028251282522825328254282552825628257282582825928260282612826228263282642826528266282672826828269282702827128272282732827428275282762827728278282792828028281282822828328284282852828628287282882828928290282912829228293282942829528296282972829828299283002830128302283032830428305283062830728308283092831028311283122831328314283152831628317283182831928320283212832228323283242832528326283272832828329283302833128332283332833428335283362833728338283392834028341283422834328344283452834628347283482834928350283512835228353283542835528356283572835828359283602836128362283632836428365283662836728368283692837028371283722837328374283752837628377283782837928380283812838228383283842838528386283872838828389283902839128392283932839428395283962839728398283992840028401284022840328404284052840628407284082840928410284112841228413284142841528416284172841828419284202842128422284232842428425284262842728428284292843028431284322843328434284352843628437284382843928440284412844228443284442844528446284472844828449284502845128452284532845428455284562845728458284592846028461284622846328464284652846628467284682846928470284712847228473284742847528476284772847828479284802848128482284832848428485284862848728488284892849028491284922849328494284952849628497284982849928500285012850228503285042850528506285072850828509285102851128512285132851428515285162851728518285192852028521285222852328524285252852628527285282852928530285312853228533285342853528536285372853828539285402854128542285432854428545285462854728548285492855028551285522855328554285552855628557285582855928560285612856228563285642856528566285672856828569285702857128572285732857428575285762857728578285792858028581285822858328584285852858628587285882858928590285912859228593285942859528596285972859828599286002860128602286032860428605286062860728608286092861028611286122861328614286152861628617286182861928620286212862228623286242862528626286272862828629286302863128632286332863428635286362863728638286392864028641286422864328644286452864628647286482864928650286512865228653286542865528656286572865828659286602866128662286632866428665286662866728668286692867028671286722867328674286752867628677286782867928680286812868228683286842868528686286872868828689286902869128692286932869428695286962869728698286992870028701287022870328704287052870628707287082870928710287112871228713287142871528716287172871828719287202872128722287232872428725287262872728728287292873028731287322873328734287352873628737287382873928740287412874228743287442874528746287472874828749287502875128752287532875428755287562875728758287592876028761287622876328764287652876628767287682876928770287712877228773287742877528776287772877828779287802878128782287832878428785287862878728788287892879028791287922879328794287952879628797287982879928800288012880228803288042880528806288072880828809288102881128812288132881428815288162881728818288192882028821288222882328824288252882628827288282882928830288312883228833288342883528836288372883828839288402884128842288432884428845288462884728848288492885028851288522885328854288552885628857288582885928860288612886228863288642886528866288672886828869288702887128872288732887428875288762887728878288792888028881288822888328884288852888628887288882888928890288912889228893288942889528896288972889828899289002890128902289032890428905289062890728908289092891028911289122891328914289152891628917289182891928920289212892228923289242892528926289272892828929289302893128932289332893428935289362893728938289392894028941289422894328944289452894628947289482894928950289512895228953289542895528956289572895828959289602896128962289632896428965289662896728968289692897028971289722897328974289752897628977289782897928980289812898228983289842898528986289872898828989289902899128992289932899428995289962899728998289992900029001290022900329004290052900629007290082900929010290112901229013290142901529016290172901829019290202902129022290232902429025290262902729028290292903029031290322903329034290352903629037290382903929040290412904229043290442904529046290472904829049290502905129052290532905429055290562905729058290592906029061290622906329064290652906629067290682906929070290712907229073290742907529076290772907829079290802908129082290832908429085290862908729088290892909029091290922909329094290952909629097290982909929100291012910229103291042910529106291072910829109291102911129112291132911429115291162911729118291192912029121291222912329124291252912629127291282912929130291312913229133291342913529136291372913829139291402914129142291432914429145291462914729148291492915029151291522915329154291552915629157291582915929160291612916229163291642916529166291672916829169291702917129172291732917429175291762917729178291792918029181291822918329184291852918629187291882918929190291912919229193291942919529196291972919829199292002920129202292032920429205292062920729208292092921029211292122921329214292152921629217292182921929220292212922229223292242922529226292272922829229292302923129232292332923429235292362923729238292392924029241292422924329244292452924629247292482924929250292512925229253292542925529256292572925829259292602926129262292632926429265292662926729268292692927029271292722927329274292752927629277292782927929280292812928229283292842928529286292872928829289292902929129292292932929429295292962929729298292992930029301293022930329304293052930629307293082930929310293112931229313293142931529316293172931829319293202932129322293232932429325293262932729328293292933029331293322933329334293352933629337293382933929340293412934229343293442934529346293472934829349293502935129352293532935429355293562935729358293592936029361293622936329364293652936629367293682936929370293712937229373293742937529376293772937829379293802938129382293832938429385293862938729388293892939029391293922939329394293952939629397293982939929400294012940229403294042940529406294072940829409294102941129412294132941429415294162941729418294192942029421294222942329424294252942629427294282942929430294312943229433294342943529436294372943829439294402944129442294432944429445294462944729448294492945029451294522945329454294552945629457294582945929460294612946229463294642946529466294672946829469294702947129472294732947429475294762947729478294792948029481294822948329484294852948629487294882948929490294912949229493294942949529496294972949829499295002950129502295032950429505295062950729508295092951029511295122951329514295152951629517295182951929520295212952229523295242952529526295272952829529295302953129532295332953429535295362953729538295392954029541295422954329544295452954629547295482954929550295512955229553295542955529556295572955829559295602956129562295632956429565295662956729568295692957029571295722957329574295752957629577295782957929580295812958229583295842958529586295872958829589295902959129592295932959429595295962959729598295992960029601296022960329604296052960629607296082960929610296112961229613296142961529616296172961829619296202962129622296232962429625296262962729628296292963029631296322963329634296352963629637296382963929640296412964229643296442964529646296472964829649296502965129652296532965429655296562965729658296592966029661296622966329664296652966629667296682966929670296712967229673296742967529676296772967829679296802968129682296832968429685296862968729688296892969029691296922969329694296952969629697296982969929700297012970229703297042970529706297072970829709297102971129712297132971429715297162971729718297192972029721297222972329724297252972629727297282972929730297312973229733297342973529736297372973829739297402974129742297432974429745297462974729748297492975029751297522975329754297552975629757297582975929760297612976229763297642976529766297672976829769297702977129772297732977429775297762977729778297792978029781297822978329784297852978629787297882978929790297912979229793297942979529796297972979829799298002980129802298032980429805298062980729808298092981029811298122981329814298152981629817298182981929820298212982229823298242982529826298272982829829298302983129832298332983429835298362983729838298392984029841298422984329844298452984629847298482984929850298512985229853298542985529856298572985829859298602986129862298632986429865298662986729868298692987029871298722987329874298752987629877298782987929880298812988229883298842988529886298872988829889298902989129892298932989429895298962989729898298992990029901299022990329904299052990629907299082990929910299112991229913299142991529916299172991829919299202992129922299232992429925299262992729928299292993029931299322993329934299352993629937299382993929940299412994229943299442994529946299472994829949299502995129952299532995429955299562995729958299592996029961299622996329964299652996629967299682996929970299712997229973299742997529976299772997829979299802998129982299832998429985299862998729988299892999029991299922999329994299952999629997299982999930000300013000230003300043000530006300073000830009300103001130012300133001430015300163001730018300193002030021300223002330024300253002630027300283002930030300313003230033300343003530036300373003830039300403004130042300433004430045300463004730048300493005030051300523005330054300553005630057300583005930060300613006230063300643006530066300673006830069300703007130072300733007430075300763007730078300793008030081300823008330084300853008630087300883008930090300913009230093300943009530096300973009830099301003010130102301033010430105301063010730108301093011030111301123011330114301153011630117301183011930120301213012230123301243012530126301273012830129301303013130132301333013430135301363013730138301393014030141301423014330144301453014630147301483014930150301513015230153301543015530156301573015830159301603016130162301633016430165301663016730168301693017030171301723017330174301753017630177301783017930180301813018230183301843018530186301873018830189301903019130192301933019430195301963019730198301993020030201302023020330204302053020630207302083020930210302113021230213302143021530216302173021830219302203022130222302233022430225302263022730228302293023030231302323023330234302353023630237302383023930240302413024230243302443024530246302473024830249302503025130252302533025430255302563025730258302593026030261302623026330264302653026630267302683026930270302713027230273302743027530276302773027830279302803028130282302833028430285302863028730288302893029030291302923029330294302953029630297302983029930300303013030230303303043030530306303073030830309303103031130312303133031430315303163031730318303193032030321303223032330324303253032630327303283032930330303313033230333303343033530336303373033830339303403034130342303433034430345303463034730348303493035030351303523035330354303553035630357303583035930360303613036230363303643036530366303673036830369303703037130372303733037430375303763037730378303793038030381303823038330384303853038630387303883038930390303913039230393303943039530396303973039830399304003040130402304033040430405304063040730408304093041030411304123041330414304153041630417304183041930420304213042230423304243042530426304273042830429304303043130432304333043430435304363043730438304393044030441304423044330444304453044630447304483044930450304513045230453304543045530456304573045830459304603046130462304633046430465304663046730468304693047030471304723047330474304753047630477304783047930480304813048230483304843048530486304873048830489304903049130492304933049430495304963049730498304993050030501305023050330504305053050630507305083050930510305113051230513305143051530516305173051830519305203052130522305233052430525305263052730528305293053030531305323053330534305353053630537305383053930540305413054230543305443054530546305473054830549305503055130552305533055430555305563055730558305593056030561305623056330564305653056630567305683056930570305713057230573305743057530576305773057830579305803058130582305833058430585305863058730588305893059030591305923059330594305953059630597305983059930600306013060230603306043060530606306073060830609306103061130612306133061430615306163061730618306193062030621306223062330624306253062630627306283062930630306313063230633306343063530636306373063830639306403064130642306433064430645306463064730648306493065030651306523065330654306553065630657306583065930660306613066230663306643066530666306673066830669306703067130672306733067430675306763067730678306793068030681306823068330684306853068630687306883068930690306913069230693306943069530696306973069830699307003070130702307033070430705307063070730708307093071030711307123071330714307153071630717307183071930720307213072230723307243072530726307273072830729307303073130732307333073430735307363073730738307393074030741307423074330744307453074630747307483074930750307513075230753307543075530756307573075830759307603076130762307633076430765307663076730768307693077030771307723077330774307753077630777307783077930780307813078230783307843078530786307873078830789307903079130792307933079430795307963079730798307993080030801308023080330804308053080630807308083080930810308113081230813308143081530816308173081830819308203082130822308233082430825308263082730828308293083030831308323083330834308353083630837308383083930840308413084230843308443084530846308473084830849308503085130852308533085430855308563085730858308593086030861308623086330864308653086630867308683086930870308713087230873308743087530876308773087830879308803088130882308833088430885308863088730888308893089030891308923089330894308953089630897308983089930900309013090230903309043090530906309073090830909309103091130912309133091430915309163091730918309193092030921309223092330924309253092630927309283092930930309313093230933309343093530936309373093830939309403094130942309433094430945309463094730948309493095030951309523095330954309553095630957309583095930960309613096230963309643096530966309673096830969309703097130972309733097430975309763097730978309793098030981309823098330984309853098630987309883098930990309913099230993309943099530996309973099830999310003100131002310033100431005310063100731008310093101031011310123101331014310153101631017310183101931020310213102231023310243102531026310273102831029310303103131032310333103431035310363103731038310393104031041310423104331044310453104631047310483104931050310513105231053310543105531056310573105831059310603106131062310633106431065310663106731068310693107031071310723107331074310753107631077310783107931080310813108231083310843108531086310873108831089310903109131092310933109431095310963109731098310993110031101311023110331104311053110631107311083110931110311113111231113311143111531116311173111831119311203112131122311233112431125311263112731128311293113031131311323113331134311353113631137311383113931140311413114231143311443114531146311473114831149311503115131152311533115431155311563115731158311593116031161311623116331164311653116631167311683116931170311713117231173311743117531176311773117831179311803118131182311833118431185311863118731188311893119031191311923119331194311953119631197311983119931200312013120231203312043120531206312073120831209312103121131212312133121431215312163121731218312193122031221312223122331224312253122631227312283122931230312313123231233312343123531236312373123831239312403124131242312433124431245312463124731248312493125031251312523125331254312553125631257312583125931260312613126231263312643126531266312673126831269312703127131272312733127431275312763127731278312793128031281312823128331284312853128631287312883128931290312913129231293312943129531296312973129831299313003130131302313033130431305313063130731308313093131031311313123131331314313153131631317313183131931320313213132231323313243132531326313273132831329313303133131332313333133431335313363133731338313393134031341313423134331344313453134631347313483134931350313513135231353313543135531356313573135831359313603136131362313633136431365313663136731368313693137031371313723137331374313753137631377313783137931380313813138231383313843138531386313873138831389313903139131392313933139431395313963139731398313993140031401314023140331404314053140631407314083140931410314113141231413314143141531416314173141831419314203142131422314233142431425314263142731428314293143031431314323143331434314353143631437314383143931440314413144231443314443144531446314473144831449314503145131452314533145431455314563145731458314593146031461314623146331464314653146631467314683146931470314713147231473314743147531476314773147831479314803148131482314833148431485314863148731488314893149031491314923149331494314953149631497314983149931500315013150231503315043150531506315073150831509315103151131512315133151431515315163151731518315193152031521315223152331524315253152631527315283152931530315313153231533315343153531536315373153831539315403154131542315433154431545315463154731548315493155031551315523155331554315553155631557315583155931560315613156231563315643156531566315673156831569315703157131572315733157431575315763157731578315793158031581315823158331584315853158631587315883158931590315913159231593315943159531596315973159831599316003160131602316033160431605316063160731608316093161031611316123161331614316153161631617316183161931620316213162231623316243162531626316273162831629316303163131632316333163431635316363163731638316393164031641316423164331644316453164631647316483164931650316513165231653316543165531656316573165831659316603166131662316633166431665316663166731668316693167031671316723167331674316753167631677316783167931680316813168231683316843168531686316873168831689316903169131692316933169431695316963169731698316993170031701317023170331704317053170631707317083170931710317113171231713317143171531716317173171831719317203172131722317233172431725317263172731728317293173031731317323173331734317353173631737317383173931740 |
- <?xml version="1.0" encoding="iso-8859-1" standalone="no"?>
- <!-- Generated by the JDiff Javadoc doclet -->
- <!-- (http://www.jdiff.org) -->
- <!-- on Sun Dec 04 01:04:32 UTC 2011 -->
- <api
- xmlns:xsi='http://www.w3.org/2001/XMLSchema-instance'
- xsi:noNamespaceSchemaLocation='api.xsd'
- name="hadoop-mapred 0.22.0"
- jdversion="1.0.9">
- <!-- Command line arguments = -doclet org.apache.hadoop.classification.tools.ExcludePrivateAnnotationsJDiffDoclet -docletpath /x1/jenkins/jenkins-slave/workspace/Hadoop-22-Build/common/mapreduce/build/ivy/lib/Hadoop/common/hadoop-common-0.22.0-SNAPSHOT.jar:/x1/jenkins/jenkins-slave/workspace/Hadoop-22-Build/common/mapreduce/build/ivy/lib/Hadoop/jdiff/jdiff-1.0.9.jar:/x1/jenkins/jenkins-slave/workspace/Hadoop-22-Build/common/mapreduce/build/ivy/lib/Hadoop/jdiff/xerces-1.4.4.jar -classpath /x1/jenkins/jenkins-slave/workspace/Hadoop-22-Build/common/mapreduce/build/classes:/x1/jenkins/jenkins-slave/workspace/Hadoop-22-Build/common/mapreduce/conf:/home/jenkins/.ivy2/cache/org.apache.hadoop/hadoop-common/jars/hadoop-common-0.22.0-SNAPSHOT.jar:/home/jenkins/.ivy2/cache/commons-cli/commons-cli/jars/commons-cli-1.2.jar:/home/jenkins/.ivy2/cache/xmlenc/xmlenc/jars/xmlenc-0.52.jar:/home/jenkins/.ivy2/cache/commons-codec/commons-codec/jars/commons-codec-1.4.jar:/home/jenkins/.ivy2/cache/commons-logging/commons-logging/jars/commons-logging-1.1.1.jar:/home/jenkins/.ivy2/cache/org.slf4j/slf4j-api/jars/slf4j-api-1.6.1.jar:/home/jenkins/.ivy2/cache/org.slf4j/slf4j-log4j12/jars/slf4j-log4j12-1.6.1.jar:/home/jenkins/.ivy2/cache/log4j/log4j/bundles/log4j-1.2.16.jar:/home/jenkins/.ivy2/cache/org.mortbay.jetty/jetty/jars/jetty-6.1.26.jar:/home/jenkins/.ivy2/cache/org.mortbay.jetty/jetty-util/jars/jetty-util-6.1.26.jar:/home/jenkins/.ivy2/cache/org.mortbay.jetty/servlet-api/jars/servlet-api-2.5-20081211.jar:/home/jenkins/.ivy2/cache/tomcat/jasper-runtime/jars/jasper-runtime-5.5.12.jar:/home/jenkins/.ivy2/cache/tomcat/jasper-compiler/jars/jasper-compiler-5.5.12.jar:/home/jenkins/.ivy2/cache/org.mortbay.jetty/jsp-2.1-jetty/jars/jsp-2.1-jetty-6.1.26.jar:/home/jenkins/.ivy2/cache/org.eclipse.jdt/core/jars/core-3.1.1.jar:/home/jenkins/.ivy2/cache/org.mortbay.jetty/jsp-api-2.1-glassfish/jars/jsp-api-2.1-glassfish-2.1.v20091210.jar:/home/jenkins/.ivy2/cache/org.mortbay.jetty/jsp-2.1-glassfish/jars/jsp-2.1-glassfish-2.1.v20091210.jar:/home/jenkins/.ivy2/cache/org.eclipse.jdt.core.compiler/ecj/jars/ecj-3.5.1.jar:/home/jenkins/.ivy2/cache/commons-el/commons-el/jars/commons-el-1.0.jar:/home/jenkins/.ivy2/cache/net.java.dev.jets3t/jets3t/jars/jets3t-0.7.1.jar:/home/jenkins/.ivy2/cache/commons-httpclient/commons-httpclient/jars/commons-httpclient-3.1.jar:/home/jenkins/.ivy2/cache/commons-net/commons-net/jars/commons-net-1.4.1.jar:/home/jenkins/.ivy2/cache/oro/oro/jars/oro-2.0.8.jar:/home/jenkins/.ivy2/cache/net.sf.kosmosfs/kfs/jars/kfs-0.3.jar:/home/jenkins/.ivy2/cache/junit/junit/jars/junit-4.8.1.jar:/home/jenkins/.ivy2/cache/hsqldb/hsqldb/jars/hsqldb-1.8.0.10.jar:/home/jenkins/.ivy2/cache/org.apache.avro/avro/jars/avro-1.5.3.jar:/home/jenkins/.ivy2/cache/org.codehaus.jackson/jackson-mapper-asl/jars/jackson-mapper-asl-1.7.3.jar:/home/jenkins/.ivy2/cache/org.codehaus.jackson/jackson-core-asl/jars/jackson-core-asl-1.7.3.jar:/home/jenkins/.ivy2/cache/com.thoughtworks.paranamer/paranamer/jars/paranamer-2.3.jar:/home/jenkins/.ivy2/cache/org.xerial.snappy/snappy-java/bundles/snappy-java-1.0.3.2.jar:/home/jenkins/.ivy2/cache/org.apache.avro/avro-ipc/jars/avro-ipc-1.5.3.jar:/home/jenkins/.ivy2/cache/org.apache.hadoop/hadoop-common-test/jars/hadoop-common-test-0.22.0-SNAPSHOT.jar:/home/jenkins/.ivy2/cache/org.apache.hadoop/hadoop-hdfs/jars/hadoop-hdfs-0.22.0-SNAPSHOT.jar:/home/jenkins/.ivy2/cache/com.google.guava/guava/jars/guava-r09.jar:/home/jenkins/.ivy2/cache/org.apache.avro/avro-compiler/jars/avro-compiler-1.5.3.jar:/home/jenkins/.ivy2/cache/commons-lang/commons-lang/jars/commons-lang-2.5.jar:/home/jenkins/.ivy2/cache/org.apache.velocity/velocity/jars/velocity-1.6.4.jar:/home/jenkins/.ivy2/cache/commons-collections/commons-collections/jars/commons-collections-3.2.1.jar:/home/jenkins/.ivy2/cache/org.aspectj/aspectjrt/jars/aspectjrt-1.6.5.jar:/home/jenkins/.ivy2/cache/org.aspectj/aspectjtools/jars/aspectjtools-1.6.5.jar:/home/jenkins/.ivy2/cache/jdiff/jdiff/jars/jdiff-1.0.9.jar:/home/jenkins/.ivy2/cache/xerces/xerces/jars/xerces-1.4.4.jar:/home/jenkins/tools/ant/latest/lib/ant-launcher.jar:/usr/share/java/xmlParserAPIs.jar:/usr/share/java/xercesImpl.jar:/home/jenkins/tools/ant/latest/lib/ant-apache-resolver.jar:/home/jenkins/tools/ant/latest/lib/ant-apache-bcel.jar:/home/jenkins/tools/ant/latest/lib/ant-jsch.jar:/home/jenkins/tools/ant/latest/lib/ant-jmf.jar:/home/jenkins/tools/ant/latest/lib/ant-apache-oro.jar:/home/jenkins/tools/ant/latest/lib/ant-netrexx.jar:/home/jenkins/tools/ant/latest/lib/ant-testutil.jar:/home/jenkins/tools/ant/latest/lib/ant-apache-xalan2.jar:/home/jenkins/tools/ant/latest/lib/ant-javamail.jar:/home/jenkins/tools/ant/latest/lib/ant.jar:/home/jenkins/tools/ant/latest/lib/ant-junit.jar:/home/jenkins/tools/ant/latest/lib/ant-swing.jar:/home/jenkins/tools/ant/latest/lib/ant-commons-net.jar:/home/jenkins/tools/ant/latest/lib/ant-jdepend.jar:/home/jenkins/tools/ant/latest/lib/ant-junit4.jar:/home/jenkins/tools/ant/latest/lib/ant-commons-logging.jar:/home/jenkins/tools/ant/latest/lib/ant-apache-bsf.jar:/home/jenkins/tools/ant/latest/lib/ant-apache-log4j.jar:/home/jenkins/tools/ant/latest/lib/ant-jai.jar:/home/jenkins/tools/ant/latest/lib/ant-apache-regexp.jar:/home/jenkins/tools/ant/latest/lib/ant-antlr.jar:/tmp/jdk1.6.0_29/lib/tools.jar -sourcepath /x1/jenkins/jenkins-slave/workspace/Hadoop-22-Build/common/mapreduce/src/java:/x1/jenkins/jenkins-slave/workspace/Hadoop-22-Build/common/mapreduce/src/tools -apidir /x1/jenkins/jenkins-slave/workspace/Hadoop-22-Build/common/mapreduce/lib/jdiff -apiname hadoop-mapred 0.22.0 -->
- <package name="org.apache.hadoop.filecache">
- <!-- start class org.apache.hadoop.filecache.DistributedCache -->
- <class name="DistributedCache" extends="org.apache.hadoop.mapreduce.filecache.DistributedCache"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use methods on {@link Job}.">
- <constructor name="DistributedCache"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <doc>
- <![CDATA[Distribute application-specific large, read-only files efficiently.
-
- <p><code>DistributedCache</code> is a facility provided by the Map-Reduce
- framework to cache files (text, archives, jars etc.) needed by applications.
- </p>
-
- <p>Applications specify the files, via urls (hdfs:// or http://) to be cached
- via the {@link org.apache.hadoop.mapred.JobConf}. The
- <code>DistributedCache</code> assumes that the files specified via urls are
- already present on the {@link FileSystem} at the path specified by the url
- and are accessible by every machine in the cluster.</p>
-
- <p>The framework will copy the necessary files on to the slave node before
- any tasks for the job are executed on that node. Its efficiency stems from
- the fact that the files are only copied once per job and the ability to
- cache archives which are un-archived on the slaves.</p>
- <p><code>DistributedCache</code> can be used to distribute simple, read-only
- data/text files and/or more complex types such as archives, jars etc.
- Archives (zip, tar and tgz/tar.gz files) are un-archived at the slave nodes.
- Jars may be optionally added to the classpath of the tasks, a rudimentary
- software distribution mechanism. Files have execution permissions.
- Optionally users can also direct it to symlink the distributed cache file(s)
- into the working directory of the task.</p>
-
- <p><code>DistributedCache</code> tracks modification timestamps of the cache
- files. Clearly the cache files should not be modified by the application
- or externally while the job is executing.</p>
-
- <p>Here is an illustrative example on how to use the
- <code>DistributedCache</code>:</p>
- <p><blockquote><pre>
- // Setting up the cache for the application
-
- 1. Copy the requisite files to the <code>FileSystem</code>:
-
- $ bin/hadoop fs -copyFromLocal lookup.dat /myapp/lookup.dat
- $ bin/hadoop fs -copyFromLocal map.zip /myapp/map.zip
- $ bin/hadoop fs -copyFromLocal mylib.jar /myapp/mylib.jar
- $ bin/hadoop fs -copyFromLocal mytar.tar /myapp/mytar.tar
- $ bin/hadoop fs -copyFromLocal mytgz.tgz /myapp/mytgz.tgz
- $ bin/hadoop fs -copyFromLocal mytargz.tar.gz /myapp/mytargz.tar.gz
-
- 2. Setup the application's <code>JobConf</code>:
-
- JobConf job = new JobConf();
- DistributedCache.addCacheFile(new URI("/myapp/lookup.dat#lookup.dat"),
- job);
- DistributedCache.addCacheArchive(new URI("/myapp/map.zip", job);
- DistributedCache.addFileToClassPath(new Path("/myapp/mylib.jar"), job);
- DistributedCache.addCacheArchive(new URI("/myapp/mytar.tar", job);
- DistributedCache.addCacheArchive(new URI("/myapp/mytgz.tgz", job);
- DistributedCache.addCacheArchive(new URI("/myapp/mytargz.tar.gz", job);
-
- 3. Use the cached files in the {@link org.apache.hadoop.mapred.Mapper}
- or {@link org.apache.hadoop.mapred.Reducer}:
-
- public static class MapClass extends MapReduceBase
- implements Mapper<K, V, K, V> {
-
- private Path[] localArchives;
- private Path[] localFiles;
-
- public void configure(JobConf job) {
- // Get the cached archives/files
- localArchives = DistributedCache.getLocalCacheArchives(job);
- localFiles = DistributedCache.getLocalCacheFiles(job);
- }
-
- public void map(K key, V value,
- OutputCollector<K, V> output, Reporter reporter)
- throws IOException {
- // Use data from the cached archives/files here
- // ...
- // ...
- output.collect(k, v);
- }
- }
-
- </pre></blockquote></p>
- It is also very common to use the DistributedCache by using
- {@link org.apache.hadoop.util.GenericOptionsParser}.
- This class includes methods that should be used by users
- (specifically those mentioned in the example above, as well
- as {@link DistributedCache#addArchiveToClassPath(Path, Configuration)}),
- as well as methods intended for use by the MapReduce framework
- (e.g., {@link org.apache.hadoop.mapred.JobClient}). For implementation
- details, see {@link TrackerDistributedCacheManager} and
- {@link TaskDistributedCacheManager}.
- @see org.apache.hadoop.mapred.JobConf
- @see org.apache.hadoop.mapred.JobClient
- @see org.apache.hadoop.mapreduce.Job
- @deprecated Use methods on {@link Job}.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.filecache.DistributedCache -->
- </package>
- <package name="org.apache.hadoop.mapred">
- <!-- start class org.apache.hadoop.mapred.ClusterStatus -->
- <class name="ClusterStatus" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link ClusterMetrics} or {@link TaskTrackerInfo} instead">
- <implements name="org.apache.hadoop.io.Writable"/>
- <method name="getTaskTrackers" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the number of task trackers in the cluster.
-
- @return the number of task trackers in the cluster.]]>
- </doc>
- </method>
- <method name="getActiveTrackerNames" return="java.util.Collection"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the names of task trackers in the cluster.
-
- @return the active task trackers in the cluster.]]>
- </doc>
- </method>
- <method name="getBlacklistedTrackerNames" return="java.util.Collection"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the names of task trackers in the cluster.
-
- @return the blacklisted task trackers in the cluster.]]>
- </doc>
- </method>
- <method name="getBlacklistedTrackers" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the number of blacklisted task trackers in the cluster.
-
- @return the number of blacklisted task trackers in the cluster.]]>
- </doc>
- </method>
- <method name="getNumExcludedNodes" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the number of excluded hosts in the cluster.
- @return the number of excluded hosts in the cluster.]]>
- </doc>
- </method>
- <method name="getTTExpiryInterval" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the tasktracker expiry interval for the cluster
- @return the expiry interval in msec]]>
- </doc>
- </method>
- <method name="getMapTasks" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the number of currently running map tasks in the cluster.
-
- @return the number of currently running map tasks in the cluster.]]>
- </doc>
- </method>
- <method name="getReduceTasks" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the number of currently running reduce tasks in the cluster.
-
- @return the number of currently running reduce tasks in the cluster.]]>
- </doc>
- </method>
- <method name="getMaxMapTasks" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the maximum capacity for running map tasks in the cluster.
-
- @return the maximum capacity for running map tasks in the cluster.]]>
- </doc>
- </method>
- <method name="getMaxReduceTasks" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the maximum capacity for running reduce tasks in the cluster.
-
- @return the maximum capacity for running reduce tasks in the cluster.]]>
- </doc>
- </method>
- <method name="getJobTrackerState" return="org.apache.hadoop.mapred.JobTracker.State"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link #getJobTrackerStatus()} instead.">
- <doc>
- <![CDATA[Get the current state of the <code>JobTracker</code>,
- as {@link JobTracker.State}
-
- @return the current state of the <code>JobTracker</code>.
- @deprecated Use {@link #getJobTrackerStatus()} instead.]]>
- </doc>
- </method>
- <method name="getJobTrackerStatus" return="org.apache.hadoop.mapreduce.Cluster.JobTrackerStatus"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the JobTracker's status.
-
- @return {@link JobTrackerStatus} of the JobTracker]]>
- </doc>
- </method>
- <method name="getBlackListedTrackersInfo" return="java.util.Collection"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Gets the list of blacklisted trackers along with reasons for blacklisting.
-
- @return the collection of {@link BlackListInfo} objects.]]>
- </doc>
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="out" type="java.io.DataOutput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="readFields"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="in" type="java.io.DataInput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[Status information on the current state of the Map-Reduce cluster.
-
- <p><code>ClusterStatus</code> provides clients with information such as:
- <ol>
- <li>
- Size of the cluster.
- </li>
- <li>
- Name of the trackers.
- </li>
- <li>
- Task capacity of the cluster.
- </li>
- <li>
- The number of currently running map & reduce tasks.
- </li>
- <li>
- State of the <code>JobTracker</code>.
- </li>
- <li>
- Details regarding black listed trackers.
- </li>
- </ol></p>
-
- <p>Clients can query for the latest <code>ClusterStatus</code>, via
- {@link JobClient#getClusterStatus()}.</p>
-
- @see JobClient
- @deprecated Use {@link ClusterMetrics} or {@link TaskTrackerInfo} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.ClusterStatus -->
- <!-- start class org.apache.hadoop.mapred.ClusterStatus.BlackListInfo -->
- <class name="ClusterStatus.BlackListInfo" extends="java.lang.Object"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.io.Writable"/>
- <method name="getTrackerName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Gets the blacklisted tasktracker's name.
-
- @return tracker's name.]]>
- </doc>
- </method>
- <method name="getReasonForBlackListing" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Gets the reason for which the tasktracker was blacklisted.
-
- @return reason which tracker was blacklisted]]>
- </doc>
- </method>
- <method name="getBlackListReport" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Gets a descriptive report about why the tasktracker was blacklisted.
-
- @return report describing why the tasktracker was blacklisted.]]>
- </doc>
- </method>
- <method name="readFields"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="in" type="java.io.DataInput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="out" type="java.io.DataOutput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="toString" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <doc>
- <![CDATA[Class which encapsulates information about a blacklisted tasktracker.
-
- The information includes the tasktracker's name and reasons for
- getting blacklisted. The toString method of the class will print
- the information in a whitespace separated fashion to enable parsing.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.ClusterStatus.BlackListInfo -->
- <!-- start class org.apache.hadoop.mapred.Counters -->
- <class name="Counters" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.Counters} instead.">
- <implements name="org.apache.hadoop.io.Writable"/>
- <implements name="java.lang.Iterable"/>
- <constructor name="Counters"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getGroupNames" return="java.util.Collection"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns the names of all counter classes.
- @return Set of counter names.]]>
- </doc>
- </method>
- <method name="iterator" return="java.util.Iterator"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getGroup" return="org.apache.hadoop.mapred.Counters.Group"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="groupName" type="java.lang.String"/>
- <doc>
- <![CDATA[Returns the named counter group, or an empty group if there is none
- with the specified name.]]>
- </doc>
- </method>
- <method name="findCounter" return="org.apache.hadoop.mapred.Counters.Counter"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="java.lang.Enum"/>
- <doc>
- <![CDATA[Find the counter for the given enum. The same enum will always return the
- same counter.
- @param key the counter key
- @return the matching counter object]]>
- </doc>
- </method>
- <method name="findCounter" return="org.apache.hadoop.mapred.Counters.Counter"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="group" type="java.lang.String"/>
- <param name="name" type="java.lang.String"/>
- <doc>
- <![CDATA[Find a counter given the group and the name.
- @param group the name of the group
- @param name the internal name of the counter
- @return the counter for that name]]>
- </doc>
- </method>
- <method name="findCounter" return="org.apache.hadoop.mapred.Counters.Counter"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="deprecated, no comment">
- <param name="group" type="java.lang.String"/>
- <param name="id" type="int"/>
- <param name="name" type="java.lang.String"/>
- <doc>
- <![CDATA[Find a counter by using strings
- @param group the name of the group
- @param id the id of the counter within the group (0 to N-1)
- @param name the internal name of the counter
- @return the counter for that name
- @deprecated]]>
- </doc>
- </method>
- <method name="incrCounter"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="java.lang.Enum"/>
- <param name="amount" type="long"/>
- <doc>
- <![CDATA[Increments the specified counter by the specified amount, creating it if
- it didn't already exist.
- @param key identifies a counter
- @param amount amount by which counter is to be incremented]]>
- </doc>
- </method>
- <method name="incrCounter"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="group" type="java.lang.String"/>
- <param name="counter" type="java.lang.String"/>
- <param name="amount" type="long"/>
- <doc>
- <![CDATA[Increments the specified counter by the specified amount, creating it if
- it didn't already exist.
- @param group the name of the group
- @param counter the internal name of the counter
- @param amount amount by which counter is to be incremented]]>
- </doc>
- </method>
- <method name="getCounter" return="long"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="java.lang.Enum"/>
- <doc>
- <![CDATA[Returns current value of the specified counter, or 0 if the counter
- does not exist.]]>
- </doc>
- </method>
- <method name="incrAllCounters"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="other" type="org.apache.hadoop.mapred.Counters"/>
- <doc>
- <![CDATA[Increments multiple counters by their amounts in another Counters
- instance.
- @param other the other Counters instance]]>
- </doc>
- </method>
- <method name="sum" return="org.apache.hadoop.mapred.Counters"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="a" type="org.apache.hadoop.mapred.Counters"/>
- <param name="b" type="org.apache.hadoop.mapred.Counters"/>
- <doc>
- <![CDATA[Convenience method for computing the sum of two sets of counters.]]>
- </doc>
- </method>
- <method name="size" return="int"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns the total number of counters, by summing the number of counters
- in each group.]]>
- </doc>
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="out" type="java.io.DataOutput"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Write the set of groups.
- The external format is:
- #groups (groupName group)*
- i.e. the number of groups followed by 0 or more groups, where each
- group is of the form:
- groupDisplayName #counters (false | true counter)*
- where each counter is of the form:
- name (false | true displayName) value]]>
- </doc>
- </method>
- <method name="readFields"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="in" type="java.io.DataInput"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Read a set of groups.]]>
- </doc>
- </method>
- <method name="log"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="log" type="org.apache.commons.logging.Log"/>
- <doc>
- <![CDATA[Logs the current counter values.
- @param log The log to use.]]>
- </doc>
- </method>
- <method name="toString" return="java.lang.String"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Return textual representation of the counter values.]]>
- </doc>
- </method>
- <method name="makeCompactString" return="java.lang.String"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Convert a counters object into a single line that is easy to parse.
- @return the string with "name=value" for each counter and separated by ","]]>
- </doc>
- </method>
- <method name="makeEscapedCompactString" return="java.lang.String"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Represent the counter in a textual format that can be converted back to
- its object form
- @return the string in the following format
- {(groupname)(group-displayname)[(countername)(displayname)(value)][][]}{}{}]]>
- </doc>
- </method>
- <method name="fromEscapedCompactString" return="org.apache.hadoop.mapred.Counters"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="compactString" type="java.lang.String"/>
- <exception name="ParseException" type="java.text.ParseException"/>
- <doc>
- <![CDATA[Convert a stringified counter representation into a counter object. Note
- that the counter can be recovered if its stringified using
- {@link #makeEscapedCompactString()}.
- @return a Counter]]>
- </doc>
- </method>
- <method name="hashCode" return="int"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="equals" return="boolean"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="obj" type="java.lang.Object"/>
- </method>
- <doc>
- <![CDATA[A set of named counters.
-
- <p><code>Counters</code> represent global counters, defined either by the
- Map-Reduce framework or applications. Each <code>Counter</code> can be of
- any {@link Enum} type.</p>
-
- <p><code>Counters</code> are bunched into {@link Group}s, each comprising of
- counters from a particular <code>Enum</code> class.
- @deprecated Use {@link org.apache.hadoop.mapreduce.Counters} instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.Counters -->
- <!-- start class org.apache.hadoop.mapred.Counters.Counter -->
- <class name="Counters.Counter" extends="org.apache.hadoop.mapreduce.Counter"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <method name="setDisplayName"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="newName" type="java.lang.String"/>
- </method>
- <method name="makeEscapedCompactString" return="java.lang.String"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns the compact stringified version of the counter in the format
- [(actual-name)(display-name)(value)]]]>
- </doc>
- </method>
- <method name="getCounter" return="long"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[What is the current value of this counter?
- @return the current value]]>
- </doc>
- </method>
- <doc>
- <![CDATA[A counter record, comprising its name and value.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.Counters.Counter -->
- <!-- start class org.apache.hadoop.mapred.Counters.Group -->
- <class name="Counters.Group" extends="java.lang.Object"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.io.Writable"/>
- <implements name="java.lang.Iterable"/>
- <method name="getName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns raw name of the group. This is the name of the enum class
- for this group of counters.]]>
- </doc>
- </method>
- <method name="getDisplayName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns localized name of the group. This is the same as getName() by
- default, but different if an appropriate ResourceBundle is found.]]>
- </doc>
- </method>
- <method name="setDisplayName"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="displayName" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the display name]]>
- </doc>
- </method>
- <method name="makeEscapedCompactString" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns the compact stringified version of the group in the format
- {(actual-name)(display-name)(value)[][][]} where [] are compact strings for the
- counters within.]]>
- </doc>
- </method>
- <method name="hashCode" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="equals" return="boolean"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="obj" type="java.lang.Object"/>
- <doc>
- <![CDATA[Checks for (content) equality of Groups]]>
- </doc>
- </method>
- <method name="getCounter" return="long"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="counterName" type="java.lang.String"/>
- <doc>
- <![CDATA[Returns the value of the specified counter, or 0 if the counter does
- not exist.]]>
- </doc>
- </method>
- <method name="getCounter" return="org.apache.hadoop.mapred.Counters.Counter"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="use {@link #getCounter(String)} instead">
- <param name="id" type="int"/>
- <param name="name" type="java.lang.String"/>
- <doc>
- <![CDATA[Get the counter for the given id and create it if it doesn't exist.
- @param id the numeric id of the counter within the group
- @param name the internal counter name
- @return the counter
- @deprecated use {@link #getCounter(String)} instead]]>
- </doc>
- </method>
- <method name="getCounterForName" return="org.apache.hadoop.mapred.Counters.Counter"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- <doc>
- <![CDATA[Get the counter for the given name and create it if it doesn't exist.
- @param name the internal counter name
- @return the counter]]>
- </doc>
- </method>
- <method name="size" return="int"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns the number of counters in this group.]]>
- </doc>
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="out" type="java.io.DataOutput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="readFields"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="in" type="java.io.DataInput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="iterator" return="java.util.Iterator"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <doc>
- <![CDATA[<code>Group</code> of counters, comprising of counters from a particular
- counter {@link Enum} class.
- <p><code>Group</code>handles localization of the class name and the
- counter names.</p>]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.Counters.Group -->
- <!-- start class org.apache.hadoop.mapred.FileAlreadyExistsException -->
- <class name="FileAlreadyExistsException" extends="java.io.IOException"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="FileAlreadyExistsException"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <constructor name="FileAlreadyExistsException" type="java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <doc>
- <![CDATA[Used when target file already exists for any operation and
- is not configured to be overwritten.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.FileAlreadyExistsException -->
- <!-- start class org.apache.hadoop.mapred.FileInputFormat -->
- <class name="FileInputFormat" extends="java.lang.Object"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.lib.input.FileInputFormat}
- instead.">
- <implements name="org.apache.hadoop.mapred.InputFormat"/>
- <constructor name="FileInputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setMinSplitSize"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="minSplitSize" type="long"/>
- </method>
- <method name="isSplitable" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="fs" type="org.apache.hadoop.fs.FileSystem"/>
- <param name="filename" type="org.apache.hadoop.fs.Path"/>
- <doc>
- <![CDATA[Is the given filename splitable? Usually, true, but if the file is
- stream compressed, it will not be.
-
- <code>FileInputFormat</code> implementations can override this and return
- <code>false</code> to ensure that individual input files are never split-up
- so that {@link Mapper}s process entire files.
-
- @param fs the file system that the file is on
- @param filename the file name to check
- @return is this file splitable?]]>
- </doc>
- </method>
- <method name="getRecordReader" return="org.apache.hadoop.mapred.RecordReader"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapred.InputSplit"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="setInputPathFilter"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="filter" type="java.lang.Class"/>
- <doc>
- <![CDATA[Set a PathFilter to be applied to the input paths for the map-reduce job.
- @param filter the PathFilter class use for filtering the input paths.]]>
- </doc>
- </method>
- <method name="getInputPathFilter" return="org.apache.hadoop.fs.PathFilter"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[Get a PathFilter instance of the filter set for the input paths.
- @return the PathFilter instance set for the job, NULL if none has been set.]]>
- </doc>
- </method>
- <method name="addInputPathRecursively"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="result" type="java.util.List"/>
- <param name="fs" type="org.apache.hadoop.fs.FileSystem"/>
- <param name="path" type="org.apache.hadoop.fs.Path"/>
- <param name="inputFilter" type="org.apache.hadoop.fs.PathFilter"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Add files in the input path recursively into the results.
- @param result
- The List to store all files.
- @param fs
- The FileSystem.
- @param path
- The input path.
- @param inputFilter
- The input filter that can be used to filter files/dirs.
- @throws IOException]]>
- </doc>
- </method>
- <method name="listStatus" return="org.apache.hadoop.fs.FileStatus[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[List input directories.
- Subclasses may override to, e.g., select only files matching a regular
- expression.
-
- @param job the job to list input paths for
- @return array of FileStatus objects
- @throws IOException if zero items.]]>
- </doc>
- </method>
- <method name="makeSplit" return="org.apache.hadoop.mapred.FileSplit"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="file" type="org.apache.hadoop.fs.Path"/>
- <param name="start" type="long"/>
- <param name="length" type="long"/>
- <param name="hosts" type="java.lang.String[]"/>
- <doc>
- <![CDATA[A factory that makes the split for this class. It can be overridden
- by sub-classes to make sub-types]]>
- </doc>
- </method>
- <method name="getSplits" return="org.apache.hadoop.mapred.InputSplit[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="numSplits" type="int"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Splits files returned by {@link #listStatus(JobConf)} when
- they're too big.]]>
- </doc>
- </method>
- <method name="computeSplitSize" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="goalSize" type="long"/>
- <param name="minSize" type="long"/>
- <param name="blockSize" type="long"/>
- </method>
- <method name="getBlockIndex" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="blkLocations" type="org.apache.hadoop.fs.BlockLocation[]"/>
- <param name="offset" type="long"/>
- </method>
- <method name="setInputPaths"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="commaSeparatedPaths" type="java.lang.String"/>
- <doc>
- <![CDATA[Sets the given comma separated paths as the list of inputs
- for the map-reduce job.
-
- @param conf Configuration of the job
- @param commaSeparatedPaths Comma separated paths to be set as
- the list of inputs for the map-reduce job.]]>
- </doc>
- </method>
- <method name="addInputPaths"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="commaSeparatedPaths" type="java.lang.String"/>
- <doc>
- <![CDATA[Add the given comma separated paths to the list of inputs for
- the map-reduce job.
-
- @param conf The configuration of the job
- @param commaSeparatedPaths Comma separated paths to be added to
- the list of inputs for the map-reduce job.]]>
- </doc>
- </method>
- <method name="setInputPaths"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="inputPaths" type="org.apache.hadoop.fs.Path[]"/>
- <doc>
- <![CDATA[Set the array of {@link Path}s as the list of inputs
- for the map-reduce job.
-
- @param conf Configuration of the job.
- @param inputPaths the {@link Path}s of the input directories/files
- for the map-reduce job.]]>
- </doc>
- </method>
- <method name="addInputPath"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="path" type="org.apache.hadoop.fs.Path"/>
- <doc>
- <![CDATA[Add a {@link Path} to the list of inputs for the map-reduce job.
-
- @param conf The configuration of the job
- @param path {@link Path} to be added to the list of inputs for
- the map-reduce job.]]>
- </doc>
- </method>
- <method name="getInputPaths" return="org.apache.hadoop.fs.Path[]"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[Get the list of input {@link Path}s for the map-reduce job.
-
- @param conf The configuration of the job
- @return the list of input {@link Path}s for the map-reduce job.]]>
- </doc>
- </method>
- <method name="getSplitHosts" return="java.lang.String[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="blkLocations" type="org.apache.hadoop.fs.BlockLocation[]"/>
- <param name="offset" type="long"/>
- <param name="splitSize" type="long"/>
- <param name="clusterMap" type="org.apache.hadoop.net.NetworkTopology"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[This function identifies and returns the hosts that contribute
- most for a given split. For calculating the contribution, rack
- locality is treated on par with host locality, so hosts from racks
- that contribute the most are preferred over hosts on racks that
- contribute less
- @param blkLocations The list of block locations
- @param offset
- @param splitSize
- @return array of hosts that contribute most to this split
- @throws IOException]]>
- </doc>
- </method>
- <field name="LOG" type="org.apache.commons.logging.Log"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="NUM_INPUT_FILES" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[A base class for file-based {@link InputFormat}.
-
- <p><code>FileInputFormat</code> is the base class for all file-based
- <code>InputFormat</code>s. This provides a generic implementation of
- {@link #getSplits(JobConf, int)}.
- Subclasses of <code>FileInputFormat</code> can also override the
- {@link #isSplitable(FileSystem, Path)} method to ensure input-files are
- not split-up and are processed as a whole by {@link Mapper}s.
- @deprecated Use {@link org.apache.hadoop.mapreduce.lib.input.FileInputFormat}
- instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.FileInputFormat -->
- <!-- start class org.apache.hadoop.mapred.FileOutputCommitter -->
- <class name="FileOutputCommitter" extends="org.apache.hadoop.mapred.OutputCommitter"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="FileOutputCommitter"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setupJob"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapred.JobContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="commitJob"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapred.JobContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="cleanupJob"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapred.JobContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="abortJob"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapred.JobContext"/>
- <param name="runState" type="int"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="setupTask"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapred.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="commitTask"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapred.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="abortTask"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapred.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="needsTaskCommit" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapred.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <field name="LOG" type="org.apache.commons.logging.Log"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="TEMP_DIR_NAME" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Temporary directory name]]>
- </doc>
- </field>
- <field name="SUCCEEDED_FILE_NAME" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[An {@link OutputCommitter} that commits files specified
- in job output directory i.e. ${mapreduce.output.fileoutputformat.outputdir}.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.FileOutputCommitter -->
- <!-- start class org.apache.hadoop.mapred.FileOutputFormat -->
- <class name="FileOutputFormat" extends="java.lang.Object"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapred.OutputFormat"/>
- <constructor name="FileOutputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setCompressOutput"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="compress" type="boolean"/>
- <doc>
- <![CDATA[Set whether the output of the job is compressed.
- @param conf the {@link JobConf} to modify
- @param compress should the output of the job be compressed?]]>
- </doc>
- </method>
- <method name="getCompressOutput" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[Is the job output compressed?
- @param conf the {@link JobConf} to look in
- @return <code>true</code> if the job output should be compressed,
- <code>false</code> otherwise]]>
- </doc>
- </method>
- <method name="setOutputCompressorClass"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="codecClass" type="java.lang.Class"/>
- <doc>
- <![CDATA[Set the {@link CompressionCodec} to be used to compress job outputs.
- @param conf the {@link JobConf} to modify
- @param codecClass the {@link CompressionCodec} to be used to
- compress the job outputs]]>
- </doc>
- </method>
- <method name="getOutputCompressorClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="defaultValue" type="java.lang.Class"/>
- <doc>
- <![CDATA[Get the {@link CompressionCodec} for compressing the job outputs.
- @param conf the {@link JobConf} to look in
- @param defaultValue the {@link CompressionCodec} to return if not set
- @return the {@link CompressionCodec} to be used to compress the
- job outputs
- @throws IllegalArgumentException if the class was specified, but not found]]>
- </doc>
- </method>
- <method name="getRecordWriter" return="org.apache.hadoop.mapred.RecordWriter"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="name" type="java.lang.String"/>
- <param name="progress" type="org.apache.hadoop.util.Progressable"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="checkOutputSpecs"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <exception name="FileAlreadyExistsException" type="org.apache.hadoop.mapred.FileAlreadyExistsException"/>
- <exception name="InvalidJobConfException" type="org.apache.hadoop.mapred.InvalidJobConfException"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="setOutputPath"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="outputDir" type="org.apache.hadoop.fs.Path"/>
- <doc>
- <![CDATA[Set the {@link Path} of the output directory for the map-reduce job.
- @param conf The configuration of the job.
- @param outputDir the {@link Path} of the output directory for
- the map-reduce job.]]>
- </doc>
- </method>
- <method name="getOutputPath" return="org.apache.hadoop.fs.Path"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[Get the {@link Path} to the output directory for the map-reduce job.
-
- @return the {@link Path} to the output directory for the map-reduce job.
- @see FileOutputFormat#getWorkOutputPath(JobConf)]]>
- </doc>
- </method>
- <method name="getWorkOutputPath" return="org.apache.hadoop.fs.Path"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[Get the {@link Path} to the task's temporary output directory
- for the map-reduce job
-
- <h4 id="SideEffectFiles">Tasks' Side-Effect Files</h4>
-
- <p><i>Note:</i> The following is valid only if the {@link OutputCommitter}
- is {@link FileOutputCommitter}. If <code>OutputCommitter</code> is not
- a <code>FileOutputCommitter</code>, the task's temporary output
- directory is same as {@link #getOutputPath(JobConf)} i.e.
- <tt>${mapreduce.output.fileoutputformat.outputdir}$</tt></p>
-
- <p>Some applications need to create/write-to side-files, which differ from
- the actual job-outputs.
-
- <p>In such cases there could be issues with 2 instances of the same TIP
- (running simultaneously e.g. speculative tasks) trying to open/write-to the
- same file (path) on HDFS. Hence the application-writer will have to pick
- unique names per task-attempt (e.g. using the attemptid, say
- <tt>attempt_200709221812_0001_m_000000_0</tt>), not just per TIP.</p>
-
- <p>To get around this the Map-Reduce framework helps the application-writer
- out by maintaining a special
- <tt>${mapreduce.output.fileoutputformat.outputdir}/_temporary/_${taskid}</tt>
- sub-directory for each task-attempt on HDFS where the output of the
- task-attempt goes. On successful completion of the task-attempt the files
- in the <tt>${mapreduce.output.fileoutputformat.outputdir}/_temporary/_${taskid}</tt> (only)
- are <i>promoted</i> to <tt>${mapreduce.output.fileoutputformat.outputdir}</tt>. Of course, the
- framework discards the sub-directory of unsuccessful task-attempts. This
- is completely transparent to the application.</p>
-
- <p>The application-writer can take advantage of this by creating any
- side-files required in <tt>${mapreduce.task.output.dir}</tt> during execution
- of his reduce-task i.e. via {@link #getWorkOutputPath(JobConf)}, and the
- framework will move them out similarly - thus she doesn't have to pick
- unique paths per task-attempt.</p>
-
- <p><i>Note</i>: the value of <tt>${mapreduce.task.output.dir}</tt> during
- execution of a particular task-attempt is actually
- <tt>${mapreduce.output.fileoutputformat.outputdir}/_temporary/_{$taskid}</tt>, and this value is
- set by the map-reduce framework. So, just create any side-files in the
- path returned by {@link #getWorkOutputPath(JobConf)} from map/reduce
- task to take advantage of this feature.</p>
-
- <p>The entire discussion holds true for maps of jobs with
- reducer=NONE (i.e. 0 reduces) since output of the map, in that case,
- goes directly to HDFS.</p>
-
- @return the {@link Path} to the task's temporary output directory
- for the map-reduce job.]]>
- </doc>
- </method>
- <method name="getTaskOutputPath" return="org.apache.hadoop.fs.Path"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="name" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Helper function to create the task's temporary output directory and
- return the path to the task's output file.
-
- @param conf job-configuration
- @param name temporary task-output filename
- @return path to the task's temporary output file
- @throws IOException]]>
- </doc>
- </method>
- <method name="getUniqueName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="name" type="java.lang.String"/>
- <doc>
- <![CDATA[Helper function to generate a name that is unique for the task.
- <p>The generated name can be used to create custom files from within the
- different tasks for the job, the names for different tasks will not collide
- with each other.</p>
- <p>The given name is postfixed with the task type, 'm' for maps, 'r' for
- reduces and the task partition number. For example, give a name 'test'
- running on the first map o the job the generated name will be
- 'test-m-00000'.</p>
- @param conf the configuration for the job.
- @param name the name to make unique.
- @return a unique name accross all tasks of the job.]]>
- </doc>
- </method>
- <method name="getPathForCustomFile" return="org.apache.hadoop.fs.Path"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="name" type="java.lang.String"/>
- <doc>
- <![CDATA[Helper function to generate a {@link Path} for a file that is unique for
- the task within the job output directory.
- <p>The path can be used to create custom files from within the map and
- reduce tasks. The path name will be unique for each task. The path parent
- will be the job output directory.</p>ls
- <p>This method uses the {@link #getUniqueName} method to make the file name
- unique for the task.</p>
- @param conf the configuration for the job.
- @param name the name for the file.
- @return a unique path accross all tasks of the job.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[A base class for {@link OutputFormat}.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.FileOutputFormat -->
- <!-- start class org.apache.hadoop.mapred.FileSplit -->
- <class name="FileSplit" extends="org.apache.hadoop.mapreduce.InputSplit"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.lib.input.FileSplit}
- instead.">
- <implements name="org.apache.hadoop.mapred.InputSplit"/>
- <constructor name="FileSplit"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </constructor>
- <constructor name="FileSplit" type="org.apache.hadoop.fs.Path, long, long, org.apache.hadoop.mapred.JobConf"
- static="false" final="false" visibility="public"
- deprecated="deprecated, no comment">
- <doc>
- <![CDATA[Constructs a split.
- @deprecated
- @param file the file name
- @param start the position of the first byte in the file to process
- @param length the number of bytes in the file to process]]>
- </doc>
- </constructor>
- <constructor name="FileSplit" type="org.apache.hadoop.fs.Path, long, long, java.lang.String[]"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Constructs a split with host information
- @param file the file name
- @param start the position of the first byte in the file to process
- @param length the number of bytes in the file to process
- @param hosts the list of hosts containing the block, possibly null]]>
- </doc>
- </constructor>
- <constructor name="FileSplit" type="org.apache.hadoop.mapreduce.lib.input.FileSplit"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getPath" return="org.apache.hadoop.fs.Path"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[The file containing this split's data.]]>
- </doc>
- </method>
- <method name="getStart" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[The position of the first byte in the file to process.]]>
- </doc>
- </method>
- <method name="getLength" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[The number of bytes in the file to process.]]>
- </doc>
- </method>
- <method name="toString" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="out" type="java.io.DataOutput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="readFields"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="in" type="java.io.DataInput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getLocations" return="java.lang.String[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[A section of an input file. Returned by {@link
- InputFormat#getSplits(JobConf, int)} and passed to
- {@link InputFormat#getRecordReader(InputSplit,JobConf,Reporter)}.
- @deprecated Use {@link org.apache.hadoop.mapreduce.lib.input.FileSplit}
- instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.FileSplit -->
- <!-- start class org.apache.hadoop.mapred.ID -->
- <class name="ID" extends="org.apache.hadoop.mapreduce.ID"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="ID" type="int"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[constructs an ID object from the given int]]>
- </doc>
- </constructor>
- <constructor name="ID"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </constructor>
- <doc>
- <![CDATA[A general identifier, which internally stores the id
- as an integer. This is the super class of {@link JobID},
- {@link TaskID} and {@link TaskAttemptID}.
-
- @see JobID
- @see TaskID
- @see TaskAttemptID]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.ID -->
- <!-- start interface org.apache.hadoop.mapred.InputFormat -->
- <interface name="InputFormat" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.InputFormat} instead.">
- <method name="getSplits" return="org.apache.hadoop.mapred.InputSplit[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="numSplits" type="int"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Logically split the set of input files for the job.
-
- <p>Each {@link InputSplit} is then assigned to an individual {@link Mapper}
- for processing.</p>
- <p><i>Note</i>: The split is a <i>logical</i> split of the inputs and the
- input files are not physically split into chunks. For e.g. a split could
- be <i><input-file-path, start, offset></i> tuple.
-
- @param job job configuration.
- @param numSplits the desired number of splits, a hint.
- @return an array of {@link InputSplit}s for the job.]]>
- </doc>
- </method>
- <method name="getRecordReader" return="org.apache.hadoop.mapred.RecordReader"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapred.InputSplit"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get the {@link RecordReader} for the given {@link InputSplit}.
- <p>It is the responsibility of the <code>RecordReader</code> to respect
- record boundaries while processing the logical split to present a
- record-oriented view to the individual task.</p>
-
- @param split the {@link InputSplit}
- @param job the job that this split belongs to
- @return a {@link RecordReader}]]>
- </doc>
- </method>
- <doc>
- <![CDATA[<code>InputFormat</code> describes the input-specification for a
- Map-Reduce job.
-
- <p>The Map-Reduce framework relies on the <code>InputFormat</code> of the
- job to:<p>
- <ol>
- <li>
- Validate the input-specification of the job.
- <li>
- Split-up the input file(s) into logical {@link InputSplit}s, each of
- which is then assigned to an individual {@link Mapper}.
- </li>
- <li>
- Provide the {@link RecordReader} implementation to be used to glean
- input records from the logical <code>InputSplit</code> for processing by
- the {@link Mapper}.
- </li>
- </ol>
-
- <p>The default behavior of file-based {@link InputFormat}s, typically
- sub-classes of {@link FileInputFormat}, is to split the
- input into <i>logical</i> {@link InputSplit}s based on the total size, in
- bytes, of the input files. However, the {@link FileSystem} blocksize of
- the input files is treated as an upper bound for input splits. A lower bound
- on the split size can be set via
- <a href="{@docRoot}/../mapred-default.html#mapreduce.input.fileinputformat.split.minsize">
- mapreduce.input.fileinputformat.split.minsize</a>.</p>
-
- <p>Clearly, logical splits based on input-size is insufficient for many
- applications since record boundaries are to respected. In such cases, the
- application has to also implement a {@link RecordReader} on whom lies the
- responsibilty to respect record-boundaries and present a record-oriented
- view of the logical <code>InputSplit</code> to the individual task.
- @see InputSplit
- @see RecordReader
- @see JobClient
- @see FileInputFormat
- @deprecated Use {@link org.apache.hadoop.mapreduce.InputFormat} instead.]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.InputFormat -->
- <!-- start interface org.apache.hadoop.mapred.InputSplit -->
- <interface name="InputSplit" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.InputSplit} instead.">
- <implements name="org.apache.hadoop.io.Writable"/>
- <method name="getLength" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get the total number of bytes in the data of the <code>InputSplit</code>.
-
- @return the number of bytes in the input split.
- @throws IOException]]>
- </doc>
- </method>
- <method name="getLocations" return="java.lang.String[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get the list of hostnames where the input split is located.
-
- @return list of hostnames where data of the <code>InputSplit</code> is
- located as an array of <code>String</code>s.
- @throws IOException]]>
- </doc>
- </method>
- <doc>
- <![CDATA[<code>InputSplit</code> represents the data to be processed by an
- individual {@link Mapper}.
- <p>Typically, it presents a byte-oriented view on the input and is the
- responsibility of {@link RecordReader} of the job to process this and present
- a record-oriented view.
-
- @see InputFormat
- @see RecordReader
- @deprecated Use {@link org.apache.hadoop.mapreduce.InputSplit} instead.]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.InputSplit -->
- <!-- start class org.apache.hadoop.mapred.InvalidFileTypeException -->
- <class name="InvalidFileTypeException" extends="java.io.IOException"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="InvalidFileTypeException"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <constructor name="InvalidFileTypeException" type="java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <doc>
- <![CDATA[Used when file type differs from the desired file type. like
- getting a file when a directory is expected. Or a wrong file type.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.InvalidFileTypeException -->
- <!-- start class org.apache.hadoop.mapred.InvalidInputException -->
- <class name="InvalidInputException" extends="java.io.IOException"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="InvalidInputException" type="java.util.List"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Create the exception with the given list.
- @param probs the list of problems to report. this list is not copied.]]>
- </doc>
- </constructor>
- <method name="getProblems" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the complete list of the problems reported.
- @return the list of problems, which must not be modified]]>
- </doc>
- </method>
- <method name="getMessage" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get a summary message of the problems found.
- @return the concatenated messages from all of the problems.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[This class wraps a list of problems with the input, so that the user
- can get a list of problems together instead of finding and fixing them one
- by one.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.InvalidInputException -->
- <!-- start class org.apache.hadoop.mapred.InvalidJobConfException -->
- <class name="InvalidJobConfException" extends="java.io.IOException"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="InvalidJobConfException"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <constructor name="InvalidJobConfException" type="java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <doc>
- <![CDATA[This exception is thrown when jobconf misses some mendatory attributes
- or value of some attributes is invalid.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.InvalidJobConfException -->
- <!-- start class org.apache.hadoop.mapred.IsolationRunner -->
- <class name="IsolationRunner" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="IsolationRunner"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="main"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="args" type="java.lang.String[]"/>
- <exception name="ClassNotFoundException" type="java.lang.ClassNotFoundException"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Run a single task.
- @param args the first argument is the task directory]]>
- </doc>
- </method>
- <doc>
- <![CDATA[IsolationRunner is intended to facilitate debugging by re-running a specific
- task, given left-over task files for a (typically failed) past job.
- Currently, it is limited to re-running map tasks.
- Users may coerce MapReduce to keep task files around by setting
- mapreduce.task.files.preserve.failedtasks. See mapred_tutorial.xml for more documentation.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.IsolationRunner -->
- <!-- start class org.apache.hadoop.mapred.JobClient -->
- <class name="JobClient" extends="org.apache.hadoop.mapreduce.tools.CLI"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link Job} and {@link Cluster} instead">
- <constructor name="JobClient"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Create a job client.]]>
- </doc>
- </constructor>
- <constructor name="JobClient" type="org.apache.hadoop.mapred.JobConf"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Build a job client with the given {@link JobConf}, and connect to the
- default {@link JobTracker}.
-
- @param conf the job configuration.
- @throws IOException]]>
- </doc>
- </constructor>
- <constructor name="JobClient" type="org.apache.hadoop.conf.Configuration"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Build a job client with the given {@link Configuration},
- and connect to the default {@link JobTracker}.
-
- @param conf the configuration.
- @throws IOException]]>
- </doc>
- </constructor>
- <constructor name="JobClient" type="java.net.InetSocketAddress, org.apache.hadoop.conf.Configuration"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Build a job client, connect to the indicated job tracker.
-
- @param jobTrackAddr the job tracker to connect to.
- @param conf configuration.]]>
- </doc>
- </constructor>
- <method name="init"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Connect to the default {@link JobTracker}.
- @param conf the job configuration.
- @throws IOException]]>
- </doc>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Close the <code>JobClient</code>.]]>
- </doc>
- </method>
- <method name="getFs" return="org.apache.hadoop.fs.FileSystem"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get a filesystem handle. We need this to prepare jobs
- for submission to the MapReduce system.
-
- @return the filesystem handle.]]>
- </doc>
- </method>
- <method name="getClusterHandle" return="org.apache.hadoop.mapreduce.Cluster"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get a handle to the Cluster]]>
- </doc>
- </method>
- <method name="submitJob" return="org.apache.hadoop.mapred.RunningJob"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobFile" type="java.lang.String"/>
- <exception name="FileNotFoundException" type="java.io.FileNotFoundException"/>
- <exception name="InvalidJobConfException" type="org.apache.hadoop.mapred.InvalidJobConfException"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Submit a job to the MR system.
-
- This returns a handle to the {@link RunningJob} which can be used to track
- the running-job.
-
- @param jobFile the job configuration.
- @return a handle to the {@link RunningJob} which can be used to track the
- running-job.
- @throws FileNotFoundException
- @throws InvalidJobConfException
- @throws IOException]]>
- </doc>
- </method>
- <method name="submitJob" return="org.apache.hadoop.mapred.RunningJob"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <exception name="FileNotFoundException" type="java.io.FileNotFoundException"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Submit a job to the MR system.
- This returns a handle to the {@link RunningJob} which can be used to track
- the running-job.
-
- @param conf the job configuration.
- @return a handle to the {@link RunningJob} which can be used to track the
- running-job.
- @throws FileNotFoundException
- @throws IOException]]>
- </doc>
- </method>
- <method name="getJob" return="org.apache.hadoop.mapred.RunningJob"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobid" type="org.apache.hadoop.mapred.JobID"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get an {@link RunningJob} object to track an ongoing job. Returns
- null if the id does not correspond to any known job.
-
- @param jobid the jobid of the job.
- @return the {@link RunningJob} handle to track the job, null if the
- <code>jobid</code> doesn't correspond to any known job.
- @throws IOException]]>
- </doc>
- </method>
- <method name="getJob" return="org.apache.hadoop.mapred.RunningJob"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="Applications should rather use {@link #getJob(JobID)}.">
- <param name="jobid" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[@deprecated Applications should rather use {@link #getJob(JobID)}.]]>
- </doc>
- </method>
- <method name="getMapTaskReports" return="org.apache.hadoop.mapred.TaskReport[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobId" type="org.apache.hadoop.mapred.JobID"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get the information of the current state of the map tasks of a job.
-
- @param jobId the job to query.
- @return the list of all of the map tips.
- @throws IOException]]>
- </doc>
- </method>
- <method name="getMapTaskReports" return="org.apache.hadoop.mapred.TaskReport[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="Applications should rather use {@link #getMapTaskReports(JobID)}">
- <param name="jobId" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[@deprecated Applications should rather use {@link #getMapTaskReports(JobID)}]]>
- </doc>
- </method>
- <method name="getReduceTaskReports" return="org.apache.hadoop.mapred.TaskReport[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobId" type="org.apache.hadoop.mapred.JobID"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get the information of the current state of the reduce tasks of a job.
-
- @param jobId the job to query.
- @return the list of all of the reduce tips.
- @throws IOException]]>
- </doc>
- </method>
- <method name="getCleanupTaskReports" return="org.apache.hadoop.mapred.TaskReport[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobId" type="org.apache.hadoop.mapred.JobID"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get the information of the current state of the cleanup tasks of a job.
-
- @param jobId the job to query.
- @return the list of all of the cleanup tips.
- @throws IOException]]>
- </doc>
- </method>
- <method name="getSetupTaskReports" return="org.apache.hadoop.mapred.TaskReport[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobId" type="org.apache.hadoop.mapred.JobID"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get the information of the current state of the setup tasks of a job.
-
- @param jobId the job to query.
- @return the list of all of the setup tips.
- @throws IOException]]>
- </doc>
- </method>
- <method name="getReduceTaskReports" return="org.apache.hadoop.mapred.TaskReport[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="Applications should rather use {@link #getReduceTaskReports(JobID)}">
- <param name="jobId" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[@deprecated Applications should rather use {@link #getReduceTaskReports(JobID)}]]>
- </doc>
- </method>
- <method name="displayTasks"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobId" type="org.apache.hadoop.mapred.JobID"/>
- <param name="type" type="java.lang.String"/>
- <param name="state" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Display the information about a job's tasks, of a particular type and
- in a particular state
-
- @param jobId the ID of the job
- @param type the type of the task (map/reduce/setup/cleanup)
- @param state the state of the task
- (pending/running/completed/failed/killed)]]>
- </doc>
- </method>
- <method name="getClusterStatus" return="org.apache.hadoop.mapred.ClusterStatus"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get status information about the Map-Reduce cluster.
-
- @return the status information about the Map-Reduce cluster as an object
- of {@link ClusterStatus}.
- @throws IOException]]>
- </doc>
- </method>
- <method name="getClusterStatus" return="org.apache.hadoop.mapred.ClusterStatus"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="detailed" type="boolean"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get status information about the Map-Reduce cluster.
-
- @param detailed if true then get a detailed status including the
- tracker names
- @return the status information about the Map-Reduce cluster as an object
- of {@link ClusterStatus}.
- @throws IOException]]>
- </doc>
- </method>
- <method name="jobsToComplete" return="org.apache.hadoop.mapred.JobStatus[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get the jobs that are not completed and not failed.
-
- @return array of {@link JobStatus} for the running/to-be-run jobs.
- @throws IOException]]>
- </doc>
- </method>
- <method name="getAllJobs" return="org.apache.hadoop.mapred.JobStatus[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get the jobs that are submitted.
-
- @return array of {@link JobStatus} for the submitted jobs.
- @throws IOException]]>
- </doc>
- </method>
- <method name="runJob" return="org.apache.hadoop.mapred.RunningJob"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Utility that submits a job, then polls for progress until the job is
- complete.
-
- @param job the job configuration.
- @throws IOException if the job fails]]>
- </doc>
- </method>
- <method name="monitorAndPrintJob" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="job" type="org.apache.hadoop.mapred.RunningJob"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Monitor a job and print status in real-time as progress is made and tasks
- fail.
- @param conf the job's configuration
- @param job the job to track
- @return true if the job succeeded
- @throws IOException if communication to the JobTracker fails]]>
- </doc>
- </method>
- <method name="setTaskOutputFilter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="newValue" type="org.apache.hadoop.mapred.JobClient.TaskStatusFilter"/>
- <doc>
- <![CDATA[Sets the output filter for tasks. only those tasks are printed whose
- output matches the filter.
- @param newValue task filter.]]>
- </doc>
- </method>
- <method name="getTaskOutputFilter" return="org.apache.hadoop.mapred.JobClient.TaskStatusFilter"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[Get the task output filter out of the JobConf.
-
- @param job the JobConf to examine.
- @return the filter level.]]>
- </doc>
- </method>
- <method name="setTaskOutputFilter"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="newValue" type="org.apache.hadoop.mapred.JobClient.TaskStatusFilter"/>
- <doc>
- <![CDATA[Modify the JobConf to set the task output filter.
-
- @param job the JobConf to modify.
- @param newValue the value to set.]]>
- </doc>
- </method>
- <method name="getTaskOutputFilter" return="org.apache.hadoop.mapred.JobClient.TaskStatusFilter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns task output filter.
- @return task filter.]]>
- </doc>
- </method>
- <method name="getCounter" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="cntrs" type="org.apache.hadoop.mapreduce.Counters"/>
- <param name="counterGroupName" type="java.lang.String"/>
- <param name="counterName" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getDefaultMaps" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get status information about the max available Maps in the cluster.
-
- @return the max available Maps in the cluster
- @throws IOException]]>
- </doc>
- </method>
- <method name="getDefaultReduces" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get status information about the max available Reduces in the cluster.
-
- @return the max available Reduces in the cluster
- @throws IOException]]>
- </doc>
- </method>
- <method name="getSystemDir" return="org.apache.hadoop.fs.Path"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Grab the jobtracker system directory path where job-specific files are to be placed.
-
- @return the system directory where job-specific files are to be placed.]]>
- </doc>
- </method>
- <method name="getRootQueues" return="org.apache.hadoop.mapred.JobQueueInfo[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Returns an array of queue information objects about root level queues
- configured
- @return the array of root level JobQueueInfo objects
- @throws IOException]]>
- </doc>
- </method>
- <method name="getChildQueues" return="org.apache.hadoop.mapred.JobQueueInfo[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="queueName" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Returns an array of queue information objects about immediate children
- of queue queueName.
-
- @param queueName
- @return the array of immediate children JobQueueInfo objects
- @throws IOException]]>
- </doc>
- </method>
- <method name="getQueues" return="org.apache.hadoop.mapred.JobQueueInfo[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Return an array of queue information objects about all the Job Queues
- configured.
-
- @return Array of JobQueueInfo objects
- @throws IOException]]>
- </doc>
- </method>
- <method name="getJobsFromQueue" return="org.apache.hadoop.mapred.JobStatus[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="queueName" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Gets all the jobs which were added to particular Job Queue
-
- @param queueName name of the Job Queue
- @return Array of jobs present in the job queue
- @throws IOException]]>
- </doc>
- </method>
- <method name="getQueueInfo" return="org.apache.hadoop.mapred.JobQueueInfo"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="queueName" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Gets the queue information associated to a particular Job Queue
-
- @param queueName name of the job queue.
- @return Queue information associated to particular queue.
- @throws IOException]]>
- </doc>
- </method>
- <method name="getQueueAclsForCurrentUser" return="org.apache.hadoop.mapred.QueueAclsInfo[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Gets the Queue ACLs for current user
- @return array of QueueAclsInfo object for current user.
- @throws IOException]]>
- </doc>
- </method>
- <method name="getDelegationToken" return="org.apache.hadoop.security.token.Token"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="renewer" type="org.apache.hadoop.io.Text"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Get a delegation token for the user from the JobTracker.
- @param renewer the user who can renew the token
- @return the new token
- @throws IOException]]>
- </doc>
- </method>
- <method name="renewDelegationToken" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="token" type="org.apache.hadoop.security.token.Token"/>
- <exception name="SecretManager.InvalidToken" type="org.apache.hadoop.security.token.SecretManager.InvalidToken"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Renew a delegation token
- @param token the token to renew
- @return true if the renewal went well
- @throws InvalidToken
- @throws IOException]]>
- </doc>
- </method>
- <method name="cancelDelegationToken"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="token" type="org.apache.hadoop.security.token.Token"/>
- <exception name="SecretManager.InvalidToken" type="org.apache.hadoop.security.token.SecretManager.InvalidToken"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Cancel a delegation token from the JobTracker
- @param token the token to cancel
- @throws IOException]]>
- </doc>
- </method>
- <method name="main"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="argv" type="java.lang.String[]"/>
- <exception name="Exception" type="java.lang.Exception"/>
- </method>
- <doc>
- <![CDATA[<code>JobClient</code> is the primary interface for the user-job to interact
- with the {@link JobTracker}.
-
- <code>JobClient</code> provides facilities to submit jobs, track their
- progress, access component-tasks' reports/logs, get the Map-Reduce cluster
- status information etc.
-
- <p>The job submission process involves:
- <ol>
- <li>
- Checking the input and output specifications of the job.
- </li>
- <li>
- Computing the {@link InputSplit}s for the job.
- </li>
- <li>
- Setup the requisite accounting information for the {@link DistributedCache}
- of the job, if necessary.
- </li>
- <li>
- Copying the job's jar and configuration to the map-reduce system directory
- on the distributed file-system.
- </li>
- <li>
- Submitting the job to the <code>JobTracker</code> and optionally monitoring
- it's status.
- </li>
- </ol></p>
-
- Normally the user creates the application, describes various facets of the
- job via {@link JobConf} and then uses the <code>JobClient</code> to submit
- the job and monitor its progress.
-
- <p>Here is an example on how to use <code>JobClient</code>:</p>
- <p><blockquote><pre>
- // Create a new JobConf
- JobConf job = new JobConf(new Configuration(), MyJob.class);
-
- // Specify various job-specific parameters
- job.setJobName("myjob");
-
- job.setInputPath(new Path("in"));
- job.setOutputPath(new Path("out"));
-
- job.setMapperClass(MyJob.MyMapper.class);
- job.setReducerClass(MyJob.MyReducer.class);
- // Submit the job, then poll for progress until the job is complete
- JobClient.runJob(job);
- </pre></blockquote></p>
-
- <h4 id="JobControl">Job Control</h4>
-
- <p>At times clients would chain map-reduce jobs to accomplish complex tasks
- which cannot be done via a single map-reduce job. This is fairly easy since
- the output of the job, typically, goes to distributed file-system and that
- can be used as the input for the next job.</p>
-
- <p>However, this also means that the onus on ensuring jobs are complete
- (success/failure) lies squarely on the clients. In such situations the
- various job-control options are:
- <ol>
- <li>
- {@link #runJob(JobConf)} : submits the job and returns only after
- the job has completed.
- </li>
- <li>
- {@link #submitJob(JobConf)} : only submits the job, then poll the
- returned handle to the {@link RunningJob} to query status and make
- scheduling decisions.
- </li>
- <li>
- {@link JobConf#setJobEndNotificationURI(String)} : setup a notification
- on job-completion, thus avoiding polling.
- </li>
- </ol></p>
-
- @see JobConf
- @see ClusterStatus
- @see Tool
- @see DistributedCache
- @deprecated Use {@link Job} and {@link Cluster} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.JobClient -->
- <!-- start class org.apache.hadoop.mapred.JobClient.TaskStatusFilter -->
- <class name="JobClient.TaskStatusFilter" extends="java.lang.Enum"
- abstract="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <method name="values" return="org.apache.hadoop.mapred.JobClient.TaskStatusFilter[]"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="valueOf" return="org.apache.hadoop.mapred.JobClient.TaskStatusFilter"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- </method>
- </class>
- <!-- end class org.apache.hadoop.mapred.JobClient.TaskStatusFilter -->
- <!-- start class org.apache.hadoop.mapred.JobConf -->
- <class name="JobConf" extends="org.apache.hadoop.conf.Configuration"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link Configuration} instead">
- <constructor name="JobConf"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Construct a map/reduce job configuration.]]>
- </doc>
- </constructor>
- <constructor name="JobConf" type="java.lang.Class"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Construct a map/reduce job configuration.
-
- @param exampleClass a class whose containing jar is used as the job's jar.]]>
- </doc>
- </constructor>
- <constructor name="JobConf" type="org.apache.hadoop.conf.Configuration"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Construct a map/reduce job configuration.
-
- @param conf a Configuration whose settings will be inherited.]]>
- </doc>
- </constructor>
- <constructor name="JobConf" type="org.apache.hadoop.conf.Configuration, java.lang.Class"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Construct a map/reduce job configuration.
-
- @param conf a Configuration whose settings will be inherited.
- @param exampleClass a class whose containing jar is used as the job's jar.]]>
- </doc>
- </constructor>
- <constructor name="JobConf" type="java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Construct a map/reduce configuration.
- @param config a Configuration-format XML job description file.]]>
- </doc>
- </constructor>
- <constructor name="JobConf" type="org.apache.hadoop.fs.Path"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Construct a map/reduce configuration.
- @param config a Configuration-format XML job description file.]]>
- </doc>
- </constructor>
- <constructor name="JobConf" type="boolean"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[A new map/reduce configuration where the behavior of reading from the
- default resources can be turned off.
- <p/>
- If the parameter {@code loadDefaults} is false, the new instance
- will not load resources from the default files.
- @param loadDefaults specifies whether to load from the default files]]>
- </doc>
- </constructor>
- <method name="getCredentials" return="org.apache.hadoop.security.Credentials"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get credentials for the job.
- @return credentials for the job]]>
- </doc>
- </method>
- <method name="getJar" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the user jar for the map-reduce job.
-
- @return the user jar for the map-reduce job.]]>
- </doc>
- </method>
- <method name="setJar"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jar" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the user jar for the map-reduce job.
-
- @param jar the user jar for the map-reduce job.]]>
- </doc>
- </method>
- <method name="getJarUnpackPattern" return="java.util.regex.Pattern"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the pattern for jar contents to unpack on the tasktracker]]>
- </doc>
- </method>
- <method name="setJarByClass"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="cls" type="java.lang.Class"/>
- <doc>
- <![CDATA[Set the job's jar file by finding an example class location.
-
- @param cls the example class.]]>
- </doc>
- </method>
- <method name="getLocalDirs" return="java.lang.String[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="deleteLocalFiles"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Use MRAsyncDiskService.moveAndDeleteAllVolumes instead.
- @see org.apache.hadoop.mapreduce.util.MRAsyncDiskService#cleanupAllVolumes()]]>
- </doc>
- </method>
- <method name="deleteLocalFiles"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="subdir" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getLocalPath" return="org.apache.hadoop.fs.Path"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="pathString" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Constructs a local file name. Files are distributed among configured
- local directories.]]>
- </doc>
- </method>
- <method name="getUser" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the reported username for this job.
-
- @return the username]]>
- </doc>
- </method>
- <method name="setUser"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="user" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the reported username for this job.
-
- @param user the username for this job.]]>
- </doc>
- </method>
- <method name="setKeepFailedTaskFiles"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="keep" type="boolean"/>
- <doc>
- <![CDATA[Set whether the framework should keep the intermediate files for
- failed tasks.
-
- @param keep <code>true</code> if framework should keep the intermediate files
- for failed tasks, <code>false</code> otherwise.]]>
- </doc>
- </method>
- <method name="getKeepFailedTaskFiles" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Should the temporary files for failed tasks be kept?
-
- @return should the files be kept?]]>
- </doc>
- </method>
- <method name="setKeepTaskFilesPattern"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="pattern" type="java.lang.String"/>
- <doc>
- <![CDATA[Set a regular expression for task names that should be kept.
- The regular expression ".*_m_000123_0" would keep the files
- for the first instance of map 123 that ran.
-
- @param pattern the java.util.regex.Pattern to match against the
- task names.]]>
- </doc>
- </method>
- <method name="getKeepTaskFilesPattern" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the regular expression that is matched against the task names
- to see if we need to keep the files.
-
- @return the pattern as a string, if it was set, othewise null.]]>
- </doc>
- </method>
- <method name="setWorkingDirectory"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="dir" type="org.apache.hadoop.fs.Path"/>
- <doc>
- <![CDATA[Set the current working directory for the default file system.
-
- @param dir the new current working directory.]]>
- </doc>
- </method>
- <method name="getWorkingDirectory" return="org.apache.hadoop.fs.Path"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the current working directory for the default file system.
-
- @return the directory name.]]>
- </doc>
- </method>
- <method name="setNumTasksToExecutePerJvm"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="numTasks" type="int"/>
- <doc>
- <![CDATA[Sets the number of tasks that a spawned task JVM should run
- before it exits
- @param numTasks the number of tasks to execute; defaults to 1;
- -1 signifies no limit]]>
- </doc>
- </method>
- <method name="getNumTasksToExecutePerJvm" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the number of tasks that a spawned JVM should execute]]>
- </doc>
- </method>
- <method name="getInputFormat" return="org.apache.hadoop.mapred.InputFormat"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the {@link InputFormat} implementation for the map-reduce job,
- defaults to {@link TextInputFormat} if not specified explicity.
-
- @return the {@link InputFormat} implementation for the map-reduce job.]]>
- </doc>
- </method>
- <method name="setInputFormat"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="theClass" type="java.lang.Class"/>
- <doc>
- <![CDATA[Set the {@link InputFormat} implementation for the map-reduce job.
-
- @param theClass the {@link InputFormat} implementation for the map-reduce
- job.]]>
- </doc>
- </method>
- <method name="getOutputFormat" return="org.apache.hadoop.mapred.OutputFormat"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the {@link OutputFormat} implementation for the map-reduce job,
- defaults to {@link TextOutputFormat} if not specified explicity.
-
- @return the {@link OutputFormat} implementation for the map-reduce job.]]>
- </doc>
- </method>
- <method name="getOutputCommitter" return="org.apache.hadoop.mapred.OutputCommitter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the {@link OutputCommitter} implementation for the map-reduce job,
- defaults to {@link FileOutputCommitter} if not specified explicitly.
-
- @return the {@link OutputCommitter} implementation for the map-reduce job.]]>
- </doc>
- </method>
- <method name="setOutputCommitter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="theClass" type="java.lang.Class"/>
- <doc>
- <![CDATA[Set the {@link OutputCommitter} implementation for the map-reduce job.
-
- @param theClass the {@link OutputCommitter} implementation for the map-reduce
- job.]]>
- </doc>
- </method>
- <method name="setOutputFormat"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="theClass" type="java.lang.Class"/>
- <doc>
- <![CDATA[Set the {@link OutputFormat} implementation for the map-reduce job.
-
- @param theClass the {@link OutputFormat} implementation for the map-reduce
- job.]]>
- </doc>
- </method>
- <method name="setCompressMapOutput"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="compress" type="boolean"/>
- <doc>
- <![CDATA[Should the map outputs be compressed before transfer?
- Uses the SequenceFile compression.
-
- @param compress should the map outputs be compressed?]]>
- </doc>
- </method>
- <method name="getCompressMapOutput" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Are the outputs of the maps be compressed?
-
- @return <code>true</code> if the outputs of the maps are to be compressed,
- <code>false</code> otherwise.]]>
- </doc>
- </method>
- <method name="setMapOutputCompressorClass"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="codecClass" type="java.lang.Class"/>
- <doc>
- <![CDATA[Set the given class as the {@link CompressionCodec} for the map outputs.
-
- @param codecClass the {@link CompressionCodec} class that will compress
- the map outputs.]]>
- </doc>
- </method>
- <method name="getMapOutputCompressorClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="defaultValue" type="java.lang.Class"/>
- <doc>
- <![CDATA[Get the {@link CompressionCodec} for compressing the map outputs.
-
- @param defaultValue the {@link CompressionCodec} to return if not set
- @return the {@link CompressionCodec} class that should be used to compress the
- map outputs.
- @throws IllegalArgumentException if the class was specified, but not found]]>
- </doc>
- </method>
- <method name="getMapOutputKeyClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the key class for the map output data. If it is not set, use the
- (final) output key class. This allows the map output key class to be
- different than the final output key class.
-
- @return the map output key class.]]>
- </doc>
- </method>
- <method name="setMapOutputKeyClass"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="theClass" type="java.lang.Class"/>
- <doc>
- <![CDATA[Set the key class for the map output data. This allows the user to
- specify the map output key class to be different than the final output
- value class.
-
- @param theClass the map output key class.]]>
- </doc>
- </method>
- <method name="getMapOutputValueClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the value class for the map output data. If it is not set, use the
- (final) output value class This allows the map output value class to be
- different than the final output value class.
-
- @return the map output value class.]]>
- </doc>
- </method>
- <method name="setMapOutputValueClass"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="theClass" type="java.lang.Class"/>
- <doc>
- <![CDATA[Set the value class for the map output data. This allows the user to
- specify the map output value class to be different than the final output
- value class.
-
- @param theClass the map output value class.]]>
- </doc>
- </method>
- <method name="getOutputKeyClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the key class for the job output data.
-
- @return the key class for the job output data.]]>
- </doc>
- </method>
- <method name="setOutputKeyClass"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="theClass" type="java.lang.Class"/>
- <doc>
- <![CDATA[Set the key class for the job output data.
-
- @param theClass the key class for the job output data.]]>
- </doc>
- </method>
- <method name="getOutputKeyComparator" return="org.apache.hadoop.io.RawComparator"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the {@link RawComparator} comparator used to compare keys.
-
- @return the {@link RawComparator} comparator used to compare keys.]]>
- </doc>
- </method>
- <method name="setOutputKeyComparatorClass"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="theClass" type="java.lang.Class"/>
- <doc>
- <![CDATA[Set the {@link RawComparator} comparator used to compare keys.
-
- @param theClass the {@link RawComparator} comparator used to
- compare keys.
- @see #setOutputValueGroupingComparator(Class)]]>
- </doc>
- </method>
- <method name="setKeyFieldComparatorOptions"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="keySpec" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the {@link KeyFieldBasedComparator} options used to compare keys.
-
- @param keySpec the key specification of the form -k pos1[,pos2], where,
- pos is of the form f[.c][opts], where f is the number
- of the key field to use, and c is the number of the first character from
- the beginning of the field. Fields and character posns are numbered
- starting with 1; a character position of zero in pos2 indicates the
- field's last character. If '.c' is omitted from pos1, it defaults to 1
- (the beginning of the field); if omitted from pos2, it defaults to 0
- (the end of the field). opts are ordering options. The supported options
- are:
- -n, (Sort numerically)
- -r, (Reverse the result of comparison)]]>
- </doc>
- </method>
- <method name="getKeyFieldComparatorOption" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the {@link KeyFieldBasedComparator} options]]>
- </doc>
- </method>
- <method name="setKeyFieldPartitionerOptions"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="keySpec" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the {@link KeyFieldBasedPartitioner} options used for
- {@link Partitioner}
-
- @param keySpec the key specification of the form -k pos1[,pos2], where,
- pos is of the form f[.c][opts], where f is the number
- of the key field to use, and c is the number of the first character from
- the beginning of the field. Fields and character posns are numbered
- starting with 1; a character position of zero in pos2 indicates the
- field's last character. If '.c' is omitted from pos1, it defaults to 1
- (the beginning of the field); if omitted from pos2, it defaults to 0
- (the end of the field).]]>
- </doc>
- </method>
- <method name="getKeyFieldPartitionerOption" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the {@link KeyFieldBasedPartitioner} options]]>
- </doc>
- </method>
- <method name="getOutputValueGroupingComparator" return="org.apache.hadoop.io.RawComparator"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the user defined {@link WritableComparable} comparator for
- grouping keys of inputs to the reduce.
-
- @return comparator set by the user for grouping values.
- @see #setOutputValueGroupingComparator(Class) for details.]]>
- </doc>
- </method>
- <method name="setOutputValueGroupingComparator"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="theClass" type="java.lang.Class"/>
- <doc>
- <![CDATA[Set the user defined {@link RawComparator} comparator for
- grouping keys in the input to the reduce.
-
- <p>This comparator should be provided if the equivalence rules for keys
- for sorting the intermediates are different from those for grouping keys
- before each call to
- {@link Reducer#reduce(Object, java.util.Iterator, OutputCollector, Reporter)}.</p>
-
- <p>For key-value pairs (K1,V1) and (K2,V2), the values (V1, V2) are passed
- in a single call to the reduce function if K1 and K2 compare as equal.</p>
-
- <p>Since {@link #setOutputKeyComparatorClass(Class)} can be used to control
- how keys are sorted, this can be used in conjunction to simulate
- <i>secondary sort on values</i>.</p>
-
- <p><i>Note</i>: This is not a guarantee of the reduce sort being
- <i>stable</i> in any sense. (In any case, with the order of available
- map-outputs to the reduce being non-deterministic, it wouldn't make
- that much sense.)</p>
-
- @param theClass the comparator class to be used for grouping keys.
- It should implement <code>RawComparator</code>.
- @see #setOutputKeyComparatorClass(Class)]]>
- </doc>
- </method>
- <method name="getUseNewMapper" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Should the framework use the new context-object code for running
- the mapper?
- @return true, if the new api should be used]]>
- </doc>
- </method>
- <method name="setUseNewMapper"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="flag" type="boolean"/>
- <doc>
- <![CDATA[Set whether the framework should use the new api for the mapper.
- This is the default for jobs submitted with the new Job api.
- @param flag true, if the new api should be used]]>
- </doc>
- </method>
- <method name="getUseNewReducer" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Should the framework use the new context-object code for running
- the reducer?
- @return true, if the new api should be used]]>
- </doc>
- </method>
- <method name="setUseNewReducer"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="flag" type="boolean"/>
- <doc>
- <![CDATA[Set whether the framework should use the new api for the reducer.
- This is the default for jobs submitted with the new Job api.
- @param flag true, if the new api should be used]]>
- </doc>
- </method>
- <method name="getOutputValueClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the value class for job outputs.
-
- @return the value class for job outputs.]]>
- </doc>
- </method>
- <method name="setOutputValueClass"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="theClass" type="java.lang.Class"/>
- <doc>
- <![CDATA[Set the value class for job outputs.
-
- @param theClass the value class for job outputs.]]>
- </doc>
- </method>
- <method name="getMapperClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the {@link Mapper} class for the job.
-
- @return the {@link Mapper} class for the job.]]>
- </doc>
- </method>
- <method name="setMapperClass"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="theClass" type="java.lang.Class"/>
- <doc>
- <![CDATA[Set the {@link Mapper} class for the job.
-
- @param theClass the {@link Mapper} class for the job.]]>
- </doc>
- </method>
- <method name="getMapRunnerClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the {@link MapRunnable} class for the job.
-
- @return the {@link MapRunnable} class for the job.]]>
- </doc>
- </method>
- <method name="setMapRunnerClass"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="theClass" type="java.lang.Class"/>
- <doc>
- <![CDATA[Expert: Set the {@link MapRunnable} class for the job.
-
- Typically used to exert greater control on {@link Mapper}s.
-
- @param theClass the {@link MapRunnable} class for the job.]]>
- </doc>
- </method>
- <method name="getPartitionerClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the {@link Partitioner} used to partition {@link Mapper}-outputs
- to be sent to the {@link Reducer}s.
-
- @return the {@link Partitioner} used to partition map-outputs.]]>
- </doc>
- </method>
- <method name="setPartitionerClass"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="theClass" type="java.lang.Class"/>
- <doc>
- <![CDATA[Set the {@link Partitioner} class used to partition
- {@link Mapper}-outputs to be sent to the {@link Reducer}s.
-
- @param theClass the {@link Partitioner} used to partition map-outputs.]]>
- </doc>
- </method>
- <method name="getReducerClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the {@link Reducer} class for the job.
-
- @return the {@link Reducer} class for the job.]]>
- </doc>
- </method>
- <method name="setReducerClass"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="theClass" type="java.lang.Class"/>
- <doc>
- <![CDATA[Set the {@link Reducer} class for the job.
-
- @param theClass the {@link Reducer} class for the job.]]>
- </doc>
- </method>
- <method name="getCombinerClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the user-defined <i>combiner</i> class used to combine map-outputs
- before being sent to the reducers. Typically the combiner is same as the
- the {@link Reducer} for the job i.e. {@link #getReducerClass()}.
-
- @return the user-defined combiner class used to combine map-outputs.]]>
- </doc>
- </method>
- <method name="setCombinerClass"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="theClass" type="java.lang.Class"/>
- <doc>
- <![CDATA[Set the user-defined <i>combiner</i> class used to combine map-outputs
- before being sent to the reducers.
-
- <p>The combiner is an application-specified aggregation operation, which
- can help cut down the amount of data transferred between the
- {@link Mapper} and the {@link Reducer}, leading to better performance.</p>
-
- <p>The framework may invoke the combiner 0, 1, or multiple times, in both
- the mapper and reducer tasks. In general, the combiner is called as the
- sort/merge result is written to disk. The combiner must:
- <ul>
- <li> be side-effect free</li>
- <li> have the same input and output key types and the same input and
- output value types</li>
- </ul></p>
-
- <p>Typically the combiner is same as the <code>Reducer</code> for the
- job i.e. {@link #setReducerClass(Class)}.</p>
-
- @param theClass the user-defined combiner class used to combine
- map-outputs.]]>
- </doc>
- </method>
- <method name="getSpeculativeExecution" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Should speculative execution be used for this job?
- Defaults to <code>true</code>.
-
- @return <code>true</code> if speculative execution be used for this job,
- <code>false</code> otherwise.]]>
- </doc>
- </method>
- <method name="setSpeculativeExecution"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="speculativeExecution" type="boolean"/>
- <doc>
- <![CDATA[Turn speculative execution on or off for this job.
-
- @param speculativeExecution <code>true</code> if speculative execution
- should be turned on, else <code>false</code>.]]>
- </doc>
- </method>
- <method name="getMapSpeculativeExecution" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Should speculative execution be used for this job for map tasks?
- Defaults to <code>true</code>.
-
- @return <code>true</code> if speculative execution be
- used for this job for map tasks,
- <code>false</code> otherwise.]]>
- </doc>
- </method>
- <method name="setMapSpeculativeExecution"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="speculativeExecution" type="boolean"/>
- <doc>
- <![CDATA[Turn speculative execution on or off for this job for map tasks.
-
- @param speculativeExecution <code>true</code> if speculative execution
- should be turned on for map tasks,
- else <code>false</code>.]]>
- </doc>
- </method>
- <method name="getReduceSpeculativeExecution" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Should speculative execution be used for this job for reduce tasks?
- Defaults to <code>true</code>.
-
- @return <code>true</code> if speculative execution be used
- for reduce tasks for this job,
- <code>false</code> otherwise.]]>
- </doc>
- </method>
- <method name="setReduceSpeculativeExecution"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="speculativeExecution" type="boolean"/>
- <doc>
- <![CDATA[Turn speculative execution on or off for this job for reduce tasks.
-
- @param speculativeExecution <code>true</code> if speculative execution
- should be turned on for reduce tasks,
- else <code>false</code>.]]>
- </doc>
- </method>
- <method name="getNumMapTasks" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get configured the number of reduce tasks for this job.
- Defaults to <code>1</code>.
-
- @return the number of reduce tasks for this job.]]>
- </doc>
- </method>
- <method name="setNumMapTasks"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="n" type="int"/>
- <doc>
- <![CDATA[Set the number of map tasks for this job.
-
- <p><i>Note</i>: This is only a <i>hint</i> to the framework. The actual
- number of spawned map tasks depends on the number of {@link InputSplit}s
- generated by the job's {@link InputFormat#getSplits(JobConf, int)}.
-
- A custom {@link InputFormat} is typically used to accurately control
- the number of map tasks for the job.</p>
-
- <h4 id="NoOfMaps">How many maps?</h4>
-
- <p>The number of maps is usually driven by the total size of the inputs
- i.e. total number of blocks of the input files.</p>
-
- <p>The right level of parallelism for maps seems to be around 10-100 maps
- per-node, although it has been set up to 300 or so for very cpu-light map
- tasks. Task setup takes awhile, so it is best if the maps take at least a
- minute to execute.</p>
-
- <p>The default behavior of file-based {@link InputFormat}s is to split the
- input into <i>logical</i> {@link InputSplit}s based on the total size, in
- bytes, of input files. However, the {@link FileSystem} blocksize of the
- input files is treated as an upper bound for input splits. A lower bound
- on the split size can be set via
- <a href="{@docRoot}/../mapred-default.html#mapreduce.input.fileinputformat.split.minsize">
- mapreduce.input.fileinputformat.split.minsize</a>.</p>
-
- <p>Thus, if you expect 10TB of input data and have a blocksize of 128MB,
- you'll end up with 82,000 maps, unless {@link #setNumMapTasks(int)} is
- used to set it even higher.</p>
-
- @param n the number of map tasks for this job.
- @see InputFormat#getSplits(JobConf, int)
- @see FileInputFormat
- @see FileSystem#getDefaultBlockSize()
- @see FileStatus#getBlockSize()]]>
- </doc>
- </method>
- <method name="getNumReduceTasks" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get configured the number of reduce tasks for this job. Defaults to
- <code>1</code>.
-
- @return the number of reduce tasks for this job.]]>
- </doc>
- </method>
- <method name="setNumReduceTasks"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="n" type="int"/>
- <doc>
- <![CDATA[Set the requisite number of reduce tasks for this job.
-
- <h4 id="NoOfReduces">How many reduces?</h4>
-
- <p>The right number of reduces seems to be <code>0.95</code> or
- <code>1.75</code> multiplied by (<<i>no. of nodes</i>> *
- <a href="{@docRoot}/../mapred-default.html#mapreduce.tasktracker.reduce.tasks.maximum">
- mapreduce.tasktracker.reduce.tasks.maximum</a>).
- </p>
-
- <p>With <code>0.95</code> all of the reduces can launch immediately and
- start transfering map outputs as the maps finish. With <code>1.75</code>
- the faster nodes will finish their first round of reduces and launch a
- second wave of reduces doing a much better job of load balancing.</p>
-
- <p>Increasing the number of reduces increases the framework overhead, but
- increases load balancing and lowers the cost of failures.</p>
-
- <p>The scaling factors above are slightly less than whole numbers to
- reserve a few reduce slots in the framework for speculative-tasks, failures
- etc.</p>
- <h4 id="ReducerNone">Reducer NONE</h4>
-
- <p>It is legal to set the number of reduce-tasks to <code>zero</code>.</p>
-
- <p>In this case the output of the map-tasks directly go to distributed
- file-system, to the path set by
- {@link FileOutputFormat#setOutputPath(JobConf, Path)}. Also, the
- framework doesn't sort the map-outputs before writing it out to HDFS.</p>
-
- @param n the number of reduce tasks for this job.]]>
- </doc>
- </method>
- <method name="getMaxMapAttempts" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the configured number of maximum attempts that will be made to run a
- map task, as specified by the <code>mapreduce.map.maxattempts</code>
- property. If this property is not already set, the default is 4 attempts.
-
- @return the max number of attempts per map task.]]>
- </doc>
- </method>
- <method name="setMaxMapAttempts"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="n" type="int"/>
- <doc>
- <![CDATA[Expert: Set the number of maximum attempts that will be made to run a
- map task.
-
- @param n the number of attempts per map task.]]>
- </doc>
- </method>
- <method name="getMaxReduceAttempts" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the configured number of maximum attempts that will be made to run a
- reduce task, as specified by the <code>mapreduce.reduce.maxattempts</code>
- property. If this property is not already set, the default is 4 attempts.
-
- @return the max number of attempts per reduce task.]]>
- </doc>
- </method>
- <method name="setMaxReduceAttempts"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="n" type="int"/>
- <doc>
- <![CDATA[Expert: Set the number of maximum attempts that will be made to run a
- reduce task.
-
- @param n the number of attempts per reduce task.]]>
- </doc>
- </method>
- <method name="getJobName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the user-specified job name. This is only used to identify the
- job to the user.
-
- @return the job's name, defaulting to "".]]>
- </doc>
- </method>
- <method name="setJobName"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the user-specified job name.
-
- @param name the job's new name.]]>
- </doc>
- </method>
- <method name="getSessionId" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the user-specified session identifier. The default is the empty string.
- The session identifier is used to tag metric data that is reported to some
- performance metrics system via the org.apache.hadoop.metrics API. The
- session identifier is intended, in particular, for use by Hadoop-On-Demand
- (HOD) which allocates a virtual Hadoop cluster dynamically and transiently.
- HOD will set the session identifier by modifying the mapred-site.xml file
- before starting the cluster.
- When not running under HOD, this identifer is expected to remain set to
- the empty string.
- @return the session identifier, defaulting to "".]]>
- </doc>
- </method>
- <method name="setSessionId"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="sessionId" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the user-specified session identifier.
- @param sessionId the new session id.]]>
- </doc>
- </method>
- <method name="setMaxTaskFailuresPerTracker"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="noFailures" type="int"/>
- <doc>
- <![CDATA[Set the maximum no. of failures of a given job per tasktracker.
- If the no. of task failures exceeds <code>noFailures</code>, the
- tasktracker is <i>blacklisted</i> for this job.
-
- @param noFailures maximum no. of failures of a given job per tasktracker.]]>
- </doc>
- </method>
- <method name="getMaxTaskFailuresPerTracker" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Expert: Get the maximum no. of failures of a given job per tasktracker.
- If the no. of task failures exceeds this, the tasktracker is
- <i>blacklisted</i> for this job.
-
- @return the maximum no. of failures of a given job per tasktracker.]]>
- </doc>
- </method>
- <method name="getMaxMapTaskFailuresPercent" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the maximum percentage of map tasks that can fail without
- the job being aborted.
-
- Each map task is executed a minimum of {@link #getMaxMapAttempts()}
- attempts before being declared as <i>failed</i>.
-
- Defaults to <code>zero</code>, i.e. <i>any</i> failed map-task results in
- the job being declared as {@link JobStatus#FAILED}.
-
- @return the maximum percentage of map tasks that can fail without
- the job being aborted.]]>
- </doc>
- </method>
- <method name="setMaxMapTaskFailuresPercent"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="percent" type="int"/>
- <doc>
- <![CDATA[Expert: Set the maximum percentage of map tasks that can fail without the
- job being aborted.
-
- Each map task is executed a minimum of {@link #getMaxMapAttempts} attempts
- before being declared as <i>failed</i>.
-
- @param percent the maximum percentage of map tasks that can fail without
- the job being aborted.]]>
- </doc>
- </method>
- <method name="getMaxReduceTaskFailuresPercent" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the maximum percentage of reduce tasks that can fail without
- the job being aborted.
-
- Each reduce task is executed a minimum of {@link #getMaxReduceAttempts()}
- attempts before being declared as <i>failed</i>.
-
- Defaults to <code>zero</code>, i.e. <i>any</i> failed reduce-task results
- in the job being declared as {@link JobStatus#FAILED}.
-
- @return the maximum percentage of reduce tasks that can fail without
- the job being aborted.]]>
- </doc>
- </method>
- <method name="setMaxReduceTaskFailuresPercent"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="percent" type="int"/>
- <doc>
- <![CDATA[Set the maximum percentage of reduce tasks that can fail without the job
- being aborted.
-
- Each reduce task is executed a minimum of {@link #getMaxReduceAttempts()}
- attempts before being declared as <i>failed</i>.
-
- @param percent the maximum percentage of reduce tasks that can fail without
- the job being aborted.]]>
- </doc>
- </method>
- <method name="setJobPriority"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="prio" type="org.apache.hadoop.mapred.JobPriority"/>
- <doc>
- <![CDATA[Set {@link JobPriority} for this job.
-
- @param prio the {@link JobPriority} for this job.]]>
- </doc>
- </method>
- <method name="getJobPriority" return="org.apache.hadoop.mapred.JobPriority"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the {@link JobPriority} for this job.
-
- @return the {@link JobPriority} for this job.]]>
- </doc>
- </method>
- <method name="getProfileEnabled" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get whether the task profiling is enabled.
- @return true if some tasks will be profiled]]>
- </doc>
- </method>
- <method name="setProfileEnabled"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="newValue" type="boolean"/>
- <doc>
- <![CDATA[Set whether the system should collect profiler information for some of
- the tasks in this job? The information is stored in the user log
- directory.
- @param newValue true means it should be gathered]]>
- </doc>
- </method>
- <method name="getProfileParams" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the profiler configuration arguments.
- The default value for this property is
- "-agentlib:hprof=cpu=samples,heap=sites,force=n,thread=y,verbose=n,file=%s"
-
- @return the parameters to pass to the task child to configure profiling]]>
- </doc>
- </method>
- <method name="setProfileParams"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="value" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the profiler configuration arguments. If the string contains a '%s' it
- will be replaced with the name of the profiling output file when the task
- runs.
- This value is passed to the task child JVM on the command line.
- @param value the configuration string]]>
- </doc>
- </method>
- <method name="getProfileTaskRange" return="org.apache.hadoop.conf.Configuration.IntegerRanges"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="isMap" type="boolean"/>
- <doc>
- <![CDATA[Get the range of maps or reduces to profile.
- @param isMap is the task a map?
- @return the task ranges]]>
- </doc>
- </method>
- <method name="setProfileTaskRange"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="isMap" type="boolean"/>
- <param name="newValue" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the ranges of maps or reduces to profile. setProfileEnabled(true)
- must also be called.
- @param newValue a set of integer ranges of the map ids]]>
- </doc>
- </method>
- <method name="setMapDebugScript"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="mDbgScript" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the debug script to run when the map tasks fail.
-
- <p>The debug script can aid debugging of failed map tasks. The script is
- given task's stdout, stderr, syslog, jobconf files as arguments.</p>
-
- <p>The debug command, run on the node where the map failed, is:</p>
- <p><pre><blockquote>
- $script $stdout $stderr $syslog $jobconf.
- </blockquote></pre></p>
-
- <p> The script file is distributed through {@link DistributedCache}
- APIs. The script needs to be symlinked. </p>
-
- <p>Here is an example on how to submit a script
- <p><blockquote><pre>
- job.setMapDebugScript("./myscript");
- DistributedCache.createSymlink(job);
- DistributedCache.addCacheFile("/debug/scripts/myscript#myscript");
- </pre></blockquote></p>
-
- @param mDbgScript the script name]]>
- </doc>
- </method>
- <method name="getMapDebugScript" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the map task's debug script.
-
- @return the debug Script for the mapred job for failed map tasks.
- @see #setMapDebugScript(String)]]>
- </doc>
- </method>
- <method name="setReduceDebugScript"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="rDbgScript" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the debug script to run when the reduce tasks fail.
-
- <p>The debug script can aid debugging of failed reduce tasks. The script
- is given task's stdout, stderr, syslog, jobconf files as arguments.</p>
-
- <p>The debug command, run on the node where the map failed, is:</p>
- <p><pre><blockquote>
- $script $stdout $stderr $syslog $jobconf.
- </blockquote></pre></p>
-
- <p> The script file is distributed through {@link DistributedCache}
- APIs. The script file needs to be symlinked </p>
-
- <p>Here is an example on how to submit a script
- <p><blockquote><pre>
- job.setReduceDebugScript("./myscript");
- DistributedCache.createSymlink(job);
- DistributedCache.addCacheFile("/debug/scripts/myscript#myscript");
- </pre></blockquote></p>
-
- @param rDbgScript the script name]]>
- </doc>
- </method>
- <method name="getReduceDebugScript" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the reduce task's debug Script
-
- @return the debug script for the mapred job for failed reduce tasks.
- @see #setReduceDebugScript(String)]]>
- </doc>
- </method>
- <method name="getJobEndNotificationURI" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the uri to be invoked in-order to send a notification after the job
- has completed (success/failure).
-
- @return the job end notification uri, <code>null</code> if it hasn't
- been set.
- @see #setJobEndNotificationURI(String)]]>
- </doc>
- </method>
- <method name="setJobEndNotificationURI"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="uri" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the uri to be invoked in-order to send a notification after the job
- has completed (success/failure).
-
- <p>The uri can contain 2 special parameters: <tt>$jobId</tt> and
- <tt>$jobStatus</tt>. Those, if present, are replaced by the job's
- identifier and completion-status respectively.</p>
-
- <p>This is typically used by application-writers to implement chaining of
- Map-Reduce jobs in an <i>asynchronous manner</i>.</p>
-
- @param uri the job end notification uri
- @see JobStatus
- @see <a href="{@docRoot}/org/apache/hadoop/mapred/JobClient.html#
- JobCompletionAndChaining">Job Completion and Chaining</a>]]>
- </doc>
- </method>
- <method name="getJobLocalDir" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get job-specific shared directory for use as scratch space
-
- <p>
- When a job starts, a shared directory is created at location
- <code>
- ${mapreduce.cluster.local.dir}/taskTracker/$user/jobcache/$jobid/work/ </code>.
- This directory is exposed to the users through
- <code>mapreduce.job.local.dir </code>.
- So, the tasks can use this space
- as scratch space and share files among them. </p>
- This value is available as System property also.
-
- @return The localized job specific shared directory]]>
- </doc>
- </method>
- <method name="getMemoryForMapTask" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get memory required to run a map task of the job, in MB.
-
- If a value is specified in the configuration, it is returned.
- Else, it returns {@link #DISABLED_MEMORY_LIMIT}.
- <p/>
- For backward compatibility, if the job configuration sets the
- key {@link #MAPRED_TASK_MAXVMEM_PROPERTY} to a value different
- from {@link #DISABLED_MEMORY_LIMIT}, that value will be used
- after converting it from bytes to MB.
- @return memory required to run a map task of the job, in MB,
- or {@link #DISABLED_MEMORY_LIMIT} if unset.]]>
- </doc>
- </method>
- <method name="setMemoryForMapTask"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="mem" type="long"/>
- </method>
- <method name="getMemoryForReduceTask" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get memory required to run a reduce task of the job, in MB.
-
- If a value is specified in the configuration, it is returned.
- Else, it returns {@link #DISABLED_MEMORY_LIMIT}.
- <p/>
- For backward compatibility, if the job configuration sets the
- key {@link #MAPRED_TASK_MAXVMEM_PROPERTY} to a value different
- from {@link #DISABLED_MEMORY_LIMIT}, that value will be used
- after converting it from bytes to MB.
- @return memory required to run a reduce task of the job, in MB,
- or {@link #DISABLED_MEMORY_LIMIT} if unset.]]>
- </doc>
- </method>
- <method name="setMemoryForReduceTask"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="mem" type="long"/>
- </method>
- <method name="getQueueName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Return the name of the queue to which this job is submitted.
- Defaults to 'default'.
-
- @return name of the queue]]>
- </doc>
- </method>
- <method name="setQueueName"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="queueName" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the name of the queue to which this job should be submitted.
-
- @param queueName Name of the queue]]>
- </doc>
- </method>
- <method name="normalizeMemoryConfigValue" return="long"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="val" type="long"/>
- <doc>
- <![CDATA[Normalize the negative values in configuration
-
- @param val
- @return normalized value]]>
- </doc>
- </method>
- <method name="getMaxVirtualMemoryForTask" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link #getMemoryForMapTask()} and
- {@link #getMemoryForReduceTask()}">
- <doc>
- <![CDATA[Get the memory required to run a task of this job, in bytes. See
- {@link #MAPRED_TASK_MAXVMEM_PROPERTY}
- <p/>
- This method is deprecated. Now, different memory limits can be
- set for map and reduce tasks of a job, in MB.
- <p/>
- For backward compatibility, if the job configuration sets the
- key {@link #MAPRED_TASK_MAXVMEM_PROPERTY} to a value different
- from {@link #DISABLED_MEMORY_LIMIT}, that value is returned.
- Otherwise, this method will return the larger of the values returned by
- {@link #getMemoryForMapTask()} and {@link #getMemoryForReduceTask()}
- after converting them into bytes.
- @return Memory required to run a task of this job, in bytes,
- or {@link #DISABLED_MEMORY_LIMIT}, if unset.
- @see #setMaxVirtualMemoryForTask(long)
- @deprecated Use {@link #getMemoryForMapTask()} and
- {@link #getMemoryForReduceTask()}]]>
- </doc>
- </method>
- <method name="setMaxVirtualMemoryForTask"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link #setMemoryForMapTask(long mem)} and
- Use {@link #setMemoryForReduceTask(long mem)}">
- <param name="vmem" type="long"/>
- <doc>
- <![CDATA[Set the maximum amount of memory any task of this job can use. See
- {@link #MAPRED_TASK_MAXVMEM_PROPERTY}
- <p/>
- mapred.task.maxvmem is split into
- mapreduce.map.memory.mb
- and mapreduce.map.memory.mb,mapred
- each of the new key are set
- as mapred.task.maxvmem / 1024
- as new values are in MB
- @param vmem Maximum amount of virtual memory in bytes any task of this job
- can use.
- @see #getMaxVirtualMemoryForTask()
- @deprecated
- Use {@link #setMemoryForMapTask(long mem)} and
- Use {@link #setMemoryForReduceTask(long mem)}]]>
- </doc>
- </method>
- <method name="getMaxPhysicalMemoryForTask" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="this variable is deprecated and nolonger in use.">
- <doc>
- <![CDATA[@deprecated this variable is deprecated and nolonger in use.]]>
- </doc>
- </method>
- <method name="setMaxPhysicalMemoryForTask"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="mem" type="long"/>
- </method>
- <field name="MAPRED_TASK_MAXVMEM_PROPERTY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="Use {@link #MAPRED_JOB_MAP_MEMORY_MB_PROPERTY} and
- {@link #MAPRED_JOB_REDUCE_MEMORY_MB_PROPERTY}">
- <doc>
- <![CDATA[@deprecated Use {@link #MAPRED_JOB_MAP_MEMORY_MB_PROPERTY} and
- {@link #MAPRED_JOB_REDUCE_MEMORY_MB_PROPERTY}]]>
- </doc>
- </field>
- <field name="UPPER_LIMIT_ON_TASK_VMEM_PROPERTY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="deprecated, no comment">
- <doc>
- <![CDATA[@deprecated]]>
- </doc>
- </field>
- <field name="MAPRED_TASK_DEFAULT_MAXVMEM_PROPERTY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="deprecated, no comment">
- <doc>
- <![CDATA[@deprecated]]>
- </doc>
- </field>
- <field name="MAPRED_TASK_MAXPMEM_PROPERTY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="deprecated, no comment">
- <doc>
- <![CDATA[@deprecated]]>
- </doc>
- </field>
- <field name="DISABLED_MEMORY_LIMIT" type="long"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[A value which if set for memory related configuration options,
- indicates that the options are turned off.]]>
- </doc>
- </field>
- <field name="MAPRED_LOCAL_DIR_PROPERTY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Property name for the configuration property mapreduce.cluster.local.dir]]>
- </doc>
- </field>
- <field name="DEFAULT_QUEUE_NAME" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Name of the queue to which jobs will be submitted, if no queue
- name is mentioned.]]>
- </doc>
- </field>
- <field name="UNPACK_JAR_PATTERN_DEFAULT" type="java.util.regex.Pattern"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Pattern for the default unpacking behavior for job jars]]>
- </doc>
- </field>
- <field name="MAPRED_TASK_JAVA_OPTS" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="Use {@link #MAPRED_MAP_TASK_JAVA_OPTS} or
- {@link #MAPRED_REDUCE_TASK_JAVA_OPTS}">
- <doc>
- <![CDATA[Configuration key to set the java command line options for the child
- map and reduce tasks.
-
- Java opts for the task tracker child processes.
- The following symbol, if present, will be interpolated: @taskid@.
- It is replaced by current TaskID. Any other occurrences of '@' will go
- unchanged.
- For example, to enable verbose gc logging to a file named for the taskid in
- /tmp and to set the heap maximum to be a gigabyte, pass a 'value' of:
- -Xmx1024m -verbose:gc -Xloggc:/tmp/@taskid@.gc
-
- The configuration variable {@link #MAPRED_TASK_ULIMIT} can be used to
- control the maximum virtual memory of the child processes.
-
- The configuration variable {@link #MAPRED_TASK_ENV} can be used to pass
- other environment variables to the child processes.
-
- @deprecated Use {@link #MAPRED_MAP_TASK_JAVA_OPTS} or
- {@link #MAPRED_REDUCE_TASK_JAVA_OPTS}]]>
- </doc>
- </field>
- <field name="MAPRED_MAP_TASK_JAVA_OPTS" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Configuration key to set the java command line options for the map tasks.
-
- Java opts for the task tracker child map processes.
- The following symbol, if present, will be interpolated: @taskid@.
- It is replaced by current TaskID. Any other occurrences of '@' will go
- unchanged.
- For example, to enable verbose gc logging to a file named for the taskid in
- /tmp and to set the heap maximum to be a gigabyte, pass a 'value' of:
- -Xmx1024m -verbose:gc -Xloggc:/tmp/@taskid@.gc
-
- The configuration variable {@link #MAPRED_MAP_TASK_ULIMIT} can be used to
- control the maximum virtual memory of the map processes.
-
- The configuration variable {@link #MAPRED_MAP_TASK_ENV} can be used to pass
- other environment variables to the map processes.]]>
- </doc>
- </field>
- <field name="MAPRED_REDUCE_TASK_JAVA_OPTS" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Configuration key to set the java command line options for the reduce tasks.
-
- Java opts for the task tracker child reduce processes.
- The following symbol, if present, will be interpolated: @taskid@.
- It is replaced by current TaskID. Any other occurrences of '@' will go
- unchanged.
- For example, to enable verbose gc logging to a file named for the taskid in
- /tmp and to set the heap maximum to be a gigabyte, pass a 'value' of:
- -Xmx1024m -verbose:gc -Xloggc:/tmp/@taskid@.gc
-
- The configuration variable {@link #MAPRED_REDUCE_TASK_ULIMIT} can be used
- to control the maximum virtual memory of the reduce processes.
-
- The configuration variable {@link #MAPRED_REDUCE_TASK_ENV} can be used to
- pass process environment variables to the reduce processes.]]>
- </doc>
- </field>
- <field name="DEFAULT_MAPRED_TASK_JAVA_OPTS" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="MAPRED_TASK_ULIMIT" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="Use {@link #MAPRED_MAP_TASK_ULIMIT} or
- {@link #MAPRED_REDUCE_TASK_ULIMIT}">
- <doc>
- <![CDATA[Configuration key to set the maximum virutal memory available to the child
- map and reduce tasks (in kilo-bytes).
-
- Note: This must be greater than or equal to the -Xmx passed to the JavaVM
- via {@link #MAPRED_TASK_JAVA_OPTS}, else the VM might not start.
-
- @deprecated Use {@link #MAPRED_MAP_TASK_ULIMIT} or
- {@link #MAPRED_REDUCE_TASK_ULIMIT}]]>
- </doc>
- </field>
- <field name="MAPRED_MAP_TASK_ULIMIT" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Configuration key to set the maximum virutal memory available to the
- map tasks (in kilo-bytes).
-
- Note: This must be greater than or equal to the -Xmx passed to the JavaVM
- via {@link #MAPRED_MAP_TASK_JAVA_OPTS}, else the VM might not start.]]>
- </doc>
- </field>
- <field name="MAPRED_REDUCE_TASK_ULIMIT" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Configuration key to set the maximum virutal memory available to the
- reduce tasks (in kilo-bytes).
-
- Note: This must be greater than or equal to the -Xmx passed to the JavaVM
- via {@link #MAPRED_REDUCE_TASK_JAVA_OPTS}, else the VM might not start.]]>
- </doc>
- </field>
- <field name="MAPRED_TASK_ENV" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="Use {@link #MAPRED_MAP_TASK_ENV} or
- {@link #MAPRED_REDUCE_TASK_ENV}">
- <doc>
- <![CDATA[Configuration key to set the environment of the child map/reduce tasks.
-
- The format of the value is <code>k1=v1,k2=v2</code>. Further it can
- reference existing environment variables via <code>$key</code>.
-
- Example:
- <ul>
- <li> A=foo - This will set the env variable A to foo. </li>
- <li> B=$X:c This is inherit tasktracker's X env variable. </li>
- </ul>
-
- @deprecated Use {@link #MAPRED_MAP_TASK_ENV} or
- {@link #MAPRED_REDUCE_TASK_ENV}]]>
- </doc>
- </field>
- <field name="MAPRED_MAP_TASK_ENV" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Configuration key to set the maximum virutal memory available to the
- map tasks.
-
- The format of the value is <code>k1=v1,k2=v2</code>. Further it can
- reference existing environment variables via <code>$key</code>.
-
- Example:
- <ul>
- <li> A=foo - This will set the env variable A to foo. </li>
- <li> B=$X:c This is inherit tasktracker's X env variable. </li>
- </ul>]]>
- </doc>
- </field>
- <field name="MAPRED_REDUCE_TASK_ENV" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Configuration key to set the maximum virutal memory available to the
- reduce tasks.
-
- The format of the value is <code>k1=v1,k2=v2</code>. Further it can
- reference existing environment variables via <code>$key</code>.
-
- Example:
- <ul>
- <li> A=foo - This will set the env variable A to foo. </li>
- <li> B=$X:c This is inherit tasktracker's X env variable. </li>
- </ul>]]>
- </doc>
- </field>
- <field name="MAPRED_MAP_TASK_LOG_LEVEL" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Configuration key to set the logging {@link Level} for the map task.
- The allowed logging levels are:
- OFF, FATAL, ERROR, WARN, INFO, DEBUG, TRACE and ALL.]]>
- </doc>
- </field>
- <field name="MAPRED_REDUCE_TASK_LOG_LEVEL" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Configuration key to set the logging {@link Level} for the reduce task.
- The allowed logging levels are:
- OFF, FATAL, ERROR, WARN, INFO, DEBUG, TRACE and ALL.]]>
- </doc>
- </field>
- <field name="DEFAULT_LOG_LEVEL" type="org.apache.log4j.Level"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Default logging level for map/reduce tasks.]]>
- </doc>
- </field>
- <doc>
- <![CDATA[A map/reduce job configuration.
-
- <p><code>JobConf</code> is the primary interface for a user to describe a
- map-reduce job to the Hadoop framework for execution. The framework tries to
- faithfully execute the job as-is described by <code>JobConf</code>, however:
- <ol>
- <li>
- Some configuration parameters might have been marked as
- <a href="{@docRoot}/org/apache/hadoop/conf/Configuration.html#FinalParams">
- final</a> by administrators and hence cannot be altered.
- </li>
- <li>
- While some job parameters are straight-forward to set
- (e.g. {@link #setNumReduceTasks(int)}), some parameters interact subtly
- rest of the framework and/or job-configuration and is relatively more
- complex for the user to control finely (e.g. {@link #setNumMapTasks(int)}).
- </li>
- </ol></p>
-
- <p><code>JobConf</code> typically specifies the {@link Mapper}, combiner
- (if any), {@link Partitioner}, {@link Reducer}, {@link InputFormat} and
- {@link OutputFormat} implementations to be used etc.
- <p>Optionally <code>JobConf</code> is used to specify other advanced facets
- of the job such as <code>Comparator</code>s to be used, files to be put in
- the {@link DistributedCache}, whether or not intermediate and/or job outputs
- are to be compressed (and how), debugability via user-provided scripts
- ( {@link #setMapDebugScript(String)}/{@link #setReduceDebugScript(String)}),
- for doing post-processing on task logs, task's stdout, stderr, syslog.
- and etc.</p>
-
- <p>Here is an example on how to configure a job via <code>JobConf</code>:</p>
- <p><blockquote><pre>
- // Create a new JobConf
- JobConf job = new JobConf(new Configuration(), MyJob.class);
-
- // Specify various job-specific parameters
- job.setJobName("myjob");
-
- FileInputFormat.setInputPaths(job, new Path("in"));
- FileOutputFormat.setOutputPath(job, new Path("out"));
-
- job.setMapperClass(MyJob.MyMapper.class);
- job.setCombinerClass(MyJob.MyReducer.class);
- job.setReducerClass(MyJob.MyReducer.class);
-
- job.setInputFormat(SequenceFileInputFormat.class);
- job.setOutputFormat(SequenceFileOutputFormat.class);
- </pre></blockquote></p>
-
- @see JobClient
- @see ClusterStatus
- @see Tool
- @see DistributedCache
- @deprecated Use {@link Configuration} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.JobConf -->
- <!-- start interface org.apache.hadoop.mapred.JobConfigurable -->
- <interface name="JobConfigurable" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <method name="configure"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[Initializes a new instance from a {@link JobConf}.
- @param job the configuration]]>
- </doc>
- </method>
- <doc>
- <![CDATA[That what may be configured.]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.JobConfigurable -->
- <!-- start interface org.apache.hadoop.mapred.JobContext -->
- <interface name="JobContext" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.JobContext} instead.">
- <implements name="org.apache.hadoop.mapreduce.JobContext"/>
- <method name="getJobConf" return="org.apache.hadoop.mapred.JobConf"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the job Configuration
-
- @return JobConf]]>
- </doc>
- </method>
- <method name="getProgressible" return="org.apache.hadoop.util.Progressable"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the progress mechanism for reporting progress.
-
- @return progress mechanism]]>
- </doc>
- </method>
- <doc>
- <![CDATA[@deprecated Use {@link org.apache.hadoop.mapreduce.JobContext} instead.]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.JobContext -->
- <!-- start class org.apache.hadoop.mapred.JobID -->
- <class name="JobID" extends="org.apache.hadoop.mapreduce.JobID"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="JobID" type="java.lang.String, int"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Constructs a JobID object
- @param jtIdentifier jobTracker identifier
- @param id job number]]>
- </doc>
- </constructor>
- <constructor name="JobID"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="downgrade" return="org.apache.hadoop.mapred.JobID"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="old" type="org.apache.hadoop.mapreduce.JobID"/>
- <doc>
- <![CDATA[Downgrade a new JobID to an old one
- @param old a new or old JobID
- @return either old or a new JobID build to match old]]>
- </doc>
- </method>
- <method name="read" return="org.apache.hadoop.mapred.JobID"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="in" type="java.io.DataInput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="forName" return="org.apache.hadoop.mapred.JobID"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="str" type="java.lang.String"/>
- <exception name="IllegalArgumentException" type="java.lang.IllegalArgumentException"/>
- <doc>
- <![CDATA[Construct a JobId object from given string
- @return constructed JobId object or null if the given String is null
- @throws IllegalArgumentException if the given string is malformed]]>
- </doc>
- </method>
- <method name="getJobIDsPattern" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jtIdentifier" type="java.lang.String"/>
- <param name="jobId" type="java.lang.Integer"/>
- <doc>
- <![CDATA[Returns a regex pattern which matches task IDs. Arguments can
- be given null, in which case that part of the regex will be generic.
- For example to obtain a regex matching <i>any job</i>
- run on the jobtracker started at <i>200707121733</i>, we would use :
- <pre>
- JobID.getTaskIDsPattern("200707121733", null);
- </pre>
- which will return :
- <pre> "job_200707121733_[0-9]*" </pre>
- @param jtIdentifier jobTracker identifier, or null
- @param jobId job number, or null
- @return a regex pattern matching JobIDs]]>
- </doc>
- </method>
- <doc>
- <![CDATA[JobID represents the immutable and unique identifier for
- the job. JobID consists of two parts. First part
- represents the jobtracker identifier, so that jobID to jobtracker map
- is defined. For cluster setup this string is the jobtracker
- start time, for local setting, it is "local".
- Second part of the JobID is the job number. <br>
- An example JobID is :
- <code>job_200707121733_0003</code> , which represents the third job
- running at the jobtracker started at <code>200707121733</code>.
- <p>
- Applications should never construct or parse JobID strings, but rather
- use appropriate constructors or {@link #forName(String)} method.
-
- @see TaskID
- @see TaskAttemptID]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.JobID -->
- <!-- start class org.apache.hadoop.mapred.JobPriority -->
- <class name="JobPriority" extends="java.lang.Enum"
- abstract="false"
- static="false" final="true" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.JobPriority} instead">
- <method name="values" return="org.apache.hadoop.mapred.JobPriority[]"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="valueOf" return="org.apache.hadoop.mapred.JobPriority"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- </method>
- <doc>
- <![CDATA[Used to describe the priority of the running job.
- @deprecated Use {@link org.apache.hadoop.mapreduce.JobPriority} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.JobPriority -->
- <!-- start class org.apache.hadoop.mapred.JobQueueInfo -->
- <class name="JobQueueInfo" extends="org.apache.hadoop.mapreduce.QueueInfo"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link QueueInfo} instead">
- <constructor name="JobQueueInfo"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Default constructor for Job Queue Info.]]>
- </doc>
- </constructor>
- <constructor name="JobQueueInfo" type="java.lang.String, java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Construct a new JobQueueInfo object using the queue name and the
- scheduling information passed.
-
- @param queueName Name of the job queue
- @param schedulingInfo Scheduling Information associated with the job
- queue]]>
- </doc>
- </constructor>
- <method name="setQueueName"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="queueName" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the queue name of the JobQueueInfo
-
- @param queueName Name of the job queue.]]>
- </doc>
- </method>
- <method name="setSchedulingInfo"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="schedulingInfo" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the scheduling information associated to particular job queue
-
- @param schedulingInfo]]>
- </doc>
- </method>
- <method name="setQueueState"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="state" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the state of the queue
- @param state state of the queue.]]>
- </doc>
- </method>
- <method name="setChildren"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="children" type="java.util.List"/>
- </method>
- <method name="getChildren" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="setProperties"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="props" type="java.util.Properties"/>
- </method>
- <method name="setJobStatuses"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="stats" type="org.apache.hadoop.mapreduce.JobStatus[]"/>
- </method>
- <doc>
- <![CDATA[Class that contains the information regarding the Job Queues which are
- maintained by the Hadoop Map/Reduce framework.
- @deprecated Use {@link QueueInfo} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.JobQueueInfo -->
- <!-- start class org.apache.hadoop.mapred.JobStatus -->
- <class name="JobStatus" extends="org.apache.hadoop.mapreduce.JobStatus"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.JobStatus} instead">
- <constructor name="JobStatus"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <constructor name="JobStatus" type="org.apache.hadoop.mapred.JobID, float, float, float, int, java.lang.String, java.lang.String, java.lang.String, java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Create a job status object for a given jobid.
- @param jobid The jobid of the job
- @param mapProgress The progress made on the maps
- @param reduceProgress The progress made on the reduces
- @param cleanupProgress The progress made on cleanup
- @param runState The current state of the job
- @param user userid of the person who submitted the job.
- @param jobName user-specified job name.
- @param jobFile job configuration file.
- @param trackingUrl link to the web-ui for details of the job.]]>
- </doc>
- </constructor>
- <constructor name="JobStatus" type="org.apache.hadoop.mapred.JobID, float, float, int, java.lang.String, java.lang.String, java.lang.String, java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Create a job status object for a given jobid.
- @param jobid The jobid of the job
- @param mapProgress The progress made on the maps
- @param reduceProgress The progress made on the reduces
- @param runState The current state of the job
- @param user userid of the person who submitted the job.
- @param jobName user-specified job name.
- @param jobFile job configuration file.
- @param trackingUrl link to the web-ui for details of the job.]]>
- </doc>
- </constructor>
- <constructor name="JobStatus" type="org.apache.hadoop.mapred.JobID, float, float, float, int, org.apache.hadoop.mapred.JobPriority, java.lang.String, java.lang.String, java.lang.String, java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Create a job status object for a given jobid.
- @param jobid The jobid of the job
- @param mapProgress The progress made on the maps
- @param reduceProgress The progress made on the reduces
- @param runState The current state of the job
- @param jp Priority of the job.
- @param user userid of the person who submitted the job.
- @param jobName user-specified job name.
- @param jobFile job configuration file.
- @param trackingUrl link to the web-ui for details of the job.]]>
- </doc>
- </constructor>
- <constructor name="JobStatus" type="org.apache.hadoop.mapred.JobID, float, float, float, float, int, org.apache.hadoop.mapred.JobPriority, java.lang.String, java.lang.String, java.lang.String, java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Create a job status object for a given jobid.
- @param jobid The jobid of the job
- @param setupProgress The progress made on the setup
- @param mapProgress The progress made on the maps
- @param reduceProgress The progress made on the reduces
- @param cleanupProgress The progress made on the cleanup
- @param runState The current state of the job
- @param jp Priority of the job.
- @param user userid of the person who submitted the job.
- @param jobName user-specified job name.
- @param jobFile job configuration file.
- @param trackingUrl link to the web-ui for details of the job.]]>
- </doc>
- </constructor>
- <method name="getJobRunState" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="state" type="int"/>
- <doc>
- <![CDATA[Helper method to get human-readable state of the job.
- @param state job state
- @return human-readable state of the job]]>
- </doc>
- </method>
- <method name="downgrade" return="org.apache.hadoop.mapred.JobStatus"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="stat" type="org.apache.hadoop.mapreduce.JobStatus"/>
- </method>
- <method name="getJobId" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="use getJobID instead">
- <doc>
- <![CDATA[@deprecated use getJobID instead]]>
- </doc>
- </method>
- <method name="getJobID" return="org.apache.hadoop.mapred.JobID"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return The jobid of the Job]]>
- </doc>
- </method>
- <method name="getJobPriority" return="org.apache.hadoop.mapred.JobPriority"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Return the priority of the job
- @return job priority]]>
- </doc>
- </method>
- <method name="setMapProgress"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="p" type="float"/>
- <doc>
- <![CDATA[Sets the map progress of this job
- @param p The value of map progress to set to]]>
- </doc>
- </method>
- <method name="setCleanupProgress"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="p" type="float"/>
- <doc>
- <![CDATA[Sets the cleanup progress of this job
- @param p The value of cleanup progress to set to]]>
- </doc>
- </method>
- <method name="setSetupProgress"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="p" type="float"/>
- <doc>
- <![CDATA[Sets the setup progress of this job
- @param p The value of setup progress to set to]]>
- </doc>
- </method>
- <method name="setReduceProgress"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="p" type="float"/>
- <doc>
- <![CDATA[Sets the reduce progress of this Job
- @param p The value of reduce progress to set to]]>
- </doc>
- </method>
- <method name="setFinishTime"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="finishTime" type="long"/>
- <doc>
- <![CDATA[Set the finish time of the job
- @param finishTime The finishTime of the job]]>
- </doc>
- </method>
- <method name="setHistoryFile"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="historyFile" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the job history file url for a completed job]]>
- </doc>
- </method>
- <method name="setTrackingUrl"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="trackingUrl" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the link to the web-ui for details of the job.]]>
- </doc>
- </method>
- <method name="setRetired"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Set the job retire flag to true.]]>
- </doc>
- </method>
- <method name="setRunState"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="state" type="int"/>
- <doc>
- <![CDATA[Change the current run state of the job.]]>
- </doc>
- </method>
- <method name="getRunState" return="int"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return running state of the job]]>
- </doc>
- </method>
- <method name="setStartTime"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="startTime" type="long"/>
- <doc>
- <![CDATA[Set the start time of the job
- @param startTime The startTime of the job]]>
- </doc>
- </method>
- <method name="setUsername"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="userName" type="java.lang.String"/>
- <doc>
- <![CDATA[@param userName The username of the job]]>
- </doc>
- </method>
- <method name="setSchedulingInfo"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="schedulingInfo" type="java.lang.String"/>
- <doc>
- <![CDATA[Used to set the scheduling information associated to a particular Job.
-
- @param schedulingInfo Scheduling information of the job]]>
- </doc>
- </method>
- <method name="setJobACLs"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="acls" type="java.util.Map"/>
- </method>
- <method name="setJobPriority"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jp" type="org.apache.hadoop.mapred.JobPriority"/>
- <doc>
- <![CDATA[Set the priority of the job, defaulting to NORMAL.
- @param jp new job priority]]>
- </doc>
- </method>
- <method name="mapProgress" return="float"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return Percentage of progress in maps]]>
- </doc>
- </method>
- <method name="cleanupProgress" return="float"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return Percentage of progress in cleanup]]>
- </doc>
- </method>
- <method name="setupProgress" return="float"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return Percentage of progress in setup]]>
- </doc>
- </method>
- <method name="reduceProgress" return="float"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return Percentage of progress in reduce]]>
- </doc>
- </method>
- <field name="RUNNING" type="int"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="SUCCEEDED" type="int"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="FAILED" type="int"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="PREP" type="int"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="KILLED" type="int"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[Describes the current status of a job. This is
- not intended to be a comprehensive piece of data.
- For that, look at JobProfile.
- @deprecated Use {@link org.apache.hadoop.mapreduce.JobStatus} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.JobStatus -->
- <!-- start class org.apache.hadoop.mapred.KeyValueLineRecordReader -->
- <class name="KeyValueLineRecordReader" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.input.KeyValueLineRecordReader}
- instead">
- <implements name="org.apache.hadoop.mapred.RecordReader"/>
- <constructor name="KeyValueLineRecordReader" type="org.apache.hadoop.conf.Configuration, org.apache.hadoop.mapred.FileSplit"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </constructor>
- <method name="getKeyClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="createKey" return="org.apache.hadoop.io.Text"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="createValue" return="org.apache.hadoop.io.Text"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="findSeparator" return="int"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="utf" type="byte[]"/>
- <param name="start" type="int"/>
- <param name="length" type="int"/>
- <param name="sep" type="byte"/>
- </method>
- <method name="next" return="boolean"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="org.apache.hadoop.io.Text"/>
- <param name="value" type="org.apache.hadoop.io.Text"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Read key/value pair in a line.]]>
- </doc>
- </method>
- <method name="getProgress" return="float"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getPos" return="long"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[This class treats a line in the input as a key/value pair separated by a
- separator character. The separator can be specified in config file
- under the attribute name mapreduce.input.keyvaluelinerecordreader.key.value.separator. The default
- separator is the tab character ('\t').
-
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.input.KeyValueLineRecordReader}
- instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.KeyValueLineRecordReader -->
- <!-- start class org.apache.hadoop.mapred.KeyValueTextInputFormat -->
- <class name="KeyValueTextInputFormat" extends="org.apache.hadoop.mapred.FileInputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.input.KeyValueTextInputFormat}
- instead">
- <implements name="org.apache.hadoop.mapred.JobConfigurable"/>
- <constructor name="KeyValueTextInputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="configure"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- </method>
- <method name="isSplitable" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="fs" type="org.apache.hadoop.fs.FileSystem"/>
- <param name="file" type="org.apache.hadoop.fs.Path"/>
- </method>
- <method name="getRecordReader" return="org.apache.hadoop.mapred.RecordReader"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="genericSplit" type="org.apache.hadoop.mapred.InputSplit"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[An {@link InputFormat} for plain text files. Files are broken into lines.
- Either linefeed or carriage-return are used to signal end of line. Each line
- is divided into key and value parts by a separator byte. If no such a byte
- exists, the key will be the entire line and value will be empty.
-
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.input.KeyValueTextInputFormat}
- instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.KeyValueTextInputFormat -->
- <!-- start class org.apache.hadoop.mapred.LineRecordReader.LineReader -->
- <class name="LineRecordReader.LineReader" extends="org.apache.hadoop.util.LineReader"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.util.LineReader} instead.">
- <constructor name="LineRecordReader.LineReader" type="java.io.InputStream, org.apache.hadoop.conf.Configuration"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </constructor>
- <doc>
- <![CDATA[A class that provides a line reader from an input stream.
- @deprecated Use {@link org.apache.hadoop.util.LineReader} instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.LineRecordReader.LineReader -->
- <!-- start class org.apache.hadoop.mapred.MapFileOutputFormat -->
- <class name="MapFileOutputFormat" extends="org.apache.hadoop.mapred.FileOutputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.output.MapFileOutputFormat} instead">
- <constructor name="MapFileOutputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getRecordWriter" return="org.apache.hadoop.mapred.RecordWriter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="name" type="java.lang.String"/>
- <param name="progress" type="org.apache.hadoop.util.Progressable"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getReaders" return="org.apache.hadoop.io.MapFile.Reader[]"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/>
- <param name="dir" type="org.apache.hadoop.fs.Path"/>
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Open the output generated by this format.]]>
- </doc>
- </method>
- <method name="getEntry" return="org.apache.hadoop.io.Writable"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="readers" type="org.apache.hadoop.io.MapFile.Reader[]"/>
- <param name="partitioner" type="org.apache.hadoop.mapred.Partitioner"/>
- <param name="key" type="K"/>
- <param name="value" type="V"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get an entry from output generated by this class.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[An {@link OutputFormat} that writes {@link MapFile}s.
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.output.MapFileOutputFormat} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.MapFileOutputFormat -->
- <!-- start interface org.apache.hadoop.mapred.Mapper -->
- <interface name="Mapper" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.Mapper} instead.">
- <implements name="org.apache.hadoop.mapred.JobConfigurable"/>
- <implements name="org.apache.hadoop.io.Closeable"/>
- <method name="map"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K1"/>
- <param name="value" type="V1"/>
- <param name="output" type="org.apache.hadoop.mapred.OutputCollector"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Maps a single input key/value pair into an intermediate key/value pair.
-
- <p>Output pairs need not be of the same types as input pairs. A given
- input pair may map to zero or many output pairs. Output pairs are
- collected with calls to
- {@link OutputCollector#collect(Object,Object)}.</p>
- <p>Applications can use the {@link Reporter} provided to report progress
- or just indicate that they are alive. In scenarios where the application
- takes an insignificant amount of time to process individual key/value
- pairs, this is crucial since the framework might assume that the task has
- timed-out and kill that task. The other way of avoiding this is to set
- <a href="{@docRoot}/../mapred-default.html#mapreduce.task.timeout">
- mapreduce.task.timeout</a> to a high-enough value (or even zero for no
- time-outs).</p>
-
- @param key the input key.
- @param value the input value.
- @param output collects mapped keys and values.
- @param reporter facility to report progress.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Maps input key/value pairs to a set of intermediate key/value pairs.
-
- <p>Maps are the individual tasks which transform input records into a
- intermediate records. The transformed intermediate records need not be of
- the same type as the input records. A given input pair may map to zero or
- many output pairs.</p>
-
- <p>The Hadoop Map-Reduce framework spawns one map task for each
- {@link InputSplit} generated by the {@link InputFormat} for the job.
- <code>Mapper</code> implementations can access the {@link JobConf} for the
- job via the {@link JobConfigurable#configure(JobConf)} and initialize
- themselves. Similarly they can use the {@link Closeable#close()} method for
- de-initialization.</p>
-
- <p>The framework then calls
- {@link #map(Object, Object, OutputCollector, Reporter)}
- for each key/value pair in the <code>InputSplit</code> for that task.</p>
-
- <p>All intermediate values associated with a given output key are
- subsequently grouped by the framework, and passed to a {@link Reducer} to
- determine the final output. Users can control the grouping by specifying
- a <code>Comparator</code> via
- {@link JobConf#setOutputKeyComparatorClass(Class)}.</p>
- <p>The grouped <code>Mapper</code> outputs are partitioned per
- <code>Reducer</code>. Users can control which keys (and hence records) go to
- which <code>Reducer</code> by implementing a custom {@link Partitioner}.
-
- <p>Users can optionally specify a <code>combiner</code>, via
- {@link JobConf#setCombinerClass(Class)}, to perform local aggregation of the
- intermediate outputs, which helps to cut down the amount of data transferred
- from the <code>Mapper</code> to the <code>Reducer</code>.
-
- <p>The intermediate, grouped outputs are always stored in
- {@link SequenceFile}s. Applications can specify if and how the intermediate
- outputs are to be compressed and which {@link CompressionCodec}s are to be
- used via the <code>JobConf</code>.</p>
-
- <p>If the job has
- <a href="{@docRoot}/org/apache/hadoop/mapred/JobConf.html#ReducerNone">zero
- reduces</a> then the output of the <code>Mapper</code> is directly written
- to the {@link FileSystem} without grouping by keys.</p>
-
- <p>Example:</p>
- <p><blockquote><pre>
- public class MyMapper<K extends WritableComparable, V extends Writable>
- extends MapReduceBase implements Mapper<K, V, K, V> {
-
- static enum MyCounters { NUM_RECORDS }
-
- private String mapTaskId;
- private String inputFile;
- private int noRecords = 0;
-
- public void configure(JobConf job) {
- mapTaskId = job.get(JobContext.TASK_ATTEMPT_ID);
- inputFile = job.get(JobContext.MAP_INPUT_FILE);
- }
-
- public void map(K key, V val,
- OutputCollector<K, V> output, Reporter reporter)
- throws IOException {
- // Process the <key, value> pair (assume this takes a while)
- // ...
- // ...
-
- // Let the framework know that we are alive, and kicking!
- // reporter.progress();
-
- // Process some more
- // ...
- // ...
-
- // Increment the no. of <key, value> pairs processed
- ++noRecords;
- // Increment counters
- reporter.incrCounter(NUM_RECORDS, 1);
-
- // Every 100 records update application-level status
- if ((noRecords%100) == 0) {
- reporter.setStatus(mapTaskId + " processed " + noRecords +
- " from input-file: " + inputFile);
- }
-
- // Output the result
- output.collect(key, val);
- }
- }
- </pre></blockquote></p>
- <p>Applications may write a custom {@link MapRunnable} to exert greater
- control on map processing e.g. multi-threaded <code>Mapper</code>s etc.</p>
-
- @see JobConf
- @see InputFormat
- @see Partitioner
- @see Reducer
- @see MapReduceBase
- @see MapRunnable
- @see SequenceFile
- @deprecated Use {@link org.apache.hadoop.mapreduce.Mapper} instead.]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.Mapper -->
- <!-- start class org.apache.hadoop.mapred.MapReduceBase -->
- <class name="MapReduceBase" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.io.Closeable"/>
- <implements name="org.apache.hadoop.mapred.JobConfigurable"/>
- <constructor name="MapReduceBase"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Default implementation that does nothing.]]>
- </doc>
- </method>
- <method name="configure"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[Default implementation that does nothing.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Base class for {@link Mapper} and {@link Reducer} implementations.
-
- <p>Provides default no-op implementations for a few methods, most non-trivial
- applications need to override some of them.</p>]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.MapReduceBase -->
- <!-- start interface org.apache.hadoop.mapred.MapRunnable -->
- <interface name="MapRunnable" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.Mapper} instead.">
- <implements name="org.apache.hadoop.mapred.JobConfigurable"/>
- <method name="run"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="input" type="org.apache.hadoop.mapred.RecordReader"/>
- <param name="output" type="org.apache.hadoop.mapred.OutputCollector"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Start mapping input <tt><key, value></tt> pairs.
-
- <p>Mapping of input records to output records is complete when this method
- returns.</p>
-
- @param input the {@link RecordReader} to read the input records.
- @param output the {@link OutputCollector} to collect the outputrecords.
- @param reporter {@link Reporter} to report progress, status-updates etc.
- @throws IOException]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Expert: Generic interface for {@link Mapper}s.
-
- <p>Custom implementations of <code>MapRunnable</code> can exert greater
- control on map processing e.g. multi-threaded, asynchronous mappers etc.</p>
-
- @see Mapper
- @deprecated Use {@link org.apache.hadoop.mapreduce.Mapper} instead.]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.MapRunnable -->
- <!-- start class org.apache.hadoop.mapred.MapRunner -->
- <class name="MapRunner" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapred.MapRunnable"/>
- <constructor name="MapRunner"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="configure"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- </method>
- <method name="run"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="input" type="org.apache.hadoop.mapred.RecordReader"/>
- <param name="output" type="org.apache.hadoop.mapred.OutputCollector"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getMapper" return="org.apache.hadoop.mapred.Mapper"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </method>
- <doc>
- <![CDATA[Default {@link MapRunnable} implementation.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.MapRunner -->
- <!-- start class org.apache.hadoop.mapred.MultiFileInputFormat -->
- <class name="MultiFileInputFormat" extends="org.apache.hadoop.mapred.FileInputFormat"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapred.lib.CombineFileInputFormat} instead">
- <constructor name="MultiFileInputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getSplits" return="org.apache.hadoop.mapred.InputSplit[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="numSplits" type="int"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getRecordReader" return="org.apache.hadoop.mapred.RecordReader"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapred.InputSplit"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[An abstract {@link InputFormat} that returns {@link MultiFileSplit}'s
- in {@link #getSplits(JobConf, int)} method. Splits are constructed from
- the files under the input paths. Each split returned contains <i>nearly</i>
- equal content length. <br>
- Subclasses implement {@link #getRecordReader(InputSplit, JobConf, Reporter)}
- to construct <code>RecordReader</code>'s for <code>MultiFileSplit</code>'s.
- @see MultiFileSplit
- @deprecated Use {@link org.apache.hadoop.mapred.lib.CombineFileInputFormat} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.MultiFileInputFormat -->
- <!-- start class org.apache.hadoop.mapred.MultiFileSplit -->
- <class name="MultiFileSplit" extends="org.apache.hadoop.mapred.lib.CombineFileSplit"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapred.lib.CombineFileSplit} instead">
- <constructor name="MultiFileSplit" type="org.apache.hadoop.mapred.JobConf, org.apache.hadoop.fs.Path[], long[]"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getLocations" return="java.lang.String[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="toString" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <doc>
- <![CDATA[A sub-collection of input files. Unlike {@link FileSplit}, MultiFileSplit
- class does not represent a split of a file, but a split of input files
- into smaller sets. The atomic unit of split is a file. <br>
- MultiFileSplit can be used to implement {@link RecordReader}'s, with
- reading one record per file.
- @see FileSplit
- @see MultiFileInputFormat
- @deprecated Use {@link org.apache.hadoop.mapred.lib.CombineFileSplit} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.MultiFileSplit -->
- <!-- start interface org.apache.hadoop.mapred.OutputCollector -->
- <interface name="OutputCollector" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <method name="collect"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <param name="value" type="V"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Adds a key/value pair to the output.
- @param key the key to collect.
- @param value to value to collect.
- @throws IOException]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Collects the <code><key, value></code> pairs output by {@link Mapper}s
- and {@link Reducer}s.
-
- <p><code>OutputCollector</code> is the generalization of the facility
- provided by the Map-Reduce framework to collect data output by either the
- <code>Mapper</code> or the <code>Reducer</code> i.e. intermediate outputs
- or the output of the job.</p>]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.OutputCollector -->
- <!-- start class org.apache.hadoop.mapred.OutputCommitter -->
- <class name="OutputCommitter" extends="org.apache.hadoop.mapreduce.OutputCommitter"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.OutputCommitter} instead.">
- <constructor name="OutputCommitter"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setupJob"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobContext" type="org.apache.hadoop.mapred.JobContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[For the framework to setup the job output during initialization
-
- @param jobContext Context of the job whose output is being written.
- @throws IOException if temporary output could not be created]]>
- </doc>
- </method>
- <method name="cleanupJob"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link #commitJob(JobContext)} or
- {@link #abortJob(JobContext, int)} instead.">
- <param name="jobContext" type="org.apache.hadoop.mapred.JobContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[For cleaning up the job's output after job completion
-
- @param jobContext Context of the job whose output is being written.
- @throws IOException
- @deprecated Use {@link #commitJob(JobContext)} or
- {@link #abortJob(JobContext, int)} instead.]]>
- </doc>
- </method>
- <method name="commitJob"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobContext" type="org.apache.hadoop.mapred.JobContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[For committing job's output after successful job completion. Note that this
- is invoked for jobs with final runstate as SUCCESSFUL.
-
- @param jobContext Context of the job whose output is being written.
- @throws IOException]]>
- </doc>
- </method>
- <method name="abortJob"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobContext" type="org.apache.hadoop.mapred.JobContext"/>
- <param name="status" type="int"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[For aborting an unsuccessful job's output. Note that this is invoked for
- jobs with final runstate as {@link JobStatus#FAILED} or
- {@link JobStatus#KILLED}
-
- @param jobContext Context of the job whose output is being written.
- @param status final runstate of the job
- @throws IOException]]>
- </doc>
- </method>
- <method name="setupTask"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskContext" type="org.apache.hadoop.mapred.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Sets up output for the task.
-
- @param taskContext Context of the task whose output is being written.
- @throws IOException]]>
- </doc>
- </method>
- <method name="needsTaskCommit" return="boolean"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskContext" type="org.apache.hadoop.mapred.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Check whether task needs a commit
-
- @param taskContext
- @return true/false
- @throws IOException]]>
- </doc>
- </method>
- <method name="commitTask"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskContext" type="org.apache.hadoop.mapred.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[To promote the task's temporary output to final output location
-
- The task's output is moved to the job's output directory.
-
- @param taskContext Context of the task whose output is being written.
- @throws IOException if commit is not]]>
- </doc>
- </method>
- <method name="abortTask"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskContext" type="org.apache.hadoop.mapred.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Discard the task output
-
- @param taskContext
- @throws IOException]]>
- </doc>
- </method>
- <method name="setupJob"
- abstract="false" native="false" synchronized="false"
- static="false" final="true" visibility="public"
- deprecated="not deprecated">
- <param name="jobContext" type="org.apache.hadoop.mapreduce.JobContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[This method implements the new interface by calling the old method. Note
- that the input types are different between the new and old apis and this
- is a bridge between the two.]]>
- </doc>
- </method>
- <method name="cleanupJob"
- abstract="false" native="false" synchronized="false"
- static="false" final="true" visibility="public"
- deprecated="Use {@link #commitJob(org.apache.hadoop.mapreduce.JobContext)}
- or {@link #abortJob(org.apache.hadoop.mapreduce.JobContext, org.apache.hadoop.mapreduce.JobStatus.State)}
- instead.">
- <param name="context" type="org.apache.hadoop.mapreduce.JobContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[This method implements the new interface by calling the old method. Note
- that the input types are different between the new and old apis and this
- is a bridge between the two.
- @deprecated Use {@link #commitJob(org.apache.hadoop.mapreduce.JobContext)}
- or {@link #abortJob(org.apache.hadoop.mapreduce.JobContext, org.apache.hadoop.mapreduce.JobStatus.State)}
- instead.]]>
- </doc>
- </method>
- <method name="commitJob"
- abstract="false" native="false" synchronized="false"
- static="false" final="true" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.JobContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[This method implements the new interface by calling the old method. Note
- that the input types are different between the new and old apis and this
- is a bridge between the two.]]>
- </doc>
- </method>
- <method name="abortJob"
- abstract="false" native="false" synchronized="false"
- static="false" final="true" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.JobContext"/>
- <param name="runState" type="org.apache.hadoop.mapreduce.JobStatus.State"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[This method implements the new interface by calling the old method. Note
- that the input types are different between the new and old apis and this
- is a bridge between the two.]]>
- </doc>
- </method>
- <method name="setupTask"
- abstract="false" native="false" synchronized="false"
- static="false" final="true" visibility="public"
- deprecated="not deprecated">
- <param name="taskContext" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[This method implements the new interface by calling the old method. Note
- that the input types are different between the new and old apis and this
- is a bridge between the two.]]>
- </doc>
- </method>
- <method name="needsTaskCommit" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="true" visibility="public"
- deprecated="not deprecated">
- <param name="taskContext" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[This method implements the new interface by calling the old method. Note
- that the input types are different between the new and old apis and this
- is a bridge between the two.]]>
- </doc>
- </method>
- <method name="commitTask"
- abstract="false" native="false" synchronized="false"
- static="false" final="true" visibility="public"
- deprecated="not deprecated">
- <param name="taskContext" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[This method implements the new interface by calling the old method. Note
- that the input types are different between the new and old apis and this
- is a bridge between the two.]]>
- </doc>
- </method>
- <method name="abortTask"
- abstract="false" native="false" synchronized="false"
- static="false" final="true" visibility="public"
- deprecated="not deprecated">
- <param name="taskContext" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[This method implements the new interface by calling the old method. Note
- that the input types are different between the new and old apis and this
- is a bridge between the two.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[<code>OutputCommitter</code> describes the commit of task output for a
- Map-Reduce job.
- <p>The Map-Reduce framework relies on the <code>OutputCommitter</code> of
- the job to:<p>
- <ol>
- <li>
- Setup the job during initialization. For example, create the temporary
- output directory for the job during the initialization of the job.
- </li>
- <li>
- Cleanup the job after the job completion. For example, remove the
- temporary output directory after the job completion.
- </li>
- <li>
- Setup the task temporary output.
- </li>
- <li>
- Check whether a task needs a commit. This is to avoid the commit
- procedure if a task does not need commit.
- </li>
- <li>
- Commit of the task output.
- </li>
- <li>
- Discard the task commit.
- </li>
- </ol>
-
- @see FileOutputCommitter
- @see JobContext
- @see TaskAttemptContext
- @deprecated Use {@link org.apache.hadoop.mapreduce.OutputCommitter} instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.OutputCommitter -->
- <!-- start interface org.apache.hadoop.mapred.OutputFormat -->
- <interface name="OutputFormat" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.OutputFormat} instead.">
- <method name="getRecordWriter" return="org.apache.hadoop.mapred.RecordWriter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="name" type="java.lang.String"/>
- <param name="progress" type="org.apache.hadoop.util.Progressable"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get the {@link RecordWriter} for the given job.
- @param ignored
- @param job configuration for the job whose output is being written.
- @param name the unique name for this part of the output.
- @param progress mechanism for reporting progress while writing to file.
- @return a {@link RecordWriter} to write the output for the job.
- @throws IOException]]>
- </doc>
- </method>
- <method name="checkOutputSpecs"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Check for validity of the output-specification for the job.
-
- <p>This is to validate the output specification for the job when it is
- a job is submitted. Typically checks that it does not already exist,
- throwing an exception when it already exists, so that output is not
- overwritten.</p>
- @param ignored
- @param job job configuration.
- @throws IOException when output should not be attempted]]>
- </doc>
- </method>
- <doc>
- <![CDATA[<code>OutputFormat</code> describes the output-specification for a
- Map-Reduce job.
- <p>The Map-Reduce framework relies on the <code>OutputFormat</code> of the
- job to:<p>
- <ol>
- <li>
- Validate the output-specification of the job. For e.g. check that the
- output directory doesn't already exist.
- <li>
- Provide the {@link RecordWriter} implementation to be used to write out
- the output files of the job. Output files are stored in a
- {@link FileSystem}.
- </li>
- </ol>
-
- @see RecordWriter
- @see JobConf
- @deprecated Use {@link org.apache.hadoop.mapreduce.OutputFormat} instead.]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.OutputFormat -->
- <!-- start class org.apache.hadoop.mapred.OutputLogFilter -->
- <class name="OutputLogFilter" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapred.Utils.OutputFileUtils.OutputLogFilter}
- instead.">
- <implements name="org.apache.hadoop.fs.PathFilter"/>
- <constructor name="OutputLogFilter"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="accept" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="path" type="org.apache.hadoop.fs.Path"/>
- </method>
- <doc>
- <![CDATA[This class filters log files from directory given
- It doesnt accept paths having _logs.
- This can be used to list paths of output directory as follows:
- Path[] fileList = FileUtil.stat2Paths(fs.listStatus(outDir,
- new OutputLogFilter()));
- @deprecated Use
- {@link org.apache.hadoop.mapred.Utils.OutputFileUtils.OutputLogFilter}
- instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.OutputLogFilter -->
- <!-- start interface org.apache.hadoop.mapred.Partitioner -->
- <interface name="Partitioner" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.Partitioner} instead.">
- <implements name="org.apache.hadoop.mapred.JobConfigurable"/>
- <method name="getPartition" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K2"/>
- <param name="value" type="V2"/>
- <param name="numPartitions" type="int"/>
- <doc>
- <![CDATA[Get the paritition number for a given key (hence record) given the total
- number of partitions i.e. number of reduce-tasks for the job.
-
- <p>Typically a hash function on a all or a subset of the key.</p>
- @param key the key to be paritioned.
- @param value the entry value.
- @param numPartitions the total number of partitions.
- @return the partition number for the <code>key</code>.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Partitions the key space.
-
- <p><code>Partitioner</code> controls the partitioning of the keys of the
- intermediate map-outputs. The key (or a subset of the key) is used to derive
- the partition, typically by a hash function. The total number of partitions
- is the same as the number of reduce tasks for the job. Hence this controls
- which of the <code>m</code> reduce tasks the intermediate key (and hence the
- record) is sent for reduction.</p>
-
- @see Reducer
- @deprecated Use {@link org.apache.hadoop.mapreduce.Partitioner} instead.]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.Partitioner -->
- <!-- start interface org.apache.hadoop.mapred.RecordReader -->
- <interface name="RecordReader" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <method name="next" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <param name="value" type="V"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Reads the next key/value pair from the input for processing.
- @param key the key to read data into
- @param value the value to read data into
- @return true iff a key/value was read, false if at EOF]]>
- </doc>
- </method>
- <method name="createKey" return="K"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Create an object of the appropriate type to be used as a key.
-
- @return a new key object.]]>
- </doc>
- </method>
- <method name="createValue" return="V"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Create an object of the appropriate type to be used as a value.
-
- @return a new value object.]]>
- </doc>
- </method>
- <method name="getPos" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Returns the current position in the input.
-
- @return the current position in the input.
- @throws IOException]]>
- </doc>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Close this {@link InputSplit} to future operations.
-
- @throws IOException]]>
- </doc>
- </method>
- <method name="getProgress" return="float"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[How much of the input has the {@link RecordReader} consumed i.e.
- has been processed by?
-
- @return progress from <code>0.0</code> to <code>1.0</code>.
- @throws IOException]]>
- </doc>
- </method>
- <doc>
- <![CDATA[<code>RecordReader</code> reads <key, value> pairs from an
- {@link InputSplit}.
-
- <p><code>RecordReader</code>, typically, converts the byte-oriented view of
- the input, provided by the <code>InputSplit</code>, and presents a
- record-oriented view for the {@link Mapper} & {@link Reducer} tasks for
- processing. It thus assumes the responsibility of processing record
- boundaries and presenting the tasks with keys and values.</p>
-
- @see InputSplit
- @see InputFormat]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.RecordReader -->
- <!-- start interface org.apache.hadoop.mapred.RecordWriter -->
- <interface name="RecordWriter" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <method name="write"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <param name="value" type="V"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Writes a key/value pair.
- @param key the key to write.
- @param value the value to write.
- @throws IOException]]>
- </doc>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Close this <code>RecordWriter</code> to future operations.
-
- @param reporter facility to report progress.
- @throws IOException]]>
- </doc>
- </method>
- <doc>
- <![CDATA[<code>RecordWriter</code> writes the output <key, value> pairs
- to an output file.
- <p><code>RecordWriter</code> implementations write the job outputs to the
- {@link FileSystem}.
-
- @see OutputFormat]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.RecordWriter -->
- <!-- start interface org.apache.hadoop.mapred.Reducer -->
- <interface name="Reducer" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.Reducer} instead.">
- <implements name="org.apache.hadoop.mapred.JobConfigurable"/>
- <implements name="org.apache.hadoop.io.Closeable"/>
- <method name="reduce"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K2"/>
- <param name="values" type="java.util.Iterator"/>
- <param name="output" type="org.apache.hadoop.mapred.OutputCollector"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[<i>Reduces</i> values for a given key.
-
- <p>The framework calls this method for each
- <code><key, (list of values)></code> pair in the grouped inputs.
- Output values must be of the same type as input values. Input keys must
- not be altered. The framework will <b>reuse</b> the key and value objects
- that are passed into the reduce, therefore the application should clone
- the objects they want to keep a copy of. In many cases, all values are
- combined into zero or one value.
- </p>
-
- <p>Output pairs are collected with calls to
- {@link OutputCollector#collect(Object,Object)}.</p>
- <p>Applications can use the {@link Reporter} provided to report progress
- or just indicate that they are alive. In scenarios where the application
- takes an insignificant amount of time to process individual key/value
- pairs, this is crucial since the framework might assume that the task has
- timed-out and kill that task. The other way of avoiding this is to set
- <a href="{@docRoot}/../mapred-default.html#mapreduce.task.timeout">
- mapreduce.task.timeout</a> to a high-enough value (or even zero for no
- time-outs).</p>
-
- @param key the key.
- @param values the list of values to reduce.
- @param output to collect keys and combined values.
- @param reporter facility to report progress.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Reduces a set of intermediate values which share a key to a smaller set of
- values.
-
- <p>The number of <code>Reducer</code>s for the job is set by the user via
- {@link JobConf#setNumReduceTasks(int)}. <code>Reducer</code> implementations
- can access the {@link JobConf} for the job via the
- {@link JobConfigurable#configure(JobConf)} method and initialize themselves.
- Similarly they can use the {@link Closeable#close()} method for
- de-initialization.</p>
- <p><code>Reducer</code> has 3 primary phases:</p>
- <ol>
- <li>
-
- <h4 id="Shuffle">Shuffle</h4>
-
- <p><code>Reducer</code> is input the grouped output of a {@link Mapper}.
- In the phase the framework, for each <code>Reducer</code>, fetches the
- relevant partition of the output of all the <code>Mapper</code>s, via HTTP.
- </p>
- </li>
-
- <li>
- <h4 id="Sort">Sort</h4>
-
- <p>The framework groups <code>Reducer</code> inputs by <code>key</code>s
- (since different <code>Mapper</code>s may have output the same key) in this
- stage.</p>
-
- <p>The shuffle and sort phases occur simultaneously i.e. while outputs are
- being fetched they are merged.</p>
-
- <h5 id="SecondarySort">SecondarySort</h5>
-
- <p>If equivalence rules for keys while grouping the intermediates are
- different from those for grouping keys before reduction, then one may
- specify a <code>Comparator</code> via
- {@link JobConf#setOutputValueGroupingComparator(Class)}.Since
- {@link JobConf#setOutputKeyComparatorClass(Class)} can be used to
- control how intermediate keys are grouped, these can be used in conjunction
- to simulate <i>secondary sort on values</i>.</p>
-
-
- For example, say that you want to find duplicate web pages and tag them
- all with the url of the "best" known example. You would set up the job
- like:
- <ul>
- <li>Map Input Key: url</li>
- <li>Map Input Value: document</li>
- <li>Map Output Key: document checksum, url pagerank</li>
- <li>Map Output Value: url</li>
- <li>Partitioner: by checksum</li>
- <li>OutputKeyComparator: by checksum and then decreasing pagerank</li>
- <li>OutputValueGroupingComparator: by checksum</li>
- </ul>
- </li>
-
- <li>
- <h4 id="Reduce">Reduce</h4>
-
- <p>In this phase the
- {@link #reduce(Object, Iterator, OutputCollector, Reporter)}
- method is called for each <code><key, (list of values)></code> pair in
- the grouped inputs.</p>
- <p>The output of the reduce task is typically written to the
- {@link FileSystem} via
- {@link OutputCollector#collect(Object, Object)}.</p>
- </li>
- </ol>
-
- <p>The output of the <code>Reducer</code> is <b>not re-sorted</b>.</p>
-
- <p>Example:</p>
- <p><blockquote><pre>
- public class MyReducer<K extends WritableComparable, V extends Writable>
- extends MapReduceBase implements Reducer<K, V, K, V> {
-
- static enum MyCounters { NUM_RECORDS }
-
- private String reduceTaskId;
- private int noKeys = 0;
-
- public void configure(JobConf job) {
- reduceTaskId = job.get(JobContext.TASK_ATTEMPT_ID);
- }
-
- public void reduce(K key, Iterator<V> values,
- OutputCollector<K, V> output,
- Reporter reporter)
- throws IOException {
-
- // Process
- int noValues = 0;
- while (values.hasNext()) {
- V value = values.next();
-
- // Increment the no. of values for this key
- ++noValues;
-
- // Process the <key, value> pair (assume this takes a while)
- // ...
- // ...
-
- // Let the framework know that we are alive, and kicking!
- if ((noValues%10) == 0) {
- reporter.progress();
- }
-
- // Process some more
- // ...
- // ...
-
- // Output the <key, value>
- output.collect(key, value);
- }
-
- // Increment the no. of <key, list of values> pairs processed
- ++noKeys;
-
- // Increment counters
- reporter.incrCounter(NUM_RECORDS, 1);
-
- // Every 100 keys update application-level status
- if ((noKeys%100) == 0) {
- reporter.setStatus(reduceTaskId + " processed " + noKeys);
- }
- }
- }
- </pre></blockquote></p>
-
- @see Mapper
- @see Partitioner
- @see Reporter
- @see MapReduceBase
- @deprecated Use {@link org.apache.hadoop.mapreduce.Reducer} instead.]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.Reducer -->
- <!-- start interface org.apache.hadoop.mapred.Reporter -->
- <interface name="Reporter" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.util.Progressable"/>
- <method name="setStatus"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="status" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the status description for the task.
-
- @param status brief description of the current status.]]>
- </doc>
- </method>
- <method name="getCounter" return="org.apache.hadoop.mapred.Counters.Counter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.Enum"/>
- <doc>
- <![CDATA[Get the {@link Counter} of the given group with the given name.
-
- @param name counter name
- @return the <code>Counter</code> of the given group/name.]]>
- </doc>
- </method>
- <method name="getCounter" return="org.apache.hadoop.mapred.Counters.Counter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="group" type="java.lang.String"/>
- <param name="name" type="java.lang.String"/>
- <doc>
- <![CDATA[Get the {@link Counter} of the given group with the given name.
-
- @param group counter group
- @param name counter name
- @return the <code>Counter</code> of the given group/name.]]>
- </doc>
- </method>
- <method name="incrCounter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="java.lang.Enum"/>
- <param name="amount" type="long"/>
- <doc>
- <![CDATA[Increments the counter identified by the key, which can be of
- any {@link Enum} type, by the specified amount.
-
- @param key key to identify the counter to be incremented. The key can be
- be any <code>Enum</code>.
- @param amount A non-negative amount by which the counter is to
- be incremented.]]>
- </doc>
- </method>
- <method name="incrCounter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="group" type="java.lang.String"/>
- <param name="counter" type="java.lang.String"/>
- <param name="amount" type="long"/>
- <doc>
- <![CDATA[Increments the counter identified by the group and counter name
- by the specified amount.
-
- @param group name to identify the group of the counter to be incremented.
- @param counter name to identify the counter within the group.
- @param amount A non-negative amount by which the counter is to
- be incremented.]]>
- </doc>
- </method>
- <method name="getInputSplit" return="org.apache.hadoop.mapred.InputSplit"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="UnsupportedOperationException" type="java.lang.UnsupportedOperationException"/>
- <doc>
- <![CDATA[Get the {@link InputSplit} object for a map.
-
- @return the <code>InputSplit</code> that the map is reading from.
- @throws UnsupportedOperationException if called outside a mapper]]>
- </doc>
- </method>
- <field name="NULL" type="org.apache.hadoop.mapred.Reporter"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[A constant of Reporter type that does nothing.]]>
- </doc>
- </field>
- <doc>
- <![CDATA[A facility for Map-Reduce applications to report progress and update
- counters, status information etc.
-
- <p>{@link Mapper} and {@link Reducer} can use the <code>Reporter</code>
- provided to report progress or just indicate that they are alive. In
- scenarios where the application takes an insignificant amount of time to
- process individual key/value pairs, this is crucial since the framework
- might assume that the task has timed-out and kill that task.
- <p>Applications can also update {@link Counters} via the provided
- <code>Reporter</code> .</p>
-
- @see Progressable
- @see Counters]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.Reporter -->
- <!-- start interface org.apache.hadoop.mapred.RunningJob -->
- <interface name="RunningJob" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.Job} instead">
- <method name="getConfiguration" return="org.apache.hadoop.conf.Configuration"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the underlying job configuration
- @return the configuration of the job.]]>
- </doc>
- </method>
- <method name="getID" return="org.apache.hadoop.mapred.JobID"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the job identifier.
-
- @return the job identifier.]]>
- </doc>
- </method>
- <method name="getJobID" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="This method is deprecated and will be removed. Applications should
- rather use {@link #getID()}.">
- <doc>
- <![CDATA[@deprecated This method is deprecated and will be removed. Applications should
- rather use {@link #getID()}.]]>
- </doc>
- </method>
- <method name="getJobName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the name of the job.
-
- @return the name of the job.]]>
- </doc>
- </method>
- <method name="getJobFile" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the path of the submitted job configuration.
-
- @return the path of the submitted job configuration.]]>
- </doc>
- </method>
- <method name="getTrackingURL" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the URL where some job progress information will be displayed.
-
- @return the URL where some job progress information will be displayed.]]>
- </doc>
- </method>
- <method name="mapProgress" return="float"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get the <i>progress</i> of the job's map-tasks, as a float between 0.0
- and 1.0. When all map tasks have completed, the function returns 1.0.
-
- @return the progress of the job's map-tasks.
- @throws IOException]]>
- </doc>
- </method>
- <method name="reduceProgress" return="float"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get the <i>progress</i> of the job's reduce-tasks, as a float between 0.0
- and 1.0. When all reduce tasks have completed, the function returns 1.0.
-
- @return the progress of the job's reduce-tasks.
- @throws IOException]]>
- </doc>
- </method>
- <method name="cleanupProgress" return="float"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get the <i>progress</i> of the job's cleanup-tasks, as a float between 0.0
- and 1.0. When all cleanup tasks have completed, the function returns 1.0.
-
- @return the progress of the job's cleanup-tasks.
- @throws IOException]]>
- </doc>
- </method>
- <method name="setupProgress" return="float"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get the <i>progress</i> of the job's setup-tasks, as a float between 0.0
- and 1.0. When all setup tasks have completed, the function returns 1.0.
-
- @return the progress of the job's setup-tasks.
- @throws IOException]]>
- </doc>
- </method>
- <method name="isComplete" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Check if the job is finished or not.
- This is a non-blocking call.
-
- @return <code>true</code> if the job is complete, else <code>false</code>.
- @throws IOException]]>
- </doc>
- </method>
- <method name="isSuccessful" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Check if the job completed successfully.
-
- @return <code>true</code> if the job succeeded, else <code>false</code>.
- @throws IOException]]>
- </doc>
- </method>
- <method name="waitForCompletion"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Blocks until the job is complete.
-
- @throws IOException]]>
- </doc>
- </method>
- <method name="getJobState" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Returns the current state of the Job.
- {@link JobStatus}
-
- @throws IOException]]>
- </doc>
- </method>
- <method name="killJob"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Kill the running job. Blocks until all job tasks have been
- killed as well. If the job is no longer running, it simply returns.
-
- @throws IOException]]>
- </doc>
- </method>
- <method name="setJobPriority"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="priority" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Set the priority of a running job.
- @param priority the new priority for the job.
- @throws IOException]]>
- </doc>
- </method>
- <method name="getTaskCompletionEvents" return="org.apache.hadoop.mapred.TaskCompletionEvent[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="startFrom" type="int"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get events indicating completion (success/failure) of component tasks.
-
- @param startFrom index to start fetching events from
- @return an array of {@link TaskCompletionEvent}s
- @throws IOException]]>
- </doc>
- </method>
- <method name="killTask"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskId" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <param name="shouldFail" type="boolean"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Kill indicated task attempt.
-
- @param taskId the id of the task to be terminated.
- @param shouldFail if true the task is failed and added to failed tasks
- list, otherwise it is just killed, w/o affecting
- job failure status.
- @throws IOException]]>
- </doc>
- </method>
- <method name="killTask"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="Applications should rather use {@link #killTask(TaskAttemptID, boolean)}">
- <param name="taskId" type="java.lang.String"/>
- <param name="shouldFail" type="boolean"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[@deprecated Applications should rather use {@link #killTask(TaskAttemptID, boolean)}]]>
- </doc>
- </method>
- <method name="getCounters" return="org.apache.hadoop.mapred.Counters"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Gets the counters for this job.
-
- @return the counters for this job.
- @throws IOException]]>
- </doc>
- </method>
- <method name="getTaskDiagnostics" return="java.lang.String[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskid" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Gets the diagnostic messages for a given task attempt.
- @param taskid
- @return the list of diagnostic messages for the task
- @throws IOException]]>
- </doc>
- </method>
- <method name="getHistoryUrl" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get the url where history file is archived. Returns empty string if
- history file is not available yet.
-
- @return the url where history file is archived
- @throws IOException]]>
- </doc>
- </method>
- <method name="isRetired" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Check whether the job has been removed from JobTracker memory and retired.
- On retire, the job history file is copied to a location known by
- {@link #getHistoryUrl()}
- @return <code>true</code> if the job retired, else <code>false</code>.
- @throws IOException]]>
- </doc>
- </method>
- <doc>
- <![CDATA[<code>RunningJob</code> is the user-interface to query for details on a
- running Map-Reduce job.
-
- <p>Clients can get hold of <code>RunningJob</code> via the {@link JobClient}
- and then query the running-job for details such as name, configuration,
- progress etc.</p>
-
- @see JobClient
- @deprecated Use {@link org.apache.hadoop.mapreduce.Job} instead]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.RunningJob -->
- <!-- start class org.apache.hadoop.mapred.SequenceFileAsBinaryInputFormat -->
- <class name="SequenceFileAsBinaryInputFormat" extends="org.apache.hadoop.mapred.SequenceFileInputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.input.SequenceFileAsBinaryInputFormat}
- instead">
- <constructor name="SequenceFileAsBinaryInputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getRecordReader" return="org.apache.hadoop.mapred.RecordReader"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapred.InputSplit"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[InputFormat reading keys, values from SequenceFiles in binary (raw)
- format.
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.input.SequenceFileAsBinaryInputFormat}
- instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.SequenceFileAsBinaryInputFormat -->
- <!-- start class org.apache.hadoop.mapred.SequenceFileAsBinaryInputFormat.SequenceFileAsBinaryRecordReader -->
- <class name="SequenceFileAsBinaryInputFormat.SequenceFileAsBinaryRecordReader" extends="java.lang.Object"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapred.RecordReader"/>
- <constructor name="SequenceFileAsBinaryInputFormat.SequenceFileAsBinaryRecordReader" type="org.apache.hadoop.conf.Configuration, org.apache.hadoop.mapred.FileSplit"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </constructor>
- <method name="createKey" return="org.apache.hadoop.io.BytesWritable"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="createValue" return="org.apache.hadoop.io.BytesWritable"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getKeyClassName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Retrieve the name of the key class for this SequenceFile.
- @see org.apache.hadoop.io.SequenceFile.Reader#getKeyClassName]]>
- </doc>
- </method>
- <method name="getValueClassName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Retrieve the name of the value class for this SequenceFile.
- @see org.apache.hadoop.io.SequenceFile.Reader#getValueClassName]]>
- </doc>
- </method>
- <method name="next" return="boolean"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="org.apache.hadoop.io.BytesWritable"/>
- <param name="val" type="org.apache.hadoop.io.BytesWritable"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Read raw bytes from a SequenceFile.]]>
- </doc>
- </method>
- <method name="getPos" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getProgress" return="float"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Return the progress within the input split
- @return 0.0 to 1.0 of the input byte range]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Read records from a SequenceFile as binary (raw) bytes.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.SequenceFileAsBinaryInputFormat.SequenceFileAsBinaryRecordReader -->
- <!-- start class org.apache.hadoop.mapred.SequenceFileAsBinaryOutputFormat -->
- <class name="SequenceFileAsBinaryOutputFormat" extends="org.apache.hadoop.mapred.SequenceFileOutputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.output.SequenceFileAsBinaryOutputFormat}
- instead">
- <constructor name="SequenceFileAsBinaryOutputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setSequenceFileOutputKeyClass"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="theClass" type="java.lang.Class"/>
- <doc>
- <![CDATA[Set the key class for the {@link SequenceFile}
- <p>This allows the user to specify the key class to be different
- from the actual class ({@link BytesWritable}) used for writing </p>
-
- @param conf the {@link JobConf} to modify
- @param theClass the SequenceFile output key class.]]>
- </doc>
- </method>
- <method name="setSequenceFileOutputValueClass"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="theClass" type="java.lang.Class"/>
- <doc>
- <![CDATA[Set the value class for the {@link SequenceFile}
- <p>This allows the user to specify the value class to be different
- from the actual class ({@link BytesWritable}) used for writing </p>
-
- @param conf the {@link JobConf} to modify
- @param theClass the SequenceFile output key class.]]>
- </doc>
- </method>
- <method name="getSequenceFileOutputKeyClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[Get the key class for the {@link SequenceFile}
-
- @return the key class of the {@link SequenceFile}]]>
- </doc>
- </method>
- <method name="getSequenceFileOutputValueClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[Get the value class for the {@link SequenceFile}
-
- @return the value class of the {@link SequenceFile}]]>
- </doc>
- </method>
- <method name="getRecordWriter" return="org.apache.hadoop.mapred.RecordWriter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="name" type="java.lang.String"/>
- <param name="progress" type="org.apache.hadoop.util.Progressable"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="checkOutputSpecs"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[An {@link OutputFormat} that writes keys, values to
- {@link SequenceFile}s in binary(raw) format
-
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.output.SequenceFileAsBinaryOutputFormat}
- instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.SequenceFileAsBinaryOutputFormat -->
- <!-- start class org.apache.hadoop.mapred.SequenceFileAsBinaryOutputFormat.WritableValueBytes -->
- <class name="SequenceFileAsBinaryOutputFormat.WritableValueBytes" extends="org.apache.hadoop.mapreduce.lib.output.SequenceFileAsBinaryOutputFormat.WritableValueBytes"
- abstract="false"
- static="true" final="false" visibility="protected"
- deprecated="not deprecated">
- <constructor name="SequenceFileAsBinaryOutputFormat.WritableValueBytes"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </constructor>
- <doc>
- <![CDATA[Inner class used for appendRaw]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.SequenceFileAsBinaryOutputFormat.WritableValueBytes -->
- <!-- start class org.apache.hadoop.mapred.SequenceFileAsTextInputFormat -->
- <class name="SequenceFileAsTextInputFormat" extends="org.apache.hadoop.mapred.SequenceFileInputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.input.SequenceFileAsTextInputFormat}
- instead">
- <constructor name="SequenceFileAsTextInputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getRecordReader" return="org.apache.hadoop.mapred.RecordReader"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapred.InputSplit"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[This class is similar to SequenceFileInputFormat,
- except it generates SequenceFileAsTextRecordReader
- which converts the input keys and values to their
- String forms by calling toString() method.
-
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.input.SequenceFileAsTextInputFormat}
- instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.SequenceFileAsTextInputFormat -->
- <!-- start class org.apache.hadoop.mapred.SequenceFileAsTextRecordReader -->
- <class name="SequenceFileAsTextRecordReader" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.input.SequenceFileAsTextRecordReader}
- instead">
- <implements name="org.apache.hadoop.mapred.RecordReader"/>
- <constructor name="SequenceFileAsTextRecordReader" type="org.apache.hadoop.conf.Configuration, org.apache.hadoop.mapred.FileSplit"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </constructor>
- <method name="createKey" return="org.apache.hadoop.io.Text"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="createValue" return="org.apache.hadoop.io.Text"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="next" return="boolean"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="org.apache.hadoop.io.Text"/>
- <param name="value" type="org.apache.hadoop.io.Text"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Read key/value pair in a line.]]>
- </doc>
- </method>
- <method name="getProgress" return="float"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getPos" return="long"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[This class converts the input keys and values to their String forms by calling toString()
- method. This class to SequenceFileAsTextInputFormat class is as LineRecordReader
- class to TextInputFormat class.
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.input.SequenceFileAsTextRecordReader}
- instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.SequenceFileAsTextRecordReader -->
- <!-- start class org.apache.hadoop.mapred.SequenceFileInputFilter -->
- <class name="SequenceFileInputFilter" extends="org.apache.hadoop.mapred.SequenceFileInputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFilter}
- instead">
- <constructor name="SequenceFileInputFilter"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getRecordReader" return="org.apache.hadoop.mapred.RecordReader"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapred.InputSplit"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Create a record reader for the given split
- @param split file split
- @param job job configuration
- @param reporter reporter who sends report to task tracker
- @return RecordReader]]>
- </doc>
- </method>
- <method name="setFilterClass"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <param name="filterClass" type="java.lang.Class"/>
- <doc>
- <![CDATA[set the filter class
-
- @param conf application configuration
- @param filterClass filter class]]>
- </doc>
- </method>
- <doc>
- <![CDATA[A class that allows a map/red job to work on a sample of sequence files.
- The sample is decided by the filter class set by the job.
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFilter}
- instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.SequenceFileInputFilter -->
- <!-- start interface org.apache.hadoop.mapred.SequenceFileInputFilter.Filter -->
- <interface name="SequenceFileInputFilter.Filter" abstract="true"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFilter.Filter"/>
- <doc>
- <![CDATA[filter interface]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.SequenceFileInputFilter.Filter -->
- <!-- start class org.apache.hadoop.mapred.SequenceFileInputFilter.FilterBase -->
- <class name="SequenceFileInputFilter.FilterBase" extends="org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFilter.FilterBase"
- abstract="true"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapred.SequenceFileInputFilter.Filter"/>
- <constructor name="SequenceFileInputFilter.FilterBase"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <doc>
- <![CDATA[base class for Filters]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.SequenceFileInputFilter.FilterBase -->
- <!-- start class org.apache.hadoop.mapred.SequenceFileInputFilter.MD5Filter -->
- <class name="SequenceFileInputFilter.MD5Filter" extends="org.apache.hadoop.mapred.SequenceFileInputFilter.FilterBase"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="SequenceFileInputFilter.MD5Filter"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setFrequency"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <param name="frequency" type="int"/>
- <doc>
- <![CDATA[set the filtering frequency in configuration
-
- @param conf configuration
- @param frequency filtering frequency]]>
- </doc>
- </method>
- <method name="setConf"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <doc>
- <![CDATA[configure the filter according to configuration
-
- @param conf configuration]]>
- </doc>
- </method>
- <method name="accept" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="java.lang.Object"/>
- <doc>
- <![CDATA[Filtering method
- If MD5(key) % frequency==0, return true; otherwise return false
- @see org.apache.hadoop.mapred.SequenceFileInputFilter.Filter#accept(Object)]]>
- </doc>
- </method>
- <field name="MD5_LEN" type="int"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[This class returns a set of records by examing the MD5 digest of its
- key against a filtering frequency <i>f</i>. The filtering criteria is
- MD5(key) % f == 0.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.SequenceFileInputFilter.MD5Filter -->
- <!-- start class org.apache.hadoop.mapred.SequenceFileInputFilter.PercentFilter -->
- <class name="SequenceFileInputFilter.PercentFilter" extends="org.apache.hadoop.mapred.SequenceFileInputFilter.FilterBase"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="SequenceFileInputFilter.PercentFilter"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setFrequency"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <param name="frequency" type="int"/>
- <doc>
- <![CDATA[set the frequency and stores it in conf
- @param conf configuration
- @param frequency filtering frequencey]]>
- </doc>
- </method>
- <method name="setConf"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <doc>
- <![CDATA[configure the filter by checking the configuration
-
- @param conf configuration]]>
- </doc>
- </method>
- <method name="accept" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="java.lang.Object"/>
- <doc>
- <![CDATA[Filtering method
- If record# % frequency==0, return true; otherwise return false
- @see org.apache.hadoop.mapred.SequenceFileInputFilter.Filter#accept(Object)]]>
- </doc>
- </method>
- <doc>
- <![CDATA[This class returns a percentage of records
- The percentage is determined by a filtering frequency <i>f</i> using
- the criteria record# % f == 0.
- For example, if the frequency is 10, one out of 10 records is returned.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.SequenceFileInputFilter.PercentFilter -->
- <!-- start class org.apache.hadoop.mapred.SequenceFileInputFilter.RegexFilter -->
- <class name="SequenceFileInputFilter.RegexFilter" extends="org.apache.hadoop.mapred.SequenceFileInputFilter.FilterBase"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="SequenceFileInputFilter.RegexFilter"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setPattern"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <param name="regex" type="java.lang.String"/>
- <exception name="PatternSyntaxException" type="java.util.regex.PatternSyntaxException"/>
- </method>
- <method name="setConf"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <doc>
- <![CDATA[configure the Filter by checking the configuration]]>
- </doc>
- </method>
- <method name="accept" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="java.lang.Object"/>
- <doc>
- <![CDATA[Filtering method
- If key matches the regex, return true; otherwise return false
- @see org.apache.hadoop.mapred.SequenceFileInputFilter.Filter#accept(Object)]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Records filter by matching key to regex]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.SequenceFileInputFilter.RegexFilter -->
- <!-- start class org.apache.hadoop.mapred.SequenceFileInputFormat -->
- <class name="SequenceFileInputFormat" extends="org.apache.hadoop.mapred.FileInputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFormat}
- instead.">
- <constructor name="SequenceFileInputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="listStatus" return="org.apache.hadoop.fs.FileStatus[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getRecordReader" return="org.apache.hadoop.mapred.RecordReader"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapred.InputSplit"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[An {@link InputFormat} for {@link SequenceFile}s.
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFormat}
- instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.SequenceFileInputFormat -->
- <!-- start class org.apache.hadoop.mapred.SequenceFileOutputFormat -->
- <class name="SequenceFileOutputFormat" extends="org.apache.hadoop.mapred.FileOutputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat}
- instead.">
- <constructor name="SequenceFileOutputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getRecordWriter" return="org.apache.hadoop.mapred.RecordWriter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="name" type="java.lang.String"/>
- <param name="progress" type="org.apache.hadoop.util.Progressable"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getReaders" return="org.apache.hadoop.io.SequenceFile.Reader[]"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <param name="dir" type="org.apache.hadoop.fs.Path"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Open the output generated by this format.]]>
- </doc>
- </method>
- <method name="getOutputCompressionType" return="org.apache.hadoop.io.SequenceFile.CompressionType"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[Get the {@link CompressionType} for the output {@link SequenceFile}.
- @param conf the {@link JobConf}
- @return the {@link CompressionType} for the output {@link SequenceFile},
- defaulting to {@link CompressionType#RECORD}]]>
- </doc>
- </method>
- <method name="setOutputCompressionType"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="style" type="org.apache.hadoop.io.SequenceFile.CompressionType"/>
- <doc>
- <![CDATA[Set the {@link CompressionType} for the output {@link SequenceFile}.
- @param conf the {@link JobConf} to modify
- @param style the {@link CompressionType} for the output
- {@link SequenceFile}]]>
- </doc>
- </method>
- <doc>
- <![CDATA[An {@link OutputFormat} that writes {@link SequenceFile}s.
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat}
- instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.SequenceFileOutputFormat -->
- <!-- start class org.apache.hadoop.mapred.SequenceFileRecordReader -->
- <class name="SequenceFileRecordReader" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapred.RecordReader"/>
- <constructor name="SequenceFileRecordReader" type="org.apache.hadoop.conf.Configuration, org.apache.hadoop.mapred.FileSplit"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </constructor>
- <method name="getKeyClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[The class of key that must be passed to {@link
- #next(Object, Object)}..]]>
- </doc>
- </method>
- <method name="getValueClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[The class of value that must be passed to {@link
- #next(Object, Object)}..]]>
- </doc>
- </method>
- <method name="createKey" return="K"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="createValue" return="V"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="next" return="boolean"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <param name="value" type="V"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="next" return="boolean"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getCurrentValue"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="value" type="V"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getProgress" return="float"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Return the progress within the input split
- @return 0.0 to 1.0 of the input byte range]]>
- </doc>
- </method>
- <method name="getPos" return="long"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="seek"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="pos" type="long"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <field name="conf" type="org.apache.hadoop.conf.Configuration"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[An {@link RecordReader} for {@link SequenceFile}s.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.SequenceFileRecordReader -->
- <!-- start class org.apache.hadoop.mapred.SkipBadRecords -->
- <class name="SkipBadRecords" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="SkipBadRecords"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getAttemptsToStartSkipping" return="int"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <doc>
- <![CDATA[Get the number of Task attempts AFTER which skip mode
- will be kicked off. When skip mode is kicked off, the
- tasks reports the range of records which it will process
- next to the TaskTracker. So that on failures, TT knows which
- ones are possibly the bad records. On further executions,
- those are skipped.
- Default value is 2.
-
- @param conf the configuration
- @return attemptsToStartSkipping no of task attempts]]>
- </doc>
- </method>
- <method name="setAttemptsToStartSkipping"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <param name="attemptsToStartSkipping" type="int"/>
- <doc>
- <![CDATA[Set the number of Task attempts AFTER which skip mode
- will be kicked off. When skip mode is kicked off, the
- tasks reports the range of records which it will process
- next to the TaskTracker. So that on failures, TT knows which
- ones are possibly the bad records. On further executions,
- those are skipped.
- Default value is 2.
-
- @param conf the configuration
- @param attemptsToStartSkipping no of task attempts]]>
- </doc>
- </method>
- <method name="getAutoIncrMapperProcCount" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <doc>
- <![CDATA[Get the flag which if set to true,
- {@link SkipBadRecords#COUNTER_MAP_PROCESSED_RECORDS} is incremented
- by MapRunner after invoking the map function. This value must be set to
- false for applications which process the records asynchronously
- or buffer the input records. For example streaming.
- In such cases applications should increment this counter on their own.
- Default value is true.
-
- @param conf the configuration
- @return <code>true</code> if auto increment
- {@link SkipBadRecords#COUNTER_MAP_PROCESSED_RECORDS}.
- <code>false</code> otherwise.]]>
- </doc>
- </method>
- <method name="setAutoIncrMapperProcCount"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <param name="autoIncr" type="boolean"/>
- <doc>
- <![CDATA[Set the flag which if set to true,
- {@link SkipBadRecords#COUNTER_MAP_PROCESSED_RECORDS} is incremented
- by MapRunner after invoking the map function. This value must be set to
- false for applications which process the records asynchronously
- or buffer the input records. For example streaming.
- In such cases applications should increment this counter on their own.
- Default value is true.
-
- @param conf the configuration
- @param autoIncr whether to auto increment
- {@link SkipBadRecords#COUNTER_MAP_PROCESSED_RECORDS}.]]>
- </doc>
- </method>
- <method name="getAutoIncrReducerProcCount" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <doc>
- <![CDATA[Get the flag which if set to true,
- {@link SkipBadRecords#COUNTER_REDUCE_PROCESSED_GROUPS} is incremented
- by framework after invoking the reduce function. This value must be set to
- false for applications which process the records asynchronously
- or buffer the input records. For example streaming.
- In such cases applications should increment this counter on their own.
- Default value is true.
-
- @param conf the configuration
- @return <code>true</code> if auto increment
- {@link SkipBadRecords#COUNTER_REDUCE_PROCESSED_GROUPS}.
- <code>false</code> otherwise.]]>
- </doc>
- </method>
- <method name="setAutoIncrReducerProcCount"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <param name="autoIncr" type="boolean"/>
- <doc>
- <![CDATA[Set the flag which if set to true,
- {@link SkipBadRecords#COUNTER_REDUCE_PROCESSED_GROUPS} is incremented
- by framework after invoking the reduce function. This value must be set to
- false for applications which process the records asynchronously
- or buffer the input records. For example streaming.
- In such cases applications should increment this counter on their own.
- Default value is true.
-
- @param conf the configuration
- @param autoIncr whether to auto increment
- {@link SkipBadRecords#COUNTER_REDUCE_PROCESSED_GROUPS}.]]>
- </doc>
- </method>
- <method name="getSkipOutputPath" return="org.apache.hadoop.fs.Path"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <doc>
- <![CDATA[Get the directory to which skipped records are written. By default it is
- the sub directory of the output _logs directory.
- User can stop writing skipped records by setting the value null.
-
- @param conf the configuration.
- @return path skip output directory. Null is returned if this is not set
- and output directory is also not set.]]>
- </doc>
- </method>
- <method name="setSkipOutputPath"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="path" type="org.apache.hadoop.fs.Path"/>
- <doc>
- <![CDATA[Set the directory to which skipped records are written. By default it is
- the sub directory of the output _logs directory.
- User can stop writing skipped records by setting the value null.
-
- @param conf the configuration.
- @param path skip output directory path]]>
- </doc>
- </method>
- <method name="getMapperMaxSkipRecords" return="long"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <doc>
- <![CDATA[Get the number of acceptable skip records surrounding the bad record PER
- bad record in mapper. The number includes the bad record as well.
- To turn the feature of detection/skipping of bad records off, set the
- value to 0.
- The framework tries to narrow down the skipped range by retrying
- until this threshold is met OR all attempts get exhausted for this task.
- Set the value to Long.MAX_VALUE to indicate that framework need not try to
- narrow down. Whatever records(depends on application) get skipped are
- acceptable.
- Default value is 0.
-
- @param conf the configuration
- @return maxSkipRecs acceptable skip records.]]>
- </doc>
- </method>
- <method name="setMapperMaxSkipRecords"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <param name="maxSkipRecs" type="long"/>
- <doc>
- <![CDATA[Set the number of acceptable skip records surrounding the bad record PER
- bad record in mapper. The number includes the bad record as well.
- To turn the feature of detection/skipping of bad records off, set the
- value to 0.
- The framework tries to narrow down the skipped range by retrying
- until this threshold is met OR all attempts get exhausted for this task.
- Set the value to Long.MAX_VALUE to indicate that framework need not try to
- narrow down. Whatever records(depends on application) get skipped are
- acceptable.
- Default value is 0.
-
- @param conf the configuration
- @param maxSkipRecs acceptable skip records.]]>
- </doc>
- </method>
- <method name="getReducerMaxSkipGroups" return="long"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <doc>
- <![CDATA[Get the number of acceptable skip groups surrounding the bad group PER
- bad group in reducer. The number includes the bad group as well.
- To turn the feature of detection/skipping of bad groups off, set the
- value to 0.
- The framework tries to narrow down the skipped range by retrying
- until this threshold is met OR all attempts get exhausted for this task.
- Set the value to Long.MAX_VALUE to indicate that framework need not try to
- narrow down. Whatever groups(depends on application) get skipped are
- acceptable.
- Default value is 0.
-
- @param conf the configuration
- @return maxSkipGrps acceptable skip groups.]]>
- </doc>
- </method>
- <method name="setReducerMaxSkipGroups"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <param name="maxSkipGrps" type="long"/>
- <doc>
- <![CDATA[Set the number of acceptable skip groups surrounding the bad group PER
- bad group in reducer. The number includes the bad group as well.
- To turn the feature of detection/skipping of bad groups off, set the
- value to 0.
- The framework tries to narrow down the skipped range by retrying
- until this threshold is met OR all attempts get exhausted for this task.
- Set the value to Long.MAX_VALUE to indicate that framework need not try to
- narrow down. Whatever groups(depends on application) get skipped are
- acceptable.
- Default value is 0.
-
- @param conf the configuration
- @param maxSkipGrps acceptable skip groups.]]>
- </doc>
- </method>
- <field name="COUNTER_GROUP" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Special counters which are written by the application and are
- used by the framework for detecting bad records. For detecting bad records
- these counters must be incremented by the application.]]>
- </doc>
- </field>
- <field name="COUNTER_MAP_PROCESSED_RECORDS" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Number of processed map records.
- @see SkipBadRecords#getAutoIncrMapperProcCount(Configuration)]]>
- </doc>
- </field>
- <field name="COUNTER_REDUCE_PROCESSED_GROUPS" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Number of processed reduce groups.
- @see SkipBadRecords#getAutoIncrReducerProcCount(Configuration)]]>
- </doc>
- </field>
- <doc>
- <![CDATA[Utility class for skip bad records functionality. It contains various
- settings related to skipping of bad records.
-
- <p>Hadoop provides an optional mode of execution in which the bad records
- are detected and skipped in further attempts.
-
- <p>This feature can be used when map/reduce tasks crashes deterministically on
- certain input. This happens due to bugs in the map/reduce function. The usual
- course would be to fix these bugs. But sometimes this is not possible;
- perhaps the bug is in third party libraries for which the source code is
- not available. Due to this, the task never reaches to completion even with
- multiple attempts and complete data for that task is lost.</p>
-
- <p>With this feature, only a small portion of data is lost surrounding
- the bad record, which may be acceptable for some user applications.
- see {@link SkipBadRecords#setMapperMaxSkipRecords(Configuration, long)}</p>
-
- <p>The skipping mode gets kicked off after certain no of failures
- see {@link SkipBadRecords#setAttemptsToStartSkipping(Configuration, int)}</p>
-
- <p>In the skipping mode, the map/reduce task maintains the record range which
- is getting processed at all times. Before giving the input to the
- map/reduce function, it sends this record range to the Task tracker.
- If task crashes, the Task tracker knows which one was the last reported
- range. On further attempts that range get skipped.</p>]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.SkipBadRecords -->
- <!-- start interface org.apache.hadoop.mapred.TaskAttemptContext -->
- <interface name="TaskAttemptContext" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.TaskAttemptContext}
- instead.">
- <implements name="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <method name="getTaskAttemptID" return="org.apache.hadoop.mapred.TaskAttemptID"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getProgressible" return="org.apache.hadoop.util.Progressable"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getJobConf" return="org.apache.hadoop.mapred.JobConf"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <doc>
- <![CDATA[@deprecated Use {@link org.apache.hadoop.mapreduce.TaskAttemptContext}
- instead.]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.TaskAttemptContext -->
- <!-- start class org.apache.hadoop.mapred.TaskAttemptID -->
- <class name="TaskAttemptID" extends="org.apache.hadoop.mapreduce.TaskAttemptID"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="TaskAttemptID" type="org.apache.hadoop.mapred.TaskID, int"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Constructs a TaskAttemptID object from given {@link TaskID}.
- @param taskId TaskID that this task belongs to
- @param id the task attempt number]]>
- </doc>
- </constructor>
- <constructor name="TaskAttemptID" type="java.lang.String, int, boolean, int, int"
- static="false" final="false" visibility="public"
- deprecated="Use {@link #TaskAttemptID(String, int, TaskType, int, int)}.">
- <doc>
- <![CDATA[Constructs a TaskId object from given parts.
- @param jtIdentifier jobTracker identifier
- @param jobId job number
- @param isMap whether the tip is a map
- @param taskId taskId number
- @param id the task attempt number
- @deprecated Use {@link #TaskAttemptID(String, int, TaskType, int, int)}.]]>
- </doc>
- </constructor>
- <constructor name="TaskAttemptID" type="java.lang.String, int, org.apache.hadoop.mapreduce.TaskType, int, int"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Constructs a TaskId object from given parts.
- @param jtIdentifier jobTracker identifier
- @param jobId job number
- @param type the TaskType
- @param taskId taskId number
- @param id the task attempt number]]>
- </doc>
- </constructor>
- <constructor name="TaskAttemptID"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="downgrade" return="org.apache.hadoop.mapred.TaskAttemptID"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="old" type="org.apache.hadoop.mapreduce.TaskAttemptID"/>
- <doc>
- <![CDATA[Downgrade a new TaskAttemptID to an old one
- @param old the new id
- @return either old or a new TaskAttemptID constructed to match old]]>
- </doc>
- </method>
- <method name="getTaskID" return="org.apache.hadoop.mapred.TaskID"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getJobID" return="org.apache.hadoop.mapred.JobID"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="read" return="org.apache.hadoop.mapred.TaskAttemptID"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="in" type="java.io.DataInput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="forName" return="org.apache.hadoop.mapred.TaskAttemptID"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="str" type="java.lang.String"/>
- <exception name="IllegalArgumentException" type="java.lang.IllegalArgumentException"/>
- <doc>
- <![CDATA[Construct a TaskAttemptID object from given string
- @return constructed TaskAttemptID object or null if the given String is null
- @throws IllegalArgumentException if the given string is malformed]]>
- </doc>
- </method>
- <method name="getTaskAttemptIDsPattern" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jtIdentifier" type="java.lang.String"/>
- <param name="jobId" type="java.lang.Integer"/>
- <param name="isMap" type="java.lang.Boolean"/>
- <param name="taskId" type="java.lang.Integer"/>
- <param name="attemptId" type="java.lang.Integer"/>
- <doc>
- <![CDATA[Returns a regex pattern which matches task attempt IDs. Arguments can
- be given null, in which case that part of the regex will be generic.
- For example to obtain a regex matching <i>all task attempt IDs</i>
- of <i>any jobtracker</i>, in <i>any job</i>, of the <i>first
- map task</i>, we would use :
- <pre>
- TaskAttemptID.getTaskAttemptIDsPattern(null, null, true, 1, null);
- </pre>
- which will return :
- <pre> "attempt_[^_]*_[0-9]*_m_000001_[0-9]*" </pre>
- @param jtIdentifier jobTracker identifier, or null
- @param jobId job number, or null
- @param isMap whether the tip is a map, or null
- @param taskId taskId number, or null
- @param attemptId the task attempt number, or null
- @return a regex pattern matching TaskAttemptIDs]]>
- </doc>
- </method>
- <method name="getTaskAttemptIDsPattern" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jtIdentifier" type="java.lang.String"/>
- <param name="jobId" type="java.lang.Integer"/>
- <param name="type" type="org.apache.hadoop.mapreduce.TaskType"/>
- <param name="taskId" type="java.lang.Integer"/>
- <param name="attemptId" type="java.lang.Integer"/>
- <doc>
- <![CDATA[Returns a regex pattern which matches task attempt IDs. Arguments can
- be given null, in which case that part of the regex will be generic.
- For example to obtain a regex matching <i>all task attempt IDs</i>
- of <i>any jobtracker</i>, in <i>any job</i>, of the <i>first
- map task</i>, we would use :
- <pre>
- TaskAttemptID.getTaskAttemptIDsPattern(null, null, TaskType.MAP, 1, null);
- </pre>
- which will return :
- <pre> "attempt_[^_]*_[0-9]*_m_000001_[0-9]*" </pre>
- @param jtIdentifier jobTracker identifier, or null
- @param jobId job number, or null
- @param type the {@link TaskType}
- @param taskId taskId number, or null
- @param attemptId the task attempt number, or null
- @return a regex pattern matching TaskAttemptIDs]]>
- </doc>
- </method>
- <doc>
- <![CDATA[TaskAttemptID represents the immutable and unique identifier for
- a task attempt. Each task attempt is one particular instance of a Map or
- Reduce Task identified by its TaskID.
-
- TaskAttemptID consists of 2 parts. First part is the
- {@link TaskID}, that this TaskAttemptID belongs to.
- Second part is the task attempt number. <br>
- An example TaskAttemptID is :
- <code>attempt_200707121733_0003_m_000005_0</code> , which represents the
- zeroth task attempt for the fifth map task in the third job
- running at the jobtracker started at <code>200707121733</code>.
- <p>
- Applications should never construct or parse TaskAttemptID strings
- , but rather use appropriate constructors or {@link #forName(String)}
- method.
-
- @see JobID
- @see TaskID]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.TaskAttemptID -->
- <!-- start class org.apache.hadoop.mapred.TaskCompletionEvent -->
- <class name="TaskCompletionEvent" extends="org.apache.hadoop.mapreduce.TaskCompletionEvent"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.TaskCompletionEvent} instead">
- <constructor name="TaskCompletionEvent"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Default constructor for Writable.]]>
- </doc>
- </constructor>
- <constructor name="TaskCompletionEvent" type="int, org.apache.hadoop.mapred.TaskAttemptID, int, boolean, org.apache.hadoop.mapred.TaskCompletionEvent.Status, java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Constructor. eventId should be created externally and incremented
- per event for each job.
- @param eventId event id, event id should be unique and assigned in
- incrementally, starting from 0.
- @param taskId task id
- @param status task's status
- @param taskTrackerHttp task tracker's host:port for http.]]>
- </doc>
- </constructor>
- <method name="getTaskId" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="use {@link #getTaskAttemptId()} instead.">
- <doc>
- <![CDATA[Returns task id.
- @return task id
- @deprecated use {@link #getTaskAttemptId()} instead.]]>
- </doc>
- </method>
- <method name="getTaskAttemptId" return="org.apache.hadoop.mapred.TaskAttemptID"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns task id.
- @return task id]]>
- </doc>
- </method>
- <method name="getTaskStatus" return="org.apache.hadoop.mapred.TaskCompletionEvent.Status"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns enum Status.SUCESS or Status.FAILURE.
- @return task tracker status]]>
- </doc>
- </method>
- <method name="setTaskId"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="use {@link #setTaskAttemptId(TaskAttemptID)} instead.">
- <param name="taskId" type="java.lang.String"/>
- <doc>
- <![CDATA[Sets task id.
- @param taskId
- @deprecated use {@link #setTaskAttemptId(TaskAttemptID)} instead.]]>
- </doc>
- </method>
- <method name="setTaskAttemptId"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="taskId" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <doc>
- <![CDATA[Sets task id.
- @param taskId]]>
- </doc>
- </method>
- <method name="setTaskStatus"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="status" type="org.apache.hadoop.mapred.TaskCompletionEvent.Status"/>
- <doc>
- <![CDATA[Set task status.
- @param status]]>
- </doc>
- </method>
- <method name="setTaskRunTime"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="taskCompletionTime" type="int"/>
- <doc>
- <![CDATA[Set the task completion time
- @param taskCompletionTime time (in millisec) the task took to complete]]>
- </doc>
- </method>
- <method name="setEventId"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="eventId" type="int"/>
- <doc>
- <![CDATA[set event Id. should be assigned incrementally starting from 0.
- @param eventId]]>
- </doc>
- </method>
- <method name="setTaskTrackerHttp"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="taskTrackerHttp" type="java.lang.String"/>
- <doc>
- <![CDATA[Set task tracker http location.
- @param taskTrackerHttp]]>
- </doc>
- </method>
- <field name="EMPTY_ARRAY" type="org.apache.hadoop.mapred.TaskCompletionEvent[]"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[This is used to track task completion events on
- job tracker.
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.TaskCompletionEvent} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.TaskCompletionEvent -->
- <!-- start class org.apache.hadoop.mapred.TaskCompletionEvent.Status -->
- <class name="TaskCompletionEvent.Status" extends="java.lang.Enum"
- abstract="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <method name="values" return="org.apache.hadoop.mapred.TaskCompletionEvent.Status[]"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="valueOf" return="org.apache.hadoop.mapred.TaskCompletionEvent.Status"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- </method>
- </class>
- <!-- end class org.apache.hadoop.mapred.TaskCompletionEvent.Status -->
- <!-- start class org.apache.hadoop.mapred.TaskID -->
- <class name="TaskID" extends="org.apache.hadoop.mapreduce.TaskID"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="TaskID" type="org.apache.hadoop.mapreduce.JobID, boolean, int"
- static="false" final="false" visibility="public"
- deprecated="Use {@link #TaskID(String, int, TaskType, int)}">
- <doc>
- <![CDATA[Constructs a TaskID object from given {@link JobID}.
- @param jobId JobID that this tip belongs to
- @param isMap whether the tip is a map
- @param id the tip number
- @deprecated Use {@link #TaskID(String, int, TaskType, int)}]]>
- </doc>
- </constructor>
- <constructor name="TaskID" type="java.lang.String, int, boolean, int"
- static="false" final="false" visibility="public"
- deprecated="Use {@link #TaskID(org.apache.hadoop.mapreduce.JobID, TaskType,
- int)}">
- <doc>
- <![CDATA[Constructs a TaskInProgressId object from given parts.
- @param jtIdentifier jobTracker identifier
- @param jobId job number
- @param isMap whether the tip is a map
- @param id the tip number
- @deprecated Use {@link #TaskID(org.apache.hadoop.mapreduce.JobID, TaskType,
- int)}]]>
- </doc>
- </constructor>
- <constructor name="TaskID" type="org.apache.hadoop.mapreduce.JobID, org.apache.hadoop.mapreduce.TaskType, int"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Constructs a TaskID object from given {@link JobID}.
- @param jobId JobID that this tip belongs to
- @param type the {@link TaskType}
- @param id the tip number]]>
- </doc>
- </constructor>
- <constructor name="TaskID" type="java.lang.String, int, org.apache.hadoop.mapreduce.TaskType, int"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Constructs a TaskInProgressId object from given parts.
- @param jtIdentifier jobTracker identifier
- @param jobId job number
- @param type the {@link TaskType}
- @param id the tip number]]>
- </doc>
- </constructor>
- <constructor name="TaskID"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="downgrade" return="org.apache.hadoop.mapred.TaskID"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="old" type="org.apache.hadoop.mapreduce.TaskID"/>
- <doc>
- <![CDATA[Downgrade a new TaskID to an old one
- @param old a new or old TaskID
- @return either old or a new TaskID build to match old]]>
- </doc>
- </method>
- <method name="read" return="org.apache.hadoop.mapred.TaskID"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="in" type="java.io.DataInput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getJobID" return="org.apache.hadoop.mapred.JobID"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getTaskIDsPattern" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="Use {@link TaskID#getTaskIDsPattern(String, Integer, TaskType,
- Integer)}">
- <param name="jtIdentifier" type="java.lang.String"/>
- <param name="jobId" type="java.lang.Integer"/>
- <param name="isMap" type="java.lang.Boolean"/>
- <param name="taskId" type="java.lang.Integer"/>
- <doc>
- <![CDATA[Returns a regex pattern which matches task IDs. Arguments can
- be given null, in which case that part of the regex will be generic.
- For example to obtain a regex matching <i>the first map task</i>
- of <i>any jobtracker</i>, of <i>any job</i>, we would use :
- <pre>
- TaskID.getTaskIDsPattern(null, null, true, 1);
- </pre>
- which will return :
- <pre> "task_[^_]*_[0-9]*_m_000001*" </pre>
- @param jtIdentifier jobTracker identifier, or null
- @param jobId job number, or null
- @param isMap whether the tip is a map, or null
- @param taskId taskId number, or null
- @return a regex pattern matching TaskIDs
- @deprecated Use {@link TaskID#getTaskIDsPattern(String, Integer, TaskType,
- Integer)}]]>
- </doc>
- </method>
- <method name="getTaskIDsPattern" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jtIdentifier" type="java.lang.String"/>
- <param name="jobId" type="java.lang.Integer"/>
- <param name="type" type="org.apache.hadoop.mapreduce.TaskType"/>
- <param name="taskId" type="java.lang.Integer"/>
- <doc>
- <![CDATA[Returns a regex pattern which matches task IDs. Arguments can
- be given null, in which case that part of the regex will be generic.
- For example to obtain a regex matching <i>the first map task</i>
- of <i>any jobtracker</i>, of <i>any job</i>, we would use :
- <pre>
- TaskID.getTaskIDsPattern(null, null, true, 1);
- </pre>
- which will return :
- <pre> "task_[^_]*_[0-9]*_m_000001*" </pre>
- @param jtIdentifier jobTracker identifier, or null
- @param jobId job number, or null
- @param type the {@link TaskType}, or null
- @param taskId taskId number, or null
- @return a regex pattern matching TaskIDs]]>
- </doc>
- </method>
- <method name="forName" return="org.apache.hadoop.mapred.TaskID"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="str" type="java.lang.String"/>
- <exception name="IllegalArgumentException" type="java.lang.IllegalArgumentException"/>
- </method>
- <doc>
- <![CDATA[TaskID represents the immutable and unique identifier for
- a Map or Reduce Task. Each TaskID encompasses multiple attempts made to
- execute the Map or Reduce Task, each of which are uniquely indentified by
- their TaskAttemptID.
-
- TaskID consists of 3 parts. First part is the {@link JobID}, that this
- TaskInProgress belongs to. Second part of the TaskID is either 'm' or 'r'
- representing whether the task is a map task or a reduce task.
- And the third part is the task number. <br>
- An example TaskID is :
- <code>task_200707121733_0003_m_000005</code> , which represents the
- fifth map task in the third job running at the jobtracker
- started at <code>200707121733</code>.
- <p>
- Applications should never construct or parse TaskID strings
- , but rather use appropriate constructors or {@link #forName(String)}
- method.
-
- @see JobID
- @see TaskAttemptID]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.TaskID -->
- <!-- start class org.apache.hadoop.mapred.TaskLog.Reader -->
- <class name="TaskLog.Reader" extends="java.io.InputStream"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="TaskLog.Reader" type="org.apache.hadoop.mapred.TaskAttemptID, org.apache.hadoop.mapred.TaskLog.LogName, long, long, boolean"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Read a log file from start to end positions. The offsets may be negative,
- in which case they are relative to the end of the file. For example,
- Reader(taskid, kind, 0, -1) is the entire file and
- Reader(taskid, kind, -4197, -1) is the last 4196 bytes.
- @param taskid the id of the task to read the log file for
- @param kind the kind of log to read
- @param start the offset to read from (negative is relative to tail)
- @param end the offset to read upto (negative is relative to tail)
- @param isCleanup whether the attempt is cleanup attempt or not
- @throws IOException]]>
- </doc>
- </constructor>
- <method name="read" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="read" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="buffer" type="byte[]"/>
- <param name="offset" type="int"/>
- <param name="length" type="int"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="available" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- </class>
- <!-- end class org.apache.hadoop.mapred.TaskLog.Reader -->
- <!-- start class org.apache.hadoop.mapred.TaskLogAppender -->
- <class name="TaskLogAppender" extends="org.apache.log4j.FileAppender"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="TaskLogAppender"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="activateOptions"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="append"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="event" type="org.apache.log4j.spi.LoggingEvent"/>
- </method>
- <method name="flush"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getTaskId" return="java.lang.String"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Getter/Setter methods for log4j.]]>
- </doc>
- </method>
- <method name="setTaskId"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskId" type="java.lang.String"/>
- </method>
- <method name="getTotalLogFileSize" return="long"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="setTotalLogFileSize"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="logSize" type="long"/>
- </method>
- <method name="setIsCleanup"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="isCleanup" type="boolean"/>
- <doc>
- <![CDATA[Set whether the task is a cleanup attempt or not.
-
- @param isCleanup
- true if the task is cleanup attempt, false otherwise.]]>
- </doc>
- </method>
- <method name="getIsCleanup" return="boolean"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get whether task is cleanup attempt or not.
-
- @return true if the task is cleanup attempt, false otherwise.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[A simple log4j-appender for the task child's
- map-reduce system logs.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.TaskLogAppender -->
- <!-- start class org.apache.hadoop.mapred.TaskReport -->
- <class name="TaskReport" extends="org.apache.hadoop.mapreduce.TaskReport"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.TaskReport} instead">
- <constructor name="TaskReport"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getTaskID" return="org.apache.hadoop.mapred.TaskID"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[The id of the task.]]>
- </doc>
- </method>
- <method name="getCounters" return="org.apache.hadoop.mapred.Counters"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="setSuccessfulAttempt"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="t" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <doc>
- <![CDATA[set successful attempt ID of the task.]]>
- </doc>
- </method>
- <method name="getSuccessfulTaskAttempt" return="org.apache.hadoop.mapred.TaskAttemptID"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the attempt ID that took this task to completion]]>
- </doc>
- </method>
- <method name="setRunningTaskAttempts"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="runningAttempts" type="java.util.Collection"/>
- <doc>
- <![CDATA[set running attempt(s) of the task.]]>
- </doc>
- </method>
- <method name="getRunningTaskAttempts" return="java.util.Collection"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the running task attempt IDs for this task]]>
- </doc>
- </method>
- <method name="setFinishTime"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="finishTime" type="long"/>
- <doc>
- <![CDATA[set finish time of task.
- @param finishTime finish time of task.]]>
- </doc>
- </method>
- <method name="setStartTime"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="startTime" type="long"/>
- <doc>
- <![CDATA[set start time of the task.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[A report on the state of a task.
- @deprecated Use {@link org.apache.hadoop.mapreduce.TaskReport} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.TaskReport -->
- <!-- start class org.apache.hadoop.mapred.TextInputFormat -->
- <class name="TextInputFormat" extends="org.apache.hadoop.mapred.FileInputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.lib.input.TextInputFormat}
- instead.">
- <implements name="org.apache.hadoop.mapred.JobConfigurable"/>
- <constructor name="TextInputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="configure"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- </method>
- <method name="isSplitable" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="fs" type="org.apache.hadoop.fs.FileSystem"/>
- <param name="file" type="org.apache.hadoop.fs.Path"/>
- </method>
- <method name="getRecordReader" return="org.apache.hadoop.mapred.RecordReader"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="genericSplit" type="org.apache.hadoop.mapred.InputSplit"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[An {@link InputFormat} for plain text files. Files are broken into lines.
- Either linefeed or carriage-return are used to signal end of line. Keys are
- the position in the file, and values are the line of text..
- @deprecated Use {@link org.apache.hadoop.mapreduce.lib.input.TextInputFormat}
- instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.TextInputFormat -->
- <!-- start class org.apache.hadoop.mapred.TextOutputFormat -->
- <class name="TextOutputFormat" extends="org.apache.hadoop.mapred.FileOutputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.output.TextOutputFormat} instead.">
- <constructor name="TextOutputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getRecordWriter" return="org.apache.hadoop.mapred.RecordWriter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="name" type="java.lang.String"/>
- <param name="progress" type="org.apache.hadoop.util.Progressable"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[An {@link OutputFormat} that writes plain text files.
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.output.TextOutputFormat} instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.TextOutputFormat -->
- <!-- start class org.apache.hadoop.mapred.TextOutputFormat.LineRecordWriter -->
- <class name="TextOutputFormat.LineRecordWriter" extends="java.lang.Object"
- abstract="false"
- static="true" final="false" visibility="protected"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapred.RecordWriter"/>
- <constructor name="TextOutputFormat.LineRecordWriter" type="java.io.DataOutputStream, java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <constructor name="TextOutputFormat.LineRecordWriter" type="java.io.DataOutputStream"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="write"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <param name="value" type="V"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <field name="out" type="java.io.DataOutputStream"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- </class>
- <!-- end class org.apache.hadoop.mapred.TextOutputFormat.LineRecordWriter -->
- <!-- start class org.apache.hadoop.mapred.Utils -->
- <class name="Utils" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="Utils"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <doc>
- <![CDATA[A utility class. It provides
- A path filter utility to filter out output/part files in the output dir]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.Utils -->
- <!-- start class org.apache.hadoop.mapred.Utils.OutputFileUtils -->
- <class name="Utils.OutputFileUtils" extends="java.lang.Object"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="Utils.OutputFileUtils"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- </class>
- <!-- end class org.apache.hadoop.mapred.Utils.OutputFileUtils -->
- <!-- start class org.apache.hadoop.mapred.Utils.OutputFileUtils.OutputFilesFilter -->
- <class name="Utils.OutputFileUtils.OutputFilesFilter" extends="org.apache.hadoop.mapred.Utils.OutputFileUtils.OutputLogFilter"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="Utils.OutputFileUtils.OutputFilesFilter"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="accept" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="path" type="org.apache.hadoop.fs.Path"/>
- </method>
- <doc>
- <![CDATA[This class filters output(part) files from the given directory
- It does not accept files with filenames _logs and _SUCCESS.
- This can be used to list paths of output directory as follows:
- Path[] fileList = FileUtil.stat2Paths(fs.listStatus(outDir,
- new OutputFilesFilter()));]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.Utils.OutputFileUtils.OutputFilesFilter -->
- <!-- start class org.apache.hadoop.mapred.Utils.OutputFileUtils.OutputLogFilter -->
- <class name="Utils.OutputFileUtils.OutputLogFilter" extends="java.lang.Object"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.fs.PathFilter"/>
- <constructor name="Utils.OutputFileUtils.OutputLogFilter"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="accept" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="path" type="org.apache.hadoop.fs.Path"/>
- </method>
- <doc>
- <![CDATA[This class filters log files from directory given
- It doesnt accept paths having _logs.
- This can be used to list paths of output directory as follows:
- Path[] fileList = FileUtil.stat2Paths(fs.listStatus(outDir,
- new OutputLogFilter()));]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.Utils.OutputFileUtils.OutputLogFilter -->
- </package>
- <package name="org.apache.hadoop.mapred.jobcontrol">
- <!-- start class org.apache.hadoop.mapred.jobcontrol.Job -->
- <class name="Job" extends="org.apache.hadoop.mapreduce.lib.jobcontrol.ControlledJob"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link ControlledJob} instead.">
- <constructor name="Job" type="org.apache.hadoop.mapred.JobConf, java.util.ArrayList"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Construct a job.
- @param jobConf a mapred job configuration representing a job to be executed.
- @param dependingJobs an array of jobs the current job depends on]]>
- </doc>
- </constructor>
- <constructor name="Job" type="org.apache.hadoop.mapred.JobConf"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </constructor>
- <method name="getAssignedJobID" return="org.apache.hadoop.mapred.JobID"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the mapred ID of this job as assigned by the
- mapred framework.]]>
- </doc>
- </method>
- <method name="setAssignedJobID"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="setAssignedJobID should not be called.
- JOBID is set by the framework.">
- <param name="mapredJobID" type="org.apache.hadoop.mapred.JobID"/>
- <doc>
- <![CDATA[@deprecated setAssignedJobID should not be called.
- JOBID is set by the framework.]]>
- </doc>
- </method>
- <method name="getJobConf" return="org.apache.hadoop.mapred.JobConf"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the mapred job conf of this job]]>
- </doc>
- </method>
- <method name="setJobConf"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobConf" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[Set the mapred job conf for this job.
- @param jobConf the mapred job conf for this job.]]>
- </doc>
- </method>
- <method name="getState" return="int"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the state of this job]]>
- </doc>
- </method>
- <method name="getJobClient" return="org.apache.hadoop.mapred.JobClient"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the job client of this job]]>
- </doc>
- </method>
- <method name="getDependingJobs" return="java.util.ArrayList"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the depending jobs of this job]]>
- </doc>
- </method>
- <field name="SUCCESS" type="int"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="WAITING" type="int"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="RUNNING" type="int"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="READY" type="int"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="FAILED" type="int"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="DEPENDENT_FAILED" type="int"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[@deprecated Use {@link ControlledJob} instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.jobcontrol.Job -->
- <!-- start class org.apache.hadoop.mapred.jobcontrol.JobControl -->
- <class name="JobControl" extends="org.apache.hadoop.mapreduce.lib.jobcontrol.JobControl"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.jobcontrol.JobControl} instead">
- <constructor name="JobControl" type="java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Construct a job control for a group of jobs.
- @param groupName a name identifying this group]]>
- </doc>
- </constructor>
- <method name="getWaitingJobs" return="java.util.ArrayList"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the jobs in the waiting state]]>
- </doc>
- </method>
- <method name="getRunningJobs" return="java.util.ArrayList"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the jobs in the running state]]>
- </doc>
- </method>
- <method name="getReadyJobs" return="java.util.ArrayList"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the jobs in the ready state]]>
- </doc>
- </method>
- <method name="getSuccessfulJobs" return="java.util.ArrayList"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the jobs in the success state]]>
- </doc>
- </method>
- <method name="getFailedJobs" return="java.util.ArrayList"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="addJobs"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobs" type="java.util.Collection"/>
- <doc>
- <![CDATA[Add a collection of jobs
-
- @param jobs]]>
- </doc>
- </method>
- <method name="getState" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the thread state]]>
- </doc>
- </method>
- <doc>
- <![CDATA[@deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.jobcontrol.JobControl} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.jobcontrol.JobControl -->
- </package>
- <package name="org.apache.hadoop.mapred.join">
- <!-- start class org.apache.hadoop.mapred.join.ArrayListBackedIterator -->
- <class name="ArrayListBackedIterator" extends="org.apache.hadoop.mapreduce.lib.join.ArrayListBackedIterator"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.join.ArrayListBackedIterator} instead">
- <implements name="org.apache.hadoop.mapred.join.ResetableIterator"/>
- <constructor name="ArrayListBackedIterator"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <constructor name="ArrayListBackedIterator" type="java.util.ArrayList"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <doc>
- <![CDATA[This class provides an implementation of ResetableIterator. The
- implementation uses an {@link java.util.ArrayList} to store elements
- added to it, replaying them as requested.
- Prefer {@link StreamBackedIterator}.
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.join.ArrayListBackedIterator} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.join.ArrayListBackedIterator -->
- <!-- start interface org.apache.hadoop.mapred.join.ComposableInputFormat -->
- <interface name="ComposableInputFormat" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.join.ComposableInputFormat} instead">
- <implements name="org.apache.hadoop.mapred.InputFormat"/>
- <method name="getRecordReader" return="org.apache.hadoop.mapred.join.ComposableRecordReader"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapred.InputSplit"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[Refinement of InputFormat requiring implementors to provide
- ComposableRecordReader instead of RecordReader.
-
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.join.ComposableInputFormat} instead]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.join.ComposableInputFormat -->
- <!-- start interface org.apache.hadoop.mapred.join.ComposableRecordReader -->
- <interface name="ComposableRecordReader" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.join.ComposableRecordReader} instead">
- <implements name="org.apache.hadoop.mapred.RecordReader"/>
- <implements name="java.lang.Comparable"/>
- <method name="id" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Return the position in the collector this class occupies.]]>
- </doc>
- </method>
- <method name="key" return="K"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Return the key this RecordReader would supply on a call to next(K,V)]]>
- </doc>
- </method>
- <method name="key"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Clone the key at the head of this RecordReader into the object provided.]]>
- </doc>
- </method>
- <method name="hasNext" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns true if the stream is not empty, but provides no guarantee that
- a call to next(K,V) will succeed.]]>
- </doc>
- </method>
- <method name="skip"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Skip key-value pairs with keys less than or equal to the key provided.]]>
- </doc>
- </method>
- <method name="accept"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jc" type="org.apache.hadoop.mapred.join.CompositeRecordReader.JoinCollector"/>
- <param name="key" type="K"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[While key-value pairs from this RecordReader match the given key, register
- them with the JoinCollector provided.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Additional operations required of a RecordReader to participate in a join.
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.join.ComposableRecordReader} instead]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.join.ComposableRecordReader -->
- <!-- start class org.apache.hadoop.mapred.join.CompositeInputFormat -->
- <class name="CompositeInputFormat" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.join.CompositeInputFormat} instead">
- <implements name="org.apache.hadoop.mapred.join.ComposableInputFormat"/>
- <constructor name="CompositeInputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setFormat"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Interpret a given string as a composite expression.
- {@code
- func ::= <ident>([<func>,]*<func>)
- func ::= tbl(<class>,"<path>")
- class ::= @see java.lang.Class#forName(java.lang.String)
- path ::= @see org.apache.hadoop.fs.Path#Path(java.lang.String)
- }
- Reads expression from the <tt>mapred.join.expr</tt> property and
- user-supplied join types from <tt>mapred.join.define.<ident></tt>
- types. Paths supplied to <tt>tbl</tt> are given as input paths to the
- InputFormat class listed.
- @see #compose(java.lang.String, java.lang.Class, java.lang.String...)]]>
- </doc>
- </method>
- <method name="addDefaults"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Adds the default set of identifiers to the parser.]]>
- </doc>
- </method>
- <method name="getSplits" return="org.apache.hadoop.mapred.InputSplit[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="numSplits" type="int"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Build a CompositeInputSplit from the child InputFormats by assigning the
- ith split from each child to the ith composite split.]]>
- </doc>
- </method>
- <method name="getRecordReader" return="org.apache.hadoop.mapred.join.ComposableRecordReader"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapred.InputSplit"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Construct a CompositeRecordReader for the children of this InputFormat
- as defined in the init expression.
- The outermost join need only be composable, not necessarily a composite.
- Mandating TupleWritable isn't strictly correct.]]>
- </doc>
- </method>
- <method name="compose" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="inf" type="java.lang.Class"/>
- <param name="path" type="java.lang.String"/>
- <doc>
- <![CDATA[Convenience method for constructing composite formats.
- Given InputFormat class (inf), path (p) return:
- {@code tbl(<inf>, <p>) }]]>
- </doc>
- </method>
- <method name="compose" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="op" type="java.lang.String"/>
- <param name="inf" type="java.lang.Class"/>
- <param name="path" type="java.lang.String[]"/>
- <doc>
- <![CDATA[Convenience method for constructing composite formats.
- Given operation (op), Object class (inf), set of paths (p) return:
- {@code <op>(tbl(<inf>,<p1>),tbl(<inf>,<p2>),...,tbl(<inf>,<pn>)) }]]>
- </doc>
- </method>
- <method name="compose" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="op" type="java.lang.String"/>
- <param name="inf" type="java.lang.Class"/>
- <param name="path" type="org.apache.hadoop.fs.Path[]"/>
- <doc>
- <![CDATA[Convenience method for constructing composite formats.
- Given operation (op), Object class (inf), set of paths (p) return:
- {@code <op>(tbl(<inf>,<p1>),tbl(<inf>,<p2>),...,tbl(<inf>,<pn>)) }]]>
- </doc>
- </method>
- <doc>
- <![CDATA[An InputFormat capable of performing joins over a set of data sources sorted
- and partitioned the same way.
- @see #setFormat
- A user may define new join types by setting the property
- <tt>mapred.join.define.<ident></tt> to a classname. In the expression
- <tt>mapred.join.expr</tt>, the identifier will be assumed to be a
- ComposableRecordReader.
- <tt>mapred.join.keycomparator</tt> can be a classname used to compare keys
- in the join.
- @see JoinRecordReader
- @see MultiFilterRecordReader
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.join.CompositeInputFormat} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.join.CompositeInputFormat -->
- <!-- start class org.apache.hadoop.mapred.join.CompositeInputSplit -->
- <class name="CompositeInputSplit" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.join.CompositeInputSplit} instead">
- <implements name="org.apache.hadoop.mapred.InputSplit"/>
- <constructor name="CompositeInputSplit"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <constructor name="CompositeInputSplit" type="int"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="add"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="s" type="org.apache.hadoop.mapred.InputSplit"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Add an InputSplit to this collection.
- @throws IOException If capacity was not specified during construction
- or if capacity has been reached.]]>
- </doc>
- </method>
- <method name="get" return="org.apache.hadoop.mapred.InputSplit"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="i" type="int"/>
- <doc>
- <![CDATA[Get ith child InputSplit.]]>
- </doc>
- </method>
- <method name="getLength" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Return the aggregate length of all child InputSplits currently added.]]>
- </doc>
- </method>
- <method name="getLength" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="i" type="int"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get the length of ith child InputSplit.]]>
- </doc>
- </method>
- <method name="getLocations" return="java.lang.String[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Collect a set of hosts from all child InputSplits.]]>
- </doc>
- </method>
- <method name="getLocation" return="java.lang.String[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="i" type="int"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[getLocations from ith InputSplit.]]>
- </doc>
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="out" type="java.io.DataOutput"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Write splits in the following format.
- {@code
- <count><class1><class2>...<classn><split1><split2>...<splitn>
- }]]>
- </doc>
- </method>
- <method name="readFields"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="in" type="java.io.DataInput"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[{@inheritDoc}
- @throws IOException If the child InputSplit cannot be read, typically
- for faliing access checks.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[This InputSplit contains a set of child InputSplits. Any InputSplit inserted
- into this collection must have a public default constructor.
-
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.join.CompositeInputSplit} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.join.CompositeInputSplit -->
- <!-- start class org.apache.hadoop.mapred.join.CompositeRecordReader -->
- <class name="CompositeRecordReader" extends="java.lang.Object"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.join.CompositeRecordReader} instead">
- <implements name="org.apache.hadoop.conf.Configurable"/>
- <constructor name="CompositeRecordReader" type="int, int, java.lang.Class"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Create a RecordReader with <tt>capacity</tt> children to position
- <tt>id</tt> in the parent reader.
- The id of a root CompositeRecordReader is -1 by convention, but relying
- on this is not recommended.]]>
- </doc>
- </constructor>
- <method name="combine" return="boolean"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="srcs" type="java.lang.Object[]"/>
- <param name="value" type="org.apache.hadoop.mapred.join.TupleWritable"/>
- </method>
- <method name="id" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Return the position in the collector this class occupies.]]>
- </doc>
- </method>
- <method name="setConf"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <method name="getConf" return="org.apache.hadoop.conf.Configuration"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <method name="getRecordReaderQueue" return="java.util.PriorityQueue"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Return sorted list of RecordReaders for this composite.]]>
- </doc>
- </method>
- <method name="getComparator" return="org.apache.hadoop.io.WritableComparator"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Return comparator defining the ordering for RecordReaders in this
- composite.]]>
- </doc>
- </method>
- <method name="add"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="rr" type="org.apache.hadoop.mapred.join.ComposableRecordReader"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Add a RecordReader to this collection.
- The id() of a RecordReader determines where in the Tuple its
- entry will appear. Adding RecordReaders with the same id has
- undefined behavior.]]>
- </doc>
- </method>
- <method name="key" return="K"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Return the key for the current join or the value at the top of the
- RecordReader heap.]]>
- </doc>
- </method>
- <method name="key"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Clone the key at the top of this RR into the given object.]]>
- </doc>
- </method>
- <method name="hasNext" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Return true if it is possible that this could emit more values.]]>
- </doc>
- </method>
- <method name="skip"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Pass skip key to child RRs.]]>
- </doc>
- </method>
- <method name="getDelegate" return="org.apache.hadoop.mapred.join.ResetableIterator"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Obtain an iterator over the child RRs apropos of the value type
- ultimately emitted from this join.]]>
- </doc>
- </method>
- <method name="accept"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jc" type="org.apache.hadoop.mapred.join.CompositeRecordReader.JoinCollector"/>
- <param name="key" type="K"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[If key provided matches that of this Composite, give JoinCollector
- iterator over values it may emit.]]>
- </doc>
- </method>
- <method name="fillJoinCollector"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="iterkey" type="K"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[For all child RRs offering the key provided, obtain an iterator
- at that position in the JoinCollector.]]>
- </doc>
- </method>
- <method name="compareTo" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="other" type="org.apache.hadoop.mapred.join.ComposableRecordReader"/>
- <doc>
- <![CDATA[Implement Comparable contract (compare key of join or head of heap
- with that of another).]]>
- </doc>
- </method>
- <method name="createKey" return="K"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Create a new key value common to all child RRs.
- @throws ClassCastException if key classes differ.]]>
- </doc>
- </method>
- <method name="createInternalValue" return="org.apache.hadoop.mapred.join.TupleWritable"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Create a value to be used internally for joins.]]>
- </doc>
- </method>
- <method name="getPos" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Unsupported (returns zero in all cases).]]>
- </doc>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Close all child RRs.]]>
- </doc>
- </method>
- <method name="getProgress" return="float"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Report progress as the minimum of all child RR progress.]]>
- </doc>
- </method>
- <field name="jc" type="org.apache.hadoop.mapred.join.CompositeRecordReader.JoinCollector"
- transient="false" volatile="false"
- static="false" final="true" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="kids" type="org.apache.hadoop.mapred.join.ComposableRecordReader[]"
- transient="false" volatile="false"
- static="false" final="true" visibility="protected"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[A RecordReader that can effect joins of RecordReaders sharing a common key
- type and partitioning.
-
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.join.CompositeRecordReader} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.join.CompositeRecordReader -->
- <!-- start class org.apache.hadoop.mapred.join.InnerJoinRecordReader -->
- <class name="InnerJoinRecordReader" extends="org.apache.hadoop.mapred.join.JoinRecordReader"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.join.InnerJoinRecordReader} instead.">
- <method name="combine" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="srcs" type="java.lang.Object[]"/>
- <param name="dst" type="org.apache.hadoop.mapred.join.TupleWritable"/>
- <doc>
- <![CDATA[Return true iff the tuple is full (all data sources contain this key).]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Full inner join.
-
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.join.InnerJoinRecordReader} instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.join.InnerJoinRecordReader -->
- <!-- start class org.apache.hadoop.mapred.join.JoinRecordReader -->
- <class name="JoinRecordReader" extends="org.apache.hadoop.mapred.join.CompositeRecordReader"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.join.JoinRecordReader} instead">
- <implements name="org.apache.hadoop.mapred.join.ComposableRecordReader"/>
- <constructor name="JoinRecordReader" type="int, org.apache.hadoop.mapred.JobConf, int, java.lang.Class"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </constructor>
- <method name="next" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <param name="value" type="org.apache.hadoop.mapred.join.TupleWritable"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Emit the next set of key, value pairs as defined by the child
- RecordReaders and operation associated with this composite RR.]]>
- </doc>
- </method>
- <method name="createValue" return="org.apache.hadoop.mapred.join.TupleWritable"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <method name="getDelegate" return="org.apache.hadoop.mapred.join.ResetableIterator"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Return an iterator wrapping the JoinCollector.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Base class for Composite joins returning Tuples of arbitrary Writables.
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.join.JoinRecordReader} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.join.JoinRecordReader -->
- <!-- start class org.apache.hadoop.mapred.join.JoinRecordReader.JoinDelegationIterator -->
- <class name="JoinRecordReader.JoinDelegationIterator" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapred.join.ResetableIterator"/>
- <constructor name="JoinRecordReader.JoinDelegationIterator"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </constructor>
- <method name="hasNext" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="next" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="val" type="org.apache.hadoop.mapred.join.TupleWritable"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="replay" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="val" type="org.apache.hadoop.mapred.join.TupleWritable"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="reset"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="add"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="item" type="org.apache.hadoop.mapred.join.TupleWritable"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="clear"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <doc>
- <![CDATA[Since the JoinCollector is effecting our operation, we need only
- provide an iterator proxy wrapping its operation.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.join.JoinRecordReader.JoinDelegationIterator -->
- <!-- start class org.apache.hadoop.mapred.join.MultiFilterRecordReader -->
- <class name="MultiFilterRecordReader" extends="org.apache.hadoop.mapred.join.CompositeRecordReader"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.join.MultiFilterRecordReader} instead">
- <implements name="org.apache.hadoop.mapred.join.ComposableRecordReader"/>
- <constructor name="MultiFilterRecordReader" type="int, org.apache.hadoop.mapred.JobConf, int, java.lang.Class"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </constructor>
- <method name="emit" return="V"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="dst" type="org.apache.hadoop.mapred.join.TupleWritable"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[For each tuple emitted, return a value (typically one of the values
- in the tuple).
- Modifying the Writables in the tuple is permitted and unlikely to affect
- join behavior in most cases, but it is not recommended. It's safer to
- clone first.]]>
- </doc>
- </method>
- <method name="combine" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="srcs" type="java.lang.Object[]"/>
- <param name="dst" type="org.apache.hadoop.mapred.join.TupleWritable"/>
- <doc>
- <![CDATA[Default implementation offers {@link #emit} every Tuple from the
- collector (the outer join of child RRs).]]>
- </doc>
- </method>
- <method name="next" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <param name="value" type="V"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <method name="createValue" return="V"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <method name="getDelegate" return="org.apache.hadoop.mapred.join.ResetableIterator"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Return an iterator returning a single value from the tuple.
- @see MultiFilterDelegationIterator]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Base class for Composite join returning values derived from multiple
- sources, but generally not tuples.
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.join.MultiFilterRecordReader} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.join.MultiFilterRecordReader -->
- <!-- start class org.apache.hadoop.mapred.join.MultiFilterRecordReader.MultiFilterDelegationIterator -->
- <class name="MultiFilterRecordReader.MultiFilterDelegationIterator" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapred.join.ResetableIterator"/>
- <constructor name="MultiFilterRecordReader.MultiFilterDelegationIterator"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </constructor>
- <method name="hasNext" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="next" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="val" type="V"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="replay" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="val" type="V"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="reset"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="add"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="item" type="V"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="clear"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <doc>
- <![CDATA[Proxy the JoinCollector, but include callback to emit.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.join.MultiFilterRecordReader.MultiFilterDelegationIterator -->
- <!-- start class org.apache.hadoop.mapred.join.OuterJoinRecordReader -->
- <class name="OuterJoinRecordReader" extends="org.apache.hadoop.mapred.join.JoinRecordReader"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.join.OuterJoinRecordReader} instead">
- <method name="combine" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="srcs" type="java.lang.Object[]"/>
- <param name="dst" type="org.apache.hadoop.mapred.join.TupleWritable"/>
- <doc>
- <![CDATA[Emit everything from the collector.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Full outer join.
-
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.join.OuterJoinRecordReader} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.join.OuterJoinRecordReader -->
- <!-- start class org.apache.hadoop.mapred.join.OverrideRecordReader -->
- <class name="OverrideRecordReader" extends="org.apache.hadoop.mapred.join.MultiFilterRecordReader"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.join.OverrideRecordReader} instead">
- <method name="emit" return="V"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="dst" type="org.apache.hadoop.mapred.join.TupleWritable"/>
- <doc>
- <![CDATA[Emit the value with the highest position in the tuple.]]>
- </doc>
- </method>
- <method name="fillJoinCollector"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="iterkey" type="K"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Instead of filling the JoinCollector with iterators from all
- data sources, fill only the rightmost for this key.
- This not only saves space by discarding the other sources, but
- it also emits the number of key-value pairs in the preferred
- RecordReader instead of repeating that stream n times, where
- n is the cardinality of the cross product of the discarded
- streams for the given key.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Prefer the "rightmost" data source for this key.
- For example, <tt>override(S1,S2,S3)</tt> will prefer values
- from S3 over S2, and values from S2 over S1 for all keys
- emitted from all sources.
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.join.OverrideRecordReader} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.join.OverrideRecordReader -->
- <!-- start class org.apache.hadoop.mapred.join.Parser -->
- <class name="Parser" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.lib.join.Parser} instead">
- <constructor name="Parser"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <doc>
- <![CDATA[Very simple shift-reduce parser for join expressions.
- This should be sufficient for the user extension permitted now, but ought to
- be replaced with a parser generator if more complex grammars are supported.
- In particular, this "shift-reduce" parser has no states. Each set
- of formals requires a different internal node type, which is responsible for
- interpreting the list of tokens it receives. This is sufficient for the
- current grammar, but it has several annoying properties that might inhibit
- extension. In particular, parenthesis are always function calls; an
- algebraic or filter grammar would not only require a node type, but must
- also work around the internals of this parser.
- For most other cases, adding classes to the hierarchy- particularly by
- extending JoinRecordReader and MultiFilterRecordReader- is fairly
- straightforward. One need only override the relevant method(s) (usually only
- {@link CompositeRecordReader#combine}) and include a property to map its
- value to an identifier in the parser.
- @deprecated Use {@link org.apache.hadoop.mapreduce.lib.join.Parser} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.join.Parser -->
- <!-- start class org.apache.hadoop.mapred.join.Parser.Node -->
- <class name="Parser.Node" extends="java.lang.Object"
- abstract="true"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapred.join.ComposableInputFormat"/>
- <constructor name="Parser.Node" type="java.lang.String"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </constructor>
- <method name="addIdentifier"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="ident" type="java.lang.String"/>
- <param name="mcstrSig" type="java.lang.Class[]"/>
- <param name="nodetype" type="java.lang.Class"/>
- <param name="cl" type="java.lang.Class"/>
- <exception name="NoSuchMethodException" type="java.lang.NoSuchMethodException"/>
- <doc>
- <![CDATA[For a given identifier, add a mapping to the nodetype for the parse
- tree and to the ComposableRecordReader to be created, including the
- formals required to invoke the constructor.
- The nodetype and constructor signature should be filled in from the
- child node.]]>
- </doc>
- </method>
- <method name="setID"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="id" type="int"/>
- </method>
- <method name="setKeyComparator"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="cmpcl" type="java.lang.Class"/>
- </method>
- <field name="rrCstrMap" type="java.util.Map"
- transient="false" volatile="false"
- static="true" final="true" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="id" type="int"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="ident" type="java.lang.String"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="cmpcl" type="java.lang.Class"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- </class>
- <!-- end class org.apache.hadoop.mapred.join.Parser.Node -->
- <!-- start class org.apache.hadoop.mapred.join.Parser.NodeToken -->
- <class name="Parser.NodeToken" extends="org.apache.hadoop.mapred.join.Parser.Token"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <method name="getNode" return="org.apache.hadoop.mapred.join.Parser.Node"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- </class>
- <!-- end class org.apache.hadoop.mapred.join.Parser.NodeToken -->
- <!-- start class org.apache.hadoop.mapred.join.Parser.NumToken -->
- <class name="Parser.NumToken" extends="org.apache.hadoop.mapred.join.Parser.Token"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="Parser.NumToken" type="double"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getNum" return="double"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- </class>
- <!-- end class org.apache.hadoop.mapred.join.Parser.NumToken -->
- <!-- start class org.apache.hadoop.mapred.join.Parser.StrToken -->
- <class name="Parser.StrToken" extends="org.apache.hadoop.mapred.join.Parser.Token"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="Parser.StrToken" type="org.apache.hadoop.mapred.join.Parser.TType, java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getStr" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- </class>
- <!-- end class org.apache.hadoop.mapred.join.Parser.StrToken -->
- <!-- start class org.apache.hadoop.mapred.join.Parser.Token -->
- <class name="Parser.Token" extends="java.lang.Object"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <method name="getType" return="org.apache.hadoop.mapred.join.Parser.TType"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getNode" return="org.apache.hadoop.mapred.join.Parser.Node"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getNum" return="double"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getStr" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[Tagged-union type for tokens from the join expression.
- @see Parser.TType]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.join.Parser.Token -->
- <!-- start class org.apache.hadoop.mapred.join.Parser.TType -->
- <class name="Parser.TType" extends="java.lang.Enum"
- abstract="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <method name="values" return="org.apache.hadoop.mapred.join.Parser.TType[]"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="valueOf" return="org.apache.hadoop.mapred.join.Parser.TType"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- </method>
- </class>
- <!-- end class org.apache.hadoop.mapred.join.Parser.TType -->
- <!-- start interface org.apache.hadoop.mapred.join.ResetableIterator -->
- <interface name="ResetableIterator" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.join.ResetableIterator} instead">
- <implements name="org.apache.hadoop.mapreduce.lib.join.ResetableIterator"/>
- <doc>
- <![CDATA[This defines an interface to a stateful Iterator that can replay elements
- added to it directly.
- Note that this does not extend {@link java.util.Iterator}.
-
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.join.ResetableIterator} instead]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.join.ResetableIterator -->
- <!-- start class org.apache.hadoop.mapred.join.ResetableIterator.EMPTY -->
- <class name="ResetableIterator.EMPTY" extends="org.apache.hadoop.mapreduce.lib.join.ResetableIterator.EMPTY"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapred.join.ResetableIterator"/>
- <constructor name="ResetableIterator.EMPTY"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- </class>
- <!-- end class org.apache.hadoop.mapred.join.ResetableIterator.EMPTY -->
- <!-- start class org.apache.hadoop.mapred.join.StreamBackedIterator -->
- <class name="StreamBackedIterator" extends="org.apache.hadoop.mapreduce.lib.join.StreamBackedIterator"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.join.StreamBackedIterator} instead">
- <implements name="org.apache.hadoop.mapred.join.ResetableIterator"/>
- <constructor name="StreamBackedIterator"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <doc>
- <![CDATA[This class provides an implementation of ResetableIterator. This
- implementation uses a byte array to store elements added to it.
-
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.join.StreamBackedIterator} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.join.StreamBackedIterator -->
- <!-- start class org.apache.hadoop.mapred.join.TupleWritable -->
- <class name="TupleWritable" extends="org.apache.hadoop.mapreduce.lib.join.TupleWritable"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.join.TupleWritable} instead">
- <constructor name="TupleWritable"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Create an empty tuple with no allocated storage for writables.]]>
- </doc>
- </constructor>
- <constructor name="TupleWritable" type="org.apache.hadoop.io.Writable[]"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Initialize tuple with storage; unknown whether any of them contain
- "written" values.]]>
- </doc>
- </constructor>
- <doc>
- <![CDATA[Writable type storing multiple {@link org.apache.hadoop.io.Writable}s.
- This is *not* a general-purpose tuple type. In almost all cases, users are
- encouraged to implement their own serializable types, which can perform
- better validation and provide more efficient encodings than this class is
- capable. TupleWritable relies on the join framework for type safety and
- assumes its instances will rarely be persisted, assumptions not only
- incompatible with, but contrary to the general case.
- @see org.apache.hadoop.io.Writable
-
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.join.TupleWritable} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.join.TupleWritable -->
- <!-- start class org.apache.hadoop.mapred.join.WrappedRecordReader -->
- <class name="WrappedRecordReader" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.join.WrappedRecordReader} instead">
- <implements name="org.apache.hadoop.mapred.join.ComposableRecordReader"/>
- <method name="id" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <method name="key" return="K"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Return the key at the head of this RR.]]>
- </doc>
- </method>
- <method name="key"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="qkey" type="K"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Clone the key at the head of this RR into the object supplied.]]>
- </doc>
- </method>
- <method name="hasNext" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Return true if the RR- including the k,v pair stored in this object-
- is exhausted.]]>
- </doc>
- </method>
- <method name="skip"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Skip key-value pairs with keys less than or equal to the key provided.]]>
- </doc>
- </method>
- <method name="next" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Read the next k,v pair into the head of this object; return true iff
- the RR and this are exhausted.]]>
- </doc>
- </method>
- <method name="accept"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="i" type="org.apache.hadoop.mapred.join.CompositeRecordReader.JoinCollector"/>
- <param name="key" type="K"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Add an iterator to the collector at the position occupied by this
- RecordReader over the values in this stream paired with the key
- provided (ie register a stream of values from this source matching K
- with a collector).]]>
- </doc>
- </method>
- <method name="next" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <param name="value" type="U"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Write key-value pair at the head of this stream to the objects provided;
- get next key-value pair from proxied RR.]]>
- </doc>
- </method>
- <method name="createKey" return="K"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Request new key from proxied RR.]]>
- </doc>
- </method>
- <method name="createValue" return="U"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Request new value from proxied RR.]]>
- </doc>
- </method>
- <method name="getProgress" return="float"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Request progress from proxied RR.]]>
- </doc>
- </method>
- <method name="getPos" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Request position from proxied RR.]]>
- </doc>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Forward close request to proxied RR.]]>
- </doc>
- </method>
- <method name="compareTo" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="other" type="org.apache.hadoop.mapred.join.ComposableRecordReader"/>
- <doc>
- <![CDATA[Implement Comparable contract (compare key at head of proxied RR
- with that of another).]]>
- </doc>
- </method>
- <method name="equals" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="other" type="java.lang.Object"/>
- <doc>
- <![CDATA[Return true iff compareTo(other) retn true.]]>
- </doc>
- </method>
- <method name="hashCode" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <doc>
- <![CDATA[Proxy class for a RecordReader participating in the join framework.
- This class keeps track of the "head" key-value pair for the
- provided RecordReader and keeps a store of values matching a key when
- this source is participating in a join.
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.join.WrappedRecordReader} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.join.WrappedRecordReader -->
- </package>
- <package name="org.apache.hadoop.mapred.lib">
- <!-- start class org.apache.hadoop.mapred.lib.BinaryPartitioner -->
- <class name="BinaryPartitioner" extends="org.apache.hadoop.mapreduce.lib.partition.BinaryPartitioner"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.partition.BinaryPartitioner}
- instead.">
- <implements name="org.apache.hadoop.mapred.Partitioner"/>
- <constructor name="BinaryPartitioner"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="configure"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- </method>
- <doc>
- <![CDATA[Partition {@link BinaryComparable} keys using a configurable part of
- the bytes array returned by {@link BinaryComparable#getBytes()}.
-
- @see org.apache.hadoop.mapreduce.lib.partition.BinaryPartitioner
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.partition.BinaryPartitioner}
- instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.BinaryPartitioner -->
- <!-- start class org.apache.hadoop.mapred.lib.ChainMapper -->
- <class name="ChainMapper" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.lib.chain.ChainMapper} instead">
- <implements name="org.apache.hadoop.mapred.Mapper"/>
- <constructor name="ChainMapper"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Constructor.]]>
- </doc>
- </constructor>
- <method name="addMapper"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="klass" type="java.lang.Class"/>
- <param name="inputKeyClass" type="java.lang.Class"/>
- <param name="inputValueClass" type="java.lang.Class"/>
- <param name="outputKeyClass" type="java.lang.Class"/>
- <param name="outputValueClass" type="java.lang.Class"/>
- <param name="byValue" type="boolean"/>
- <param name="mapperConf" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[Adds a Mapper class to the chain job's JobConf.
- <p/>
- It has to be specified how key and values are passed from one element of
- the chain to the next, by value or by reference. If a Mapper leverages the
- assumed semantics that the key and values are not modified by the collector
- 'by value' must be used. If the Mapper does not expect this semantics, as
- an optimization to avoid serialization and deserialization 'by reference'
- can be used.
- <p/>
- For the added Mapper the configuration given for it,
- <code>mapperConf</code>, have precedence over the job's JobConf. This
- precedence is in effect when the task is running.
- <p/>
- IMPORTANT: There is no need to specify the output key/value classes for the
- ChainMapper, this is done by the addMapper for the last mapper in the chain
- <p/>
- @param job job's JobConf to add the Mapper class.
- @param klass the Mapper class to add.
- @param inputKeyClass mapper input key class.
- @param inputValueClass mapper input value class.
- @param outputKeyClass mapper output key class.
- @param outputValueClass mapper output value class.
- @param byValue indicates if key/values should be passed by value
- to the next Mapper in the chain, if any.
- @param mapperConf a JobConf with the configuration for the Mapper
- class. It is recommended to use a JobConf without default values using the
- <code>JobConf(boolean loadDefaults)</code> constructor with FALSE.]]>
- </doc>
- </method>
- <method name="configure"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[Configures the ChainMapper and all the Mappers in the chain.
- <p/>
- If this method is overriden <code>super.configure(...)</code> should be
- invoked at the beginning of the overwriter method.]]>
- </doc>
- </method>
- <method name="map"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="java.lang.Object"/>
- <param name="value" type="java.lang.Object"/>
- <param name="output" type="org.apache.hadoop.mapred.OutputCollector"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Chains the <code>map(...)</code> methods of the Mappers in the chain.]]>
- </doc>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Closes the ChainMapper and all the Mappers in the chain.
- <p/>
- If this method is overriden <code>super.close()</code> should be
- invoked at the end of the overwriter method.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[The ChainMapper class allows to use multiple Mapper classes within a single
- Map task.
- <p/>
- The Mapper classes are invoked in a chained (or piped) fashion, the output of
- the first becomes the input of the second, and so on until the last Mapper,
- the output of the last Mapper will be written to the task's output.
- <p/>
- The key functionality of this feature is that the Mappers in the chain do not
- need to be aware that they are executed in a chain. This enables having
- reusable specialized Mappers that can be combined to perform composite
- operations within a single task.
- <p/>
- Special care has to be taken when creating chains that the key/values output
- by a Mapper are valid for the following Mapper in the chain. It is assumed
- all Mappers and the Reduce in the chain use maching output and input key and
- value classes as no conversion is done by the chaining code.
- <p/>
- Using the ChainMapper and the ChainReducer classes is possible to compose
- Map/Reduce jobs that look like <code>[MAP+ / REDUCE MAP*]</code>. And
- immediate benefit of this pattern is a dramatic reduction in disk IO.
- <p/>
- IMPORTANT: There is no need to specify the output key/value classes for the
- ChainMapper, this is done by the addMapper for the last mapper in the chain.
- <p/>
- ChainMapper usage pattern:
- <p/>
- <pre>
- ...
- conf.setJobName("chain");
- conf.setInputFormat(TextInputFormat.class);
- conf.setOutputFormat(TextOutputFormat.class);
- <p/>
- JobConf mapAConf = new JobConf(false);
- ...
- ChainMapper.addMapper(conf, AMap.class, LongWritable.class, Text.class,
- Text.class, Text.class, true, mapAConf);
- <p/>
- JobConf mapBConf = new JobConf(false);
- ...
- ChainMapper.addMapper(conf, BMap.class, Text.class, Text.class,
- LongWritable.class, Text.class, false, mapBConf);
- <p/>
- JobConf reduceConf = new JobConf(false);
- ...
- ChainReducer.setReducer(conf, XReduce.class, LongWritable.class, Text.class,
- Text.class, Text.class, true, reduceConf);
- <p/>
- ChainReducer.addMapper(conf, CMap.class, Text.class, Text.class,
- LongWritable.class, Text.class, false, null);
- <p/>
- ChainReducer.addMapper(conf, DMap.class, LongWritable.class, Text.class,
- LongWritable.class, LongWritable.class, true, null);
- <p/>
- FileInputFormat.setInputPaths(conf, inDir);
- FileOutputFormat.setOutputPath(conf, outDir);
- ...
- <p/>
- JobClient jc = new JobClient(conf);
- RunningJob job = jc.submitJob(conf);
- ...
- </pre>
- @deprecated
- Use {@link org.apache.hadoop.mapreduce.lib.chain.ChainMapper} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.ChainMapper -->
- <!-- start class org.apache.hadoop.mapred.lib.ChainReducer -->
- <class name="ChainReducer" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.lib.chain.ChainReducer} instead">
- <implements name="org.apache.hadoop.mapred.Reducer"/>
- <constructor name="ChainReducer"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Constructor.]]>
- </doc>
- </constructor>
- <method name="setReducer"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="klass" type="java.lang.Class"/>
- <param name="inputKeyClass" type="java.lang.Class"/>
- <param name="inputValueClass" type="java.lang.Class"/>
- <param name="outputKeyClass" type="java.lang.Class"/>
- <param name="outputValueClass" type="java.lang.Class"/>
- <param name="byValue" type="boolean"/>
- <param name="reducerConf" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[Sets the Reducer class to the chain job's JobConf.
- <p/>
- It has to be specified how key and values are passed from one element of
- the chain to the next, by value or by reference. If a Reducer leverages the
- assumed semantics that the key and values are not modified by the collector
- 'by value' must be used. If the Reducer does not expect this semantics, as
- an optimization to avoid serialization and deserialization 'by reference'
- can be used.
- <p/>
- For the added Reducer the configuration given for it,
- <code>reducerConf</code>, have precedence over the job's JobConf. This
- precedence is in effect when the task is running.
- <p/>
- IMPORTANT: There is no need to specify the output key/value classes for the
- ChainReducer, this is done by the setReducer or the addMapper for the last
- element in the chain.
- @param job job's JobConf to add the Reducer class.
- @param klass the Reducer class to add.
- @param inputKeyClass reducer input key class.
- @param inputValueClass reducer input value class.
- @param outputKeyClass reducer output key class.
- @param outputValueClass reducer output value class.
- @param byValue indicates if key/values should be passed by value
- to the next Mapper in the chain, if any.
- @param reducerConf a JobConf with the configuration for the Reducer
- class. It is recommended to use a JobConf without default values using the
- <code>JobConf(boolean loadDefaults)</code> constructor with FALSE.]]>
- </doc>
- </method>
- <method name="addMapper"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="klass" type="java.lang.Class"/>
- <param name="inputKeyClass" type="java.lang.Class"/>
- <param name="inputValueClass" type="java.lang.Class"/>
- <param name="outputKeyClass" type="java.lang.Class"/>
- <param name="outputValueClass" type="java.lang.Class"/>
- <param name="byValue" type="boolean"/>
- <param name="mapperConf" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[Adds a Mapper class to the chain job's JobConf.
- <p/>
- It has to be specified how key and values are passed from one element of
- the chain to the next, by value or by reference. If a Mapper leverages the
- assumed semantics that the key and values are not modified by the collector
- 'by value' must be used. If the Mapper does not expect this semantics, as
- an optimization to avoid serialization and deserialization 'by reference'
- can be used.
- <p/>
- For the added Mapper the configuration given for it,
- <code>mapperConf</code>, have precedence over the job's JobConf. This
- precedence is in effect when the task is running.
- <p/>
- IMPORTANT: There is no need to specify the output key/value classes for the
- ChainMapper, this is done by the addMapper for the last mapper in the chain
- .
- @param job chain job's JobConf to add the Mapper class.
- @param klass the Mapper class to add.
- @param inputKeyClass mapper input key class.
- @param inputValueClass mapper input value class.
- @param outputKeyClass mapper output key class.
- @param outputValueClass mapper output value class.
- @param byValue indicates if key/values should be passed by value
- to the next Mapper in the chain, if any.
- @param mapperConf a JobConf with the configuration for the Mapper
- class. It is recommended to use a JobConf without default values using the
- <code>JobConf(boolean loadDefaults)</code> constructor with FALSE.]]>
- </doc>
- </method>
- <method name="configure"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[Configures the ChainReducer, the Reducer and all the Mappers in the chain.
- <p/>
- If this method is overriden <code>super.configure(...)</code> should be
- invoked at the beginning of the overwriter method.]]>
- </doc>
- </method>
- <method name="reduce"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="java.lang.Object"/>
- <param name="values" type="java.util.Iterator"/>
- <param name="output" type="org.apache.hadoop.mapred.OutputCollector"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Chains the <code>reduce(...)</code> method of the Reducer with the
- <code>map(...) </code> methods of the Mappers in the chain.]]>
- </doc>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Closes the ChainReducer, the Reducer and all the Mappers in the chain.
- <p/>
- If this method is overriden <code>super.close()</code> should be
- invoked at the end of the overwriter method.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[The ChainReducer class allows to chain multiple Mapper classes after a
- Reducer within the Reducer task.
- <p/>
- For each record output by the Reducer, the Mapper classes are invoked in a
- chained (or piped) fashion, the output of the first becomes the input of the
- second, and so on until the last Mapper, the output of the last Mapper will
- be written to the task's output.
- <p/>
- The key functionality of this feature is that the Mappers in the chain do not
- need to be aware that they are executed after the Reducer or in a chain.
- This enables having reusable specialized Mappers that can be combined to
- perform composite operations within a single task.
- <p/>
- Special care has to be taken when creating chains that the key/values output
- by a Mapper are valid for the following Mapper in the chain. It is assumed
- all Mappers and the Reduce in the chain use maching output and input key and
- value classes as no conversion is done by the chaining code.
- <p/>
- Using the ChainMapper and the ChainReducer classes is possible to compose
- Map/Reduce jobs that look like <code>[MAP+ / REDUCE MAP*]</code>. And
- immediate benefit of this pattern is a dramatic reduction in disk IO.
- <p/>
- IMPORTANT: There is no need to specify the output key/value classes for the
- ChainReducer, this is done by the setReducer or the addMapper for the last
- element in the chain.
- <p/>
- ChainReducer usage pattern:
- <p/>
- <pre>
- ...
- conf.setJobName("chain");
- conf.setInputFormat(TextInputFormat.class);
- conf.setOutputFormat(TextOutputFormat.class);
- <p/>
- JobConf mapAConf = new JobConf(false);
- ...
- ChainMapper.addMapper(conf, AMap.class, LongWritable.class, Text.class,
- Text.class, Text.class, true, mapAConf);
- <p/>
- JobConf mapBConf = new JobConf(false);
- ...
- ChainMapper.addMapper(conf, BMap.class, Text.class, Text.class,
- LongWritable.class, Text.class, false, mapBConf);
- <p/>
- JobConf reduceConf = new JobConf(false);
- ...
- ChainReducer.setReducer(conf, XReduce.class, LongWritable.class, Text.class,
- Text.class, Text.class, true, reduceConf);
- <p/>
- ChainReducer.addMapper(conf, CMap.class, Text.class, Text.class,
- LongWritable.class, Text.class, false, null);
- <p/>
- ChainReducer.addMapper(conf, DMap.class, LongWritable.class, Text.class,
- LongWritable.class, LongWritable.class, true, null);
- <p/>
- FileInputFormat.setInputPaths(conf, inDir);
- FileOutputFormat.setOutputPath(conf, outDir);
- ...
- <p/>
- JobClient jc = new JobClient(conf);
- RunningJob job = jc.submitJob(conf);
- ...
- </pre>
- @deprecated
- Use {@link org.apache.hadoop.mapreduce.lib.chain.ChainReducer} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.ChainReducer -->
- <!-- start class org.apache.hadoop.mapred.lib.CombineFileInputFormat -->
- <class name="CombineFileInputFormat" extends="org.apache.hadoop.mapreduce.lib.input.CombineFileInputFormat"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.input.CombineFileInputFormat}">
- <implements name="org.apache.hadoop.mapred.InputFormat"/>
- <constructor name="CombineFileInputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[default constructor]]>
- </doc>
- </constructor>
- <method name="getSplits" return="org.apache.hadoop.mapred.InputSplit[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="numSplits" type="int"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="createPool"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="Use {@link #createPool(List)}.">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="filters" type="java.util.List"/>
- <doc>
- <![CDATA[Create a new pool and add the filters to it.
- A split cannot have files from different pools.
- @deprecated Use {@link #createPool(List)}.]]>
- </doc>
- </method>
- <method name="createPool"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="Use {@link #createPool(PathFilter...)}.">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="filters" type="org.apache.hadoop.fs.PathFilter[]"/>
- <doc>
- <![CDATA[Create a new pool and add the filters to it.
- A pathname can satisfy any one of the specified filters.
- A split cannot have files from different pools.
- @deprecated Use {@link #createPool(PathFilter...)}.]]>
- </doc>
- </method>
- <method name="getRecordReader" return="org.apache.hadoop.mapred.RecordReader"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapred.InputSplit"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[This is not implemented yet.]]>
- </doc>
- </method>
- <method name="createRecordReader" return="org.apache.hadoop.mapreduce.RecordReader"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapreduce.InputSplit"/>
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[An abstract {@link org.apache.hadoop.mapred.InputFormat} that returns {@link CombineFileSplit}'s
- in {@link org.apache.hadoop.mapred.InputFormat#getSplits(JobConf, int)} method.
- Splits are constructed from the files under the input paths.
- A split cannot have files from different pools.
- Each split returned may contain blocks from different files.
- If a maxSplitSize is specified, then blocks on the same node are
- combined to form a single split. Blocks that are left over are
- then combined with other blocks in the same rack.
- If maxSplitSize is not specified, then blocks from the same rack
- are combined in a single split; no attempt is made to create
- node-local splits.
- If the maxSplitSize is equal to the block size, then this class
- is similar to the default spliting behaviour in Hadoop: each
- block is a locally processed split.
- Subclasses implement {@link org.apache.hadoop.mapred.InputFormat#getRecordReader(InputSplit, JobConf, Reporter)}
- to construct <code>RecordReader</code>'s for <code>CombineFileSplit</code>'s.
- @see CombineFileSplit
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.input.CombineFileInputFormat}]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.CombineFileInputFormat -->
- <!-- start class org.apache.hadoop.mapred.lib.CombineFileRecordReader -->
- <class name="CombineFileRecordReader" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.input.CombineFileRecordReader}">
- <implements name="org.apache.hadoop.mapred.RecordReader"/>
- <constructor name="CombineFileRecordReader" type="org.apache.hadoop.mapred.JobConf, org.apache.hadoop.mapred.lib.CombineFileSplit, org.apache.hadoop.mapred.Reporter, java.lang.Class"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[A generic RecordReader that can hand out different recordReaders
- for each chunk in the CombineFileSplit.]]>
- </doc>
- </constructor>
- <method name="next" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <param name="value" type="V"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="createKey" return="K"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="createValue" return="V"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getPos" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[return the amount of data processed]]>
- </doc>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getProgress" return="float"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[return progress based on the amount of data processed so far.]]>
- </doc>
- </method>
- <method name="initNextRecordReader" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get the record reader for the next chunk in this CombineFileSplit.]]>
- </doc>
- </method>
- <field name="split" type="org.apache.hadoop.mapred.lib.CombineFileSplit"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="jc" type="org.apache.hadoop.mapred.JobConf"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="reporter" type="org.apache.hadoop.mapred.Reporter"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="rrClass" type="java.lang.Class"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="rrConstructor" type="java.lang.reflect.Constructor"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="fs" type="org.apache.hadoop.fs.FileSystem"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="idx" type="int"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="progress" type="long"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="curReader" type="org.apache.hadoop.mapred.RecordReader"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[A generic RecordReader that can hand out different recordReaders
- for each chunk in a {@link CombineFileSplit}.
- A CombineFileSplit can combine data chunks from multiple files.
- This class allows using different RecordReaders for processing
- these data chunks from different files.
- @see CombineFileSplit
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.input.CombineFileRecordReader}]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.CombineFileRecordReader -->
- <!-- start class org.apache.hadoop.mapred.lib.CombineFileSplit -->
- <class name="CombineFileSplit" extends="org.apache.hadoop.mapreduce.lib.input.CombineFileSplit"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.input.CombineFileSplit}">
- <implements name="org.apache.hadoop.mapred.InputSplit"/>
- <constructor name="CombineFileSplit"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <constructor name="CombineFileSplit" type="org.apache.hadoop.mapred.JobConf, org.apache.hadoop.fs.Path[], long[], long[], java.lang.String[]"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <constructor name="CombineFileSplit" type="org.apache.hadoop.mapred.JobConf, org.apache.hadoop.fs.Path[], long[]"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <constructor name="CombineFileSplit" type="org.apache.hadoop.mapred.lib.CombineFileSplit"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Copy constructor]]>
- </doc>
- </constructor>
- <method name="getJob" return="org.apache.hadoop.mapred.JobConf"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <doc>
- <![CDATA[@deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.input.CombineFileSplit}]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.CombineFileSplit -->
- <!-- start class org.apache.hadoop.mapred.lib.FieldSelectionMapReduce -->
- <class name="FieldSelectionMapReduce" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link FieldSelectionMapper} and
- {@link FieldSelectionReducer} instead">
- <implements name="org.apache.hadoop.mapred.Mapper"/>
- <implements name="org.apache.hadoop.mapred.Reducer"/>
- <constructor name="FieldSelectionMapReduce"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="map"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <param name="val" type="V"/>
- <param name="output" type="org.apache.hadoop.mapred.OutputCollector"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[The identify function. Input key/value pair is written directly to output.]]>
- </doc>
- </method>
- <method name="configure"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="reduce"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="org.apache.hadoop.io.Text"/>
- <param name="values" type="java.util.Iterator"/>
- <param name="output" type="org.apache.hadoop.mapred.OutputCollector"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <field name="LOG" type="org.apache.commons.logging.Log"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[This class implements a mapper/reducer class that can be used to perform
- field selections in a manner similar to unix cut. The input data is treated
- as fields separated by a user specified separator (the default value is
- "\t"). The user can specify a list of fields that form the map output keys,
- and a list of fields that form the map output values. If the inputformat is
- TextInputFormat, the mapper will ignore the key to the map function. and the
- fields are from the value only. Otherwise, the fields are the union of those
- from the key and those from the value.
-
- The field separator is under attribute "mapreduce.fieldsel.data.field.separator"
-
- The map output field list spec is under attribute
- "mapreduce.fieldsel.map.output.key.value.fields.spec".
- The value is expected to be like "keyFieldsSpec:valueFieldsSpec"
- key/valueFieldsSpec are comma (,) separated field spec: fieldSpec,fieldSpec,fieldSpec ...
- Each field spec can be a simple number (e.g. 5) specifying a specific field, or a range
- (like 2-5) to specify a range of fields, or an open range (like 3-) specifying all
- the fields starting from field 3. The open range field spec applies value fields only.
- They have no effect on the key fields.
-
- Here is an example: "4,3,0,1:6,5,1-3,7-". It specifies to use fields 4,3,0 and 1 for keys,
- and use fields 6,5,1,2,3,7 and above for values.
-
- The reduce output field list spec is under attribute
- "mapreduce.fieldsel.reduce.output.key.value.fields.spec".
-
- The reducer extracts output key/value pairs in a similar manner, except that
- the key is never ignored.
- @deprecated Use {@link FieldSelectionMapper} and
- {@link FieldSelectionReducer} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.FieldSelectionMapReduce -->
- <!-- start class org.apache.hadoop.mapred.lib.FilterOutputFormat -->
- <class name="FilterOutputFormat" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.output.FilterOutputFormat} instead.">
- <implements name="org.apache.hadoop.mapred.OutputFormat"/>
- <constructor name="FilterOutputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <constructor name="FilterOutputFormat" type="org.apache.hadoop.mapred.OutputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Create a FilterOutputFormat based on the supplied output format.
- @param out the underlying OutputFormat]]>
- </doc>
- </constructor>
- <method name="getRecordWriter" return="org.apache.hadoop.mapred.RecordWriter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="name" type="java.lang.String"/>
- <param name="progress" type="org.apache.hadoop.util.Progressable"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="checkOutputSpecs"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <field name="baseOut" type="org.apache.hadoop.mapred.OutputFormat"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[FilterOutputFormat is a convenience class that wraps OutputFormat.
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.output.FilterOutputFormat} instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.FilterOutputFormat -->
- <!-- start class org.apache.hadoop.mapred.lib.FilterOutputFormat.FilterRecordWriter -->
- <class name="FilterOutputFormat.FilterRecordWriter" extends="java.lang.Object"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapred.RecordWriter"/>
- <constructor name="FilterOutputFormat.FilterRecordWriter"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </constructor>
- <constructor name="FilterOutputFormat.FilterRecordWriter" type="org.apache.hadoop.mapred.RecordWriter"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </constructor>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <param name="value" type="V"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <field name="rawWriter" type="org.apache.hadoop.mapred.RecordWriter"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[<code>FilterRecordWriter</code> is a convenience wrapper
- class that implements {@link RecordWriter}.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.FilterOutputFormat.FilterRecordWriter -->
- <!-- start class org.apache.hadoop.mapred.lib.HashPartitioner -->
- <class name="HashPartitioner" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.partition.HashPartitioner} instead.">
- <implements name="org.apache.hadoop.mapred.Partitioner"/>
- <constructor name="HashPartitioner"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="configure"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- </method>
- <method name="getPartition" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K2"/>
- <param name="value" type="V2"/>
- <param name="numReduceTasks" type="int"/>
- <doc>
- <![CDATA[Use {@link Object#hashCode()} to partition.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Partition keys by their {@link Object#hashCode()}.
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.partition.HashPartitioner} instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.HashPartitioner -->
- <!-- start class org.apache.hadoop.mapred.lib.IdentityMapper -->
- <class name="IdentityMapper" extends="org.apache.hadoop.mapred.MapReduceBase"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.Mapper} instead.">
- <implements name="org.apache.hadoop.mapred.Mapper"/>
- <constructor name="IdentityMapper"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="map"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <param name="val" type="V"/>
- <param name="output" type="org.apache.hadoop.mapred.OutputCollector"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[The identify function. Input key/value pair is written directly to
- output.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Implements the identity function, mapping inputs directly to outputs.
- @deprecated Use {@link org.apache.hadoop.mapreduce.Mapper} instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.IdentityMapper -->
- <!-- start class org.apache.hadoop.mapred.lib.IdentityReducer -->
- <class name="IdentityReducer" extends="org.apache.hadoop.mapred.MapReduceBase"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.Reducer} instead.">
- <implements name="org.apache.hadoop.mapred.Reducer"/>
- <constructor name="IdentityReducer"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="reduce"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <param name="values" type="java.util.Iterator"/>
- <param name="output" type="org.apache.hadoop.mapred.OutputCollector"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Writes all keys and values directly to output.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Performs no reduction, writing all input values directly to the output.
- @deprecated Use {@link org.apache.hadoop.mapreduce.Reducer} instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.IdentityReducer -->
- <!-- start class org.apache.hadoop.mapred.lib.InputSampler -->
- <class name="InputSampler" extends="org.apache.hadoop.mapreduce.lib.partition.InputSampler"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.partition.InputSampler}">
- <constructor name="InputSampler" type="org.apache.hadoop.mapred.JobConf"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="writePartitionFile"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="sampler" type="org.apache.hadoop.mapreduce.lib.partition.InputSampler.Sampler"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="ClassNotFoundException" type="java.lang.ClassNotFoundException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <doc>
- <![CDATA[@deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.partition.InputSampler}]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.InputSampler -->
- <!-- start class org.apache.hadoop.mapred.lib.InverseMapper -->
- <class name="InverseMapper" extends="org.apache.hadoop.mapred.MapReduceBase"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.lib.map.InverseMapper}
- instead.">
- <implements name="org.apache.hadoop.mapred.Mapper"/>
- <constructor name="InverseMapper"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="map"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <param name="value" type="V"/>
- <param name="output" type="org.apache.hadoop.mapred.OutputCollector"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[The inverse function. Input keys and values are swapped.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[A {@link Mapper} that swaps keys and values.
- @deprecated Use {@link org.apache.hadoop.mapreduce.lib.map.InverseMapper}
- instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.InverseMapper -->
- <!-- start class org.apache.hadoop.mapred.lib.KeyFieldBasedComparator -->
- <class name="KeyFieldBasedComparator" extends="org.apache.hadoop.mapreduce.lib.partition.KeyFieldBasedComparator"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.partition.KeyFieldBasedComparator}
- instead">
- <implements name="org.apache.hadoop.mapred.JobConfigurable"/>
- <constructor name="KeyFieldBasedComparator"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="configure"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- </method>
- <doc>
- <![CDATA[This comparator implementation provides a subset of the features provided
- by the Unix/GNU Sort. In particular, the supported features are:
- -n, (Sort numerically)
- -r, (Reverse the result of comparison)
- -k pos1[,pos2], where pos is of the form f[.c][opts], where f is the number
- of the field to use, and c is the number of the first character from the
- beginning of the field. Fields and character posns are numbered starting
- with 1; a character position of zero in pos2 indicates the field's last
- character. If '.c' is omitted from pos1, it defaults to 1 (the beginning
- of the field); if omitted from pos2, it defaults to 0 (the end of the
- field). opts are ordering options (any of 'nr' as described above).
- We assume that the fields in the key are separated by
- {@link JobContext#MAP_OUTPUT_KEY_FIELD_SEPERATOR}
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.partition.KeyFieldBasedComparator}
- instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.KeyFieldBasedComparator -->
- <!-- start class org.apache.hadoop.mapred.lib.KeyFieldBasedPartitioner -->
- <class name="KeyFieldBasedPartitioner" extends="org.apache.hadoop.mapreduce.lib.partition.KeyFieldBasedPartitioner"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.partition.KeyFieldBasedPartitioner}
- instead">
- <implements name="org.apache.hadoop.mapred.Partitioner"/>
- <constructor name="KeyFieldBasedPartitioner"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="configure"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- </method>
- <doc>
- <![CDATA[Defines a way to partition keys based on certain key fields (also see
- {@link KeyFieldBasedComparator}.
- The key specification supported is of the form -k pos1[,pos2], where,
- pos is of the form f[.c][opts], where f is the number
- of the key field to use, and c is the number of the first character from
- the beginning of the field. Fields and character posns are numbered
- starting with 1; a character position of zero in pos2 indicates the
- field's last character. If '.c' is omitted from pos1, it defaults to 1
- (the beginning of the field); if omitted from pos2, it defaults to 0
- (the end of the field).
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.partition.KeyFieldBasedPartitioner}
- instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.KeyFieldBasedPartitioner -->
- <!-- start class org.apache.hadoop.mapred.lib.LazyOutputFormat -->
- <class name="LazyOutputFormat" extends="org.apache.hadoop.mapred.lib.FilterOutputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.output.LazyOutputFormat} instead.">
- <constructor name="LazyOutputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setOutputFormatClass"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="theClass" type="java.lang.Class"/>
- <doc>
- <![CDATA[Set the underlying output format for LazyOutputFormat.
- @param job the {@link JobConf} to modify
- @param theClass the underlying class]]>
- </doc>
- </method>
- <method name="getRecordWriter" return="org.apache.hadoop.mapred.RecordWriter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="name" type="java.lang.String"/>
- <param name="progress" type="org.apache.hadoop.util.Progressable"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="checkOutputSpecs"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[A Convenience class that creates output lazily.
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.output.LazyOutputFormat} instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.LazyOutputFormat -->
- <!-- start class org.apache.hadoop.mapred.lib.LongSumReducer -->
- <class name="LongSumReducer" extends="org.apache.hadoop.mapred.MapReduceBase"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.lib.reduce.LongSumReducer}
- instead.">
- <implements name="org.apache.hadoop.mapred.Reducer"/>
- <constructor name="LongSumReducer"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="reduce"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <param name="values" type="java.util.Iterator"/>
- <param name="output" type="org.apache.hadoop.mapred.OutputCollector"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[A {@link Reducer} that sums long values.
- @deprecated Use {@link org.apache.hadoop.mapreduce.lib.reduce.LongSumReducer}
- instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.LongSumReducer -->
- <!-- start class org.apache.hadoop.mapred.lib.MultipleInputs -->
- <class name="MultipleInputs" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.input.MultipleInputs} instead">
- <constructor name="MultipleInputs"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="addInputPath"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="path" type="org.apache.hadoop.fs.Path"/>
- <param name="inputFormatClass" type="java.lang.Class"/>
- <doc>
- <![CDATA[Add a {@link Path} with a custom {@link InputFormat} to the list of
- inputs for the map-reduce job.
-
- @param conf The configuration of the job
- @param path {@link Path} to be added to the list of inputs for the job
- @param inputFormatClass {@link InputFormat} class to use for this path]]>
- </doc>
- </method>
- <method name="addInputPath"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="path" type="org.apache.hadoop.fs.Path"/>
- <param name="inputFormatClass" type="java.lang.Class"/>
- <param name="mapperClass" type="java.lang.Class"/>
- <doc>
- <![CDATA[Add a {@link Path} with a custom {@link InputFormat} and
- {@link Mapper} to the list of inputs for the map-reduce job.
-
- @param conf The configuration of the job
- @param path {@link Path} to be added to the list of inputs for the job
- @param inputFormatClass {@link InputFormat} class to use for this path
- @param mapperClass {@link Mapper} class to use for this path]]>
- </doc>
- </method>
- <doc>
- <![CDATA[This class supports MapReduce jobs that have multiple input paths with
- a different {@link InputFormat} and {@link Mapper} for each path
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.input.MultipleInputs} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.MultipleInputs -->
- <!-- start class org.apache.hadoop.mapred.lib.MultipleOutputFormat -->
- <class name="MultipleOutputFormat" extends="org.apache.hadoop.mapred.FileOutputFormat"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.output.MultipleOutputs} instead">
- <constructor name="MultipleOutputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getRecordWriter" return="org.apache.hadoop.mapred.RecordWriter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="fs" type="org.apache.hadoop.fs.FileSystem"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="name" type="java.lang.String"/>
- <param name="arg3" type="org.apache.hadoop.util.Progressable"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Create a composite record writer that can write key/value data to different
- output files
-
- @param fs
- the file system to use
- @param job
- the job conf for the job
- @param name
- the leaf file name for the output file (such as part-00000")
- @param arg3
- a progressable for reporting progress.
- @return a composite record writer
- @throws IOException]]>
- </doc>
- </method>
- <method name="generateLeafFileName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- <doc>
- <![CDATA[Generate the leaf name for the output file name. The default behavior does
- not change the leaf file name (such as part-00000)
-
- @param name
- the leaf file name for the output file
- @return the given leaf file name]]>
- </doc>
- </method>
- <method name="generateFileNameForKeyValue" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <param name="value" type="V"/>
- <param name="name" type="java.lang.String"/>
- <doc>
- <![CDATA[Generate the file output file name based on the given key and the leaf file
- name. The default behavior is that the file name does not depend on the
- key.
-
- @param key
- the key of the output data
- @param name
- the leaf file name
- @return generated file name]]>
- </doc>
- </method>
- <method name="generateActualKey" return="K"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <param name="value" type="V"/>
- <doc>
- <![CDATA[Generate the actual key from the given key/value. The default behavior is that
- the actual key is equal to the given key
-
- @param key
- the key of the output data
- @param value
- the value of the output data
- @return the actual key derived from the given key/value]]>
- </doc>
- </method>
- <method name="generateActualValue" return="V"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <param name="value" type="V"/>
- <doc>
- <![CDATA[Generate the actual value from the given key and value. The default behavior is that
- the actual value is equal to the given value
-
- @param key
- the key of the output data
- @param value
- the value of the output data
- @return the actual value derived from the given key/value]]>
- </doc>
- </method>
- <method name="getInputFileBasedOutputFileName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="name" type="java.lang.String"/>
- <doc>
- <![CDATA[Generate the outfile name based on a given anme and the input file name. If
- the {@link JobContext#MAP_INPUT_FILE} does not exists (i.e. this is not for a map only job),
- the given name is returned unchanged. If the config value for
- "num.of.trailing.legs.to.use" is not set, or set 0 or negative, the given
- name is returned unchanged. Otherwise, return a file name consisting of the
- N trailing legs of the input file name where N is the config value for
- "num.of.trailing.legs.to.use".
-
- @param job
- the job config
- @param name
- the output file name
- @return the outfile name based on a given anme and the input file name.]]>
- </doc>
- </method>
- <method name="getBaseRecordWriter" return="org.apache.hadoop.mapred.RecordWriter"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="fs" type="org.apache.hadoop.fs.FileSystem"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="name" type="java.lang.String"/>
- <param name="arg3" type="org.apache.hadoop.util.Progressable"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[@param fs
- the file system to use
- @param job
- a job conf object
- @param name
- the name of the file over which a record writer object will be
- constructed
- @param arg3
- a progressable object
- @return A RecordWriter object over the given file
- @throws IOException]]>
- </doc>
- </method>
- <doc>
- <![CDATA[This abstract class extends the FileOutputFormat, allowing to write the
- output data to different output files. There are three basic use cases for
- this class.
-
- Case one: This class is used for a map reduce job with at least one reducer.
- The reducer wants to write data to different files depending on the actual
- keys. It is assumed that a key (or value) encodes the actual key (value)
- and the desired location for the actual key (value).
-
- Case two: This class is used for a map only job. The job wants to use an
- output file name that is either a part of the input file name of the input
- data, or some derivation of it.
-
- Case three: This class is used for a map only job. The job wants to use an
- output file name that depends on both the keys and the input file name,
-
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.output.MultipleOutputs} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.MultipleOutputFormat -->
- <!-- start class org.apache.hadoop.mapred.lib.MultipleOutputs -->
- <class name="MultipleOutputs" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.output.MultipleOutputs} instead">
- <constructor name="MultipleOutputs" type="org.apache.hadoop.mapred.JobConf"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Creates and initializes multiple named outputs support, it should be
- instantiated in the Mapper/Reducer configure method.
- @param job the job configuration object]]>
- </doc>
- </constructor>
- <method name="getNamedOutputsList" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[Returns list of channel names.
- @param conf job conf
- @return List of channel Names]]>
- </doc>
- </method>
- <method name="isMultiNamedOutput" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="namedOutput" type="java.lang.String"/>
- <doc>
- <![CDATA[Returns if a named output is multiple.
- @param conf job conf
- @param namedOutput named output
- @return <code>true</code> if the name output is multi, <code>false</code>
- if it is single. If the name output is not defined it returns
- <code>false</code>]]>
- </doc>
- </method>
- <method name="getNamedOutputFormatClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="namedOutput" type="java.lang.String"/>
- <doc>
- <![CDATA[Returns the named output OutputFormat.
- @param conf job conf
- @param namedOutput named output
- @return namedOutput OutputFormat]]>
- </doc>
- </method>
- <method name="getNamedOutputKeyClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="namedOutput" type="java.lang.String"/>
- <doc>
- <![CDATA[Returns the key class for a named output.
- @param conf job conf
- @param namedOutput named output
- @return class for the named output key]]>
- </doc>
- </method>
- <method name="getNamedOutputValueClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="namedOutput" type="java.lang.String"/>
- <doc>
- <![CDATA[Returns the value class for a named output.
- @param conf job conf
- @param namedOutput named output
- @return class of named output value]]>
- </doc>
- </method>
- <method name="addNamedOutput"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="namedOutput" type="java.lang.String"/>
- <param name="outputFormatClass" type="java.lang.Class"/>
- <param name="keyClass" type="java.lang.Class"/>
- <param name="valueClass" type="java.lang.Class"/>
- <doc>
- <![CDATA[Adds a named output for the job.
- <p/>
- @param conf job conf to add the named output
- @param namedOutput named output name, it has to be a word, letters
- and numbers only, cannot be the word 'part' as
- that is reserved for the
- default output.
- @param outputFormatClass OutputFormat class.
- @param keyClass key class
- @param valueClass value class]]>
- </doc>
- </method>
- <method name="addMultiNamedOutput"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="namedOutput" type="java.lang.String"/>
- <param name="outputFormatClass" type="java.lang.Class"/>
- <param name="keyClass" type="java.lang.Class"/>
- <param name="valueClass" type="java.lang.Class"/>
- <doc>
- <![CDATA[Adds a multi named output for the job.
- <p/>
- @param conf job conf to add the named output
- @param namedOutput named output name, it has to be a word, letters
- and numbers only, cannot be the word 'part' as
- that is reserved for the
- default output.
- @param outputFormatClass OutputFormat class.
- @param keyClass key class
- @param valueClass value class]]>
- </doc>
- </method>
- <method name="setCountersEnabled"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="enabled" type="boolean"/>
- <doc>
- <![CDATA[Enables or disables counters for the named outputs.
- <p/>
- By default these counters are disabled.
- <p/>
- MultipleOutputs supports counters, by default the are disabled.
- The counters group is the {@link MultipleOutputs} class name.
- </p>
- The names of the counters are the same as the named outputs. For multi
- named outputs the name of the counter is the concatenation of the named
- output, and underscore '_' and the multiname.
- @param conf job conf to enableadd the named output.
- @param enabled indicates if the counters will be enabled or not.]]>
- </doc>
- </method>
- <method name="getCountersEnabled" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[Returns if the counters for the named outputs are enabled or not.
- <p/>
- By default these counters are disabled.
- <p/>
- MultipleOutputs supports counters, by default the are disabled.
- The counters group is the {@link MultipleOutputs} class name.
- </p>
- The names of the counters are the same as the named outputs. For multi
- named outputs the name of the counter is the concatenation of the named
- output, and underscore '_' and the multiname.
- @param conf job conf to enableadd the named output.
- @return TRUE if the counters are enabled, FALSE if they are disabled.]]>
- </doc>
- </method>
- <method name="getNamedOutputs" return="java.util.Iterator"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns iterator with the defined name outputs.
- @return iterator with the defined named outputs]]>
- </doc>
- </method>
- <method name="getCollector" return="org.apache.hadoop.mapred.OutputCollector"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="namedOutput" type="java.lang.String"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Gets the output collector for a named output.
- <p/>
- @param namedOutput the named output name
- @param reporter the reporter
- @return the output collector for the given named output
- @throws IOException thrown if output collector could not be created]]>
- </doc>
- </method>
- <method name="getCollector" return="org.apache.hadoop.mapred.OutputCollector"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="namedOutput" type="java.lang.String"/>
- <param name="multiName" type="java.lang.String"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Gets the output collector for a multi named output.
- <p/>
- @param namedOutput the named output name
- @param multiName the multi name part
- @param reporter the reporter
- @return the output collector for the given named output
- @throws IOException thrown if output collector could not be created]]>
- </doc>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Closes all the opened named outputs.
- <p/>
- If overriden subclasses must invoke <code>super.close()</code> at the
- end of their <code>close()</code>
- @throws java.io.IOException thrown if any of the MultipleOutput files
- could not be closed properly.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[The MultipleOutputs class simplifies writting to additional outputs other
- than the job default output via the <code>OutputCollector</code> passed to
- the <code>map()</code> and <code>reduce()</code> methods of the
- <code>Mapper</code> and <code>Reducer</code> implementations.
- <p/>
- Each additional output, or named output, may be configured with its own
- <code>OutputFormat</code>, with its own key class and with its own value
- class.
- <p/>
- A named output can be a single file or a multi file. The later is refered as
- a multi named output.
- <p/>
- A multi named output is an unbound set of files all sharing the same
- <code>OutputFormat</code>, key class and value class configuration.
- <p/>
- When named outputs are used within a <code>Mapper</code> implementation,
- key/values written to a name output are not part of the reduce phase, only
- key/values written to the job <code>OutputCollector</code> are part of the
- reduce phase.
- <p/>
- MultipleOutputs supports counters, by default the are disabled. The counters
- group is the {@link MultipleOutputs} class name.
- </p>
- The names of the counters are the same as the named outputs. For multi
- named outputs the name of the counter is the concatenation of the named
- output, and underscore '_' and the multiname.
- <p/>
- Job configuration usage pattern is:
- <pre>
- JobConf conf = new JobConf();
- conf.setInputPath(inDir);
- FileOutputFormat.setOutputPath(conf, outDir);
- conf.setMapperClass(MOMap.class);
- conf.setReducerClass(MOReduce.class);
- ...
- // Defines additional single text based output 'text' for the job
- MultipleOutputs.addNamedOutput(conf, "text", TextOutputFormat.class,
- LongWritable.class, Text.class);
- // Defines additional multi sequencefile based output 'sequence' for the
- // job
- MultipleOutputs.addMultiNamedOutput(conf, "seq",
- SequenceFileOutputFormat.class,
- LongWritable.class, Text.class);
- ...
- JobClient jc = new JobClient();
- RunningJob job = jc.submitJob(conf);
- ...
- </pre>
- <p/>
- Job configuration usage pattern is:
- <pre>
- public class MOReduce implements
- Reducer<WritableComparable, Writable> {
- private MultipleOutputs mos;
- public void configure(JobConf conf) {
- ...
- mos = new MultipleOutputs(conf);
- }
- public void reduce(WritableComparable key, Iterator<Writable> values,
- OutputCollector output, Reporter reporter)
- throws IOException {
- ...
- mos.getCollector("text", reporter).collect(key, new Text("Hello"));
- mos.getCollector("seq", "A", reporter).collect(key, new Text("Bye"));
- mos.getCollector("seq", "B", reporter).collect(key, new Text("Chau"));
- ...
- }
- public void close() throws IOException {
- mos.close();
- ...
- }
- }
- </pre>
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.output.MultipleOutputs} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.MultipleOutputs -->
- <!-- start class org.apache.hadoop.mapred.lib.MultipleSequenceFileOutputFormat -->
- <class name="MultipleSequenceFileOutputFormat" extends="org.apache.hadoop.mapred.lib.MultipleOutputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.output.MultipleOutputs} instead">
- <constructor name="MultipleSequenceFileOutputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getBaseRecordWriter" return="org.apache.hadoop.mapred.RecordWriter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="fs" type="org.apache.hadoop.fs.FileSystem"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="name" type="java.lang.String"/>
- <param name="arg3" type="org.apache.hadoop.util.Progressable"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[This class extends the MultipleOutputFormat, allowing to write the output data
- to different output files in sequence file output format.
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.output.MultipleOutputs} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.MultipleSequenceFileOutputFormat -->
- <!-- start class org.apache.hadoop.mapred.lib.MultipleTextOutputFormat -->
- <class name="MultipleTextOutputFormat" extends="org.apache.hadoop.mapred.lib.MultipleOutputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.output.MultipleOutputs} instead">
- <constructor name="MultipleTextOutputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getBaseRecordWriter" return="org.apache.hadoop.mapred.RecordWriter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="fs" type="org.apache.hadoop.fs.FileSystem"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="name" type="java.lang.String"/>
- <param name="arg3" type="org.apache.hadoop.util.Progressable"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[This class extends the MultipleOutputFormat, allowing to write the output
- data to different output files in Text output format.
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.output.MultipleOutputs} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.MultipleTextOutputFormat -->
- <!-- start class org.apache.hadoop.mapred.lib.MultithreadedMapRunner -->
- <class name="MultithreadedMapRunner" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link MultithreadedMapper} instead.">
- <implements name="org.apache.hadoop.mapred.MapRunnable"/>
- <constructor name="MultithreadedMapRunner"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="configure"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobConf" type="org.apache.hadoop.mapred.JobConf"/>
- </method>
- <method name="run"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="input" type="org.apache.hadoop.mapred.RecordReader"/>
- <param name="output" type="org.apache.hadoop.mapred.OutputCollector"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[Multithreaded implementation for @link org.apache.hadoop.mapred.MapRunnable.
- <p>
- It can be used instead of the default implementation,
- @link org.apache.hadoop.mapred.MapRunner, when the Map operation is not CPU
- bound in order to improve throughput.
- <p>
- Map implementations using this MapRunnable must be thread-safe.
- <p>
- The Map-Reduce job has to be configured to use this MapRunnable class (using
- the JobConf.setMapRunnerClass method) and
- the number of thread the thread-pool can use with the
- <code>mapred.map.multithreadedrunner.threads</code> property, its default
- value is 10 threads.
- <p>
- @deprecated Use {@link MultithreadedMapper} instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.MultithreadedMapRunner -->
- <!-- start class org.apache.hadoop.mapred.lib.NLineInputFormat -->
- <class name="NLineInputFormat" extends="org.apache.hadoop.mapred.FileInputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.input.NLineInputFormat} instead">
- <implements name="org.apache.hadoop.mapred.JobConfigurable"/>
- <constructor name="NLineInputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getRecordReader" return="org.apache.hadoop.mapred.RecordReader"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="genericSplit" type="org.apache.hadoop.mapred.InputSplit"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getSplits" return="org.apache.hadoop.mapred.InputSplit[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="numSplits" type="int"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Logically splits the set of input files for the job, splits N lines
- of the input as one split.
-
- @see org.apache.hadoop.mapred.FileInputFormat#getSplits(JobConf, int)]]>
- </doc>
- </method>
- <method name="configure"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- </method>
- <doc>
- <![CDATA[NLineInputFormat which splits N lines of input as one split.
- In many "pleasantly" parallel applications, each process/mapper
- processes the same input file (s), but with computations are
- controlled by different parameters.(Referred to as "parameter sweeps").
- One way to achieve this, is to specify a set of parameters
- (one set per line) as input in a control file
- (which is the input path to the map-reduce application,
- where as the input dataset is specified
- via a config variable in JobConf.).
-
- The NLineInputFormat can be used in such applications, that splits
- the input file such that by default, one line is fed as
- a value to one map task, and key is the offset.
- i.e. (k,v) is (LongWritable, Text).
- The location hints will span the whole mapred cluster.
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.input.NLineInputFormat} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.NLineInputFormat -->
- <!-- start class org.apache.hadoop.mapred.lib.NullOutputFormat -->
- <class name="NullOutputFormat" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.output.NullOutputFormat} instead.">
- <implements name="org.apache.hadoop.mapred.OutputFormat"/>
- <constructor name="NullOutputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getRecordWriter" return="org.apache.hadoop.mapred.RecordWriter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="name" type="java.lang.String"/>
- <param name="progress" type="org.apache.hadoop.util.Progressable"/>
- </method>
- <method name="checkOutputSpecs"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- </method>
- <doc>
- <![CDATA[Consume all outputs and put them in /dev/null.
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.output.NullOutputFormat} instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.NullOutputFormat -->
- <!-- start class org.apache.hadoop.mapred.lib.RegexMapper -->
- <class name="RegexMapper" extends="org.apache.hadoop.mapred.MapReduceBase"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.lib.map.RegexMapper}">
- <implements name="org.apache.hadoop.mapred.Mapper"/>
- <constructor name="RegexMapper"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="configure"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- </method>
- <method name="map"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <param name="value" type="org.apache.hadoop.io.Text"/>
- <param name="output" type="org.apache.hadoop.mapred.OutputCollector"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[A {@link Mapper} that extracts text matching a regular expression.
- @deprecated Use {@link org.apache.hadoop.mapreduce.lib.map.RegexMapper}]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.RegexMapper -->
- <!-- start class org.apache.hadoop.mapred.lib.TokenCountMapper -->
- <class name="TokenCountMapper" extends="org.apache.hadoop.mapred.MapReduceBase"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.map.TokenCounterMapper} instead.">
- <implements name="org.apache.hadoop.mapred.Mapper"/>
- <constructor name="TokenCountMapper"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="map"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <param name="value" type="org.apache.hadoop.io.Text"/>
- <param name="output" type="org.apache.hadoop.mapred.OutputCollector"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[A {@link Mapper} that maps text values into <token,freq> pairs. Uses
- {@link StringTokenizer} to break text into tokens.
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.map.TokenCounterMapper} instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.TokenCountMapper -->
- <!-- start class org.apache.hadoop.mapred.lib.TotalOrderPartitioner -->
- <class name="TotalOrderPartitioner" extends="org.apache.hadoop.mapreduce.lib.partition.TotalOrderPartitioner"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.partition.TotalOrderPartitioner}">
- <implements name="org.apache.hadoop.mapred.Partitioner"/>
- <constructor name="TotalOrderPartitioner"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="configure"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- </method>
- <doc>
- <![CDATA[Partitioner effecting a total order by reading split points from
- an externally generated source.
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.partition.TotalOrderPartitioner}]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.TotalOrderPartitioner -->
- </package>
- <package name="org.apache.hadoop.mapred.lib.aggregate">
- <!-- start class org.apache.hadoop.mapred.lib.aggregate.DoubleValueSum -->
- <class name="DoubleValueSum" extends="org.apache.hadoop.mapreduce.lib.aggregate.DoubleValueSum"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.aggregate.DoubleValueSum} instead">
- <implements name="org.apache.hadoop.mapred.lib.aggregate.ValueAggregator"/>
- <constructor name="DoubleValueSum"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <doc>
- <![CDATA[This class implements a value aggregator that sums up a sequence of double
- values.
-
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.aggregate.DoubleValueSum} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.aggregate.DoubleValueSum -->
- <!-- start class org.apache.hadoop.mapred.lib.aggregate.LongValueMax -->
- <class name="LongValueMax" extends="org.apache.hadoop.mapreduce.lib.aggregate.LongValueMax"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.aggregate.LongValueMax} instead">
- <implements name="org.apache.hadoop.mapred.lib.aggregate.ValueAggregator"/>
- <constructor name="LongValueMax"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <doc>
- <![CDATA[This class implements a value aggregator that maintain the maximum of
- a sequence of long values.
-
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.aggregate.LongValueMax} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.aggregate.LongValueMax -->
- <!-- start class org.apache.hadoop.mapred.lib.aggregate.LongValueMin -->
- <class name="LongValueMin" extends="org.apache.hadoop.mapreduce.lib.aggregate.LongValueMin"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.aggregate.LongValueMin} instead">
- <implements name="org.apache.hadoop.mapred.lib.aggregate.ValueAggregator"/>
- <constructor name="LongValueMin"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <doc>
- <![CDATA[This class implements a value aggregator that maintain the minimum of
- a sequence of long values.
-
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.aggregate.LongValueMin} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.aggregate.LongValueMin -->
- <!-- start class org.apache.hadoop.mapred.lib.aggregate.LongValueSum -->
- <class name="LongValueSum" extends="org.apache.hadoop.mapreduce.lib.aggregate.LongValueSum"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.aggregate.LongValueSum} instead">
- <implements name="org.apache.hadoop.mapred.lib.aggregate.ValueAggregator"/>
- <constructor name="LongValueSum"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <doc>
- <![CDATA[This class implements a value aggregator that sums up
- a sequence of long values.
-
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.aggregate.LongValueSum} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.aggregate.LongValueSum -->
- <!-- start class org.apache.hadoop.mapred.lib.aggregate.StringValueMax -->
- <class name="StringValueMax" extends="org.apache.hadoop.mapreduce.lib.aggregate.StringValueMax"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.aggregate.StringValueMax} instead">
- <implements name="org.apache.hadoop.mapred.lib.aggregate.ValueAggregator"/>
- <constructor name="StringValueMax"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <doc>
- <![CDATA[This class implements a value aggregator that maintain the biggest of
- a sequence of strings.
-
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.aggregate.StringValueMax} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.aggregate.StringValueMax -->
- <!-- start class org.apache.hadoop.mapred.lib.aggregate.StringValueMin -->
- <class name="StringValueMin" extends="org.apache.hadoop.mapreduce.lib.aggregate.StringValueMin"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.aggregate.StringValueMin} instead">
- <implements name="org.apache.hadoop.mapred.lib.aggregate.ValueAggregator"/>
- <constructor name="StringValueMin"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <doc>
- <![CDATA[This class implements a value aggregator that maintain the smallest of
- a sequence of strings.
-
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.aggregate.StringValueMin} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.aggregate.StringValueMin -->
- <!-- start class org.apache.hadoop.mapred.lib.aggregate.UniqValueCount -->
- <class name="UniqValueCount" extends="org.apache.hadoop.mapreduce.lib.aggregate.UniqValueCount"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.aggregate.UniqValueCount} instead">
- <implements name="org.apache.hadoop.mapred.lib.aggregate.ValueAggregator"/>
- <constructor name="UniqValueCount"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[the default constructor]]>
- </doc>
- </constructor>
- <constructor name="UniqValueCount" type="long"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[constructor
- @param maxNum the limit in the number of unique values to keep.]]>
- </doc>
- </constructor>
- <doc>
- <![CDATA[This class implements a value aggregator that dedupes a sequence of objects.
-
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.aggregate.UniqValueCount} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.aggregate.UniqValueCount -->
- <!-- start class org.apache.hadoop.mapred.lib.aggregate.UserDefinedValueAggregatorDescriptor -->
- <class name="UserDefinedValueAggregatorDescriptor" extends="org.apache.hadoop.mapreduce.lib.aggregate.UserDefinedValueAggregatorDescriptor"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.aggregate.UserDefinedValueAggregatorDescriptor}
- instead">
- <implements name="org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorDescriptor"/>
- <constructor name="UserDefinedValueAggregatorDescriptor" type="java.lang.String, org.apache.hadoop.mapred.JobConf"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@param className the class name of the user defined descriptor class
- @param job a configure object used for decriptor configuration]]>
- </doc>
- </constructor>
- <method name="createInstance" return="java.lang.Object"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="className" type="java.lang.String"/>
- <doc>
- <![CDATA[Create an instance of the given class
- @param className the name of the class
- @return a dynamically created instance of the given class]]>
- </doc>
- </method>
- <method name="configure"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[Do nothing.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[This class implements a wrapper for a user defined value aggregator descriptor.
- It servs two functions: One is to create an object of ValueAggregatorDescriptor from the
- name of a user defined class that may be dynamically loaded. The other is to
- deligate inviokations of generateKeyValPairs function to the created object.
-
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.aggregate.UserDefinedValueAggregatorDescriptor}
- instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.aggregate.UserDefinedValueAggregatorDescriptor -->
- <!-- start interface org.apache.hadoop.mapred.lib.aggregate.ValueAggregator -->
- <interface name="ValueAggregator" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregator} instead">
- <implements name="org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregator"/>
- <doc>
- <![CDATA[This interface defines the minimal protocol for value aggregators.
-
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregator} instead]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.lib.aggregate.ValueAggregator -->
- <!-- start class org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorBaseDescriptor -->
- <class name="ValueAggregatorBaseDescriptor" extends="org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorBaseDescriptor"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorBaseDescriptor}
- instead">
- <implements name="org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorDescriptor"/>
- <constructor name="ValueAggregatorBaseDescriptor"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="generateEntry" return="java.util.Map.Entry"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="type" type="java.lang.String"/>
- <param name="id" type="java.lang.String"/>
- <param name="val" type="org.apache.hadoop.io.Text"/>
- <doc>
- <![CDATA[@param type the aggregation type
- @param id the aggregation id
- @param val the val associated with the id to be aggregated
- @return an Entry whose key is the aggregation id prefixed with
- the aggregation type.]]>
- </doc>
- </method>
- <method name="generateValueAggregator" return="org.apache.hadoop.mapred.lib.aggregate.ValueAggregator"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="type" type="java.lang.String"/>
- <doc>
- <![CDATA[@param type the aggregation type
- @return a value aggregator of the given type.]]>
- </doc>
- </method>
- <method name="configure"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[get the input file name.
-
- @param job a job configuration object]]>
- </doc>
- </method>
- <field name="UNIQ_VALUE_COUNT" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="LONG_VALUE_SUM" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="DOUBLE_VALUE_SUM" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="VALUE_HISTOGRAM" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="LONG_VALUE_MAX" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="LONG_VALUE_MIN" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="STRING_VALUE_MAX" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="STRING_VALUE_MIN" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[This class implements the common functionalities of
- the subclasses of ValueAggregatorDescriptor class.
-
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorBaseDescriptor}
- instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorBaseDescriptor -->
- <!-- start class org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorCombiner -->
- <class name="ValueAggregatorCombiner" extends="org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorJobBase"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorCombiner}
- instead">
- <constructor name="ValueAggregatorCombiner"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="configure"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[Combiner does not need to configure.]]>
- </doc>
- </method>
- <method name="reduce"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="org.apache.hadoop.io.Text"/>
- <param name="values" type="java.util.Iterator"/>
- <param name="output" type="org.apache.hadoop.mapred.OutputCollector"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Combines values for a given key.
- @param key the key is expected to be a Text object, whose prefix indicates
- the type of aggregation to aggregate the values.
- @param values the values to combine
- @param output to collect combined values]]>
- </doc>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Do nothing.]]>
- </doc>
- </method>
- <method name="map"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="arg0" type="K1"/>
- <param name="arg1" type="V1"/>
- <param name="arg2" type="org.apache.hadoop.mapred.OutputCollector"/>
- <param name="arg3" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Do nothing. Should not be called.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[This class implements the generic combiner of Aggregate.
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorCombiner}
- instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorCombiner -->
- <!-- start interface org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorDescriptor -->
- <interface name="ValueAggregatorDescriptor" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorDescriptor}
- instead">
- <implements name="org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorDescriptor"/>
- <method name="configure"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[Configure the object
-
- @param job
- a JobConf object that may contain the information that can be used
- to configure the object.]]>
- </doc>
- </method>
- <field name="TYPE_SEPARATOR" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="ONE" type="org.apache.hadoop.io.Text"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[This interface defines the contract a value aggregator descriptor must
- support. Such a descriptor can be configured with a JobConf object. Its main
- function is to generate a list of aggregation-id/value pairs. An aggregation
- id encodes an aggregation type which is used to guide the way to aggregate
- the value in the reduce/combiner phrase of an Aggregate based job.The mapper in
- an Aggregate based map/reduce job may create one or more of
- ValueAggregatorDescriptor objects at configuration time. For each input
- key/value pair, the mapper will use those objects to create aggregation
- id/value pairs.
-
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorDescriptor}
- instead]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorDescriptor -->
- <!-- start class org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorJob -->
- <class name="ValueAggregatorJob" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorJob} instead">
- <constructor name="ValueAggregatorJob"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="createValueAggregatorJobs" return="org.apache.hadoop.mapred.jobcontrol.JobControl"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="args" type="java.lang.String[]"/>
- <param name="descriptors" type="java.lang.Class[]"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="createValueAggregatorJobs" return="org.apache.hadoop.mapred.jobcontrol.JobControl"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="args" type="java.lang.String[]"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="createValueAggregatorJob" return="org.apache.hadoop.mapred.JobConf"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="args" type="java.lang.String[]"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Create an Aggregate based map/reduce job.
-
- @param args the arguments used for job creation. Generic hadoop
- arguments are accepted.
- @return a JobConf object ready for submission.
-
- @throws IOException
- @see GenericOptionsParser]]>
- </doc>
- </method>
- <method name="createValueAggregatorJob" return="org.apache.hadoop.mapred.JobConf"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="args" type="java.lang.String[]"/>
- <param name="descriptors" type="java.lang.Class[]"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="setAggregatorDescriptors"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="descriptors" type="java.lang.Class[]"/>
- </method>
- <method name="main"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="args" type="java.lang.String[]"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[create and run an Aggregate based map/reduce job.
-
- @param args the arguments used for job creation
- @throws IOException]]>
- </doc>
- </method>
- <doc>
- <![CDATA[This is the main class for creating a map/reduce job using Aggregate
- framework. The Aggregate is a specialization of map/reduce framework,
- specilizing for performing various simple aggregations.
-
- Generally speaking, in order to implement an application using Map/Reduce
- model, the developer is to implement Map and Reduce functions (and possibly
- combine function). However, a lot of applications related to counting and
- statistics computing have very similar characteristics. Aggregate abstracts
- out the general patterns of these functions and implementing those patterns.
- In particular, the package provides generic mapper/redducer/combiner classes,
- and a set of built-in value aggregators, and a generic utility class that
- helps user create map/reduce jobs using the generic class. The built-in
- aggregators include:
-
- sum over numeric values count the number of distinct values compute the
- histogram of values compute the minimum, maximum, media,average, standard
- deviation of numeric values
-
- The developer using Aggregate will need only to provide a plugin class
- conforming to the following interface:
-
- public interface ValueAggregatorDescriptor { public ArrayList<Entry>
- generateKeyValPairs(Object key, Object value); public void
- configure(JobConfjob); }
-
- The package also provides a base class, ValueAggregatorBaseDescriptor,
- implementing the above interface. The user can extend the base class and
- implement generateKeyValPairs accordingly.
-
- The primary work of generateKeyValPairs is to emit one or more key/value
- pairs based on the input key/value pair. The key in an output key/value pair
- encode two pieces of information: aggregation type and aggregation id. The
- value will be aggregated onto the aggregation id according the aggregation
- type.
-
- This class offers a function to generate a map/reduce job using Aggregate
- framework. The function takes the following parameters: input directory spec
- input format (text or sequence file) output directory a file specifying the
- user plugin class
-
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorJob} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorJob -->
- <!-- start class org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorJobBase -->
- <class name="ValueAggregatorJobBase" extends="java.lang.Object"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorJobBase}
- instead">
- <implements name="org.apache.hadoop.mapred.Mapper"/>
- <implements name="org.apache.hadoop.mapred.Reducer"/>
- <constructor name="ValueAggregatorJobBase"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="configure"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- </method>
- <method name="logSpec"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <field name="aggregatorDescriptorList" type="java.util.ArrayList"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[This abstract class implements some common functionalities of the
- the generic mapper, reducer and combiner classes of Aggregate.
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorJobBase}
- instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorJobBase -->
- <!-- start class org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorMapper -->
- <class name="ValueAggregatorMapper" extends="org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorJobBase"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorMapper}
- instead">
- <constructor name="ValueAggregatorMapper"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="map"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K1"/>
- <param name="value" type="V1"/>
- <param name="output" type="org.apache.hadoop.mapred.OutputCollector"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[the map function. It iterates through the value aggregator descriptor
- list to generate aggregation id/value pairs and emit them.]]>
- </doc>
- </method>
- <method name="reduce"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="arg0" type="org.apache.hadoop.io.Text"/>
- <param name="arg1" type="java.util.Iterator"/>
- <param name="arg2" type="org.apache.hadoop.mapred.OutputCollector"/>
- <param name="arg3" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Do nothing. Should not be called.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[This class implements the generic mapper of Aggregate.
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorMapper}
- instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorMapper -->
- <!-- start class org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorReducer -->
- <class name="ValueAggregatorReducer" extends="org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorJobBase"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorReducer}
- instead">
- <constructor name="ValueAggregatorReducer"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="reduce"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="org.apache.hadoop.io.Text"/>
- <param name="values" type="java.util.Iterator"/>
- <param name="output" type="org.apache.hadoop.mapred.OutputCollector"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[@param key
- the key is expected to be a Text object, whose prefix indicates
- the type of aggregation to aggregate the values. In effect, data
- driven computing is achieved. It is assumed that each aggregator's
- getReport method emits appropriate output for the aggregator. This
- may be further customiized.
- @value the values to be aggregated]]>
- </doc>
- </method>
- <method name="map"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="arg0" type="K1"/>
- <param name="arg1" type="V1"/>
- <param name="arg2" type="org.apache.hadoop.mapred.OutputCollector"/>
- <param name="arg3" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Do nothing. Should not be called]]>
- </doc>
- </method>
- <doc>
- <![CDATA[This class implements the generic reducer of Aggregate.
-
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorReducer}
- instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.aggregate.ValueAggregatorReducer -->
- <!-- start class org.apache.hadoop.mapred.lib.aggregate.ValueHistogram -->
- <class name="ValueHistogram" extends="org.apache.hadoop.mapreduce.lib.aggregate.ValueHistogram"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.aggregate.ValueHistogram} instead">
- <implements name="org.apache.hadoop.mapred.lib.aggregate.ValueAggregator"/>
- <constructor name="ValueHistogram"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <doc>
- <![CDATA[This class implements a value aggregator that computes the
- histogram of a sequence of strings.
-
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.aggregate.ValueHistogram} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.aggregate.ValueHistogram -->
- </package>
- <package name="org.apache.hadoop.mapred.lib.db">
- <!-- start class org.apache.hadoop.mapred.lib.db.DBConfiguration -->
- <class name="DBConfiguration" extends="org.apache.hadoop.mapreduce.lib.db.DBConfiguration"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.db.DBConfiguration} instead">
- <method name="configureDB"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="driverClass" type="java.lang.String"/>
- <param name="dbUrl" type="java.lang.String"/>
- <param name="userName" type="java.lang.String"/>
- <param name="passwd" type="java.lang.String"/>
- <doc>
- <![CDATA[Sets the DB access related fields in the JobConf.
- @param job the job
- @param driverClass JDBC Driver class name
- @param dbUrl JDBC DB access URL.
- @param userName DB access username
- @param passwd DB access passwd]]>
- </doc>
- </method>
- <method name="configureDB"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="driverClass" type="java.lang.String"/>
- <param name="dbUrl" type="java.lang.String"/>
- <doc>
- <![CDATA[Sets the DB access related fields in the JobConf.
- @param job the job
- @param driverClass JDBC Driver class name
- @param dbUrl JDBC DB access URL.]]>
- </doc>
- </method>
- <field name="DRIVER_CLASS_PROPERTY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[The JDBC Driver class name]]>
- </doc>
- </field>
- <field name="URL_PROPERTY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[JDBC Database access URL]]>
- </doc>
- </field>
- <field name="USERNAME_PROPERTY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[User name to access the database]]>
- </doc>
- </field>
- <field name="PASSWORD_PROPERTY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Password to access the database]]>
- </doc>
- </field>
- <field name="INPUT_TABLE_NAME_PROPERTY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Input table name]]>
- </doc>
- </field>
- <field name="INPUT_FIELD_NAMES_PROPERTY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Field names in the Input table]]>
- </doc>
- </field>
- <field name="INPUT_CONDITIONS_PROPERTY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[WHERE clause in the input SELECT statement]]>
- </doc>
- </field>
- <field name="INPUT_ORDER_BY_PROPERTY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[ORDER BY clause in the input SELECT statement]]>
- </doc>
- </field>
- <field name="INPUT_QUERY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Whole input query, exluding LIMIT...OFFSET]]>
- </doc>
- </field>
- <field name="INPUT_COUNT_QUERY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Input query to get the count of records]]>
- </doc>
- </field>
- <field name="INPUT_CLASS_PROPERTY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Class name implementing DBWritable which will hold input tuples]]>
- </doc>
- </field>
- <field name="OUTPUT_TABLE_NAME_PROPERTY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Output table name]]>
- </doc>
- </field>
- <field name="OUTPUT_FIELD_NAMES_PROPERTY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Field names in the Output table]]>
- </doc>
- </field>
- <field name="OUTPUT_FIELD_COUNT_PROPERTY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Number of fields in the Output table]]>
- </doc>
- </field>
- <doc>
- <![CDATA[@deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.db.DBConfiguration} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.db.DBConfiguration -->
- <!-- start class org.apache.hadoop.mapred.lib.db.DBInputFormat -->
- <class name="DBInputFormat" extends="org.apache.hadoop.mapreduce.lib.db.DBInputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.lib.db.DBInputFormat} instead.">
- <implements name="org.apache.hadoop.mapred.InputFormat"/>
- <implements name="org.apache.hadoop.mapred.JobConfigurable"/>
- <constructor name="DBInputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="configure"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <method name="getRecordReader" return="org.apache.hadoop.mapred.RecordReader"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapred.InputSplit"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <method name="getSplits" return="org.apache.hadoop.mapred.InputSplit[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="chunks" type="int"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <method name="setInput"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="inputClass" type="java.lang.Class"/>
- <param name="tableName" type="java.lang.String"/>
- <param name="conditions" type="java.lang.String"/>
- <param name="orderBy" type="java.lang.String"/>
- <param name="fieldNames" type="java.lang.String[]"/>
- <doc>
- <![CDATA[Initializes the map-part of the job with the appropriate input settings.
-
- @param job The job
- @param inputClass the class object implementing DBWritable, which is the
- Java object holding tuple fields.
- @param tableName The table to read data from
- @param conditions The condition which to select data with, eg. '(updated >
- 20070101 AND length > 0)'
- @param orderBy the fieldNames in the orderBy clause.
- @param fieldNames The field names in the table
- @see #setInput(JobConf, Class, String, String)]]>
- </doc>
- </method>
- <method name="setInput"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="inputClass" type="java.lang.Class"/>
- <param name="inputQuery" type="java.lang.String"/>
- <param name="inputCountQuery" type="java.lang.String"/>
- <doc>
- <![CDATA[Initializes the map-part of the job with the appropriate input settings.
-
- @param job The job
- @param inputClass the class object implementing DBWritable, which is the
- Java object holding tuple fields.
- @param inputQuery the input query to select fields. Example :
- "SELECT f1, f2, f3 FROM Mytable ORDER BY f1"
- @param inputCountQuery the input query that returns the number of records in
- the table.
- Example : "SELECT COUNT(f1) FROM Mytable"
- @see #setInput(JobConf, Class, String, String, String, String...)]]>
- </doc>
- </method>
- <doc>
- <![CDATA[@deprecated
- Use {@link org.apache.hadoop.mapreduce.lib.db.DBInputFormat} instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.db.DBInputFormat -->
- <!-- start class org.apache.hadoop.mapred.lib.db.DBInputFormat.DBInputSplit -->
- <class name="DBInputFormat.DBInputSplit" extends="org.apache.hadoop.mapreduce.lib.db.DBInputFormat.DBInputSplit"
- abstract="false"
- static="true" final="false" visibility="protected"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapred.InputSplit"/>
- <constructor name="DBInputFormat.DBInputSplit"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Default Constructor]]>
- </doc>
- </constructor>
- <constructor name="DBInputFormat.DBInputSplit" type="long, long"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Convenience Constructor
- @param start the index of the first row to select
- @param end the index of the last row to select]]>
- </doc>
- </constructor>
- <doc>
- <![CDATA[A InputSplit that spans a set of rows]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.db.DBInputFormat.DBInputSplit -->
- <!-- start class org.apache.hadoop.mapred.lib.db.DBInputFormat.DBRecordReader -->
- <class name="DBInputFormat.DBRecordReader" extends="org.apache.hadoop.mapreduce.lib.db.DBRecordReader"
- abstract="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapred.RecordReader"/>
- <constructor name="DBInputFormat.DBRecordReader" type="org.apache.hadoop.mapred.lib.db.DBInputFormat.DBInputSplit, java.lang.Class, org.apache.hadoop.mapred.JobConf, java.sql.Connection, org.apache.hadoop.mapred.lib.db.DBConfiguration, java.lang.String, java.lang.String[], java.lang.String"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <exception name="SQLException" type="java.sql.SQLException"/>
- <doc>
- <![CDATA[@param split The InputSplit to read data for
- @throws SQLException]]>
- </doc>
- </constructor>
- <method name="createKey" return="org.apache.hadoop.io.LongWritable"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <method name="createValue" return="T"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <method name="getPos" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="next" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="org.apache.hadoop.io.LongWritable"/>
- <param name="value" type="T"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <doc>
- <![CDATA[A RecordReader that reads records from a SQL table.
- Emits LongWritables containing the record number as
- key and DBWritables as value.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.db.DBInputFormat.DBRecordReader -->
- <!-- start class org.apache.hadoop.mapred.lib.db.DBInputFormat.NullDBWritable -->
- <class name="DBInputFormat.NullDBWritable" extends="org.apache.hadoop.mapreduce.lib.db.DBInputFormat.NullDBWritable"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapred.lib.db.DBWritable"/>
- <implements name="org.apache.hadoop.io.Writable"/>
- <constructor name="DBInputFormat.NullDBWritable"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <doc>
- <![CDATA[A Class that does nothing, implementing DBWritable]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.db.DBInputFormat.NullDBWritable -->
- <!-- start class org.apache.hadoop.mapred.lib.db.DBOutputFormat -->
- <class name="DBOutputFormat" extends="org.apache.hadoop.mapreduce.lib.db.DBOutputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use org.apache.hadoop.mapreduce.lib.db.DBOutputFormat instead">
- <implements name="org.apache.hadoop.mapred.OutputFormat"/>
- <constructor name="DBOutputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="checkOutputSpecs"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="filesystem" type="org.apache.hadoop.fs.FileSystem"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <method name="getRecordWriter" return="org.apache.hadoop.mapred.RecordWriter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="filesystem" type="org.apache.hadoop.fs.FileSystem"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="name" type="java.lang.String"/>
- <param name="progress" type="org.apache.hadoop.util.Progressable"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <method name="setOutput"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="tableName" type="java.lang.String"/>
- <param name="fieldNames" type="java.lang.String[]"/>
- <doc>
- <![CDATA[Initializes the reduce-part of the job with the appropriate output settings
-
- @param job The job
- @param tableName The table to insert data into
- @param fieldNames The field names in the table.]]>
- </doc>
- </method>
- <method name="setOutput"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="tableName" type="java.lang.String"/>
- <param name="fieldCount" type="int"/>
- <doc>
- <![CDATA[Initializes the reduce-part of the job with the appropriate output settings
-
- @param job The job
- @param tableName The table to insert data into
- @param fieldCount the number of fields in the table.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[@deprecated Use org.apache.hadoop.mapreduce.lib.db.DBOutputFormat instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.db.DBOutputFormat -->
- <!-- start class org.apache.hadoop.mapred.lib.db.DBOutputFormat.DBRecordWriter -->
- <class name="DBOutputFormat.DBRecordWriter" extends="org.apache.hadoop.mapreduce.lib.db.DBOutputFormat.DBRecordWriter"
- abstract="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapred.RecordWriter"/>
- <constructor name="DBOutputFormat.DBRecordWriter" type="java.sql.Connection, java.sql.PreparedStatement"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <exception name="SQLException" type="java.sql.SQLException"/>
- </constructor>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <doc>
- <![CDATA[A RecordWriter that writes the reduce output to a SQL table]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.db.DBOutputFormat.DBRecordWriter -->
- <!-- start interface org.apache.hadoop.mapred.lib.db.DBWritable -->
- <interface name="DBWritable" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.lib.db.DBWritable} instead">
- <implements name="org.apache.hadoop.mapreduce.lib.db.DBWritable"/>
- <doc>
- <![CDATA[@deprecated
- Use {@link org.apache.hadoop.mapreduce.lib.db.DBWritable} instead]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.lib.db.DBWritable -->
- </package>
- <package name="org.apache.hadoop.mapred.pipes">
- <!-- start class org.apache.hadoop.mapred.pipes.Submitter -->
- <class name="Submitter" extends="org.apache.hadoop.conf.Configured"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.util.Tool"/>
- <constructor name="Submitter"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <constructor name="Submitter" type="org.apache.hadoop.conf.Configuration"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getExecutable" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[Get the URI of the application's executable.
- @param conf
- @return the URI where the application's executable is located]]>
- </doc>
- </method>
- <method name="setExecutable"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="executable" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the URI for the application's executable. Normally this is a hdfs:
- location.
- @param conf
- @param executable The URI of the application's executable.]]>
- </doc>
- </method>
- <method name="setIsJavaRecordReader"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="value" type="boolean"/>
- <doc>
- <![CDATA[Set whether the job is using a Java RecordReader.
- @param conf the configuration to modify
- @param value the new value]]>
- </doc>
- </method>
- <method name="getIsJavaRecordReader" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[Check whether the job is using a Java RecordReader
- @param conf the configuration to check
- @return is it a Java RecordReader?]]>
- </doc>
- </method>
- <method name="setIsJavaMapper"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="value" type="boolean"/>
- <doc>
- <![CDATA[Set whether the Mapper is written in Java.
- @param conf the configuration to modify
- @param value the new value]]>
- </doc>
- </method>
- <method name="getIsJavaMapper" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[Check whether the job is using a Java Mapper.
- @param conf the configuration to check
- @return is it a Java Mapper?]]>
- </doc>
- </method>
- <method name="setIsJavaReducer"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="value" type="boolean"/>
- <doc>
- <![CDATA[Set whether the Reducer is written in Java.
- @param conf the configuration to modify
- @param value the new value]]>
- </doc>
- </method>
- <method name="getIsJavaReducer" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[Check whether the job is using a Java Reducer.
- @param conf the configuration to check
- @return is it a Java Reducer?]]>
- </doc>
- </method>
- <method name="setIsJavaRecordWriter"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="value" type="boolean"/>
- <doc>
- <![CDATA[Set whether the job will use a Java RecordWriter.
- @param conf the configuration to modify
- @param value the new value to set]]>
- </doc>
- </method>
- <method name="getIsJavaRecordWriter" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[Will the reduce use a Java RecordWriter?
- @param conf the configuration to check
- @return true, if the output of the job will be written by Java]]>
- </doc>
- </method>
- <method name="getKeepCommandFile" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[Does the user want to keep the command file for debugging? If this is
- true, pipes will write a copy of the command data to a file in the
- task directory named "downlink.data", which may be used to run the C++
- program under the debugger. You probably also want to set
- JobConf.setKeepFailedTaskFiles(true) to keep the entire directory from
- being deleted.
- To run using the data file, set the environment variable
- "mapreduce.pipes.commandfile" to point to the file.
- @param conf the configuration to check
- @return will the framework save the command file?]]>
- </doc>
- </method>
- <method name="setKeepCommandFile"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="keep" type="boolean"/>
- <doc>
- <![CDATA[Set whether to keep the command file for debugging
- @param conf the configuration to modify
- @param keep the new value]]>
- </doc>
- </method>
- <method name="submitJob" return="org.apache.hadoop.mapred.RunningJob"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="Use {@link Submitter#runJob(JobConf)}">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Submit a job to the map/reduce cluster. All of the necessary modifications
- to the job to run under pipes are made to the configuration.
- @param conf the job to submit to the cluster (MODIFIED)
- @throws IOException
- @deprecated Use {@link Submitter#runJob(JobConf)}]]>
- </doc>
- </method>
- <method name="runJob" return="org.apache.hadoop.mapred.RunningJob"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Submit a job to the map/reduce cluster. All of the necessary modifications
- to the job to run under pipes are made to the configuration.
- @param conf the job to submit to the cluster (MODIFIED)
- @throws IOException]]>
- </doc>
- </method>
- <method name="jobSubmit" return="org.apache.hadoop.mapred.RunningJob"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Submit a job to the Map-Reduce framework.
- This returns a handle to the {@link RunningJob} which can be used to track
- the running-job.
-
- @param conf the job configuration.
- @return a handle to the {@link RunningJob} which can be used to track the
- running-job.
- @throws IOException]]>
- </doc>
- </method>
- <method name="run" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="args" type="java.lang.String[]"/>
- <exception name="Exception" type="java.lang.Exception"/>
- </method>
- <method name="main"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="args" type="java.lang.String[]"/>
- <exception name="Exception" type="java.lang.Exception"/>
- <doc>
- <![CDATA[Submit a pipes job based on the command line arguments.
- @param args]]>
- </doc>
- </method>
- <field name="LOG" type="org.apache.commons.logging.Log"
- transient="false" volatile="false"
- static="true" final="true" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="PRESERVE_COMMANDFILE" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="EXECUTABLE" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="INTERPRETOR" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="IS_JAVA_MAP" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="IS_JAVA_RR" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="IS_JAVA_RW" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="IS_JAVA_REDUCE" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="PARTITIONER" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="INPUT_FORMAT" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="PORT" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[The main entry point and job submitter. It may either be used as a command
- line-based or API-based method to launch Pipes jobs.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.pipes.Submitter -->
- </package>
- <package name="org.apache.hadoop.mapred.tools">
- <!-- start class org.apache.hadoop.mapred.tools.MRAdmin -->
- <class name="MRAdmin" extends="org.apache.hadoop.conf.Configured"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.util.Tool"/>
- <constructor name="MRAdmin"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <constructor name="MRAdmin" type="org.apache.hadoop.conf.Configuration"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="refreshSuperUserGroupsConfiguration" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[refreshSuperUserGroupsConfiguration {@link JobTracker}.
- @return exitcode 0 on success, non-zero on failure
- @throws IOException]]>
- </doc>
- </method>
- <method name="run" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="args" type="java.lang.String[]"/>
- <exception name="Exception" type="java.lang.Exception"/>
- </method>
- <method name="main"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="args" type="java.lang.String[]"/>
- <exception name="Exception" type="java.lang.Exception"/>
- </method>
- <doc>
- <![CDATA[Administrative access to Hadoop Map-Reduce.
-
- Currently it only provides the ability to connect to the {@link JobTracker}
- and 1) refresh the service-level authorization policy, 2) refresh queue acl
- properties.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.tools.MRAdmin -->
- </package>
- <package name="org.apache.hadoop.mapreduce">
- <!-- start class org.apache.hadoop.mapreduce.Cluster -->
- <class name="Cluster" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="Cluster" type="org.apache.hadoop.conf.Configuration"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </constructor>
- <constructor name="Cluster" type="java.net.InetSocketAddress, org.apache.hadoop.conf.Configuration"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </constructor>
- <method name="close"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Close the <code>Cluster</code>.]]>
- </doc>
- </method>
- <method name="getFileSystem" return="org.apache.hadoop.fs.FileSystem"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Get the file system where job-specific files are stored
-
- @return object of FileSystem
- @throws IOException
- @throws InterruptedException]]>
- </doc>
- </method>
- <method name="getJob" return="org.apache.hadoop.mapreduce.Job"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobId" type="org.apache.hadoop.mapreduce.JobID"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Get job corresponding to jobid.
-
- @param jobId
- @return object of {@link Job}
- @throws IOException
- @throws InterruptedException]]>
- </doc>
- </method>
- <method name="getQueues" return="org.apache.hadoop.mapreduce.QueueInfo[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Get all the queues in cluster.
-
- @return array of {@link QueueInfo}
- @throws IOException
- @throws InterruptedException]]>
- </doc>
- </method>
- <method name="getQueue" return="org.apache.hadoop.mapreduce.QueueInfo"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Get queue information for the specified name.
-
- @param name queuename
- @return object of {@link QueueInfo}
- @throws IOException
- @throws InterruptedException]]>
- </doc>
- </method>
- <method name="getClusterStatus" return="org.apache.hadoop.mapreduce.ClusterMetrics"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Get current cluster status.
-
- @return object of {@link ClusterMetrics}
- @throws IOException
- @throws InterruptedException]]>
- </doc>
- </method>
- <method name="getActiveTaskTrackers" return="org.apache.hadoop.mapreduce.TaskTrackerInfo[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Get all active trackers in the cluster.
-
- @return array of {@link TaskTrackerInfo}
- @throws IOException
- @throws InterruptedException]]>
- </doc>
- </method>
- <method name="getBlackListedTaskTrackers" return="org.apache.hadoop.mapreduce.TaskTrackerInfo[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Get blacklisted trackers.
-
- @return array of {@link TaskTrackerInfo}
- @throws IOException
- @throws InterruptedException]]>
- </doc>
- </method>
- <method name="getAllJobs" return="org.apache.hadoop.mapreduce.Job[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Get all the jobs in cluster.
-
- @return array of {@link Job}
- @throws IOException
- @throws InterruptedException]]>
- </doc>
- </method>
- <method name="getSystemDir" return="org.apache.hadoop.fs.Path"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Grab the jobtracker system directory path where
- job-specific files will be placed.
-
- @return the system directory where job-specific files are to be placed.]]>
- </doc>
- </method>
- <method name="getStagingAreaDir" return="org.apache.hadoop.fs.Path"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Grab the jobtracker's view of the staging directory path where
- job-specific files will be placed.
-
- @return the staging directory where job-specific files are to be placed.]]>
- </doc>
- </method>
- <method name="getJobHistoryUrl" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobId" type="org.apache.hadoop.mapreduce.JobID"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Get the job history file path for a given job id. The job history file at
- this path may or may not be existing depending on the job completion state.
- The file is present only for the completed jobs.
- @param jobId the JobID of the job submitted by the current user.
- @return the file path of the job history file
- @throws IOException
- @throws InterruptedException]]>
- </doc>
- </method>
- <method name="getQueueAclsForCurrentUser" return="org.apache.hadoop.mapreduce.QueueAclsInfo[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Gets the Queue ACLs for current user
- @return array of QueueAclsInfo object for current user.
- @throws IOException]]>
- </doc>
- </method>
- <method name="getRootQueues" return="org.apache.hadoop.mapreduce.QueueInfo[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Gets the root level queues.
- @return array of JobQueueInfo object.
- @throws IOException]]>
- </doc>
- </method>
- <method name="getChildQueues" return="org.apache.hadoop.mapreduce.QueueInfo[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="queueName" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Returns immediate children of queueName.
- @param queueName
- @return array of JobQueueInfo which are children of queueName
- @throws IOException]]>
- </doc>
- </method>
- <method name="getJobTrackerState" return="org.apache.hadoop.mapreduce.server.jobtracker.State"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link #getJobTrackerStatus()} instead.">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Get JobTracker's state
-
- @return {@link State} of the JobTracker
- @throws IOException
- @throws InterruptedException
- @deprecated Use {@link #getJobTrackerStatus()} instead.]]>
- </doc>
- </method>
- <method name="getJobTrackerStatus" return="org.apache.hadoop.mapreduce.Cluster.JobTrackerStatus"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Get the JobTracker's status.
-
- @return {@link JobTrackerStatus} of the JobTracker
- @throws IOException
- @throws InterruptedException]]>
- </doc>
- </method>
- <method name="getTaskTrackerExpiryInterval" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Get the tasktracker expiry interval for the cluster
- @return the expiry interval in msec]]>
- </doc>
- </method>
- <method name="getDelegationToken" return="org.apache.hadoop.security.token.Token"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="renewer" type="org.apache.hadoop.io.Text"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Get a delegation token for the user from the JobTracker.
- @param renewer the user who can renew the token
- @return the new token
- @throws IOException]]>
- </doc>
- </method>
- <method name="renewDelegationToken" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="token" type="org.apache.hadoop.security.token.Token"/>
- <exception name="SecretManager.InvalidToken" type="org.apache.hadoop.security.token.SecretManager.InvalidToken"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Renew a delegation token
- @param token the token to renew
- @return the new expiration time
- @throws InvalidToken
- @throws IOException]]>
- </doc>
- </method>
- <method name="cancelDelegationToken"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="token" type="org.apache.hadoop.security.token.Token"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Cancel a delegation token from the JobTracker
- @param token the token to cancel
- @throws IOException]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Provides a way to access information about the map/reduce cluster.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.Cluster -->
- <!-- start class org.apache.hadoop.mapreduce.Cluster.JobTrackerStatus -->
- <class name="Cluster.JobTrackerStatus" extends="java.lang.Enum"
- abstract="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <method name="values" return="org.apache.hadoop.mapreduce.Cluster.JobTrackerStatus[]"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="valueOf" return="org.apache.hadoop.mapreduce.Cluster.JobTrackerStatus"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- </method>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.Cluster.JobTrackerStatus -->
- <!-- start class org.apache.hadoop.mapreduce.ClusterMetrics -->
- <class name="ClusterMetrics" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.io.Writable"/>
- <constructor name="ClusterMetrics"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <constructor name="ClusterMetrics" type="int, int, int, int, int, int, int, int, int, int, int, int"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getRunningMaps" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the number of running map tasks in the cluster.
-
- @return running maps]]>
- </doc>
- </method>
- <method name="getRunningReduces" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the number of running reduce tasks in the cluster.
-
- @return running reduces]]>
- </doc>
- </method>
- <method name="getOccupiedMapSlots" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get number of occupied map slots in the cluster.
-
- @return occupied map slot count]]>
- </doc>
- </method>
- <method name="getOccupiedReduceSlots" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the number of occupied reduce slots in the cluster.
-
- @return occupied reduce slot count]]>
- </doc>
- </method>
- <method name="getReservedMapSlots" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get number of reserved map slots in the cluster.
-
- @return reserved map slot count]]>
- </doc>
- </method>
- <method name="getReservedReduceSlots" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the number of reserved reduce slots in the cluster.
-
- @return reserved reduce slot count]]>
- </doc>
- </method>
- <method name="getMapSlotCapacity" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the total number of map slots in the cluster.
-
- @return map slot capacity]]>
- </doc>
- </method>
- <method name="getReduceSlotCapacity" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the total number of reduce slots in the cluster.
-
- @return reduce slot capacity]]>
- </doc>
- </method>
- <method name="getTotalJobSubmissions" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the total number of job submissions in the cluster.
-
- @return total number of job submissions]]>
- </doc>
- </method>
- <method name="getTaskTrackerCount" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the number of active trackers in the cluster.
-
- @return active tracker count.]]>
- </doc>
- </method>
- <method name="getBlackListedTaskTrackerCount" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the number of blacklisted trackers in the cluster.
-
- @return blacklisted tracker count]]>
- </doc>
- </method>
- <method name="getDecommissionedTaskTrackerCount" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the number of decommissioned trackers in the cluster.
-
- @return decommissioned tracker count]]>
- </doc>
- </method>
- <method name="readFields"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="in" type="java.io.DataInput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="out" type="java.io.DataOutput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[Status information on the current state of the Map-Reduce cluster.
-
- <p><code>ClusterMetrics</code> provides clients with information such as:
- <ol>
- <li>
- Size of the cluster.
- </li>
- <li>
- Number of blacklisted and decommissioned trackers.
- </li>
- <li>
- Slot capacity of the cluster.
- </li>
- <li>
- The number of currently occupied/reserved map & reduce slots.
- </li>
- <li>
- The number of currently running map & reduce tasks.
- </li>
- <li>
- The number of job submissions.
- </li>
- </ol></p>
-
- <p>Clients can query for the latest <code>ClusterMetrics</code>, via
- {@link Cluster#getClusterStatus()}.</p>
-
- @see Cluster]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.ClusterMetrics -->
- <!-- start class org.apache.hadoop.mapreduce.ContextFactory -->
- <class name="ContextFactory" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="ContextFactory"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="cloneContext" return="org.apache.hadoop.mapreduce.JobContext"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="original" type="org.apache.hadoop.mapreduce.JobContext"/>
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Clone a job or task attempt context with a new configuration.
- @param original the original context
- @param conf the new configuration
- @return a new context object
- @throws InterruptedException
- @throws IOException]]>
- </doc>
- </method>
- <method name="cloneMapContext" return="org.apache.hadoop.mapreduce.Mapper.Context"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.MapContext"/>
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <param name="reader" type="org.apache.hadoop.mapreduce.RecordReader"/>
- <param name="writer" type="org.apache.hadoop.mapreduce.RecordWriter"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Copy a mapper context, optionally replacing the input and output.
- @param <K1> input key type
- @param <V1> input value type
- @param <K2> output key type
- @param <V2> output value type
- @param context the context to clone
- @param conf a new configuration
- @param reader Reader to read from. Null means to clone from context.
- @param writer Writer to write to. Null means to clone from context.
- @return a new context. it will not be the same class as the original.
- @throws IOException
- @throws InterruptedException]]>
- </doc>
- </method>
- <doc>
- <![CDATA[A factory to allow applications to deal with inconsistencies between
- MapReduce Context Objects API between hadoop-0.20 and later versions.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.ContextFactory -->
- <!-- start class org.apache.hadoop.mapreduce.Counter -->
- <class name="Counter" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.io.Writable"/>
- <constructor name="Counter"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </constructor>
- <constructor name="Counter" type="java.lang.String, java.lang.String"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </constructor>
- <constructor name="Counter" type="java.lang.String, java.lang.String, long"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Create a counter.
- @param name the name within the group's enum.
- @param displayName a name to be displayed.
- @param value the counter value.]]>
- </doc>
- </constructor>
- <method name="setDisplayName"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="displayName" type="java.lang.String"/>
- </method>
- <method name="readFields"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="in" type="java.io.DataInput"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Read the binary representation of the counter]]>
- </doc>
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="out" type="java.io.DataOutput"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Write the binary representation of the counter]]>
- </doc>
- </method>
- <method name="getName" return="java.lang.String"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getDisplayName" return="java.lang.String"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the name of the counter.
- @return the user facing name of the counter]]>
- </doc>
- </method>
- <method name="getValue" return="long"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[What is the current value of this counter?
- @return the current value]]>
- </doc>
- </method>
- <method name="setValue"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="value" type="long"/>
- <doc>
- <![CDATA[Set this counter by the given value
- @param value the value to set]]>
- </doc>
- </method>
- <method name="increment"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="incr" type="long"/>
- <doc>
- <![CDATA[Increment this counter by the given value
- @param incr the value to increase this counter by]]>
- </doc>
- </method>
- <method name="equals" return="boolean"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="genericRight" type="java.lang.Object"/>
- </method>
- <method name="hashCode" return="int"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <doc>
- <![CDATA[A named counter that tracks the progress of a map/reduce job.
-
- <p><code>Counters</code> represent global counters, defined either by the
- Map-Reduce framework or applications. Each <code>Counter</code> is named by
- an {@link Enum} and has a long for the value.</p>
-
- <p><code>Counters</code> are bunched into Groups, each comprising of
- counters from a particular <code>Enum</code> class.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.Counter -->
- <!-- start class org.apache.hadoop.mapreduce.CounterGroup -->
- <class name="CounterGroup" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.io.Writable"/>
- <implements name="java.lang.Iterable"/>
- <constructor name="CounterGroup" type="java.lang.String"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </constructor>
- <constructor name="CounterGroup" type="java.lang.String, java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Create a CounterGroup.
- @param name the name of the group's enum.
- @param displayName a name to be displayed for the group.]]>
- </doc>
- </constructor>
- <method name="getName" return="java.lang.String"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the internal name of the group
- @return the internal name]]>
- </doc>
- </method>
- <method name="getDisplayName" return="java.lang.String"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the display name of the group.
- @return the human readable name]]>
- </doc>
- </method>
- <method name="addCounter"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="counter" type="org.apache.hadoop.mapreduce.Counter"/>
- <doc>
- <![CDATA[Add a counter to this group.]]>
- </doc>
- </method>
- <method name="findCounter" return="org.apache.hadoop.mapreduce.Counter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="counterName" type="java.lang.String"/>
- <param name="displayName" type="java.lang.String"/>
- <doc>
- <![CDATA[Find a counter in a group.
- @param counterName the name of the counter
- @param displayName the display name of the counter
- @return the counter that was found or added]]>
- </doc>
- </method>
- <method name="findCounter" return="org.apache.hadoop.mapreduce.Counter"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="counterName" type="java.lang.String"/>
- </method>
- <method name="iterator" return="java.util.Iterator"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="out" type="java.io.DataOutput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="readFields"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="in" type="java.io.DataInput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="size" return="int"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns the number of counters in this group.]]>
- </doc>
- </method>
- <method name="equals" return="boolean"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="genericRight" type="java.lang.Object"/>
- </method>
- <method name="hashCode" return="int"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="incrAllCounters"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="rightGroup" type="org.apache.hadoop.mapreduce.CounterGroup"/>
- </method>
- <doc>
- <![CDATA[A group of {@link Counter}s that logically belong together. Typically,
- it is an {@link Enum} subclass and the counters are the values.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.CounterGroup -->
- <!-- start class org.apache.hadoop.mapreduce.Counters -->
- <class name="Counters" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.io.Writable"/>
- <implements name="java.lang.Iterable"/>
- <constructor name="Counters"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <constructor name="Counters" type="org.apache.hadoop.mapred.Counters"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Utility method to create a Counters object from the
- org.apache.hadoop.mapred counters
- @param counters]]>
- </doc>
- </constructor>
- <method name="addGroup"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="group" type="org.apache.hadoop.mapreduce.CounterGroup"/>
- <doc>
- <![CDATA[Add a group.]]>
- </doc>
- </method>
- <method name="findCounter" return="org.apache.hadoop.mapreduce.Counter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="groupName" type="java.lang.String"/>
- <param name="counterName" type="java.lang.String"/>
- </method>
- <method name="findCounter" return="org.apache.hadoop.mapreduce.Counter"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="java.lang.Enum"/>
- <doc>
- <![CDATA[Find the counter for the given enum. The same enum will always return the
- same counter.
- @param key the counter key
- @return the matching counter object]]>
- </doc>
- </method>
- <method name="getGroupNames" return="java.util.Collection"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns the names of all counter classes.
- @return Set of counter names.]]>
- </doc>
- </method>
- <method name="iterator" return="java.util.Iterator"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getGroup" return="org.apache.hadoop.mapreduce.CounterGroup"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="groupName" type="java.lang.String"/>
- <doc>
- <![CDATA[Returns the named counter group, or an empty group if there is none
- with the specified name.]]>
- </doc>
- </method>
- <method name="countCounters" return="int"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns the total number of counters, by summing the number of counters
- in each group.]]>
- </doc>
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="out" type="java.io.DataOutput"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Write the set of groups.
- The external format is:
- #groups (groupName group)*
- i.e. the number of groups followed by 0 or more groups, where each
- group is of the form:
- groupDisplayName #counters (false | true counter)*
- where each counter is of the form:
- name (false | true displayName) value]]>
- </doc>
- </method>
- <method name="readFields"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="in" type="java.io.DataInput"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Read a set of groups.]]>
- </doc>
- </method>
- <method name="toString" return="java.lang.String"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Return textual representation of the counter values.]]>
- </doc>
- </method>
- <method name="incrAllCounters"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="other" type="org.apache.hadoop.mapreduce.Counters"/>
- <doc>
- <![CDATA[Increments multiple counters by their amounts in another Counters
- instance.
- @param other the other Counters instance]]>
- </doc>
- </method>
- <method name="equals" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="genericRight" type="java.lang.Object"/>
- </method>
- <method name="hashCode" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.Counters -->
- <!-- start class org.apache.hadoop.mapreduce.ID -->
- <class name="ID" extends="java.lang.Object"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.io.WritableComparable"/>
- <constructor name="ID" type="int"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[constructs an ID object from the given int]]>
- </doc>
- </constructor>
- <constructor name="ID"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </constructor>
- <method name="getId" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[returns the int which represents the identifier]]>
- </doc>
- </method>
- <method name="toString" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="hashCode" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="equals" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="o" type="java.lang.Object"/>
- </method>
- <method name="compareTo" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="that" type="org.apache.hadoop.mapreduce.ID"/>
- <doc>
- <![CDATA[Compare IDs by associated numbers]]>
- </doc>
- </method>
- <method name="readFields"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="in" type="java.io.DataInput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="out" type="java.io.DataOutput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <field name="SEPARATOR" type="char"
- transient="false" volatile="false"
- static="true" final="true" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="id" type="int"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[A general identifier, which internally stores the id
- as an integer. This is the super class of {@link JobID},
- {@link TaskID} and {@link TaskAttemptID}.
-
- @see JobID
- @see TaskID
- @see TaskAttemptID]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.ID -->
- <!-- start class org.apache.hadoop.mapreduce.InputFormat -->
- <class name="InputFormat" extends="java.lang.Object"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="InputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getSplits" return="java.util.List"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.JobContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Logically split the set of input files for the job.
-
- <p>Each {@link InputSplit} is then assigned to an individual {@link Mapper}
- for processing.</p>
- <p><i>Note</i>: The split is a <i>logical</i> split of the inputs and the
- input files are not physically split into chunks. For e.g. a split could
- be <i><input-file-path, start, offset></i> tuple. The InputFormat
- also creates the {@link RecordReader} to read the {@link InputSplit}.
-
- @param context job configuration.
- @return an array of {@link InputSplit}s for the job.]]>
- </doc>
- </method>
- <method name="createRecordReader" return="org.apache.hadoop.mapreduce.RecordReader"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapreduce.InputSplit"/>
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Create a record reader for a given split. The framework will call
- {@link RecordReader#initialize(InputSplit, TaskAttemptContext)} before
- the split is used.
- @param split the split to be read
- @param context the information about the task
- @return a new record reader
- @throws IOException
- @throws InterruptedException]]>
- </doc>
- </method>
- <doc>
- <![CDATA[<code>InputFormat</code> describes the input-specification for a
- Map-Reduce job.
-
- <p>The Map-Reduce framework relies on the <code>InputFormat</code> of the
- job to:<p>
- <ol>
- <li>
- Validate the input-specification of the job.
- <li>
- Split-up the input file(s) into logical {@link InputSplit}s, each of
- which is then assigned to an individual {@link Mapper}.
- </li>
- <li>
- Provide the {@link RecordReader} implementation to be used to glean
- input records from the logical <code>InputSplit</code> for processing by
- the {@link Mapper}.
- </li>
- </ol>
-
- <p>The default behavior of file-based {@link InputFormat}s, typically
- sub-classes of {@link FileInputFormat}, is to split the
- input into <i>logical</i> {@link InputSplit}s based on the total size, in
- bytes, of the input files. However, the {@link FileSystem} blocksize of
- the input files is treated as an upper bound for input splits. A lower bound
- on the split size can be set via
- <a href="{@docRoot}/../mapred-default.html#mapreduce.input.fileinputformat.split.minsize">
- mapreduce.input.fileinputformat.split.minsize</a>.</p>
-
- <p>Clearly, logical splits based on input-size is insufficient for many
- applications since record boundaries are to respected. In such cases, the
- application has to also implement a {@link RecordReader} on whom lies the
- responsibility to respect record-boundaries and present a record-oriented
- view of the logical <code>InputSplit</code> to the individual task.
- @see InputSplit
- @see RecordReader
- @see FileInputFormat]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.InputFormat -->
- <!-- start class org.apache.hadoop.mapreduce.InputSplit -->
- <class name="InputSplit" extends="java.lang.Object"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="InputSplit"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getLength" return="long"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Get the size of the split, so that the input splits can be sorted by size.
- @return the number of bytes in the split
- @throws IOException
- @throws InterruptedException]]>
- </doc>
- </method>
- <method name="getLocations" return="java.lang.String[]"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Get the list of nodes by name where the data for the split would be local.
- The locations do not need to be serialized.
- @return a new array of the node nodes.
- @throws IOException
- @throws InterruptedException]]>
- </doc>
- </method>
- <doc>
- <![CDATA[<code>InputSplit</code> represents the data to be processed by an
- individual {@link Mapper}.
- <p>Typically, it presents a byte-oriented view on the input and is the
- responsibility of {@link RecordReader} of the job to process this and present
- a record-oriented view.
-
- @see InputFormat
- @see RecordReader]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.InputSplit -->
- <!-- start class org.apache.hadoop.mapreduce.Job -->
- <class name="Job" extends="org.apache.hadoop.mapreduce.task.JobContextImpl"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.JobContext"/>
- <constructor name="Job"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </constructor>
- <constructor name="Job" type="org.apache.hadoop.conf.Configuration"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </constructor>
- <constructor name="Job" type="org.apache.hadoop.conf.Configuration, java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </constructor>
- <method name="getInstance" return="org.apache.hadoop.mapreduce.Job"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Creates a new {@link Job} with no particular {@link Cluster} .
- A Cluster will be created with a generic {@link Configuration}.
-
- @return the {@link Job} , with no connection to a cluster yet.
- @throws IOException]]>
- </doc>
- </method>
- <method name="getInstance" return="org.apache.hadoop.mapreduce.Job"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Creates a new {@link Job} with no particular {@link Cluster} .
- A Cluster will be created from the conf parameter only when it's needed.
-
- @param conf the configuration
- @return the {@link Job} , with no connection to a cluster yet.
- @throws IOException]]>
- </doc>
- </method>
- <method name="getInstance" return="org.apache.hadoop.mapreduce.Job"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <param name="jobName" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Creates a new {@link Job} with no particular {@link Cluster} and a given jobName.
- A Cluster will be created from the conf parameter only when it's needed.
-
- @param conf the configuration
- @return the {@link Job} , with no connection to a cluster yet.
- @throws IOException]]>
- </doc>
- </method>
- <method name="getInstance" return="org.apache.hadoop.mapreduce.Job"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="cluster" type="org.apache.hadoop.mapreduce.Cluster"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getInstance" return="org.apache.hadoop.mapreduce.Job"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="cluster" type="org.apache.hadoop.mapreduce.Cluster"/>
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getInstance" return="org.apache.hadoop.mapreduce.Job"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="cluster" type="org.apache.hadoop.mapreduce.Cluster"/>
- <param name="status" type="org.apache.hadoop.mapreduce.JobStatus"/>
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getStatus" return="org.apache.hadoop.mapreduce.JobStatus"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="getJobState" return="org.apache.hadoop.mapreduce.JobStatus.State"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Returns the current state of the Job.
-
- @return JobStatus#State
- @throws IOException
- @throws InterruptedException]]>
- </doc>
- </method>
- <method name="getTrackingURL" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the URL where some job progress information will be displayed.
-
- @return the URL where some job progress information will be displayed.]]>
- </doc>
- </method>
- <method name="getJobFile" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the path of the submitted job configuration.
-
- @return the path of the submitted job configuration.]]>
- </doc>
- </method>
- <method name="getStartTime" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get start time of the job.
-
- @return the start time of the job]]>
- </doc>
- </method>
- <method name="getFinishTime" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Get finish time of the job.
-
- @return the finish time of the job]]>
- </doc>
- </method>
- <method name="getSchedulingInfo" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get scheduling info of the job.
-
- @return the scheduling info of the job]]>
- </doc>
- </method>
- <method name="getPriority" return="org.apache.hadoop.mapreduce.JobPriority"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Get scheduling info of the job.
-
- @return the scheduling info of the job]]>
- </doc>
- </method>
- <method name="getJobName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[The user-specified job name.]]>
- </doc>
- </method>
- <method name="getHistoryUrl" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="isRetired" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="toString" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Dump stats to screen.]]>
- </doc>
- </method>
- <method name="getTaskReports" return="org.apache.hadoop.mapreduce.TaskReport[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="type" type="org.apache.hadoop.mapreduce.TaskType"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Get the information of the current state of the tasks of a job.
-
- @param type Type of the task
- @return the list of all of the map tips.
- @throws IOException]]>
- </doc>
- </method>
- <method name="mapProgress" return="float"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Get the <i>progress</i> of the job's map-tasks, as a float between 0.0
- and 1.0. When all map tasks have completed, the function returns 1.0.
-
- @return the progress of the job's map-tasks.
- @throws IOException]]>
- </doc>
- </method>
- <method name="reduceProgress" return="float"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Get the <i>progress</i> of the job's reduce-tasks, as a float between 0.0
- and 1.0. When all reduce tasks have completed, the function returns 1.0.
-
- @return the progress of the job's reduce-tasks.
- @throws IOException]]>
- </doc>
- </method>
- <method name="cleanupProgress" return="float"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Get the <i>progress</i> of the job's cleanup-tasks, as a float between 0.0
- and 1.0. When all cleanup tasks have completed, the function returns 1.0.
-
- @return the progress of the job's cleanup-tasks.
- @throws IOException]]>
- </doc>
- </method>
- <method name="setupProgress" return="float"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Get the <i>progress</i> of the job's setup-tasks, as a float between 0.0
- and 1.0. When all setup tasks have completed, the function returns 1.0.
-
- @return the progress of the job's setup-tasks.
- @throws IOException]]>
- </doc>
- </method>
- <method name="isComplete" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Check if the job is finished or not.
- This is a non-blocking call.
-
- @return <code>true</code> if the job is complete, else <code>false</code>.
- @throws IOException]]>
- </doc>
- </method>
- <method name="isSuccessful" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Check if the job completed successfully.
-
- @return <code>true</code> if the job succeeded, else <code>false</code>.
- @throws IOException]]>
- </doc>
- </method>
- <method name="killJob"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Kill the running job. Blocks until all job tasks have been
- killed as well. If the job is no longer running, it simply returns.
-
- @throws IOException]]>
- </doc>
- </method>
- <method name="setPriority"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="priority" type="org.apache.hadoop.mapreduce.JobPriority"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Set the priority of a running job.
- @param priority the new priority for the job.
- @throws IOException]]>
- </doc>
- </method>
- <method name="getTaskCompletionEvents" return="org.apache.hadoop.mapreduce.TaskCompletionEvent[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="startFrom" type="int"/>
- <param name="numEvents" type="int"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Get events indicating completion (success/failure) of component tasks.
-
- @param startFrom index to start fetching events from
- @param numEvents number of events to fetch
- @return an array of {@link TaskCompletionEvent}s
- @throws IOException]]>
- </doc>
- </method>
- <method name="killTask" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskId" type="org.apache.hadoop.mapreduce.TaskAttemptID"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Kill indicated task attempt.
-
- @param taskId the id of the task to be terminated.
- @throws IOException]]>
- </doc>
- </method>
- <method name="failTask" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskId" type="org.apache.hadoop.mapreduce.TaskAttemptID"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Fail indicated task attempt.
-
- @param taskId the id of the task to be terminated.
- @throws IOException]]>
- </doc>
- </method>
- <method name="getCounters" return="org.apache.hadoop.mapreduce.Counters"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Gets the counters for this job. May return null if the job has been
- retired and the job is no longer in the completed job store.
-
- @return the counters for this job.
- @throws IOException]]>
- </doc>
- </method>
- <method name="getTaskDiagnostics" return="java.lang.String[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskid" type="org.apache.hadoop.mapreduce.TaskAttemptID"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Gets the diagnostic messages for a given task attempt.
- @param taskid
- @return the list of diagnostic messages for the task
- @throws IOException]]>
- </doc>
- </method>
- <method name="setNumReduceTasks"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="tasks" type="int"/>
- <exception name="IllegalStateException" type="java.lang.IllegalStateException"/>
- <doc>
- <![CDATA[Set the number of reduce tasks for the job.
- @param tasks the number of reduce tasks
- @throws IllegalStateException if the job is submitted]]>
- </doc>
- </method>
- <method name="setWorkingDirectory"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="dir" type="org.apache.hadoop.fs.Path"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Set the current working directory for the default file system.
-
- @param dir the new current working directory.
- @throws IllegalStateException if the job is submitted]]>
- </doc>
- </method>
- <method name="setInputFormatClass"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="cls" type="java.lang.Class"/>
- <exception name="IllegalStateException" type="java.lang.IllegalStateException"/>
- <doc>
- <![CDATA[Set the {@link InputFormat} for the job.
- @param cls the <code>InputFormat</code> to use
- @throws IllegalStateException if the job is submitted]]>
- </doc>
- </method>
- <method name="setOutputFormatClass"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="cls" type="java.lang.Class"/>
- <exception name="IllegalStateException" type="java.lang.IllegalStateException"/>
- <doc>
- <![CDATA[Set the {@link OutputFormat} for the job.
- @param cls the <code>OutputFormat</code> to use
- @throws IllegalStateException if the job is submitted]]>
- </doc>
- </method>
- <method name="setMapperClass"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="cls" type="java.lang.Class"/>
- <exception name="IllegalStateException" type="java.lang.IllegalStateException"/>
- <doc>
- <![CDATA[Set the {@link Mapper} for the job.
- @param cls the <code>Mapper</code> to use
- @throws IllegalStateException if the job is submitted]]>
- </doc>
- </method>
- <method name="setJarByClass"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="cls" type="java.lang.Class"/>
- <doc>
- <![CDATA[Set the Jar by finding where a given class came from.
- @param cls the example class]]>
- </doc>
- </method>
- <method name="setJar"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jar" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the job jar]]>
- </doc>
- </method>
- <method name="setUser"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="user" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the reported username for this job.
-
- @param user the username for this job.]]>
- </doc>
- </method>
- <method name="setCombinerClass"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="cls" type="java.lang.Class"/>
- <exception name="IllegalStateException" type="java.lang.IllegalStateException"/>
- <doc>
- <![CDATA[Set the combiner class for the job.
- @param cls the combiner to use
- @throws IllegalStateException if the job is submitted]]>
- </doc>
- </method>
- <method name="setReducerClass"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="cls" type="java.lang.Class"/>
- <exception name="IllegalStateException" type="java.lang.IllegalStateException"/>
- <doc>
- <![CDATA[Set the {@link Reducer} for the job.
- @param cls the <code>Reducer</code> to use
- @throws IllegalStateException if the job is submitted]]>
- </doc>
- </method>
- <method name="setPartitionerClass"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="cls" type="java.lang.Class"/>
- <exception name="IllegalStateException" type="java.lang.IllegalStateException"/>
- <doc>
- <![CDATA[Set the {@link Partitioner} for the job.
- @param cls the <code>Partitioner</code> to use
- @throws IllegalStateException if the job is submitted]]>
- </doc>
- </method>
- <method name="setMapOutputKeyClass"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="theClass" type="java.lang.Class"/>
- <exception name="IllegalStateException" type="java.lang.IllegalStateException"/>
- <doc>
- <![CDATA[Set the key class for the map output data. This allows the user to
- specify the map output key class to be different than the final output
- value class.
-
- @param theClass the map output key class.
- @throws IllegalStateException if the job is submitted]]>
- </doc>
- </method>
- <method name="setMapOutputValueClass"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="theClass" type="java.lang.Class"/>
- <exception name="IllegalStateException" type="java.lang.IllegalStateException"/>
- <doc>
- <![CDATA[Set the value class for the map output data. This allows the user to
- specify the map output value class to be different than the final output
- value class.
-
- @param theClass the map output value class.
- @throws IllegalStateException if the job is submitted]]>
- </doc>
- </method>
- <method name="setOutputKeyClass"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="theClass" type="java.lang.Class"/>
- <exception name="IllegalStateException" type="java.lang.IllegalStateException"/>
- <doc>
- <![CDATA[Set the key class for the job output data.
-
- @param theClass the key class for the job output data.
- @throws IllegalStateException if the job is submitted]]>
- </doc>
- </method>
- <method name="setOutputValueClass"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="theClass" type="java.lang.Class"/>
- <exception name="IllegalStateException" type="java.lang.IllegalStateException"/>
- <doc>
- <![CDATA[Set the value class for job outputs.
-
- @param theClass the value class for job outputs.
- @throws IllegalStateException if the job is submitted]]>
- </doc>
- </method>
- <method name="setSortComparatorClass"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="cls" type="java.lang.Class"/>
- <exception name="IllegalStateException" type="java.lang.IllegalStateException"/>
- <doc>
- <![CDATA[Define the comparator that controls how the keys are sorted before they
- are passed to the {@link Reducer}.
- @param cls the raw comparator
- @throws IllegalStateException if the job is submitted]]>
- </doc>
- </method>
- <method name="setGroupingComparatorClass"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="cls" type="java.lang.Class"/>
- <exception name="IllegalStateException" type="java.lang.IllegalStateException"/>
- <doc>
- <![CDATA[Define the comparator that controls which keys are grouped together
- for a single call to
- {@link Reducer#reduce(Object, Iterable,
- org.apache.hadoop.mapreduce.Reducer.Context)}
- @param cls the raw comparator to use
- @throws IllegalStateException if the job is submitted]]>
- </doc>
- </method>
- <method name="setJobName"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- <exception name="IllegalStateException" type="java.lang.IllegalStateException"/>
- <doc>
- <![CDATA[Set the user-specified job name.
-
- @param name the job's new name.
- @throws IllegalStateException if the job is submitted]]>
- </doc>
- </method>
- <method name="setSpeculativeExecution"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="speculativeExecution" type="boolean"/>
- <doc>
- <![CDATA[Turn speculative execution on or off for this job.
-
- @param speculativeExecution <code>true</code> if speculative execution
- should be turned on, else <code>false</code>.]]>
- </doc>
- </method>
- <method name="setMapSpeculativeExecution"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="speculativeExecution" type="boolean"/>
- <doc>
- <![CDATA[Turn speculative execution on or off for this job for map tasks.
-
- @param speculativeExecution <code>true</code> if speculative execution
- should be turned on for map tasks,
- else <code>false</code>.]]>
- </doc>
- </method>
- <method name="setReduceSpeculativeExecution"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="speculativeExecution" type="boolean"/>
- <doc>
- <![CDATA[Turn speculative execution on or off for this job for reduce tasks.
-
- @param speculativeExecution <code>true</code> if speculative execution
- should be turned on for reduce tasks,
- else <code>false</code>.]]>
- </doc>
- </method>
- <method name="setJobSetupCleanupNeeded"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="needed" type="boolean"/>
- <doc>
- <![CDATA[Specify whether job-setup and job-cleanup is needed for the job
-
- @param needed If <code>true</code>, job-setup and job-cleanup will be
- considered from {@link OutputCommitter}
- else ignored.]]>
- </doc>
- </method>
- <method name="setCacheArchives"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="archives" type="java.net.URI[]"/>
- <doc>
- <![CDATA[Set the given set of archives
- @param archives The list of archives that need to be localized]]>
- </doc>
- </method>
- <method name="setCacheFiles"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="files" type="java.net.URI[]"/>
- <doc>
- <![CDATA[Set the given set of files
- @param files The list of files that need to be localized]]>
- </doc>
- </method>
- <method name="addCacheArchive"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="uri" type="java.net.URI"/>
- <doc>
- <![CDATA[Add a archives to be localized
- @param uri The uri of the cache to be localized]]>
- </doc>
- </method>
- <method name="addCacheFile"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="uri" type="java.net.URI"/>
- <doc>
- <![CDATA[Add a file to be localized
- @param uri The uri of the cache to be localized]]>
- </doc>
- </method>
- <method name="addFileToClassPath"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="file" type="org.apache.hadoop.fs.Path"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Add an file path to the current set of classpath entries It adds the file
- to cache as well.
-
- Files added with this method will not be unpacked while being added to the
- classpath.
- To add archives to classpath, use the {@link #addArchiveToClassPath(Path)}
- method instead.
- @param file Path of the file to be added]]>
- </doc>
- </method>
- <method name="addArchiveToClassPath"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="archive" type="org.apache.hadoop.fs.Path"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Add an archive path to the current set of classpath entries. It adds the
- archive to cache as well.
-
- Archive files will be unpacked and added to the classpath
- when being distributed.
- @param archive Path of the archive to be added]]>
- </doc>
- </method>
- <method name="createSymlink"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[This method allows you to create symlinks in the current working directory
- of the task to all the cache files/archives]]>
- </doc>
- </method>
- <method name="setMaxMapAttempts"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="n" type="int"/>
- <doc>
- <![CDATA[Expert: Set the number of maximum attempts that will be made to run a
- map task.
-
- @param n the number of attempts per map task.]]>
- </doc>
- </method>
- <method name="setMaxReduceAttempts"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="n" type="int"/>
- <doc>
- <![CDATA[Expert: Set the number of maximum attempts that will be made to run a
- reduce task.
-
- @param n the number of attempts per reduce task.]]>
- </doc>
- </method>
- <method name="setProfileEnabled"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="newValue" type="boolean"/>
- <doc>
- <![CDATA[Set whether the system should collect profiler information for some of
- the tasks in this job? The information is stored in the user log
- directory.
- @param newValue true means it should be gathered]]>
- </doc>
- </method>
- <method name="setProfileParams"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="value" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the profiler configuration arguments. If the string contains a '%s' it
- will be replaced with the name of the profiling output file when the task
- runs.
- This value is passed to the task child JVM on the command line.
- @param value the configuration string]]>
- </doc>
- </method>
- <method name="setProfileTaskRange"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="isMap" type="boolean"/>
- <param name="newValue" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the ranges of maps or reduces to profile. setProfileEnabled(true)
- must also be called.
- @param newValue a set of integer ranges of the map ids]]>
- </doc>
- </method>
- <method name="setCancelDelegationTokenUponJobCompletion"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="value" type="boolean"/>
- <doc>
- <![CDATA[Sets the flag that will allow the JobTracker to cancel the HDFS delegation
- tokens upon job completion. Defaults to true.]]>
- </doc>
- </method>
- <method name="submit"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <exception name="ClassNotFoundException" type="java.lang.ClassNotFoundException"/>
- <doc>
- <![CDATA[Submit the job to the cluster and return immediately.
- @throws IOException]]>
- </doc>
- </method>
- <method name="waitForCompletion" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="verbose" type="boolean"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <exception name="ClassNotFoundException" type="java.lang.ClassNotFoundException"/>
- <doc>
- <![CDATA[Submit the job to the cluster and wait for it to finish.
- @param verbose print the progress to the user
- @return true if the job succeeded
- @throws IOException thrown if the communication with the
- <code>JobTracker</code> is lost]]>
- </doc>
- </method>
- <method name="monitorAndPrintJob" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Monitor a job and print status in real-time as progress is made and tasks
- fail.
- @return true if the job succeeded
- @throws IOException if communication to the JobTracker fails]]>
- </doc>
- </method>
- <method name="getProgressPollInterval" return="int"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <doc>
- <![CDATA[The interval at which monitorAndPrintJob() prints status]]>
- </doc>
- </method>
- <method name="getCompletionPollInterval" return="int"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <doc>
- <![CDATA[The interval at which waitForCompletion() should check.]]>
- </doc>
- </method>
- <method name="getTaskOutputFilter" return="org.apache.hadoop.mapreduce.Job.TaskStatusFilter"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <doc>
- <![CDATA[Get the task output filter.
-
- @param conf the configuration.
- @return the filter level.]]>
- </doc>
- </method>
- <method name="setTaskOutputFilter"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <param name="newValue" type="org.apache.hadoop.mapreduce.Job.TaskStatusFilter"/>
- <doc>
- <![CDATA[Modify the Configuration to set the task output filter.
-
- @param conf the Configuration to modify.
- @param newValue the value to set.]]>
- </doc>
- </method>
- <field name="OUTPUT_FILTER" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="COMPLETION_POLL_INTERVAL_KEY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Key in mapred-*.xml that sets completionPollInvervalMillis]]>
- </doc>
- </field>
- <field name="PROGRESS_MONITOR_POLL_INTERVAL_KEY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Key in mapred-*.xml that sets progMonitorPollIntervalMillis]]>
- </doc>
- </field>
- <field name="USED_GENERIC_PARSER" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="SUBMIT_REPLICATION" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[The job submitter's view of the Job.
-
- <p>It allows the user to configure the
- job, submit it, control its execution, and query the state. The set methods
- only work until the job is submitted, afterwards they will throw an
- IllegalStateException. </p>
-
- <p>
- Normally the user creates the application, describes various facets of the
- job via {@link Job} and then submits the job and monitor its progress.</p>
-
- <p>Here is an example on how to submit a job:</p>
- <p><blockquote><pre>
- // Create a new Job
- Job job = new Job(new Configuration());
- job.setJarByClass(MyJob.class);
-
- // Specify various job-specific parameters
- job.setJobName("myjob");
-
- job.setInputPath(new Path("in"));
- job.setOutputPath(new Path("out"));
-
- job.setMapperClass(MyJob.MyMapper.class);
- job.setReducerClass(MyJob.MyReducer.class);
- // Submit the job, then poll for progress until the job is complete
- job.waitForCompletion(true);
- </pre></blockquote></p>]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.Job -->
- <!-- start class org.apache.hadoop.mapreduce.Job.JobState -->
- <class name="Job.JobState" extends="java.lang.Enum"
- abstract="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <method name="values" return="org.apache.hadoop.mapreduce.Job.JobState[]"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="valueOf" return="org.apache.hadoop.mapreduce.Job.JobState"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- </method>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.Job.JobState -->
- <!-- start class org.apache.hadoop.mapreduce.Job.TaskStatusFilter -->
- <class name="Job.TaskStatusFilter" extends="java.lang.Enum"
- abstract="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <method name="values" return="org.apache.hadoop.mapreduce.Job.TaskStatusFilter[]"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="valueOf" return="org.apache.hadoop.mapreduce.Job.TaskStatusFilter"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- </method>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.Job.TaskStatusFilter -->
- <!-- start interface org.apache.hadoop.mapreduce.JobContext -->
- <interface name="JobContext" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.MRJobConfig"/>
- <method name="getConfiguration" return="org.apache.hadoop.conf.Configuration"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Return the configuration for the job.
- @return the shared configuration object]]>
- </doc>
- </method>
- <method name="getCredentials" return="org.apache.hadoop.security.Credentials"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get credentials for the job.
- @return credentials for the job]]>
- </doc>
- </method>
- <method name="getJobID" return="org.apache.hadoop.mapreduce.JobID"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the unique ID for the job.
- @return the object with the job id]]>
- </doc>
- </method>
- <method name="getNumReduceTasks" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get configured the number of reduce tasks for this job. Defaults to
- <code>1</code>.
- @return the number of reduce tasks for this job.]]>
- </doc>
- </method>
- <method name="getWorkingDirectory" return="org.apache.hadoop.fs.Path"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get the current working directory for the default file system.
-
- @return the directory name.]]>
- </doc>
- </method>
- <method name="getOutputKeyClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the key class for the job output data.
- @return the key class for the job output data.]]>
- </doc>
- </method>
- <method name="getOutputValueClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the value class for job outputs.
- @return the value class for job outputs.]]>
- </doc>
- </method>
- <method name="getMapOutputKeyClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the key class for the map output data. If it is not set, use the
- (final) output key class. This allows the map output key class to be
- different than the final output key class.
- @return the map output key class.]]>
- </doc>
- </method>
- <method name="getMapOutputValueClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the value class for the map output data. If it is not set, use the
- (final) output value class This allows the map output value class to be
- different than the final output value class.
-
- @return the map output value class.]]>
- </doc>
- </method>
- <method name="getJobName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the user-specified job name. This is only used to identify the
- job to the user.
-
- @return the job's name, defaulting to "".]]>
- </doc>
- </method>
- <method name="getInputFormatClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="ClassNotFoundException" type="java.lang.ClassNotFoundException"/>
- <doc>
- <![CDATA[Get the {@link InputFormat} class for the job.
-
- @return the {@link InputFormat} class for the job.]]>
- </doc>
- </method>
- <method name="getMapperClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="ClassNotFoundException" type="java.lang.ClassNotFoundException"/>
- <doc>
- <![CDATA[Get the {@link Mapper} class for the job.
-
- @return the {@link Mapper} class for the job.]]>
- </doc>
- </method>
- <method name="getCombinerClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="ClassNotFoundException" type="java.lang.ClassNotFoundException"/>
- <doc>
- <![CDATA[Get the combiner class for the job.
-
- @return the combiner class for the job.]]>
- </doc>
- </method>
- <method name="getReducerClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="ClassNotFoundException" type="java.lang.ClassNotFoundException"/>
- <doc>
- <![CDATA[Get the {@link Reducer} class for the job.
-
- @return the {@link Reducer} class for the job.]]>
- </doc>
- </method>
- <method name="getOutputFormatClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="ClassNotFoundException" type="java.lang.ClassNotFoundException"/>
- <doc>
- <![CDATA[Get the {@link OutputFormat} class for the job.
-
- @return the {@link OutputFormat} class for the job.]]>
- </doc>
- </method>
- <method name="getPartitionerClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="ClassNotFoundException" type="java.lang.ClassNotFoundException"/>
- <doc>
- <![CDATA[Get the {@link Partitioner} class for the job.
-
- @return the {@link Partitioner} class for the job.]]>
- </doc>
- </method>
- <method name="getSortComparator" return="org.apache.hadoop.io.RawComparator"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the {@link RawComparator} comparator used to compare keys.
-
- @return the {@link RawComparator} comparator used to compare keys.]]>
- </doc>
- </method>
- <method name="getJar" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the pathname of the job's jar.
- @return the pathname]]>
- </doc>
- </method>
- <method name="getGroupingComparator" return="org.apache.hadoop.io.RawComparator"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the user defined {@link RawComparator} comparator for
- grouping keys of inputs to the reduce.
-
- @return comparator set by the user for grouping values.
- @see Job#setGroupingComparatorClass(Class) for details.]]>
- </doc>
- </method>
- <method name="getJobSetupCleanupNeeded" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get whether job-setup and job-cleanup is needed for the job
-
- @return boolean]]>
- </doc>
- </method>
- <method name="getProfileEnabled" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get whether the task profiling is enabled.
- @return true if some tasks will be profiled]]>
- </doc>
- </method>
- <method name="getProfileParams" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the profiler configuration arguments.
- The default value for this property is
- "-agentlib:hprof=cpu=samples,heap=sites,force=n,thread=y,verbose=n,file=%s"
-
- @return the parameters to pass to the task child to configure profiling]]>
- </doc>
- </method>
- <method name="getProfileTaskRange" return="org.apache.hadoop.conf.Configuration.IntegerRanges"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="isMap" type="boolean"/>
- <doc>
- <![CDATA[Get the range of maps or reduces to profile.
- @param isMap is the task a map?
- @return the task ranges]]>
- </doc>
- </method>
- <method name="getUser" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the reported username for this job.
-
- @return the username]]>
- </doc>
- </method>
- <method name="getSymlink" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[This method checks to see if symlinks are to be create for the
- localized cache files in the current working directory
- @return true if symlinks are to be created- else return false]]>
- </doc>
- </method>
- <method name="getArchiveClassPaths" return="org.apache.hadoop.fs.Path[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the archive entries in classpath as an array of Path]]>
- </doc>
- </method>
- <method name="getCacheArchives" return="java.net.URI[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get cache archives set in the Configuration
- @return A URI array of the caches set in the Configuration
- @throws IOException]]>
- </doc>
- </method>
- <method name="getCacheFiles" return="java.net.URI[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get cache files set in the Configuration
- @return A URI array of the files set in the Configuration
- @throws IOException]]>
- </doc>
- </method>
- <method name="getLocalCacheArchives" return="org.apache.hadoop.fs.Path[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Return the path array of the localized caches
- @return A path array of localized caches
- @throws IOException]]>
- </doc>
- </method>
- <method name="getLocalCacheFiles" return="org.apache.hadoop.fs.Path[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Return the path array of the localized files
- @return A path array of localized files
- @throws IOException]]>
- </doc>
- </method>
- <method name="getFileClassPaths" return="org.apache.hadoop.fs.Path[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the file entries in classpath as an array of Path]]>
- </doc>
- </method>
- <method name="getArchiveTimestamps" return="java.lang.String[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the timestamps of the archives. Used by internal
- DistributedCache and MapReduce code.
- @return a string array of timestamps
- @throws IOException]]>
- </doc>
- </method>
- <method name="getFileTimestamps" return="java.lang.String[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the timestamps of the files. Used by internal
- DistributedCache and MapReduce code.
- @return a string array of timestamps
- @throws IOException]]>
- </doc>
- </method>
- <method name="getMaxMapAttempts" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the configured number of maximum attempts that will be made to run a
- map task, as specified by the <code>mapred.map.max.attempts</code>
- property. If this property is not already set, the default is 4 attempts.
-
- @return the max number of attempts per map task.]]>
- </doc>
- </method>
- <method name="getMaxReduceAttempts" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the configured number of maximum attempts that will be made to run a
- reduce task, as specified by the <code>mapred.reduce.max.attempts</code>
- property. If this property is not already set, the default is 4 attempts.
-
- @return the max number of attempts per reduce task.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[A read-only view of the job that is provided to the tasks while they
- are running.]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapreduce.JobContext -->
- <!-- start class org.apache.hadoop.mapreduce.JobCounter -->
- <class name="JobCounter" extends="java.lang.Enum"
- abstract="false"
- static="false" final="true" visibility="public"
- deprecated="not deprecated">
- <method name="values" return="org.apache.hadoop.mapreduce.JobCounter[]"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="valueOf" return="org.apache.hadoop.mapreduce.JobCounter"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- </method>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.JobCounter -->
- <!-- start class org.apache.hadoop.mapreduce.JobID -->
- <class name="JobID" extends="org.apache.hadoop.mapred.ID"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="java.lang.Comparable"/>
- <constructor name="JobID" type="java.lang.String, int"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Constructs a JobID object
- @param jtIdentifier jobTracker identifier
- @param id job number]]>
- </doc>
- </constructor>
- <constructor name="JobID"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getJtIdentifier" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="equals" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="o" type="java.lang.Object"/>
- </method>
- <method name="compareTo" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="o" type="org.apache.hadoop.mapreduce.ID"/>
- <doc>
- <![CDATA[Compare JobIds by first jtIdentifiers, then by job numbers]]>
- </doc>
- </method>
- <method name="appendTo" return="java.lang.StringBuilder"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="builder" type="java.lang.StringBuilder"/>
- <doc>
- <![CDATA[Add the stuff after the "job" prefix to the given builder. This is useful,
- because the sub-ids use this substring at the start of their string.
- @param builder the builder to append to
- @return the builder that was passed in]]>
- </doc>
- </method>
- <method name="hashCode" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="toString" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="readFields"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="in" type="java.io.DataInput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="out" type="java.io.DataOutput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="forName" return="org.apache.hadoop.mapreduce.JobID"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="str" type="java.lang.String"/>
- <exception name="IllegalArgumentException" type="java.lang.IllegalArgumentException"/>
- <doc>
- <![CDATA[Construct a JobId object from given string
- @return constructed JobId object or null if the given String is null
- @throws IllegalArgumentException if the given string is malformed]]>
- </doc>
- </method>
- <field name="JOB" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="JOBID_REGEX" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="idFormat" type="java.text.NumberFormat"
- transient="false" volatile="false"
- static="true" final="true" visibility="protected"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[JobID represents the immutable and unique identifier for
- the job. JobID consists of two parts. First part
- represents the jobtracker identifier, so that jobID to jobtracker map
- is defined. For cluster setup this string is the jobtracker
- start time, for local setting, it is "local".
- Second part of the JobID is the job number. <br>
- An example JobID is :
- <code>job_200707121733_0003</code> , which represents the third job
- running at the jobtracker started at <code>200707121733</code>.
- <p>
- Applications should never construct or parse JobID strings, but rather
- use appropriate constructors or {@link #forName(String)} method.
-
- @see TaskID
- @see TaskAttemptID
- @see org.apache.hadoop.mapred.JobTracker#getNewJobId()
- @see org.apache.hadoop.mapred.JobTracker#getStartTime()]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.JobID -->
- <!-- start class org.apache.hadoop.mapreduce.JobPriority -->
- <class name="JobPriority" extends="java.lang.Enum"
- abstract="false"
- static="false" final="true" visibility="public"
- deprecated="not deprecated">
- <method name="values" return="org.apache.hadoop.mapreduce.JobPriority[]"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="valueOf" return="org.apache.hadoop.mapreduce.JobPriority"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- </method>
- <doc>
- <![CDATA[Used to describe the priority of the running job.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.JobPriority -->
- <!-- start class org.apache.hadoop.mapreduce.JobStatus -->
- <class name="JobStatus" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.io.Writable"/>
- <implements name="java.lang.Cloneable"/>
- <constructor name="JobStatus"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <constructor name="JobStatus" type="org.apache.hadoop.mapreduce.JobID, float, float, float, float, org.apache.hadoop.mapreduce.JobStatus.State, org.apache.hadoop.mapreduce.JobPriority, java.lang.String, java.lang.String, java.lang.String, java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Create a job status object for a given jobid.
- @param jobid The jobid of the job
- @param setupProgress The progress made on the setup
- @param mapProgress The progress made on the maps
- @param reduceProgress The progress made on the reduces
- @param cleanupProgress The progress made on the cleanup
- @param runState The current state of the job
- @param jp Priority of the job.
- @param user userid of the person who submitted the job.
- @param jobName user-specified job name.
- @param jobFile job configuration file.
- @param trackingUrl link to the web-ui for details of the job.]]>
- </doc>
- </constructor>
- <method name="setMapProgress"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="p" type="float"/>
- <doc>
- <![CDATA[Sets the map progress of this job
- @param p The value of map progress to set to]]>
- </doc>
- </method>
- <method name="setCleanupProgress"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="p" type="float"/>
- <doc>
- <![CDATA[Sets the cleanup progress of this job
- @param p The value of cleanup progress to set to]]>
- </doc>
- </method>
- <method name="setSetupProgress"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="p" type="float"/>
- <doc>
- <![CDATA[Sets the setup progress of this job
- @param p The value of setup progress to set to]]>
- </doc>
- </method>
- <method name="setReduceProgress"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="p" type="float"/>
- <doc>
- <![CDATA[Sets the reduce progress of this Job
- @param p The value of reduce progress to set to]]>
- </doc>
- </method>
- <method name="setPriority"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="jp" type="org.apache.hadoop.mapreduce.JobPriority"/>
- <doc>
- <![CDATA[Set the priority of the job, defaulting to NORMAL.
- @param jp new job priority]]>
- </doc>
- </method>
- <method name="setFinishTime"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="finishTime" type="long"/>
- <doc>
- <![CDATA[Set the finish time of the job
- @param finishTime The finishTime of the job]]>
- </doc>
- </method>
- <method name="setHistoryFile"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="historyFile" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the job history file url for a completed job]]>
- </doc>
- </method>
- <method name="setTrackingUrl"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="trackingUrl" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the link to the web-ui for details of the job.]]>
- </doc>
- </method>
- <method name="setRetired"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Set the job retire flag to true.]]>
- </doc>
- </method>
- <method name="setState"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="state" type="org.apache.hadoop.mapreduce.JobStatus.State"/>
- <doc>
- <![CDATA[Change the current run state of the job.]]>
- </doc>
- </method>
- <method name="setStartTime"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="startTime" type="long"/>
- <doc>
- <![CDATA[Set the start time of the job
- @param startTime The startTime of the job]]>
- </doc>
- </method>
- <method name="setUsername"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="userName" type="java.lang.String"/>
- <doc>
- <![CDATA[@param userName The username of the job]]>
- </doc>
- </method>
- <method name="setSchedulingInfo"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="schedulingInfo" type="java.lang.String"/>
- <doc>
- <![CDATA[Used to set the scheduling information associated to a particular Job.
-
- @param schedulingInfo Scheduling information of the job]]>
- </doc>
- </method>
- <method name="setJobACLs"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="acls" type="java.util.Map"/>
- <doc>
- <![CDATA[Set the job acls.
-
- @param acls {@link Map} from {@link JobACL} to {@link AccessControlList}]]>
- </doc>
- </method>
- <method name="getMapProgress" return="float"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return Percentage of progress in maps]]>
- </doc>
- </method>
- <method name="getCleanupProgress" return="float"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return Percentage of progress in cleanup]]>
- </doc>
- </method>
- <method name="getSetupProgress" return="float"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return Percentage of progress in setup]]>
- </doc>
- </method>
- <method name="getReduceProgress" return="float"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return Percentage of progress in reduce]]>
- </doc>
- </method>
- <method name="getState" return="org.apache.hadoop.mapreduce.JobStatus.State"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return running state of the job]]>
- </doc>
- </method>
- <method name="getStartTime" return="long"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return start time of the job]]>
- </doc>
- </method>
- <method name="clone" return="java.lang.Object"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getJobID" return="org.apache.hadoop.mapreduce.JobID"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return The jobid of the Job]]>
- </doc>
- </method>
- <method name="getUsername" return="java.lang.String"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the username of the job]]>
- </doc>
- </method>
- <method name="getSchedulingInfo" return="java.lang.String"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Gets the Scheduling information associated to a particular Job.
- @return the scheduling information of the job]]>
- </doc>
- </method>
- <method name="getJobACLs" return="java.util.Map"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the job acls.
-
- @return a {@link Map} from {@link JobACL} to {@link AccessControlList}]]>
- </doc>
- </method>
- <method name="getPriority" return="org.apache.hadoop.mapreduce.JobPriority"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Return the priority of the job
- @return job priority]]>
- </doc>
- </method>
- <method name="isJobComplete" return="boolean"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns true if the status is for a completed job.]]>
- </doc>
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="out" type="java.io.DataOutput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="readFields"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="in" type="java.io.DataInput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getJobName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the user-specified job name.]]>
- </doc>
- </method>
- <method name="getJobFile" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the configuration file for the job.]]>
- </doc>
- </method>
- <method name="getTrackingUrl" return="java.lang.String"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the link to the web-ui for details of the job.]]>
- </doc>
- </method>
- <method name="getFinishTime" return="long"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the finish time of the job.]]>
- </doc>
- </method>
- <method name="isRetired" return="boolean"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Check whether the job has retired.]]>
- </doc>
- </method>
- <method name="getHistoryFile" return="java.lang.String"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the job history file name for a completed job. If job is not
- completed or history file not available then return null.]]>
- </doc>
- </method>
- <method name="toString" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <doc>
- <![CDATA[Describes the current status of a job.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.JobStatus -->
- <!-- start class org.apache.hadoop.mapreduce.JobStatus.State -->
- <class name="JobStatus.State" extends="java.lang.Enum"
- abstract="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <method name="values" return="org.apache.hadoop.mapreduce.JobStatus.State[]"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="valueOf" return="org.apache.hadoop.mapreduce.JobStatus.State"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- </method>
- <method name="getValue" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <doc>
- <![CDATA[Current state of the job]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.JobStatus.State -->
- <!-- start interface org.apache.hadoop.mapreduce.MapContext -->
- <interface name="MapContext" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.TaskInputOutputContext"/>
- <method name="getInputSplit" return="org.apache.hadoop.mapreduce.InputSplit"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the input split for this map.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[The context that is given to the {@link Mapper}.
- @param <KEYIN> the key input type to the Mapper
- @param <VALUEIN> the value input type to the Mapper
- @param <KEYOUT> the key output type from the Mapper
- @param <VALUEOUT> the value output type from the Mapper]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapreduce.MapContext -->
- <!-- start class org.apache.hadoop.mapreduce.Mapper -->
- <class name="Mapper" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="Mapper"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setup"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.Mapper.Context"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Called once at the beginning of the task.]]>
- </doc>
- </method>
- <method name="map"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="key" type="KEYIN"/>
- <param name="value" type="VALUEIN"/>
- <param name="context" type="org.apache.hadoop.mapreduce.Mapper.Context"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Called once for each key/value pair in the input split. Most applications
- should override this, but the default is the identity function.]]>
- </doc>
- </method>
- <method name="cleanup"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.Mapper.Context"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Called once at the end of the task.]]>
- </doc>
- </method>
- <method name="run"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.Mapper.Context"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Expert users can override this method for more complete control over the
- execution of the Mapper.
- @param context
- @throws IOException]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Maps input key/value pairs to a set of intermediate key/value pairs.
-
- <p>Maps are the individual tasks which transform input records into a
- intermediate records. The transformed intermediate records need not be of
- the same type as the input records. A given input pair may map to zero or
- many output pairs.</p>
-
- <p>The Hadoop Map-Reduce framework spawns one map task for each
- {@link InputSplit} generated by the {@link InputFormat} for the job.
- <code>Mapper</code> implementations can access the {@link Configuration} for
- the job via the {@link JobContext#getConfiguration()}.
-
- <p>The framework first calls
- {@link #setup(org.apache.hadoop.mapreduce.Mapper.Context)}, followed by
- {@link #map(Object, Object, Context)}
- for each key/value pair in the <code>InputSplit</code>. Finally
- {@link #cleanup(Context)} is called.</p>
-
- <p>All intermediate values associated with a given output key are
- subsequently grouped by the framework, and passed to a {@link Reducer} to
- determine the final output. Users can control the sorting and grouping by
- specifying two key {@link RawComparator} classes.</p>
- <p>The <code>Mapper</code> outputs are partitioned per
- <code>Reducer</code>. Users can control which keys (and hence records) go to
- which <code>Reducer</code> by implementing a custom {@link Partitioner}.
-
- <p>Users can optionally specify a <code>combiner</code>, via
- {@link Job#setCombinerClass(Class)}, to perform local aggregation of the
- intermediate outputs, which helps to cut down the amount of data transferred
- from the <code>Mapper</code> to the <code>Reducer</code>.
-
- <p>Applications can specify if and how the intermediate
- outputs are to be compressed and which {@link CompressionCodec}s are to be
- used via the <code>Configuration</code>.</p>
-
- <p>If the job has zero
- reduces then the output of the <code>Mapper</code> is directly written
- to the {@link OutputFormat} without sorting by keys.</p>
-
- <p>Example:</p>
- <p><blockquote><pre>
- public class TokenCounterMapper
- extends Mapper<Object, Text, Text, IntWritable>{
-
- private final static IntWritable one = new IntWritable(1);
- private Text word = new Text();
-
- public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
- StringTokenizer itr = new StringTokenizer(value.toString());
- while (itr.hasMoreTokens()) {
- word.set(itr.nextToken());
- context.write(word, one);
- }
- }
- }
- </pre></blockquote></p>
- <p>Applications may override the {@link #run(Context)} method to exert
- greater control on map processing e.g. multi-threaded <code>Mapper</code>s
- etc.</p>
-
- @see InputFormat
- @see JobContext
- @see Partitioner
- @see Reducer]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.Mapper -->
- <!-- start class org.apache.hadoop.mapreduce.Mapper.Context -->
- <class name="Mapper.Context" extends="java.lang.Object"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.MapContext"/>
- <constructor name="Mapper.Context"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <doc>
- <![CDATA[The <code>Context</code> passed on to the {@link Mapper} implementations.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.Mapper.Context -->
- <!-- start class org.apache.hadoop.mapreduce.MarkableIterator -->
- <class name="MarkableIterator" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.MarkableIteratorInterface"/>
- <constructor name="MarkableIterator" type="java.util.Iterator"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Create a new iterator layered on the input iterator
- @param itr underlying iterator that implements MarkableIteratorInterface]]>
- </doc>
- </constructor>
- <method name="mark"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="reset"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="clearMark"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="hasNext" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="next" return="VALUE"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="remove"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <doc>
- <![CDATA[<code>MarkableIterator</code> is a wrapper iterator class that
- implements the {@link MarkableIteratorInterface}.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.MarkableIterator -->
- <!-- start class org.apache.hadoop.mapreduce.OutputCommitter -->
- <class name="OutputCommitter" extends="java.lang.Object"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="OutputCommitter"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setupJob"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobContext" type="org.apache.hadoop.mapreduce.JobContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[For the framework to setup the job output during initialization
-
- @param jobContext Context of the job whose output is being written.
- @throws IOException if temporary output could not be created]]>
- </doc>
- </method>
- <method name="cleanupJob"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link #commitJob(JobContext)} or
- {@link #abortJob(JobContext, JobStatus.State)} instead.">
- <param name="jobContext" type="org.apache.hadoop.mapreduce.JobContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[For cleaning up the job's output after job completion
-
- @param jobContext Context of the job whose output is being written.
- @throws IOException
- @deprecated Use {@link #commitJob(JobContext)} or
- {@link #abortJob(JobContext, JobStatus.State)} instead.]]>
- </doc>
- </method>
- <method name="commitJob"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobContext" type="org.apache.hadoop.mapreduce.JobContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[For committing job's output after successful job completion. Note that this
- is invoked for jobs with final runstate as SUCCESSFUL.
-
- @param jobContext Context of the job whose output is being written.
- @throws IOException]]>
- </doc>
- </method>
- <method name="abortJob"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobContext" type="org.apache.hadoop.mapreduce.JobContext"/>
- <param name="state" type="org.apache.hadoop.mapreduce.JobStatus.State"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[For aborting an unsuccessful job's output. Note that this is invoked for
- jobs with final runstate as {@link JobStatus.State#FAILED} or
- {@link JobStatus.State#KILLED}.
- @param jobContext Context of the job whose output is being written.
- @param state final runstate of the job
- @throws IOException]]>
- </doc>
- </method>
- <method name="setupTask"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskContext" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Sets up output for the task.
-
- @param taskContext Context of the task whose output is being written.
- @throws IOException]]>
- </doc>
- </method>
- <method name="needsTaskCommit" return="boolean"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskContext" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Check whether task needs a commit
-
- @param taskContext
- @return true/false
- @throws IOException]]>
- </doc>
- </method>
- <method name="commitTask"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskContext" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[To promote the task's temporary output to final output location
-
- The task's output is moved to the job's output directory.
-
- @param taskContext Context of the task whose output is being written.
- @throws IOException if commit is not]]>
- </doc>
- </method>
- <method name="abortTask"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskContext" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Discard the task output
-
- @param taskContext
- @throws IOException]]>
- </doc>
- </method>
- <doc>
- <![CDATA[<code>OutputCommitter</code> describes the commit of task output for a
- Map-Reduce job.
- <p>The Map-Reduce framework relies on the <code>OutputCommitter</code> of
- the job to:<p>
- <ol>
- <li>
- Setup the job during initialization. For example, create the temporary
- output directory for the job during the initialization of the job.
- </li>
- <li>
- Cleanup the job after the job completion. For example, remove the
- temporary output directory after the job completion.
- </li>
- <li>
- Setup the task temporary output.
- </li>
- <li>
- Check whether a task needs a commit. This is to avoid the commit
- procedure if a task does not need commit.
- </li>
- <li>
- Commit of the task output.
- </li>
- <li>
- Discard the task commit.
- </li>
- </ol>
-
- @see org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter
- @see JobContext
- @see TaskAttemptContext]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.OutputCommitter -->
- <!-- start class org.apache.hadoop.mapreduce.OutputFormat -->
- <class name="OutputFormat" extends="java.lang.Object"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="OutputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getRecordWriter" return="org.apache.hadoop.mapreduce.RecordWriter"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Get the {@link RecordWriter} for the given task.
- @param context the information about the current task.
- @return a {@link RecordWriter} to write the output for the job.
- @throws IOException]]>
- </doc>
- </method>
- <method name="checkOutputSpecs"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.JobContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Check for validity of the output-specification for the job.
-
- <p>This is to validate the output specification for the job when it is
- a job is submitted. Typically checks that it does not already exist,
- throwing an exception when it already exists, so that output is not
- overwritten.</p>
- @param context information about the job
- @throws IOException when output should not be attempted]]>
- </doc>
- </method>
- <method name="getOutputCommitter" return="org.apache.hadoop.mapreduce.OutputCommitter"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Get the output committer for this output format. This is responsible
- for ensuring the output is committed correctly.
- @param context the task context
- @return an output committer
- @throws IOException
- @throws InterruptedException]]>
- </doc>
- </method>
- <doc>
- <![CDATA[<code>OutputFormat</code> describes the output-specification for a
- Map-Reduce job.
- <p>The Map-Reduce framework relies on the <code>OutputFormat</code> of the
- job to:<p>
- <ol>
- <li>
- Validate the output-specification of the job. For e.g. check that the
- output directory doesn't already exist.
- <li>
- Provide the {@link RecordWriter} implementation to be used to write out
- the output files of the job. Output files are stored in a
- {@link FileSystem}.
- </li>
- </ol>
-
- @see RecordWriter]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.OutputFormat -->
- <!-- start class org.apache.hadoop.mapreduce.Partitioner -->
- <class name="Partitioner" extends="java.lang.Object"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="Partitioner"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getPartition" return="int"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="KEY"/>
- <param name="value" type="VALUE"/>
- <param name="numPartitions" type="int"/>
- <doc>
- <![CDATA[Get the partition number for a given key (hence record) given the total
- number of partitions i.e. number of reduce-tasks for the job.
-
- <p>Typically a hash function on a all or a subset of the key.</p>
- @param key the key to be partioned.
- @param value the entry value.
- @param numPartitions the total number of partitions.
- @return the partition number for the <code>key</code>.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Partitions the key space.
-
- <p><code>Partitioner</code> controls the partitioning of the keys of the
- intermediate map-outputs. The key (or a subset of the key) is used to derive
- the partition, typically by a hash function. The total number of partitions
- is the same as the number of reduce tasks for the job. Hence this controls
- which of the <code>m</code> reduce tasks the intermediate key (and hence the
- record) is sent for reduction.</p>
-
- @see Reducer]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.Partitioner -->
- <!-- start class org.apache.hadoop.mapreduce.QueueAclsInfo -->
- <class name="QueueAclsInfo" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.io.Writable"/>
- <constructor name="QueueAclsInfo"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Default constructor for QueueAclsInfo.]]>
- </doc>
- </constructor>
- <constructor name="QueueAclsInfo" type="java.lang.String, java.lang.String[]"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Construct a new QueueAclsInfo object using the queue name and the
- queue operations array
-
- @param queueName Name of the job queue
- @param operations]]>
- </doc>
- </constructor>
- <method name="getQueueName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get queue name.
-
- @return name]]>
- </doc>
- </method>
- <method name="setQueueName"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="queueName" type="java.lang.String"/>
- </method>
- <method name="getOperations" return="java.lang.String[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get opearations allowed on queue.
-
- @return array of String]]>
- </doc>
- </method>
- <method name="readFields"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="in" type="java.io.DataInput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="out" type="java.io.DataOutput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[Class to encapsulate Queue ACLs for a particular
- user.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.QueueAclsInfo -->
- <!-- start class org.apache.hadoop.mapreduce.QueueInfo -->
- <class name="QueueInfo" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.io.Writable"/>
- <constructor name="QueueInfo"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Default constructor for QueueInfo.]]>
- </doc>
- </constructor>
- <constructor name="QueueInfo" type="java.lang.String, java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Construct a new QueueInfo object using the queue name and the
- scheduling information passed.
-
- @param queueName Name of the job queue
- @param schedulingInfo Scheduling Information associated with the job
- queue]]>
- </doc>
- </constructor>
- <constructor name="QueueInfo" type="java.lang.String, java.lang.String, org.apache.hadoop.mapreduce.QueueState, org.apache.hadoop.mapreduce.JobStatus[]"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@param queueName
- @param schedulingInfo
- @param state
- @param stats]]>
- </doc>
- </constructor>
- <method name="setQueueName"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="queueName" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the queue name of the JobQueueInfo
-
- @param queueName Name of the job queue.]]>
- </doc>
- </method>
- <method name="getQueueName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the queue name from JobQueueInfo
-
- @return queue name]]>
- </doc>
- </method>
- <method name="setSchedulingInfo"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="schedulingInfo" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the scheduling information associated to particular job queue
-
- @param schedulingInfo]]>
- </doc>
- </method>
- <method name="getSchedulingInfo" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Gets the scheduling information associated to particular job queue.
- If nothing is set would return <b>"N/A"</b>
-
- @return Scheduling information associated to particular Job Queue]]>
- </doc>
- </method>
- <method name="setState"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="state" type="org.apache.hadoop.mapreduce.QueueState"/>
- <doc>
- <![CDATA[Set the state of the queue
- @param state state of the queue.]]>
- </doc>
- </method>
- <method name="getState" return="org.apache.hadoop.mapreduce.QueueState"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Return the queue state
- @return the queue state.]]>
- </doc>
- </method>
- <method name="setJobStatuses"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="stats" type="org.apache.hadoop.mapreduce.JobStatus[]"/>
- </method>
- <method name="getQueueChildren" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get immediate children.
-
- @return list of QueueInfo]]>
- </doc>
- </method>
- <method name="setQueueChildren"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="children" type="java.util.List"/>
- </method>
- <method name="getProperties" return="java.util.Properties"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get properties.
-
- @return Properties]]>
- </doc>
- </method>
- <method name="setProperties"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="props" type="java.util.Properties"/>
- </method>
- <method name="getJobStatuses" return="org.apache.hadoop.mapreduce.JobStatus[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the jobs submitted to queue
- @return list of JobStatus for the submitted jobs]]>
- </doc>
- </method>
- <method name="readFields"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="in" type="java.io.DataInput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="out" type="java.io.DataOutput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[Class that contains the information regarding the Job Queues which are
- maintained by the Hadoop Map/Reduce framework.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.QueueInfo -->
- <!-- start class org.apache.hadoop.mapreduce.QueueState -->
- <class name="QueueState" extends="java.lang.Enum"
- abstract="false"
- static="false" final="true" visibility="public"
- deprecated="not deprecated">
- <method name="values" return="org.apache.hadoop.mapreduce.QueueState[]"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="valueOf" return="org.apache.hadoop.mapreduce.QueueState"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- </method>
- <method name="getStateName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the stateName]]>
- </doc>
- </method>
- <method name="getState" return="org.apache.hadoop.mapreduce.QueueState"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="state" type="java.lang.String"/>
- </method>
- <method name="toString" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <doc>
- <![CDATA[Enum representing queue state]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.QueueState -->
- <!-- start class org.apache.hadoop.mapreduce.RecordReader -->
- <class name="RecordReader" extends="java.lang.Object"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="java.io.Closeable"/>
- <constructor name="RecordReader"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="initialize"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapreduce.InputSplit"/>
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Called once at initialization.
- @param split the split that defines the range of records to read
- @param context the information about the task
- @throws IOException
- @throws InterruptedException]]>
- </doc>
- </method>
- <method name="nextKeyValue" return="boolean"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Read the next key, value pair.
- @return true if a key/value pair was read
- @throws IOException
- @throws InterruptedException]]>
- </doc>
- </method>
- <method name="getCurrentKey" return="KEYIN"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Get the current key
- @return the current key or null if there is no current key
- @throws IOException
- @throws InterruptedException]]>
- </doc>
- </method>
- <method name="getCurrentValue" return="VALUEIN"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Get the current value.
- @return the object that was read
- @throws IOException
- @throws InterruptedException]]>
- </doc>
- </method>
- <method name="getProgress" return="float"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[The current progress of the record reader through its data.
- @return a number between 0.0 and 1.0 that is the fraction of the data read
- @throws IOException
- @throws InterruptedException]]>
- </doc>
- </method>
- <method name="close"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Close the record reader.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[The record reader breaks the data into key/value pairs for input to the
- {@link Mapper}.
- @param <KEYIN>
- @param <VALUEIN>]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.RecordReader -->
- <!-- start class org.apache.hadoop.mapreduce.RecordWriter -->
- <class name="RecordWriter" extends="java.lang.Object"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="RecordWriter"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="write"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <param name="value" type="V"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Writes a key/value pair.
- @param key the key to write.
- @param value the value to write.
- @throws IOException]]>
- </doc>
- </method>
- <method name="close"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Close this <code>RecordWriter</code> to future operations.
-
- @param context the context of the task
- @throws IOException]]>
- </doc>
- </method>
- <doc>
- <![CDATA[<code>RecordWriter</code> writes the output <key, value> pairs
- to an output file.
- <p><code>RecordWriter</code> implementations write the job outputs to the
- {@link FileSystem}.
-
- @see OutputFormat]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.RecordWriter -->
- <!-- start interface org.apache.hadoop.mapreduce.ReduceContext -->
- <interface name="ReduceContext" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.TaskInputOutputContext"/>
- <method name="nextKey" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Start processing next unique key.]]>
- </doc>
- </method>
- <method name="getValues" return="java.lang.Iterable"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Iterate through the values for the current key, reusing the same value
- object, which is stored in the context.
- @return the series of values associated with the current key. All of the
- objects returned directly and indirectly from this method are reused.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[The context passed to the {@link Reducer}.
- @param <KEYIN> the class of the input keys
- @param <VALUEIN> the class of the input values
- @param <KEYOUT> the class of the output keys
- @param <VALUEOUT> the class of the output values]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapreduce.ReduceContext -->
- <!-- start interface org.apache.hadoop.mapreduce.ReduceContext.ValueIterator -->
- <interface name="ReduceContext.ValueIterator" abstract="true"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.MarkableIteratorInterface"/>
- <method name="resetBackupStore"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[This method is called when the reducer moves from one key to
- another.
- @throws IOException]]>
- </doc>
- </method>
- <doc>
- <![CDATA[{@link Iterator} to iterate over values for a given group of records.]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapreduce.ReduceContext.ValueIterator -->
- <!-- start class org.apache.hadoop.mapreduce.Reducer -->
- <class name="Reducer" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="Reducer"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setup"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.Reducer.Context"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Called once at the start of the task.]]>
- </doc>
- </method>
- <method name="reduce"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="key" type="KEYIN"/>
- <param name="values" type="java.lang.Iterable"/>
- <param name="context" type="org.apache.hadoop.mapreduce.Reducer.Context"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[This method is called once for each key. Most applications will define
- their reduce class by overriding this method. The default implementation
- is an identity function.]]>
- </doc>
- </method>
- <method name="cleanup"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.Reducer.Context"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Called once at the end of the task.]]>
- </doc>
- </method>
- <method name="run"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.Reducer.Context"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Advanced application writers can use the
- {@link #run(org.apache.hadoop.mapreduce.Reducer.Context)} method to
- control how the reduce task works.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Reduces a set of intermediate values which share a key to a smaller set of
- values.
-
- <p><code>Reducer</code> implementations
- can access the {@link Configuration} for the job via the
- {@link JobContext#getConfiguration()} method.</p>
- <p><code>Reducer</code> has 3 primary phases:</p>
- <ol>
- <li>
-
- <h4 id="Shuffle">Shuffle</h4>
-
- <p>The <code>Reducer</code> copies the sorted output from each
- {@link Mapper} using HTTP across the network.</p>
- </li>
-
- <li>
- <h4 id="Sort">Sort</h4>
-
- <p>The framework merge sorts <code>Reducer</code> inputs by
- <code>key</code>s
- (since different <code>Mapper</code>s may have output the same key).</p>
-
- <p>The shuffle and sort phases occur simultaneously i.e. while outputs are
- being fetched they are merged.</p>
-
- <h5 id="SecondarySort">SecondarySort</h5>
-
- <p>To achieve a secondary sort on the values returned by the value
- iterator, the application should extend the key with the secondary
- key and define a grouping comparator. The keys will be sorted using the
- entire key, but will be grouped using the grouping comparator to decide
- which keys and values are sent in the same call to reduce.The grouping
- comparator is specified via
- {@link Job#setGroupingComparatorClass(Class)}. The sort order is
- controlled by
- {@link Job#setSortComparatorClass(Class)}.</p>
-
-
- For example, say that you want to find duplicate web pages and tag them
- all with the url of the "best" known example. You would set up the job
- like:
- <ul>
- <li>Map Input Key: url</li>
- <li>Map Input Value: document</li>
- <li>Map Output Key: document checksum, url pagerank</li>
- <li>Map Output Value: url</li>
- <li>Partitioner: by checksum</li>
- <li>OutputKeyComparator: by checksum and then decreasing pagerank</li>
- <li>OutputValueGroupingComparator: by checksum</li>
- </ul>
- </li>
-
- <li>
- <h4 id="Reduce">Reduce</h4>
-
- <p>In this phase the
- {@link #reduce(Object, Iterable, Context)}
- method is called for each <code><key, (collection of values)></code> in
- the sorted inputs.</p>
- <p>The output of the reduce task is typically written to a
- {@link RecordWriter} via
- {@link Context#write(Object, Object)}.</p>
- </li>
- </ol>
-
- <p>The output of the <code>Reducer</code> is <b>not re-sorted</b>.</p>
-
- <p>Example:</p>
- <p><blockquote><pre>
- public class IntSumReducer<Key> extends Reducer<Key,IntWritable,
- Key,IntWritable> {
- private IntWritable result = new IntWritable();
-
- public void reduce(Key key, Iterable<IntWritable> values,
- Context context) throws IOException, InterruptedException {
- int sum = 0;
- for (IntWritable val : values) {
- sum += val.get();
- }
- result.set(sum);
- context.write(key, result);
- }
- }
- </pre></blockquote></p>
-
- @see Mapper
- @see Partitioner]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.Reducer -->
- <!-- start class org.apache.hadoop.mapreduce.Reducer.Context -->
- <class name="Reducer.Context" extends="java.lang.Object"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.ReduceContext"/>
- <constructor name="Reducer.Context"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <doc>
- <![CDATA[The <code>Context</code> passed on to the {@link Reducer} implementations.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.Reducer.Context -->
- <!-- start interface org.apache.hadoop.mapreduce.TaskAttemptContext -->
- <interface name="TaskAttemptContext" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.JobContext"/>
- <implements name="org.apache.hadoop.util.Progressable"/>
- <method name="getTaskAttemptID" return="org.apache.hadoop.mapreduce.TaskAttemptID"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the unique name for this task attempt.]]>
- </doc>
- </method>
- <method name="setStatus"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="msg" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the current status of the task to the given string.]]>
- </doc>
- </method>
- <method name="getStatus" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the last set status message.
- @return the current status message]]>
- </doc>
- </method>
- <method name="getCounter" return="org.apache.hadoop.mapreduce.Counter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="counterName" type="java.lang.Enum"/>
- <doc>
- <![CDATA[Get the {@link Counter} for the given <code>counterName</code>.
- @param counterName counter name
- @return the <code>Counter</code> for the given <code>counterName</code>]]>
- </doc>
- </method>
- <method name="getCounter" return="org.apache.hadoop.mapreduce.Counter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="groupName" type="java.lang.String"/>
- <param name="counterName" type="java.lang.String"/>
- <doc>
- <![CDATA[Get the {@link Counter} for the given <code>groupName</code> and
- <code>counterName</code>.
- @param counterName counter name
- @return the <code>Counter</code> for the given <code>groupName</code> and
- <code>counterName</code>]]>
- </doc>
- </method>
- <doc>
- <![CDATA[The context for task attempts.]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapreduce.TaskAttemptContext -->
- <!-- start class org.apache.hadoop.mapreduce.TaskAttemptID -->
- <class name="TaskAttemptID" extends="org.apache.hadoop.mapred.ID"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="TaskAttemptID" type="org.apache.hadoop.mapreduce.TaskID, int"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Constructs a TaskAttemptID object from given {@link TaskID}.
- @param taskId TaskID that this task belongs to
- @param id the task attempt number]]>
- </doc>
- </constructor>
- <constructor name="TaskAttemptID" type="java.lang.String, int, org.apache.hadoop.mapreduce.TaskType, int, int"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Constructs a TaskId object from given parts.
- @param jtIdentifier jobTracker identifier
- @param jobId job number
- @param type the TaskType
- @param taskId taskId number
- @param id the task attempt number]]>
- </doc>
- </constructor>
- <constructor name="TaskAttemptID"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getJobID" return="org.apache.hadoop.mapreduce.JobID"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns the {@link JobID} object that this task attempt belongs to]]>
- </doc>
- </method>
- <method name="getTaskID" return="org.apache.hadoop.mapreduce.TaskID"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns the {@link TaskID} object that this task attempt belongs to]]>
- </doc>
- </method>
- <method name="getTaskType" return="org.apache.hadoop.mapreduce.TaskType"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns the TaskType of the TaskAttemptID]]>
- </doc>
- </method>
- <method name="equals" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="o" type="java.lang.Object"/>
- </method>
- <method name="appendTo" return="java.lang.StringBuilder"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="builder" type="java.lang.StringBuilder"/>
- <doc>
- <![CDATA[Add the unique string to the StringBuilder
- @param builder the builder to append ot
- @return the builder that was passed in.]]>
- </doc>
- </method>
- <method name="readFields"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="in" type="java.io.DataInput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="out" type="java.io.DataOutput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="hashCode" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="compareTo" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="o" type="org.apache.hadoop.mapreduce.ID"/>
- <doc>
- <![CDATA[Compare TaskIds by first tipIds, then by task numbers.]]>
- </doc>
- </method>
- <method name="toString" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="forName" return="org.apache.hadoop.mapreduce.TaskAttemptID"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="str" type="java.lang.String"/>
- <exception name="IllegalArgumentException" type="java.lang.IllegalArgumentException"/>
- <doc>
- <![CDATA[Construct a TaskAttemptID object from given string
- @return constructed TaskAttemptID object or null if the given String is null
- @throws IllegalArgumentException if the given string is malformed]]>
- </doc>
- </method>
- <field name="ATTEMPT" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="protected"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[TaskAttemptID represents the immutable and unique identifier for
- a task attempt. Each task attempt is one particular instance of a Map or
- Reduce Task identified by its TaskID.
-
- TaskAttemptID consists of 2 parts. First part is the
- {@link TaskID}, that this TaskAttemptID belongs to.
- Second part is the task attempt number. <br>
- An example TaskAttemptID is :
- <code>attempt_200707121733_0003_m_000005_0</code> , which represents the
- zeroth task attempt for the fifth map task in the third job
- running at the jobtracker started at <code>200707121733</code>.
- <p>
- Applications should never construct or parse TaskAttemptID strings
- , but rather use appropriate constructors or {@link #forName(String)}
- method.
-
- @see JobID
- @see TaskID]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.TaskAttemptID -->
- <!-- start class org.apache.hadoop.mapreduce.TaskCompletionEvent -->
- <class name="TaskCompletionEvent" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.io.Writable"/>
- <constructor name="TaskCompletionEvent"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Default constructor for Writable.]]>
- </doc>
- </constructor>
- <constructor name="TaskCompletionEvent" type="int, org.apache.hadoop.mapreduce.TaskAttemptID, int, boolean, org.apache.hadoop.mapreduce.TaskCompletionEvent.Status, java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Constructor. eventId should be created externally and incremented
- per event for each job.
- @param eventId event id, event id should be unique and assigned in
- incrementally, starting from 0.
- @param taskId task id
- @param status task's status
- @param taskTrackerHttp task tracker's host:port for http.]]>
- </doc>
- </constructor>
- <method name="getEventId" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns event Id.
- @return event id]]>
- </doc>
- </method>
- <method name="getTaskAttemptId" return="org.apache.hadoop.mapreduce.TaskAttemptID"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns task id.
- @return task id]]>
- </doc>
- </method>
- <method name="getStatus" return="org.apache.hadoop.mapreduce.TaskCompletionEvent.Status"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns enum Status.SUCESS or Status.FAILURE.
- @return task tracker status]]>
- </doc>
- </method>
- <method name="getTaskTrackerHttp" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[http location of the tasktracker where this task ran.
- @return http location of tasktracker user logs]]>
- </doc>
- </method>
- <method name="getTaskRunTime" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns time (in millisec) the task took to complete.]]>
- </doc>
- </method>
- <method name="setTaskRunTime"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="taskCompletionTime" type="int"/>
- <doc>
- <![CDATA[Set the task completion time
- @param taskCompletionTime time (in millisec) the task took to complete]]>
- </doc>
- </method>
- <method name="setEventId"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="eventId" type="int"/>
- <doc>
- <![CDATA[set event Id. should be assigned incrementally starting from 0.
- @param eventId]]>
- </doc>
- </method>
- <method name="setTaskAttemptId"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="taskId" type="org.apache.hadoop.mapreduce.TaskAttemptID"/>
- <doc>
- <![CDATA[Sets task id.
- @param taskId]]>
- </doc>
- </method>
- <method name="setTaskStatus"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="status" type="org.apache.hadoop.mapreduce.TaskCompletionEvent.Status"/>
- <doc>
- <![CDATA[Set task status.
- @param status]]>
- </doc>
- </method>
- <method name="setTaskTrackerHttp"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="taskTrackerHttp" type="java.lang.String"/>
- <doc>
- <![CDATA[Set task tracker http location.
- @param taskTrackerHttp]]>
- </doc>
- </method>
- <method name="toString" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="equals" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="o" type="java.lang.Object"/>
- </method>
- <method name="hashCode" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="isMapTask" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="idWithinJob" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="out" type="java.io.DataOutput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="readFields"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="in" type="java.io.DataInput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <field name="EMPTY_ARRAY" type="org.apache.hadoop.mapreduce.TaskCompletionEvent[]"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[This is used to track task completion events on
- job tracker.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.TaskCompletionEvent -->
- <!-- start class org.apache.hadoop.mapreduce.TaskCompletionEvent.Status -->
- <class name="TaskCompletionEvent.Status" extends="java.lang.Enum"
- abstract="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <method name="values" return="org.apache.hadoop.mapreduce.TaskCompletionEvent.Status[]"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="valueOf" return="org.apache.hadoop.mapreduce.TaskCompletionEvent.Status"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- </method>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.TaskCompletionEvent.Status -->
- <!-- start class org.apache.hadoop.mapreduce.TaskCounter -->
- <class name="TaskCounter" extends="java.lang.Enum"
- abstract="false"
- static="false" final="true" visibility="public"
- deprecated="not deprecated">
- <method name="values" return="org.apache.hadoop.mapreduce.TaskCounter[]"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="valueOf" return="org.apache.hadoop.mapreduce.TaskCounter"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- </method>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.TaskCounter -->
- <!-- start class org.apache.hadoop.mapreduce.TaskID -->
- <class name="TaskID" extends="org.apache.hadoop.mapred.ID"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="TaskID" type="org.apache.hadoop.mapreduce.JobID, org.apache.hadoop.mapreduce.TaskType, int"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Constructs a TaskID object from given {@link JobID}.
- @param jobId JobID that this tip belongs to
- @param type the {@link TaskType} of the task
- @param id the tip number]]>
- </doc>
- </constructor>
- <constructor name="TaskID" type="java.lang.String, int, org.apache.hadoop.mapreduce.TaskType, int"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Constructs a TaskInProgressId object from given parts.
- @param jtIdentifier jobTracker identifier
- @param jobId job number
- @param type the TaskType
- @param id the tip number]]>
- </doc>
- </constructor>
- <constructor name="TaskID"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getJobID" return="org.apache.hadoop.mapreduce.JobID"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns the {@link JobID} object that this tip belongs to]]>
- </doc>
- </method>
- <method name="getTaskType" return="org.apache.hadoop.mapreduce.TaskType"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the type of the task]]>
- </doc>
- </method>
- <method name="equals" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="o" type="java.lang.Object"/>
- </method>
- <method name="compareTo" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="o" type="org.apache.hadoop.mapreduce.ID"/>
- <doc>
- <![CDATA[Compare TaskInProgressIds by first jobIds, then by tip numbers. Reduces are
- defined as greater then maps.]]>
- </doc>
- </method>
- <method name="toString" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="appendTo" return="java.lang.StringBuilder"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="builder" type="java.lang.StringBuilder"/>
- <doc>
- <![CDATA[Add the unique string to the given builder.
- @param builder the builder to append to
- @return the builder that was passed in]]>
- </doc>
- </method>
- <method name="hashCode" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="readFields"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="in" type="java.io.DataInput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="out" type="java.io.DataOutput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="forName" return="org.apache.hadoop.mapreduce.TaskID"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="str" type="java.lang.String"/>
- <exception name="IllegalArgumentException" type="java.lang.IllegalArgumentException"/>
- <doc>
- <![CDATA[Construct a TaskID object from given string
- @return constructed TaskID object or null if the given String is null
- @throws IllegalArgumentException if the given string is malformed]]>
- </doc>
- </method>
- <method name="getRepresentingCharacter" return="char"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="type" type="org.apache.hadoop.mapreduce.TaskType"/>
- <doc>
- <![CDATA[Gets the character representing the {@link TaskType}
- @param type the TaskType
- @return the character]]>
- </doc>
- </method>
- <method name="getTaskType" return="org.apache.hadoop.mapreduce.TaskType"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="c" type="char"/>
- <doc>
- <![CDATA[Gets the {@link TaskType} corresponding to the character
- @param c the character
- @return the TaskType]]>
- </doc>
- </method>
- <method name="getAllTaskTypes" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <field name="TASK" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="idFormat" type="java.text.NumberFormat"
- transient="false" volatile="false"
- static="true" final="true" visibility="protected"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[TaskID represents the immutable and unique identifier for
- a Map or Reduce Task. Each TaskID encompasses multiple attempts made to
- execute the Map or Reduce Task, each of which are uniquely indentified by
- their TaskAttemptID.
-
- TaskID consists of 3 parts. First part is the {@link JobID}, that this
- TaskInProgress belongs to. Second part of the TaskID is either 'm' or 'r'
- representing whether the task is a map task or a reduce task.
- And the third part is the task number. <br>
- An example TaskID is :
- <code>task_200707121733_0003_m_000005</code> , which represents the
- fifth map task in the third job running at the jobtracker
- started at <code>200707121733</code>.
- <p>
- Applications should never construct or parse TaskID strings
- , but rather use appropriate constructors or {@link #forName(String)}
- method.
-
- @see JobID
- @see TaskAttemptID]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.TaskID -->
- <!-- start interface org.apache.hadoop.mapreduce.TaskInputOutputContext -->
- <interface name="TaskInputOutputContext" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <method name="nextKeyValue" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Advance to the next key, value pair, returning null if at end.
- @return the key object that was read into, or null if no more]]>
- </doc>
- </method>
- <method name="getCurrentKey" return="KEYIN"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Get the current key.
- @return the current key object or null if there isn't one
- @throws IOException
- @throws InterruptedException]]>
- </doc>
- </method>
- <method name="getCurrentValue" return="VALUEIN"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Get the current value.
- @return the value object that was read into
- @throws IOException
- @throws InterruptedException]]>
- </doc>
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="KEYOUT"/>
- <param name="value" type="VALUEOUT"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Generate an output key/value pair.]]>
- </doc>
- </method>
- <method name="getOutputCommitter" return="org.apache.hadoop.mapreduce.OutputCommitter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the {@link OutputCommitter} for the task-attempt.
- @return the <code>OutputCommitter</code> for the task-attempt]]>
- </doc>
- </method>
- <doc>
- <![CDATA[A context object that allows input and output from the task. It is only
- supplied to the {@link Mapper} or {@link Reducer}.
- @param <KEYIN> the input key type for the task
- @param <VALUEIN> the input value type for the task
- @param <KEYOUT> the output key type for the task
- @param <VALUEOUT> the output value type for the task]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapreduce.TaskInputOutputContext -->
- <!-- start class org.apache.hadoop.mapreduce.TaskTrackerInfo -->
- <class name="TaskTrackerInfo" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.io.Writable"/>
- <constructor name="TaskTrackerInfo"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <constructor name="TaskTrackerInfo" type="java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <constructor name="TaskTrackerInfo" type="java.lang.String, java.lang.String, java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getTaskTrackerName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Gets the tasktracker's name.
-
- @return tracker's name.]]>
- </doc>
- </method>
- <method name="isBlacklisted" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Whether tracker is blacklisted
- @return true if tracker is blacklisted
- false otherwise]]>
- </doc>
- </method>
- <method name="getReasonForBlacklist" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Gets the reason for which the tasktracker was blacklisted.
-
- @return reason which tracker was blacklisted]]>
- </doc>
- </method>
- <method name="getBlacklistReport" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Gets a descriptive report about why the tasktracker was blacklisted.
-
- @return report describing why the tasktracker was blacklisted.]]>
- </doc>
- </method>
- <method name="readFields"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="in" type="java.io.DataInput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="out" type="java.io.DataOutput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[Information about TaskTracker.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.TaskTrackerInfo -->
- <!-- start class org.apache.hadoop.mapreduce.TaskType -->
- <class name="TaskType" extends="java.lang.Enum"
- abstract="false"
- static="false" final="true" visibility="public"
- deprecated="not deprecated">
- <method name="values" return="org.apache.hadoop.mapreduce.TaskType[]"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="valueOf" return="org.apache.hadoop.mapreduce.TaskType"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- </method>
- <doc>
- <![CDATA[Enum for map, reduce, job-setup, job-cleanup, task-cleanup task types.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.TaskType -->
- </package>
- <package name="org.apache.hadoop.mapreduce.lib.aggregate">
- <!-- start class org.apache.hadoop.mapreduce.lib.aggregate.DoubleValueSum -->
- <class name="DoubleValueSum" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregator"/>
- <constructor name="DoubleValueSum"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[The default constructor]]>
- </doc>
- </constructor>
- <method name="addNextValue"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="val" type="java.lang.Object"/>
- <doc>
- <![CDATA[add a value to the aggregator
-
- @param val
- an object whose string representation represents a double value.]]>
- </doc>
- </method>
- <method name="addNextValue"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="val" type="double"/>
- <doc>
- <![CDATA[add a value to the aggregator
-
- @param val
- a double value.]]>
- </doc>
- </method>
- <method name="getReport" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the string representation of the aggregated value]]>
- </doc>
- </method>
- <method name="getSum" return="double"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the aggregated value]]>
- </doc>
- </method>
- <method name="reset"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[reset the aggregator]]>
- </doc>
- </method>
- <method name="getCombinerOutput" return="java.util.ArrayList"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return return an array of one element. The element is a string
- representation of the aggregated value. The return value is
- expected to be used by the a combiner.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[This class implements a value aggregator that sums up a sequence of double
- values.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.aggregate.DoubleValueSum -->
- <!-- start class org.apache.hadoop.mapreduce.lib.aggregate.LongValueMax -->
- <class name="LongValueMax" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregator"/>
- <constructor name="LongValueMax"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[the default constructor]]>
- </doc>
- </constructor>
- <method name="addNextValue"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="val" type="java.lang.Object"/>
- <doc>
- <![CDATA[add a value to the aggregator
-
- @param val
- an object whose string representation represents a long value.]]>
- </doc>
- </method>
- <method name="addNextValue"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="newVal" type="long"/>
- <doc>
- <![CDATA[add a value to the aggregator
-
- @param newVal
- a long value.]]>
- </doc>
- </method>
- <method name="getVal" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the aggregated value]]>
- </doc>
- </method>
- <method name="getReport" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the string representation of the aggregated value]]>
- </doc>
- </method>
- <method name="reset"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[reset the aggregator]]>
- </doc>
- </method>
- <method name="getCombinerOutput" return="java.util.ArrayList"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return return an array of one element. The element is a string
- representation of the aggregated value. The return value is
- expected to be used by the a combiner.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[This class implements a value aggregator that maintain the maximum of
- a sequence of long values.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.aggregate.LongValueMax -->
- <!-- start class org.apache.hadoop.mapreduce.lib.aggregate.LongValueMin -->
- <class name="LongValueMin" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregator"/>
- <constructor name="LongValueMin"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[the default constructor]]>
- </doc>
- </constructor>
- <method name="addNextValue"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="val" type="java.lang.Object"/>
- <doc>
- <![CDATA[add a value to the aggregator
-
- @param val
- an object whose string representation represents a long value.]]>
- </doc>
- </method>
- <method name="addNextValue"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="newVal" type="long"/>
- <doc>
- <![CDATA[add a value to the aggregator
-
- @param newVal
- a long value.]]>
- </doc>
- </method>
- <method name="getVal" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the aggregated value]]>
- </doc>
- </method>
- <method name="getReport" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the string representation of the aggregated value]]>
- </doc>
- </method>
- <method name="reset"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[reset the aggregator]]>
- </doc>
- </method>
- <method name="getCombinerOutput" return="java.util.ArrayList"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return return an array of one element. The element is a string
- representation of the aggregated value. The return value is
- expected to be used by the a combiner.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[This class implements a value aggregator that maintain the minimum of
- a sequence of long values.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.aggregate.LongValueMin -->
- <!-- start class org.apache.hadoop.mapreduce.lib.aggregate.LongValueSum -->
- <class name="LongValueSum" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregator"/>
- <constructor name="LongValueSum"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[the default constructor]]>
- </doc>
- </constructor>
- <method name="addNextValue"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="val" type="java.lang.Object"/>
- <doc>
- <![CDATA[add a value to the aggregator
-
- @param val
- an object whose string representation represents a long value.]]>
- </doc>
- </method>
- <method name="addNextValue"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="val" type="long"/>
- <doc>
- <![CDATA[add a value to the aggregator
-
- @param val
- a long value.]]>
- </doc>
- </method>
- <method name="getSum" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the aggregated value]]>
- </doc>
- </method>
- <method name="getReport" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the string representation of the aggregated value]]>
- </doc>
- </method>
- <method name="reset"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[reset the aggregator]]>
- </doc>
- </method>
- <method name="getCombinerOutput" return="java.util.ArrayList"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return return an array of one element. The element is a string
- representation of the aggregated value. The return value is
- expected to be used by the a combiner.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[This class implements a value aggregator that sums up
- a sequence of long values.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.aggregate.LongValueSum -->
- <!-- start class org.apache.hadoop.mapreduce.lib.aggregate.StringValueMax -->
- <class name="StringValueMax" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregator"/>
- <constructor name="StringValueMax"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[the default constructor]]>
- </doc>
- </constructor>
- <method name="addNextValue"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="val" type="java.lang.Object"/>
- <doc>
- <![CDATA[add a value to the aggregator
-
- @param val
- a string.]]>
- </doc>
- </method>
- <method name="getVal" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the aggregated value]]>
- </doc>
- </method>
- <method name="getReport" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the string representation of the aggregated value]]>
- </doc>
- </method>
- <method name="reset"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[reset the aggregator]]>
- </doc>
- </method>
- <method name="getCombinerOutput" return="java.util.ArrayList"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return return an array of one element. The element is a string
- representation of the aggregated value. The return value is
- expected to be used by the a combiner.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[This class implements a value aggregator that maintain the biggest of
- a sequence of strings.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.aggregate.StringValueMax -->
- <!-- start class org.apache.hadoop.mapreduce.lib.aggregate.StringValueMin -->
- <class name="StringValueMin" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregator"/>
- <constructor name="StringValueMin"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[the default constructor]]>
- </doc>
- </constructor>
- <method name="addNextValue"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="val" type="java.lang.Object"/>
- <doc>
- <![CDATA[add a value to the aggregator
-
- @param val
- a string.]]>
- </doc>
- </method>
- <method name="getVal" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the aggregated value]]>
- </doc>
- </method>
- <method name="getReport" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the string representation of the aggregated value]]>
- </doc>
- </method>
- <method name="reset"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[reset the aggregator]]>
- </doc>
- </method>
- <method name="getCombinerOutput" return="java.util.ArrayList"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return return an array of one element. The element is a string
- representation of the aggregated value. The return value is
- expected to be used by the a combiner.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[This class implements a value aggregator that maintain the smallest of
- a sequence of strings.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.aggregate.StringValueMin -->
- <!-- start class org.apache.hadoop.mapreduce.lib.aggregate.UniqValueCount -->
- <class name="UniqValueCount" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregator"/>
- <constructor name="UniqValueCount"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[the default constructor]]>
- </doc>
- </constructor>
- <constructor name="UniqValueCount" type="long"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[constructor
- @param maxNum the limit in the number of unique values to keep.]]>
- </doc>
- </constructor>
- <method name="setMaxItems" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="n" type="long"/>
- <doc>
- <![CDATA[Set the limit on the number of unique values
- @param n the desired limit on the number of unique values
- @return the new limit on the number of unique values]]>
- </doc>
- </method>
- <method name="addNextValue"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="val" type="java.lang.Object"/>
- <doc>
- <![CDATA[add a value to the aggregator
-
- @param val
- an object.]]>
- </doc>
- </method>
- <method name="getReport" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return return the number of unique objects aggregated]]>
- </doc>
- </method>
- <method name="getUniqueItems" return="java.util.Set"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the set of the unique objects]]>
- </doc>
- </method>
- <method name="reset"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[reset the aggregator]]>
- </doc>
- </method>
- <method name="getCombinerOutput" return="java.util.ArrayList"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return return an array of the unique objects. The return value is
- expected to be used by the a combiner.]]>
- </doc>
- </method>
- <field name="MAX_NUM_UNIQUE_VALUES" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[This class implements a value aggregator that dedupes a sequence of objects.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.aggregate.UniqValueCount -->
- <!-- start class org.apache.hadoop.mapreduce.lib.aggregate.UserDefinedValueAggregatorDescriptor -->
- <class name="UserDefinedValueAggregatorDescriptor" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorDescriptor"/>
- <constructor name="UserDefinedValueAggregatorDescriptor" type="java.lang.String, org.apache.hadoop.conf.Configuration"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@param className the class name of the user defined descriptor class
- @param conf a configure object used for decriptor configuration]]>
- </doc>
- </constructor>
- <method name="createInstance" return="java.lang.Object"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="className" type="java.lang.String"/>
- <doc>
- <![CDATA[Create an instance of the given class
- @param className the name of the class
- @return a dynamically created instance of the given class]]>
- </doc>
- </method>
- <method name="generateKeyValPairs" return="java.util.ArrayList"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="java.lang.Object"/>
- <param name="val" type="java.lang.Object"/>
- <doc>
- <![CDATA[Generate a list of aggregation-id/value pairs for the given
- key/value pairs by delegating the invocation to the real object.
-
- @param key
- input key
- @param val
- input value
- @return a list of aggregation id/value pairs. An aggregation id encodes an
- aggregation type which is used to guide the way to aggregate the
- value in the reduce/combiner phrase of an Aggregate based job.]]>
- </doc>
- </method>
- <method name="toString" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the string representation of this object.]]>
- </doc>
- </method>
- <method name="configure"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <doc>
- <![CDATA[Do nothing.]]>
- </doc>
- </method>
- <field name="theAggregatorDescriptor" type="org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorDescriptor"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[This class implements a wrapper for a user defined value
- aggregator descriptor.
- It serves two functions: One is to create an object of
- ValueAggregatorDescriptor from the name of a user defined class
- that may be dynamically loaded. The other is to
- delegate invocations of generateKeyValPairs function to the created object.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.aggregate.UserDefinedValueAggregatorDescriptor -->
- <!-- start interface org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregator -->
- <interface name="ValueAggregator" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <method name="addNextValue"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="val" type="java.lang.Object"/>
- <doc>
- <![CDATA[add a value to the aggregator
-
- @param val the value to be added]]>
- </doc>
- </method>
- <method name="reset"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[reset the aggregator]]>
- </doc>
- </method>
- <method name="getReport" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the string representation of the agregator]]>
- </doc>
- </method>
- <method name="getCombinerOutput" return="java.util.ArrayList"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return an array of values as the outputs of the combiner.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[This interface defines the minimal protocol for value aggregators.]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregator -->
- <!-- start class org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorBaseDescriptor -->
- <class name="ValueAggregatorBaseDescriptor" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorDescriptor"/>
- <constructor name="ValueAggregatorBaseDescriptor"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="generateEntry" return="java.util.Map.Entry"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="type" type="java.lang.String"/>
- <param name="id" type="java.lang.String"/>
- <param name="val" type="org.apache.hadoop.io.Text"/>
- <doc>
- <![CDATA[@param type the aggregation type
- @param id the aggregation id
- @param val the val associated with the id to be aggregated
- @return an Entry whose key is the aggregation id prefixed with
- the aggregation type.]]>
- </doc>
- </method>
- <method name="generateValueAggregator" return="org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregator"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="type" type="java.lang.String"/>
- <param name="uniqCount" type="long"/>
- <doc>
- <![CDATA[@param type the aggregation type
- @param uniqCount the limit in the number of unique values to keep,
- if type is UNIQ_VALUE_COUNT
- @return a value aggregator of the given type.]]>
- </doc>
- </method>
- <method name="generateKeyValPairs" return="java.util.ArrayList"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="java.lang.Object"/>
- <param name="val" type="java.lang.Object"/>
- <doc>
- <![CDATA[Generate 1 or 2 aggregation-id/value pairs for the given key/value pair.
- The first id will be of type LONG_VALUE_SUM, with "record_count" as
- its aggregation id. If the input is a file split,
- the second id of the same type will be generated too, with the file name
- as its aggregation id. This achieves the behavior of counting the total
- number of records in the input data, and the number of records
- in each input file.
-
- @param key
- input key
- @param val
- input value
- @return a list of aggregation id/value pairs. An aggregation id encodes an
- aggregation type which is used to guide the way to aggregate the
- value in the reduce/combiner phrase of an Aggregate based job.]]>
- </doc>
- </method>
- <method name="configure"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <doc>
- <![CDATA[get the input file name.
-
- @param conf a configuration object]]>
- </doc>
- </method>
- <field name="UNIQ_VALUE_COUNT" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="LONG_VALUE_SUM" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="DOUBLE_VALUE_SUM" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="VALUE_HISTOGRAM" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="LONG_VALUE_MAX" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="LONG_VALUE_MIN" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="STRING_VALUE_MAX" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="STRING_VALUE_MIN" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="inputFile" type="java.lang.String"
- transient="false" volatile="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[This class implements the common functionalities of
- the subclasses of ValueAggregatorDescriptor class.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorBaseDescriptor -->
- <!-- start class org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorCombiner -->
- <class name="ValueAggregatorCombiner" extends="org.apache.hadoop.mapreduce.Reducer"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="ValueAggregatorCombiner"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="reduce"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="org.apache.hadoop.io.Text"/>
- <param name="values" type="java.lang.Iterable"/>
- <param name="context" type="org.apache.hadoop.mapreduce.Reducer.Context"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Combines values for a given key.
- @param key the key is expected to be a Text object, whose prefix indicates
- the type of aggregation to aggregate the values.
- @param values the values to combine
- @param context to collect combined values]]>
- </doc>
- </method>
- <doc>
- <![CDATA[This class implements the generic combiner of Aggregate.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorCombiner -->
- <!-- start interface org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorDescriptor -->
- <interface name="ValueAggregatorDescriptor" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <method name="generateKeyValPairs" return="java.util.ArrayList"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="java.lang.Object"/>
- <param name="val" type="java.lang.Object"/>
- <doc>
- <![CDATA[Generate a list of aggregation-id/value pairs for
- the given key/value pair.
- This function is usually called by the mapper of an Aggregate based job.
-
- @param key
- input key
- @param val
- input value
- @return a list of aggregation id/value pairs. An aggregation id encodes an
- aggregation type which is used to guide the way to aggregate the
- value in the reduce/combiner phrase of an Aggregate based job.]]>
- </doc>
- </method>
- <method name="configure"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <doc>
- <![CDATA[Configure the object
-
- @param conf
- a Configuration object that may contain the information
- that can be used to configure the object.]]>
- </doc>
- </method>
- <field name="TYPE_SEPARATOR" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="ONE" type="org.apache.hadoop.io.Text"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[This interface defines the contract a value aggregator descriptor must
- support. Such a descriptor can be configured with a {@link Configuration}
- object. Its main function is to generate a list of aggregation-id/value
- pairs. An aggregation id encodes an aggregation type which is used to
- guide the way to aggregate the value in the reduce/combiner phrase of an
- Aggregate based job.
- The mapper in an Aggregate based map/reduce job may create one or more of
- ValueAggregatorDescriptor objects at configuration time. For each input
- key/value pair, the mapper will use those objects to create aggregation
- id/value pairs.]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorDescriptor -->
- <!-- start class org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorJob -->
- <class name="ValueAggregatorJob" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="ValueAggregatorJob"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="createValueAggregatorJobs" return="org.apache.hadoop.mapreduce.lib.jobcontrol.JobControl"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="args" type="java.lang.String[]"/>
- <param name="descriptors" type="java.lang.Class[]"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="createValueAggregatorJobs" return="org.apache.hadoop.mapreduce.lib.jobcontrol.JobControl"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="args" type="java.lang.String[]"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="createValueAggregatorJob" return="org.apache.hadoop.mapreduce.Job"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <param name="args" type="java.lang.String[]"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Create an Aggregate based map/reduce job.
-
- @param conf The configuration for job
- @param args the arguments used for job creation. Generic hadoop
- arguments are accepted.
- @return a Job object ready for submission.
-
- @throws IOException
- @see GenericOptionsParser]]>
- </doc>
- </method>
- <method name="createValueAggregatorJob" return="org.apache.hadoop.mapreduce.Job"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="args" type="java.lang.String[]"/>
- <param name="descriptors" type="java.lang.Class[]"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="setAggregatorDescriptors" return="org.apache.hadoop.conf.Configuration"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="descriptors" type="java.lang.Class[]"/>
- </method>
- <method name="main"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="args" type="java.lang.String[]"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <exception name="ClassNotFoundException" type="java.lang.ClassNotFoundException"/>
- <doc>
- <![CDATA[create and run an Aggregate based map/reduce job.
-
- @param args the arguments used for job creation
- @throws IOException]]>
- </doc>
- </method>
- <doc>
- <![CDATA[This is the main class for creating a map/reduce job using Aggregate
- framework. The Aggregate is a specialization of map/reduce framework,
- specializing for performing various simple aggregations.
-
- Generally speaking, in order to implement an application using Map/Reduce
- model, the developer is to implement Map and Reduce functions (and possibly
- combine function). However, a lot of applications related to counting and
- statistics computing have very similar characteristics. Aggregate abstracts
- out the general patterns of these functions and implementing those patterns.
- In particular, the package provides generic mapper/redducer/combiner
- classes, and a set of built-in value aggregators, and a generic utility
- class that helps user create map/reduce jobs using the generic class.
- The built-in aggregators include:
-
- sum over numeric values count the number of distinct values compute the
- histogram of values compute the minimum, maximum, media,average, standard
- deviation of numeric values
-
- The developer using Aggregate will need only to provide a plugin class
- conforming to the following interface:
-
- public interface ValueAggregatorDescriptor { public ArrayList<Entry>
- generateKeyValPairs(Object key, Object value); public void
- configure(Configuration conf); }
-
- The package also provides a base class, ValueAggregatorBaseDescriptor,
- implementing the above interface. The user can extend the base class and
- implement generateKeyValPairs accordingly.
-
- The primary work of generateKeyValPairs is to emit one or more key/value
- pairs based on the input key/value pair. The key in an output key/value pair
- encode two pieces of information: aggregation type and aggregation id. The
- value will be aggregated onto the aggregation id according the aggregation
- type.
-
- This class offers a function to generate a map/reduce job using Aggregate
- framework. The function takes the following parameters: input directory spec
- input format (text or sequence file) output directory a file specifying the
- user plugin class]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorJob -->
- <!-- start class org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorJobBase -->
- <class name="ValueAggregatorJobBase" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="ValueAggregatorJobBase"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setup"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.conf.Configuration"/>
- </method>
- <method name="getValueAggregatorDescriptor" return="org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorDescriptor"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="spec" type="java.lang.String"/>
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- </method>
- <method name="getAggregatorDescriptors" return="java.util.ArrayList"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- </method>
- <method name="logSpec"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="protected"
- deprecated="not deprecated">
- </method>
- <field name="DESCRIPTOR" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="DESCRIPTOR_NUM" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="USER_JAR" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="aggregatorDescriptorList" type="java.util.ArrayList"
- transient="false" volatile="false"
- static="true" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[This abstract class implements some common functionalities of the
- the generic mapper, reducer and combiner classes of Aggregate.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorJobBase -->
- <!-- start class org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorMapper -->
- <class name="ValueAggregatorMapper" extends="org.apache.hadoop.mapreduce.Mapper"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="ValueAggregatorMapper"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setup"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.Mapper.Context"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="map"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K1"/>
- <param name="value" type="V1"/>
- <param name="context" type="org.apache.hadoop.mapreduce.Mapper.Context"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[the map function. It iterates through the value aggregator descriptor
- list to generate aggregation id/value pairs and emit them.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[This class implements the generic mapper of Aggregate.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorMapper -->
- <!-- start class org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorReducer -->
- <class name="ValueAggregatorReducer" extends="org.apache.hadoop.mapreduce.Reducer"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="ValueAggregatorReducer"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setup"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.Reducer.Context"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="reduce"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="org.apache.hadoop.io.Text"/>
- <param name="values" type="java.lang.Iterable"/>
- <param name="context" type="org.apache.hadoop.mapreduce.Reducer.Context"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[@param key
- the key is expected to be a Text object, whose prefix indicates
- the type of aggregation to aggregate the values. In effect, data
- driven computing is achieved. It is assumed that each aggregator's
- getReport method emits appropriate output for the aggregator. This
- may be further customized.
- @param values the values to be aggregated
- @param context]]>
- </doc>
- </method>
- <doc>
- <![CDATA[This class implements the generic reducer of Aggregate.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorReducer -->
- <!-- start class org.apache.hadoop.mapreduce.lib.aggregate.ValueHistogram -->
- <class name="ValueHistogram" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregator"/>
- <constructor name="ValueHistogram"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="addNextValue"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="val" type="java.lang.Object"/>
- <doc>
- <![CDATA[add the given val to the aggregator.
-
- @param val the value to be added. It is expected to be a string
- in the form of xxxx\tnum, meaning xxxx has num occurrences.]]>
- </doc>
- </method>
- <method name="getReport" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the string representation of this aggregator.
- It includes the following basic statistics of the histogram:
- the number of unique values
- the minimum value
- the media value
- the maximum value
- the average value
- the standard deviation]]>
- </doc>
- </method>
- <method name="getReportDetails" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return a string representation of the list of value/frequence pairs of
- the histogram]]>
- </doc>
- </method>
- <method name="getCombinerOutput" return="java.util.ArrayList"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return a list value/frequence pairs.
- The return value is expected to be used by the reducer.]]>
- </doc>
- </method>
- <method name="getReportItems" return="java.util.TreeMap"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return a TreeMap representation of the histogram]]>
- </doc>
- </method>
- <method name="reset"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[reset the aggregator]]>
- </doc>
- </method>
- <doc>
- <![CDATA[This class implements a value aggregator that computes the
- histogram of a sequence of strings.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.aggregate.ValueHistogram -->
- </package>
- <package name="org.apache.hadoop.mapreduce.lib.chain">
- <!-- start class org.apache.hadoop.mapreduce.lib.chain.ChainMapper -->
- <class name="ChainMapper" extends="org.apache.hadoop.mapreduce.Mapper"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="ChainMapper"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="addMapper"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <param name="klass" type="java.lang.Class"/>
- <param name="inputKeyClass" type="java.lang.Class"/>
- <param name="inputValueClass" type="java.lang.Class"/>
- <param name="outputKeyClass" type="java.lang.Class"/>
- <param name="outputValueClass" type="java.lang.Class"/>
- <param name="mapperConf" type="org.apache.hadoop.conf.Configuration"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Adds a {@link Mapper} class to the chain mapper.
-
- <p>
- The key and values are passed from one element of the chain to the next, by
- value. For the added Mapper the configuration given for it,
- <code>mapperConf</code>, have precedence over the job's Configuration. This
- precedence is in effect when the task is running.
- </p>
- <p>
- IMPORTANT: There is no need to specify the output key/value classes for the
- ChainMapper, this is done by the addMapper for the last mapper in the chain
- </p>
-
- @param job
- The job.
- @param klass
- the Mapper class to add.
- @param inputKeyClass
- mapper input key class.
- @param inputValueClass
- mapper input value class.
- @param outputKeyClass
- mapper output key class.
- @param outputValueClass
- mapper output value class.
- @param mapperConf
- a configuration for the Mapper class. It is recommended to use a
- Configuration without default values using the
- <code>Configuration(boolean loadDefaults)</code> constructor with
- FALSE.]]>
- </doc>
- </method>
- <method name="setup"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.Mapper.Context"/>
- </method>
- <method name="run"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.Mapper.Context"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <doc>
- <![CDATA[The ChainMapper class allows to use multiple Mapper classes within a single
- Map task.
-
- <p>
- The Mapper classes are invoked in a chained (or piped) fashion, the output of
- the first becomes the input of the second, and so on until the last Mapper,
- the output of the last Mapper will be written to the task's output.
- </p>
- <p>
- The key functionality of this feature is that the Mappers in the chain do not
- need to be aware that they are executed in a chain. This enables having
- reusable specialized Mappers that can be combined to perform composite
- operations within a single task.
- </p>
- <p>
- Special care has to be taken when creating chains that the key/values output
- by a Mapper are valid for the following Mapper in the chain. It is assumed
- all Mappers and the Reduce in the chain use matching output and input key and
- value classes as no conversion is done by the chaining code.
- </p>
- <p>
- Using the ChainMapper and the ChainReducer classes is possible to compose
- Map/Reduce jobs that look like <code>[MAP+ / REDUCE MAP*]</code>. And
- immediate benefit of this pattern is a dramatic reduction in disk IO.
- </p>
- <p>
- IMPORTANT: There is no need to specify the output key/value classes for the
- ChainMapper, this is done by the addMapper for the last mapper in the chain.
- </p>
- ChainMapper usage pattern:
- <p/>
-
- <pre>
- ...
- Job = new Job(conf);
- <p/>
- Configuration mapAConf = new Configuration(false);
- ...
- ChainMapper.addMapper(job, AMap.class, LongWritable.class, Text.class,
- Text.class, Text.class, true, mapAConf);
- <p/>
- Configuration mapBConf = new Configuration(false);
- ...
- ChainMapper.addMapper(job, BMap.class, Text.class, Text.class,
- LongWritable.class, Text.class, false, mapBConf);
- <p/>
- ...
- <p/>
- job.waitForComplettion(true);
- ...
- </pre>]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.chain.ChainMapper -->
- <!-- start class org.apache.hadoop.mapreduce.lib.chain.ChainReducer -->
- <class name="ChainReducer" extends="org.apache.hadoop.mapreduce.Reducer"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="ChainReducer"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setReducer"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <param name="klass" type="java.lang.Class"/>
- <param name="inputKeyClass" type="java.lang.Class"/>
- <param name="inputValueClass" type="java.lang.Class"/>
- <param name="outputKeyClass" type="java.lang.Class"/>
- <param name="outputValueClass" type="java.lang.Class"/>
- <param name="reducerConf" type="org.apache.hadoop.conf.Configuration"/>
- <doc>
- <![CDATA[Sets the {@link Reducer} class to the chain job.
-
- <p>
- The key and values are passed from one element of the chain to the next, by
- value. For the added Reducer the configuration given for it,
- <code>reducerConf</code>, have precedence over the job's Configuration.
- This precedence is in effect when the task is running.
- </p>
- <p>
- IMPORTANT: There is no need to specify the output key/value classes for the
- ChainReducer, this is done by the setReducer or the addMapper for the last
- element in the chain.
- </p>
-
- @param job
- the job
- @param klass
- the Reducer class to add.
- @param inputKeyClass
- reducer input key class.
- @param inputValueClass
- reducer input value class.
- @param outputKeyClass
- reducer output key class.
- @param outputValueClass
- reducer output value class.
- @param reducerConf
- a configuration for the Reducer class. It is recommended to use a
- Configuration without default values using the
- <code>Configuration(boolean loadDefaults)</code> constructor with
- FALSE.]]>
- </doc>
- </method>
- <method name="addMapper"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <param name="klass" type="java.lang.Class"/>
- <param name="inputKeyClass" type="java.lang.Class"/>
- <param name="inputValueClass" type="java.lang.Class"/>
- <param name="outputKeyClass" type="java.lang.Class"/>
- <param name="outputValueClass" type="java.lang.Class"/>
- <param name="mapperConf" type="org.apache.hadoop.conf.Configuration"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Adds a {@link Mapper} class to the chain reducer.
-
- <p>
- The key and values are passed from one element of the chain to the next, by
- value For the added Mapper the configuration given for it,
- <code>mapperConf</code>, have precedence over the job's Configuration. This
- precedence is in effect when the task is running.
- </p>
- <p>
- IMPORTANT: There is no need to specify the output key/value classes for the
- ChainMapper, this is done by the addMapper for the last mapper in the
- chain.
- </p>
-
- @param job
- The job.
- @param klass
- the Mapper class to add.
- @param inputKeyClass
- mapper input key class.
- @param inputValueClass
- mapper input value class.
- @param outputKeyClass
- mapper output key class.
- @param outputValueClass
- mapper output value class.
- @param mapperConf
- a configuration for the Mapper class. It is recommended to use a
- Configuration without default values using the
- <code>Configuration(boolean loadDefaults)</code> constructor with
- FALSE.]]>
- </doc>
- </method>
- <method name="setup"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.Reducer.Context"/>
- </method>
- <method name="run"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.Reducer.Context"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <doc>
- <![CDATA[The ChainReducer class allows to chain multiple Mapper classes after a
- Reducer within the Reducer task.
-
- <p>
- For each record output by the Reducer, the Mapper classes are invoked in a
- chained (or piped) fashion. The output of the reducer becomes the input of
- the first mapper and output of first becomes the input of the second, and so
- on until the last Mapper, the output of the last Mapper will be written to
- the task's output.
- </p>
- <p>
- The key functionality of this feature is that the Mappers in the chain do not
- need to be aware that they are executed after the Reducer or in a chain. This
- enables having reusable specialized Mappers that can be combined to perform
- composite operations within a single task.
- </p>
- <p>
- Special care has to be taken when creating chains that the key/values output
- by a Mapper are valid for the following Mapper in the chain. It is assumed
- all Mappers and the Reduce in the chain use matching output and input key and
- value classes as no conversion is done by the chaining code.
- </p>
- </p> Using the ChainMapper and the ChainReducer classes is possible to
- compose Map/Reduce jobs that look like <code>[MAP+ / REDUCE MAP*]</code>. And
- immediate benefit of this pattern is a dramatic reduction in disk IO. </p>
- <p>
- IMPORTANT: There is no need to specify the output key/value classes for the
- ChainReducer, this is done by the setReducer or the addMapper for the last
- element in the chain.
- </p>
- ChainReducer usage pattern:
- <p/>
-
- <pre>
- ...
- Job = new Job(conf);
- ....
- <p/>
- Configuration reduceConf = new Configuration(false);
- ...
- ChainReducer.setReducer(job, XReduce.class, LongWritable.class, Text.class,
- Text.class, Text.class, true, reduceConf);
- <p/>
- ChainReducer.addMapper(job, CMap.class, Text.class, Text.class,
- LongWritable.class, Text.class, false, null);
- <p/>
- ChainReducer.addMapper(job, DMap.class, LongWritable.class, Text.class,
- LongWritable.class, LongWritable.class, true, null);
- <p/>
- ...
- <p/>
- job.waitForCompletion(true);
- ...
- </pre>]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.chain.ChainReducer -->
- </package>
- <package name="org.apache.hadoop.mapreduce.lib.db">
- <!-- start class org.apache.hadoop.mapreduce.lib.db.BigDecimalSplitter -->
- <class name="BigDecimalSplitter" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.lib.db.DBSplitter"/>
- <constructor name="BigDecimalSplitter"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="split" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <param name="results" type="java.sql.ResultSet"/>
- <param name="colName" type="java.lang.String"/>
- <exception name="SQLException" type="java.sql.SQLException"/>
- </method>
- <method name="tryDivide" return="java.math.BigDecimal"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="numerator" type="java.math.BigDecimal"/>
- <param name="denominator" type="java.math.BigDecimal"/>
- <doc>
- <![CDATA[Divide numerator by denominator. If impossible in exact mode, use rounding.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Implement DBSplitter over BigDecimal values.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.db.BigDecimalSplitter -->
- <!-- start class org.apache.hadoop.mapreduce.lib.db.BooleanSplitter -->
- <class name="BooleanSplitter" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.lib.db.DBSplitter"/>
- <constructor name="BooleanSplitter"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="split" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <param name="results" type="java.sql.ResultSet"/>
- <param name="colName" type="java.lang.String"/>
- <exception name="SQLException" type="java.sql.SQLException"/>
- </method>
- <doc>
- <![CDATA[Implement DBSplitter over boolean values.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.db.BooleanSplitter -->
- <!-- start class org.apache.hadoop.mapreduce.lib.db.DataDrivenDBInputFormat -->
- <class name="DataDrivenDBInputFormat" extends="org.apache.hadoop.mapreduce.lib.db.DBInputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.conf.Configurable"/>
- <constructor name="DataDrivenDBInputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getSplitter" return="org.apache.hadoop.mapreduce.lib.db.DBSplitter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="sqlDataType" type="int"/>
- <doc>
- <![CDATA[@return the DBSplitter implementation to use to divide the table/query into InputSplits.]]>
- </doc>
- </method>
- <method name="getSplits" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.JobContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <method name="getBoundingValsQuery" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return a query which returns the minimum and maximum values for
- the order-by column.
- The min value should be in the first column, and the
- max value should be in the second column of the results.]]>
- </doc>
- </method>
- <method name="setBoundingQuery"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <param name="query" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the user-defined bounding query to use with a user-defined query.
- This *must* include the substring "$CONDITIONS"
- (DataDrivenDBInputFormat.SUBSTITUTE_TOKEN) inside the WHERE clause,
- so that DataDrivenDBInputFormat knows where to insert split clauses.
- e.g., "SELECT foo FROM mytable WHERE $CONDITIONS"
- This will be expanded to something like:
- SELECT foo FROM mytable WHERE (id > 100) AND (id < 250)
- inside each split.]]>
- </doc>
- </method>
- <method name="createDBRecordReader" return="org.apache.hadoop.mapreduce.RecordReader"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapreduce.lib.db.DBInputFormat.DBInputSplit"/>
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="setInput"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <param name="inputClass" type="java.lang.Class"/>
- <param name="tableName" type="java.lang.String"/>
- <param name="conditions" type="java.lang.String"/>
- <param name="splitBy" type="java.lang.String"/>
- <param name="fieldNames" type="java.lang.String[]"/>
- <doc>
- <![CDATA[Note that the "orderBy" column is called the "splitBy" in this version.
- We reuse the same field, but it's not strictly ordering it -- just partitioning
- the results.]]>
- </doc>
- </method>
- <method name="setInput"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <param name="inputClass" type="java.lang.Class"/>
- <param name="inputQuery" type="java.lang.String"/>
- <param name="inputBoundingQuery" type="java.lang.String"/>
- <doc>
- <![CDATA[setInput() takes a custom query and a separate "bounding query" to use
- instead of the custom "count query" used by DBInputFormat.]]>
- </doc>
- </method>
- <field name="SUBSTITUTE_TOKEN" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[If users are providing their own query, the following string is expected to
- appear in the WHERE clause, which will be substituted with a pair of conditions
- on the input to allow input splits to parallelise the import.]]>
- </doc>
- </field>
- <doc>
- <![CDATA[A InputFormat that reads input data from an SQL table.
- Operates like DBInputFormat, but instead of using LIMIT and OFFSET to demarcate
- splits, it tries to generate WHERE clauses which separate the data into roughly
- equivalent shards.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.db.DataDrivenDBInputFormat -->
- <!-- start class org.apache.hadoop.mapreduce.lib.db.DataDrivenDBInputFormat.DataDrivenDBInputSplit -->
- <class name="DataDrivenDBInputFormat.DataDrivenDBInputSplit" extends="org.apache.hadoop.mapreduce.lib.db.DBInputFormat.DBInputSplit"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="DataDrivenDBInputFormat.DataDrivenDBInputSplit"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Default Constructor]]>
- </doc>
- </constructor>
- <constructor name="DataDrivenDBInputFormat.DataDrivenDBInputSplit" type="java.lang.String, java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Convenience Constructor
- @param lower the string to be put in the WHERE clause to guard on the 'lower' end
- @param upper the string to be put in the WHERE clause to guard on the 'upper' end]]>
- </doc>
- </constructor>
- <method name="getLength" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[@return The total row count in this split]]>
- </doc>
- </method>
- <method name="readFields"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="input" type="java.io.DataInput"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="output" type="java.io.DataOutput"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <method name="getLowerClause" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getUpperClause" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <doc>
- <![CDATA[A InputSplit that spans a set of rows]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.db.DataDrivenDBInputFormat.DataDrivenDBInputSplit -->
- <!-- start class org.apache.hadoop.mapreduce.lib.db.DataDrivenDBRecordReader -->
- <class name="DataDrivenDBRecordReader" extends="org.apache.hadoop.mapreduce.lib.db.DBRecordReader"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="DataDrivenDBRecordReader" type="org.apache.hadoop.mapreduce.lib.db.DBInputFormat.DBInputSplit, java.lang.Class, org.apache.hadoop.conf.Configuration, java.sql.Connection, org.apache.hadoop.mapreduce.lib.db.DBConfiguration, java.lang.String, java.lang.String[], java.lang.String, java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="SQLException" type="java.sql.SQLException"/>
- <doc>
- <![CDATA[@param split The InputSplit to read data for
- @throws SQLException]]>
- </doc>
- </constructor>
- <method name="getSelectQuery" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns the query for selecting the records,
- subclasses can override this for custom behaviour.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[A RecordReader that reads records from a SQL table,
- using data-driven WHERE clause splits.
- Emits LongWritables containing the record number as
- key and DBWritables as value.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.db.DataDrivenDBRecordReader -->
- <!-- start class org.apache.hadoop.mapreduce.lib.db.DateSplitter -->
- <class name="DateSplitter" extends="org.apache.hadoop.mapreduce.lib.db.IntegerSplitter"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="DateSplitter"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="split" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <param name="results" type="java.sql.ResultSet"/>
- <param name="colName" type="java.lang.String"/>
- <exception name="SQLException" type="java.sql.SQLException"/>
- </method>
- <method name="dateToString" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="d" type="java.util.Date"/>
- <doc>
- <![CDATA[Given a Date 'd', format it as a string for use in a SQL date
- comparison operation.
- @param d the date to format.
- @return the string representing this date in SQL with any appropriate
- quotation characters, etc.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Implement DBSplitter over date/time values.
- Make use of logic from IntegerSplitter, since date/time are just longs
- in Java.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.db.DateSplitter -->
- <!-- start class org.apache.hadoop.mapreduce.lib.db.DBConfiguration -->
- <class name="DBConfiguration" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="DBConfiguration" type="org.apache.hadoop.conf.Configuration"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="configureDB"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <param name="driverClass" type="java.lang.String"/>
- <param name="dbUrl" type="java.lang.String"/>
- <param name="userName" type="java.lang.String"/>
- <param name="passwd" type="java.lang.String"/>
- <doc>
- <![CDATA[Sets the DB access related fields in the {@link Configuration}.
- @param conf the configuration
- @param driverClass JDBC Driver class name
- @param dbUrl JDBC DB access URL.
- @param userName DB access username
- @param passwd DB access passwd]]>
- </doc>
- </method>
- <method name="configureDB"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.conf.Configuration"/>
- <param name="driverClass" type="java.lang.String"/>
- <param name="dbUrl" type="java.lang.String"/>
- <doc>
- <![CDATA[Sets the DB access related fields in the JobConf.
- @param job the job
- @param driverClass JDBC Driver class name
- @param dbUrl JDBC DB access URL.]]>
- </doc>
- </method>
- <method name="getConnection" return="java.sql.Connection"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="ClassNotFoundException" type="java.lang.ClassNotFoundException"/>
- <exception name="SQLException" type="java.sql.SQLException"/>
- <doc>
- <![CDATA[Returns a connection object o the DB
- @throws ClassNotFoundException
- @throws SQLException]]>
- </doc>
- </method>
- <method name="getConf" return="org.apache.hadoop.conf.Configuration"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getInputTableName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="setInputTableName"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="tableName" type="java.lang.String"/>
- </method>
- <method name="getInputFieldNames" return="java.lang.String[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="setInputFieldNames"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="fieldNames" type="java.lang.String[]"/>
- </method>
- <method name="getInputConditions" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="setInputConditions"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conditions" type="java.lang.String"/>
- </method>
- <method name="getInputOrderBy" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="setInputOrderBy"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="orderby" type="java.lang.String"/>
- </method>
- <method name="getInputQuery" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="setInputQuery"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="query" type="java.lang.String"/>
- </method>
- <method name="getInputCountQuery" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="setInputCountQuery"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="query" type="java.lang.String"/>
- </method>
- <method name="setInputBoundingQuery"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="query" type="java.lang.String"/>
- </method>
- <method name="getInputBoundingQuery" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getInputClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="setInputClass"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="inputClass" type="java.lang.Class"/>
- </method>
- <method name="getOutputTableName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="setOutputTableName"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="tableName" type="java.lang.String"/>
- </method>
- <method name="getOutputFieldNames" return="java.lang.String[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="setOutputFieldNames"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="fieldNames" type="java.lang.String[]"/>
- </method>
- <method name="setOutputFieldCount"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="fieldCount" type="int"/>
- </method>
- <method name="getOutputFieldCount" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <field name="DRIVER_CLASS_PROPERTY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[The JDBC Driver class name]]>
- </doc>
- </field>
- <field name="URL_PROPERTY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[JDBC Database access URL]]>
- </doc>
- </field>
- <field name="USERNAME_PROPERTY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[User name to access the database]]>
- </doc>
- </field>
- <field name="PASSWORD_PROPERTY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Password to access the database]]>
- </doc>
- </field>
- <field name="INPUT_TABLE_NAME_PROPERTY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Input table name]]>
- </doc>
- </field>
- <field name="INPUT_FIELD_NAMES_PROPERTY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Field names in the Input table]]>
- </doc>
- </field>
- <field name="INPUT_CONDITIONS_PROPERTY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[WHERE clause in the input SELECT statement]]>
- </doc>
- </field>
- <field name="INPUT_ORDER_BY_PROPERTY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[ORDER BY clause in the input SELECT statement]]>
- </doc>
- </field>
- <field name="INPUT_QUERY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Whole input query, exluding LIMIT...OFFSET]]>
- </doc>
- </field>
- <field name="INPUT_COUNT_QUERY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Input query to get the count of records]]>
- </doc>
- </field>
- <field name="INPUT_BOUNDING_QUERY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Input query to get the max and min values of the jdbc.input.query]]>
- </doc>
- </field>
- <field name="INPUT_CLASS_PROPERTY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Class name implementing DBWritable which will hold input tuples]]>
- </doc>
- </field>
- <field name="OUTPUT_TABLE_NAME_PROPERTY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Output table name]]>
- </doc>
- </field>
- <field name="OUTPUT_FIELD_NAMES_PROPERTY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Field names in the Output table]]>
- </doc>
- </field>
- <field name="OUTPUT_FIELD_COUNT_PROPERTY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Number of fields in the Output table]]>
- </doc>
- </field>
- <doc>
- <![CDATA[A container for configuration property names for jobs with DB input/output.
-
- The job can be configured using the static methods in this class,
- {@link DBInputFormat}, and {@link DBOutputFormat}.
- Alternatively, the properties can be set in the configuration with proper
- values.
-
- @see DBConfiguration#configureDB(Configuration, String, String, String, String)
- @see DBInputFormat#setInput(Job, Class, String, String)
- @see DBInputFormat#setInput(Job, Class, String, String, String, String...)
- @see DBOutputFormat#setOutput(Job, String, String...)]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.db.DBConfiguration -->
- <!-- start class org.apache.hadoop.mapreduce.lib.db.DBInputFormat -->
- <class name="DBInputFormat" extends="org.apache.hadoop.mapreduce.InputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.conf.Configurable"/>
- <constructor name="DBInputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setConf"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <method name="getConf" return="org.apache.hadoop.conf.Configuration"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getDBConf" return="org.apache.hadoop.mapreduce.lib.db.DBConfiguration"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getConnection" return="java.sql.Connection"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getDBProductName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="createDBRecordReader" return="org.apache.hadoop.mapreduce.RecordReader"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapreduce.lib.db.DBInputFormat.DBInputSplit"/>
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="createRecordReader" return="org.apache.hadoop.mapreduce.RecordReader"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapreduce.InputSplit"/>
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <method name="getSplits" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.JobContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <method name="getCountQuery" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns the query for getting the total number of rows,
- subclasses can override this for custom behaviour.]]>
- </doc>
- </method>
- <method name="setInput"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <param name="inputClass" type="java.lang.Class"/>
- <param name="tableName" type="java.lang.String"/>
- <param name="conditions" type="java.lang.String"/>
- <param name="orderBy" type="java.lang.String"/>
- <param name="fieldNames" type="java.lang.String[]"/>
- <doc>
- <![CDATA[Initializes the map-part of the job with the appropriate input settings.
-
- @param job The map-reduce job
- @param inputClass the class object implementing DBWritable, which is the
- Java object holding tuple fields.
- @param tableName The table to read data from
- @param conditions The condition which to select data with,
- eg. '(updated > 20070101 AND length > 0)'
- @param orderBy the fieldNames in the orderBy clause.
- @param fieldNames The field names in the table
- @see #setInput(Job, Class, String, String)]]>
- </doc>
- </method>
- <method name="setInput"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <param name="inputClass" type="java.lang.Class"/>
- <param name="inputQuery" type="java.lang.String"/>
- <param name="inputCountQuery" type="java.lang.String"/>
- <doc>
- <![CDATA[Initializes the map-part of the job with the appropriate input settings.
-
- @param job The map-reduce job
- @param inputClass the class object implementing DBWritable, which is the
- Java object holding tuple fields.
- @param inputQuery the input query to select fields. Example :
- "SELECT f1, f2, f3 FROM Mytable ORDER BY f1"
- @param inputCountQuery the input query that returns
- the number of records in the table.
- Example : "SELECT COUNT(f1) FROM Mytable"
- @see #setInput(Job, Class, String, String, String, String...)]]>
- </doc>
- </method>
- <method name="closeConnection"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </method>
- <doc>
- <![CDATA[A InputFormat that reads input data from an SQL table.
- <p>
- DBInputFormat emits LongWritables containing the record number as
- key and DBWritables as value.
-
- The SQL query, and input class can be using one of the two
- setInput methods.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.db.DBInputFormat -->
- <!-- start class org.apache.hadoop.mapreduce.lib.db.DBInputFormat.DBInputSplit -->
- <class name="DBInputFormat.DBInputSplit" extends="org.apache.hadoop.mapreduce.InputSplit"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.io.Writable"/>
- <constructor name="DBInputFormat.DBInputSplit"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Default Constructor]]>
- </doc>
- </constructor>
- <constructor name="DBInputFormat.DBInputSplit" type="long, long"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Convenience Constructor
- @param start the index of the first row to select
- @param end the index of the last row to select]]>
- </doc>
- </constructor>
- <method name="getLocations" return="java.lang.String[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <method name="getStart" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return The index of the first row to select]]>
- </doc>
- </method>
- <method name="getEnd" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return The index of the last row to select]]>
- </doc>
- </method>
- <method name="getLength" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[@return The total row count in this split]]>
- </doc>
- </method>
- <method name="readFields"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="input" type="java.io.DataInput"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="output" type="java.io.DataOutput"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <doc>
- <![CDATA[A InputSplit that spans a set of rows]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.db.DBInputFormat.DBInputSplit -->
- <!-- start class org.apache.hadoop.mapreduce.lib.db.DBInputFormat.NullDBWritable -->
- <class name="DBInputFormat.NullDBWritable" extends="java.lang.Object"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.lib.db.DBWritable"/>
- <implements name="org.apache.hadoop.io.Writable"/>
- <constructor name="DBInputFormat.NullDBWritable"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="readFields"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="in" type="java.io.DataInput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="readFields"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="arg0" type="java.sql.ResultSet"/>
- <exception name="SQLException" type="java.sql.SQLException"/>
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="out" type="java.io.DataOutput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="arg0" type="java.sql.PreparedStatement"/>
- <exception name="SQLException" type="java.sql.SQLException"/>
- </method>
- <doc>
- <![CDATA[A Class that does nothing, implementing DBWritable]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.db.DBInputFormat.NullDBWritable -->
- <!-- start class org.apache.hadoop.mapreduce.lib.db.DBOutputFormat -->
- <class name="DBOutputFormat" extends="org.apache.hadoop.mapreduce.OutputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="DBOutputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="checkOutputSpecs"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.JobContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="getOutputCommitter" return="org.apache.hadoop.mapreduce.OutputCommitter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="constructQuery" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="table" type="java.lang.String"/>
- <param name="fieldNames" type="java.lang.String[]"/>
- <doc>
- <![CDATA[Constructs the query used as the prepared statement to insert data.
-
- @param table
- the table to insert into
- @param fieldNames
- the fields to insert into. If field names are unknown, supply an
- array of nulls.]]>
- </doc>
- </method>
- <method name="getRecordWriter" return="org.apache.hadoop.mapreduce.RecordWriter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <method name="setOutput"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <param name="tableName" type="java.lang.String"/>
- <param name="fieldNames" type="java.lang.String[]"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Initializes the reduce-part of the job with
- the appropriate output settings
-
- @param job The job
- @param tableName The table to insert data into
- @param fieldNames The field names in the table.]]>
- </doc>
- </method>
- <method name="setOutput"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <param name="tableName" type="java.lang.String"/>
- <param name="fieldCount" type="int"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Initializes the reduce-part of the job
- with the appropriate output settings
-
- @param job The job
- @param tableName The table to insert data into
- @param fieldCount the number of fields in the table.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[A OutputFormat that sends the reduce output to a SQL table.
- <p>
- {@link DBOutputFormat} accepts <key,value> pairs, where
- key has a type extending DBWritable. Returned {@link RecordWriter}
- writes <b>only the key</b> to the database with a batch SQL query.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.db.DBOutputFormat -->
- <!-- start class org.apache.hadoop.mapreduce.lib.db.DBOutputFormat.DBRecordWriter -->
- <class name="DBOutputFormat.DBRecordWriter" extends="org.apache.hadoop.mapreduce.RecordWriter"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="DBOutputFormat.DBRecordWriter"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="SQLException" type="java.sql.SQLException"/>
- </constructor>
- <constructor name="DBOutputFormat.DBRecordWriter" type="java.sql.Connection, java.sql.PreparedStatement"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="SQLException" type="java.sql.SQLException"/>
- </constructor>
- <method name="getConnection" return="java.sql.Connection"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getStatement" return="java.sql.PreparedStatement"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <param name="value" type="V"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <doc>
- <![CDATA[A RecordWriter that writes the reduce output to a SQL table]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.db.DBOutputFormat.DBRecordWriter -->
- <!-- start class org.apache.hadoop.mapreduce.lib.db.DBRecordReader -->
- <class name="DBRecordReader" extends="org.apache.hadoop.mapreduce.RecordReader"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="DBRecordReader" type="org.apache.hadoop.mapreduce.lib.db.DBInputFormat.DBInputSplit, java.lang.Class, org.apache.hadoop.conf.Configuration, java.sql.Connection, org.apache.hadoop.mapreduce.lib.db.DBConfiguration, java.lang.String, java.lang.String[], java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="SQLException" type="java.sql.SQLException"/>
- <doc>
- <![CDATA[@param split The InputSplit to read data for
- @throws SQLException]]>
- </doc>
- </constructor>
- <method name="executeQuery" return="java.sql.ResultSet"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="query" type="java.lang.String"/>
- <exception name="SQLException" type="java.sql.SQLException"/>
- </method>
- <method name="getSelectQuery" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns the query for selecting the records,
- subclasses can override this for custom behaviour.]]>
- </doc>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <method name="initialize"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapreduce.InputSplit"/>
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="getCurrentKey" return="org.apache.hadoop.io.LongWritable"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <method name="getCurrentValue" return="T"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <method name="createValue" return="T"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="deprecated, no comment">
- <doc>
- <![CDATA[@deprecated]]>
- </doc>
- </method>
- <method name="getPos" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="deprecated, no comment">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[@deprecated]]>
- </doc>
- </method>
- <method name="next" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link #nextKeyValue()}">
- <param name="key" type="org.apache.hadoop.io.LongWritable"/>
- <param name="value" type="T"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[@deprecated Use {@link #nextKeyValue()}]]>
- </doc>
- </method>
- <method name="getProgress" return="float"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <method name="nextKeyValue" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <method name="getSplit" return="org.apache.hadoop.mapreduce.lib.db.DBInputFormat.DBInputSplit"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </method>
- <method name="getFieldNames" return="java.lang.String[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </method>
- <method name="getTableName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </method>
- <method name="getConditions" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </method>
- <method name="getDBConf" return="org.apache.hadoop.mapreduce.lib.db.DBConfiguration"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </method>
- <method name="getConnection" return="java.sql.Connection"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </method>
- <method name="getStatement" return="java.sql.PreparedStatement"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </method>
- <method name="setStatement"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="stmt" type="java.sql.PreparedStatement"/>
- </method>
- <field name="statement" type="java.sql.PreparedStatement"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[A RecordReader that reads records from a SQL table.
- Emits LongWritables containing the record number as
- key and DBWritables as value.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.db.DBRecordReader -->
- <!-- start interface org.apache.hadoop.mapreduce.lib.db.DBSplitter -->
- <interface name="DBSplitter" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <method name="split" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <param name="results" type="java.sql.ResultSet"/>
- <param name="colName" type="java.lang.String"/>
- <exception name="SQLException" type="java.sql.SQLException"/>
- <doc>
- <![CDATA[Given a ResultSet containing one record (and already advanced to that record)
- with two columns (a low value, and a high value, both of the same type), determine
- a set of splits that span the given values.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[DBSplitter will generate DBInputSplits to use with DataDrivenDBInputFormat.
- DataDrivenDBInputFormat needs to interpolate between two values that
- represent the lowest and highest valued records to import. Depending
- on the data-type of the column, this requires different behavior.
- DBSplitter implementations should perform this for a data type or family
- of data types.]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapreduce.lib.db.DBSplitter -->
- <!-- start interface org.apache.hadoop.mapreduce.lib.db.DBWritable -->
- <interface name="DBWritable" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <method name="write"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="statement" type="java.sql.PreparedStatement"/>
- <exception name="SQLException" type="java.sql.SQLException"/>
- <doc>
- <![CDATA[Sets the fields of the object in the {@link PreparedStatement}.
- @param statement the statement that the fields are put into.
- @throws SQLException]]>
- </doc>
- </method>
- <method name="readFields"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="resultSet" type="java.sql.ResultSet"/>
- <exception name="SQLException" type="java.sql.SQLException"/>
- <doc>
- <![CDATA[Reads the fields of the object from the {@link ResultSet}.
- @param resultSet the {@link ResultSet} to get the fields from.
- @throws SQLException]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Objects that are read from/written to a database should implement
- <code>DBWritable</code>. DBWritable, is similar to {@link Writable}
- except that the {@link #write(PreparedStatement)} method takes a
- {@link PreparedStatement}, and {@link #readFields(ResultSet)}
- takes a {@link ResultSet}.
- <p>
- Implementations are responsible for writing the fields of the object
- to PreparedStatement, and reading the fields of the object from the
- ResultSet.
-
- <p>Example:</p>
- If we have the following table in the database :
- <pre>
- CREATE TABLE MyTable (
- counter INTEGER NOT NULL,
- timestamp BIGINT NOT NULL,
- );
- </pre>
- then we can read/write the tuples from/to the table with :
- <p><pre>
- public class MyWritable implements Writable, DBWritable {
- // Some data
- private int counter;
- private long timestamp;
-
- //Writable#write() implementation
- public void write(DataOutput out) throws IOException {
- out.writeInt(counter);
- out.writeLong(timestamp);
- }
-
- //Writable#readFields() implementation
- public void readFields(DataInput in) throws IOException {
- counter = in.readInt();
- timestamp = in.readLong();
- }
-
- public void write(PreparedStatement statement) throws SQLException {
- statement.setInt(1, counter);
- statement.setLong(2, timestamp);
- }
-
- public void readFields(ResultSet resultSet) throws SQLException {
- counter = resultSet.getInt(1);
- timestamp = resultSet.getLong(2);
- }
- }
- </pre></p>]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapreduce.lib.db.DBWritable -->
- <!-- start class org.apache.hadoop.mapreduce.lib.db.FloatSplitter -->
- <class name="FloatSplitter" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.lib.db.DBSplitter"/>
- <constructor name="FloatSplitter"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="split" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <param name="results" type="java.sql.ResultSet"/>
- <param name="colName" type="java.lang.String"/>
- <exception name="SQLException" type="java.sql.SQLException"/>
- </method>
- <doc>
- <![CDATA[Implement DBSplitter over floating-point values.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.db.FloatSplitter -->
- <!-- start class org.apache.hadoop.mapreduce.lib.db.IntegerSplitter -->
- <class name="IntegerSplitter" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.lib.db.DBSplitter"/>
- <constructor name="IntegerSplitter"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="split" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <param name="results" type="java.sql.ResultSet"/>
- <param name="colName" type="java.lang.String"/>
- <exception name="SQLException" type="java.sql.SQLException"/>
- </method>
- <doc>
- <![CDATA[Implement DBSplitter over integer values.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.db.IntegerSplitter -->
- <!-- start class org.apache.hadoop.mapreduce.lib.db.MySQLDataDrivenDBRecordReader -->
- <class name="MySQLDataDrivenDBRecordReader" extends="org.apache.hadoop.mapreduce.lib.db.DataDrivenDBRecordReader"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="MySQLDataDrivenDBRecordReader" type="org.apache.hadoop.mapreduce.lib.db.DBInputFormat.DBInputSplit, java.lang.Class, org.apache.hadoop.conf.Configuration, java.sql.Connection, org.apache.hadoop.mapreduce.lib.db.DBConfiguration, java.lang.String, java.lang.String[], java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="SQLException" type="java.sql.SQLException"/>
- </constructor>
- <method name="executeQuery" return="java.sql.ResultSet"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="query" type="java.lang.String"/>
- <exception name="SQLException" type="java.sql.SQLException"/>
- </method>
- <doc>
- <![CDATA[A RecordReader that reads records from a MySQL table via DataDrivenDBRecordReader]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.db.MySQLDataDrivenDBRecordReader -->
- <!-- start class org.apache.hadoop.mapreduce.lib.db.MySQLDBRecordReader -->
- <class name="MySQLDBRecordReader" extends="org.apache.hadoop.mapreduce.lib.db.DBRecordReader"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="MySQLDBRecordReader" type="org.apache.hadoop.mapreduce.lib.db.DBInputFormat.DBInputSplit, java.lang.Class, org.apache.hadoop.conf.Configuration, java.sql.Connection, org.apache.hadoop.mapreduce.lib.db.DBConfiguration, java.lang.String, java.lang.String[], java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="SQLException" type="java.sql.SQLException"/>
- </constructor>
- <method name="executeQuery" return="java.sql.ResultSet"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="query" type="java.lang.String"/>
- <exception name="SQLException" type="java.sql.SQLException"/>
- </method>
- <doc>
- <![CDATA[A RecordReader that reads records from a MySQL table.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.db.MySQLDBRecordReader -->
- <!-- start class org.apache.hadoop.mapreduce.lib.db.OracleDataDrivenDBInputFormat -->
- <class name="OracleDataDrivenDBInputFormat" extends="org.apache.hadoop.mapreduce.lib.db.DataDrivenDBInputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.conf.Configurable"/>
- <constructor name="OracleDataDrivenDBInputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getSplitter" return="org.apache.hadoop.mapreduce.lib.db.DBSplitter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="sqlDataType" type="int"/>
- <doc>
- <![CDATA[@return the DBSplitter implementation to use to divide the table/query into InputSplits.]]>
- </doc>
- </method>
- <method name="createDBRecordReader" return="org.apache.hadoop.mapreduce.RecordReader"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapreduce.lib.db.DBInputFormat.DBInputSplit"/>
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[A InputFormat that reads input data from an SQL table in an Oracle db.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.db.OracleDataDrivenDBInputFormat -->
- <!-- start class org.apache.hadoop.mapreduce.lib.db.OracleDataDrivenDBRecordReader -->
- <class name="OracleDataDrivenDBRecordReader" extends="org.apache.hadoop.mapreduce.lib.db.DataDrivenDBRecordReader"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="OracleDataDrivenDBRecordReader" type="org.apache.hadoop.mapreduce.lib.db.DBInputFormat.DBInputSplit, java.lang.Class, org.apache.hadoop.conf.Configuration, java.sql.Connection, org.apache.hadoop.mapreduce.lib.db.DBConfiguration, java.lang.String, java.lang.String[], java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="SQLException" type="java.sql.SQLException"/>
- </constructor>
- <doc>
- <![CDATA[A RecordReader that reads records from a Oracle table via DataDrivenDBRecordReader]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.db.OracleDataDrivenDBRecordReader -->
- <!-- start class org.apache.hadoop.mapreduce.lib.db.OracleDateSplitter -->
- <class name="OracleDateSplitter" extends="org.apache.hadoop.mapreduce.lib.db.DateSplitter"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="OracleDateSplitter"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="dateToString" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="d" type="java.util.Date"/>
- </method>
- <doc>
- <![CDATA[Implement DBSplitter over date/time values returned by an Oracle db.
- Make use of logic from DateSplitter, since this just needs to use
- some Oracle-specific functions on the formatting end when generating
- InputSplits.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.db.OracleDateSplitter -->
- <!-- start class org.apache.hadoop.mapreduce.lib.db.OracleDBRecordReader -->
- <class name="OracleDBRecordReader" extends="org.apache.hadoop.mapreduce.lib.db.DBRecordReader"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="OracleDBRecordReader" type="org.apache.hadoop.mapreduce.lib.db.DBInputFormat.DBInputSplit, java.lang.Class, org.apache.hadoop.conf.Configuration, java.sql.Connection, org.apache.hadoop.mapreduce.lib.db.DBConfiguration, java.lang.String, java.lang.String[], java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="SQLException" type="java.sql.SQLException"/>
- </constructor>
- <method name="getSelectQuery" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns the query for selecting the records from an Oracle DB.]]>
- </doc>
- </method>
- <method name="setSessionTimeZone"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <param name="conn" type="java.sql.Connection"/>
- <exception name="SQLException" type="java.sql.SQLException"/>
- <doc>
- <![CDATA[Set session time zone
- @param conf The current configuration.
- We read the 'oracle.sessionTimeZone' property from here.
- @param conn The connection to alter the timezone properties of.]]>
- </doc>
- </method>
- <field name="SESSION_TIMEZONE_KEY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Configuration key to set to a timezone string.]]>
- </doc>
- </field>
- <doc>
- <![CDATA[A RecordReader that reads records from an Oracle SQL table.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.db.OracleDBRecordReader -->
- <!-- start class org.apache.hadoop.mapreduce.lib.db.TextSplitter -->
- <class name="TextSplitter" extends="org.apache.hadoop.mapreduce.lib.db.BigDecimalSplitter"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="TextSplitter"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="split" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <param name="results" type="java.sql.ResultSet"/>
- <param name="colName" type="java.lang.String"/>
- <exception name="SQLException" type="java.sql.SQLException"/>
- <doc>
- <![CDATA[This method needs to determine the splits between two user-provided strings.
- In the case where the user's strings are 'A' and 'Z', this is not hard; we
- could create two splits from ['A', 'M') and ['M', 'Z'], 26 splits for strings
- beginning with each letter, etc.
- If a user has provided us with the strings "Ham" and "Haze", however, we need
- to create splits that differ in the third letter.
- The algorithm used is as follows:
- Since there are 2**16 unicode characters, we interpret characters as digits in
- base 65536. Given a string 's' containing characters s_0, s_1 .. s_n, we interpret
- the string as the number: 0.s_0 s_1 s_2.. s_n in base 65536. Having mapped the
- low and high strings into floating-point values, we then use the BigDecimalSplitter
- to establish the even split points, then map the resulting floating point values
- back into strings.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Implement DBSplitter over text strings.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.db.TextSplitter -->
- </package>
- <package name="org.apache.hadoop.mapreduce.lib.fieldsel">
- <!-- start class org.apache.hadoop.mapreduce.lib.fieldsel.FieldSelectionHelper -->
- <class name="FieldSelectionHelper" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="FieldSelectionHelper"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <constructor name="FieldSelectionHelper" type="org.apache.hadoop.io.Text, org.apache.hadoop.io.Text"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="parseOutputKeyValueSpec" return="int"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="keyValueSpec" type="java.lang.String"/>
- <param name="keyFieldList" type="java.util.List"/>
- <param name="valueFieldList" type="java.util.List"/>
- </method>
- <method name="specToString" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="fieldSeparator" type="java.lang.String"/>
- <param name="keyValueSpec" type="java.lang.String"/>
- <param name="allValueFieldsFrom" type="int"/>
- <param name="keyFieldList" type="java.util.List"/>
- <param name="valueFieldList" type="java.util.List"/>
- </method>
- <method name="getKey" return="org.apache.hadoop.io.Text"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getValue" return="org.apache.hadoop.io.Text"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="extractOutputKeyValue"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="java.lang.String"/>
- <param name="val" type="java.lang.String"/>
- <param name="fieldSep" type="java.lang.String"/>
- <param name="keyFieldList" type="java.util.List"/>
- <param name="valFieldList" type="java.util.List"/>
- <param name="allValueFieldsFrom" type="int"/>
- <param name="ignoreKey" type="boolean"/>
- <param name="isMap" type="boolean"/>
- </method>
- <field name="emptyText" type="org.apache.hadoop.io.Text"
- transient="false" volatile="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="DATA_FIELD_SEPERATOR" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="MAP_OUTPUT_KEY_VALUE_SPEC" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="REDUCE_OUTPUT_KEY_VALUE_SPEC" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[This class implements a mapper/reducer class that can be used to perform
- field selections in a manner similar to unix cut. The input data is treated
- as fields separated by a user specified separator (the default value is
- "\t"). The user can specify a list of fields that form the map output keys,
- and a list of fields that form the map output values. If the inputformat is
- TextInputFormat, the mapper will ignore the key to the map function. and the
- fields are from the value only. Otherwise, the fields are the union of those
- from the key and those from the value.
-
- The field separator is under attribute "mapreduce.fieldsel.data.field.separator"
-
- The map output field list spec is under attribute
- "mapreduce.fieldsel.map.output.key.value.fields.spec".
- The value is expected to be like "keyFieldsSpec:valueFieldsSpec"
- key/valueFieldsSpec are comma (,) separated field spec: fieldSpec,fieldSpec,fieldSpec ...
- Each field spec can be a simple number (e.g. 5) specifying a specific field, or a range
- (like 2-5) to specify a range of fields, or an open range (like 3-) specifying all
- the fields starting from field 3. The open range field spec applies value fields only.
- They have no effect on the key fields.
-
- Here is an example: "4,3,0,1:6,5,1-3,7-". It specifies to use fields 4,3,0 and 1 for keys,
- and use fields 6,5,1,2,3,7 and above for values.
-
- The reduce output field list spec is under attribute
- "mapreduce.fieldsel.reduce.output.key.value.fields.spec".
-
- The reducer extracts output key/value pairs in a similar manner, except that
- the key is never ignored.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.fieldsel.FieldSelectionHelper -->
- <!-- start class org.apache.hadoop.mapreduce.lib.fieldsel.FieldSelectionMapper -->
- <class name="FieldSelectionMapper" extends="org.apache.hadoop.mapreduce.Mapper"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="FieldSelectionMapper"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setup"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.Mapper.Context"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="map"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <param name="val" type="V"/>
- <param name="context" type="org.apache.hadoop.mapreduce.Mapper.Context"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[The identify function. Input key/value pair is written directly to output.]]>
- </doc>
- </method>
- <field name="LOG" type="org.apache.commons.logging.Log"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[This class implements a mapper class that can be used to perform
- field selections in a manner similar to unix cut. The input data is treated
- as fields separated by a user specified separator (the default value is
- "\t"). The user can specify a list of fields that form the map output keys,
- and a list of fields that form the map output values. If the inputformat is
- TextInputFormat, the mapper will ignore the key to the map function. and the
- fields are from the value only. Otherwise, the fields are the union of those
- from the key and those from the value.
-
- The field separator is under attribute "mapreduce.fieldsel.data.field.separator"
-
- The map output field list spec is under attribute
- "mapreduce.fieldsel.map.output.key.value.fields.spec".
- The value is expected to be like
- "keyFieldsSpec:valueFieldsSpec" key/valueFieldsSpec are comma (,) separated
- field spec: fieldSpec,fieldSpec,fieldSpec ... Each field spec can be a
- simple number (e.g. 5) specifying a specific field, or a range (like 2-5)
- to specify a range of fields, or an open range (like 3-) specifying all
- the fields starting from field 3. The open range field spec applies value
- fields only. They have no effect on the key fields.
-
- Here is an example: "4,3,0,1:6,5,1-3,7-". It specifies to use fields
- 4,3,0 and 1 for keys, and use fields 6,5,1,2,3,7 and above for values.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.fieldsel.FieldSelectionMapper -->
- <!-- start class org.apache.hadoop.mapreduce.lib.fieldsel.FieldSelectionReducer -->
- <class name="FieldSelectionReducer" extends="org.apache.hadoop.mapreduce.Reducer"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="FieldSelectionReducer"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setup"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.Reducer.Context"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="reduce"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="org.apache.hadoop.io.Text"/>
- <param name="values" type="java.lang.Iterable"/>
- <param name="context" type="org.apache.hadoop.mapreduce.Reducer.Context"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <field name="LOG" type="org.apache.commons.logging.Log"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[This class implements a reducer class that can be used to perform field
- selections in a manner similar to unix cut.
-
- The input data is treated as fields separated by a user specified
- separator (the default value is "\t"). The user can specify a list of
- fields that form the reduce output keys, and a list of fields that form
- the reduce output values. The fields are the union of those from the key
- and those from the value.
-
- The field separator is under attribute "mapreduce.fieldsel.data.field.separator"
-
- The reduce output field list spec is under attribute
- "mapreduce.fieldsel.reduce.output.key.value.fields.spec".
- The value is expected to be like
- "keyFieldsSpec:valueFieldsSpec" key/valueFieldsSpec are comma (,)
- separated field spec: fieldSpec,fieldSpec,fieldSpec ... Each field spec
- can be a simple number (e.g. 5) specifying a specific field, or a range
- (like 2-5) to specify a range of fields, or an open range (like 3-)
- specifying all the fields starting from field 3. The open range field
- spec applies value fields only. They have no effect on the key fields.
-
- Here is an example: "4,3,0,1:6,5,1-3,7-". It specifies to use fields
- 4,3,0 and 1 for keys, and use fields 6,5,1,2,3,7 and above for values.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.fieldsel.FieldSelectionReducer -->
- </package>
- <package name="org.apache.hadoop.mapreduce.lib.input">
- <!-- start class org.apache.hadoop.mapreduce.lib.input.CombineFileInputFormat -->
- <class name="CombineFileInputFormat" extends="org.apache.hadoop.mapreduce.lib.input.FileInputFormat"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="CombineFileInputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[default constructor]]>
- </doc>
- </constructor>
- <method name="setMaxSplitSize"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="maxSplitSize" type="long"/>
- <doc>
- <![CDATA[Specify the maximum size (in bytes) of each split. Each split is
- approximately equal to the specified size.]]>
- </doc>
- </method>
- <method name="setMinSplitSizeNode"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="minSplitSizeNode" type="long"/>
- <doc>
- <![CDATA[Specify the minimum size (in bytes) of each split per node.
- This applies to data that is left over after combining data on a single
- node into splits that are of maximum size specified by maxSplitSize.
- This leftover data will be combined into its own split if its size
- exceeds minSplitSizeNode.]]>
- </doc>
- </method>
- <method name="setMinSplitSizeRack"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="minSplitSizeRack" type="long"/>
- <doc>
- <![CDATA[Specify the minimum size (in bytes) of each split per rack.
- This applies to data that is left over after combining data on a single
- rack into splits that are of maximum size specified by maxSplitSize.
- This leftover data will be combined into its own split if its size
- exceeds minSplitSizeRack.]]>
- </doc>
- </method>
- <method name="createPool"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="filters" type="java.util.List"/>
- <doc>
- <![CDATA[Create a new pool and add the filters to it.
- A split cannot have files from different pools.]]>
- </doc>
- </method>
- <method name="createPool"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="filters" type="org.apache.hadoop.fs.PathFilter[]"/>
- <doc>
- <![CDATA[Create a new pool and add the filters to it.
- A pathname can satisfy any one of the specified filters.
- A split cannot have files from different pools.]]>
- </doc>
- </method>
- <method name="isSplitable" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.JobContext"/>
- <param name="file" type="org.apache.hadoop.fs.Path"/>
- </method>
- <method name="getSplits" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.JobContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="createRecordReader" return="org.apache.hadoop.mapreduce.RecordReader"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapreduce.InputSplit"/>
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[This is not implemented yet.]]>
- </doc>
- </method>
- <field name="SPLIT_MINSIZE_PERNODE" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="SPLIT_MINSIZE_PERRACK" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[An abstract {@link InputFormat} that returns {@link CombineFileSplit}'s in
- {@link InputFormat#getSplits(JobContext)} method.
-
- Splits are constructed from the files under the input paths.
- A split cannot have files from different pools.
- Each split returned may contain blocks from different files.
- If a maxSplitSize is specified, then blocks on the same node are
- combined to form a single split. Blocks that are left over are
- then combined with other blocks in the same rack.
- If maxSplitSize is not specified, then blocks from the same rack
- are combined in a single split; no attempt is made to create
- node-local splits.
- If the maxSplitSize is equal to the block size, then this class
- is similar to the default splitting behavior in Hadoop: each
- block is a locally processed split.
- Subclasses implement
- {@link InputFormat#createRecordReader(InputSplit, TaskAttemptContext)}
- to construct <code>RecordReader</code>'s for
- <code>CombineFileSplit</code>'s.
-
- @see CombineFileSplit]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.input.CombineFileInputFormat -->
- <!-- start class org.apache.hadoop.mapreduce.lib.input.CombineFileRecordReader -->
- <class name="CombineFileRecordReader" extends="org.apache.hadoop.mapreduce.RecordReader"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="CombineFileRecordReader" type="org.apache.hadoop.mapreduce.lib.input.CombineFileSplit, org.apache.hadoop.mapreduce.TaskAttemptContext, java.lang.Class"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[A generic RecordReader that can hand out different recordReaders
- for each chunk in the CombineFileSplit.]]>
- </doc>
- </constructor>
- <method name="initialize"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapreduce.InputSplit"/>
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="nextKeyValue" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="getCurrentKey" return="K"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="getCurrentValue" return="V"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getProgress" return="float"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[return progress based on the amount of data processed so far.]]>
- </doc>
- </method>
- <method name="initNextRecordReader" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get the record reader for the next chunk in this CombineFileSplit.]]>
- </doc>
- </method>
- <field name="split" type="org.apache.hadoop.mapreduce.lib.input.CombineFileSplit"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="rrClass" type="java.lang.Class"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="rrConstructor" type="java.lang.reflect.Constructor"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="fs" type="org.apache.hadoop.fs.FileSystem"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="idx" type="int"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="progress" type="long"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="curReader" type="org.apache.hadoop.mapreduce.RecordReader"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[A generic RecordReader that can hand out different recordReaders
- for each chunk in a {@link CombineFileSplit}.
- A CombineFileSplit can combine data chunks from multiple files.
- This class allows using different RecordReaders for processing
- these data chunks from different files.
- @see CombineFileSplit]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.input.CombineFileRecordReader -->
- <!-- start class org.apache.hadoop.mapreduce.lib.input.CombineFileSplit -->
- <class name="CombineFileSplit" extends="org.apache.hadoop.mapreduce.InputSplit"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.io.Writable"/>
- <constructor name="CombineFileSplit"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[default constructor]]>
- </doc>
- </constructor>
- <constructor name="CombineFileSplit" type="org.apache.hadoop.fs.Path[], long[], long[], java.lang.String[]"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <constructor name="CombineFileSplit" type="org.apache.hadoop.fs.Path[], long[]"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <constructor name="CombineFileSplit" type="org.apache.hadoop.mapreduce.lib.input.CombineFileSplit"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Copy constructor]]>
- </doc>
- </constructor>
- <method name="getLength" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getStartOffsets" return="long[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns an array containing the start offsets of the files in the split]]>
- </doc>
- </method>
- <method name="getLengths" return="long[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns an array containing the lengths of the files in the split]]>
- </doc>
- </method>
- <method name="getOffset" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="i" type="int"/>
- <doc>
- <![CDATA[Returns the start offset of the i<sup>th</sup> Path]]>
- </doc>
- </method>
- <method name="getLength" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="i" type="int"/>
- <doc>
- <![CDATA[Returns the length of the i<sup>th</sup> Path]]>
- </doc>
- </method>
- <method name="getNumPaths" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns the number of Paths in the split]]>
- </doc>
- </method>
- <method name="getPath" return="org.apache.hadoop.fs.Path"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="i" type="int"/>
- <doc>
- <![CDATA[Returns the i<sup>th</sup> Path]]>
- </doc>
- </method>
- <method name="getPaths" return="org.apache.hadoop.fs.Path[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns all the Paths in the split]]>
- </doc>
- </method>
- <method name="getLocations" return="java.lang.String[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Returns all the Paths where this input-split resides]]>
- </doc>
- </method>
- <method name="readFields"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="in" type="java.io.DataInput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="out" type="java.io.DataOutput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="toString" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <doc>
- <![CDATA[A sub-collection of input files.
-
- Unlike {@link FileSplit}, CombineFileSplit class does not represent
- a split of a file, but a split of input files into smaller sets.
- A split may contain blocks from different file but all
- the blocks in the same split are probably local to some rack <br>
- CombineFileSplit can be used to implement {@link RecordReader}'s,
- with reading one record per file.
-
- @see FileSplit
- @see CombineFileInputFormat]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.input.CombineFileSplit -->
- <!-- start class org.apache.hadoop.mapreduce.lib.input.FileInputFormat -->
- <class name="FileInputFormat" extends="org.apache.hadoop.mapreduce.InputFormat"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="FileInputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getFormatMinSplitSize" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the lower bound on split size imposed by the format.
- @return the number of bytes of the minimal split for this format]]>
- </doc>
- </method>
- <method name="isSplitable" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.JobContext"/>
- <param name="filename" type="org.apache.hadoop.fs.Path"/>
- <doc>
- <![CDATA[Is the given filename splitable? Usually, true, but if the file is
- stream compressed, it will not be.
-
- <code>FileInputFormat</code> implementations can override this and return
- <code>false</code> to ensure that individual input files are never split-up
- so that {@link Mapper}s process entire files.
-
- @param context the job context
- @param filename the file name to check
- @return is this file splitable?]]>
- </doc>
- </method>
- <method name="setInputPathFilter"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <param name="filter" type="java.lang.Class"/>
- <doc>
- <![CDATA[Set a PathFilter to be applied to the input paths for the map-reduce job.
- @param job the job to modify
- @param filter the PathFilter class use for filtering the input paths.]]>
- </doc>
- </method>
- <method name="setMinInputSplitSize"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <param name="size" type="long"/>
- <doc>
- <![CDATA[Set the minimum input split size
- @param job the job to modify
- @param size the minimum size]]>
- </doc>
- </method>
- <method name="getMinSplitSize" return="long"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.JobContext"/>
- <doc>
- <![CDATA[Get the minimum split size
- @param job the job
- @return the minimum number of bytes that can be in a split]]>
- </doc>
- </method>
- <method name="setMaxInputSplitSize"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <param name="size" type="long"/>
- <doc>
- <![CDATA[Set the maximum split size
- @param job the job to modify
- @param size the maximum split size]]>
- </doc>
- </method>
- <method name="getMaxSplitSize" return="long"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.JobContext"/>
- <doc>
- <![CDATA[Get the maximum split size.
- @param context the job to look at.
- @return the maximum number of bytes a split can include]]>
- </doc>
- </method>
- <method name="getInputPathFilter" return="org.apache.hadoop.fs.PathFilter"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.JobContext"/>
- <doc>
- <![CDATA[Get a PathFilter instance of the filter set for the input paths.
- @return the PathFilter instance set for the job, NULL if none has been set.]]>
- </doc>
- </method>
- <method name="listStatus" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.JobContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[List input directories.
- Subclasses may override to, e.g., select only files matching a regular
- expression.
-
- @param job the job to list input paths for
- @return array of FileStatus objects
- @throws IOException if zero items.]]>
- </doc>
- </method>
- <method name="makeSplit" return="org.apache.hadoop.mapreduce.lib.input.FileSplit"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="file" type="org.apache.hadoop.fs.Path"/>
- <param name="start" type="long"/>
- <param name="length" type="long"/>
- <param name="hosts" type="java.lang.String[]"/>
- <doc>
- <![CDATA[A factory that makes the split for this class. It can be overridden
- by sub-classes to make sub-types]]>
- </doc>
- </method>
- <method name="getSplits" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.JobContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Generate the list of files and make them into FileSplits.
- @param job the job context
- @throws IOException]]>
- </doc>
- </method>
- <method name="computeSplitSize" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="blockSize" type="long"/>
- <param name="minSize" type="long"/>
- <param name="maxSize" type="long"/>
- </method>
- <method name="getBlockIndex" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="blkLocations" type="org.apache.hadoop.fs.BlockLocation[]"/>
- <param name="offset" type="long"/>
- </method>
- <method name="setInputPaths"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <param name="commaSeparatedPaths" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Sets the given comma separated paths as the list of inputs
- for the map-reduce job.
-
- @param job the job
- @param commaSeparatedPaths Comma separated paths to be set as
- the list of inputs for the map-reduce job.]]>
- </doc>
- </method>
- <method name="addInputPaths"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <param name="commaSeparatedPaths" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Add the given comma separated paths to the list of inputs for
- the map-reduce job.
-
- @param job The job to modify
- @param commaSeparatedPaths Comma separated paths to be added to
- the list of inputs for the map-reduce job.]]>
- </doc>
- </method>
- <method name="setInputPaths"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <param name="inputPaths" type="org.apache.hadoop.fs.Path[]"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Set the array of {@link Path}s as the list of inputs
- for the map-reduce job.
-
- @param job The job to modify
- @param inputPaths the {@link Path}s of the input directories/files
- for the map-reduce job.]]>
- </doc>
- </method>
- <method name="addInputPath"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <param name="path" type="org.apache.hadoop.fs.Path"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Add a {@link Path} to the list of inputs for the map-reduce job.
-
- @param job The {@link Job} to modify
- @param path {@link Path} to be added to the list of inputs for
- the map-reduce job.]]>
- </doc>
- </method>
- <method name="getInputPaths" return="org.apache.hadoop.fs.Path[]"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.JobContext"/>
- <doc>
- <![CDATA[Get the list of input {@link Path}s for the map-reduce job.
-
- @param context The job
- @return the list of input {@link Path}s for the map-reduce job.]]>
- </doc>
- </method>
- <field name="COUNTER_GROUP" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="BYTES_READ" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="INPUT_DIR" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="SPLIT_MAXSIZE" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="SPLIT_MINSIZE" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="PATHFILTER_CLASS" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="NUM_INPUT_FILES" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[A base class for file-based {@link InputFormat}s.
-
- <p><code>FileInputFormat</code> is the base class for all file-based
- <code>InputFormat</code>s. This provides a generic implementation of
- {@link #getSplits(JobContext)}.
- Subclasses of <code>FileInputFormat</code> can also override the
- {@link #isSplitable(JobContext, Path)} method to ensure input-files are
- not split-up and are processed as a whole by {@link Mapper}s.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.input.FileInputFormat -->
- <!-- start class org.apache.hadoop.mapreduce.lib.input.FileSplit -->
- <class name="FileSplit" extends="org.apache.hadoop.mapreduce.InputSplit"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.io.Writable"/>
- <constructor name="FileSplit"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <constructor name="FileSplit" type="org.apache.hadoop.fs.Path, long, long, java.lang.String[]"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Constructs a split with host information
- @param file the file name
- @param start the position of the first byte in the file to process
- @param length the number of bytes in the file to process
- @param hosts the list of hosts containing the block, possibly null]]>
- </doc>
- </constructor>
- <method name="getPath" return="org.apache.hadoop.fs.Path"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[The file containing this split's data.]]>
- </doc>
- </method>
- <method name="getStart" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[The position of the first byte in the file to process.]]>
- </doc>
- </method>
- <method name="getLength" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[The number of bytes in the file to process.]]>
- </doc>
- </method>
- <method name="toString" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="out" type="java.io.DataOutput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="readFields"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="in" type="java.io.DataInput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getLocations" return="java.lang.String[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[A section of an input file. Returned by {@link
- InputFormat#getSplits(JobContext)} and passed to
- {@link InputFormat#createRecordReader(InputSplit,TaskAttemptContext)}.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.input.FileSplit -->
- <!-- start class org.apache.hadoop.mapreduce.lib.input.InvalidInputException -->
- <class name="InvalidInputException" extends="java.io.IOException"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="InvalidInputException" type="java.util.List"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Create the exception with the given list.
- @param probs the list of problems to report. this list is not copied.]]>
- </doc>
- </constructor>
- <method name="getProblems" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the complete list of the problems reported.
- @return the list of problems, which must not be modified]]>
- </doc>
- </method>
- <method name="getMessage" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get a summary message of the problems found.
- @return the concatenated messages from all of the problems.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[This class wraps a list of problems with the input, so that the user
- can get a list of problems together instead of finding and fixing them one
- by one.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.input.InvalidInputException -->
- <!-- start class org.apache.hadoop.mapreduce.lib.input.KeyValueLineRecordReader -->
- <class name="KeyValueLineRecordReader" extends="org.apache.hadoop.mapreduce.RecordReader"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="KeyValueLineRecordReader" type="org.apache.hadoop.conf.Configuration"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </constructor>
- <method name="initialize"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="genericSplit" type="org.apache.hadoop.mapreduce.InputSplit"/>
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="findSeparator" return="int"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="utf" type="byte[]"/>
- <param name="start" type="int"/>
- <param name="length" type="int"/>
- <param name="sep" type="byte"/>
- </method>
- <method name="setKeyValue"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="org.apache.hadoop.io.Text"/>
- <param name="value" type="org.apache.hadoop.io.Text"/>
- <param name="line" type="byte[]"/>
- <param name="lineLen" type="int"/>
- <param name="pos" type="int"/>
- </method>
- <method name="nextKeyValue" return="boolean"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Read key/value pair in a line.]]>
- </doc>
- </method>
- <method name="getCurrentKey" return="org.apache.hadoop.io.Text"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getCurrentValue" return="org.apache.hadoop.io.Text"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getProgress" return="float"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <field name="KEY_VALUE_SEPERATOR" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[This class treats a line in the input as a key/value pair separated by a
- separator character. The separator can be specified in config file
- under the attribute name mapreduce.input.keyvaluelinerecordreader.key.value.separator. The default
- separator is the tab character ('\t').]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.input.KeyValueLineRecordReader -->
- <!-- start class org.apache.hadoop.mapreduce.lib.input.KeyValueTextInputFormat -->
- <class name="KeyValueTextInputFormat" extends="org.apache.hadoop.mapreduce.lib.input.FileInputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="KeyValueTextInputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="isSplitable" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.JobContext"/>
- <param name="file" type="org.apache.hadoop.fs.Path"/>
- </method>
- <method name="createRecordReader" return="org.apache.hadoop.mapreduce.RecordReader"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="genericSplit" type="org.apache.hadoop.mapreduce.InputSplit"/>
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[An {@link InputFormat} for plain text files. Files are broken into lines.
- Either line feed or carriage-return are used to signal end of line.
- Each line is divided into key and value parts by a separator byte. If no
- such a byte exists, the key will be the entire line and value will be empty.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.input.KeyValueTextInputFormat -->
- <!-- start class org.apache.hadoop.mapreduce.lib.input.MultipleInputs -->
- <class name="MultipleInputs" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="MultipleInputs"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="addInputPath"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <param name="path" type="org.apache.hadoop.fs.Path"/>
- <param name="inputFormatClass" type="java.lang.Class"/>
- <doc>
- <![CDATA[Add a {@link Path} with a custom {@link InputFormat} to the list of
- inputs for the map-reduce job.
-
- @param job The {@link Job}
- @param path {@link Path} to be added to the list of inputs for the job
- @param inputFormatClass {@link InputFormat} class to use for this path]]>
- </doc>
- </method>
- <method name="addInputPath"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <param name="path" type="org.apache.hadoop.fs.Path"/>
- <param name="inputFormatClass" type="java.lang.Class"/>
- <param name="mapperClass" type="java.lang.Class"/>
- <doc>
- <![CDATA[Add a {@link Path} with a custom {@link InputFormat} and
- {@link Mapper} to the list of inputs for the map-reduce job.
-
- @param job The {@link Job}
- @param path {@link Path} to be added to the list of inputs for the job
- @param inputFormatClass {@link InputFormat} class to use for this path
- @param mapperClass {@link Mapper} class to use for this path]]>
- </doc>
- </method>
- <field name="DIR_FORMATS" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="DIR_MAPPERS" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[This class supports MapReduce jobs that have multiple input paths with
- a different {@link InputFormat} and {@link Mapper} for each path]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.input.MultipleInputs -->
- <!-- start class org.apache.hadoop.mapreduce.lib.input.NLineInputFormat -->
- <class name="NLineInputFormat" extends="org.apache.hadoop.mapreduce.lib.input.FileInputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="NLineInputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="createRecordReader" return="org.apache.hadoop.mapreduce.RecordReader"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="genericSplit" type="org.apache.hadoop.mapreduce.InputSplit"/>
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getSplits" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.JobContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Logically splits the set of input files for the job, splits N lines
- of the input as one split.
-
- @see FileInputFormat#getSplits(JobContext)]]>
- </doc>
- </method>
- <method name="getSplitsForFile" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="status" type="org.apache.hadoop.fs.FileStatus"/>
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <param name="numLinesPerSplit" type="int"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="setNumLinesPerSplit"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <param name="numLines" type="int"/>
- <doc>
- <![CDATA[Set the number of lines per split
- @param job the job to modify
- @param numLines the number of lines per split]]>
- </doc>
- </method>
- <method name="getNumLinesPerSplit" return="int"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.JobContext"/>
- <doc>
- <![CDATA[Get the number of lines per split
- @param job the job
- @return the number of lines per split]]>
- </doc>
- </method>
- <field name="LINES_PER_MAP" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[NLineInputFormat which splits N lines of input as one split.
- In many "pleasantly" parallel applications, each process/mapper
- processes the same input file (s), but with computations are
- controlled by different parameters.(Referred to as "parameter sweeps").
- One way to achieve this, is to specify a set of parameters
- (one set per line) as input in a control file
- (which is the input path to the map-reduce application,
- where as the input dataset is specified
- via a config variable in JobConf.).
-
- The NLineInputFormat can be used in such applications, that splits
- the input file such that by default, one line is fed as
- a value to one map task, and key is the offset.
- i.e. (k,v) is (LongWritable, Text).
- The location hints will span the whole mapred cluster.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.input.NLineInputFormat -->
- <!-- start class org.apache.hadoop.mapreduce.lib.input.SequenceFileAsBinaryInputFormat -->
- <class name="SequenceFileAsBinaryInputFormat" extends="org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="SequenceFileAsBinaryInputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="createRecordReader" return="org.apache.hadoop.mapreduce.RecordReader"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapreduce.InputSplit"/>
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[InputFormat reading keys, values from SequenceFiles in binary (raw)
- format.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.input.SequenceFileAsBinaryInputFormat -->
- <!-- start class org.apache.hadoop.mapreduce.lib.input.SequenceFileAsBinaryInputFormat.SequenceFileAsBinaryRecordReader -->
- <class name="SequenceFileAsBinaryInputFormat.SequenceFileAsBinaryRecordReader" extends="org.apache.hadoop.mapreduce.RecordReader"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="SequenceFileAsBinaryInputFormat.SequenceFileAsBinaryRecordReader"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="initialize"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapreduce.InputSplit"/>
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="getCurrentKey" return="org.apache.hadoop.io.BytesWritable"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="getCurrentValue" return="org.apache.hadoop.io.BytesWritable"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="getKeyClassName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Retrieve the name of the key class for this SequenceFile.
- @see org.apache.hadoop.io.SequenceFile.Reader#getKeyClassName]]>
- </doc>
- </method>
- <method name="getValueClassName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Retrieve the name of the value class for this SequenceFile.
- @see org.apache.hadoop.io.SequenceFile.Reader#getValueClassName]]>
- </doc>
- </method>
- <method name="nextKeyValue" return="boolean"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Read raw bytes from a SequenceFile.]]>
- </doc>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getProgress" return="float"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Return the progress within the input split
- @return 0.0 to 1.0 of the input byte range]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Read records from a SequenceFile as binary (raw) bytes.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.input.SequenceFileAsBinaryInputFormat.SequenceFileAsBinaryRecordReader -->
- <!-- start class org.apache.hadoop.mapreduce.lib.input.SequenceFileAsTextInputFormat -->
- <class name="SequenceFileAsTextInputFormat" extends="org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="SequenceFileAsTextInputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="createRecordReader" return="org.apache.hadoop.mapreduce.RecordReader"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapreduce.InputSplit"/>
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[This class is similar to SequenceFileInputFormat, except it generates
- SequenceFileAsTextRecordReader which converts the input keys and values
- to their String forms by calling toString() method.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.input.SequenceFileAsTextInputFormat -->
- <!-- start class org.apache.hadoop.mapreduce.lib.input.SequenceFileAsTextRecordReader -->
- <class name="SequenceFileAsTextRecordReader" extends="org.apache.hadoop.mapreduce.RecordReader"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="SequenceFileAsTextRecordReader"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </constructor>
- <method name="initialize"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapreduce.InputSplit"/>
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="getCurrentKey" return="org.apache.hadoop.io.Text"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="getCurrentValue" return="org.apache.hadoop.io.Text"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="nextKeyValue" return="boolean"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Read key/value pair in a line.]]>
- </doc>
- </method>
- <method name="getProgress" return="float"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[This class converts the input keys and values to their String forms by
- calling toString() method. This class to SequenceFileAsTextInputFormat
- class is as LineRecordReader class to TextInputFormat class.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.input.SequenceFileAsTextRecordReader -->
- <!-- start class org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFilter -->
- <class name="SequenceFileInputFilter" extends="org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="SequenceFileInputFilter"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="createRecordReader" return="org.apache.hadoop.mapreduce.RecordReader"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapreduce.InputSplit"/>
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Create a record reader for the given split
- @param split file split
- @param context the task-attempt context
- @return RecordReader]]>
- </doc>
- </method>
- <method name="setFilterClass"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <param name="filterClass" type="java.lang.Class"/>
- <doc>
- <![CDATA[set the filter class
-
- @param job The job
- @param filterClass filter class]]>
- </doc>
- </method>
- <field name="LOG" type="org.apache.commons.logging.Log"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="FILTER_CLASS" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="FILTER_FREQUENCY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="FILTER_REGEX" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[A class that allows a map/red job to work on a sample of sequence files.
- The sample is decided by the filter class set by the job.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFilter -->
- <!-- start interface org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFilter.Filter -->
- <interface name="SequenceFileInputFilter.Filter" abstract="true"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.conf.Configurable"/>
- <method name="accept" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="java.lang.Object"/>
- <doc>
- <![CDATA[filter function
- Decide if a record should be filtered or not
- @param key record key
- @return true if a record is accepted; return false otherwise]]>
- </doc>
- </method>
- <doc>
- <![CDATA[filter interface]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFilter.Filter -->
- <!-- start class org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFilter.FilterBase -->
- <class name="SequenceFileInputFilter.FilterBase" extends="java.lang.Object"
- abstract="true"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFilter.Filter"/>
- <constructor name="SequenceFileInputFilter.FilterBase"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getConf" return="org.apache.hadoop.conf.Configuration"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <doc>
- <![CDATA[base class for Filters]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFilter.FilterBase -->
- <!-- start class org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFilter.MD5Filter -->
- <class name="SequenceFileInputFilter.MD5Filter" extends="org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFilter.FilterBase"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="SequenceFileInputFilter.MD5Filter"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setFrequency"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <param name="frequency" type="int"/>
- <doc>
- <![CDATA[set the filtering frequency in configuration
-
- @param conf configuration
- @param frequency filtering frequency]]>
- </doc>
- </method>
- <method name="setConf"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <doc>
- <![CDATA[configure the filter according to configuration
-
- @param conf configuration]]>
- </doc>
- </method>
- <method name="accept" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="java.lang.Object"/>
- <doc>
- <![CDATA[Filtering method
- If MD5(key) % frequency==0, return true; otherwise return false
- @see Filter#accept(Object)]]>
- </doc>
- </method>
- <field name="MD5_LEN" type="int"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[This class returns a set of records by examing the MD5 digest of its
- key against a filtering frequency <i>f</i>. The filtering criteria is
- MD5(key) % f == 0.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFilter.MD5Filter -->
- <!-- start class org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFilter.PercentFilter -->
- <class name="SequenceFileInputFilter.PercentFilter" extends="org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFilter.FilterBase"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="SequenceFileInputFilter.PercentFilter"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setFrequency"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <param name="frequency" type="int"/>
- <doc>
- <![CDATA[set the frequency and stores it in conf
- @param conf configuration
- @param frequency filtering frequencey]]>
- </doc>
- </method>
- <method name="setConf"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <doc>
- <![CDATA[configure the filter by checking the configuration
-
- @param conf configuration]]>
- </doc>
- </method>
- <method name="accept" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="java.lang.Object"/>
- <doc>
- <![CDATA[Filtering method
- If record# % frequency==0, return true; otherwise return false
- @see Filter#accept(Object)]]>
- </doc>
- </method>
- <doc>
- <![CDATA[This class returns a percentage of records
- The percentage is determined by a filtering frequency <i>f</i> using
- the criteria record# % f == 0.
- For example, if the frequency is 10, one out of 10 records is returned.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFilter.PercentFilter -->
- <!-- start class org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFilter.RegexFilter -->
- <class name="SequenceFileInputFilter.RegexFilter" extends="org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFilter.FilterBase"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="SequenceFileInputFilter.RegexFilter"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setPattern"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <param name="regex" type="java.lang.String"/>
- <exception name="PatternSyntaxException" type="java.util.regex.PatternSyntaxException"/>
- <doc>
- <![CDATA[Define the filtering regex and stores it in conf
- @param conf where the regex is set
- @param regex regex used as a filter]]>
- </doc>
- </method>
- <method name="setConf"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <doc>
- <![CDATA[configure the Filter by checking the configuration]]>
- </doc>
- </method>
- <method name="accept" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="java.lang.Object"/>
- <doc>
- <![CDATA[Filtering method
- If key matches the regex, return true; otherwise return false
- @see Filter#accept(Object)]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Records filter by matching key to regex]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFilter.RegexFilter -->
- <!-- start class org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFormat -->
- <class name="SequenceFileInputFormat" extends="org.apache.hadoop.mapreduce.lib.input.FileInputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="SequenceFileInputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="createRecordReader" return="org.apache.hadoop.mapreduce.RecordReader"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapreduce.InputSplit"/>
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getFormatMinSplitSize" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </method>
- <method name="listStatus" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.JobContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[An {@link InputFormat} for {@link SequenceFile}s.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFormat -->
- <!-- start class org.apache.hadoop.mapreduce.lib.input.SequenceFileRecordReader -->
- <class name="SequenceFileRecordReader" extends="org.apache.hadoop.mapreduce.RecordReader"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="SequenceFileRecordReader"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="initialize"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapreduce.InputSplit"/>
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="nextKeyValue" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="getCurrentKey" return="K"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getCurrentValue" return="V"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getProgress" return="float"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Return the progress within the input split
- @return 0.0 to 1.0 of the input byte range]]>
- </doc>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <field name="conf" type="org.apache.hadoop.conf.Configuration"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[An {@link RecordReader} for {@link SequenceFile}s.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.input.SequenceFileRecordReader -->
- <!-- start class org.apache.hadoop.mapreduce.lib.input.TextInputFormat -->
- <class name="TextInputFormat" extends="org.apache.hadoop.mapreduce.lib.input.FileInputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="TextInputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="createRecordReader" return="org.apache.hadoop.mapreduce.RecordReader"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapreduce.InputSplit"/>
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- </method>
- <method name="isSplitable" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.JobContext"/>
- <param name="file" type="org.apache.hadoop.fs.Path"/>
- </method>
- <doc>
- <![CDATA[An {@link InputFormat} for plain text files. Files are broken into lines.
- Either linefeed or carriage-return are used to signal end of line. Keys are
- the position in the file, and values are the line of text..]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.input.TextInputFormat -->
- </package>
- <package name="org.apache.hadoop.mapreduce.lib.jobcontrol">
- <!-- start class org.apache.hadoop.mapreduce.lib.jobcontrol.ControlledJob -->
- <class name="ControlledJob" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="ControlledJob" type="org.apache.hadoop.mapreduce.Job, java.util.List"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Construct a job.
- @param job a mapreduce job to be executed.
- @param dependingJobs an array of jobs the current job depends on]]>
- </doc>
- </constructor>
- <constructor name="ControlledJob" type="org.apache.hadoop.conf.Configuration"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Construct a job.
-
- @param conf mapred job configuration representing a job to be executed.
- @throws IOException]]>
- </doc>
- </constructor>
- <method name="toString" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getJobName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the job name of this job]]>
- </doc>
- </method>
- <method name="setJobName"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobName" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the job name for this job.
- @param jobName the job name]]>
- </doc>
- </method>
- <method name="getJobID" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the job ID of this job assigned by JobControl]]>
- </doc>
- </method>
- <method name="setJobID"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="id" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the job ID for this job.
- @param id the job ID]]>
- </doc>
- </method>
- <method name="getMapredJobID" return="org.apache.hadoop.mapreduce.JobID"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the mapred ID of this job as assigned by the
- mapred framework.]]>
- </doc>
- </method>
- <method name="getJob" return="org.apache.hadoop.mapreduce.Job"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the mapreduce job]]>
- </doc>
- </method>
- <method name="setJob"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <doc>
- <![CDATA[Set the mapreduce job
- @param job the mapreduce job for this job.]]>
- </doc>
- </method>
- <method name="getJobState" return="org.apache.hadoop.mapreduce.lib.jobcontrol.ControlledJob.State"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the state of this job]]>
- </doc>
- </method>
- <method name="setJobState"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="state" type="org.apache.hadoop.mapreduce.lib.jobcontrol.ControlledJob.State"/>
- <doc>
- <![CDATA[Set the state for this job.
- @param state the new state for this job.]]>
- </doc>
- </method>
- <method name="getMessage" return="java.lang.String"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the message of this job]]>
- </doc>
- </method>
- <method name="setMessage"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="message" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the message for this job.
- @param message the message for this job.]]>
- </doc>
- </method>
- <method name="getDependentJobs" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the depending jobs of this job]]>
- </doc>
- </method>
- <method name="addDependingJob" return="boolean"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="dependingJob" type="org.apache.hadoop.mapreduce.lib.jobcontrol.ControlledJob"/>
- <doc>
- <![CDATA[Add a job to this jobs' dependency list.
- Dependent jobs can only be added while a Job
- is waiting to run, not during or afterwards.
-
- @param dependingJob Job that this Job depends on.
- @return <tt>true</tt> if the Job was added.]]>
- </doc>
- </method>
- <method name="isCompleted" return="boolean"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return true if this job is in a complete state]]>
- </doc>
- </method>
- <method name="isReady" return="boolean"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return true if this job is in READY state]]>
- </doc>
- </method>
- <method name="killJob"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="submit"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Submit this job to mapred. The state becomes RUNNING if submission
- is successful, FAILED otherwise.]]>
- </doc>
- </method>
- <field name="CREATE_DIR" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[This class encapsulates a MapReduce job and its dependency. It monitors
- the states of the depending jobs and updates the state of this job.
- A job starts in the WAITING state. If it does not have any depending jobs,
- or all of the depending jobs are in SUCCESS state, then the job state
- will become READY. If any depending jobs fail, the job will fail too.
- When in READY state, the job can be submitted to Hadoop for execution, with
- the state changing into RUNNING state. From RUNNING state, the job
- can get into SUCCESS or FAILED state, depending
- the status of the job execution.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.jobcontrol.ControlledJob -->
- <!-- start class org.apache.hadoop.mapreduce.lib.jobcontrol.ControlledJob.State -->
- <class name="ControlledJob.State" extends="java.lang.Enum"
- abstract="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <method name="values" return="org.apache.hadoop.mapreduce.lib.jobcontrol.ControlledJob.State[]"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="valueOf" return="org.apache.hadoop.mapreduce.lib.jobcontrol.ControlledJob.State"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- </method>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.jobcontrol.ControlledJob.State -->
- <!-- start class org.apache.hadoop.mapreduce.lib.jobcontrol.JobControl -->
- <class name="JobControl" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="java.lang.Runnable"/>
- <constructor name="JobControl" type="java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Construct a job control for a group of jobs.
- @param groupName a name identifying this group]]>
- </doc>
- </constructor>
- <method name="getWaitingJobList" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the jobs in the waiting state]]>
- </doc>
- </method>
- <method name="getRunningJobList" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the jobs in the running state]]>
- </doc>
- </method>
- <method name="getReadyJobsList" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the jobs in the ready state]]>
- </doc>
- </method>
- <method name="getSuccessfulJobList" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the jobs in the success state]]>
- </doc>
- </method>
- <method name="getFailedJobList" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="addJob" return="java.lang.String"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="aJob" type="org.apache.hadoop.mapreduce.lib.jobcontrol.ControlledJob"/>
- <doc>
- <![CDATA[Add a new job.
- @param aJob the new job]]>
- </doc>
- </method>
- <method name="addJobCollection"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobs" type="java.util.Collection"/>
- <doc>
- <![CDATA[Add a collection of jobs
-
- @param jobs]]>
- </doc>
- </method>
- <method name="getThreadState" return="org.apache.hadoop.mapreduce.lib.jobcontrol.JobControl.ThreadState"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return the thread state]]>
- </doc>
- </method>
- <method name="stop"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[set the thread state to STOPPING so that the
- thread will stop when it wakes up.]]>
- </doc>
- </method>
- <method name="suspend"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[suspend the running thread]]>
- </doc>
- </method>
- <method name="resume"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[resume the suspended thread]]>
- </doc>
- </method>
- <method name="allFinished" return="boolean"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="run"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[The main loop for the thread.
- The loop does the following:
- Check the states of the running jobs
- Update the states of waiting jobs
- Submit the jobs in ready state]]>
- </doc>
- </method>
- <doc>
- <![CDATA[This class encapsulates a set of MapReduce jobs and its dependency.
-
- It tracks the states of the jobs by placing them into different tables
- according to their states.
-
- This class provides APIs for the client app to add a job to the group
- and to get the jobs in the group in different states. When a job is
- added, an ID unique to the group is assigned to the job.
-
- This class has a thread that submits jobs when they become ready,
- monitors the states of the running jobs, and updates the states of jobs
- based on the state changes of their depending jobs states. The class
- provides APIs for suspending/resuming the thread, and
- for stopping the thread.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.jobcontrol.JobControl -->
- <!-- start class org.apache.hadoop.mapreduce.lib.jobcontrol.JobControl.ThreadState -->
- <class name="JobControl.ThreadState" extends="java.lang.Enum"
- abstract="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <method name="values" return="org.apache.hadoop.mapreduce.lib.jobcontrol.JobControl.ThreadState[]"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="valueOf" return="org.apache.hadoop.mapreduce.lib.jobcontrol.JobControl.ThreadState"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- </method>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.jobcontrol.JobControl.ThreadState -->
- </package>
- <package name="org.apache.hadoop.mapreduce.lib.join">
- <!-- start class org.apache.hadoop.mapreduce.lib.join.ArrayListBackedIterator -->
- <class name="ArrayListBackedIterator" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.lib.join.ResetableIterator"/>
- <constructor name="ArrayListBackedIterator"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <constructor name="ArrayListBackedIterator" type="java.util.ArrayList"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="hasNext" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="next" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="val" type="X"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="replay" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="val" type="X"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="reset"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="add"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="item" type="X"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="clear"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <doc>
- <![CDATA[This class provides an implementation of ResetableIterator. The
- implementation uses an {@link java.util.ArrayList} to store elements
- added to it, replaying them as requested.
- Prefer {@link StreamBackedIterator}.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.join.ArrayListBackedIterator -->
- <!-- start class org.apache.hadoop.mapreduce.lib.join.ComposableInputFormat -->
- <class name="ComposableInputFormat" extends="org.apache.hadoop.mapreduce.InputFormat"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="ComposableInputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="createRecordReader" return="org.apache.hadoop.mapreduce.lib.join.ComposableRecordReader"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapreduce.InputSplit"/>
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <doc>
- <![CDATA[Refinement of InputFormat requiring implementors to provide
- ComposableRecordReader instead of RecordReader.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.join.ComposableInputFormat -->
- <!-- start class org.apache.hadoop.mapreduce.lib.join.ComposableRecordReader -->
- <class name="ComposableRecordReader" extends="org.apache.hadoop.mapreduce.RecordReader"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="java.lang.Comparable"/>
- <constructor name="ComposableRecordReader"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <doc>
- <![CDATA[Additional operations required of a RecordReader to participate in a join.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.join.ComposableRecordReader -->
- <!-- start class org.apache.hadoop.mapreduce.lib.join.CompositeInputFormat -->
- <class name="CompositeInputFormat" extends="org.apache.hadoop.mapreduce.InputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="CompositeInputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setFormat"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Interpret a given string as a composite expression.
- {@code
- func ::= <ident>([<func>,]*<func>)
- func ::= tbl(<class>,"<path>")
- class ::= @see java.lang.Class#forName(java.lang.String)
- path ::= @see org.apache.hadoop.fs.Path#Path(java.lang.String)
- }
- Reads expression from the <tt>mapreduce.join.expr</tt> property and
- user-supplied join types from <tt>mapreduce.join.define.<ident></tt>
- types. Paths supplied to <tt>tbl</tt> are given as input paths to the
- InputFormat class listed.
- @see #compose(java.lang.String, java.lang.Class, java.lang.String...)]]>
- </doc>
- </method>
- <method name="addDefaults"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Adds the default set of identifiers to the parser.]]>
- </doc>
- </method>
- <method name="getSplits" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.JobContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Build a CompositeInputSplit from the child InputFormats by assigning the
- ith split from each child to the ith composite split.]]>
- </doc>
- </method>
- <method name="createRecordReader" return="org.apache.hadoop.mapreduce.RecordReader"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapreduce.InputSplit"/>
- <param name="taskContext" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Construct a CompositeRecordReader for the children of this InputFormat
- as defined in the init expression.
- The outermost join need only be composable, not necessarily a composite.
- Mandating TupleWritable isn't strictly correct.]]>
- </doc>
- </method>
- <method name="compose" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="inf" type="java.lang.Class"/>
- <param name="path" type="java.lang.String"/>
- <doc>
- <![CDATA[Convenience method for constructing composite formats.
- Given InputFormat class (inf), path (p) return:
- {@code tbl(<inf>, <p>) }]]>
- </doc>
- </method>
- <method name="compose" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="op" type="java.lang.String"/>
- <param name="inf" type="java.lang.Class"/>
- <param name="path" type="java.lang.String[]"/>
- <doc>
- <![CDATA[Convenience method for constructing composite formats.
- Given operation (op), Object class (inf), set of paths (p) return:
- {@code <op>(tbl(<inf>,<p1>),tbl(<inf>,<p2>),...,tbl(<inf>,<pn>)) }]]>
- </doc>
- </method>
- <method name="compose" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="op" type="java.lang.String"/>
- <param name="inf" type="java.lang.Class"/>
- <param name="path" type="org.apache.hadoop.fs.Path[]"/>
- <doc>
- <![CDATA[Convenience method for constructing composite formats.
- Given operation (op), Object class (inf), set of paths (p) return:
- {@code <op>(tbl(<inf>,<p1>),tbl(<inf>,<p2>),...,tbl(<inf>,<pn>)) }]]>
- </doc>
- </method>
- <field name="JOIN_EXPR" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="JOIN_COMPARATOR" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[An InputFormat capable of performing joins over a set of data sources sorted
- and partitioned the same way.
- @see #setFormat
- A user may define new join types by setting the property
- <tt>mapreduce.join.define.<ident></tt> to a classname.
- In the expression <tt>mapreduce.join.expr</tt>, the identifier will be
- assumed to be a ComposableRecordReader.
- <tt>mapreduce.join.keycomparator</tt> can be a classname used to compare
- keys in the join.
- @see JoinRecordReader
- @see MultiFilterRecordReader]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.join.CompositeInputFormat -->
- <!-- start class org.apache.hadoop.mapreduce.lib.join.CompositeInputSplit -->
- <class name="CompositeInputSplit" extends="org.apache.hadoop.mapreduce.InputSplit"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.io.Writable"/>
- <constructor name="CompositeInputSplit"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <constructor name="CompositeInputSplit" type="int"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="add"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="s" type="org.apache.hadoop.mapreduce.InputSplit"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Add an InputSplit to this collection.
- @throws IOException If capacity was not specified during construction
- or if capacity has been reached.]]>
- </doc>
- </method>
- <method name="get" return="org.apache.hadoop.mapreduce.InputSplit"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="i" type="int"/>
- <doc>
- <![CDATA[Get ith child InputSplit.]]>
- </doc>
- </method>
- <method name="getLength" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Return the aggregate length of all child InputSplits currently added.]]>
- </doc>
- </method>
- <method name="getLength" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="i" type="int"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Get the length of ith child InputSplit.]]>
- </doc>
- </method>
- <method name="getLocations" return="java.lang.String[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Collect a set of hosts from all child InputSplits.]]>
- </doc>
- </method>
- <method name="getLocation" return="java.lang.String[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="i" type="int"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[getLocations from ith InputSplit.]]>
- </doc>
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="out" type="java.io.DataOutput"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Write splits in the following format.
- {@code
- <count><class1><class2>...<classn><split1><split2>...<splitn>
- }]]>
- </doc>
- </method>
- <method name="readFields"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="in" type="java.io.DataInput"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[{@inheritDoc}
- @throws IOException If the child InputSplit cannot be read, typically
- for failing access checks.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[This InputSplit contains a set of child InputSplits. Any InputSplit inserted
- into this collection must have a public default constructor.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.join.CompositeInputSplit -->
- <!-- start class org.apache.hadoop.mapreduce.lib.join.CompositeRecordReader -->
- <class name="CompositeRecordReader" extends="org.apache.hadoop.mapreduce.lib.join.ComposableRecordReader"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.conf.Configurable"/>
- <constructor name="CompositeRecordReader" type="int, int, java.lang.Class"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Create a RecordReader with <tt>capacity</tt> children to position
- <tt>id</tt> in the parent reader.
- The id of a root CompositeRecordReader is -1 by convention, but relying
- on this is not recommended.]]>
- </doc>
- </constructor>
- <method name="combine" return="boolean"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="srcs" type="java.lang.Object[]"/>
- <param name="value" type="org.apache.hadoop.mapreduce.lib.join.TupleWritable"/>
- </method>
- <method name="initialize"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapreduce.InputSplit"/>
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="id" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Return the position in the collector this class occupies.]]>
- </doc>
- </method>
- <method name="setConf"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <method name="getConf" return="org.apache.hadoop.conf.Configuration"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <method name="getRecordReaderQueue" return="java.util.PriorityQueue"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Return sorted list of RecordReaders for this composite.]]>
- </doc>
- </method>
- <method name="getComparator" return="org.apache.hadoop.io.WritableComparator"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Return comparator defining the ordering for RecordReaders in this
- composite.]]>
- </doc>
- </method>
- <method name="add"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="rr" type="org.apache.hadoop.mapreduce.lib.join.ComposableRecordReader"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Add a RecordReader to this collection.
- The id() of a RecordReader determines where in the Tuple its
- entry will appear. Adding RecordReaders with the same id has
- undefined behavior.]]>
- </doc>
- </method>
- <method name="key" return="K"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Return the key for the current join or the value at the top of the
- RecordReader heap.]]>
- </doc>
- </method>
- <method name="key"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Clone the key at the top of this RR into the given object.]]>
- </doc>
- </method>
- <method name="getCurrentKey" return="K"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="hasNext" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Return true if it is possible that this could emit more values.]]>
- </doc>
- </method>
- <method name="skip"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Pass skip key to child RRs.]]>
- </doc>
- </method>
- <method name="getDelegate" return="org.apache.hadoop.mapreduce.lib.join.ResetableIterator"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Obtain an iterator over the child RRs apropos of the value type
- ultimately emitted from this join.]]>
- </doc>
- </method>
- <method name="accept"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jc" type="org.apache.hadoop.mapreduce.lib.join.CompositeRecordReader.JoinCollector"/>
- <param name="key" type="K"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[If key provided matches that of this Composite, give JoinCollector
- iterator over values it may emit.]]>
- </doc>
- </method>
- <method name="fillJoinCollector"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="iterkey" type="K"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[For all child RRs offering the key provided, obtain an iterator
- at that position in the JoinCollector.]]>
- </doc>
- </method>
- <method name="compareTo" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="other" type="org.apache.hadoop.mapreduce.lib.join.ComposableRecordReader"/>
- <doc>
- <![CDATA[Implement Comparable contract (compare key of join or head of heap
- with that of another).]]>
- </doc>
- </method>
- <method name="createKey" return="K"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Create a new key common to all child RRs.
- @throws ClassCastException if key classes differ.]]>
- </doc>
- </method>
- <method name="createTupleWritable" return="org.apache.hadoop.mapreduce.lib.join.TupleWritable"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Create a value to be used internally for joins.]]>
- </doc>
- </method>
- <method name="getCurrentValue" return="X"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Close all child RRs.]]>
- </doc>
- </method>
- <method name="getProgress" return="float"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Report progress as the minimum of all child RR progress.]]>
- </doc>
- </method>
- <field name="conf" type="org.apache.hadoop.conf.Configuration"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="keyclass" type="java.lang.Class"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="jc" type="org.apache.hadoop.mapreduce.lib.join.CompositeRecordReader.JoinCollector"
- transient="false" volatile="false"
- static="false" final="true" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="kids" type="org.apache.hadoop.mapreduce.lib.join.ComposableRecordReader[]"
- transient="false" volatile="false"
- static="false" final="true" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="key" type="K"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="value" type="X"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[A RecordReader that can effect joins of RecordReaders sharing a common key
- type and partitioning.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.join.CompositeRecordReader -->
- <!-- start class org.apache.hadoop.mapreduce.lib.join.CompositeRecordReader.JoinCollector -->
- <class name="CompositeRecordReader.JoinCollector" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="CompositeRecordReader.JoinCollector" type="int"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Construct a collector capable of handling the specified number of
- children.]]>
- </doc>
- </constructor>
- <method name="add"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="id" type="int"/>
- <param name="i" type="org.apache.hadoop.mapreduce.lib.join.ResetableIterator"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Register a given iterator at position id.]]>
- </doc>
- </method>
- <method name="key" return="K"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Return the key associated with this collection.]]>
- </doc>
- </method>
- <method name="reset"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <doc>
- <![CDATA[Codify the contents of the collector to be iterated over.
- When this is called, all RecordReaders registered for this
- key should have added ResetableIterators.]]>
- </doc>
- </method>
- <method name="clear"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Clear all state information.]]>
- </doc>
- </method>
- <method name="hasNext" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns false if exhausted or if reset(K) has not been called.]]>
- </doc>
- </method>
- <method name="next" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="val" type="org.apache.hadoop.mapreduce.lib.join.TupleWritable"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Populate Tuple from iterators.
- It should be the case that, given iterators i_1...i_n over values from
- sources s_1...s_n sharing key k, repeated calls to next should yield
- I x I.]]>
- </doc>
- </method>
- <method name="replay" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="val" type="org.apache.hadoop.mapreduce.lib.join.TupleWritable"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Replay the last Tuple emitted.]]>
- </doc>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Close all child iterators.]]>
- </doc>
- </method>
- <method name="flush" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="value" type="org.apache.hadoop.mapreduce.lib.join.TupleWritable"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Write the next value into key, value as accepted by the operation
- associated with this set of RecordReaders.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Collector for join values.
- This accumulates values for a given key from the child RecordReaders. If
- one or more child RR contain duplicate keys, this will emit the cross
- product of the associated values until exhausted.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.join.CompositeRecordReader.JoinCollector -->
- <!-- start class org.apache.hadoop.mapreduce.lib.join.InnerJoinRecordReader -->
- <class name="InnerJoinRecordReader" extends="org.apache.hadoop.mapreduce.lib.join.JoinRecordReader"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <method name="combine" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="srcs" type="java.lang.Object[]"/>
- <param name="dst" type="org.apache.hadoop.mapreduce.lib.join.TupleWritable"/>
- <doc>
- <![CDATA[Return true iff the tuple is full (all data sources contain this key).]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Full inner join.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.join.InnerJoinRecordReader -->
- <!-- start class org.apache.hadoop.mapreduce.lib.join.JoinRecordReader -->
- <class name="JoinRecordReader" extends="org.apache.hadoop.mapreduce.lib.join.CompositeRecordReader"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="JoinRecordReader" type="int, org.apache.hadoop.conf.Configuration, int, java.lang.Class"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </constructor>
- <method name="nextKeyValue" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Emit the next set of key, value pairs as defined by the child
- RecordReaders and operation associated with this composite RR.]]>
- </doc>
- </method>
- <method name="createValue" return="org.apache.hadoop.mapreduce.lib.join.TupleWritable"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getDelegate" return="org.apache.hadoop.mapreduce.lib.join.ResetableIterator"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Return an iterator wrapping the JoinCollector.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Base class for Composite joins returning Tuples of arbitrary Writables.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.join.JoinRecordReader -->
- <!-- start class org.apache.hadoop.mapreduce.lib.join.JoinRecordReader.JoinDelegationIterator -->
- <class name="JoinRecordReader.JoinDelegationIterator" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.lib.join.ResetableIterator"/>
- <constructor name="JoinRecordReader.JoinDelegationIterator"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </constructor>
- <method name="hasNext" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="next" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="val" type="org.apache.hadoop.mapreduce.lib.join.TupleWritable"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="replay" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="val" type="org.apache.hadoop.mapreduce.lib.join.TupleWritable"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="reset"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="add"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="item" type="org.apache.hadoop.mapreduce.lib.join.TupleWritable"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="clear"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <doc>
- <![CDATA[Since the JoinCollector is effecting our operation, we need only
- provide an iterator proxy wrapping its operation.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.join.JoinRecordReader.JoinDelegationIterator -->
- <!-- start class org.apache.hadoop.mapreduce.lib.join.MultiFilterRecordReader -->
- <class name="MultiFilterRecordReader" extends="org.apache.hadoop.mapreduce.lib.join.CompositeRecordReader"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="MultiFilterRecordReader" type="int, org.apache.hadoop.conf.Configuration, int, java.lang.Class"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </constructor>
- <method name="emit" return="V"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="dst" type="org.apache.hadoop.mapreduce.lib.join.TupleWritable"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[For each tuple emitted, return a value (typically one of the values
- in the tuple).
- Modifying the Writables in the tuple is permitted and unlikely to affect
- join behavior in most cases, but it is not recommended. It's safer to
- clone first.]]>
- </doc>
- </method>
- <method name="combine" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="srcs" type="java.lang.Object[]"/>
- <param name="dst" type="org.apache.hadoop.mapreduce.lib.join.TupleWritable"/>
- <doc>
- <![CDATA[Default implementation offers {@link #emit} every Tuple from the
- collector (the outer join of child RRs).]]>
- </doc>
- </method>
- <method name="nextKeyValue" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <method name="initialize"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapreduce.InputSplit"/>
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="getDelegate" return="org.apache.hadoop.mapreduce.lib.join.ResetableIterator"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Return an iterator returning a single value from the tuple.
- @see MultiFilterDelegationIterator]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Base class for Composite join returning values derived from multiple
- sources, but generally not tuples.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.join.MultiFilterRecordReader -->
- <!-- start class org.apache.hadoop.mapreduce.lib.join.MultiFilterRecordReader.MultiFilterDelegationIterator -->
- <class name="MultiFilterRecordReader.MultiFilterDelegationIterator" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.lib.join.ResetableIterator"/>
- <constructor name="MultiFilterRecordReader.MultiFilterDelegationIterator"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </constructor>
- <method name="hasNext" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="next" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="val" type="V"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="replay" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="val" type="V"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="reset"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="add"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="item" type="V"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="clear"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <doc>
- <![CDATA[Proxy the JoinCollector, but include callback to emit.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.join.MultiFilterRecordReader.MultiFilterDelegationIterator -->
- <!-- start class org.apache.hadoop.mapreduce.lib.join.OuterJoinRecordReader -->
- <class name="OuterJoinRecordReader" extends="org.apache.hadoop.mapreduce.lib.join.JoinRecordReader"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <method name="combine" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="srcs" type="java.lang.Object[]"/>
- <param name="dst" type="org.apache.hadoop.mapreduce.lib.join.TupleWritable"/>
- <doc>
- <![CDATA[Emit everything from the collector.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Full outer join.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.join.OuterJoinRecordReader -->
- <!-- start class org.apache.hadoop.mapreduce.lib.join.OverrideRecordReader -->
- <class name="OverrideRecordReader" extends="org.apache.hadoop.mapreduce.lib.join.MultiFilterRecordReader"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <method name="emit" return="V"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="dst" type="org.apache.hadoop.mapreduce.lib.join.TupleWritable"/>
- <doc>
- <![CDATA[Emit the value with the highest position in the tuple.]]>
- </doc>
- </method>
- <method name="createValue" return="V"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="fillJoinCollector"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="iterkey" type="K"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Instead of filling the JoinCollector with iterators from all
- data sources, fill only the rightmost for this key.
- This not only saves space by discarding the other sources, but
- it also emits the number of key-value pairs in the preferred
- RecordReader instead of repeating that stream n times, where
- n is the cardinality of the cross product of the discarded
- streams for the given key.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Prefer the "rightmost" data source for this key.
- For example, <tt>override(S1,S2,S3)</tt> will prefer values
- from S3 over S2, and values from S2 over S1 for all keys
- emitted from all sources.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.join.OverrideRecordReader -->
- <!-- start class org.apache.hadoop.mapreduce.lib.join.Parser -->
- <class name="Parser" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="Parser"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <doc>
- <![CDATA[Very simple shift-reduce parser for join expressions.
- This should be sufficient for the user extension permitted now, but ought to
- be replaced with a parser generator if more complex grammars are supported.
- In particular, this "shift-reduce" parser has no states. Each set
- of formals requires a different internal node type, which is responsible for
- interpreting the list of tokens it receives. This is sufficient for the
- current grammar, but it has several annoying properties that might inhibit
- extension. In particular, parenthesis are always function calls; an
- algebraic or filter grammar would not only require a node type, but must
- also work around the internals of this parser.
- For most other cases, adding classes to the hierarchy- particularly by
- extending JoinRecordReader and MultiFilterRecordReader- is fairly
- straightforward. One need only override the relevant method(s) (usually only
- {@link CompositeRecordReader#combine}) and include a property to map its
- value to an identifier in the parser.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.join.Parser -->
- <!-- start class org.apache.hadoop.mapreduce.lib.join.Parser.Node -->
- <class name="Parser.Node" extends="org.apache.hadoop.mapreduce.lib.join.ComposableInputFormat"
- abstract="true"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="Parser.Node" type="java.lang.String"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </constructor>
- <method name="addIdentifier"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="ident" type="java.lang.String"/>
- <param name="mcstrSig" type="java.lang.Class[]"/>
- <param name="nodetype" type="java.lang.Class"/>
- <param name="cl" type="java.lang.Class"/>
- <exception name="NoSuchMethodException" type="java.lang.NoSuchMethodException"/>
- <doc>
- <![CDATA[For a given identifier, add a mapping to the nodetype for the parse
- tree and to the ComposableRecordReader to be created, including the
- formals required to invoke the constructor.
- The nodetype and constructor signature should be filled in from the
- child node.]]>
- </doc>
- </method>
- <method name="setID"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="id" type="int"/>
- </method>
- <method name="setKeyComparator"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="cmpcl" type="java.lang.Class"/>
- </method>
- <field name="rrCstrMap" type="java.util.Map"
- transient="false" volatile="false"
- static="true" final="true" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="id" type="int"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="ident" type="java.lang.String"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="cmpcl" type="java.lang.Class"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.join.Parser.Node -->
- <!-- start class org.apache.hadoop.mapreduce.lib.join.Parser.NodeToken -->
- <class name="Parser.NodeToken" extends="org.apache.hadoop.mapreduce.lib.join.Parser.Token"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <method name="getNode" return="org.apache.hadoop.mapreduce.lib.join.Parser.Node"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.join.Parser.NodeToken -->
- <!-- start class org.apache.hadoop.mapreduce.lib.join.Parser.NumToken -->
- <class name="Parser.NumToken" extends="org.apache.hadoop.mapreduce.lib.join.Parser.Token"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="Parser.NumToken" type="double"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getNum" return="double"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.join.Parser.NumToken -->
- <!-- start class org.apache.hadoop.mapreduce.lib.join.Parser.StrToken -->
- <class name="Parser.StrToken" extends="org.apache.hadoop.mapreduce.lib.join.Parser.Token"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="Parser.StrToken" type="org.apache.hadoop.mapreduce.lib.join.Parser.TType, java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getStr" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.join.Parser.StrToken -->
- <!-- start class org.apache.hadoop.mapreduce.lib.join.Parser.Token -->
- <class name="Parser.Token" extends="java.lang.Object"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <method name="getType" return="org.apache.hadoop.mapreduce.lib.join.Parser.TType"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getNode" return="org.apache.hadoop.mapreduce.lib.join.Parser.Node"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getNum" return="double"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getStr" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[Tagged-union type for tokens from the join expression.
- @see Parser.TType]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.join.Parser.Token -->
- <!-- start class org.apache.hadoop.mapreduce.lib.join.Parser.TType -->
- <class name="Parser.TType" extends="java.lang.Enum"
- abstract="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <method name="values" return="org.apache.hadoop.mapreduce.lib.join.Parser.TType[]"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="valueOf" return="org.apache.hadoop.mapreduce.lib.join.Parser.TType"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- </method>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.join.Parser.TType -->
- <!-- start interface org.apache.hadoop.mapreduce.lib.join.ResetableIterator -->
- <interface name="ResetableIterator" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <method name="hasNext" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[True if a call to next may return a value. This is permitted false
- positives, but not false negatives.]]>
- </doc>
- </method>
- <method name="next" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="val" type="T"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Assign next value to actual.
- It is required that elements added to a ResetableIterator be returned in
- the same order after a call to {@link #reset} (FIFO).
- Note that a call to this may fail for nested joins (i.e. more elements
- available, but none satisfying the constraints of the join)]]>
- </doc>
- </method>
- <method name="replay" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="val" type="T"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Assign last value returned to actual.]]>
- </doc>
- </method>
- <method name="reset"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Set iterator to return to the start of its range. Must be called after
- calling {@link #add} to avoid a ConcurrentModificationException.]]>
- </doc>
- </method>
- <method name="add"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="item" type="T"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Add an element to the collection of elements to iterate over.]]>
- </doc>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Close datasources and release resources. Calling methods on the iterator
- after calling close has undefined behavior.]]>
- </doc>
- </method>
- <method name="clear"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Close datasources, but do not release internal resources. Calling this
- method should permit the object to be reused with a different datasource.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[This defines an interface to a stateful Iterator that can replay elements
- added to it directly.
- Note that this does not extend {@link java.util.Iterator}.]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapreduce.lib.join.ResetableIterator -->
- <!-- start class org.apache.hadoop.mapreduce.lib.join.ResetableIterator.EMPTY -->
- <class name="ResetableIterator.EMPTY" extends="java.lang.Object"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.lib.join.ResetableIterator"/>
- <constructor name="ResetableIterator.EMPTY"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="hasNext" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="reset"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="clear"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="next" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="val" type="U"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="replay" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="val" type="U"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="add"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="item" type="U"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.join.ResetableIterator.EMPTY -->
- <!-- start class org.apache.hadoop.mapreduce.lib.join.StreamBackedIterator -->
- <class name="StreamBackedIterator" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.lib.join.ResetableIterator"/>
- <constructor name="StreamBackedIterator"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="hasNext" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="next" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="val" type="X"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="replay" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="val" type="X"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="reset"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="add"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="item" type="X"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="clear"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <doc>
- <![CDATA[This class provides an implementation of ResetableIterator. This
- implementation uses a byte array to store elements added to it.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.join.StreamBackedIterator -->
- <!-- start class org.apache.hadoop.mapreduce.lib.join.TupleWritable -->
- <class name="TupleWritable" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.io.Writable"/>
- <implements name="java.lang.Iterable"/>
- <constructor name="TupleWritable"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Create an empty tuple with no allocated storage for writables.]]>
- </doc>
- </constructor>
- <constructor name="TupleWritable" type="org.apache.hadoop.io.Writable[]"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Initialize tuple with storage; unknown whether any of them contain
- "written" values.]]>
- </doc>
- </constructor>
- <method name="has" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="i" type="int"/>
- <doc>
- <![CDATA[Return true if tuple has an element at the position provided.]]>
- </doc>
- </method>
- <method name="get" return="org.apache.hadoop.io.Writable"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="i" type="int"/>
- <doc>
- <![CDATA[Get ith Writable from Tuple.]]>
- </doc>
- </method>
- <method name="size" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[The number of children in this Tuple.]]>
- </doc>
- </method>
- <method name="equals" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="other" type="java.lang.Object"/>
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <method name="hashCode" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="iterator" return="java.util.Iterator"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Return an iterator over the elements in this tuple.
- Note that this doesn't flatten the tuple; one may receive tuples
- from this iterator.]]>
- </doc>
- </method>
- <method name="toString" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Convert Tuple to String as in the following.
- <tt>[<child1>,<child2>,...,<childn>]</tt>]]>
- </doc>
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="out" type="java.io.DataOutput"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Writes each Writable to <code>out</code>.
- TupleWritable format:
- {@code
- <count><type1><type2>...<typen><obj1><obj2>...<objn>
- }]]>
- </doc>
- </method>
- <method name="readFields"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="in" type="java.io.DataInput"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <field name="written" type="java.util.BitSet"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[Writable type storing multiple {@link org.apache.hadoop.io.Writable}s.
- This is *not* a general-purpose tuple type. In almost all cases, users are
- encouraged to implement their own serializable types, which can perform
- better validation and provide more efficient encodings than this class is
- capable. TupleWritable relies on the join framework for type safety and
- assumes its instances will rarely be persisted, assumptions not only
- incompatible with, but contrary to the general case.
- @see org.apache.hadoop.io.Writable]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.join.TupleWritable -->
- <!-- start class org.apache.hadoop.mapreduce.lib.join.WrappedRecordReader -->
- <class name="WrappedRecordReader" extends="org.apache.hadoop.mapreduce.lib.join.ComposableRecordReader"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="WrappedRecordReader" type="int"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </constructor>
- <method name="initialize"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapreduce.InputSplit"/>
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="createKey" return="K"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Request new key from proxied RR.]]>
- </doc>
- </method>
- <method name="createValue" return="U"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="id" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <method name="key" return="K"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Return the key at the head of this RR.]]>
- </doc>
- </method>
- <method name="key"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="qkey" type="K"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Clone the key at the head of this RR into the object supplied.]]>
- </doc>
- </method>
- <method name="hasNext" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Return true if the RR- including the k,v pair stored in this object-
- is exhausted.]]>
- </doc>
- </method>
- <method name="skip"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Skip key-value pairs with keys less than or equal to the key provided.]]>
- </doc>
- </method>
- <method name="accept"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="i" type="org.apache.hadoop.mapreduce.lib.join.CompositeRecordReader.JoinCollector"/>
- <param name="key" type="K"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Add an iterator to the collector at the position occupied by this
- RecordReader over the values in this stream paired with the key
- provided (ie register a stream of values from this source matching K
- with a collector).]]>
- </doc>
- </method>
- <method name="nextKeyValue" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Read the next k,v pair into the head of this object; return true iff
- the RR and this are exhausted.]]>
- </doc>
- </method>
- <method name="getCurrentKey" return="K"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Get current key]]>
- </doc>
- </method>
- <method name="getCurrentValue" return="U"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Get current value]]>
- </doc>
- </method>
- <method name="getProgress" return="float"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Request progress from proxied RR.]]>
- </doc>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Forward close request to proxied RR.]]>
- </doc>
- </method>
- <method name="compareTo" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="other" type="org.apache.hadoop.mapreduce.lib.join.ComposableRecordReader"/>
- <doc>
- <![CDATA[Implement Comparable contract (compare key at head of proxied RR
- with that of another).]]>
- </doc>
- </method>
- <method name="equals" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="other" type="java.lang.Object"/>
- <doc>
- <![CDATA[Return true iff compareTo(other) retn true.]]>
- </doc>
- </method>
- <method name="hashCode" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <field name="empty" type="boolean"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="cmp" type="org.apache.hadoop.io.WritableComparator"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[Proxy class for a RecordReader participating in the join framework.
-
- This class keeps track of the "head" key-value pair for the
- provided RecordReader and keeps a store of values matching a key when
- this source is participating in a join.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.join.WrappedRecordReader -->
- </package>
- <package name="org.apache.hadoop.mapreduce.lib.map">
- <!-- start class org.apache.hadoop.mapreduce.lib.map.InverseMapper -->
- <class name="InverseMapper" extends="org.apache.hadoop.mapreduce.Mapper"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="InverseMapper"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="map"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <param name="value" type="V"/>
- <param name="context" type="org.apache.hadoop.mapreduce.Mapper.Context"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[The inverse function. Input keys and values are swapped.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[A {@link Mapper} that swaps keys and values.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.map.InverseMapper -->
- <!-- start class org.apache.hadoop.mapreduce.lib.map.MultithreadedMapper -->
- <class name="MultithreadedMapper" extends="org.apache.hadoop.mapreduce.Mapper"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="MultithreadedMapper"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getNumberOfThreads" return="int"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.JobContext"/>
- <doc>
- <![CDATA[The number of threads in the thread pool that will run the map function.
- @param job the job
- @return the number of threads]]>
- </doc>
- </method>
- <method name="setNumberOfThreads"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <param name="threads" type="int"/>
- <doc>
- <![CDATA[Set the number of threads in the pool for running maps.
- @param job the job to modify
- @param threads the new number of threads]]>
- </doc>
- </method>
- <method name="getMapperClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.JobContext"/>
- <doc>
- <![CDATA[Get the application's mapper class.
- @param <K1> the map's input key type
- @param <V1> the map's input value type
- @param <K2> the map's output key type
- @param <V2> the map's output value type
- @param job the job
- @return the mapper class to run]]>
- </doc>
- </method>
- <method name="setMapperClass"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <param name="cls" type="java.lang.Class"/>
- <doc>
- <![CDATA[Set the application's mapper class.
- @param <K1> the map input key type
- @param <V1> the map input value type
- @param <K2> the map output key type
- @param <V2> the map output value type
- @param job the job to modify
- @param cls the class to use as the mapper]]>
- </doc>
- </method>
- <method name="run"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.Mapper.Context"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Run the application's maps using a thread pool.]]>
- </doc>
- </method>
- <field name="NUM_THREADS" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="MAP_CLASS" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[Multithreaded implementation for @link org.apache.hadoop.mapreduce.Mapper.
- <p>
- It can be used instead of the default implementation,
- @link org.apache.hadoop.mapred.MapRunner, when the Map operation is not CPU
- bound in order to improve throughput.
- <p>
- Mapper implementations using this MapRunnable must be thread-safe.
- <p>
- The Map-Reduce job has to be configured with the mapper to use via
- {@link #setMapperClass(Configuration, Class)} and
- the number of thread the thread-pool can use with the
- {@link #getNumberOfThreads(Configuration) method. The default
- value is 10 threads.
- <p>]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.map.MultithreadedMapper -->
- <!-- start class org.apache.hadoop.mapreduce.lib.map.RegexMapper -->
- <class name="RegexMapper" extends="org.apache.hadoop.mapreduce.Mapper"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="RegexMapper"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setup"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.Mapper.Context"/>
- </method>
- <method name="map"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <param name="value" type="org.apache.hadoop.io.Text"/>
- <param name="context" type="org.apache.hadoop.mapreduce.Mapper.Context"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <field name="PATTERN" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="GROUP" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[A {@link Mapper} that extracts text matching a regular expression.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.map.RegexMapper -->
- <!-- start class org.apache.hadoop.mapreduce.lib.map.TokenCounterMapper -->
- <class name="TokenCounterMapper" extends="org.apache.hadoop.mapreduce.Mapper"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="TokenCounterMapper"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="map"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="java.lang.Object"/>
- <param name="value" type="org.apache.hadoop.io.Text"/>
- <param name="context" type="org.apache.hadoop.mapreduce.Mapper.Context"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <doc>
- <![CDATA[Tokenize the input values and emit each word with a count of 1.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.map.TokenCounterMapper -->
- <!-- start class org.apache.hadoop.mapreduce.lib.map.WrappedMapper -->
- <class name="WrappedMapper" extends="org.apache.hadoop.mapreduce.Mapper"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="WrappedMapper"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getMapContext" return="org.apache.hadoop.mapreduce.Mapper.Context"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="mapContext" type="org.apache.hadoop.mapreduce.MapContext"/>
- <doc>
- <![CDATA[Get a wrapped {@link Mapper.Context} for custom implementations.
- @param mapContext <code>MapContext</code> to be wrapped
- @return a wrapped <code>Mapper.Context</code> for custom implementations]]>
- </doc>
- </method>
- <doc>
- <![CDATA[A {@link Mapper} which wraps a given one to allow custom
- {@link Mapper.Context} implementations.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.map.WrappedMapper -->
- <!-- start class org.apache.hadoop.mapreduce.lib.map.WrappedMapper.Context -->
- <class name="WrappedMapper.Context" extends="org.apache.hadoop.mapreduce.Mapper.Context"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="WrappedMapper.Context" type="org.apache.hadoop.mapreduce.MapContext"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getInputSplit" return="org.apache.hadoop.mapreduce.InputSplit"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the input split for this map.]]>
- </doc>
- </method>
- <method name="getCurrentKey" return="KEYIN"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="getCurrentValue" return="VALUEIN"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="nextKeyValue" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="getCounter" return="org.apache.hadoop.mapreduce.Counter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="counterName" type="java.lang.Enum"/>
- </method>
- <method name="getCounter" return="org.apache.hadoop.mapreduce.Counter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="groupName" type="java.lang.String"/>
- <param name="counterName" type="java.lang.String"/>
- </method>
- <method name="getOutputCommitter" return="org.apache.hadoop.mapreduce.OutputCommitter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="KEYOUT"/>
- <param name="value" type="VALUEOUT"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="getStatus" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getTaskAttemptID" return="org.apache.hadoop.mapreduce.TaskAttemptID"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="setStatus"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="msg" type="java.lang.String"/>
- </method>
- <method name="getArchiveClassPaths" return="org.apache.hadoop.fs.Path[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getArchiveTimestamps" return="java.lang.String[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getCacheArchives" return="java.net.URI[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getCacheFiles" return="java.net.URI[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getCombinerClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="ClassNotFoundException" type="java.lang.ClassNotFoundException"/>
- </method>
- <method name="getConfiguration" return="org.apache.hadoop.conf.Configuration"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getFileClassPaths" return="org.apache.hadoop.fs.Path[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getFileTimestamps" return="java.lang.String[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getGroupingComparator" return="org.apache.hadoop.io.RawComparator"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getInputFormatClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="ClassNotFoundException" type="java.lang.ClassNotFoundException"/>
- </method>
- <method name="getJar" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getJobID" return="org.apache.hadoop.mapreduce.JobID"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getJobName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getJobSetupCleanupNeeded" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getLocalCacheArchives" return="org.apache.hadoop.fs.Path[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getLocalCacheFiles" return="org.apache.hadoop.fs.Path[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getMapOutputKeyClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getMapOutputValueClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getMapperClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="ClassNotFoundException" type="java.lang.ClassNotFoundException"/>
- </method>
- <method name="getMaxMapAttempts" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getMaxReduceAttempts" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getNumReduceTasks" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getOutputFormatClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="ClassNotFoundException" type="java.lang.ClassNotFoundException"/>
- </method>
- <method name="getOutputKeyClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getOutputValueClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getPartitionerClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="ClassNotFoundException" type="java.lang.ClassNotFoundException"/>
- </method>
- <method name="getReducerClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="ClassNotFoundException" type="java.lang.ClassNotFoundException"/>
- </method>
- <method name="getSortComparator" return="org.apache.hadoop.io.RawComparator"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getSymlink" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getWorkingDirectory" return="org.apache.hadoop.fs.Path"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="progress"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getProfileEnabled" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getProfileParams" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getProfileTaskRange" return="org.apache.hadoop.conf.Configuration.IntegerRanges"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="isMap" type="boolean"/>
- </method>
- <method name="getUser" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getCredentials" return="org.apache.hadoop.security.Credentials"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <field name="mapContext" type="org.apache.hadoop.mapreduce.MapContext"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.map.WrappedMapper.Context -->
- </package>
- <package name="org.apache.hadoop.mapreduce.lib.output">
- <!-- start class org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter -->
- <class name="FileOutputCommitter" extends="org.apache.hadoop.mapreduce.OutputCommitter"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="FileOutputCommitter" type="org.apache.hadoop.fs.Path, org.apache.hadoop.mapreduce.TaskAttemptContext"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Create a file output committer
- @param outputPath the job's output path
- @param context the task's context
- @throws IOException]]>
- </doc>
- </constructor>
- <method name="setupJob"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.JobContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Create the temporary directory that is the root of all of the task
- work directories.
- @param context the job's context]]>
- </doc>
- </method>
- <method name="commitJob"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.JobContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Delete the temporary directory, including all of the work directories.
- Create a _SUCCESS file to make it as successful.
- @param context the job's context]]>
- </doc>
- </method>
- <method name="cleanupJob"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.JobContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="abortJob"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.JobContext"/>
- <param name="state" type="org.apache.hadoop.mapreduce.JobStatus.State"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Delete the temporary directory, including all of the work directories.
- @param context the job's context]]>
- </doc>
- </method>
- <method name="setupTask"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[No task setup required.]]>
- </doc>
- </method>
- <method name="commitTask"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Move the files from the work directory to the job output directory
- @param context the task context]]>
- </doc>
- </method>
- <method name="abortTask"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Delete the work directory
- @throws IOException]]>
- </doc>
- </method>
- <method name="needsTaskCommit" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Did this task write any files in the work directory?
- @param context the task's context]]>
- </doc>
- </method>
- <method name="getWorkPath" return="org.apache.hadoop.fs.Path"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get the directory that the task should write results into
- @return the work directory
- @throws IOException]]>
- </doc>
- </method>
- <field name="TEMP_DIR_NAME" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="protected"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Temporary directory name]]>
- </doc>
- </field>
- <field name="SUCCEEDED_FILE_NAME" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[An {@link OutputCommitter} that commits files specified
- in job output directory i.e. ${mapreduce.output.fileoutputformat.outputdir}.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter -->
- <!-- start class org.apache.hadoop.mapreduce.lib.output.FileOutputFormat -->
- <class name="FileOutputFormat" extends="org.apache.hadoop.mapreduce.OutputFormat"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="FileOutputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setCompressOutput"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <param name="compress" type="boolean"/>
- <doc>
- <![CDATA[Set whether the output of the job is compressed.
- @param job the job to modify
- @param compress should the output of the job be compressed?]]>
- </doc>
- </method>
- <method name="getCompressOutput" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.JobContext"/>
- <doc>
- <![CDATA[Is the job output compressed?
- @param job the Job to look in
- @return <code>true</code> if the job output should be compressed,
- <code>false</code> otherwise]]>
- </doc>
- </method>
- <method name="setOutputCompressorClass"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <param name="codecClass" type="java.lang.Class"/>
- <doc>
- <![CDATA[Set the {@link CompressionCodec} to be used to compress job outputs.
- @param job the job to modify
- @param codecClass the {@link CompressionCodec} to be used to
- compress the job outputs]]>
- </doc>
- </method>
- <method name="getOutputCompressorClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.JobContext"/>
- <param name="defaultValue" type="java.lang.Class"/>
- <doc>
- <![CDATA[Get the {@link CompressionCodec} for compressing the job outputs.
- @param job the {@link Job} to look in
- @param defaultValue the {@link CompressionCodec} to return if not set
- @return the {@link CompressionCodec} to be used to compress the
- job outputs
- @throws IllegalArgumentException if the class was specified, but not found]]>
- </doc>
- </method>
- <method name="getRecordWriter" return="org.apache.hadoop.mapreduce.RecordWriter"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="checkOutputSpecs"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.JobContext"/>
- <exception name="FileAlreadyExistsException" type="org.apache.hadoop.fs.FileAlreadyExistsException"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="setOutputPath"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <param name="outputDir" type="org.apache.hadoop.fs.Path"/>
- <doc>
- <![CDATA[Set the {@link Path} of the output directory for the map-reduce job.
- @param job The job to modify
- @param outputDir the {@link Path} of the output directory for
- the map-reduce job.]]>
- </doc>
- </method>
- <method name="getOutputPath" return="org.apache.hadoop.fs.Path"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.JobContext"/>
- <doc>
- <![CDATA[Get the {@link Path} to the output directory for the map-reduce job.
-
- @return the {@link Path} to the output directory for the map-reduce job.
- @see FileOutputFormat#getWorkOutputPath(TaskInputOutputContext)]]>
- </doc>
- </method>
- <method name="getWorkOutputPath" return="org.apache.hadoop.fs.Path"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.TaskInputOutputContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Get the {@link Path} to the task's temporary output directory
- for the map-reduce job
-
- <h4 id="SideEffectFiles">Tasks' Side-Effect Files</h4>
-
- <p>Some applications need to create/write-to side-files, which differ from
- the actual job-outputs.
-
- <p>In such cases there could be issues with 2 instances of the same TIP
- (running simultaneously e.g. speculative tasks) trying to open/write-to the
- same file (path) on HDFS. Hence the application-writer will have to pick
- unique names per task-attempt (e.g. using the attemptid, say
- <tt>attempt_200709221812_0001_m_000000_0</tt>), not just per TIP.</p>
-
- <p>To get around this the Map-Reduce framework helps the application-writer
- out by maintaining a special
- <tt>${mapreduce.output.fileoutputformat.outputdir}/_temporary/_${taskid}</tt>
- sub-directory for each task-attempt on HDFS where the output of the
- task-attempt goes. On successful completion of the task-attempt the files
- in the <tt>${mapreduce.output.fileoutputformat.outputdir}/_temporary/_${taskid}</tt> (only)
- are <i>promoted</i> to <tt>${mapreduce.output.fileoutputformat.outputdir}</tt>. Of course, the
- framework discards the sub-directory of unsuccessful task-attempts. This
- is completely transparent to the application.</p>
-
- <p>The application-writer can take advantage of this by creating any
- side-files required in a work directory during execution
- of his task i.e. via
- {@link #getWorkOutputPath(TaskInputOutputContext)}, and
- the framework will move them out similarly - thus she doesn't have to pick
- unique paths per task-attempt.</p>
-
- <p>The entire discussion holds true for maps of jobs with
- reducer=NONE (i.e. 0 reduces) since output of the map, in that case,
- goes directly to HDFS.</p>
-
- @return the {@link Path} to the task's temporary output directory
- for the map-reduce job.]]>
- </doc>
- </method>
- <method name="getPathForWorkFile" return="org.apache.hadoop.fs.Path"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.TaskInputOutputContext"/>
- <param name="name" type="java.lang.String"/>
- <param name="extension" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Helper function to generate a {@link Path} for a file that is unique for
- the task within the job output directory.
- <p>The path can be used to create custom files from within the map and
- reduce tasks. The path name will be unique for each task. The path parent
- will be the job output directory.</p>ls
- <p>This method uses the {@link #getUniqueFile} method to make the file name
- unique for the task.</p>
- @param context the context for the task.
- @param name the name for the file.
- @param extension the extension for the file
- @return a unique path accross all tasks of the job.]]>
- </doc>
- </method>
- <method name="getUniqueFile" return="java.lang.String"
- abstract="false" native="false" synchronized="true"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <param name="name" type="java.lang.String"/>
- <param name="extension" type="java.lang.String"/>
- <doc>
- <![CDATA[Generate a unique filename, based on the task id, name, and extension
- @param context the task that is calling this
- @param name the base filename
- @param extension the filename extension
- @return a string like $name-[mrsct]-$id$extension]]>
- </doc>
- </method>
- <method name="getDefaultWorkFile" return="org.apache.hadoop.fs.Path"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <param name="extension" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get the default path and filename for the output format.
- @param context the task context
- @param extension an extension to add to the filename
- @return a full path $output/_temporary/$taskid/part-[mr]-$id
- @throws IOException]]>
- </doc>
- </method>
- <method name="getOutputName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.JobContext"/>
- <doc>
- <![CDATA[Get the base output name for the output file.]]>
- </doc>
- </method>
- <method name="setOutputName"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.JobContext"/>
- <param name="name" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the base output name for output file to be created.]]>
- </doc>
- </method>
- <method name="getOutputCommitter" return="org.apache.hadoop.mapreduce.OutputCommitter"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <field name="BASE_OUTPUT_NAME" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="PART" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="COMPRESS" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="COMPRESS_CODEC" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="COMPRESS_TYPE" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="OUTDIR" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[A base class for {@link OutputFormat}s that read from {@link FileSystem}s.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.output.FileOutputFormat -->
- <!-- start class org.apache.hadoop.mapreduce.lib.output.FilterOutputFormat -->
- <class name="FilterOutputFormat" extends="org.apache.hadoop.mapreduce.OutputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="FilterOutputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <constructor name="FilterOutputFormat" type="org.apache.hadoop.mapreduce.OutputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Create a FilterOutputFormat based on the underlying output format.
- @param baseOut the underlying OutputFormat]]>
- </doc>
- </constructor>
- <method name="getRecordWriter" return="org.apache.hadoop.mapreduce.RecordWriter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="checkOutputSpecs"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.JobContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="getOutputCommitter" return="org.apache.hadoop.mapreduce.OutputCommitter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <field name="baseOut" type="org.apache.hadoop.mapreduce.OutputFormat"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[FilterOutputFormat is a convenience class that wraps OutputFormat.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.output.FilterOutputFormat -->
- <!-- start class org.apache.hadoop.mapreduce.lib.output.FilterOutputFormat.FilterRecordWriter -->
- <class name="FilterOutputFormat.FilterRecordWriter" extends="org.apache.hadoop.mapreduce.RecordWriter"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="FilterOutputFormat.FilterRecordWriter"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <constructor name="FilterOutputFormat.FilterRecordWriter" type="org.apache.hadoop.mapreduce.RecordWriter"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="write"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <param name="value" type="V"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <field name="rawWriter" type="org.apache.hadoop.mapreduce.RecordWriter"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[<code>FilterRecordWriter</code> is a convenience wrapper
- class that extends the {@link RecordWriter}.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.output.FilterOutputFormat.FilterRecordWriter -->
- <!-- start class org.apache.hadoop.mapreduce.lib.output.LazyOutputFormat -->
- <class name="LazyOutputFormat" extends="org.apache.hadoop.mapreduce.lib.output.FilterOutputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="LazyOutputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setOutputFormatClass"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <param name="theClass" type="java.lang.Class"/>
- <doc>
- <![CDATA[Set the underlying output format for LazyOutputFormat.
- @param job the {@link Job} to modify
- @param theClass the underlying class]]>
- </doc>
- </method>
- <method name="getRecordWriter" return="org.apache.hadoop.mapreduce.RecordWriter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="checkOutputSpecs"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.JobContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="getOutputCommitter" return="org.apache.hadoop.mapreduce.OutputCommitter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <field name="OUTPUT_FORMAT" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[A Convenience class that creates output lazily.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.output.LazyOutputFormat -->
- <!-- start class org.apache.hadoop.mapreduce.lib.output.MapFileOutputFormat -->
- <class name="MapFileOutputFormat" extends="org.apache.hadoop.mapreduce.lib.output.FileOutputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="MapFileOutputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getRecordWriter" return="org.apache.hadoop.mapreduce.RecordWriter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getReaders" return="org.apache.hadoop.io.MapFile.Reader[]"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="dir" type="org.apache.hadoop.fs.Path"/>
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Open the output generated by this format.]]>
- </doc>
- </method>
- <method name="getEntry" return="org.apache.hadoop.io.Writable"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="readers" type="org.apache.hadoop.io.MapFile.Reader[]"/>
- <param name="partitioner" type="org.apache.hadoop.mapreduce.Partitioner"/>
- <param name="key" type="K"/>
- <param name="value" type="V"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get an entry from output generated by this class.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[An {@link org.apache.hadoop.mapreduce.OutputFormat} that writes
- {@link MapFile}s.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.output.MapFileOutputFormat -->
- <!-- start class org.apache.hadoop.mapreduce.lib.output.MultipleOutputs -->
- <class name="MultipleOutputs" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="MultipleOutputs" type="org.apache.hadoop.mapreduce.TaskInputOutputContext"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Creates and initializes multiple outputs support,
- it should be instantiated in the Mapper/Reducer setup method.
- @param context the TaskInputOutputContext object]]>
- </doc>
- </constructor>
- <method name="addNamedOutput"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <param name="namedOutput" type="java.lang.String"/>
- <param name="outputFormatClass" type="java.lang.Class"/>
- <param name="keyClass" type="java.lang.Class"/>
- <param name="valueClass" type="java.lang.Class"/>
- <doc>
- <![CDATA[Adds a named output for the job.
- <p/>
- @param job job to add the named output
- @param namedOutput named output name, it has to be a word, letters
- and numbers only, cannot be the word 'part' as
- that is reserved for the default output.
- @param outputFormatClass OutputFormat class.
- @param keyClass key class
- @param valueClass value class]]>
- </doc>
- </method>
- <method name="setCountersEnabled"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <param name="enabled" type="boolean"/>
- <doc>
- <![CDATA[Enables or disables counters for the named outputs.
-
- The counters group is the {@link MultipleOutputs} class name.
- The names of the counters are the same as the named outputs. These
- counters count the number records written to each output name.
- By default these counters are disabled.
- @param job job to enable counters
- @param enabled indicates if the counters will be enabled or not.]]>
- </doc>
- </method>
- <method name="getCountersEnabled" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.JobContext"/>
- <doc>
- <![CDATA[Returns if the counters for the named outputs are enabled or not.
- By default these counters are disabled.
- @param job the job
- @return TRUE if the counters are enabled, FALSE if they are disabled.]]>
- </doc>
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="namedOutput" type="java.lang.String"/>
- <param name="key" type="K"/>
- <param name="value" type="V"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Write key and value to the namedOutput.
- Output path is a unique file generated for the namedOutput.
- For example, {namedOutput}-(m|r)-{part-number}
-
- @param namedOutput the named output name
- @param key the key
- @param value the value]]>
- </doc>
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="namedOutput" type="java.lang.String"/>
- <param name="key" type="K"/>
- <param name="value" type="V"/>
- <param name="baseOutputPath" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Write key and value to baseOutputPath using the namedOutput.
-
- @param namedOutput the named output name
- @param key the key
- @param value the value
- @param baseOutputPath base-output path to write the record to.
- Note: Framework will generate unique filename for the baseOutputPath]]>
- </doc>
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="KEYOUT"/>
- <param name="value" type="VALUEOUT"/>
- <param name="baseOutputPath" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Write key value to an output file name.
-
- Gets the record writer from job's output format.
- Job's output format should be a FileOutputFormat.
-
- @param key the key
- @param value the value
- @param baseOutputPath base-output path to write the record to.
- Note: Framework will generate unique filename for the baseOutputPath]]>
- </doc>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Closes all the opened outputs.
-
- This should be called from cleanup method of map/reduce task.
- If overridden subclasses must invoke <code>super.close()</code> at the
- end of their <code>close()</code>]]>
- </doc>
- </method>
- <doc>
- <![CDATA[The MultipleOutputs class simplifies writing output data
- to multiple outputs
-
- <p>
- Case one: writing to additional outputs other than the job default output.
- Each additional output, or named output, may be configured with its own
- <code>OutputFormat</code>, with its own key class and with its own value
- class.
-
- <p>
- Case two: to write data to different files provided by user
- </p>
-
- <p>
- MultipleOutputs supports counters, by default they are disabled. The
- counters group is the {@link MultipleOutputs} class name. The names of the
- counters are the same as the output name. These count the number records
- written to each output name.
- </p>
-
- Usage pattern for job submission:
- <pre>
- Job job = new Job();
- FileInputFormat.setInputPath(job, inDir);
- FileOutputFormat.setOutputPath(job, outDir);
- job.setMapperClass(MOMap.class);
- job.setReducerClass(MOReduce.class);
- ...
- // Defines additional single text based output 'text' for the job
- MultipleOutputs.addNamedOutput(job, "text", TextOutputFormat.class,
- LongWritable.class, Text.class);
- // Defines additional sequence-file based output 'sequence' for the job
- MultipleOutputs.addNamedOutput(job, "seq",
- SequenceFileOutputFormat.class,
- LongWritable.class, Text.class);
- ...
- job.waitForCompletion(true);
- ...
- </pre>
- <p>
- Usage in Reducer:
- <pre>
- <K, V> String generateFileName(K k, V v) {
- return k.toString() + "_" + v.toString();
- }
-
- public class MOReduce extends
- Reducer<WritableComparable, Writable,WritableComparable, Writable> {
- private MultipleOutputs mos;
- public void setup(Context context) {
- ...
- mos = new MultipleOutputs(context);
- }
- public void reduce(WritableComparable key, Iterator<Writable> values,
- Context context)
- throws IOException {
- ...
- mos.write("text", , key, new Text("Hello"));
- mos.write("seq", LongWritable(1), new Text("Bye"), "seq_a");
- mos.write("seq", LongWritable(2), key, new Text("Chau"), "seq_b");
- mos.write(key, new Text("value"), generateFileName(key, new Text("value")));
- ...
- }
- public void cleanup(Context) throws IOException {
- mos.close();
- ...
- }
- }
- </pre>]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.output.MultipleOutputs -->
- <!-- start class org.apache.hadoop.mapreduce.lib.output.NullOutputFormat -->
- <class name="NullOutputFormat" extends="org.apache.hadoop.mapreduce.OutputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="NullOutputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getRecordWriter" return="org.apache.hadoop.mapreduce.RecordWriter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- </method>
- <method name="checkOutputSpecs"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.JobContext"/>
- </method>
- <method name="getOutputCommitter" return="org.apache.hadoop.mapreduce.OutputCommitter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- </method>
- <doc>
- <![CDATA[Consume all outputs and put them in /dev/null.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.output.NullOutputFormat -->
- <!-- start class org.apache.hadoop.mapreduce.lib.output.SequenceFileAsBinaryOutputFormat -->
- <class name="SequenceFileAsBinaryOutputFormat" extends="org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="SequenceFileAsBinaryOutputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setSequenceFileOutputKeyClass"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <param name="theClass" type="java.lang.Class"/>
- <doc>
- <![CDATA[Set the key class for the {@link SequenceFile}
- <p>This allows the user to specify the key class to be different
- from the actual class ({@link BytesWritable}) used for writing </p>
-
- @param job the {@link Job} to modify
- @param theClass the SequenceFile output key class.]]>
- </doc>
- </method>
- <method name="setSequenceFileOutputValueClass"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <param name="theClass" type="java.lang.Class"/>
- <doc>
- <![CDATA[Set the value class for the {@link SequenceFile}
- <p>This allows the user to specify the value class to be different
- from the actual class ({@link BytesWritable}) used for writing </p>
-
- @param job the {@link Job} to modify
- @param theClass the SequenceFile output key class.]]>
- </doc>
- </method>
- <method name="getSequenceFileOutputKeyClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.JobContext"/>
- <doc>
- <![CDATA[Get the key class for the {@link SequenceFile}
-
- @return the key class of the {@link SequenceFile}]]>
- </doc>
- </method>
- <method name="getSequenceFileOutputValueClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.JobContext"/>
- <doc>
- <![CDATA[Get the value class for the {@link SequenceFile}
-
- @return the value class of the {@link SequenceFile}]]>
- </doc>
- </method>
- <method name="getRecordWriter" return="org.apache.hadoop.mapreduce.RecordWriter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="checkOutputSpecs"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.JobContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <field name="KEY_CLASS" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="VALUE_CLASS" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[An {@link org.apache.hadoop.mapreduce.OutputFormat} that writes keys,
- values to {@link SequenceFile}s in binary(raw) format]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.output.SequenceFileAsBinaryOutputFormat -->
- <!-- start class org.apache.hadoop.mapreduce.lib.output.SequenceFileAsBinaryOutputFormat.WritableValueBytes -->
- <class name="SequenceFileAsBinaryOutputFormat.WritableValueBytes" extends="java.lang.Object"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.io.SequenceFile.ValueBytes"/>
- <constructor name="SequenceFileAsBinaryOutputFormat.WritableValueBytes"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <constructor name="SequenceFileAsBinaryOutputFormat.WritableValueBytes" type="org.apache.hadoop.io.BytesWritable"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="reset"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="value" type="org.apache.hadoop.io.BytesWritable"/>
- </method>
- <method name="writeUncompressedBytes"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="outStream" type="java.io.DataOutputStream"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="writeCompressedBytes"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="outStream" type="java.io.DataOutputStream"/>
- <exception name="IllegalArgumentException" type="java.lang.IllegalArgumentException"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getSize" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <doc>
- <![CDATA[Inner class used for appendRaw]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.output.SequenceFileAsBinaryOutputFormat.WritableValueBytes -->
- <!-- start class org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat -->
- <class name="SequenceFileOutputFormat" extends="org.apache.hadoop.mapreduce.lib.output.FileOutputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="SequenceFileOutputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getSequenceWriter" return="org.apache.hadoop.io.SequenceFile.Writer"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <param name="keyClass" type="java.lang.Class"/>
- <param name="valueClass" type="java.lang.Class"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getRecordWriter" return="org.apache.hadoop.mapreduce.RecordWriter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="getOutputCompressionType" return="org.apache.hadoop.io.SequenceFile.CompressionType"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.JobContext"/>
- <doc>
- <![CDATA[Get the {@link CompressionType} for the output {@link SequenceFile}.
- @param job the {@link Job}
- @return the {@link CompressionType} for the output {@link SequenceFile},
- defaulting to {@link CompressionType#RECORD}]]>
- </doc>
- </method>
- <method name="setOutputCompressionType"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <param name="style" type="org.apache.hadoop.io.SequenceFile.CompressionType"/>
- <doc>
- <![CDATA[Set the {@link CompressionType} for the output {@link SequenceFile}.
- @param job the {@link Job} to modify
- @param style the {@link CompressionType} for the output
- {@link SequenceFile}]]>
- </doc>
- </method>
- <doc>
- <![CDATA[An {@link OutputFormat} that writes {@link SequenceFile}s.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat -->
- <!-- start class org.apache.hadoop.mapreduce.lib.output.TextOutputFormat -->
- <class name="TextOutputFormat" extends="org.apache.hadoop.mapreduce.lib.output.FileOutputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="TextOutputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getRecordWriter" return="org.apache.hadoop.mapreduce.RecordWriter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <field name="SEPERATOR" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[An {@link OutputFormat} that writes plain text files.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.output.TextOutputFormat -->
- <!-- start class org.apache.hadoop.mapreduce.lib.output.TextOutputFormat.LineRecordWriter -->
- <class name="TextOutputFormat.LineRecordWriter" extends="org.apache.hadoop.mapreduce.RecordWriter"
- abstract="false"
- static="true" final="false" visibility="protected"
- deprecated="not deprecated">
- <constructor name="TextOutputFormat.LineRecordWriter" type="java.io.DataOutputStream, java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <constructor name="TextOutputFormat.LineRecordWriter" type="java.io.DataOutputStream"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="write"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <param name="value" type="V"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <field name="out" type="java.io.DataOutputStream"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.output.TextOutputFormat.LineRecordWriter -->
- </package>
- <package name="org.apache.hadoop.mapreduce.lib.partition">
- <!-- start class org.apache.hadoop.mapreduce.lib.partition.BinaryPartitioner -->
- <class name="BinaryPartitioner" extends="org.apache.hadoop.mapreduce.Partitioner"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.conf.Configurable"/>
- <constructor name="BinaryPartitioner"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setOffsets"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <param name="left" type="int"/>
- <param name="right" type="int"/>
- <doc>
- <![CDATA[Set the subarray to be used for partitioning to
- <code>bytes[left:(right+1)]</code> in Python syntax.
-
- @param conf configuration object
- @param left left Python-style offset
- @param right right Python-style offset]]>
- </doc>
- </method>
- <method name="setLeftOffset"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <param name="offset" type="int"/>
- <doc>
- <![CDATA[Set the subarray to be used for partitioning to
- <code>bytes[offset:]</code> in Python syntax.
-
- @param conf configuration object
- @param offset left Python-style offset]]>
- </doc>
- </method>
- <method name="setRightOffset"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <param name="offset" type="int"/>
- <doc>
- <![CDATA[Set the subarray to be used for partitioning to
- <code>bytes[:(offset+1)]</code> in Python syntax.
-
- @param conf configuration object
- @param offset right Python-style offset]]>
- </doc>
- </method>
- <method name="setConf"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- </method>
- <method name="getConf" return="org.apache.hadoop.conf.Configuration"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getPartition" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="org.apache.hadoop.io.BinaryComparable"/>
- <param name="value" type="V"/>
- <param name="numPartitions" type="int"/>
- <doc>
- <![CDATA[Use (the specified slice of the array returned by)
- {@link BinaryComparable#getBytes()} to partition.]]>
- </doc>
- </method>
- <field name="LEFT_OFFSET_PROPERTY_NAME" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="RIGHT_OFFSET_PROPERTY_NAME" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[<p>Partition {@link BinaryComparable} keys using a configurable part of
- the bytes array returned by {@link BinaryComparable#getBytes()}.</p>
-
- <p>The subarray to be used for the partitioning can be defined by means
- of the following properties:
- <ul>
- <li>
- <i>mapreduce.partition.binarypartitioner.left.offset</i>:
- left offset in array (0 by default)
- </li>
- <li>
- <i>mapreduce.partition.binarypartitioner.right.offset</i>:
- right offset in array (-1 by default)
- </li>
- </ul>
- Like in Python, both negative and positive offsets are allowed, but
- the meaning is slightly different. In case of an array of length 5,
- for instance, the possible offsets are:
- <pre><code>
- +---+---+---+---+---+
- | B | B | B | B | B |
- +---+---+---+---+---+
- 0 1 2 3 4
- -5 -4 -3 -2 -1
- </code></pre>
- The first row of numbers gives the position of the offsets 0...5 in
- the array; the second row gives the corresponding negative offsets.
- Contrary to Python, the specified subarray has byte <code>i</code>
- and <code>j</code> as first and last element, repectively, when
- <code>i</code> and <code>j</code> are the left and right offset.
-
- <p>For Hadoop programs written in Java, it is advisable to use one of
- the following static convenience methods for setting the offsets:
- <ul>
- <li>{@link #setOffsets}</li>
- <li>{@link #setLeftOffset}</li>
- <li>{@link #setRightOffset}</li>
- </ul></p>]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.partition.BinaryPartitioner -->
- <!-- start class org.apache.hadoop.mapreduce.lib.partition.HashPartitioner -->
- <class name="HashPartitioner" extends="org.apache.hadoop.mapreduce.Partitioner"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="HashPartitioner"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getPartition" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <param name="value" type="V"/>
- <param name="numReduceTasks" type="int"/>
- <doc>
- <![CDATA[Use {@link Object#hashCode()} to partition.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Partition keys by their {@link Object#hashCode()}.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.partition.HashPartitioner -->
- <!-- start class org.apache.hadoop.mapreduce.lib.partition.InputSampler -->
- <class name="InputSampler" extends="org.apache.hadoop.conf.Configured"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.util.Tool"/>
- <constructor name="InputSampler" type="org.apache.hadoop.conf.Configuration"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="writePartitionFile"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <param name="sampler" type="org.apache.hadoop.mapreduce.lib.partition.InputSampler.Sampler"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="ClassNotFoundException" type="java.lang.ClassNotFoundException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Write a partition file for the given job, using the Sampler provided.
- Queries the sampler for a sample keyset, sorts by the output key
- comparator, selects the keys for each rank, and writes to the destination
- returned from {@link TotalOrderPartitioner#getPartitionFile}.]]>
- </doc>
- </method>
- <method name="run" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="args" type="java.lang.String[]"/>
- <exception name="Exception" type="java.lang.Exception"/>
- <doc>
- <![CDATA[Driver for InputSampler from the command line.
- Configures a JobConf instance and calls {@link #writePartitionFile}.]]>
- </doc>
- </method>
- <method name="main"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="args" type="java.lang.String[]"/>
- <exception name="Exception" type="java.lang.Exception"/>
- </method>
- <doc>
- <![CDATA[Utility for collecting samples and writing a partition file for
- {@link TotalOrderPartitioner}.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.partition.InputSampler -->
- <!-- start class org.apache.hadoop.mapreduce.lib.partition.InputSampler.IntervalSampler -->
- <class name="InputSampler.IntervalSampler" extends="java.lang.Object"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.lib.partition.InputSampler.Sampler"/>
- <constructor name="InputSampler.IntervalSampler" type="double"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Create a new IntervalSampler sampling <em>all</em> splits.
- @param freq The frequency with which records will be emitted.]]>
- </doc>
- </constructor>
- <constructor name="InputSampler.IntervalSampler" type="double, int"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Create a new IntervalSampler.
- @param freq The frequency with which records will be emitted.
- @param maxSplitsSampled The maximum number of splits to examine.
- @see #getSample]]>
- </doc>
- </constructor>
- <method name="getSample" return="K[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="inf" type="org.apache.hadoop.mapreduce.InputFormat"/>
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[For each split sampled, emit when the ratio of the number of records
- retained to the total record count is less than the specified
- frequency.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Sample from s splits at regular intervals.
- Useful for sorted data.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.partition.InputSampler.IntervalSampler -->
- <!-- start class org.apache.hadoop.mapreduce.lib.partition.InputSampler.RandomSampler -->
- <class name="InputSampler.RandomSampler" extends="java.lang.Object"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.lib.partition.InputSampler.Sampler"/>
- <constructor name="InputSampler.RandomSampler" type="double, int"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Create a new RandomSampler sampling <em>all</em> splits.
- This will read every split at the client, which is very expensive.
- @param freq Probability with which a key will be chosen.
- @param numSamples Total number of samples to obtain from all selected
- splits.]]>
- </doc>
- </constructor>
- <constructor name="InputSampler.RandomSampler" type="double, int, int"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Create a new RandomSampler.
- @param freq Probability with which a key will be chosen.
- @param numSamples Total number of samples to obtain from all selected
- splits.
- @param maxSplitsSampled The maximum number of splits to examine.]]>
- </doc>
- </constructor>
- <method name="getSample" return="K[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="inf" type="org.apache.hadoop.mapreduce.InputFormat"/>
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Randomize the split order, then take the specified number of keys from
- each split sampled, where each key is selected with the specified
- probability and possibly replaced by a subsequently selected key when
- the quota of keys from that split is satisfied.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Sample from random points in the input.
- General-purpose sampler. Takes numSamples / maxSplitsSampled inputs from
- each split.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.partition.InputSampler.RandomSampler -->
- <!-- start interface org.apache.hadoop.mapreduce.lib.partition.InputSampler.Sampler -->
- <interface name="InputSampler.Sampler" abstract="true"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <method name="getSample" return="K[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="inf" type="org.apache.hadoop.mapreduce.InputFormat"/>
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[For a given job, collect and return a subset of the keys from the
- input data.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Interface to sample using an
- {@link org.apache.hadoop.mapreduce.InputFormat}.]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapreduce.lib.partition.InputSampler.Sampler -->
- <!-- start class org.apache.hadoop.mapreduce.lib.partition.InputSampler.SplitSampler -->
- <class name="InputSampler.SplitSampler" extends="java.lang.Object"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.lib.partition.InputSampler.Sampler"/>
- <constructor name="InputSampler.SplitSampler" type="int"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Create a SplitSampler sampling <em>all</em> splits.
- Takes the first numSamples / numSplits records from each split.
- @param numSamples Total number of samples to obtain from all selected
- splits.]]>
- </doc>
- </constructor>
- <constructor name="InputSampler.SplitSampler" type="int, int"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Create a new SplitSampler.
- @param numSamples Total number of samples to obtain from all selected
- splits.
- @param maxSplitsSampled The maximum number of splits to examine.]]>
- </doc>
- </constructor>
- <method name="getSample" return="K[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="inf" type="org.apache.hadoop.mapreduce.InputFormat"/>
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[From each split sampled, take the first numSamples / numSplits records.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Samples the first n records from s splits.
- Inexpensive way to sample random data.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.partition.InputSampler.SplitSampler -->
- <!-- start class org.apache.hadoop.mapreduce.lib.partition.KeyFieldBasedComparator -->
- <class name="KeyFieldBasedComparator" extends="org.apache.hadoop.io.WritableComparator"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.conf.Configurable"/>
- <constructor name="KeyFieldBasedComparator"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setConf"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- </method>
- <method name="getConf" return="org.apache.hadoop.conf.Configuration"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="compare" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="b1" type="byte[]"/>
- <param name="s1" type="int"/>
- <param name="l1" type="int"/>
- <param name="b2" type="byte[]"/>
- <param name="s2" type="int"/>
- <param name="l2" type="int"/>
- </method>
- <method name="setKeyFieldComparatorOptions"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <param name="keySpec" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the {@link KeyFieldBasedComparator} options used to compare keys.
-
- @param keySpec the key specification of the form -k pos1[,pos2], where,
- pos is of the form f[.c][opts], where f is the number
- of the key field to use, and c is the number of the first character from
- the beginning of the field. Fields and character posns are numbered
- starting with 1; a character position of zero in pos2 indicates the
- field's last character. If '.c' is omitted from pos1, it defaults to 1
- (the beginning of the field); if omitted from pos2, it defaults to 0
- (the end of the field). opts are ordering options. The supported options
- are:
- -n, (Sort numerically)
- -r, (Reverse the result of comparison)]]>
- </doc>
- </method>
- <method name="getKeyFieldComparatorOption" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.JobContext"/>
- <doc>
- <![CDATA[Get the {@link KeyFieldBasedComparator} options]]>
- </doc>
- </method>
- <field name="COMPARATOR_OPTIONS" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[This comparator implementation provides a subset of the features provided
- by the Unix/GNU Sort. In particular, the supported features are:
- -n, (Sort numerically)
- -r, (Reverse the result of comparison)
- -k pos1[,pos2], where pos is of the form f[.c][opts], where f is the number
- of the field to use, and c is the number of the first character from the
- beginning of the field. Fields and character posns are numbered starting
- with 1; a character position of zero in pos2 indicates the field's last
- character. If '.c' is omitted from pos1, it defaults to 1 (the beginning
- of the field); if omitted from pos2, it defaults to 0 (the end of the
- field). opts are ordering options (any of 'nr' as described above).
- We assume that the fields in the key are separated by
- {@link JobContext#MAP_OUTPUT_KEY_FIELD_SEPERATOR}.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.partition.KeyFieldBasedComparator -->
- <!-- start class org.apache.hadoop.mapreduce.lib.partition.KeyFieldBasedPartitioner -->
- <class name="KeyFieldBasedPartitioner" extends="org.apache.hadoop.mapreduce.Partitioner"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.conf.Configurable"/>
- <constructor name="KeyFieldBasedPartitioner"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setConf"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- </method>
- <method name="getConf" return="org.apache.hadoop.conf.Configuration"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getPartition" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K2"/>
- <param name="value" type="V2"/>
- <param name="numReduceTasks" type="int"/>
- </method>
- <method name="hashCode" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="b" type="byte[]"/>
- <param name="start" type="int"/>
- <param name="end" type="int"/>
- <param name="currentHash" type="int"/>
- </method>
- <method name="getPartition" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="hash" type="int"/>
- <param name="numReduceTasks" type="int"/>
- </method>
- <method name="setKeyFieldPartitionerOptions"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <param name="keySpec" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the {@link KeyFieldBasedPartitioner} options used for
- {@link Partitioner}
-
- @param keySpec the key specification of the form -k pos1[,pos2], where,
- pos is of the form f[.c][opts], where f is the number
- of the key field to use, and c is the number of the first character from
- the beginning of the field. Fields and character posns are numbered
- starting with 1; a character position of zero in pos2 indicates the
- field's last character. If '.c' is omitted from pos1, it defaults to 1
- (the beginning of the field); if omitted from pos2, it defaults to 0
- (the end of the field).]]>
- </doc>
- </method>
- <method name="getKeyFieldPartitionerOption" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.JobContext"/>
- <doc>
- <![CDATA[Get the {@link KeyFieldBasedPartitioner} options]]>
- </doc>
- </method>
- <field name="PARTITIONER_OPTIONS" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[Defines a way to partition keys based on certain key fields (also see
- {@link KeyFieldBasedComparator}.
- The key specification supported is of the form -k pos1[,pos2], where,
- pos is of the form f[.c][opts], where f is the number
- of the key field to use, and c is the number of the first character from
- the beginning of the field. Fields and character posns are numbered
- starting with 1; a character position of zero in pos2 indicates the
- field's last character. If '.c' is omitted from pos1, it defaults to 1
- (the beginning of the field); if omitted from pos2, it defaults to 0
- (the end of the field).]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.partition.KeyFieldBasedPartitioner -->
- <!-- start class org.apache.hadoop.mapreduce.lib.partition.TotalOrderPartitioner -->
- <class name="TotalOrderPartitioner" extends="org.apache.hadoop.mapreduce.Partitioner"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.conf.Configurable"/>
- <constructor name="TotalOrderPartitioner"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setConf"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <doc>
- <![CDATA[Read in the partition file and build indexing data structures.
- If the keytype is {@link org.apache.hadoop.io.BinaryComparable} and
- <tt>total.order.partitioner.natural.order</tt> is not false, a trie
- of the first <tt>total.order.partitioner.max.trie.depth</tt>(2) + 1 bytes
- will be built. Otherwise, keys will be located using a binary search of
- the partition keyset using the {@link org.apache.hadoop.io.RawComparator}
- defined for this job. The input file must be sorted with the same
- comparator and contain {@link Job#getNumReduceTasks()} - 1 keys.]]>
- </doc>
- </method>
- <method name="getConf" return="org.apache.hadoop.conf.Configuration"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getPartition" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <param name="value" type="V"/>
- <param name="numPartitions" type="int"/>
- </method>
- <method name="setPartitionFile"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <param name="p" type="org.apache.hadoop.fs.Path"/>
- <doc>
- <![CDATA[Set the path to the SequenceFile storing the sorted partition keyset.
- It must be the case that for <tt>R</tt> reduces, there are <tt>R-1</tt>
- keys in the SequenceFile.]]>
- </doc>
- </method>
- <method name="getPartitionFile" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <doc>
- <![CDATA[Get the path to the SequenceFile storing the sorted partition keyset.
- @see #setPartitionFile(Configuration, Path)]]>
- </doc>
- </method>
- <field name="DEFAULT_PATH" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="PARTITIONER_PATH" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="MAX_TRIE_DEPTH" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="NATURAL_ORDER" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[Partitioner effecting a total order by reading split points from
- an externally generated source.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.partition.TotalOrderPartitioner -->
- </package>
- <package name="org.apache.hadoop.mapreduce.lib.reduce">
- <!-- start class org.apache.hadoop.mapreduce.lib.reduce.IntSumReducer -->
- <class name="IntSumReducer" extends="org.apache.hadoop.mapreduce.Reducer"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="IntSumReducer"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="reduce"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="Key"/>
- <param name="values" type="java.lang.Iterable"/>
- <param name="context" type="org.apache.hadoop.mapreduce.Reducer.Context"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.reduce.IntSumReducer -->
- <!-- start class org.apache.hadoop.mapreduce.lib.reduce.LongSumReducer -->
- <class name="LongSumReducer" extends="org.apache.hadoop.mapreduce.Reducer"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="LongSumReducer"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="reduce"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="KEY"/>
- <param name="values" type="java.lang.Iterable"/>
- <param name="context" type="org.apache.hadoop.mapreduce.Reducer.Context"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.reduce.LongSumReducer -->
- <!-- start class org.apache.hadoop.mapreduce.lib.reduce.WrappedReducer -->
- <class name="WrappedReducer" extends="org.apache.hadoop.mapreduce.Reducer"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="WrappedReducer"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getReducerContext" return="org.apache.hadoop.mapreduce.Reducer.Context"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="reduceContext" type="org.apache.hadoop.mapreduce.ReduceContext"/>
- <doc>
- <![CDATA[A a wrapped {@link Reducer.Context} for custom implementations.
- @param reduceContext <code>ReduceContext</code> to be wrapped
- @return a wrapped <code>Reducer.Context</code> for custom implementations]]>
- </doc>
- </method>
- <doc>
- <![CDATA[A {@link Reducer} which wraps a given one to allow for custom
- {@link Reducer.Context} implementations.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.reduce.WrappedReducer -->
- <!-- start class org.apache.hadoop.mapreduce.lib.reduce.WrappedReducer.Context -->
- <class name="WrappedReducer.Context" extends="org.apache.hadoop.mapreduce.Reducer.Context"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="WrappedReducer.Context" type="org.apache.hadoop.mapreduce.ReduceContext"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getCurrentKey" return="KEYIN"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="getCurrentValue" return="VALUEIN"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="nextKeyValue" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="getCounter" return="org.apache.hadoop.mapreduce.Counter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="counterName" type="java.lang.Enum"/>
- </method>
- <method name="getCounter" return="org.apache.hadoop.mapreduce.Counter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="groupName" type="java.lang.String"/>
- <param name="counterName" type="java.lang.String"/>
- </method>
- <method name="getOutputCommitter" return="org.apache.hadoop.mapreduce.OutputCommitter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="KEYOUT"/>
- <param name="value" type="VALUEOUT"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="getStatus" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getTaskAttemptID" return="org.apache.hadoop.mapreduce.TaskAttemptID"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="setStatus"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="msg" type="java.lang.String"/>
- </method>
- <method name="getArchiveClassPaths" return="org.apache.hadoop.fs.Path[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getArchiveTimestamps" return="java.lang.String[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getCacheArchives" return="java.net.URI[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getCacheFiles" return="java.net.URI[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getCombinerClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="ClassNotFoundException" type="java.lang.ClassNotFoundException"/>
- </method>
- <method name="getConfiguration" return="org.apache.hadoop.conf.Configuration"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getFileClassPaths" return="org.apache.hadoop.fs.Path[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getFileTimestamps" return="java.lang.String[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getGroupingComparator" return="org.apache.hadoop.io.RawComparator"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getInputFormatClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="ClassNotFoundException" type="java.lang.ClassNotFoundException"/>
- </method>
- <method name="getJar" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getJobID" return="org.apache.hadoop.mapreduce.JobID"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getJobName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getJobSetupCleanupNeeded" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getLocalCacheArchives" return="org.apache.hadoop.fs.Path[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getLocalCacheFiles" return="org.apache.hadoop.fs.Path[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getMapOutputKeyClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getMapOutputValueClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getMapperClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="ClassNotFoundException" type="java.lang.ClassNotFoundException"/>
- </method>
- <method name="getMaxMapAttempts" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getMaxReduceAttempts" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getNumReduceTasks" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getOutputFormatClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="ClassNotFoundException" type="java.lang.ClassNotFoundException"/>
- </method>
- <method name="getOutputKeyClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getOutputValueClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getPartitionerClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="ClassNotFoundException" type="java.lang.ClassNotFoundException"/>
- </method>
- <method name="getReducerClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="ClassNotFoundException" type="java.lang.ClassNotFoundException"/>
- </method>
- <method name="getSortComparator" return="org.apache.hadoop.io.RawComparator"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getSymlink" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getWorkingDirectory" return="org.apache.hadoop.fs.Path"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="progress"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getValues" return="java.lang.Iterable"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="nextKey" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="getProfileEnabled" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getProfileParams" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getProfileTaskRange" return="org.apache.hadoop.conf.Configuration.IntegerRanges"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="isMap" type="boolean"/>
- </method>
- <method name="getUser" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getCredentials" return="org.apache.hadoop.security.Credentials"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <field name="reduceContext" type="org.apache.hadoop.mapreduce.ReduceContext"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.reduce.WrappedReducer.Context -->
- </package>
- <package name="org.apache.hadoop.mapreduce.security">
- <!-- start class org.apache.hadoop.mapreduce.security.TokenCache -->
- <class name="TokenCache" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="TokenCache"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getSecretKey" return="byte[]"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="credentials" type="org.apache.hadoop.security.Credentials"/>
- <param name="alias" type="org.apache.hadoop.io.Text"/>
- <doc>
- <![CDATA[auxiliary method to get user's secret keys..
- @param alias
- @return secret key from the storage]]>
- </doc>
- </method>
- <method name="obtainTokensForNamenodes"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="credentials" type="org.apache.hadoop.security.Credentials"/>
- <param name="ps" type="org.apache.hadoop.fs.Path[]"/>
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Convenience method to obtain delegation tokens from namenodes
- corresponding to the paths passed.
- @param credentials
- @param ps array of paths
- @param conf configuration
- @throws IOException]]>
- </doc>
- </method>
- <method name="getDelegationToken" return="org.apache.hadoop.security.token.Token"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="credentials" type="org.apache.hadoop.security.Credentials"/>
- <param name="namenode" type="java.lang.String"/>
- <doc>
- <![CDATA[@param namenode
- @return delegation token]]>
- </doc>
- </method>
- <method name="loadTokens" return="org.apache.hadoop.security.Credentials"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobTokenFile" type="java.lang.String"/>
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[load job token from a file
- @param conf
- @throws IOException]]>
- </doc>
- </method>
- <method name="setJobToken"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="t" type="org.apache.hadoop.security.token.Token"/>
- <param name="credentials" type="org.apache.hadoop.security.Credentials"/>
- <doc>
- <![CDATA[store job token
- @param t]]>
- </doc>
- </method>
- <method name="getJobToken" return="org.apache.hadoop.security.token.Token"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="credentials" type="org.apache.hadoop.security.Credentials"/>
- <doc>
- <![CDATA[@return job token]]>
- </doc>
- </method>
- <field name="JOB_TOKEN_HDFS_FILE" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[file name used on HDFS for generated job token]]>
- </doc>
- </field>
- <field name="JOB_TOKENS_FILENAME" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[conf setting for job tokens cache file name]]>
- </doc>
- </field>
- <doc>
- <![CDATA[This class provides user facing APIs for transferring secrets from
- the job client to the tasks.
- The secrets can be stored just before submission of jobs and read during
- the task execution.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.security.TokenCache -->
- </package>
- <package name="org.apache.hadoop.mapreduce.server.jobtracker">
- <!-- start class org.apache.hadoop.mapreduce.server.jobtracker.State -->
- <class name="State" extends="java.lang.Enum"
- abstract="false"
- static="false" final="true" visibility="public"
- deprecated="Use {@link JobTrackerStatus} instead.">
- <method name="values" return="org.apache.hadoop.mapreduce.server.jobtracker.State[]"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="valueOf" return="org.apache.hadoop.mapreduce.server.jobtracker.State"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- </method>
- <doc>
- <![CDATA[Describes the state of JobTracker
- @deprecated Use {@link JobTrackerStatus} instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.server.jobtracker.State -->
- </package>
- <package name="org.apache.hadoop.mapreduce.tools">
- <!-- start class org.apache.hadoop.mapreduce.tools.CLI -->
- <class name="CLI" extends="org.apache.hadoop.conf.Configured"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.util.Tool"/>
- <constructor name="CLI"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <constructor name="CLI" type="org.apache.hadoop.conf.Configuration"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="run" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="argv" type="java.lang.String[]"/>
- <exception name="Exception" type="java.lang.Exception"/>
- </method>
- <method name="getCounter" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="counters" type="org.apache.hadoop.mapreduce.Counters"/>
- <param name="counterGroupName" type="java.lang.String"/>
- <param name="counterName" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getTaskLogURL" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="taskId" type="org.apache.hadoop.mapreduce.TaskAttemptID"/>
- <param name="baseUrl" type="java.lang.String"/>
- </method>
- <method name="displayTasks"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapreduce.Job"/>
- <param name="type" type="java.lang.String"/>
- <param name="state" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Display the information about a job's tasks, of a particular type and
- in a particular state
-
- @param job the job
- @param type the type of the task (map/reduce/setup/cleanup)
- @param state the state of the task
- (pending/running/completed/failed/killed)]]>
- </doc>
- </method>
- <method name="displayJobList"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="jobs" type="org.apache.hadoop.mapreduce.Job[]"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </method>
- <method name="main"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="argv" type="java.lang.String[]"/>
- <exception name="Exception" type="java.lang.Exception"/>
- </method>
- <doc>
- <![CDATA[Interprets the map reduce cli options]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.tools.CLI -->
- </package>
- <package name="org.apache.hadoop.fs">
- <!-- start class org.apache.hadoop.fs.HarFileSystem -->
- <class name="HarFileSystem" extends="org.apache.hadoop.fs.FilterFileSystem"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="HarFileSystem"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[public construction of harfilesystem]]>
- </doc>
- </constructor>
- <constructor name="HarFileSystem" type="org.apache.hadoop.fs.FileSystem"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Constructor to create a HarFileSystem with an
- underlying filesystem.
- @param fs]]>
- </doc>
- </constructor>
- <method name="initialize"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.net.URI"/>
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Initialize a Har filesystem per har archive. The
- archive home directory is the top level directory
- in the filesystem that contains the HAR archive.
- Be careful with this method, you do not want to go
- on creating new Filesystem instances per call to
- path.getFileSystem().
- the uri of Har is
- har://underlyingfsscheme-host:port/archivepath.
- or
- har:///archivepath. This assumes the underlying filesystem
- to be used in case not specified.]]>
- </doc>
- </method>
- <method name="getHarVersion" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getWorkingDirectory" return="org.apache.hadoop.fs.Path"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[return the top level archive.]]>
- </doc>
- </method>
- <method name="getUri" return="java.net.URI"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns the uri of this filesystem.
- The uri is of the form
- har://underlyingfsschema-host:port/pathintheunderlyingfs]]>
- </doc>
- </method>
- <method name="makeQualified" return="org.apache.hadoop.fs.Path"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="path" type="org.apache.hadoop.fs.Path"/>
- </method>
- <method name="getFileBlockLocations" return="org.apache.hadoop.fs.BlockLocation[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="file" type="org.apache.hadoop.fs.FileStatus"/>
- <param name="start" type="long"/>
- <param name="len" type="long"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[get block locations from the underlying fs
- @param file the input filestatus to get block locations
- @param start the start in the file
- @param len the length in the file
- @return block locations for this segment of file
- @throws IOException]]>
- </doc>
- </method>
- <method name="getHarHash" return="int"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="p" type="org.apache.hadoop.fs.Path"/>
- <doc>
- <![CDATA[the hash of the path p inside iniside
- the filesystem
- @param p the path in the harfilesystem
- @return the hash code of the path.]]>
- </doc>
- </method>
- <method name="getFileStatus" return="org.apache.hadoop.fs.FileStatus"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="f" type="org.apache.hadoop.fs.Path"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[return the filestatus of files in har archive.
- The permission returned are that of the archive
- index files. The permissions are not persisted
- while creating a hadoop archive.
- @param f the path in har filesystem
- @return filestatus.
- @throws IOException]]>
- </doc>
- </method>
- <method name="getFileChecksum" return="org.apache.hadoop.fs.FileChecksum"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="f" type="org.apache.hadoop.fs.Path"/>
- <doc>
- <![CDATA[@return null since no checksum algorithm is implemented.]]>
- </doc>
- </method>
- <method name="open" return="org.apache.hadoop.fs.FSDataInputStream"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="f" type="org.apache.hadoop.fs.Path"/>
- <param name="bufferSize" type="int"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Returns a har input stream which fakes end of
- file. It reads the index files to get the part
- file name and the size and start of the file.]]>
- </doc>
- </method>
- <method name="create" return="org.apache.hadoop.fs.FSDataOutputStream"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="f" type="org.apache.hadoop.fs.Path"/>
- <param name="bufferSize" type="int"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="create" return="org.apache.hadoop.fs.FSDataOutputStream"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="f" type="org.apache.hadoop.fs.Path"/>
- <param name="permission" type="org.apache.hadoop.fs.permission.FsPermission"/>
- <param name="flag" type="java.util.EnumSet"/>
- <param name="bufferSize" type="int"/>
- <param name="replication" type="short"/>
- <param name="blockSize" type="long"/>
- <param name="progress" type="org.apache.hadoop.util.Progressable"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="setReplication" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="src" type="org.apache.hadoop.fs.Path"/>
- <param name="replication" type="short"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Not implemented.]]>
- </doc>
- </method>
- <method name="delete" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="f" type="org.apache.hadoop.fs.Path"/>
- <param name="recursive" type="boolean"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Not implemented.]]>
- </doc>
- </method>
- <method name="listStatus" return="org.apache.hadoop.fs.FileStatus[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="f" type="org.apache.hadoop.fs.Path"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[liststatus returns the children of a directory
- after looking up the index files.]]>
- </doc>
- </method>
- <method name="getHomeDirectory" return="org.apache.hadoop.fs.Path"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[return the top level archive path.]]>
- </doc>
- </method>
- <method name="setWorkingDirectory"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="newDir" type="org.apache.hadoop.fs.Path"/>
- </method>
- <method name="mkdirs" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="f" type="org.apache.hadoop.fs.Path"/>
- <param name="permission" type="org.apache.hadoop.fs.permission.FsPermission"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[not implemented.]]>
- </doc>
- </method>
- <method name="copyFromLocalFile"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="delSrc" type="boolean"/>
- <param name="src" type="org.apache.hadoop.fs.Path"/>
- <param name="dst" type="org.apache.hadoop.fs.Path"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[not implemented.]]>
- </doc>
- </method>
- <method name="copyToLocalFile"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="delSrc" type="boolean"/>
- <param name="src" type="org.apache.hadoop.fs.Path"/>
- <param name="dst" type="org.apache.hadoop.fs.Path"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[copies the file in the har filesystem to a local file.]]>
- </doc>
- </method>
- <method name="startLocalOutput" return="org.apache.hadoop.fs.Path"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="fsOutputFile" type="org.apache.hadoop.fs.Path"/>
- <param name="tmpLocalFile" type="org.apache.hadoop.fs.Path"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[not implemented.]]>
- </doc>
- </method>
- <method name="completeLocalOutput"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="fsOutputFile" type="org.apache.hadoop.fs.Path"/>
- <param name="tmpLocalFile" type="org.apache.hadoop.fs.Path"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[not implemented.]]>
- </doc>
- </method>
- <method name="setOwner"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="p" type="org.apache.hadoop.fs.Path"/>
- <param name="username" type="java.lang.String"/>
- <param name="groupname" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[not implemented.]]>
- </doc>
- </method>
- <method name="setPermission"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="p" type="org.apache.hadoop.fs.Path"/>
- <param name="permisssion" type="org.apache.hadoop.fs.permission.FsPermission"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Not implemented.]]>
- </doc>
- </method>
- <field name="VERSION" type="int"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[This is an implementation of the Hadoop Archive
- Filesystem. This archive Filesystem has index files
- of the form _index* and has contents of the form
- part-*. The index files store the indexes of the
- real files. The index files are of the form _masterindex
- and _index. The master index is a level of indirection
- in to the index file to make the look ups faster. the index
- file is sorted with hash code of the paths that it contains
- and the master index contains pointers to the positions in
- index for ranges of hashcodes.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.fs.HarFileSystem -->
- </package>
- <package name="org.apache.hadoop.tools">
- <!-- start class org.apache.hadoop.tools.DistCh -->
- <class name="DistCh" extends="org.apache.hadoop.tools.DistTool"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <method name="run" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="args" type="java.lang.String[]"/>
- <exception name="Exception" type="java.lang.Exception"/>
- <doc>
- <![CDATA[This is the main driver for recursively changing files properties.]]>
- </doc>
- </method>
- <method name="main"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="args" type="java.lang.String[]"/>
- <exception name="Exception" type="java.lang.Exception"/>
- </method>
- <doc>
- <![CDATA[A Map-reduce program to recursively change files properties
- such as owner, group and permission.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.DistCh -->
- <!-- start class org.apache.hadoop.tools.DistCp -->
- <class name="DistCp" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.util.Tool"/>
- <constructor name="DistCp" type="org.apache.hadoop.conf.Configuration"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setConf"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- </method>
- <method name="getConf" return="org.apache.hadoop.conf.Configuration"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="copy"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <param name="srcPath" type="java.lang.String"/>
- <param name="destPath" type="java.lang.String"/>
- <param name="logPath" type="org.apache.hadoop.fs.Path"/>
- <param name="srcAsList" type="boolean"/>
- <param name="ignoreReadFailures" type="boolean"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="run" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="args" type="java.lang.String[]"/>
- <doc>
- <![CDATA[This is the main driver for recursively copying directories
- across file systems. It takes at least two cmdline parameters. A source
- URL and a destination URL. It then essentially does an "ls -lR" on the
- source URL, and writes the output in a round-robin manner to all the map
- input files. The mapper actually copies the files allotted to it. The
- reduce is empty.]]>
- </doc>
- </method>
- <method name="main"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="args" type="java.lang.String[]"/>
- <exception name="Exception" type="java.lang.Exception"/>
- </method>
- <method name="getRandomId" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <field name="LOG" type="org.apache.commons.logging.Log"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[A Map-reduce program to recursively copy directories between
- different file-systems.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.DistCp -->
- <!-- start class org.apache.hadoop.tools.DistCp.DuplicationException -->
- <class name="DistCp.DuplicationException" extends="java.io.IOException"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <field name="ERROR_CODE" type="int"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Error code for this exception]]>
- </doc>
- </field>
- <doc>
- <![CDATA[An exception class for duplicated source files.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.DistCp.DuplicationException -->
- <!-- start class org.apache.hadoop.tools.HadoopArchives -->
- <class name="HadoopArchives" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.util.Tool"/>
- <constructor name="HadoopArchives" type="org.apache.hadoop.conf.Configuration"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setConf"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- </method>
- <method name="getConf" return="org.apache.hadoop.conf.Configuration"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="run" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="args" type="java.lang.String[]"/>
- <exception name="Exception" type="java.lang.Exception"/>
- <doc>
- <![CDATA[the main driver for creating the archives
- it takes at least three command line parameters. The parent path,
- The src and the dest. It does an lsr on the source paths.
- The mapper created archuves and the reducer creates
- the archive index.]]>
- </doc>
- </method>
- <method name="main"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="args" type="java.lang.String[]"/>
- <doc>
- <![CDATA[the main functions]]>
- </doc>
- </method>
- <field name="VERSION" type="int"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[a archive creation utility.
- This class provides methods that can be used
- to create hadoop archives. For understanding of
- Hadoop archives look at {@link HarFileSystem}.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.HadoopArchives -->
- <!-- start class org.apache.hadoop.tools.Logalyzer -->
- <class name="Logalyzer" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="Logalyzer"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="doArchive"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="logListURI" type="java.lang.String"/>
- <param name="archiveDirectory" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[doArchive: Workhorse function to archive log-files.
- @param logListURI : The uri which will serve list of log-files to archive.
- @param archiveDirectory : The directory to store archived logfiles.
- @throws IOException]]>
- </doc>
- </method>
- <method name="doAnalyze"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="inputFilesDirectory" type="java.lang.String"/>
- <param name="outputDirectory" type="java.lang.String"/>
- <param name="grepPattern" type="java.lang.String"/>
- <param name="sortColumns" type="java.lang.String"/>
- <param name="columnSeparator" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[doAnalyze:
- @param inputFilesDirectory : Directory containing the files to be analyzed.
- @param outputDirectory : Directory to store analysis (output).
- @param grepPattern : Pattern to *grep* for.
- @param sortColumns : Sort specification for output.
- @param columnSeparator : Column separator.
- @throws IOException]]>
- </doc>
- </method>
- <method name="main"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="args" type="java.lang.String[]"/>
- </method>
- <field name="SORT_COLUMNS" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="COLUMN_SEPARATOR" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[Logalyzer: A utility tool for archiving and analyzing hadoop logs.
- <p>
- This tool supports archiving and anaylzing (sort/grep) of log-files.
- It takes as input
- a) Input uri which will serve uris of the logs to be archived.
- b) Output directory (not mandatory).
- b) Directory on dfs to archive the logs.
- c) The sort/grep patterns for analyzing the files and separator for boundaries.
- Usage:
- Logalyzer -archive -archiveDir <directory to archive logs> -analysis <directory> -logs <log-list uri> -grep <pattern> -sort <col1, col2> -separator <separator>
- <p>]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.Logalyzer -->
- <!-- start class org.apache.hadoop.tools.Logalyzer.LogComparator -->
- <class name="Logalyzer.LogComparator" extends="org.apache.hadoop.io.Text.Comparator"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.conf.Configurable"/>
- <constructor name="Logalyzer.LogComparator"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setConf"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- </method>
- <method name="getConf" return="org.apache.hadoop.conf.Configuration"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="compare" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="b1" type="byte[]"/>
- <param name="s1" type="int"/>
- <param name="l1" type="int"/>
- <param name="b2" type="byte[]"/>
- <param name="s2" type="int"/>
- <param name="l2" type="int"/>
- </method>
- <doc>
- <![CDATA[A WritableComparator optimized for UTF8 keys of the logs.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.Logalyzer.LogComparator -->
- <!-- start class org.apache.hadoop.tools.Logalyzer.LogRegexMapper -->
- <class name="Logalyzer.LogRegexMapper" extends="org.apache.hadoop.mapred.MapReduceBase"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapred.Mapper"/>
- <constructor name="Logalyzer.LogRegexMapper"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="configure"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- </method>
- <method name="map"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="K"/>
- <param name="value" type="org.apache.hadoop.io.Text"/>
- <param name="output" type="org.apache.hadoop.mapred.OutputCollector"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[A {@link Mapper} that extracts text matching a regular expression.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.Logalyzer.LogRegexMapper -->
- </package>
- <package name="org.apache.hadoop.tools.rumen">
- <!-- start class org.apache.hadoop.tools.rumen.AbstractClusterStory -->
- <class name="AbstractClusterStory" extends="java.lang.Object"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.tools.rumen.ClusterStory"/>
- <constructor name="AbstractClusterStory"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getMachines" return="java.util.Set"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getRacks" return="java.util.Set"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getRandomMachines" return="org.apache.hadoop.tools.rumen.MachineNode[]"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="expected" type="int"/>
- <param name="random" type="java.util.Random"/>
- </method>
- <method name="buildMachineNodeMap"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </method>
- <method name="getMachineByName" return="org.apache.hadoop.tools.rumen.MachineNode"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- </method>
- <method name="distance" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="a" type="org.apache.hadoop.tools.rumen.Node"/>
- <param name="b" type="org.apache.hadoop.tools.rumen.Node"/>
- </method>
- <method name="buildRackNodeMap"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </method>
- <method name="getRackByName" return="org.apache.hadoop.tools.rumen.RackNode"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- </method>
- <method name="getMaximumDistance" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="parseTopologyTree"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </method>
- <field name="machineNodes" type="java.util.Set"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="rackNodes" type="java.util.Set"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="mNodesFlattened" type="org.apache.hadoop.tools.rumen.MachineNode[]"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="mNodeMap" type="java.util.Map"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="rNodeMap" type="java.util.Map"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="maximumDistance" type="int"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[{@link AbstractClusterStory} provides a partial implementation of
- {@link ClusterStory} by parsing the topology tree.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.AbstractClusterStory -->
- <!-- start class org.apache.hadoop.tools.rumen.CDFPiecewiseLinearRandomGenerator -->
- <class name="CDFPiecewiseLinearRandomGenerator" extends="org.apache.hadoop.tools.rumen.CDFRandomGenerator"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="CDFPiecewiseLinearRandomGenerator" type="org.apache.hadoop.tools.rumen.LoggedDiscreteCDF"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@param cdf
- builds a CDFRandomValue engine around this
- {@link LoggedDiscreteCDF}, with a defaultly seeded RNG]]>
- </doc>
- </constructor>
- <constructor name="CDFPiecewiseLinearRandomGenerator" type="org.apache.hadoop.tools.rumen.LoggedDiscreteCDF, long"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@param cdf
- builds a CDFRandomValue engine around this
- {@link LoggedDiscreteCDF}, with an explicitly seeded RNG
- @param seed
- the random number generator seed]]>
- </doc>
- </constructor>
- <method name="valueAt" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="probability" type="double"/>
- <doc>
- <![CDATA[TODO This code assumes that the empirical minimum resp. maximum is the
- epistomological minimum resp. maximum. This is probably okay for the
- minimum, because that likely represents a task where everything went well,
- but for the maximum we may want to develop a way of extrapolating past the
- maximum.]]>
- </doc>
- </method>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.CDFPiecewiseLinearRandomGenerator -->
- <!-- start class org.apache.hadoop.tools.rumen.CDFRandomGenerator -->
- <class name="CDFRandomGenerator" extends="java.lang.Object"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <method name="initializeTables"
- abstract="false" native="false" synchronized="false"
- static="false" final="true" visibility="protected"
- deprecated="not deprecated">
- <param name="cdf" type="org.apache.hadoop.tools.rumen.LoggedDiscreteCDF"/>
- </method>
- <method name="floorIndex" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="probe" type="double"/>
- </method>
- <method name="getRankingAt" return="double"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="index" type="int"/>
- </method>
- <method name="getDatumAt" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="index" type="int"/>
- </method>
- <method name="randomValue" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="valueAt" return="long"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="probability" type="double"/>
- </method>
- <doc>
- <![CDATA[An instance of this class generates random values that confirm to the
- embedded {@link LoggedDiscreteCDF} . The discrete CDF is a pointwise
- approximation of the "real" CDF. We therefore have a choice of interpolation
- rules.
-
- A concrete subclass of this abstract class will implement valueAt(double)
- using a class-dependent interpolation rule.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.CDFRandomGenerator -->
- <!-- start interface org.apache.hadoop.tools.rumen.ClusterStory -->
- <interface name="ClusterStory" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <method name="getMachines" return="java.util.Set"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get all machines of the cluster.
- @return A read-only set that contains all machines of the cluster.]]>
- </doc>
- </method>
- <method name="getRacks" return="java.util.Set"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get all racks of the cluster.
- @return A read-only set that contains all racks of the cluster.]]>
- </doc>
- </method>
- <method name="getClusterTopology" return="org.apache.hadoop.tools.rumen.Node"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the cluster topology tree.
- @return The root node of the cluster topology tree.]]>
- </doc>
- </method>
- <method name="getRandomMachines" return="org.apache.hadoop.tools.rumen.MachineNode[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="expected" type="int"/>
- <param name="random" type="java.util.Random"/>
- <doc>
- <![CDATA[Select a random set of machines.
- @param expected The expected sample size.
- @param random Random number generator to use.
- @return An array of up to expected number of {@link MachineNode}s.]]>
- </doc>
- </method>
- <method name="getMachineByName" return="org.apache.hadoop.tools.rumen.MachineNode"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- <doc>
- <![CDATA[Get {@link MachineNode} by its host name.
-
- @return The {@link MachineNode} with the same name. Or null if not found.]]>
- </doc>
- </method>
- <method name="getRackByName" return="org.apache.hadoop.tools.rumen.RackNode"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- <doc>
- <![CDATA[Get {@link RackNode} by its name.
- @return The {@link RackNode} with the same name. Or null if not found.]]>
- </doc>
- </method>
- <method name="distance" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="a" type="org.apache.hadoop.tools.rumen.Node"/>
- <param name="b" type="org.apache.hadoop.tools.rumen.Node"/>
- <doc>
- <![CDATA[Determine the distance between two {@link Node}s. Currently, the distance
- is loosely defined as the length of the longer path for either a or b to
- reach their common ancestor.
-
- @param a
- @param b
- @return The distance between {@link Node} a and {@link Node} b.]]>
- </doc>
- </method>
- <method name="getMaximumDistance" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the maximum distance possible between any two nodes.
- @return the maximum distance possible between any two nodes.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[{@link ClusterStory} represents all configurations of a MapReduce cluster,
- including nodes, network topology, and slot configurations.]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.tools.rumen.ClusterStory -->
- <!-- start class org.apache.hadoop.tools.rumen.ClusterTopologyReader -->
- <class name="ClusterTopologyReader" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="ClusterTopologyReader" type="org.apache.hadoop.fs.Path, org.apache.hadoop.conf.Configuration"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Constructor.
-
- @param path
- Path to the JSON-encoded topology file, possibly compressed.
- @param conf
- @throws IOException]]>
- </doc>
- </constructor>
- <constructor name="ClusterTopologyReader" type="java.io.InputStream"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Constructor.
-
- @param input
- The input stream for the JSON-encoded topology data.]]>
- </doc>
- </constructor>
- <method name="get" return="org.apache.hadoop.tools.rumen.LoggedNetworkTopology"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the {@link LoggedNetworkTopology} object.
-
- @return The {@link LoggedNetworkTopology} object parsed from the input.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Reading JSON-encoded cluster topology and produce the parsed
- {@link LoggedNetworkTopology} object.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.ClusterTopologyReader -->
- <!-- start class org.apache.hadoop.tools.rumen.CurrentJHParser -->
- <class name="CurrentJHParser" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.tools.rumen.JobHistoryParser"/>
- <constructor name="CurrentJHParser" type="java.io.InputStream"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </constructor>
- <method name="canParse" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="input" type="java.io.InputStream"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Can this parser parse the input?
-
- @param input
- @return Whether this parser can parse the input.
- @throws IOException]]>
- </doc>
- </method>
- <method name="nextEvent" return="org.apache.hadoop.mapreduce.jobhistory.HistoryEvent"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[{@link JobHistoryParser} that parses {@link JobHistory} files produced by
- {@link org.apache.hadoop.mapreduce.jobhistory.JobHistory} in the same source
- code tree as rumen.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.CurrentJHParser -->
- <!-- start interface org.apache.hadoop.tools.rumen.DeepCompare -->
- <interface name="DeepCompare" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <method name="deepCompare"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="other" type="org.apache.hadoop.tools.rumen.DeepCompare"/>
- <param name="myLocation" type="org.apache.hadoop.tools.rumen.TreePath"/>
- <exception name="DeepInequalityException" type="org.apache.hadoop.tools.rumen.DeepInequalityException"/>
- <doc>
- <![CDATA[@param other
- the other comparand that's being compared to me
- @param myLocation
- the path that got to me. In the root, myLocation is null. To
- process the scalar {@code foo} field of the root we will make a
- recursive call with a {@link TreePath} whose {@code fieldName} is
- {@code "bar"} and whose {@code index} is -1 and whose {@code
- parent} is {@code null}. To process the plural {@code bar} field
- of the root we will make a recursive call with a {@link TreePath}
- whose fieldName is {@code "foo"} and whose {@code index} is -1 and
- whose {@code parent} is also {@code null}.
- @throws DeepInequalityException]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Classes that implement this interface can deep-compare [for equality only,
- not order] with another instance. They do a deep compare. If there is any
- semantically significant difference, an implementer throws an Exception to be
- thrown with a chain of causes describing the chain of field references and
- indices that get you to the miscompared point.]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.tools.rumen.DeepCompare -->
- <!-- start class org.apache.hadoop.tools.rumen.DeepInequalityException -->
- <class name="DeepInequalityException" extends="java.lang.Exception"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="DeepInequalityException" type="java.lang.String, org.apache.hadoop.tools.rumen.TreePath, java.lang.Throwable"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@param message
- an exception message
- @param path
- the path that gets from the root to the inequality
-
- This is the constructor that I intend to have used for this
- exception.]]>
- </doc>
- </constructor>
- <constructor name="DeepInequalityException" type="java.lang.String, org.apache.hadoop.tools.rumen.TreePath"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@param message
- an exception message
- @param path
- the path that gets from the root to the inequality
-
- This is the constructor that I intend to have used for this
- exception.]]>
- </doc>
- </constructor>
- <doc>
- <![CDATA[We use this exception class in the unit test, and we do a deep comparison
- when we run the]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.DeepInequalityException -->
- <!-- start class org.apache.hadoop.tools.rumen.DefaultInputDemuxer -->
- <class name="DefaultInputDemuxer" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.tools.rumen.InputDemuxer"/>
- <constructor name="DefaultInputDemuxer"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="bindTo"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="path" type="org.apache.hadoop.fs.Path"/>
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getNext" return="org.apache.hadoop.tools.rumen.Pair"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[{@link DefaultInputDemuxer} acts as a pass-through demuxer. It just opens
- each file and returns back the input stream. If the input is compressed, it
- would return a decompression stream.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.DefaultInputDemuxer -->
- <!-- start class org.apache.hadoop.tools.rumen.DefaultOutputter -->
- <class name="DefaultOutputter" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.tools.rumen.Outputter"/>
- <constructor name="DefaultOutputter"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="init"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="path" type="org.apache.hadoop.fs.Path"/>
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="output"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="object" type="T"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[The default {@link Outputter} that outputs to a plain file. Compression
- will be applied if the path has the right suffix.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.DefaultOutputter -->
- <!-- start class org.apache.hadoop.tools.rumen.DeskewedJobTraceReader -->
- <class name="DeskewedJobTraceReader" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="java.io.Closeable"/>
- <constructor name="DeskewedJobTraceReader" type="org.apache.hadoop.tools.rumen.JobTraceReader, int, boolean"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Constructor.
-
- @param reader
- the {@link JobTraceReader} that's being protected
- @param skewBufferLength
- [the number of late jobs that can preced a later out-of-order
- earlier job
- @throws IOException]]>
- </doc>
- </constructor>
- <constructor name="DeskewedJobTraceReader" type="org.apache.hadoop.tools.rumen.JobTraceReader"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </constructor>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.DeskewedJobTraceReader -->
- <!-- start class org.apache.hadoop.tools.rumen.Folder -->
- <class name="Folder" extends="org.apache.hadoop.conf.Configured"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.util.Tool"/>
- <constructor name="Folder"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="run" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="args" type="java.lang.String[]"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="run" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="main"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="args" type="java.lang.String[]"/>
- <doc>
- <![CDATA[@param args]]>
- </doc>
- </method>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.Folder -->
- <!-- start class org.apache.hadoop.tools.rumen.Hadoop20JHParser -->
- <class name="Hadoop20JHParser" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.tools.rumen.JobHistoryParser"/>
- <constructor name="Hadoop20JHParser" type="java.io.InputStream"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </constructor>
- <method name="canParse" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="input" type="java.io.InputStream"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Can this parser parse the input?
-
- @param input
- @return Whether this parser can parse the input.
- @throws IOException
-
- We will deem a stream to be a good 0.20 job history stream if the
- first line is exactly "Meta VERSION=\"1\" ."]]>
- </doc>
- </method>
- <method name="nextEvent" return="org.apache.hadoop.mapreduce.jobhistory.HistoryEvent"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[{@link JobHistoryParser} to parse job histories for hadoop 0.20 (META=1).]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.Hadoop20JHParser -->
- <!-- start class org.apache.hadoop.tools.rumen.HadoopLogsAnalyzer -->
- <class name="HadoopLogsAnalyzer" extends="org.apache.hadoop.conf.Configured"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.util.Tool"/>
- <constructor name="HadoopLogsAnalyzer"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="run" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="args" type="java.lang.String[]"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="main"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="args" type="java.lang.String[]"/>
- <doc>
- <![CDATA[@param args
-
- Last arg is the input file. That file can be a directory, in which
- case you get all the files in sorted order. We will decompress
- files whose nmes end in .gz .
-
- switches: -c collect line types.
-
- -d debug mode
-
- -delays print out the delays [interval between job submit time and
- launch time]
-
- -runtimes print out the job runtimes
-
- -spreads print out the ratio of 10%ile and 90%ile, of both the
- successful map task attempt run times and the the successful
- reduce task attempt run times
-
- -tasktimes prints out individual task time distributions
-
- collects all the line types and prints the first example of each
- one]]>
- </doc>
- </method>
- <doc>
- <![CDATA[This is the main class for rumen log mining functionality.
-
- It reads a directory of job tracker logs, and computes various information
- about it. See {@code usage()}, below.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.HadoopLogsAnalyzer -->
- <!-- start interface org.apache.hadoop.tools.rumen.InputDemuxer -->
- <interface name="InputDemuxer" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="java.io.Closeable"/>
- <method name="bindTo"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="path" type="org.apache.hadoop.fs.Path"/>
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Bind the {@link InputDemuxer} to a particular file.
-
- @param path
- The path to the file it should bind to.
- @param conf
- Configuration
- @throws IOException
-
- Returns true when the binding succeeds. If the file can be read
- but is in the wrong format, returns false. IOException is
- reserved for read errors.]]>
- </doc>
- </method>
- <method name="getNext" return="org.apache.hadoop.tools.rumen.Pair"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get the next <name, input> pair. The name should preserve the original job
- history file or job conf file name. The input object should be closed
- before calling getNext() again. The old input object would be invalid after
- calling getNext() again.
-
- @return the next <name, input> pair.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[{@link InputDemuxer} dem-ultiplexes the input files into individual input
- streams.]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.tools.rumen.InputDemuxer -->
- <!-- start class org.apache.hadoop.tools.rumen.Job20LineHistoryEventEmitter -->
- <class name="Job20LineHistoryEventEmitter" extends="org.apache.hadoop.tools.rumen.HistoryEventEmitter"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.Job20LineHistoryEventEmitter -->
- <!-- start class org.apache.hadoop.tools.rumen.JobBuilder -->
- <class name="JobBuilder" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="JobBuilder" type="java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getJobID" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="process"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="event" type="org.apache.hadoop.mapreduce.jobhistory.HistoryEvent"/>
- <doc>
- <![CDATA[Process one {@link HistoryEvent}
-
- @param event
- The {@link HistoryEvent} to be processed.]]>
- </doc>
- </method>
- <method name="process"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="java.util.Properties"/>
- <doc>
- <![CDATA[Process a collection of JobConf {@link Properties}. We do not restrict it
- to be called once. It is okay to process a conf before, during or after the
- events.
-
- @param conf
- The job conf properties to be added.]]>
- </doc>
- </method>
- <method name="build" return="org.apache.hadoop.tools.rumen.LoggedJob"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Request the builder to build the final object. Once called, the
- {@link JobBuilder} would accept no more events or job-conf properties.
-
- @return Parsed {@link LoggedJob} object.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[{@link JobBuilder} builds one job. It processes a sequence of
- {@link HistoryEvent}s.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.JobBuilder -->
- <!-- start class org.apache.hadoop.tools.rumen.JobConfigurationParser -->
- <class name="JobConfigurationParser" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="JobConfigurationParser" type="java.util.List"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Constructor
-
- @param interested
- properties we should extract from the job configuration xml.]]>
- </doc>
- </constructor>
- <doc>
- <![CDATA[{@link JobConfigurationParser} parses the job configuration xml file, and
- extracts various framework specific properties. It parses the file using a
- stream-parser and thus is more memory efficient. [This optimization may be
- postponed for a future release]]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.JobConfigurationParser -->
- <!-- start class org.apache.hadoop.tools.rumen.JobConfPropertyNames -->
- <class name="JobConfPropertyNames" extends="java.lang.Enum"
- abstract="false"
- static="false" final="true" visibility="public"
- deprecated="not deprecated">
- <method name="values" return="org.apache.hadoop.tools.rumen.JobConfPropertyNames[]"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="valueOf" return="org.apache.hadoop.tools.rumen.JobConfPropertyNames"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- </method>
- <method name="getCandidates" return="java.lang.String[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.JobConfPropertyNames -->
- <!-- start interface org.apache.hadoop.tools.rumen.JobHistoryParser -->
- <interface name="JobHistoryParser" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="java.io.Closeable"/>
- <method name="nextEvent" return="org.apache.hadoop.mapreduce.jobhistory.HistoryEvent"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get the next {@link HistoryEvent}
- @return the next {@link HistoryEvent}. If no more events left, return null.
- @throws IOException]]>
- </doc>
- </method>
- <doc>
- <![CDATA[{@link JobHistoryParser} defines the interface of a Job History file parser.]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.tools.rumen.JobHistoryParser -->
- <!-- start class org.apache.hadoop.tools.rumen.JobHistoryParserFactory -->
- <class name="JobHistoryParserFactory" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="JobHistoryParserFactory"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getParser" return="org.apache.hadoop.tools.rumen.JobHistoryParser"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="ris" type="org.apache.hadoop.tools.rumen.RewindableInputStream"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[{@link JobHistoryParserFactory} is a singleton class that attempts to
- determine the version of job history and return a proper parser.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.JobHistoryParserFactory -->
- <!-- start class org.apache.hadoop.tools.rumen.JobHistoryParserFactory.VersionDetector -->
- <class name="JobHistoryParserFactory.VersionDetector" extends="java.lang.Enum"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <method name="values" return="org.apache.hadoop.tools.rumen.JobHistoryParserFactory.VersionDetector[]"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="valueOf" return="org.apache.hadoop.tools.rumen.JobHistoryParserFactory.VersionDetector"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- </method>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.JobHistoryParserFactory.VersionDetector -->
- <!-- start interface org.apache.hadoop.tools.rumen.JobStory -->
- <interface name="JobStory" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <method name="getJobConf" return="org.apache.hadoop.mapred.JobConf"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the {@link JobConf} for the job.
- @return the <code>JobConf</code> for the job]]>
- </doc>
- </method>
- <method name="getName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the job name.
- @return the job name]]>
- </doc>
- </method>
- <method name="getJobID" return="org.apache.hadoop.mapreduce.JobID"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the job ID
- @return the job ID]]>
- </doc>
- </method>
- <method name="getUser" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the user who ran the job.
- @return the user who ran the job]]>
- </doc>
- </method>
- <method name="getSubmissionTime" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the job submission time.
- @return the job submission time]]>
- </doc>
- </method>
- <method name="getNumberMaps" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the number of maps in the {@link JobStory}.
- @return the number of maps in the <code>Job</code>]]>
- </doc>
- </method>
- <method name="getNumberReduces" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the number of reduce in the {@link JobStory}.
- @return the number of reduces in the <code>Job</code>]]>
- </doc>
- </method>
- <method name="getInputSplits" return="org.apache.hadoop.mapreduce.InputSplit[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the input splits for the job.
- @return the input splits for the job]]>
- </doc>
- </method>
- <method name="getTaskInfo" return="org.apache.hadoop.tools.rumen.TaskInfo"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskType" type="org.apache.hadoop.mapreduce.TaskType"/>
- <param name="taskNumber" type="int"/>
- <doc>
- <![CDATA[Get {@link TaskInfo} for a given task.
- @param taskType {@link TaskType} of the task
- @param taskNumber Partition number of the task
- @return the <code>TaskInfo</code> for the given task]]>
- </doc>
- </method>
- <method name="getTaskAttemptInfo" return="org.apache.hadoop.tools.rumen.TaskAttemptInfo"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskType" type="org.apache.hadoop.mapreduce.TaskType"/>
- <param name="taskNumber" type="int"/>
- <param name="taskAttemptNumber" type="int"/>
- <doc>
- <![CDATA[Get {@link TaskAttemptInfo} for a given task-attempt, without regard to
- impact of locality (e.g. not needed to make scheduling decisions).
- @param taskType {@link TaskType} of the task-attempt
- @param taskNumber Partition number of the task-attempt
- @param taskAttemptNumber Attempt number of the task
- @return the <code>TaskAttemptInfo</code> for the given task-attempt]]>
- </doc>
- </method>
- <method name="getMapTaskAttemptInfoAdjusted" return="org.apache.hadoop.tools.rumen.TaskAttemptInfo"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskNumber" type="int"/>
- <param name="taskAttemptNumber" type="int"/>
- <param name="locality" type="int"/>
- <doc>
- <![CDATA[Get {@link TaskAttemptInfo} for a given task-attempt, considering impact
- of locality.
- @param taskNumber Partition number of the task-attempt
- @param taskAttemptNumber Attempt number of the task
- @param locality Data locality of the task as scheduled in simulation
- @return the <code>TaskAttemptInfo</code> for the given task-attempt]]>
- </doc>
- </method>
- <method name="getOutcome" return="org.apache.hadoop.tools.rumen.Pre21JobHistoryConstants.Values"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the outcome of the job execution.
- @return The outcome of the job execution.]]>
- </doc>
- </method>
- <method name="getQueueName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the queue where the job is submitted.
- @return the queue where the job is submitted.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[{@link JobStory} represents the runtime information available for a
- completed Map-Reduce job.]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.tools.rumen.JobStory -->
- <!-- start interface org.apache.hadoop.tools.rumen.JobStoryProducer -->
- <interface name="JobStoryProducer" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="java.io.Closeable"/>
- <method name="getNextJob" return="org.apache.hadoop.tools.rumen.JobStory"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get the next job.
- @return The next job. Or null if no more job is available.
- @throws IOException]]>
- </doc>
- </method>
- <doc>
- <![CDATA[{@link JobStoryProducer} produces the sequence of {@link JobStory}'s.]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.tools.rumen.JobStoryProducer -->
- <!-- start class org.apache.hadoop.tools.rumen.JobTraceReader -->
- <class name="JobTraceReader" extends="org.apache.hadoop.tools.rumen.JsonObjectMapperParser"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="JobTraceReader" type="org.apache.hadoop.fs.Path, org.apache.hadoop.conf.Configuration"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Constructor.
-
- @param path
- Path to the JSON trace file, possibly compressed.
- @param conf
- @throws IOException]]>
- </doc>
- </constructor>
- <constructor name="JobTraceReader" type="java.io.InputStream"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Constructor.
-
- @param input
- The input stream for the JSON trace.]]>
- </doc>
- </constructor>
- <doc>
- <![CDATA[Reading JSON-encoded job traces and produce {@link LoggedJob} instances.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.JobTraceReader -->
- <!-- start class org.apache.hadoop.tools.rumen.JsonObjectMapperWriter -->
- <class name="JsonObjectMapperWriter" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="java.io.Closeable"/>
- <constructor name="JsonObjectMapperWriter" type="java.io.OutputStream, boolean"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </constructor>
- <method name="write"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="object" type="T"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[Simple wrapper around {@link JsonGenerator} to write objects in JSON format.
- @param <T> The type of the objects to be written.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.JsonObjectMapperWriter -->
- <!-- start class org.apache.hadoop.tools.rumen.LoggedDiscreteCDF -->
- <class name="LoggedDiscreteCDF" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.tools.rumen.DeepCompare"/>
- <constructor name="LoggedDiscreteCDF"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getMinimum" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getRankings" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getMaximum" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getNumberValues" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="deepCompare"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="comparand" type="org.apache.hadoop.tools.rumen.DeepCompare"/>
- <param name="loc" type="org.apache.hadoop.tools.rumen.TreePath"/>
- <exception name="DeepInequalityException" type="org.apache.hadoop.tools.rumen.DeepInequalityException"/>
- </method>
- <doc>
- <![CDATA[A {@link LoggedDiscreteCDF} is a discrete approximation of a cumulative
- distribution function, with this class set up to meet the requirements of the
- Jackson JSON parser/generator.
-
- All of the public methods are simply accessors for the instance variables we
- want to write out in the JSON files.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.LoggedDiscreteCDF -->
- <!-- start class org.apache.hadoop.tools.rumen.LoggedJob -->
- <class name="LoggedJob" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.tools.rumen.DeepCompare"/>
- <method name="setUnknownAttribute"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="attributeName" type="java.lang.String"/>
- <param name="ignored" type="java.lang.Object"/>
- </method>
- <method name="getUser" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getJobID" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getPriority" return="org.apache.hadoop.tools.rumen.LoggedJob.JobPriority"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getComputonsPerMapInputByte" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getComputonsPerMapOutputByte" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getComputonsPerReduceInputByte" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getComputonsPerReduceOutputByte" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getSubmitTime" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getLaunchTime" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getFinishTime" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getHeapMegabytes" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getTotalMaps" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getTotalReduces" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getOutcome" return="org.apache.hadoop.tools.rumen.Pre21JobHistoryConstants.Values"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getJobtype" return="org.apache.hadoop.tools.rumen.LoggedJob.JobType"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getDirectDependantJobs" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getMapTasks" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getReduceTasks" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getOtherTasks" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getSuccessfulMapAttemptCDFs" return="java.util.ArrayList"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getFailedMapAttemptCDFs" return="java.util.ArrayList"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getSuccessfulReduceAttemptCDF" return="org.apache.hadoop.tools.rumen.LoggedDiscreteCDF"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getFailedReduceAttemptCDF" return="org.apache.hadoop.tools.rumen.LoggedDiscreteCDF"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getMapperTriesToSucceed" return="double[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getFailedMapperFraction" return="double"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getRelativeTime" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getQueue" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getJobName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getClusterMapMB" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getClusterReduceMB" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getJobMapMB" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getJobReduceMB" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="deepCompare"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="comparand" type="org.apache.hadoop.tools.rumen.DeepCompare"/>
- <param name="loc" type="org.apache.hadoop.tools.rumen.TreePath"/>
- <exception name="DeepInequalityException" type="org.apache.hadoop.tools.rumen.DeepInequalityException"/>
- </method>
- <doc>
- <![CDATA[A {@link LoggedDiscreteCDF} is a representation of an hadoop job, with the
- details of this class set up to meet the requirements of the Jackson JSON
- parser/generator.
-
- All of the public methods are simply accessors for the instance variables we
- want to write out in the JSON files.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.LoggedJob -->
- <!-- start class org.apache.hadoop.tools.rumen.LoggedJob.JobPriority -->
- <class name="LoggedJob.JobPriority" extends="java.lang.Enum"
- abstract="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <method name="values" return="org.apache.hadoop.tools.rumen.LoggedJob.JobPriority[]"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="valueOf" return="org.apache.hadoop.tools.rumen.LoggedJob.JobPriority"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- </method>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.LoggedJob.JobPriority -->
- <!-- start class org.apache.hadoop.tools.rumen.LoggedJob.JobType -->
- <class name="LoggedJob.JobType" extends="java.lang.Enum"
- abstract="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <method name="values" return="org.apache.hadoop.tools.rumen.LoggedJob.JobType[]"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="valueOf" return="org.apache.hadoop.tools.rumen.LoggedJob.JobType"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- </method>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.LoggedJob.JobType -->
- <!-- start class org.apache.hadoop.tools.rumen.LoggedLocation -->
- <class name="LoggedLocation" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.tools.rumen.DeepCompare"/>
- <constructor name="LoggedLocation"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getLayers" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="setUnknownAttribute"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="attributeName" type="java.lang.String"/>
- <param name="ignored" type="java.lang.Object"/>
- </method>
- <method name="deepCompare"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="comparand" type="org.apache.hadoop.tools.rumen.DeepCompare"/>
- <param name="loc" type="org.apache.hadoop.tools.rumen.TreePath"/>
- <exception name="DeepInequalityException" type="org.apache.hadoop.tools.rumen.DeepInequalityException"/>
- </method>
- <doc>
- <![CDATA[A {@link LoggedLocation} is a representation of a point in an hierarchical
- network, represented as a series of membership names, broadest first.
-
- For example, if your network has <i>hosts</i> grouped into <i>racks</i>, then
- in onecluster you might have a node {@code node1} on rack {@code rack1}. This
- would be represented with a ArrayList of two layers, with two {@link String}
- s being {@code "rack1"} and {@code "node1"}.
-
- The details of this class are set up to meet the requirements of the Jackson
- JSON parser/generator.
-
- All of the public methods are simply accessors for the instance variables we
- want to write out in the JSON files.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.LoggedLocation -->
- <!-- start class org.apache.hadoop.tools.rumen.LoggedNetworkTopology -->
- <class name="LoggedNetworkTopology" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.tools.rumen.DeepCompare"/>
- <constructor name="LoggedNetworkTopology"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setUnknownAttribute"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="attributeName" type="java.lang.String"/>
- <param name="ignored" type="java.lang.Object"/>
- </method>
- <method name="getName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getChildren" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="deepCompare"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="comparand" type="org.apache.hadoop.tools.rumen.DeepCompare"/>
- <param name="loc" type="org.apache.hadoop.tools.rumen.TreePath"/>
- <exception name="DeepInequalityException" type="org.apache.hadoop.tools.rumen.DeepInequalityException"/>
- </method>
- <doc>
- <![CDATA[A {@link LoggedNetworkTopology} represents a tree that in turn represents a
- hierarchy of hosts. The current version requires the tree to have all leaves
- at the same level.
-
- All of the public methods are simply accessors for the instance variables we
- want to write out in the JSON files.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.LoggedNetworkTopology -->
- <!-- start class org.apache.hadoop.tools.rumen.LoggedSingleRelativeRanking -->
- <class name="LoggedSingleRelativeRanking" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.tools.rumen.DeepCompare"/>
- <constructor name="LoggedSingleRelativeRanking"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setUnknownAttribute"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="attributeName" type="java.lang.String"/>
- <param name="ignored" type="java.lang.Object"/>
- </method>
- <method name="getRelativeRanking" return="double"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getDatum" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="deepCompare"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="comparand" type="org.apache.hadoop.tools.rumen.DeepCompare"/>
- <param name="loc" type="org.apache.hadoop.tools.rumen.TreePath"/>
- <exception name="DeepInequalityException" type="org.apache.hadoop.tools.rumen.DeepInequalityException"/>
- </method>
- <doc>
- <![CDATA[A {@link LoggedSingleRelativeRanking} represents an X-Y coordinate of a
- single point in a discrete CDF.
-
- All of the public methods are simply accessors for the instance variables we
- want to write out in the JSON files.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.LoggedSingleRelativeRanking -->
- <!-- start class org.apache.hadoop.tools.rumen.LoggedTask -->
- <class name="LoggedTask" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.tools.rumen.DeepCompare"/>
- <method name="setUnknownAttribute"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="attributeName" type="java.lang.String"/>
- <param name="ignored" type="java.lang.Object"/>
- </method>
- <method name="getInputBytes" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getInputRecords" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getOutputBytes" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getOutputRecords" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getTaskID" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getStartTime" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getFinishTime" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getAttempts" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getPreferredLocations" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getTaskStatus" return="org.apache.hadoop.tools.rumen.Pre21JobHistoryConstants.Values"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getTaskType" return="org.apache.hadoop.tools.rumen.Pre21JobHistoryConstants.Values"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="incorporateCounters"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="counters" type="org.apache.hadoop.mapreduce.jobhistory.JhCounters"/>
- </method>
- <method name="deepCompare"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="comparand" type="org.apache.hadoop.tools.rumen.DeepCompare"/>
- <param name="loc" type="org.apache.hadoop.tools.rumen.TreePath"/>
- <exception name="DeepInequalityException" type="org.apache.hadoop.tools.rumen.DeepInequalityException"/>
- </method>
- <doc>
- <![CDATA[A {@link LoggedTask} represents a [hadoop] task that is part of a hadoop job.
- It knows about the [pssibly empty] sequence of attempts, its I/O footprint,
- and its runtime.
-
- All of the public methods are simply accessors for the instance variables we
- want to write out in the JSON files.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.LoggedTask -->
- <!-- start class org.apache.hadoop.tools.rumen.LoggedTaskAttempt -->
- <class name="LoggedTaskAttempt" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.tools.rumen.DeepCompare"/>
- <method name="setUnknownAttribute"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="attributeName" type="java.lang.String"/>
- <param name="ignored" type="java.lang.Object"/>
- </method>
- <method name="getShuffleFinished" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getSortFinished" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getAttemptID" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getResult" return="org.apache.hadoop.tools.rumen.Pre21JobHistoryConstants.Values"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getStartTime" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getFinishTime" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getHostName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getHdfsBytesRead" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getHdfsBytesWritten" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getFileBytesRead" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getFileBytesWritten" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getMapInputRecords" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getMapOutputBytes" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getMapOutputRecords" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getCombineInputRecords" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getReduceInputGroups" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getReduceInputRecords" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getReduceShuffleBytes" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getReduceOutputRecords" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getSpilledRecords" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getLocation" return="org.apache.hadoop.tools.rumen.LoggedLocation"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getMapInputBytes" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="incorporateCounters"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="counters" type="org.apache.hadoop.mapreduce.jobhistory.JhCounters"/>
- </method>
- <method name="deepCompare"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="comparand" type="org.apache.hadoop.tools.rumen.DeepCompare"/>
- <param name="loc" type="org.apache.hadoop.tools.rumen.TreePath"/>
- <exception name="DeepInequalityException" type="org.apache.hadoop.tools.rumen.DeepInequalityException"/>
- </method>
- <doc>
- <![CDATA[A {@link LoggedTaskAttempt} represents an attempt to run an hadoop task in a
- hadoop job. Note that a task can have several attempts.
-
- All of the public methods are simply accessors for the instance variables we
- want to write out in the JSON files.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.LoggedTaskAttempt -->
- <!-- start class org.apache.hadoop.tools.rumen.MachineNode -->
- <class name="MachineNode" extends="org.apache.hadoop.tools.rumen.Node"
- abstract="false"
- static="false" final="true" visibility="public"
- deprecated="not deprecated">
- <method name="equals" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="obj" type="java.lang.Object"/>
- </method>
- <method name="hashCode" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getMemory" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the available physical RAM of the node.
- @return The available physical RAM of the node, in KB.]]>
- </doc>
- </method>
- <method name="getMapSlots" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the number of map slots of the node.
- @return The number of map slots of the node.]]>
- </doc>
- </method>
- <method name="getReduceSlots" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the number of reduce slots of the node.
- @return The number of reduce slots fo the node.]]>
- </doc>
- </method>
- <method name="getMemoryPerMapSlot" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the amount of RAM reserved for each map slot.
- @return the amount of RAM reserved for each map slot, in KB.]]>
- </doc>
- </method>
- <method name="getMemoryPerReduceSlot" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the amount of RAM reserved for each reduce slot.
- @return the amount of RAM reserved for each reduce slot, in KB.]]>
- </doc>
- </method>
- <method name="getNumCores" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the number of cores of the node.
- @return the number of cores of the node.]]>
- </doc>
- </method>
- <method name="getRackNode" return="org.apache.hadoop.tools.rumen.RackNode"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the rack node that the machine belongs to.
-
- @return The rack node that the machine belongs to. Returns null if the
- machine does not belong to any rack.]]>
- </doc>
- </method>
- <method name="addChild" return="boolean"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="child" type="org.apache.hadoop.tools.rumen.Node"/>
- </method>
- <doc>
- <![CDATA[{@link MachineNode} represents the configuration of a cluster node.
- {@link MachineNode} should be constructed by {@link MachineNode.Builder}.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.MachineNode -->
- <!-- start class org.apache.hadoop.tools.rumen.MachineNode.Builder -->
- <class name="MachineNode.Builder" extends="java.lang.Object"
- abstract="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <constructor name="MachineNode.Builder" type="java.lang.String, int"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Start building a new NodeInfo object.
- @param name
- Unique name of the node. Typically the fully qualified domain
- name.]]>
- </doc>
- </constructor>
- <method name="setMemory" return="org.apache.hadoop.tools.rumen.MachineNode.Builder"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="memory" type="long"/>
- <doc>
- <![CDATA[Set the physical memory of the node.
- @param memory Available RAM in KB.]]>
- </doc>
- </method>
- <method name="setMapSlots" return="org.apache.hadoop.tools.rumen.MachineNode.Builder"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="mapSlots" type="int"/>
- <doc>
- <![CDATA[Set the number of map slot for the node.
- @param mapSlots The number of map slots for the node.]]>
- </doc>
- </method>
- <method name="setReduceSlots" return="org.apache.hadoop.tools.rumen.MachineNode.Builder"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="reduceSlots" type="int"/>
- <doc>
- <![CDATA[Set the number of reduce slot for the node.
- @param reduceSlots The number of reduce slots for the node.]]>
- </doc>
- </method>
- <method name="setMemoryPerMapSlot" return="org.apache.hadoop.tools.rumen.MachineNode.Builder"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="memoryPerMapSlot" type="long"/>
- <doc>
- <![CDATA[Set the amount of RAM reserved for each map slot.
- @param memoryPerMapSlot The amount of RAM reserved for each map slot, in KB.]]>
- </doc>
- </method>
- <method name="setMemoryPerReduceSlot" return="org.apache.hadoop.tools.rumen.MachineNode.Builder"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="memoryPerReduceSlot" type="long"/>
- <doc>
- <![CDATA[Set the amount of RAM reserved for each reduce slot.
- @param memoryPerReduceSlot The amount of RAM reserved for each reduce slot, in KB.]]>
- </doc>
- </method>
- <method name="setNumCores" return="org.apache.hadoop.tools.rumen.MachineNode.Builder"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="numCores" type="int"/>
- <doc>
- <![CDATA[Set the number of cores for the node.
- @param numCores Number of cores for the node.]]>
- </doc>
- </method>
- <method name="cloneFrom" return="org.apache.hadoop.tools.rumen.MachineNode.Builder"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="ref" type="org.apache.hadoop.tools.rumen.MachineNode"/>
- <doc>
- <![CDATA[Clone the settings from a reference {@link MachineNode} object.
- @param ref The reference {@link MachineNode} object.]]>
- </doc>
- </method>
- <method name="build" return="org.apache.hadoop.tools.rumen.MachineNode"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Build the {@link MachineNode} object.
- @return The {@link MachineNode} object being built.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Builder for a NodeInfo object]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.MachineNode.Builder -->
- <!-- start class org.apache.hadoop.tools.rumen.MapAttempt20LineHistoryEventEmitter -->
- <class name="MapAttempt20LineHistoryEventEmitter" extends="org.apache.hadoop.tools.rumen.TaskAttempt20LineEventEmitter"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="MapAttempt20LineHistoryEventEmitter"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </constructor>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.MapAttempt20LineHistoryEventEmitter -->
- <!-- start class org.apache.hadoop.tools.rumen.MapTaskAttemptInfo -->
- <class name="MapTaskAttemptInfo" extends="org.apache.hadoop.tools.rumen.TaskAttemptInfo"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="MapTaskAttemptInfo" type="org.apache.hadoop.mapred.TaskStatus.State, org.apache.hadoop.tools.rumen.TaskInfo, long"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getRuntime" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getMapRuntime" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the runtime for the <b>map</b> phase of the map-task attempt.
-
- @return the runtime for the <b>map</b> phase of the map-task attempt]]>
- </doc>
- </method>
- <doc>
- <![CDATA[{@link MapTaskAttemptInfo} represents the information with regard to a
- map task attempt.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.MapTaskAttemptInfo -->
- <!-- start class org.apache.hadoop.tools.rumen.Node -->
- <class name="Node" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="java.lang.Comparable"/>
- <constructor name="Node" type="java.lang.String, int"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@param name
- A unique name to identify a node in the cluster.
- @param level
- The level of the node in the cluster]]>
- </doc>
- </constructor>
- <method name="getName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the name of the node.
-
- @return The name of the node.]]>
- </doc>
- </method>
- <method name="getLevel" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the level of the node.
- @return The level of the node.]]>
- </doc>
- </method>
- <method name="addChild" return="boolean"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="child" type="org.apache.hadoop.tools.rumen.Node"/>
- <doc>
- <![CDATA[Add a child node to this node.
- @param child The child node to be added. The child node should currently not be belong to another cluster topology.
- @return Boolean indicating whether the node is successfully added.]]>
- </doc>
- </method>
- <method name="hasChildren" return="boolean"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Does this node have any children?
- @return Boolean indicate whether this node has any children.]]>
- </doc>
- </method>
- <method name="getChildren" return="java.util.Set"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the children of this node.
-
- @return The children of this node. If no child, an empty set will be
- returned. The returned set is read-only.]]>
- </doc>
- </method>
- <method name="getParent" return="org.apache.hadoop.tools.rumen.Node"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the parent node.
- @return the parent node. If root node, return null.]]>
- </doc>
- </method>
- <method name="hashCode" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="equals" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="obj" type="java.lang.Object"/>
- </method>
- <method name="toString" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="compareTo" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="o" type="org.apache.hadoop.tools.rumen.Node"/>
- </method>
- <doc>
- <![CDATA[{@link Node} represents a node in the cluster topology. A node can be a
- {@link MachineNode}, or a {@link RackNode}, etc.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.Node -->
- <!-- start interface org.apache.hadoop.tools.rumen.Outputter -->
- <interface name="Outputter" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="java.io.Closeable"/>
- <method name="init"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="path" type="org.apache.hadoop.fs.Path"/>
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Initialize the {@link Outputter} to a specific path.
- @param path The {@link Path} to the output file.
- @param conf Configuration
- @throws IOException]]>
- </doc>
- </method>
- <method name="output"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="object" type="T"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Output an object.
- @param object The objecte.
- @throws IOException]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Interface to output a sequence of objects of type T.]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.tools.rumen.Outputter -->
- <!-- start class org.apache.hadoop.tools.rumen.Pre21JobHistoryConstants -->
- <class name="Pre21JobHistoryConstants" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="Pre21JobHistoryConstants"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.Pre21JobHistoryConstants -->
- <!-- start class org.apache.hadoop.tools.rumen.Pre21JobHistoryConstants.Values -->
- <class name="Pre21JobHistoryConstants.Values" extends="java.lang.Enum"
- abstract="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <method name="values" return="org.apache.hadoop.tools.rumen.Pre21JobHistoryConstants.Values[]"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="valueOf" return="org.apache.hadoop.tools.rumen.Pre21JobHistoryConstants.Values"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- </method>
- <doc>
- <![CDATA[This enum contains some of the values commonly used by history log events.
- since values in history can only be strings - Values.name() is used in
- most places in history file.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.Pre21JobHistoryConstants.Values -->
- <!-- start class org.apache.hadoop.tools.rumen.RackNode -->
- <class name="RackNode" extends="org.apache.hadoop.tools.rumen.Node"
- abstract="false"
- static="false" final="true" visibility="public"
- deprecated="not deprecated">
- <constructor name="RackNode" type="java.lang.String, int"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="addChild" return="boolean"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="child" type="org.apache.hadoop.tools.rumen.Node"/>
- </method>
- <method name="getMachinesInRack" return="java.util.Set"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the machine nodes that belong to the rack.
- @return The machine nodes that belong to the rack.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[{@link RackNode} represents a rack node in the cluster topology.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.RackNode -->
- <!-- start class org.apache.hadoop.tools.rumen.RandomSeedGenerator -->
- <class name="RandomSeedGenerator" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="RandomSeedGenerator"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getSeed" return="long"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="streamId" type="java.lang.String"/>
- <param name="masterSeed" type="long"/>
- <doc>
- <![CDATA[Generates a new random seed.
- @param streamId a string identifying the stream of random numbers
- @param masterSeed higher level master random seed
- @return the random seed. Different (streamId, masterSeed) pairs result in
- (vastly) different random seeds.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[The purpose of this class is to generate new random seeds from a master
- seed. This is needed to make the Random().next*() calls in rumen and mumak
- deterministic so that mumak simulations become deterministically replayable.
- In these tools we need many independent streams of random numbers, some of
- which are created dynamically. We seed these streams with the sub-seeds
- returned by RandomSeedGenerator.
-
- For a slightly more complicated approach to generating multiple streams of
- random numbers with better theoretical guarantees, see
- P. L'Ecuyer, R. Simard, E. J. Chen, and W. D. Kelton,
- ``An Objected-Oriented Random-Number Package with Many Long Streams and
- Substreams'', Operations Research, 50, 6 (2002), 1073--1075
- http://www.iro.umontreal.ca/~lecuyer/papers.html
- http://www.iro.umontreal.ca/~lecuyer/myftp/streams00/]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.RandomSeedGenerator -->
- <!-- start class org.apache.hadoop.tools.rumen.ReduceAttempt20LineHistoryEventEmitter -->
- <class name="ReduceAttempt20LineHistoryEventEmitter" extends="org.apache.hadoop.tools.rumen.TaskAttempt20LineEventEmitter"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.ReduceAttempt20LineHistoryEventEmitter -->
- <!-- start class org.apache.hadoop.tools.rumen.ReduceTaskAttemptInfo -->
- <class name="ReduceTaskAttemptInfo" extends="org.apache.hadoop.tools.rumen.TaskAttemptInfo"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="ReduceTaskAttemptInfo" type="org.apache.hadoop.mapred.TaskStatus.State, org.apache.hadoop.tools.rumen.TaskInfo, long, long, long"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getReduceRuntime" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the runtime for the <b>reduce</b> phase of the reduce task-attempt.
-
- @return the runtime for the <b>reduce</b> phase of the reduce task-attempt]]>
- </doc>
- </method>
- <method name="getShuffleRuntime" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the runtime for the <b>shuffle</b> phase of the reduce task-attempt.
-
- @return the runtime for the <b>shuffle</b> phase of the reduce task-attempt]]>
- </doc>
- </method>
- <method name="getMergeRuntime" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the runtime for the <b>merge</b> phase of the reduce task-attempt
-
- @return the runtime for the <b>merge</b> phase of the reduce task-attempt]]>
- </doc>
- </method>
- <method name="getRuntime" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <doc>
- <![CDATA[{@link ReduceTaskAttemptInfo} represents the information with regard to a
- reduce task attempt.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.ReduceTaskAttemptInfo -->
- <!-- start class org.apache.hadoop.tools.rumen.RewindableInputStream -->
- <class name="RewindableInputStream" extends="java.io.InputStream"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="RewindableInputStream" type="java.io.InputStream"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Constructor.
-
- @param input]]>
- </doc>
- </constructor>
- <constructor name="RewindableInputStream" type="java.io.InputStream, int"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Constructor
-
- @param input
- input stream.
- @param maxBytesToRemember
- Maximum number of bytes we need to remember at the beginning of
- the stream. If {@link #rewind()} is called after so many bytes are
- read from the stream, {@link #rewind()} would fail.]]>
- </doc>
- </constructor>
- <method name="read" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="read" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="buffer" type="byte[]"/>
- <param name="offset" type="int"/>
- <param name="length" type="int"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="rewind" return="java.io.InputStream"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[A simple wrapper class to make any input stream "rewindable". It could be
- made more memory efficient by grow the internal buffer adaptively.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.RewindableInputStream -->
- <!-- start class org.apache.hadoop.tools.rumen.Task20LineHistoryEventEmitter -->
- <class name="Task20LineHistoryEventEmitter" extends="org.apache.hadoop.tools.rumen.HistoryEventEmitter"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="Task20LineHistoryEventEmitter"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </constructor>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.Task20LineHistoryEventEmitter -->
- <!-- start class org.apache.hadoop.tools.rumen.TaskAttempt20LineEventEmitter -->
- <class name="TaskAttempt20LineEventEmitter" extends="org.apache.hadoop.tools.rumen.HistoryEventEmitter"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="TaskAttempt20LineEventEmitter"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </constructor>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.TaskAttempt20LineEventEmitter -->
- <!-- start class org.apache.hadoop.tools.rumen.TaskAttemptInfo -->
- <class name="TaskAttemptInfo" extends="java.lang.Object"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="TaskAttemptInfo" type="org.apache.hadoop.mapred.TaskStatus.State, org.apache.hadoop.tools.rumen.TaskInfo"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </constructor>
- <method name="getRunState" return="org.apache.hadoop.mapred.TaskStatus.State"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the final {@link State} of the task-attempt.
-
- @return the final <code>State</code> of the task-attempt]]>
- </doc>
- </method>
- <method name="getRuntime" return="long"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the total runtime for the task-attempt.
-
- @return the total runtime for the task-attempt]]>
- </doc>
- </method>
- <method name="getTaskInfo" return="org.apache.hadoop.tools.rumen.TaskInfo"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the {@link TaskInfo} for the given task-attempt.
-
- @return the <code>TaskInfo</code> for the given task-attempt]]>
- </doc>
- </method>
- <field name="state" type="org.apache.hadoop.mapred.TaskStatus.State"
- transient="false" volatile="false"
- static="false" final="true" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="taskInfo" type="org.apache.hadoop.tools.rumen.TaskInfo"
- transient="false" volatile="false"
- static="false" final="true" visibility="protected"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[{@link TaskAttemptInfo} is a collection of statistics about a particular
- task-attempt gleaned from job-history of the job.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.TaskAttemptInfo -->
- <!-- start class org.apache.hadoop.tools.rumen.TaskInfo -->
- <class name="TaskInfo" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="TaskInfo" type="long, int, long, int, long"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getInputBytes" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return Raw bytes read from the FileSystem into the task. Note that this
- may not always match the input bytes to the task.]]>
- </doc>
- </method>
- <method name="getInputRecords" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return Number of records input to this task.]]>
- </doc>
- </method>
- <method name="getOutputBytes" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return Raw bytes written to the destination FileSystem. Note that this may
- not match output bytes.]]>
- </doc>
- </method>
- <method name="getOutputRecords" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return Number of records output from this task.]]>
- </doc>
- </method>
- <method name="getTaskMemory" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return Memory used by the task leq the heap size.]]>
- </doc>
- </method>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.TaskInfo -->
- <!-- start class org.apache.hadoop.tools.rumen.TopologyBuilder -->
- <class name="TopologyBuilder" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="TopologyBuilder"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="process"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="event" type="org.apache.hadoop.mapreduce.jobhistory.HistoryEvent"/>
- <doc>
- <![CDATA[Process one {@link HistoryEvent}
-
- @param event
- The {@link HistoryEvent} to be processed.]]>
- </doc>
- </method>
- <method name="process"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="java.util.Properties"/>
- <doc>
- <![CDATA[Process a collection of JobConf {@link Properties}. We do not restrict it
- to be called once.
-
- @param conf
- The job conf properties to be added.]]>
- </doc>
- </method>
- <method name="build" return="org.apache.hadoop.tools.rumen.LoggedNetworkTopology"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Request the builder to build the final object. Once called, the
- {@link TopologyBuilder} would accept no more events or job-conf properties.
-
- @return Parsed {@link LoggedNetworkTopology} object.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Building the cluster topology.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.TopologyBuilder -->
- <!-- start class org.apache.hadoop.tools.rumen.TraceBuilder -->
- <class name="TraceBuilder" extends="org.apache.hadoop.conf.Configured"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.util.Tool"/>
- <constructor name="TraceBuilder"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="main"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="args" type="java.lang.String[]"/>
- </method>
- <method name="run" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="args" type="java.lang.String[]"/>
- <exception name="Exception" type="java.lang.Exception"/>
- </method>
- <doc>
- <![CDATA[The main driver of the Rumen Parser.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.TraceBuilder -->
- <!-- start class org.apache.hadoop.tools.rumen.TreePath -->
- <class name="TreePath" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="TreePath" type="org.apache.hadoop.tools.rumen.TreePath, java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <constructor name="TreePath" type="org.apache.hadoop.tools.rumen.TreePath, java.lang.String, int"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="toString" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <doc>
- <![CDATA[This describes a path from a node to the root. We use it when we compare two
- trees during rumen unit tests. If the trees are not identical, this chain
- will be converted to a string which describes the path from the root to the
- fields that did not compare.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.TreePath -->
- <!-- start class org.apache.hadoop.tools.rumen.ZombieCluster -->
- <class name="ZombieCluster" extends="org.apache.hadoop.tools.rumen.AbstractClusterStory"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="ZombieCluster" type="org.apache.hadoop.tools.rumen.LoggedNetworkTopology, org.apache.hadoop.tools.rumen.MachineNode"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Construct a homogeneous cluster. We assume that the leaves on the topology
- are {@link MachineNode}s, and the parents of {@link MachineNode}s are
- {@link RackNode}s. We also expect all leaf nodes are on the same level.
-
- @param topology
- The network topology.
- @param defaultNode
- The default node setting.]]>
- </doc>
- </constructor>
- <constructor name="ZombieCluster" type="org.apache.hadoop.fs.Path, org.apache.hadoop.tools.rumen.MachineNode, org.apache.hadoop.conf.Configuration"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Construct a homogeneous cluster. We assume that the leaves on the topology
- are {@link MachineNode}s, and the parents of {@link MachineNode}s are
- {@link RackNode}s. We also expect all leaf nodes are on the same level.
-
- @param path Path to the JSON-encoded topology file.
- @param conf
- @param defaultNode
- The default node setting.
- @throws IOException]]>
- </doc>
- </constructor>
- <constructor name="ZombieCluster" type="java.io.InputStream, org.apache.hadoop.tools.rumen.MachineNode"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Construct a homogeneous cluster. We assume that the leaves on the topology
- are {@link MachineNode}s, and the parents of {@link MachineNode}s are
- {@link RackNode}s. We also expect all leaf nodes are on the same level.
-
- @param input The input stream for the JSON-encoded topology file.
- @param defaultNode
- The default node setting.
- @throws IOException]]>
- </doc>
- </constructor>
- <method name="getClusterTopology" return="org.apache.hadoop.tools.rumen.Node"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <doc>
- <![CDATA[{@link ZombieCluster} rebuilds the cluster topology using the information
- obtained from job history logs.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.ZombieCluster -->
- <!-- start class org.apache.hadoop.tools.rumen.ZombieJob -->
- <class name="ZombieJob" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.tools.rumen.JobStory"/>
- <constructor name="ZombieJob" type="org.apache.hadoop.tools.rumen.LoggedJob, org.apache.hadoop.tools.rumen.ClusterStory, long"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[This constructor creates a {@link ZombieJob} with the same semantics as the
- {@link LoggedJob} passed in this parameter
-
- @param job
- The dead job this ZombieJob instance is based on.
- @param cluster
- The cluster topology where the dead job ran on. This argument can
- be null if we do not have knowledge of the cluster topology.
- @param seed
- Seed for the random number generator for filling in information
- not available from the ZombieJob.]]>
- </doc>
- </constructor>
- <constructor name="ZombieJob" type="org.apache.hadoop.tools.rumen.LoggedJob, org.apache.hadoop.tools.rumen.ClusterStory"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[This constructor creates a {@link ZombieJob} with the same semantics as the
- {@link LoggedJob} passed in this parameter
-
- @param job
- The dead job this ZombieJob instance is based on.
- @param cluster
- The cluster topology where the dead job ran on. This argument can
- be null if we do not have knowledge of the cluster topology.]]>
- </doc>
- </constructor>
- <method name="getJobConf" return="org.apache.hadoop.mapred.JobConf"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getInputSplits" return="org.apache.hadoop.mapreduce.InputSplit[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getJobID" return="org.apache.hadoop.mapreduce.JobID"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getNumberMaps" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getNumberReduces" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getOutcome" return="org.apache.hadoop.tools.rumen.Pre21JobHistoryConstants.Values"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getSubmissionTime" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getQueueName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getNumLoggedMaps" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Getting the number of map tasks that are actually logged in the trace.
- @return The number of map tasks that are actually logged in the trace.]]>
- </doc>
- </method>
- <method name="getNumLoggedReduces" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Getting the number of reduce tasks that are actually logged in the trace.
- @return The number of map tasks that are actually logged in the trace.]]>
- </doc>
- </method>
- <method name="getUser" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getLoggedJob" return="org.apache.hadoop.tools.rumen.LoggedJob"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the underlining {@link LoggedJob} object read directly from the trace.
- This is mainly for debugging.
-
- @return the underlining {@link LoggedJob} object]]>
- </doc>
- </method>
- <method name="getTaskAttemptInfo" return="org.apache.hadoop.tools.rumen.TaskAttemptInfo"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskType" type="org.apache.hadoop.mapreduce.TaskType"/>
- <param name="taskNumber" type="int"/>
- <param name="taskAttemptNumber" type="int"/>
- <doc>
- <![CDATA[Get a {@link TaskAttemptInfo} with a {@link TaskAttemptID} associated with
- taskType, taskNumber, and taskAttemptNumber. This function does not care
- about locality, and follows the following decision logic: 1. Make up a
- {@link TaskAttemptInfo} if the task attempt is missing in trace, 2. Make up
- a {@link TaskAttemptInfo} if the task attempt has a KILLED final status in
- trace, 3. Otherwise (final state is SUCCEEDED or FAILED), construct the
- {@link TaskAttemptInfo} from the trace.]]>
- </doc>
- </method>
- <method name="getTaskInfo" return="org.apache.hadoop.tools.rumen.TaskInfo"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskType" type="org.apache.hadoop.mapreduce.TaskType"/>
- <param name="taskNumber" type="int"/>
- </method>
- <method name="getMapTaskAttemptInfoAdjusted" return="org.apache.hadoop.tools.rumen.TaskAttemptInfo"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskNumber" type="int"/>
- <param name="taskAttemptNumber" type="int"/>
- <param name="locality" type="int"/>
- <doc>
- <![CDATA[Get a {@link TaskAttemptInfo} with a {@link TaskAttemptID} associated with
- taskType, taskNumber, and taskAttemptNumber. This function considers
- locality, and follows the following decision logic: 1. Make up a
- {@link TaskAttemptInfo} if the task attempt is missing in trace, 2. Make up
- a {@link TaskAttemptInfo} if the task attempt has a KILLED final status in
- trace, 3. If final state is FAILED, construct a {@link TaskAttemptInfo}
- from the trace, without considering locality. 4. If final state is
- SUCCEEDED, construct a {@link TaskAttemptInfo} from the trace, with runtime
- scaled according to locality in simulation and locality in trace.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[{@link ZombieJob} is a layer above {@link LoggedJob} raw JSON objects.
-
- Each {@link ZombieJob} object represents a job in job history. For everything
- that exists in job history, contents are returned unchanged faithfully. To
- get input splits of a non-exist task, a non-exist task attempt, or an
- ill-formed task attempt, proper objects are made up from statistical
- sketches.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.ZombieJob -->
- <!-- start class org.apache.hadoop.tools.rumen.ZombieJobProducer -->
- <class name="ZombieJobProducer" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.tools.rumen.JobStoryProducer"/>
- <constructor name="ZombieJobProducer" type="org.apache.hadoop.fs.Path, org.apache.hadoop.tools.rumen.ZombieCluster, org.apache.hadoop.conf.Configuration"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Constructor
-
- @param path
- Path to the JSON trace file, possibly compressed.
- @param cluster
- The topology of the cluster that corresponds to the jobs in the
- trace. The argument can be null if we do not have knowledge of the
- cluster topology.
- @param conf
- @throws IOException]]>
- </doc>
- </constructor>
- <constructor name="ZombieJobProducer" type="org.apache.hadoop.fs.Path, org.apache.hadoop.tools.rumen.ZombieCluster, org.apache.hadoop.conf.Configuration, long"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Constructor
-
- @param path
- Path to the JSON trace file, possibly compressed.
- @param cluster
- The topology of the cluster that corresponds to the jobs in the
- trace. The argument can be null if we do not have knowledge of the
- cluster topology.
- @param conf
- @param randomSeed
- use a deterministic seed.
- @throws IOException]]>
- </doc>
- </constructor>
- <constructor name="ZombieJobProducer" type="java.io.InputStream, org.apache.hadoop.tools.rumen.ZombieCluster"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Constructor
-
- @param input
- The input stream for the JSON trace.
- @param cluster
- The topology of the cluster that corresponds to the jobs in the
- trace. The argument can be null if we do not have knowledge of the
- cluster topology.
- @throws IOException]]>
- </doc>
- </constructor>
- <constructor name="ZombieJobProducer" type="java.io.InputStream, org.apache.hadoop.tools.rumen.ZombieCluster, long"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Constructor
-
- @param input
- The input stream for the JSON trace.
- @param cluster
- The topology of the cluster that corresponds to the jobs in the
- trace. The argument can be null if we do not have knowledge of the
- cluster topology.
- @param randomSeed
- use a deterministic seed.
- @throws IOException]]>
- </doc>
- </constructor>
- <method name="getNextJob" return="org.apache.hadoop.tools.rumen.ZombieJob"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[Producing {@link JobStory}s from job trace.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.tools.rumen.ZombieJobProducer -->
- </package>
- </api>
|
