| 12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301130213031304130513061307130813091310131113121313131413151316131713181319132013211322132313241325132613271328132913301331133213331334133513361337133813391340134113421343134413451346134713481349135013511352135313541355135613571358135913601361136213631364136513661367136813691370137113721373137413751376137713781379138013811382138313841385138613871388138913901391139213931394139513961397139813991400140114021403140414051406140714081409141014111412141314141415141614171418141914201421142214231424142514261427142814291430143114321433143414351436143714381439144014411442144314441445144614471448144914501451145214531454145514561457145814591460146114621463146414651466146714681469147014711472147314741475147614771478147914801481148214831484148514861487148814891490149114921493149414951496149714981499150015011502150315041505150615071508150915101511151215131514151515161517151815191520152115221523152415251526152715281529153015311532153315341535153615371538153915401541154215431544154515461547154815491550155115521553155415551556155715581559156015611562156315641565156615671568156915701571157215731574157515761577157815791580158115821583158415851586158715881589159015911592159315941595159615971598159916001601160216031604160516061607160816091610161116121613161416151616161716181619162016211622162316241625162616271628162916301631163216331634163516361637163816391640164116421643164416451646164716481649165016511652165316541655165616571658165916601661166216631664166516661667166816691670167116721673167416751676167716781679168016811682168316841685168616871688168916901691169216931694169516961697169816991700170117021703170417051706170717081709171017111712171317141715171617171718171917201721172217231724172517261727172817291730173117321733173417351736173717381739174017411742174317441745174617471748174917501751175217531754175517561757175817591760176117621763176417651766176717681769177017711772177317741775177617771778177917801781178217831784178517861787178817891790179117921793179417951796179717981799180018011802180318041805180618071808180918101811181218131814181518161817181818191820182118221823182418251826182718281829183018311832183318341835183618371838183918401841184218431844184518461847184818491850185118521853185418551856185718581859186018611862186318641865186618671868186918701871187218731874187518761877187818791880188118821883188418851886188718881889189018911892189318941895189618971898189919001901190219031904190519061907190819091910191119121913191419151916191719181919192019211922192319241925192619271928192919301931193219331934193519361937193819391940194119421943194419451946194719481949195019511952195319541955195619571958195919601961196219631964196519661967196819691970197119721973197419751976197719781979198019811982198319841985198619871988198919901991199219931994199519961997199819992000200120022003200420052006200720082009201020112012201320142015201620172018201920202021202220232024202520262027202820292030203120322033203420352036203720382039204020412042204320442045204620472048204920502051205220532054205520562057205820592060206120622063206420652066206720682069207020712072207320742075207620772078207920802081208220832084208520862087208820892090209120922093209420952096209720982099210021012102210321042105210621072108210921102111211221132114211521162117211821192120212121222123212421252126212721282129213021312132213321342135213621372138213921402141214221432144214521462147214821492150215121522153215421552156215721582159216021612162216321642165216621672168216921702171217221732174217521762177217821792180218121822183218421852186218721882189219021912192219321942195219621972198219922002201220222032204220522062207220822092210221122122213221422152216221722182219222022212222222322242225222622272228222922302231223222332234223522362237223822392240224122422243224422452246224722482249225022512252225322542255225622572258225922602261226222632264226522662267226822692270227122722273227422752276227722782279228022812282228322842285228622872288228922902291229222932294229522962297229822992300230123022303230423052306230723082309231023112312231323142315231623172318231923202321232223232324232523262327232823292330233123322333233423352336233723382339234023412342234323442345234623472348234923502351235223532354235523562357235823592360236123622363236423652366236723682369237023712372237323742375237623772378237923802381238223832384238523862387238823892390239123922393239423952396239723982399240024012402240324042405240624072408240924102411241224132414241524162417241824192420242124222423242424252426242724282429243024312432243324342435243624372438243924402441244224432444244524462447244824492450245124522453245424552456245724582459246024612462246324642465246624672468246924702471247224732474247524762477247824792480248124822483248424852486248724882489249024912492249324942495249624972498249925002501250225032504250525062507250825092510251125122513251425152516251725182519252025212522252325242525252625272528252925302531253225332534253525362537253825392540254125422543254425452546254725482549255025512552255325542555255625572558255925602561256225632564256525662567256825692570257125722573257425752576257725782579258025812582258325842585258625872588258925902591259225932594259525962597259825992600260126022603260426052606260726082609261026112612261326142615261626172618261926202621262226232624262526262627262826292630263126322633263426352636263726382639264026412642264326442645264626472648264926502651265226532654265526562657265826592660266126622663266426652666266726682669267026712672267326742675267626772678267926802681268226832684268526862687268826892690269126922693269426952696269726982699270027012702270327042705270627072708270927102711271227132714271527162717271827192720272127222723272427252726272727282729273027312732273327342735273627372738273927402741274227432744274527462747274827492750275127522753275427552756275727582759276027612762276327642765276627672768276927702771277227732774277527762777277827792780278127822783278427852786278727882789279027912792279327942795279627972798279928002801280228032804280528062807280828092810281128122813281428152816281728182819282028212822282328242825282628272828282928302831283228332834283528362837283828392840284128422843284428452846284728482849285028512852285328542855285628572858285928602861286228632864286528662867286828692870287128722873287428752876287728782879288028812882288328842885288628872888288928902891289228932894289528962897289828992900290129022903290429052906290729082909291029112912291329142915291629172918291929202921292229232924292529262927292829292930293129322933293429352936293729382939294029412942294329442945294629472948294929502951295229532954295529562957295829592960296129622963296429652966296729682969297029712972297329742975297629772978297929802981298229832984298529862987298829892990299129922993299429952996299729982999300030013002300330043005300630073008300930103011301230133014301530163017301830193020302130223023302430253026302730283029303030313032303330343035303630373038303930403041304230433044304530463047304830493050305130523053305430553056305730583059306030613062306330643065306630673068306930703071307230733074307530763077307830793080308130823083308430853086308730883089309030913092309330943095309630973098309931003101310231033104310531063107310831093110311131123113311431153116311731183119312031213122312331243125312631273128312931303131313231333134313531363137313831393140314131423143314431453146314731483149315031513152315331543155315631573158315931603161316231633164316531663167316831693170317131723173317431753176317731783179318031813182318331843185318631873188318931903191319231933194319531963197319831993200320132023203320432053206320732083209321032113212321332143215321632173218321932203221322232233224322532263227322832293230323132323233323432353236323732383239324032413242324332443245324632473248324932503251325232533254325532563257325832593260326132623263326432653266326732683269327032713272327332743275327632773278327932803281328232833284328532863287328832893290329132923293329432953296329732983299330033013302330333043305330633073308330933103311331233133314331533163317331833193320332133223323332433253326332733283329333033313332333333343335333633373338333933403341334233433344334533463347334833493350335133523353335433553356335733583359336033613362336333643365336633673368336933703371337233733374337533763377337833793380338133823383338433853386338733883389339033913392339333943395339633973398339934003401340234033404340534063407340834093410341134123413341434153416341734183419342034213422342334243425342634273428342934303431343234333434343534363437343834393440344134423443344434453446344734483449345034513452345334543455345634573458345934603461346234633464346534663467346834693470347134723473347434753476347734783479348034813482348334843485348634873488348934903491349234933494349534963497349834993500350135023503350435053506350735083509351035113512351335143515351635173518351935203521352235233524352535263527352835293530353135323533353435353536353735383539354035413542354335443545354635473548354935503551355235533554355535563557355835593560356135623563356435653566356735683569357035713572357335743575357635773578357935803581358235833584358535863587358835893590359135923593359435953596359735983599360036013602360336043605360636073608360936103611361236133614361536163617361836193620362136223623362436253626362736283629363036313632363336343635363636373638363936403641364236433644364536463647364836493650365136523653365436553656365736583659366036613662366336643665366636673668366936703671367236733674367536763677367836793680368136823683368436853686368736883689369036913692369336943695369636973698369937003701370237033704370537063707370837093710371137123713371437153716371737183719372037213722372337243725372637273728372937303731373237333734373537363737373837393740374137423743374437453746374737483749375037513752375337543755375637573758375937603761376237633764376537663767376837693770377137723773377437753776377737783779378037813782378337843785378637873788378937903791379237933794379537963797379837993800380138023803380438053806380738083809381038113812381338143815381638173818381938203821382238233824382538263827382838293830383138323833383438353836383738383839384038413842384338443845384638473848384938503851385238533854385538563857385838593860386138623863386438653866386738683869387038713872387338743875387638773878387938803881388238833884388538863887388838893890389138923893389438953896389738983899390039013902390339043905390639073908390939103911391239133914391539163917391839193920392139223923392439253926392739283929393039313932393339343935393639373938393939403941394239433944394539463947394839493950395139523953395439553956395739583959396039613962396339643965396639673968396939703971397239733974397539763977397839793980398139823983398439853986398739883989399039913992399339943995399639973998399940004001400240034004400540064007400840094010401140124013401440154016401740184019402040214022402340244025402640274028402940304031403240334034403540364037403840394040404140424043404440454046404740484049405040514052405340544055405640574058405940604061406240634064406540664067406840694070407140724073407440754076407740784079408040814082408340844085408640874088408940904091409240934094409540964097409840994100410141024103410441054106410741084109411041114112411341144115411641174118411941204121412241234124412541264127412841294130413141324133413441354136413741384139414041414142414341444145414641474148414941504151415241534154415541564157415841594160416141624163416441654166416741684169417041714172417341744175417641774178417941804181418241834184418541864187418841894190419141924193419441954196419741984199420042014202420342044205420642074208420942104211421242134214421542164217421842194220422142224223422442254226422742284229423042314232423342344235423642374238423942404241424242434244424542464247424842494250425142524253425442554256425742584259426042614262426342644265426642674268426942704271427242734274427542764277427842794280428142824283428442854286428742884289429042914292429342944295429642974298429943004301430243034304430543064307430843094310431143124313431443154316431743184319432043214322432343244325432643274328432943304331433243334334433543364337433843394340434143424343434443454346434743484349435043514352435343544355435643574358435943604361436243634364436543664367436843694370437143724373437443754376437743784379438043814382438343844385438643874388438943904391439243934394439543964397439843994400440144024403440444054406440744084409441044114412441344144415441644174418441944204421442244234424442544264427442844294430443144324433443444354436443744384439444044414442444344444445444644474448444944504451445244534454445544564457445844594460446144624463446444654466446744684469447044714472447344744475447644774478447944804481448244834484448544864487448844894490449144924493449444954496449744984499450045014502450345044505450645074508450945104511451245134514451545164517451845194520452145224523452445254526452745284529453045314532453345344535453645374538453945404541454245434544454545464547454845494550455145524553455445554556455745584559456045614562456345644565456645674568456945704571457245734574457545764577457845794580458145824583458445854586458745884589459045914592459345944595459645974598459946004601460246034604460546064607460846094610461146124613461446154616461746184619462046214622462346244625462646274628462946304631463246334634463546364637463846394640464146424643464446454646464746484649465046514652465346544655465646574658465946604661466246634664466546664667466846694670467146724673467446754676467746784679468046814682468346844685468646874688468946904691469246934694469546964697469846994700470147024703470447054706470747084709471047114712471347144715471647174718471947204721472247234724472547264727472847294730473147324733473447354736473747384739474047414742474347444745474647474748474947504751475247534754475547564757475847594760476147624763476447654766476747684769477047714772477347744775477647774778477947804781478247834784478547864787478847894790479147924793479447954796479747984799480048014802480348044805480648074808480948104811481248134814481548164817481848194820482148224823482448254826482748284829483048314832483348344835483648374838483948404841484248434844484548464847484848494850485148524853485448554856485748584859486048614862486348644865486648674868486948704871487248734874487548764877487848794880488148824883488448854886488748884889489048914892489348944895489648974898489949004901490249034904490549064907490849094910491149124913491449154916491749184919492049214922492349244925492649274928492949304931493249334934493549364937493849394940494149424943494449454946494749484949495049514952495349544955495649574958495949604961496249634964496549664967496849694970497149724973497449754976497749784979498049814982498349844985498649874988498949904991499249934994499549964997499849995000500150025003500450055006500750085009501050115012501350145015501650175018501950205021502250235024502550265027502850295030503150325033503450355036503750385039504050415042504350445045504650475048504950505051505250535054505550565057505850595060506150625063506450655066506750685069507050715072507350745075507650775078507950805081508250835084508550865087508850895090509150925093509450955096509750985099510051015102510351045105510651075108510951105111511251135114511551165117511851195120512151225123512451255126512751285129513051315132513351345135513651375138513951405141514251435144514551465147514851495150515151525153515451555156515751585159516051615162516351645165516651675168516951705171517251735174517551765177517851795180518151825183518451855186518751885189519051915192519351945195519651975198519952005201520252035204520552065207520852095210521152125213521452155216521752185219522052215222522352245225522652275228522952305231523252335234523552365237523852395240524152425243524452455246524752485249525052515252525352545255525652575258525952605261526252635264526552665267526852695270527152725273527452755276527752785279528052815282528352845285528652875288528952905291529252935294529552965297529852995300530153025303530453055306530753085309531053115312531353145315531653175318531953205321532253235324532553265327532853295330533153325333533453355336533753385339534053415342534353445345534653475348534953505351535253535354535553565357535853595360536153625363536453655366536753685369537053715372537353745375537653775378537953805381538253835384538553865387538853895390539153925393539453955396539753985399540054015402540354045405540654075408540954105411541254135414541554165417541854195420542154225423542454255426542754285429543054315432543354345435543654375438543954405441544254435444544554465447544854495450545154525453545454555456545754585459546054615462546354645465546654675468546954705471547254735474547554765477547854795480548154825483548454855486548754885489549054915492549354945495549654975498549955005501550255035504550555065507550855095510551155125513551455155516551755185519552055215522552355245525552655275528552955305531553255335534553555365537553855395540554155425543554455455546554755485549555055515552555355545555555655575558555955605561556255635564556555665567556855695570557155725573557455755576557755785579558055815582558355845585558655875588558955905591559255935594559555965597559855995600560156025603560456055606560756085609561056115612561356145615561656175618561956205621562256235624562556265627562856295630563156325633563456355636563756385639564056415642564356445645564656475648564956505651565256535654565556565657565856595660566156625663566456655666566756685669567056715672567356745675567656775678567956805681568256835684568556865687568856895690569156925693569456955696569756985699570057015702570357045705570657075708570957105711571257135714571557165717571857195720572157225723572457255726572757285729573057315732573357345735573657375738573957405741574257435744574557465747574857495750575157525753575457555756575757585759576057615762576357645765576657675768576957705771577257735774577557765777577857795780578157825783578457855786578757885789579057915792579357945795579657975798579958005801580258035804580558065807580858095810581158125813581458155816581758185819582058215822582358245825582658275828582958305831583258335834583558365837583858395840584158425843584458455846584758485849585058515852585358545855585658575858585958605861586258635864586558665867586858695870587158725873587458755876587758785879588058815882588358845885588658875888588958905891589258935894589558965897589858995900590159025903590459055906590759085909591059115912591359145915591659175918591959205921592259235924592559265927592859295930593159325933593459355936593759385939594059415942594359445945594659475948594959505951595259535954595559565957595859595960596159625963596459655966596759685969597059715972597359745975597659775978597959805981598259835984598559865987598859895990599159925993599459955996599759985999600060016002600360046005600660076008600960106011601260136014601560166017601860196020602160226023602460256026602760286029603060316032603360346035603660376038603960406041604260436044604560466047604860496050605160526053605460556056605760586059606060616062606360646065606660676068606960706071607260736074607560766077607860796080608160826083608460856086608760886089609060916092609360946095609660976098609961006101610261036104610561066107610861096110611161126113611461156116611761186119612061216122612361246125612661276128612961306131613261336134613561366137613861396140614161426143614461456146614761486149615061516152615361546155615661576158615961606161616261636164616561666167616861696170617161726173617461756176617761786179618061816182618361846185618661876188618961906191619261936194619561966197619861996200620162026203620462056206620762086209621062116212621362146215621662176218621962206221622262236224622562266227622862296230623162326233623462356236623762386239624062416242624362446245624662476248624962506251625262536254625562566257625862596260626162626263626462656266626762686269627062716272627362746275627662776278627962806281628262836284628562866287628862896290629162926293629462956296629762986299630063016302630363046305630663076308630963106311631263136314631563166317631863196320632163226323632463256326632763286329633063316332633363346335633663376338633963406341634263436344634563466347634863496350635163526353635463556356635763586359636063616362636363646365636663676368636963706371637263736374637563766377637863796380638163826383638463856386638763886389639063916392639363946395639663976398639964006401640264036404640564066407640864096410641164126413641464156416641764186419642064216422642364246425642664276428642964306431643264336434643564366437643864396440644164426443644464456446644764486449645064516452645364546455645664576458645964606461646264636464646564666467646864696470647164726473647464756476647764786479648064816482648364846485648664876488648964906491649264936494649564966497649864996500650165026503650465056506650765086509651065116512651365146515651665176518651965206521652265236524652565266527652865296530653165326533653465356536653765386539654065416542654365446545654665476548654965506551655265536554655565566557655865596560656165626563656465656566656765686569657065716572657365746575657665776578657965806581658265836584658565866587658865896590659165926593659465956596659765986599660066016602660366046605660666076608660966106611661266136614661566166617661866196620662166226623662466256626662766286629663066316632663366346635663666376638663966406641664266436644664566466647664866496650665166526653665466556656665766586659666066616662666366646665666666676668666966706671667266736674667566766677667866796680668166826683668466856686668766886689669066916692669366946695669666976698669967006701670267036704670567066707670867096710671167126713671467156716671767186719672067216722672367246725672667276728672967306731673267336734673567366737673867396740674167426743674467456746674767486749675067516752675367546755675667576758675967606761676267636764676567666767676867696770677167726773677467756776677767786779678067816782678367846785678667876788678967906791679267936794679567966797679867996800680168026803680468056806680768086809681068116812681368146815681668176818681968206821682268236824682568266827682868296830683168326833683468356836683768386839684068416842684368446845684668476848684968506851685268536854685568566857685868596860686168626863686468656866686768686869687068716872687368746875687668776878687968806881688268836884688568866887688868896890689168926893689468956896689768986899690069016902690369046905690669076908690969106911691269136914691569166917691869196920692169226923692469256926692769286929693069316932693369346935693669376938693969406941694269436944694569466947694869496950695169526953695469556956695769586959696069616962696369646965696669676968696969706971697269736974697569766977697869796980698169826983698469856986698769886989699069916992699369946995699669976998699970007001700270037004700570067007700870097010701170127013701470157016701770187019702070217022702370247025702670277028702970307031703270337034703570367037703870397040704170427043704470457046704770487049705070517052705370547055705670577058705970607061706270637064706570667067706870697070707170727073707470757076707770787079708070817082708370847085708670877088708970907091709270937094709570967097709870997100710171027103710471057106710771087109711071117112711371147115711671177118711971207121712271237124712571267127712871297130713171327133713471357136713771387139714071417142714371447145714671477148714971507151715271537154715571567157715871597160716171627163716471657166716771687169717071717172717371747175717671777178717971807181718271837184718571867187718871897190719171927193719471957196719771987199720072017202720372047205720672077208720972107211721272137214721572167217721872197220722172227223722472257226722772287229723072317232723372347235723672377238723972407241724272437244724572467247724872497250725172527253725472557256725772587259726072617262726372647265726672677268726972707271727272737274727572767277727872797280728172827283728472857286728772887289729072917292729372947295729672977298729973007301730273037304730573067307730873097310731173127313731473157316731773187319732073217322732373247325732673277328732973307331733273337334733573367337733873397340734173427343734473457346734773487349735073517352735373547355735673577358735973607361736273637364736573667367736873697370737173727373737473757376737773787379738073817382738373847385738673877388738973907391739273937394739573967397739873997400740174027403740474057406740774087409741074117412741374147415741674177418741974207421742274237424742574267427742874297430743174327433743474357436743774387439744074417442744374447445744674477448744974507451745274537454745574567457745874597460746174627463746474657466746774687469747074717472747374747475747674777478747974807481748274837484748574867487748874897490749174927493749474957496749774987499750075017502750375047505750675077508750975107511751275137514751575167517751875197520752175227523752475257526752775287529753075317532753375347535753675377538753975407541754275437544754575467547754875497550755175527553755475557556755775587559756075617562756375647565756675677568756975707571757275737574757575767577757875797580758175827583758475857586758775887589759075917592759375947595759675977598759976007601760276037604760576067607760876097610761176127613761476157616761776187619762076217622762376247625762676277628762976307631763276337634763576367637763876397640764176427643764476457646764776487649765076517652765376547655765676577658765976607661766276637664766576667667766876697670767176727673767476757676767776787679768076817682768376847685768676877688768976907691769276937694769576967697769876997700770177027703770477057706770777087709771077117712771377147715771677177718771977207721772277237724772577267727772877297730773177327733773477357736773777387739774077417742774377447745774677477748774977507751775277537754775577567757775877597760776177627763776477657766776777687769777077717772777377747775777677777778777977807781778277837784778577867787778877897790779177927793779477957796779777987799780078017802780378047805780678077808780978107811781278137814781578167817781878197820782178227823782478257826782778287829783078317832783378347835783678377838783978407841784278437844784578467847784878497850785178527853785478557856785778587859786078617862786378647865786678677868786978707871787278737874787578767877787878797880788178827883788478857886788778887889789078917892789378947895789678977898789979007901790279037904790579067907790879097910791179127913791479157916791779187919792079217922792379247925792679277928792979307931793279337934793579367937793879397940794179427943794479457946794779487949795079517952795379547955795679577958795979607961796279637964796579667967796879697970797179727973797479757976797779787979798079817982798379847985798679877988798979907991799279937994799579967997799879998000800180028003800480058006800780088009801080118012801380148015801680178018801980208021802280238024802580268027802880298030803180328033803480358036803780388039804080418042804380448045804680478048804980508051805280538054805580568057805880598060806180628063806480658066806780688069807080718072807380748075807680778078807980808081808280838084808580868087808880898090809180928093809480958096809780988099810081018102810381048105810681078108810981108111811281138114811581168117811881198120812181228123812481258126812781288129813081318132813381348135813681378138813981408141814281438144814581468147814881498150815181528153815481558156815781588159816081618162816381648165816681678168816981708171817281738174817581768177817881798180818181828183818481858186818781888189819081918192819381948195819681978198819982008201820282038204820582068207820882098210821182128213821482158216821782188219822082218222822382248225822682278228822982308231823282338234823582368237823882398240824182428243824482458246824782488249825082518252825382548255825682578258825982608261826282638264826582668267826882698270827182728273827482758276827782788279828082818282828382848285828682878288828982908291829282938294829582968297829882998300830183028303830483058306830783088309831083118312831383148315831683178318831983208321832283238324832583268327832883298330833183328333833483358336833783388339834083418342834383448345834683478348834983508351835283538354835583568357835883598360836183628363836483658366836783688369837083718372837383748375837683778378837983808381838283838384838583868387838883898390839183928393839483958396839783988399840084018402840384048405840684078408840984108411841284138414841584168417841884198420842184228423842484258426842784288429843084318432843384348435843684378438843984408441844284438444844584468447844884498450845184528453845484558456845784588459846084618462846384648465846684678468846984708471847284738474847584768477847884798480848184828483848484858486848784888489849084918492849384948495849684978498849985008501850285038504850585068507850885098510851185128513851485158516851785188519852085218522852385248525852685278528852985308531853285338534853585368537853885398540854185428543854485458546854785488549855085518552855385548555855685578558855985608561856285638564856585668567856885698570857185728573857485758576857785788579858085818582858385848585858685878588858985908591859285938594859585968597859885998600860186028603860486058606860786088609861086118612861386148615861686178618861986208621862286238624862586268627862886298630863186328633863486358636863786388639864086418642864386448645864686478648864986508651865286538654865586568657865886598660866186628663866486658666866786688669867086718672867386748675867686778678867986808681868286838684868586868687868886898690869186928693869486958696869786988699870087018702870387048705870687078708870987108711871287138714871587168717871887198720872187228723872487258726872787288729873087318732873387348735873687378738873987408741874287438744874587468747874887498750875187528753875487558756875787588759876087618762876387648765876687678768876987708771877287738774877587768777877887798780878187828783878487858786878787888789879087918792879387948795879687978798879988008801880288038804880588068807880888098810881188128813881488158816881788188819882088218822882388248825882688278828882988308831883288338834883588368837883888398840884188428843884488458846884788488849885088518852885388548855885688578858885988608861886288638864886588668867886888698870887188728873887488758876887788788879888088818882888388848885888688878888888988908891889288938894889588968897889888998900890189028903890489058906890789088909891089118912891389148915891689178918891989208921892289238924892589268927892889298930893189328933893489358936893789388939894089418942894389448945894689478948894989508951895289538954895589568957895889598960896189628963896489658966896789688969897089718972897389748975897689778978897989808981898289838984898589868987898889898990899189928993899489958996899789988999900090019002900390049005900690079008900990109011901290139014901590169017901890199020902190229023902490259026902790289029903090319032903390349035903690379038903990409041904290439044904590469047904890499050905190529053905490559056905790589059906090619062906390649065906690679068906990709071907290739074907590769077907890799080908190829083908490859086908790889089909090919092909390949095909690979098909991009101910291039104910591069107910891099110911191129113911491159116911791189119912091219122912391249125912691279128912991309131913291339134913591369137913891399140914191429143914491459146914791489149915091519152915391549155915691579158915991609161916291639164916591669167916891699170917191729173917491759176917791789179918091819182918391849185918691879188918991909191919291939194919591969197919891999200920192029203920492059206920792089209921092119212921392149215921692179218921992209221922292239224922592269227922892299230923192329233923492359236923792389239924092419242924392449245924692479248924992509251925292539254925592569257925892599260926192629263926492659266926792689269927092719272927392749275927692779278927992809281928292839284928592869287928892899290929192929293929492959296929792989299930093019302930393049305930693079308930993109311931293139314931593169317931893199320932193229323932493259326932793289329933093319332933393349335933693379338933993409341934293439344934593469347934893499350935193529353935493559356935793589359936093619362936393649365936693679368936993709371937293739374937593769377937893799380938193829383938493859386938793889389939093919392939393949395939693979398939994009401940294039404940594069407940894099410941194129413941494159416941794189419942094219422942394249425942694279428942994309431943294339434943594369437943894399440944194429443944494459446944794489449945094519452945394549455945694579458945994609461946294639464946594669467946894699470947194729473947494759476947794789479948094819482948394849485948694879488948994909491949294939494949594969497949894999500950195029503950495059506950795089509951095119512951395149515951695179518951995209521952295239524952595269527952895299530953195329533953495359536953795389539954095419542954395449545954695479548954995509551955295539554955595569557955895599560956195629563956495659566956795689569957095719572957395749575957695779578957995809581958295839584958595869587958895899590959195929593959495959596959795989599960096019602960396049605960696079608960996109611961296139614961596169617961896199620962196229623962496259626962796289629963096319632963396349635963696379638963996409641964296439644964596469647964896499650965196529653965496559656965796589659966096619662966396649665966696679668966996709671967296739674967596769677967896799680968196829683968496859686968796889689969096919692969396949695969696979698969997009701970297039704970597069707970897099710971197129713971497159716971797189719972097219722972397249725972697279728972997309731973297339734973597369737973897399740974197429743974497459746974797489749975097519752975397549755975697579758975997609761976297639764976597669767976897699770977197729773977497759776977797789779978097819782978397849785978697879788978997909791979297939794979597969797979897999800980198029803980498059806980798089809981098119812981398149815981698179818981998209821982298239824982598269827982898299830983198329833983498359836983798389839984098419842984398449845984698479848984998509851985298539854985598569857985898599860986198629863986498659866986798689869987098719872987398749875987698779878987998809881988298839884988598869887988898899890989198929893989498959896989798989899990099019902990399049905990699079908990999109911991299139914991599169917991899199920992199229923992499259926992799289929993099319932993399349935993699379938993999409941994299439944994599469947994899499950995199529953995499559956995799589959996099619962996399649965996699679968996999709971997299739974997599769977997899799980998199829983998499859986998799889989999099919992999399949995999699979998999910000100011000210003100041000510006100071000810009100101001110012100131001410015100161001710018100191002010021100221002310024100251002610027100281002910030100311003210033100341003510036100371003810039100401004110042100431004410045100461004710048100491005010051100521005310054100551005610057100581005910060100611006210063100641006510066100671006810069100701007110072100731007410075100761007710078100791008010081100821008310084100851008610087100881008910090100911009210093100941009510096100971009810099101001010110102101031010410105101061010710108101091011010111101121011310114101151011610117101181011910120101211012210123101241012510126101271012810129101301013110132101331013410135101361013710138101391014010141101421014310144101451014610147101481014910150101511015210153101541015510156101571015810159101601016110162101631016410165101661016710168101691017010171101721017310174101751017610177101781017910180101811018210183101841018510186101871018810189101901019110192101931019410195101961019710198101991020010201102021020310204102051020610207102081020910210102111021210213102141021510216102171021810219102201022110222102231022410225102261022710228102291023010231102321023310234102351023610237102381023910240102411024210243102441024510246102471024810249102501025110252102531025410255102561025710258102591026010261102621026310264102651026610267102681026910270102711027210273102741027510276102771027810279102801028110282102831028410285102861028710288102891029010291102921029310294102951029610297102981029910300103011030210303103041030510306103071030810309103101031110312103131031410315103161031710318103191032010321103221032310324103251032610327103281032910330103311033210333103341033510336103371033810339103401034110342103431034410345103461034710348103491035010351103521035310354103551035610357103581035910360103611036210363103641036510366103671036810369103701037110372103731037410375103761037710378103791038010381103821038310384103851038610387103881038910390103911039210393103941039510396103971039810399104001040110402104031040410405104061040710408104091041010411104121041310414104151041610417104181041910420104211042210423104241042510426104271042810429104301043110432104331043410435104361043710438104391044010441104421044310444104451044610447104481044910450104511045210453104541045510456104571045810459104601046110462104631046410465104661046710468104691047010471104721047310474104751047610477104781047910480104811048210483104841048510486104871048810489104901049110492104931049410495104961049710498104991050010501105021050310504105051050610507105081050910510105111051210513105141051510516105171051810519105201052110522105231052410525105261052710528105291053010531105321053310534105351053610537105381053910540105411054210543105441054510546105471054810549105501055110552105531055410555105561055710558105591056010561105621056310564105651056610567105681056910570105711057210573105741057510576105771057810579105801058110582105831058410585105861058710588105891059010591105921059310594105951059610597105981059910600106011060210603106041060510606106071060810609106101061110612106131061410615106161061710618106191062010621106221062310624106251062610627106281062910630106311063210633106341063510636106371063810639106401064110642106431064410645106461064710648106491065010651106521065310654106551065610657106581065910660106611066210663106641066510666106671066810669106701067110672106731067410675106761067710678106791068010681106821068310684106851068610687106881068910690106911069210693106941069510696106971069810699107001070110702107031070410705107061070710708107091071010711107121071310714107151071610717107181071910720107211072210723107241072510726107271072810729107301073110732107331073410735107361073710738107391074010741107421074310744107451074610747107481074910750107511075210753107541075510756107571075810759107601076110762107631076410765107661076710768107691077010771107721077310774107751077610777107781077910780107811078210783107841078510786107871078810789107901079110792107931079410795107961079710798107991080010801108021080310804108051080610807108081080910810108111081210813108141081510816108171081810819108201082110822108231082410825108261082710828108291083010831108321083310834108351083610837108381083910840108411084210843108441084510846108471084810849108501085110852108531085410855108561085710858108591086010861108621086310864108651086610867108681086910870108711087210873108741087510876108771087810879108801088110882108831088410885108861088710888108891089010891108921089310894108951089610897108981089910900109011090210903109041090510906109071090810909109101091110912109131091410915109161091710918109191092010921109221092310924109251092610927109281092910930109311093210933109341093510936109371093810939109401094110942109431094410945109461094710948109491095010951109521095310954109551095610957109581095910960109611096210963109641096510966109671096810969109701097110972109731097410975109761097710978109791098010981109821098310984109851098610987109881098910990109911099210993109941099510996109971099810999110001100111002110031100411005110061100711008110091101011011110121101311014110151101611017110181101911020110211102211023110241102511026110271102811029110301103111032110331103411035110361103711038110391104011041110421104311044110451104611047110481104911050110511105211053110541105511056110571105811059110601106111062110631106411065110661106711068110691107011071110721107311074110751107611077110781107911080110811108211083110841108511086110871108811089110901109111092110931109411095110961109711098110991110011101111021110311104111051110611107111081110911110111111111211113111141111511116111171111811119111201112111122111231112411125111261112711128111291113011131111321113311134111351113611137111381113911140111411114211143111441114511146111471114811149111501115111152111531115411155111561115711158111591116011161111621116311164111651116611167111681116911170111711117211173111741117511176111771117811179111801118111182111831118411185111861118711188111891119011191111921119311194111951119611197111981119911200112011120211203112041120511206112071120811209112101121111212112131121411215112161121711218112191122011221112221122311224112251122611227112281122911230112311123211233112341123511236112371123811239112401124111242112431124411245112461124711248112491125011251112521125311254112551125611257112581125911260112611126211263112641126511266112671126811269112701127111272112731127411275112761127711278112791128011281112821128311284112851128611287112881128911290112911129211293112941129511296112971129811299113001130111302113031130411305113061130711308113091131011311113121131311314113151131611317113181131911320113211132211323113241132511326113271132811329113301133111332113331133411335113361133711338113391134011341113421134311344113451134611347113481134911350113511135211353113541135511356113571135811359113601136111362113631136411365113661136711368113691137011371113721137311374113751137611377113781137911380113811138211383113841138511386113871138811389113901139111392113931139411395113961139711398113991140011401114021140311404114051140611407114081140911410114111141211413114141141511416114171141811419114201142111422114231142411425114261142711428114291143011431114321143311434114351143611437114381143911440114411144211443114441144511446114471144811449114501145111452114531145411455114561145711458114591146011461114621146311464114651146611467114681146911470114711147211473114741147511476114771147811479114801148111482114831148411485114861148711488114891149011491114921149311494114951149611497114981149911500115011150211503115041150511506115071150811509115101151111512115131151411515115161151711518115191152011521115221152311524115251152611527115281152911530115311153211533115341153511536115371153811539115401154111542115431154411545115461154711548115491155011551115521155311554115551155611557115581155911560115611156211563115641156511566115671156811569115701157111572115731157411575115761157711578115791158011581115821158311584115851158611587115881158911590115911159211593115941159511596115971159811599116001160111602116031160411605116061160711608116091161011611116121161311614116151161611617116181161911620116211162211623116241162511626116271162811629116301163111632116331163411635116361163711638116391164011641116421164311644116451164611647116481164911650116511165211653116541165511656116571165811659116601166111662116631166411665116661166711668116691167011671116721167311674116751167611677116781167911680116811168211683116841168511686116871168811689116901169111692116931169411695116961169711698116991170011701117021170311704117051170611707117081170911710117111171211713117141171511716117171171811719117201172111722117231172411725117261172711728117291173011731117321173311734117351173611737117381173911740117411174211743117441174511746117471174811749117501175111752117531175411755117561175711758117591176011761117621176311764117651176611767117681176911770117711177211773117741177511776117771177811779117801178111782117831178411785117861178711788117891179011791117921179311794117951179611797117981179911800118011180211803118041180511806118071180811809118101181111812118131181411815118161181711818118191182011821118221182311824118251182611827118281182911830118311183211833118341183511836118371183811839118401184111842118431184411845118461184711848118491185011851118521185311854118551185611857118581185911860118611186211863118641186511866118671186811869118701187111872118731187411875118761187711878118791188011881118821188311884118851188611887118881188911890118911189211893118941189511896118971189811899119001190111902119031190411905119061190711908119091191011911119121191311914119151191611917119181191911920119211192211923119241192511926119271192811929119301193111932119331193411935119361193711938119391194011941119421194311944119451194611947119481194911950119511195211953119541195511956119571195811959119601196111962119631196411965119661196711968119691197011971119721197311974119751197611977119781197911980119811198211983119841198511986119871198811989119901199111992119931199411995119961199711998119991200012001120021200312004120051200612007120081200912010120111201212013120141201512016120171201812019120201202112022120231202412025120261202712028120291203012031120321203312034120351203612037120381203912040120411204212043120441204512046120471204812049120501205112052120531205412055120561205712058120591206012061120621206312064120651206612067120681206912070120711207212073120741207512076120771207812079120801208112082120831208412085120861208712088120891209012091120921209312094120951209612097120981209912100121011210212103121041210512106121071210812109121101211112112121131211412115121161211712118121191212012121121221212312124121251212612127121281212912130121311213212133121341213512136121371213812139121401214112142121431214412145121461214712148121491215012151121521215312154121551215612157121581215912160121611216212163121641216512166121671216812169121701217112172121731217412175121761217712178121791218012181121821218312184121851218612187121881218912190121911219212193121941219512196121971219812199122001220112202122031220412205122061220712208122091221012211122121221312214122151221612217122181221912220122211222212223122241222512226122271222812229122301223112232122331223412235122361223712238122391224012241122421224312244122451224612247122481224912250122511225212253122541225512256122571225812259122601226112262122631226412265122661226712268122691227012271122721227312274122751227612277122781227912280122811228212283122841228512286122871228812289122901229112292122931229412295122961229712298122991230012301123021230312304123051230612307123081230912310123111231212313123141231512316123171231812319123201232112322123231232412325123261232712328123291233012331123321233312334123351233612337123381233912340123411234212343123441234512346123471234812349123501235112352123531235412355123561235712358123591236012361123621236312364123651236612367123681236912370123711237212373123741237512376123771237812379123801238112382123831238412385123861238712388123891239012391123921239312394123951239612397123981239912400124011240212403124041240512406124071240812409124101241112412124131241412415124161241712418124191242012421124221242312424124251242612427124281242912430124311243212433124341243512436124371243812439124401244112442124431244412445124461244712448124491245012451124521245312454124551245612457124581245912460124611246212463124641246512466124671246812469124701247112472124731247412475124761247712478124791248012481124821248312484124851248612487124881248912490124911249212493124941249512496124971249812499125001250112502125031250412505125061250712508125091251012511125121251312514125151251612517125181251912520125211252212523125241252512526125271252812529125301253112532125331253412535125361253712538125391254012541125421254312544125451254612547125481254912550125511255212553125541255512556125571255812559125601256112562125631256412565125661256712568125691257012571125721257312574125751257612577125781257912580125811258212583125841258512586125871258812589125901259112592125931259412595125961259712598125991260012601126021260312604126051260612607126081260912610126111261212613126141261512616126171261812619126201262112622126231262412625126261262712628126291263012631126321263312634126351263612637126381263912640126411264212643126441264512646126471264812649126501265112652126531265412655126561265712658126591266012661126621266312664126651266612667126681266912670126711267212673126741267512676126771267812679126801268112682126831268412685126861268712688126891269012691126921269312694126951269612697126981269912700127011270212703127041270512706127071270812709127101271112712127131271412715127161271712718127191272012721127221272312724127251272612727127281272912730127311273212733127341273512736127371273812739127401274112742127431274412745127461274712748127491275012751127521275312754127551275612757127581275912760127611276212763127641276512766127671276812769127701277112772127731277412775127761277712778127791278012781127821278312784127851278612787127881278912790127911279212793127941279512796127971279812799128001280112802128031280412805128061280712808128091281012811128121281312814128151281612817128181281912820128211282212823128241282512826128271282812829128301283112832128331283412835128361283712838128391284012841128421284312844128451284612847128481284912850128511285212853128541285512856128571285812859128601286112862128631286412865128661286712868128691287012871128721287312874128751287612877128781287912880128811288212883128841288512886128871288812889128901289112892128931289412895128961289712898128991290012901129021290312904129051290612907129081290912910129111291212913129141291512916129171291812919129201292112922129231292412925129261292712928129291293012931129321293312934129351293612937129381293912940129411294212943129441294512946129471294812949129501295112952129531295412955129561295712958129591296012961129621296312964129651296612967129681296912970129711297212973129741297512976129771297812979129801298112982129831298412985129861298712988129891299012991129921299312994129951299612997129981299913000130011300213003130041300513006130071300813009130101301113012130131301413015130161301713018130191302013021130221302313024130251302613027130281302913030130311303213033130341303513036130371303813039130401304113042130431304413045130461304713048130491305013051130521305313054130551305613057130581305913060130611306213063130641306513066130671306813069130701307113072130731307413075130761307713078130791308013081130821308313084130851308613087130881308913090130911309213093130941309513096130971309813099131001310113102131031310413105131061310713108131091311013111131121311313114131151311613117131181311913120131211312213123131241312513126131271312813129131301313113132131331313413135131361313713138131391314013141131421314313144131451314613147131481314913150131511315213153131541315513156131571315813159131601316113162131631316413165131661316713168131691317013171131721317313174131751317613177131781317913180131811318213183131841318513186131871318813189131901319113192131931319413195131961319713198131991320013201132021320313204132051320613207132081320913210132111321213213132141321513216132171321813219132201322113222132231322413225132261322713228132291323013231132321323313234132351323613237132381323913240132411324213243132441324513246132471324813249132501325113252132531325413255132561325713258132591326013261132621326313264132651326613267132681326913270132711327213273132741327513276132771327813279132801328113282132831328413285132861328713288132891329013291132921329313294132951329613297132981329913300133011330213303133041330513306133071330813309133101331113312133131331413315133161331713318133191332013321133221332313324133251332613327133281332913330133311333213333133341333513336133371333813339133401334113342133431334413345133461334713348133491335013351133521335313354133551335613357133581335913360133611336213363133641336513366133671336813369133701337113372133731337413375133761337713378133791338013381133821338313384133851338613387133881338913390133911339213393133941339513396133971339813399134001340113402134031340413405134061340713408134091341013411134121341313414134151341613417134181341913420134211342213423134241342513426134271342813429134301343113432134331343413435134361343713438134391344013441134421344313444134451344613447134481344913450134511345213453134541345513456134571345813459134601346113462134631346413465134661346713468134691347013471134721347313474134751347613477134781347913480134811348213483134841348513486134871348813489134901349113492134931349413495134961349713498134991350013501135021350313504135051350613507135081350913510135111351213513135141351513516135171351813519135201352113522135231352413525135261352713528135291353013531135321353313534135351353613537135381353913540135411354213543135441354513546135471354813549135501355113552135531355413555135561355713558135591356013561135621356313564135651356613567135681356913570135711357213573135741357513576135771357813579135801358113582135831358413585135861358713588135891359013591135921359313594135951359613597135981359913600136011360213603136041360513606136071360813609136101361113612136131361413615136161361713618136191362013621136221362313624136251362613627136281362913630136311363213633136341363513636136371363813639136401364113642136431364413645136461364713648136491365013651136521365313654136551365613657136581365913660136611366213663136641366513666136671366813669136701367113672136731367413675136761367713678136791368013681136821368313684136851368613687136881368913690136911369213693136941369513696136971369813699137001370113702137031370413705137061370713708137091371013711137121371313714137151371613717137181371913720137211372213723137241372513726137271372813729137301373113732137331373413735137361373713738137391374013741137421374313744137451374613747137481374913750137511375213753137541375513756137571375813759137601376113762137631376413765137661376713768137691377013771137721377313774137751377613777137781377913780137811378213783137841378513786137871378813789137901379113792137931379413795137961379713798137991380013801138021380313804138051380613807138081380913810138111381213813138141381513816138171381813819138201382113822138231382413825138261382713828138291383013831138321383313834138351383613837138381383913840138411384213843138441384513846138471384813849138501385113852138531385413855138561385713858138591386013861138621386313864138651386613867138681386913870138711387213873138741387513876138771387813879138801388113882138831388413885138861388713888138891389013891138921389313894138951389613897138981389913900139011390213903139041390513906139071390813909139101391113912139131391413915139161391713918139191392013921139221392313924139251392613927139281392913930139311393213933139341393513936139371393813939139401394113942139431394413945139461394713948139491395013951139521395313954139551395613957139581395913960139611396213963139641396513966139671396813969139701397113972139731397413975139761397713978139791398013981139821398313984139851398613987139881398913990139911399213993139941399513996139971399813999140001400114002140031400414005140061400714008140091401014011140121401314014140151401614017140181401914020140211402214023140241402514026140271402814029140301403114032140331403414035140361403714038140391404014041140421404314044140451404614047140481404914050140511405214053140541405514056140571405814059140601406114062140631406414065140661406714068140691407014071140721407314074140751407614077140781407914080140811408214083140841408514086140871408814089140901409114092140931409414095140961409714098140991410014101141021410314104141051410614107141081410914110141111411214113141141411514116141171411814119141201412114122141231412414125141261412714128141291413014131141321413314134141351413614137141381413914140141411414214143141441414514146141471414814149141501415114152141531415414155141561415714158141591416014161141621416314164141651416614167141681416914170141711417214173141741417514176141771417814179141801418114182141831418414185141861418714188141891419014191141921419314194141951419614197141981419914200142011420214203142041420514206142071420814209142101421114212142131421414215142161421714218142191422014221142221422314224142251422614227142281422914230142311423214233142341423514236142371423814239142401424114242142431424414245142461424714248142491425014251142521425314254142551425614257142581425914260142611426214263142641426514266142671426814269142701427114272142731427414275142761427714278142791428014281142821428314284142851428614287142881428914290142911429214293142941429514296142971429814299143001430114302143031430414305143061430714308143091431014311143121431314314143151431614317143181431914320143211432214323143241432514326143271432814329143301433114332143331433414335143361433714338143391434014341143421434314344143451434614347143481434914350143511435214353143541435514356143571435814359143601436114362143631436414365143661436714368143691437014371143721437314374143751437614377143781437914380143811438214383143841438514386143871438814389143901439114392143931439414395143961439714398143991440014401144021440314404144051440614407144081440914410144111441214413144141441514416144171441814419144201442114422144231442414425144261442714428144291443014431144321443314434144351443614437144381443914440144411444214443144441444514446144471444814449144501445114452144531445414455144561445714458144591446014461144621446314464144651446614467144681446914470144711447214473144741447514476144771447814479144801448114482144831448414485144861448714488144891449014491144921449314494144951449614497144981449914500145011450214503145041450514506145071450814509145101451114512145131451414515145161451714518145191452014521145221452314524145251452614527145281452914530145311453214533145341453514536145371453814539145401454114542145431454414545145461454714548145491455014551145521455314554145551455614557145581455914560145611456214563145641456514566145671456814569145701457114572145731457414575145761457714578145791458014581145821458314584145851458614587145881458914590145911459214593145941459514596145971459814599146001460114602146031460414605146061460714608146091461014611146121461314614146151461614617146181461914620146211462214623146241462514626146271462814629146301463114632146331463414635146361463714638146391464014641146421464314644146451464614647146481464914650146511465214653146541465514656146571465814659146601466114662146631466414665146661466714668146691467014671146721467314674146751467614677146781467914680146811468214683146841468514686146871468814689146901469114692146931469414695146961469714698146991470014701147021470314704147051470614707147081470914710147111471214713147141471514716147171471814719147201472114722147231472414725147261472714728147291473014731147321473314734147351473614737147381473914740147411474214743147441474514746147471474814749147501475114752147531475414755147561475714758147591476014761147621476314764147651476614767147681476914770147711477214773147741477514776147771477814779147801478114782147831478414785147861478714788147891479014791147921479314794147951479614797147981479914800148011480214803148041480514806148071480814809148101481114812148131481414815148161481714818148191482014821148221482314824148251482614827148281482914830148311483214833148341483514836148371483814839148401484114842148431484414845148461484714848148491485014851148521485314854148551485614857148581485914860148611486214863148641486514866148671486814869148701487114872148731487414875148761487714878148791488014881148821488314884148851488614887148881488914890148911489214893148941489514896148971489814899149001490114902149031490414905149061490714908149091491014911149121491314914149151491614917149181491914920149211492214923149241492514926149271492814929149301493114932149331493414935149361493714938149391494014941149421494314944149451494614947149481494914950149511495214953149541495514956149571495814959149601496114962149631496414965149661496714968149691497014971149721497314974149751497614977149781497914980149811498214983149841498514986149871498814989149901499114992149931499414995149961499714998149991500015001150021500315004150051500615007150081500915010150111501215013150141501515016150171501815019150201502115022150231502415025150261502715028150291503015031150321503315034150351503615037150381503915040150411504215043150441504515046150471504815049150501505115052150531505415055150561505715058150591506015061150621506315064150651506615067150681506915070150711507215073150741507515076150771507815079150801508115082150831508415085150861508715088150891509015091150921509315094150951509615097150981509915100151011510215103151041510515106151071510815109151101511115112151131511415115151161511715118151191512015121151221512315124151251512615127151281512915130151311513215133151341513515136151371513815139151401514115142151431514415145151461514715148151491515015151151521515315154151551515615157151581515915160151611516215163151641516515166151671516815169151701517115172151731517415175151761517715178151791518015181151821518315184151851518615187151881518915190151911519215193151941519515196151971519815199152001520115202152031520415205152061520715208152091521015211152121521315214152151521615217152181521915220152211522215223152241522515226152271522815229152301523115232152331523415235152361523715238152391524015241152421524315244152451524615247152481524915250152511525215253152541525515256152571525815259152601526115262152631526415265152661526715268152691527015271152721527315274152751527615277152781527915280152811528215283152841528515286152871528815289152901529115292152931529415295152961529715298152991530015301153021530315304153051530615307153081530915310153111531215313153141531515316153171531815319153201532115322153231532415325153261532715328153291533015331153321533315334153351533615337153381533915340153411534215343153441534515346153471534815349153501535115352153531535415355153561535715358153591536015361153621536315364153651536615367153681536915370153711537215373153741537515376153771537815379153801538115382153831538415385153861538715388153891539015391153921539315394153951539615397153981539915400154011540215403154041540515406154071540815409154101541115412154131541415415154161541715418154191542015421154221542315424154251542615427154281542915430154311543215433154341543515436154371543815439154401544115442154431544415445154461544715448154491545015451154521545315454154551545615457154581545915460154611546215463154641546515466154671546815469154701547115472154731547415475154761547715478154791548015481154821548315484154851548615487154881548915490154911549215493154941549515496154971549815499155001550115502155031550415505155061550715508155091551015511155121551315514155151551615517155181551915520155211552215523155241552515526155271552815529155301553115532155331553415535155361553715538155391554015541155421554315544155451554615547155481554915550155511555215553155541555515556155571555815559155601556115562155631556415565155661556715568155691557015571155721557315574155751557615577155781557915580155811558215583155841558515586155871558815589155901559115592155931559415595155961559715598155991560015601156021560315604156051560615607156081560915610156111561215613156141561515616156171561815619156201562115622156231562415625156261562715628156291563015631156321563315634156351563615637156381563915640156411564215643156441564515646156471564815649156501565115652156531565415655156561565715658156591566015661156621566315664156651566615667156681566915670156711567215673156741567515676156771567815679156801568115682156831568415685156861568715688156891569015691156921569315694156951569615697156981569915700157011570215703157041570515706157071570815709157101571115712157131571415715157161571715718157191572015721157221572315724157251572615727157281572915730157311573215733157341573515736157371573815739157401574115742157431574415745157461574715748157491575015751157521575315754157551575615757157581575915760157611576215763157641576515766157671576815769157701577115772157731577415775157761577715778157791578015781157821578315784157851578615787157881578915790157911579215793157941579515796157971579815799158001580115802158031580415805158061580715808158091581015811158121581315814158151581615817158181581915820158211582215823158241582515826158271582815829158301583115832158331583415835158361583715838158391584015841158421584315844158451584615847158481584915850158511585215853158541585515856158571585815859158601586115862158631586415865158661586715868158691587015871158721587315874158751587615877158781587915880158811588215883158841588515886158871588815889158901589115892158931589415895158961589715898158991590015901159021590315904159051590615907159081590915910159111591215913159141591515916159171591815919159201592115922159231592415925159261592715928159291593015931159321593315934159351593615937159381593915940159411594215943159441594515946159471594815949159501595115952159531595415955159561595715958159591596015961159621596315964159651596615967159681596915970159711597215973159741597515976159771597815979159801598115982159831598415985159861598715988159891599015991159921599315994159951599615997159981599916000160011600216003160041600516006160071600816009160101601116012160131601416015160161601716018160191602016021160221602316024160251602616027160281602916030160311603216033160341603516036160371603816039160401604116042160431604416045160461604716048160491605016051160521605316054160551605616057160581605916060160611606216063160641606516066160671606816069160701607116072160731607416075160761607716078160791608016081160821608316084160851608616087160881608916090160911609216093160941609516096160971609816099161001610116102161031610416105161061610716108161091611016111161121611316114161151611616117161181611916120161211612216123161241612516126161271612816129161301613116132161331613416135161361613716138161391614016141161421614316144161451614616147161481614916150161511615216153161541615516156161571615816159161601616116162161631616416165161661616716168161691617016171161721617316174161751617616177161781617916180161811618216183161841618516186161871618816189161901619116192161931619416195161961619716198161991620016201162021620316204162051620616207162081620916210162111621216213162141621516216162171621816219162201622116222162231622416225162261622716228162291623016231162321623316234162351623616237162381623916240162411624216243162441624516246162471624816249162501625116252162531625416255162561625716258162591626016261162621626316264162651626616267162681626916270162711627216273162741627516276162771627816279162801628116282162831628416285162861628716288162891629016291162921629316294162951629616297162981629916300163011630216303163041630516306163071630816309163101631116312163131631416315163161631716318163191632016321163221632316324163251632616327163281632916330163311633216333163341633516336163371633816339163401634116342163431634416345163461634716348163491635016351163521635316354163551635616357163581635916360163611636216363163641636516366163671636816369163701637116372163731637416375163761637716378163791638016381163821638316384163851638616387163881638916390163911639216393163941639516396163971639816399164001640116402164031640416405164061640716408164091641016411164121641316414164151641616417164181641916420164211642216423164241642516426164271642816429164301643116432164331643416435164361643716438164391644016441164421644316444164451644616447164481644916450164511645216453164541645516456164571645816459164601646116462164631646416465164661646716468164691647016471164721647316474164751647616477164781647916480164811648216483164841648516486164871648816489164901649116492164931649416495164961649716498164991650016501165021650316504165051650616507165081650916510165111651216513165141651516516165171651816519165201652116522165231652416525165261652716528165291653016531165321653316534165351653616537165381653916540165411654216543165441654516546165471654816549165501655116552165531655416555165561655716558165591656016561165621656316564165651656616567165681656916570165711657216573165741657516576165771657816579165801658116582165831658416585165861658716588165891659016591165921659316594165951659616597165981659916600166011660216603166041660516606166071660816609166101661116612166131661416615166161661716618166191662016621166221662316624166251662616627166281662916630166311663216633166341663516636166371663816639166401664116642166431664416645166461664716648166491665016651166521665316654166551665616657166581665916660166611666216663166641666516666166671666816669166701667116672166731667416675166761667716678166791668016681166821668316684166851668616687166881668916690166911669216693166941669516696166971669816699167001670116702167031670416705167061670716708167091671016711167121671316714167151671616717167181671916720167211672216723167241672516726167271672816729167301673116732167331673416735167361673716738167391674016741167421674316744167451674616747167481674916750167511675216753167541675516756167571675816759167601676116762167631676416765167661676716768167691677016771167721677316774167751677616777167781677916780167811678216783167841678516786167871678816789167901679116792167931679416795167961679716798167991680016801168021680316804168051680616807168081680916810168111681216813168141681516816168171681816819168201682116822168231682416825168261682716828168291683016831168321683316834168351683616837168381683916840168411684216843168441684516846168471684816849168501685116852168531685416855168561685716858168591686016861168621686316864168651686616867168681686916870168711687216873168741687516876168771687816879168801688116882168831688416885168861688716888168891689016891168921689316894168951689616897168981689916900169011690216903169041690516906169071690816909169101691116912169131691416915169161691716918169191692016921169221692316924169251692616927169281692916930169311693216933169341693516936169371693816939169401694116942169431694416945169461694716948169491695016951169521695316954169551695616957169581695916960169611696216963169641696516966169671696816969169701697116972169731697416975169761697716978169791698016981169821698316984169851698616987169881698916990169911699216993169941699516996169971699816999170001700117002170031700417005170061700717008170091701017011170121701317014170151701617017170181701917020170211702217023170241702517026170271702817029170301703117032170331703417035170361703717038170391704017041170421704317044170451704617047170481704917050170511705217053170541705517056170571705817059170601706117062170631706417065170661706717068170691707017071170721707317074170751707617077170781707917080170811708217083170841708517086170871708817089170901709117092170931709417095170961709717098170991710017101171021710317104171051710617107171081710917110171111711217113171141711517116171171711817119171201712117122171231712417125171261712717128171291713017131171321713317134171351713617137171381713917140171411714217143171441714517146171471714817149171501715117152171531715417155171561715717158171591716017161171621716317164171651716617167171681716917170171711717217173171741717517176171771717817179171801718117182171831718417185171861718717188171891719017191171921719317194171951719617197171981719917200172011720217203172041720517206172071720817209172101721117212172131721417215172161721717218172191722017221172221722317224172251722617227172281722917230172311723217233172341723517236172371723817239172401724117242172431724417245172461724717248172491725017251172521725317254172551725617257172581725917260172611726217263172641726517266172671726817269172701727117272172731727417275172761727717278172791728017281172821728317284172851728617287172881728917290172911729217293172941729517296172971729817299173001730117302173031730417305173061730717308173091731017311173121731317314173151731617317173181731917320173211732217323173241732517326173271732817329173301733117332173331733417335173361733717338173391734017341173421734317344173451734617347173481734917350173511735217353173541735517356173571735817359173601736117362173631736417365173661736717368173691737017371173721737317374173751737617377173781737917380173811738217383173841738517386173871738817389173901739117392173931739417395173961739717398173991740017401174021740317404174051740617407174081740917410174111741217413174141741517416174171741817419174201742117422174231742417425174261742717428174291743017431174321743317434174351743617437174381743917440174411744217443174441744517446174471744817449174501745117452174531745417455174561745717458174591746017461174621746317464174651746617467174681746917470174711747217473174741747517476174771747817479174801748117482174831748417485174861748717488174891749017491174921749317494174951749617497174981749917500175011750217503175041750517506175071750817509175101751117512175131751417515175161751717518175191752017521175221752317524175251752617527175281752917530175311753217533175341753517536175371753817539175401754117542175431754417545175461754717548175491755017551175521755317554175551755617557175581755917560175611756217563175641756517566175671756817569175701757117572175731757417575175761757717578175791758017581175821758317584175851758617587175881758917590175911759217593175941759517596175971759817599176001760117602176031760417605176061760717608176091761017611176121761317614176151761617617176181761917620176211762217623176241762517626176271762817629176301763117632176331763417635176361763717638176391764017641176421764317644176451764617647176481764917650176511765217653176541765517656176571765817659176601766117662176631766417665176661766717668176691767017671176721767317674176751767617677176781767917680176811768217683176841768517686176871768817689176901769117692176931769417695176961769717698176991770017701177021770317704177051770617707177081770917710177111771217713177141771517716177171771817719177201772117722177231772417725177261772717728177291773017731177321773317734177351773617737177381773917740177411774217743177441774517746177471774817749177501775117752177531775417755177561775717758177591776017761177621776317764177651776617767177681776917770177711777217773177741777517776177771777817779177801778117782177831778417785177861778717788177891779017791177921779317794177951779617797177981779917800178011780217803178041780517806178071780817809178101781117812178131781417815178161781717818178191782017821178221782317824178251782617827178281782917830178311783217833178341783517836178371783817839178401784117842178431784417845178461784717848178491785017851178521785317854178551785617857178581785917860178611786217863178641786517866178671786817869178701787117872178731787417875178761787717878178791788017881178821788317884178851788617887178881788917890178911789217893178941789517896178971789817899179001790117902179031790417905179061790717908179091791017911179121791317914179151791617917179181791917920179211792217923179241792517926179271792817929179301793117932179331793417935179361793717938179391794017941179421794317944179451794617947179481794917950179511795217953179541795517956179571795817959179601796117962179631796417965179661796717968179691797017971179721797317974179751797617977179781797917980179811798217983179841798517986179871798817989179901799117992179931799417995179961799717998179991800018001180021800318004180051800618007180081800918010180111801218013180141801518016180171801818019180201802118022180231802418025180261802718028180291803018031180321803318034180351803618037180381803918040180411804218043180441804518046180471804818049180501805118052180531805418055180561805718058180591806018061180621806318064180651806618067180681806918070180711807218073180741807518076180771807818079180801808118082180831808418085180861808718088180891809018091180921809318094180951809618097180981809918100181011810218103181041810518106181071810818109181101811118112181131811418115181161811718118181191812018121181221812318124181251812618127181281812918130181311813218133181341813518136181371813818139181401814118142181431814418145181461814718148181491815018151181521815318154181551815618157181581815918160181611816218163181641816518166181671816818169181701817118172181731817418175181761817718178181791818018181181821818318184181851818618187181881818918190181911819218193181941819518196181971819818199182001820118202182031820418205182061820718208182091821018211182121821318214182151821618217182181821918220182211822218223182241822518226182271822818229182301823118232182331823418235182361823718238182391824018241182421824318244182451824618247182481824918250182511825218253182541825518256182571825818259182601826118262182631826418265182661826718268182691827018271182721827318274182751827618277182781827918280182811828218283182841828518286182871828818289182901829118292182931829418295182961829718298182991830018301183021830318304183051830618307183081830918310183111831218313183141831518316183171831818319183201832118322183231832418325183261832718328183291833018331183321833318334183351833618337183381833918340183411834218343183441834518346183471834818349183501835118352183531835418355183561835718358183591836018361183621836318364183651836618367183681836918370183711837218373183741837518376183771837818379183801838118382183831838418385183861838718388183891839018391183921839318394183951839618397183981839918400184011840218403184041840518406184071840818409184101841118412184131841418415184161841718418184191842018421184221842318424184251842618427184281842918430184311843218433184341843518436184371843818439184401844118442184431844418445184461844718448184491845018451184521845318454184551845618457184581845918460184611846218463184641846518466184671846818469184701847118472184731847418475184761847718478184791848018481184821848318484184851848618487184881848918490184911849218493184941849518496184971849818499185001850118502185031850418505185061850718508185091851018511185121851318514185151851618517185181851918520185211852218523185241852518526185271852818529185301853118532185331853418535185361853718538185391854018541185421854318544185451854618547185481854918550185511855218553185541855518556185571855818559185601856118562185631856418565185661856718568185691857018571185721857318574185751857618577185781857918580185811858218583185841858518586185871858818589185901859118592185931859418595185961859718598185991860018601186021860318604186051860618607186081860918610186111861218613186141861518616186171861818619186201862118622186231862418625186261862718628186291863018631186321863318634186351863618637186381863918640186411864218643186441864518646186471864818649186501865118652186531865418655186561865718658186591866018661186621866318664186651866618667186681866918670186711867218673186741867518676186771867818679186801868118682186831868418685186861868718688186891869018691186921869318694186951869618697186981869918700187011870218703187041870518706187071870818709187101871118712187131871418715187161871718718187191872018721187221872318724187251872618727187281872918730187311873218733187341873518736187371873818739187401874118742187431874418745187461874718748187491875018751187521875318754187551875618757187581875918760187611876218763187641876518766187671876818769187701877118772187731877418775187761877718778187791878018781187821878318784187851878618787187881878918790187911879218793187941879518796187971879818799188001880118802188031880418805188061880718808188091881018811188121881318814188151881618817188181881918820188211882218823188241882518826188271882818829188301883118832188331883418835188361883718838188391884018841188421884318844188451884618847188481884918850188511885218853188541885518856188571885818859188601886118862188631886418865188661886718868188691887018871188721887318874188751887618877188781887918880188811888218883188841888518886188871888818889188901889118892188931889418895188961889718898188991890018901189021890318904189051890618907189081890918910189111891218913189141891518916189171891818919189201892118922189231892418925189261892718928189291893018931189321893318934189351893618937189381893918940189411894218943189441894518946189471894818949189501895118952189531895418955189561895718958189591896018961189621896318964189651896618967189681896918970189711897218973189741897518976189771897818979189801898118982189831898418985189861898718988189891899018991189921899318994189951899618997189981899919000190011900219003190041900519006190071900819009190101901119012190131901419015190161901719018190191902019021190221902319024190251902619027190281902919030190311903219033190341903519036190371903819039190401904119042190431904419045190461904719048190491905019051190521905319054190551905619057190581905919060190611906219063190641906519066190671906819069190701907119072190731907419075190761907719078190791908019081190821908319084190851908619087190881908919090190911909219093190941909519096190971909819099191001910119102191031910419105191061910719108191091911019111191121911319114191151911619117191181911919120191211912219123191241912519126191271912819129191301913119132191331913419135191361913719138191391914019141191421914319144191451914619147191481914919150191511915219153191541915519156191571915819159191601916119162191631916419165191661916719168191691917019171191721917319174191751917619177191781917919180191811918219183191841918519186191871918819189191901919119192191931919419195191961919719198191991920019201192021920319204192051920619207192081920919210192111921219213192141921519216192171921819219192201922119222192231922419225192261922719228192291923019231192321923319234192351923619237192381923919240192411924219243192441924519246192471924819249192501925119252192531925419255192561925719258192591926019261192621926319264192651926619267192681926919270192711927219273192741927519276192771927819279192801928119282192831928419285192861928719288192891929019291192921929319294192951929619297192981929919300193011930219303193041930519306193071930819309193101931119312193131931419315193161931719318193191932019321193221932319324193251932619327193281932919330193311933219333193341933519336193371933819339193401934119342193431934419345193461934719348193491935019351193521935319354193551935619357193581935919360193611936219363193641936519366193671936819369193701937119372193731937419375193761937719378193791938019381193821938319384193851938619387193881938919390193911939219393193941939519396193971939819399194001940119402194031940419405194061940719408194091941019411194121941319414194151941619417194181941919420194211942219423194241942519426194271942819429194301943119432194331943419435194361943719438194391944019441194421944319444194451944619447194481944919450194511945219453194541945519456194571945819459194601946119462194631946419465194661946719468194691947019471194721947319474194751947619477194781947919480194811948219483194841948519486194871948819489194901949119492194931949419495194961949719498194991950019501195021950319504195051950619507195081950919510195111951219513195141951519516195171951819519195201952119522195231952419525195261952719528195291953019531195321953319534195351953619537195381953919540195411954219543195441954519546195471954819549195501955119552195531955419555195561955719558195591956019561195621956319564195651956619567195681956919570195711957219573195741957519576195771957819579195801958119582195831958419585195861958719588195891959019591195921959319594195951959619597195981959919600196011960219603196041960519606196071960819609196101961119612196131961419615196161961719618196191962019621196221962319624196251962619627196281962919630196311963219633196341963519636196371963819639196401964119642196431964419645196461964719648196491965019651196521965319654196551965619657196581965919660196611966219663196641966519666196671966819669196701967119672196731967419675196761967719678196791968019681196821968319684196851968619687196881968919690196911969219693196941969519696196971969819699197001970119702197031970419705197061970719708197091971019711197121971319714197151971619717197181971919720197211972219723197241972519726197271972819729197301973119732197331973419735197361973719738197391974019741197421974319744197451974619747197481974919750197511975219753197541975519756197571975819759197601976119762197631976419765197661976719768197691977019771197721977319774197751977619777197781977919780197811978219783197841978519786197871978819789197901979119792197931979419795197961979719798197991980019801198021980319804198051980619807198081980919810198111981219813198141981519816198171981819819198201982119822198231982419825198261982719828198291983019831198321983319834198351983619837198381983919840198411984219843198441984519846198471984819849198501985119852198531985419855198561985719858198591986019861198621986319864198651986619867198681986919870198711987219873198741987519876198771987819879198801988119882198831988419885198861988719888198891989019891198921989319894198951989619897198981989919900199011990219903199041990519906199071990819909199101991119912199131991419915199161991719918199191992019921199221992319924199251992619927199281992919930199311993219933199341993519936199371993819939199401994119942199431994419945199461994719948199491995019951199521995319954199551995619957199581995919960199611996219963199641996519966199671996819969199701997119972199731997419975199761997719978199791998019981199821998319984199851998619987199881998919990199911999219993199941999519996199971999819999200002000120002200032000420005200062000720008200092001020011200122001320014200152001620017200182001920020200212002220023200242002520026200272002820029200302003120032200332003420035200362003720038200392004020041200422004320044200452004620047200482004920050200512005220053200542005520056200572005820059200602006120062200632006420065200662006720068200692007020071200722007320074200752007620077200782007920080200812008220083200842008520086200872008820089200902009120092200932009420095200962009720098200992010020101201022010320104201052010620107201082010920110201112011220113201142011520116201172011820119201202012120122201232012420125201262012720128201292013020131201322013320134201352013620137201382013920140201412014220143201442014520146201472014820149201502015120152201532015420155201562015720158201592016020161201622016320164201652016620167201682016920170201712017220173201742017520176201772017820179201802018120182201832018420185201862018720188201892019020191201922019320194201952019620197201982019920200202012020220203202042020520206202072020820209202102021120212202132021420215202162021720218202192022020221202222022320224202252022620227202282022920230202312023220233202342023520236202372023820239202402024120242202432024420245202462024720248202492025020251202522025320254202552025620257202582025920260202612026220263202642026520266202672026820269202702027120272202732027420275202762027720278202792028020281202822028320284202852028620287202882028920290202912029220293202942029520296202972029820299203002030120302203032030420305203062030720308203092031020311203122031320314203152031620317203182031920320203212032220323203242032520326203272032820329203302033120332203332033420335203362033720338203392034020341203422034320344203452034620347203482034920350203512035220353203542035520356203572035820359203602036120362203632036420365203662036720368203692037020371203722037320374203752037620377203782037920380203812038220383203842038520386203872038820389203902039120392203932039420395203962039720398203992040020401204022040320404204052040620407204082040920410204112041220413204142041520416204172041820419204202042120422204232042420425204262042720428204292043020431204322043320434204352043620437204382043920440204412044220443204442044520446204472044820449204502045120452204532045420455204562045720458204592046020461204622046320464204652046620467204682046920470204712047220473204742047520476204772047820479204802048120482204832048420485204862048720488204892049020491204922049320494204952049620497204982049920500205012050220503205042050520506205072050820509205102051120512205132051420515205162051720518205192052020521205222052320524205252052620527205282052920530205312053220533205342053520536205372053820539205402054120542205432054420545205462054720548205492055020551205522055320554205552055620557205582055920560205612056220563205642056520566205672056820569205702057120572205732057420575205762057720578205792058020581205822058320584205852058620587205882058920590205912059220593205942059520596205972059820599206002060120602206032060420605206062060720608206092061020611206122061320614206152061620617206182061920620206212062220623206242062520626206272062820629206302063120632206332063420635206362063720638206392064020641206422064320644206452064620647206482064920650206512065220653206542065520656206572065820659206602066120662206632066420665206662066720668206692067020671206722067320674206752067620677206782067920680206812068220683206842068520686206872068820689206902069120692206932069420695206962069720698206992070020701207022070320704207052070620707207082070920710207112071220713207142071520716207172071820719207202072120722207232072420725207262072720728207292073020731207322073320734207352073620737207382073920740207412074220743207442074520746207472074820749207502075120752207532075420755207562075720758207592076020761207622076320764207652076620767207682076920770207712077220773207742077520776207772077820779207802078120782207832078420785207862078720788207892079020791207922079320794207952079620797207982079920800208012080220803208042080520806208072080820809208102081120812208132081420815208162081720818208192082020821208222082320824208252082620827208282082920830208312083220833208342083520836208372083820839208402084120842208432084420845208462084720848208492085020851208522085320854208552085620857208582085920860208612086220863208642086520866208672086820869208702087120872208732087420875208762087720878208792088020881208822088320884208852088620887208882088920890208912089220893208942089520896208972089820899209002090120902209032090420905209062090720908209092091020911209122091320914209152091620917209182091920920209212092220923209242092520926209272092820929209302093120932209332093420935209362093720938209392094020941209422094320944209452094620947209482094920950209512095220953209542095520956209572095820959209602096120962209632096420965209662096720968209692097020971209722097320974209752097620977209782097920980209812098220983209842098520986209872098820989209902099120992209932099420995209962099720998209992100021001210022100321004210052100621007210082100921010210112101221013210142101521016210172101821019210202102121022210232102421025210262102721028210292103021031210322103321034210352103621037210382103921040210412104221043210442104521046210472104821049210502105121052210532105421055210562105721058210592106021061210622106321064210652106621067210682106921070210712107221073210742107521076210772107821079210802108121082210832108421085210862108721088210892109021091210922109321094210952109621097210982109921100211012110221103211042110521106211072110821109211102111121112211132111421115211162111721118211192112021121211222112321124211252112621127211282112921130211312113221133211342113521136211372113821139211402114121142211432114421145211462114721148211492115021151211522115321154211552115621157211582115921160211612116221163211642116521166211672116821169211702117121172211732117421175211762117721178211792118021181211822118321184211852118621187211882118921190211912119221193211942119521196211972119821199212002120121202212032120421205212062120721208212092121021211212122121321214212152121621217212182121921220212212122221223212242122521226212272122821229212302123121232212332123421235212362123721238212392124021241212422124321244212452124621247212482124921250212512125221253212542125521256212572125821259212602126121262212632126421265212662126721268212692127021271212722127321274212752127621277212782127921280212812128221283212842128521286212872128821289212902129121292212932129421295212962129721298212992130021301213022130321304213052130621307213082130921310213112131221313213142131521316213172131821319213202132121322213232132421325213262132721328213292133021331213322133321334213352133621337213382133921340213412134221343213442134521346213472134821349213502135121352213532135421355213562135721358213592136021361213622136321364213652136621367213682136921370213712137221373213742137521376213772137821379213802138121382213832138421385213862138721388213892139021391213922139321394213952139621397213982139921400214012140221403214042140521406214072140821409214102141121412214132141421415214162141721418214192142021421214222142321424214252142621427214282142921430214312143221433214342143521436214372143821439214402144121442214432144421445214462144721448214492145021451214522145321454214552145621457214582145921460214612146221463214642146521466214672146821469214702147121472214732147421475214762147721478214792148021481214822148321484214852148621487214882148921490214912149221493214942149521496214972149821499215002150121502215032150421505215062150721508215092151021511215122151321514215152151621517215182151921520215212152221523215242152521526215272152821529215302153121532215332153421535215362153721538215392154021541215422154321544215452154621547215482154921550215512155221553215542155521556215572155821559215602156121562215632156421565215662156721568215692157021571215722157321574215752157621577215782157921580215812158221583215842158521586215872158821589215902159121592215932159421595215962159721598215992160021601216022160321604216052160621607216082160921610216112161221613216142161521616216172161821619216202162121622216232162421625216262162721628216292163021631216322163321634216352163621637216382163921640216412164221643216442164521646216472164821649216502165121652216532165421655216562165721658216592166021661216622166321664216652166621667216682166921670216712167221673216742167521676216772167821679216802168121682216832168421685216862168721688216892169021691216922169321694216952169621697216982169921700217012170221703217042170521706217072170821709217102171121712217132171421715217162171721718217192172021721217222172321724217252172621727217282172921730217312173221733217342173521736217372173821739217402174121742217432174421745217462174721748217492175021751217522175321754217552175621757217582175921760217612176221763217642176521766217672176821769217702177121772217732177421775217762177721778217792178021781217822178321784217852178621787217882178921790217912179221793217942179521796217972179821799218002180121802218032180421805218062180721808218092181021811218122181321814218152181621817218182181921820218212182221823218242182521826218272182821829218302183121832218332183421835218362183721838218392184021841218422184321844218452184621847218482184921850218512185221853218542185521856218572185821859218602186121862218632186421865218662186721868218692187021871218722187321874218752187621877218782187921880218812188221883218842188521886218872188821889218902189121892218932189421895218962189721898218992190021901219022190321904219052190621907219082190921910219112191221913219142191521916219172191821919219202192121922219232192421925219262192721928219292193021931219322193321934219352193621937219382193921940219412194221943219442194521946219472194821949219502195121952219532195421955219562195721958219592196021961219622196321964219652196621967219682196921970219712197221973219742197521976219772197821979219802198121982219832198421985219862198721988219892199021991219922199321994219952199621997219982199922000220012200222003220042200522006220072200822009220102201122012220132201422015220162201722018220192202022021220222202322024220252202622027220282202922030220312203222033220342203522036220372203822039220402204122042220432204422045220462204722048220492205022051220522205322054220552205622057220582205922060220612206222063220642206522066220672206822069220702207122072220732207422075220762207722078220792208022081220822208322084220852208622087220882208922090220912209222093220942209522096220972209822099221002210122102221032210422105221062210722108221092211022111221122211322114221152211622117221182211922120221212212222123221242212522126221272212822129221302213122132221332213422135221362213722138221392214022141221422214322144221452214622147221482214922150221512215222153221542215522156221572215822159221602216122162221632216422165221662216722168221692217022171221722217322174221752217622177221782217922180221812218222183221842218522186221872218822189221902219122192221932219422195221962219722198221992220022201222022220322204222052220622207222082220922210222112221222213222142221522216222172221822219222202222122222222232222422225222262222722228222292223022231222322223322234222352223622237222382223922240222412224222243222442224522246222472224822249222502225122252222532225422255222562225722258222592226022261222622226322264222652226622267222682226922270222712227222273222742227522276222772227822279222802228122282222832228422285222862228722288222892229022291222922229322294222952229622297222982229922300223012230222303223042230522306223072230822309223102231122312223132231422315223162231722318223192232022321223222232322324223252232622327223282232922330223312233222333223342233522336223372233822339223402234122342223432234422345223462234722348223492235022351223522235322354223552235622357223582235922360223612236222363223642236522366223672236822369223702237122372223732237422375223762237722378223792238022381223822238322384223852238622387223882238922390223912239222393223942239522396223972239822399224002240122402224032240422405224062240722408224092241022411224122241322414224152241622417224182241922420224212242222423224242242522426224272242822429224302243122432224332243422435224362243722438224392244022441224422244322444224452244622447224482244922450224512245222453224542245522456224572245822459224602246122462224632246422465224662246722468224692247022471224722247322474224752247622477224782247922480224812248222483224842248522486224872248822489224902249122492224932249422495224962249722498224992250022501225022250322504225052250622507225082250922510225112251222513225142251522516225172251822519225202252122522225232252422525225262252722528225292253022531225322253322534225352253622537225382253922540225412254222543225442254522546225472254822549225502255122552225532255422555225562255722558225592256022561225622256322564225652256622567225682256922570225712257222573225742257522576225772257822579225802258122582225832258422585225862258722588225892259022591225922259322594225952259622597225982259922600226012260222603226042260522606226072260822609226102261122612226132261422615226162261722618226192262022621226222262322624226252262622627226282262922630226312263222633226342263522636226372263822639226402264122642226432264422645226462264722648226492265022651226522265322654226552265622657226582265922660226612266222663226642266522666226672266822669226702267122672226732267422675226762267722678226792268022681226822268322684226852268622687226882268922690226912269222693226942269522696226972269822699227002270122702227032270422705227062270722708227092271022711227122271322714227152271622717227182271922720227212272222723227242272522726227272272822729227302273122732227332273422735227362273722738227392274022741227422274322744227452274622747227482274922750227512275222753227542275522756227572275822759227602276122762227632276422765227662276722768227692277022771227722277322774227752277622777227782277922780227812278222783227842278522786227872278822789227902279122792227932279422795227962279722798227992280022801228022280322804228052280622807228082280922810228112281222813228142281522816228172281822819228202282122822228232282422825228262282722828228292283022831228322283322834228352283622837228382283922840228412284222843228442284522846228472284822849228502285122852228532285422855228562285722858228592286022861228622286322864228652286622867228682286922870228712287222873228742287522876228772287822879228802288122882228832288422885228862288722888228892289022891228922289322894228952289622897228982289922900229012290222903229042290522906229072290822909229102291122912229132291422915229162291722918229192292022921229222292322924229252292622927229282292922930229312293222933229342293522936229372293822939229402294122942229432294422945229462294722948229492295022951229522295322954229552295622957229582295922960229612296222963229642296522966229672296822969229702297122972229732297422975229762297722978229792298022981229822298322984229852298622987229882298922990229912299222993229942299522996229972299822999230002300123002230032300423005230062300723008230092301023011230122301323014230152301623017230182301923020230212302223023230242302523026230272302823029230302303123032230332303423035230362303723038230392304023041230422304323044230452304623047230482304923050230512305223053230542305523056230572305823059230602306123062230632306423065230662306723068230692307023071230722307323074230752307623077230782307923080230812308223083230842308523086230872308823089230902309123092230932309423095230962309723098230992310023101231022310323104231052310623107231082310923110231112311223113231142311523116231172311823119231202312123122231232312423125231262312723128231292313023131231322313323134231352313623137231382313923140231412314223143231442314523146231472314823149231502315123152231532315423155231562315723158231592316023161231622316323164231652316623167231682316923170231712317223173231742317523176231772317823179231802318123182231832318423185231862318723188231892319023191231922319323194231952319623197231982319923200232012320223203232042320523206232072320823209232102321123212232132321423215232162321723218232192322023221232222322323224232252322623227232282322923230232312323223233232342323523236232372323823239232402324123242232432324423245232462324723248232492325023251232522325323254232552325623257232582325923260232612326223263232642326523266232672326823269232702327123272232732327423275232762327723278232792328023281232822328323284232852328623287232882328923290232912329223293232942329523296232972329823299233002330123302233032330423305233062330723308233092331023311233122331323314233152331623317233182331923320233212332223323233242332523326233272332823329233302333123332233332333423335233362333723338233392334023341233422334323344233452334623347233482334923350233512335223353233542335523356233572335823359233602336123362233632336423365233662336723368233692337023371233722337323374233752337623377233782337923380233812338223383233842338523386233872338823389233902339123392233932339423395233962339723398233992340023401234022340323404234052340623407234082340923410234112341223413234142341523416234172341823419234202342123422234232342423425234262342723428234292343023431234322343323434234352343623437234382343923440234412344223443234442344523446234472344823449234502345123452234532345423455234562345723458234592346023461234622346323464234652346623467234682346923470234712347223473234742347523476234772347823479234802348123482234832348423485234862348723488234892349023491234922349323494234952349623497234982349923500235012350223503235042350523506235072350823509235102351123512235132351423515235162351723518235192352023521235222352323524235252352623527235282352923530235312353223533235342353523536235372353823539235402354123542235432354423545235462354723548235492355023551235522355323554235552355623557235582355923560235612356223563235642356523566235672356823569235702357123572235732357423575235762357723578235792358023581235822358323584235852358623587235882358923590235912359223593235942359523596235972359823599236002360123602236032360423605236062360723608236092361023611236122361323614236152361623617236182361923620236212362223623236242362523626236272362823629236302363123632236332363423635236362363723638236392364023641236422364323644236452364623647236482364923650236512365223653236542365523656236572365823659236602366123662236632366423665236662366723668236692367023671236722367323674236752367623677236782367923680236812368223683236842368523686236872368823689236902369123692236932369423695236962369723698236992370023701237022370323704237052370623707237082370923710237112371223713237142371523716237172371823719237202372123722237232372423725237262372723728237292373023731237322373323734237352373623737237382373923740237412374223743237442374523746237472374823749237502375123752237532375423755237562375723758237592376023761237622376323764237652376623767237682376923770237712377223773237742377523776237772377823779237802378123782237832378423785237862378723788237892379023791237922379323794237952379623797237982379923800238012380223803238042380523806238072380823809238102381123812238132381423815238162381723818238192382023821238222382323824238252382623827238282382923830238312383223833238342383523836238372383823839238402384123842238432384423845238462384723848238492385023851238522385323854238552385623857238582385923860238612386223863238642386523866238672386823869238702387123872238732387423875238762387723878238792388023881238822388323884238852388623887238882388923890238912389223893238942389523896238972389823899239002390123902239032390423905239062390723908239092391023911239122391323914239152391623917239182391923920239212392223923239242392523926239272392823929239302393123932239332393423935239362393723938239392394023941239422394323944239452394623947239482394923950239512395223953239542395523956239572395823959239602396123962239632396423965239662396723968239692397023971239722397323974239752397623977239782397923980239812398223983239842398523986239872398823989239902399123992239932399423995239962399723998239992400024001240022400324004240052400624007240082400924010240112401224013240142401524016240172401824019240202402124022240232402424025240262402724028240292403024031240322403324034240352403624037240382403924040240412404224043240442404524046240472404824049240502405124052240532405424055240562405724058240592406024061240622406324064240652406624067240682406924070240712407224073240742407524076240772407824079240802408124082240832408424085240862408724088240892409024091240922409324094240952409624097240982409924100241012410224103241042410524106241072410824109241102411124112241132411424115241162411724118241192412024121241222412324124241252412624127241282412924130241312413224133241342413524136241372413824139241402414124142241432414424145241462414724148241492415024151241522415324154241552415624157241582415924160241612416224163241642416524166241672416824169241702417124172241732417424175241762417724178241792418024181241822418324184241852418624187241882418924190241912419224193241942419524196241972419824199242002420124202242032420424205242062420724208242092421024211242122421324214242152421624217242182421924220242212422224223242242422524226242272422824229242302423124232242332423424235242362423724238242392424024241242422424324244242452424624247242482424924250242512425224253242542425524256242572425824259242602426124262242632426424265242662426724268242692427024271242722427324274242752427624277242782427924280242812428224283242842428524286242872428824289242902429124292242932429424295242962429724298242992430024301243022430324304243052430624307243082430924310243112431224313243142431524316243172431824319243202432124322243232432424325243262432724328243292433024331243322433324334243352433624337243382433924340243412434224343243442434524346243472434824349243502435124352243532435424355243562435724358243592436024361243622436324364243652436624367243682436924370243712437224373243742437524376243772437824379243802438124382243832438424385243862438724388243892439024391243922439324394243952439624397243982439924400244012440224403244042440524406244072440824409244102441124412244132441424415244162441724418244192442024421244222442324424244252442624427244282442924430244312443224433244342443524436244372443824439244402444124442244432444424445244462444724448244492445024451244522445324454244552445624457244582445924460244612446224463244642446524466244672446824469244702447124472244732447424475244762447724478244792448024481244822448324484244852448624487244882448924490244912449224493244942449524496244972449824499245002450124502245032450424505245062450724508245092451024511245122451324514245152451624517245182451924520245212452224523245242452524526245272452824529245302453124532245332453424535245362453724538245392454024541245422454324544245452454624547245482454924550245512455224553245542455524556245572455824559245602456124562245632456424565245662456724568245692457024571245722457324574245752457624577245782457924580245812458224583245842458524586245872458824589245902459124592245932459424595245962459724598245992460024601246022460324604246052460624607246082460924610246112461224613246142461524616246172461824619246202462124622246232462424625246262462724628246292463024631246322463324634246352463624637246382463924640246412464224643246442464524646246472464824649246502465124652246532465424655246562465724658246592466024661246622466324664246652466624667246682466924670246712467224673246742467524676246772467824679246802468124682246832468424685246862468724688246892469024691246922469324694246952469624697246982469924700247012470224703247042470524706247072470824709247102471124712247132471424715247162471724718247192472024721247222472324724247252472624727247282472924730247312473224733247342473524736247372473824739247402474124742247432474424745247462474724748247492475024751247522475324754247552475624757247582475924760247612476224763247642476524766247672476824769247702477124772247732477424775247762477724778247792478024781247822478324784247852478624787247882478924790247912479224793247942479524796247972479824799248002480124802248032480424805248062480724808248092481024811248122481324814248152481624817248182481924820248212482224823248242482524826248272482824829248302483124832248332483424835248362483724838248392484024841248422484324844248452484624847248482484924850248512485224853248542485524856248572485824859248602486124862248632486424865248662486724868248692487024871248722487324874248752487624877248782487924880248812488224883248842488524886248872488824889248902489124892248932489424895248962489724898248992490024901249022490324904249052490624907249082490924910249112491224913249142491524916249172491824919249202492124922249232492424925249262492724928249292493024931249322493324934249352493624937249382493924940249412494224943249442494524946249472494824949249502495124952249532495424955249562495724958249592496024961249622496324964249652496624967249682496924970249712497224973249742497524976249772497824979249802498124982249832498424985249862498724988249892499024991249922499324994249952499624997249982499925000250012500225003250042500525006250072500825009250102501125012250132501425015250162501725018250192502025021250222502325024250252502625027250282502925030250312503225033250342503525036250372503825039250402504125042250432504425045250462504725048250492505025051250522505325054250552505625057250582505925060250612506225063250642506525066250672506825069250702507125072250732507425075250762507725078250792508025081250822508325084250852508625087250882508925090250912509225093250942509525096250972509825099251002510125102251032510425105251062510725108251092511025111251122511325114251152511625117251182511925120251212512225123251242512525126251272512825129251302513125132251332513425135251362513725138251392514025141251422514325144251452514625147251482514925150251512515225153251542515525156251572515825159251602516125162251632516425165251662516725168251692517025171251722517325174251752517625177251782517925180251812518225183251842518525186251872518825189251902519125192251932519425195251962519725198251992520025201252022520325204252052520625207252082520925210252112521225213252142521525216252172521825219252202522125222252232522425225252262522725228252292523025231252322523325234252352523625237252382523925240252412524225243252442524525246252472524825249252502525125252252532525425255252562525725258252592526025261252622526325264252652526625267252682526925270252712527225273252742527525276252772527825279252802528125282252832528425285252862528725288252892529025291252922529325294252952529625297252982529925300253012530225303253042530525306253072530825309253102531125312253132531425315253162531725318253192532025321253222532325324253252532625327253282532925330253312533225333253342533525336253372533825339253402534125342253432534425345253462534725348253492535025351253522535325354253552535625357253582535925360253612536225363253642536525366253672536825369253702537125372253732537425375253762537725378253792538025381253822538325384253852538625387253882538925390253912539225393253942539525396253972539825399254002540125402254032540425405254062540725408254092541025411254122541325414254152541625417254182541925420254212542225423254242542525426254272542825429254302543125432254332543425435254362543725438254392544025441254422544325444254452544625447254482544925450254512545225453254542545525456254572545825459254602546125462254632546425465254662546725468254692547025471254722547325474254752547625477254782547925480254812548225483254842548525486254872548825489254902549125492254932549425495254962549725498254992550025501255022550325504255052550625507255082550925510255112551225513255142551525516255172551825519255202552125522255232552425525255262552725528255292553025531255322553325534255352553625537255382553925540255412554225543255442554525546255472554825549255502555125552255532555425555255562555725558255592556025561255622556325564255652556625567255682556925570255712557225573255742557525576255772557825579255802558125582255832558425585255862558725588255892559025591255922559325594255952559625597255982559925600256012560225603256042560525606256072560825609256102561125612256132561425615256162561725618256192562025621256222562325624256252562625627256282562925630256312563225633256342563525636256372563825639256402564125642256432564425645256462564725648256492565025651256522565325654256552565625657256582565925660256612566225663256642566525666256672566825669256702567125672256732567425675256762567725678256792568025681256822568325684256852568625687256882568925690256912569225693256942569525696256972569825699257002570125702257032570425705257062570725708257092571025711257122571325714257152571625717257182571925720257212572225723257242572525726257272572825729257302573125732257332573425735257362573725738257392574025741257422574325744257452574625747257482574925750257512575225753257542575525756257572575825759257602576125762257632576425765257662576725768257692577025771257722577325774257752577625777257782577925780257812578225783257842578525786257872578825789257902579125792257932579425795257962579725798257992580025801258022580325804258052580625807258082580925810258112581225813258142581525816258172581825819258202582125822258232582425825258262582725828258292583025831258322583325834258352583625837258382583925840258412584225843258442584525846258472584825849258502585125852258532585425855258562585725858258592586025861258622586325864258652586625867258682586925870258712587225873258742587525876258772587825879258802588125882258832588425885258862588725888258892589025891258922589325894258952589625897258982589925900259012590225903259042590525906259072590825909259102591125912259132591425915259162591725918259192592025921259222592325924259252592625927259282592925930259312593225933259342593525936259372593825939259402594125942259432594425945259462594725948259492595025951259522595325954259552595625957259582595925960259612596225963259642596525966259672596825969259702597125972259732597425975259762597725978259792598025981259822598325984259852598625987259882598925990259912599225993259942599525996259972599825999260002600126002260032600426005260062600726008260092601026011260122601326014260152601626017260182601926020260212602226023260242602526026260272602826029260302603126032260332603426035260362603726038260392604026041260422604326044260452604626047260482604926050260512605226053260542605526056260572605826059260602606126062260632606426065260662606726068260692607026071260722607326074260752607626077260782607926080260812608226083260842608526086260872608826089260902609126092260932609426095260962609726098260992610026101261022610326104261052610626107261082610926110261112611226113261142611526116261172611826119261202612126122261232612426125261262612726128261292613026131261322613326134261352613626137261382613926140261412614226143261442614526146261472614826149261502615126152261532615426155261562615726158261592616026161261622616326164261652616626167261682616926170261712617226173261742617526176261772617826179261802618126182261832618426185261862618726188261892619026191261922619326194261952619626197261982619926200262012620226203262042620526206262072620826209262102621126212262132621426215262162621726218262192622026221262222622326224262252622626227262282622926230262312623226233262342623526236262372623826239262402624126242262432624426245262462624726248262492625026251262522625326254262552625626257262582625926260262612626226263262642626526266262672626826269262702627126272262732627426275262762627726278262792628026281262822628326284262852628626287262882628926290262912629226293262942629526296262972629826299263002630126302263032630426305263062630726308263092631026311263122631326314263152631626317263182631926320263212632226323263242632526326263272632826329263302633126332263332633426335263362633726338263392634026341263422634326344263452634626347263482634926350263512635226353263542635526356263572635826359263602636126362263632636426365263662636726368263692637026371263722637326374263752637626377263782637926380263812638226383263842638526386263872638826389263902639126392263932639426395263962639726398263992640026401264022640326404264052640626407264082640926410264112641226413264142641526416264172641826419264202642126422264232642426425264262642726428264292643026431264322643326434264352643626437264382643926440264412644226443264442644526446264472644826449264502645126452264532645426455264562645726458264592646026461264622646326464264652646626467264682646926470264712647226473264742647526476264772647826479264802648126482264832648426485264862648726488264892649026491264922649326494264952649626497264982649926500265012650226503265042650526506265072650826509265102651126512265132651426515265162651726518265192652026521265222652326524265252652626527265282652926530265312653226533265342653526536265372653826539265402654126542265432654426545265462654726548265492655026551265522655326554265552655626557265582655926560265612656226563265642656526566265672656826569265702657126572265732657426575265762657726578265792658026581265822658326584265852658626587265882658926590265912659226593265942659526596265972659826599266002660126602266032660426605266062660726608266092661026611266122661326614266152661626617266182661926620266212662226623266242662526626266272662826629266302663126632266332663426635266362663726638266392664026641266422664326644266452664626647266482664926650266512665226653266542665526656266572665826659266602666126662266632666426665266662666726668266692667026671266722667326674266752667626677266782667926680266812668226683266842668526686266872668826689266902669126692266932669426695266962669726698266992670026701267022670326704267052670626707267082670926710267112671226713267142671526716267172671826719267202672126722267232672426725267262672726728267292673026731267322673326734267352673626737267382673926740267412674226743267442674526746267472674826749267502675126752267532675426755267562675726758267592676026761267622676326764267652676626767267682676926770267712677226773267742677526776267772677826779267802678126782267832678426785267862678726788267892679026791267922679326794267952679626797267982679926800268012680226803268042680526806268072680826809268102681126812268132681426815268162681726818268192682026821268222682326824268252682626827268282682926830268312683226833268342683526836268372683826839268402684126842268432684426845268462684726848268492685026851268522685326854268552685626857268582685926860268612686226863268642686526866268672686826869268702687126872268732687426875268762687726878268792688026881268822688326884268852688626887268882688926890268912689226893268942689526896268972689826899269002690126902269032690426905269062690726908269092691026911269122691326914269152691626917269182691926920269212692226923269242692526926269272692826929269302693126932269332693426935269362693726938269392694026941269422694326944269452694626947269482694926950269512695226953269542695526956269572695826959269602696126962269632696426965269662696726968269692697026971269722697326974269752697626977269782697926980269812698226983269842698526986269872698826989269902699126992269932699426995269962699726998269992700027001270022700327004270052700627007270082700927010270112701227013270142701527016270172701827019270202702127022270232702427025270262702727028270292703027031270322703327034270352703627037270382703927040270412704227043270442704527046270472704827049270502705127052270532705427055270562705727058270592706027061270622706327064270652706627067270682706927070270712707227073270742707527076270772707827079270802708127082270832708427085270862708727088270892709027091270922709327094270952709627097270982709927100271012710227103271042710527106271072710827109271102711127112271132711427115271162711727118271192712027121271222712327124271252712627127271282712927130271312713227133271342713527136271372713827139271402714127142271432714427145271462714727148271492715027151271522715327154271552715627157271582715927160271612716227163271642716527166271672716827169271702717127172271732717427175271762717727178271792718027181271822718327184271852718627187271882718927190271912719227193271942719527196271972719827199272002720127202272032720427205272062720727208272092721027211272122721327214272152721627217272182721927220272212722227223272242722527226272272722827229272302723127232272332723427235272362723727238272392724027241272422724327244272452724627247272482724927250272512725227253272542725527256272572725827259272602726127262272632726427265272662726727268272692727027271272722727327274272752727627277272782727927280272812728227283272842728527286272872728827289272902729127292272932729427295272962729727298272992730027301273022730327304273052730627307273082730927310273112731227313273142731527316273172731827319273202732127322273232732427325273262732727328273292733027331273322733327334273352733627337273382733927340273412734227343273442734527346273472734827349273502735127352273532735427355273562735727358273592736027361273622736327364273652736627367273682736927370273712737227373273742737527376273772737827379273802738127382273832738427385273862738727388273892739027391273922739327394273952739627397273982739927400274012740227403274042740527406274072740827409274102741127412274132741427415274162741727418274192742027421274222742327424274252742627427274282742927430274312743227433274342743527436274372743827439274402744127442274432744427445274462744727448274492745027451274522745327454274552745627457274582745927460274612746227463274642746527466274672746827469274702747127472274732747427475274762747727478274792748027481274822748327484274852748627487274882748927490274912749227493274942749527496274972749827499275002750127502275032750427505275062750727508275092751027511275122751327514275152751627517275182751927520275212752227523275242752527526275272752827529275302753127532275332753427535275362753727538275392754027541275422754327544275452754627547275482754927550275512755227553275542755527556275572755827559275602756127562275632756427565275662756727568275692757027571275722757327574275752757627577275782757927580275812758227583275842758527586275872758827589275902759127592275932759427595275962759727598275992760027601276022760327604276052760627607276082760927610276112761227613276142761527616276172761827619276202762127622276232762427625276262762727628276292763027631276322763327634276352763627637276382763927640276412764227643276442764527646276472764827649276502765127652276532765427655276562765727658276592766027661276622766327664276652766627667276682766927670276712767227673276742767527676276772767827679276802768127682276832768427685276862768727688276892769027691276922769327694276952769627697276982769927700277012770227703277042770527706277072770827709277102771127712277132771427715277162771727718277192772027721277222772327724277252772627727277282772927730277312773227733277342773527736277372773827739277402774127742277432774427745277462774727748277492775027751277522775327754277552775627757277582775927760277612776227763277642776527766277672776827769277702777127772277732777427775277762777727778277792778027781277822778327784277852778627787277882778927790277912779227793277942779527796277972779827799278002780127802278032780427805278062780727808278092781027811278122781327814278152781627817278182781927820278212782227823278242782527826278272782827829278302783127832278332783427835278362783727838278392784027841278422784327844278452784627847278482784927850278512785227853278542785527856278572785827859278602786127862278632786427865278662786727868278692787027871278722787327874278752787627877278782787927880278812788227883278842788527886278872788827889278902789127892278932789427895278962789727898278992790027901279022790327904279052790627907279082790927910279112791227913279142791527916279172791827919279202792127922279232792427925279262792727928279292793027931279322793327934279352793627937279382793927940279412794227943279442794527946279472794827949279502795127952279532795427955279562795727958279592796027961279622796327964279652796627967279682796927970279712797227973279742797527976279772797827979279802798127982279832798427985279862798727988279892799027991279922799327994279952799627997279982799928000280012800228003280042800528006280072800828009280102801128012280132801428015280162801728018280192802028021280222802328024280252802628027280282802928030280312803228033280342803528036280372803828039280402804128042280432804428045280462804728048280492805028051280522805328054280552805628057280582805928060280612806228063280642806528066280672806828069280702807128072280732807428075280762807728078280792808028081280822808328084280852808628087280882808928090280912809228093280942809528096280972809828099281002810128102281032810428105281062810728108281092811028111281122811328114281152811628117281182811928120281212812228123281242812528126281272812828129281302813128132281332813428135281362813728138281392814028141281422814328144281452814628147281482814928150281512815228153281542815528156281572815828159281602816128162281632816428165281662816728168281692817028171281722817328174281752817628177281782817928180281812818228183281842818528186281872818828189281902819128192281932819428195281962819728198281992820028201282022820328204282052820628207282082820928210282112821228213282142821528216282172821828219282202822128222282232822428225282262822728228282292823028231282322823328234282352823628237282382823928240282412824228243282442824528246282472824828249282502825128252282532825428255282562825728258282592826028261282622826328264282652826628267282682826928270282712827228273282742827528276282772827828279282802828128282282832828428285282862828728288282892829028291282922829328294282952829628297282982829928300283012830228303283042830528306283072830828309283102831128312283132831428315283162831728318283192832028321283222832328324283252832628327283282832928330283312833228333283342833528336283372833828339283402834128342283432834428345283462834728348283492835028351283522835328354283552835628357283582835928360283612836228363283642836528366283672836828369283702837128372283732837428375283762837728378283792838028381283822838328384283852838628387283882838928390283912839228393283942839528396283972839828399284002840128402284032840428405284062840728408284092841028411284122841328414284152841628417284182841928420284212842228423284242842528426284272842828429284302843128432284332843428435284362843728438284392844028441284422844328444284452844628447284482844928450284512845228453284542845528456284572845828459284602846128462284632846428465284662846728468284692847028471284722847328474284752847628477284782847928480284812848228483284842848528486284872848828489284902849128492284932849428495284962849728498284992850028501285022850328504285052850628507285082850928510285112851228513285142851528516285172851828519285202852128522285232852428525285262852728528285292853028531285322853328534285352853628537285382853928540285412854228543285442854528546285472854828549285502855128552285532855428555285562855728558285592856028561285622856328564285652856628567285682856928570285712857228573285742857528576285772857828579285802858128582285832858428585285862858728588285892859028591285922859328594285952859628597285982859928600286012860228603286042860528606286072860828609286102861128612286132861428615286162861728618286192862028621286222862328624286252862628627286282862928630286312863228633286342863528636286372863828639286402864128642286432864428645286462864728648286492865028651286522865328654286552865628657286582865928660286612866228663286642866528666286672866828669286702867128672286732867428675286762867728678286792868028681286822868328684286852868628687286882868928690286912869228693286942869528696286972869828699287002870128702287032870428705287062870728708287092871028711287122871328714287152871628717287182871928720287212872228723287242872528726287272872828729287302873128732287332873428735287362873728738287392874028741287422874328744287452874628747287482874928750287512875228753287542875528756287572875828759287602876128762287632876428765287662876728768287692877028771287722877328774287752877628777287782877928780287812878228783287842878528786287872878828789287902879128792287932879428795287962879728798287992880028801288022880328804288052880628807288082880928810288112881228813288142881528816288172881828819288202882128822288232882428825288262882728828288292883028831288322883328834288352883628837288382883928840288412884228843288442884528846288472884828849288502885128852288532885428855288562885728858288592886028861288622886328864288652886628867288682886928870288712887228873288742887528876288772887828879288802888128882288832888428885288862888728888288892889028891288922889328894288952889628897288982889928900289012890228903289042890528906289072890828909289102891128912289132891428915289162891728918289192892028921289222892328924289252892628927289282892928930289312893228933289342893528936289372893828939289402894128942289432894428945289462894728948289492895028951289522895328954289552895628957289582895928960289612896228963289642896528966289672896828969289702897128972289732897428975289762897728978289792898028981289822898328984289852898628987289882898928990289912899228993289942899528996289972899828999290002900129002290032900429005290062900729008290092901029011290122901329014290152901629017290182901929020290212902229023290242902529026290272902829029290302903129032290332903429035290362903729038290392904029041290422904329044290452904629047290482904929050290512905229053290542905529056290572905829059290602906129062290632906429065290662906729068290692907029071290722907329074290752907629077290782907929080290812908229083290842908529086290872908829089290902909129092290932909429095290962909729098290992910029101291022910329104291052910629107291082910929110291112911229113291142911529116291172911829119291202912129122291232912429125291262912729128291292913029131291322913329134291352913629137291382913929140291412914229143291442914529146291472914829149291502915129152291532915429155291562915729158291592916029161291622916329164291652916629167291682916929170291712917229173291742917529176291772917829179291802918129182291832918429185291862918729188291892919029191291922919329194291952919629197291982919929200292012920229203292042920529206292072920829209292102921129212292132921429215292162921729218292192922029221292222922329224292252922629227292282922929230292312923229233292342923529236292372923829239292402924129242292432924429245292462924729248292492925029251292522925329254292552925629257292582925929260292612926229263292642926529266292672926829269292702927129272292732927429275292762927729278292792928029281292822928329284292852928629287292882928929290292912929229293292942929529296292972929829299293002930129302293032930429305293062930729308293092931029311293122931329314293152931629317293182931929320293212932229323293242932529326293272932829329293302933129332293332933429335293362933729338293392934029341293422934329344293452934629347293482934929350293512935229353293542935529356293572935829359293602936129362293632936429365293662936729368293692937029371293722937329374293752937629377293782937929380293812938229383293842938529386293872938829389293902939129392293932939429395293962939729398293992940029401294022940329404294052940629407294082940929410294112941229413294142941529416294172941829419294202942129422294232942429425294262942729428294292943029431294322943329434294352943629437294382943929440294412944229443294442944529446294472944829449294502945129452294532945429455294562945729458294592946029461294622946329464294652946629467294682946929470294712947229473294742947529476294772947829479294802948129482294832948429485294862948729488294892949029491294922949329494294952949629497294982949929500295012950229503295042950529506295072950829509295102951129512295132951429515295162951729518295192952029521295222952329524295252952629527295282952929530295312953229533295342953529536295372953829539295402954129542295432954429545295462954729548295492955029551295522955329554295552955629557295582955929560295612956229563295642956529566295672956829569295702957129572295732957429575295762957729578295792958029581295822958329584295852958629587295882958929590295912959229593295942959529596295972959829599296002960129602296032960429605296062960729608296092961029611296122961329614296152961629617296182961929620296212962229623296242962529626296272962829629296302963129632296332963429635296362963729638296392964029641296422964329644296452964629647296482964929650296512965229653296542965529656296572965829659296602966129662296632966429665296662966729668296692967029671296722967329674296752967629677296782967929680296812968229683296842968529686296872968829689296902969129692296932969429695296962969729698296992970029701297022970329704297052970629707297082970929710297112971229713297142971529716297172971829719297202972129722297232972429725297262972729728297292973029731297322973329734297352973629737297382973929740297412974229743297442974529746297472974829749297502975129752297532975429755297562975729758297592976029761297622976329764297652976629767297682976929770297712977229773297742977529776297772977829779297802978129782297832978429785297862978729788297892979029791297922979329794297952979629797297982979929800298012980229803298042980529806298072980829809298102981129812298132981429815298162981729818298192982029821298222982329824298252982629827298282982929830298312983229833298342983529836298372983829839298402984129842298432984429845298462984729848298492985029851298522985329854298552985629857298582985929860298612986229863298642986529866298672986829869298702987129872298732987429875298762987729878298792988029881298822988329884298852988629887298882988929890298912989229893298942989529896298972989829899299002990129902299032990429905299062990729908299092991029911299122991329914299152991629917299182991929920299212992229923299242992529926299272992829929299302993129932299332993429935299362993729938299392994029941299422994329944299452994629947299482994929950299512995229953299542995529956299572995829959299602996129962299632996429965299662996729968299692997029971299722997329974299752997629977299782997929980299812998229983299842998529986299872998829989299902999129992299932999429995299962999729998299993000030001300023000330004300053000630007300083000930010300113001230013300143001530016300173001830019300203002130022300233002430025300263002730028300293003030031300323003330034300353003630037300383003930040300413004230043300443004530046300473004830049300503005130052300533005430055300563005730058300593006030061300623006330064300653006630067300683006930070300713007230073300743007530076300773007830079300803008130082300833008430085300863008730088300893009030091300923009330094300953009630097300983009930100301013010230103301043010530106301073010830109301103011130112301133011430115301163011730118301193012030121301223012330124301253012630127301283012930130301313013230133301343013530136301373013830139301403014130142301433014430145301463014730148301493015030151301523015330154301553015630157301583015930160301613016230163301643016530166301673016830169301703017130172301733017430175301763017730178301793018030181301823018330184301853018630187301883018930190301913019230193301943019530196301973019830199302003020130202302033020430205302063020730208302093021030211302123021330214302153021630217302183021930220302213022230223302243022530226302273022830229302303023130232302333023430235302363023730238302393024030241302423024330244302453024630247302483024930250302513025230253302543025530256302573025830259302603026130262302633026430265302663026730268302693027030271302723027330274302753027630277302783027930280302813028230283302843028530286302873028830289302903029130292302933029430295302963029730298302993030030301303023030330304303053030630307303083030930310303113031230313303143031530316303173031830319303203032130322303233032430325303263032730328303293033030331303323033330334303353033630337303383033930340303413034230343303443034530346303473034830349303503035130352303533035430355303563035730358303593036030361303623036330364303653036630367303683036930370303713037230373303743037530376303773037830379303803038130382303833038430385303863038730388303893039030391303923039330394303953039630397303983039930400304013040230403304043040530406304073040830409304103041130412304133041430415304163041730418304193042030421304223042330424304253042630427304283042930430304313043230433304343043530436304373043830439304403044130442304433044430445304463044730448304493045030451304523045330454304553045630457304583045930460304613046230463304643046530466304673046830469304703047130472304733047430475304763047730478304793048030481304823048330484304853048630487304883048930490304913049230493304943049530496304973049830499305003050130502305033050430505305063050730508305093051030511305123051330514305153051630517305183051930520305213052230523305243052530526305273052830529305303053130532305333053430535305363053730538305393054030541305423054330544305453054630547305483054930550305513055230553305543055530556305573055830559305603056130562305633056430565305663056730568305693057030571305723057330574305753057630577305783057930580305813058230583305843058530586305873058830589305903059130592305933059430595305963059730598305993060030601306023060330604306053060630607306083060930610306113061230613306143061530616306173061830619306203062130622306233062430625306263062730628306293063030631306323063330634306353063630637306383063930640306413064230643306443064530646306473064830649306503065130652306533065430655306563065730658306593066030661306623066330664306653066630667306683066930670306713067230673306743067530676306773067830679306803068130682306833068430685306863068730688306893069030691306923069330694306953069630697306983069930700307013070230703307043070530706307073070830709307103071130712307133071430715307163071730718307193072030721307223072330724307253072630727307283072930730307313073230733307343073530736307373073830739307403074130742307433074430745307463074730748307493075030751307523075330754307553075630757307583075930760307613076230763307643076530766307673076830769307703077130772307733077430775307763077730778307793078030781307823078330784307853078630787307883078930790307913079230793307943079530796307973079830799308003080130802308033080430805308063080730808308093081030811308123081330814308153081630817308183081930820308213082230823308243082530826308273082830829308303083130832308333083430835308363083730838308393084030841308423084330844308453084630847308483084930850308513085230853308543085530856308573085830859308603086130862308633086430865308663086730868308693087030871308723087330874308753087630877308783087930880308813088230883308843088530886308873088830889308903089130892308933089430895308963089730898308993090030901309023090330904309053090630907309083090930910309113091230913309143091530916309173091830919309203092130922309233092430925309263092730928309293093030931309323093330934309353093630937309383093930940309413094230943309443094530946309473094830949309503095130952309533095430955309563095730958309593096030961309623096330964309653096630967309683096930970309713097230973309743097530976309773097830979309803098130982309833098430985309863098730988309893099030991309923099330994309953099630997309983099931000310013100231003310043100531006310073100831009310103101131012310133101431015310163101731018310193102031021310223102331024310253102631027310283102931030310313103231033310343103531036310373103831039310403104131042310433104431045310463104731048310493105031051310523105331054310553105631057310583105931060310613106231063310643106531066310673106831069310703107131072310733107431075310763107731078310793108031081310823108331084310853108631087310883108931090310913109231093310943109531096310973109831099311003110131102311033110431105311063110731108311093111031111311123111331114311153111631117311183111931120311213112231123311243112531126311273112831129311303113131132311333113431135311363113731138311393114031141311423114331144311453114631147311483114931150311513115231153311543115531156311573115831159311603116131162311633116431165311663116731168311693117031171311723117331174311753117631177311783117931180311813118231183311843118531186311873118831189311903119131192311933119431195311963119731198311993120031201312023120331204312053120631207312083120931210312113121231213312143121531216312173121831219312203122131222312233122431225312263122731228312293123031231312323123331234312353123631237312383123931240 |
- <?xml version="1.0" encoding="iso-8859-1" standalone="no"?>
- <!-- Generated by the JDiff Javadoc doclet -->
- <!-- (http://www.jdiff.org) -->
- <!-- on Tue Aug 24 11:40:41 PDT 2010 -->
- <api
- xmlns:xsi='http://www.w3.org/2001/XMLSchema-instance'
- xsi:noNamespaceSchemaLocation='api.xsd'
- name="hadoop-mapred 0.21.0"
- jdversion="1.0.9">
- <!-- Command line arguments = -doclet org.apache.hadoop.classification.tools.ExcludePrivateAnnotationsJDiffDoclet -docletpath /Users/tom/workspace/hadoop-mapreduce-0.21-committer/build/ivy/lib/Hadoop/common/hadoop-common-0.21.0.jar:/Users/tom/workspace/hadoop-mapreduce-0.21-committer/build/ivy/lib/Hadoop/jdiff/jdiff-1.0.9.jar:/Users/tom/workspace/hadoop-mapreduce-0.21-committer/build/ivy/lib/Hadoop/jdiff/xerces-1.4.4.jar -classpath /Users/tom/workspace/hadoop-mapreduce-0.21-committer/build/classes:/Users/tom/workspace/hadoop-mapreduce-0.21-committer/conf:/Users/tom/.ivy2/cache/org.apache.hadoop/hadoop-common/jars/hadoop-common-0.21.0-SNAPSHOT.jar:/Users/tom/.ivy2/cache/commons-cli/commons-cli/jars/commons-cli-1.2.jar:/Users/tom/.ivy2/cache/xmlenc/xmlenc/jars/xmlenc-0.52.jar:/Users/tom/.ivy2/cache/commons-httpclient/commons-httpclient/jars/commons-httpclient-3.1.jar:/Users/tom/.ivy2/cache/commons-codec/commons-codec/jars/commons-codec-1.4.jar:/Users/tom/.ivy2/cache/commons-net/commons-net/jars/commons-net-1.4.1.jar:/Users/tom/.ivy2/cache/oro/oro/jars/oro-2.0.8.jar:/Users/tom/.ivy2/cache/org.mortbay.jetty/jetty/jars/jetty-6.1.14.jar:/Users/tom/.ivy2/cache/org.mortbay.jetty/jetty-util/jars/jetty-util-6.1.14.jar:/Users/tom/.ivy2/cache/org.mortbay.jetty/servlet-api-2.5/jars/servlet-api-2.5-6.1.14.jar:/Users/tom/.ivy2/cache/tomcat/jasper-runtime/jars/jasper-runtime-5.5.12.jar:/Users/tom/.ivy2/cache/tomcat/jasper-compiler/jars/jasper-compiler-5.5.12.jar:/Users/tom/.ivy2/cache/org.mortbay.jetty/jsp-api-2.1/jars/jsp-api-2.1-6.1.14.jar:/Users/tom/.ivy2/cache/org.mortbay.jetty/jsp-2.1/jars/jsp-2.1-6.1.14.jar:/Users/tom/.ivy2/cache/org.eclipse.jdt/core/jars/core-3.1.1.jar:/Users/tom/.ivy2/cache/ant/ant/jars/ant-1.6.5.jar:/Users/tom/.ivy2/cache/commons-el/commons-el/jars/commons-el-1.0.jar:/Users/tom/.ivy2/cache/net.java.dev.jets3t/jets3t/jars/jets3t-0.7.1.jar:/Users/tom/.ivy2/cache/commons-logging/commons-logging/jars/commons-logging-1.1.1.jar:/Users/tom/.ivy2/cache/net.sf.kosmosfs/kfs/jars/kfs-0.3.jar:/Users/tom/.ivy2/cache/junit/junit/jars/junit-4.8.1.jar:/Users/tom/.ivy2/cache/hsqldb/hsqldb/jars/hsqldb-1.8.0.10.jar:/Users/tom/.ivy2/cache/org.apache.hadoop/avro/jars/avro-1.3.2.jar:/Users/tom/.ivy2/cache/org.codehaus.jackson/jackson-mapper-asl/jars/jackson-mapper-asl-1.4.2.jar:/Users/tom/.ivy2/cache/org.codehaus.jackson/jackson-core-asl/jars/jackson-core-asl-1.4.2.jar:/Users/tom/.ivy2/cache/org.slf4j/slf4j-api/jars/slf4j-api-1.5.11.jar:/Users/tom/.ivy2/cache/com.thoughtworks.paranamer/paranamer/jars/paranamer-2.2.jar:/Users/tom/.ivy2/cache/com.thoughtworks.paranamer/paranamer-ant/jars/paranamer-ant-2.2.jar:/Users/tom/.ivy2/cache/com.thoughtworks.paranamer/paranamer-generator/jars/paranamer-generator-2.2.jar:/Users/tom/.ivy2/cache/com.thoughtworks.qdox/qdox/jars/qdox-1.10.1.jar:/Users/tom/.ivy2/cache/asm/asm/jars/asm-3.2.jar:/Users/tom/.ivy2/cache/commons-lang/commons-lang/jars/commons-lang-2.5.jar:/Users/tom/.ivy2/cache/org.apache.hadoop/hadoop-common-test/jars/hadoop-common-test-0.21.0-SNAPSHOT.jar:/Users/tom/.ivy2/cache/org.apache.ftpserver/ftplet-api/bundles/ftplet-api-1.0.0.jar:/Users/tom/.ivy2/cache/org.apache.mina/mina-core/bundles/mina-core-2.0.0-M5.jar:/Users/tom/.ivy2/cache/org.apache.ftpserver/ftpserver-core/bundles/ftpserver-core-1.0.0.jar:/Users/tom/.ivy2/cache/org.apache.ftpserver/ftpserver-deprecated/jars/ftpserver-deprecated-1.0.0-M2.jar:/Users/tom/.ivy2/cache/org.apache.hadoop/hadoop-hdfs/jars/hadoop-hdfs-0.21.0-SNAPSHOT.jar:/Users/tom/.ivy2/cache/log4j/log4j/jars/log4j-1.2.15.jar:/Users/tom/.ivy2/cache/org.slf4j/slf4j-log4j12/jars/slf4j-log4j12-1.5.11.jar:/Users/tom/.ivy2/cache/org.aspectj/aspectjrt/jars/aspectjrt-1.6.5.jar:/Users/tom/.ivy2/cache/org.aspectj/aspectjtools/jars/aspectjtools-1.6.5.jar:/Users/tom/.ivy2/cache/jdiff/jdiff/jars/jdiff-1.0.9.jar:/Users/tom/.ivy2/cache/xerces/xerces/jars/xerces-1.4.4.jar:/usr/share/ant/lib/ant-launcher.jar:/Users/tom/.ant/lib/ivy.jar:/usr/share/ant/lib/ant-antlr.jar:/usr/share/ant/lib/ant-jai.jar:/usr/share/ant/lib/ant-jmf.jar:/usr/share/ant/lib/ant-junit.jar:/usr/share/ant/lib/ant-nodeps.jar:/usr/share/ant/lib/ant-swing.jar:/usr/share/ant/lib/ant-testutil.jar:/usr/share/ant/lib/ant-trax.jar:/usr/share/ant/lib/ant.jar:/usr/share/ant/lib/ivy-2.1.0.jar:/usr/share/ant/lib/xercesImpl.jar:/usr/share/ant/lib/xml-apis.jar -sourcepath /Users/tom/workspace/hadoop-mapreduce-0.21-committer/src/java:/Users/tom/workspace/hadoop-mapreduce-0.21-committer/src/tools -apidir /Users/tom/workspace/hadoop-mapreduce-0.21-committer/lib/jdiff -apiname hadoop-mapred 0.21.0 -->
- <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="not deprecated">
- <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="not deprecated">
- <doc>
- <![CDATA[Get the current state of the <code>JobTracker</code>,
- as {@link JobTracker.State}
-
- @return the current state of the <code>JobTracker</code>.]]>
- </doc>
- </method>
- <method name="getUsedMemory" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the total heap memory used by the <code>JobTracker</code>
-
- @return the size of heap memory used by the <code>JobTracker</code>]]>
- </doc>
- </method>
- <method name="getMaxMemory" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the maximum configured heap memory that can be used by the <code>JobTracker</code>
-
- @return the configured size of max heap memory that can be used by the <code>JobTracker</code>]]>
- </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]]>
- </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="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>
- <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.]]>
- </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="not deprecated">
- <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.
- 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="not deprecated">
- <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)}.
- 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="not deprecated">
- <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]]>
- </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="not deprecated">
- <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]]>
- </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="not deprecated">
- <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]]>
- </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="not deprecated">
- <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="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]]>
- </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="not deprecated">
- <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>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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').]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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]]>
- </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="not deprecated">
- <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]]>
- </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="not deprecated">
- <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]]>
- </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="not deprecated">
- <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]]>
- </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="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.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]]>
- </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="not deprecated">
- <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]]>
- </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="not deprecated">
- <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]]>
- </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="not deprecated">
- <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]]>
- </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="not deprecated">
- <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]]>
- </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="not deprecated">
- <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.]]>
- </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="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="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]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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>
- </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="not deprecated">
- <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.]]>
- </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="false"
- 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="false"
- 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="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="setTotalLogFileSize"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="logSize" type="long"/>
- </method>
- <method name="setIsCleanup"
- abstract="false" native="false" synchronized="false"
- 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="false"
- 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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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..]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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>
- </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="not deprecated">
- <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>
- </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="not deprecated">
- <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}.]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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]]>
- </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="not deprecated">
- <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.]]>
- </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="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.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.]]>
- </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="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.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.]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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.]]>
- </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="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.mapred.join.TupleWritable"/>
- <doc>
- <![CDATA[Emit everything from the collector.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Full outer join.]]>
- </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="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.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.]]>
- </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="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.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="not deprecated">
- <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}.]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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]]>
- </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="not deprecated">
- <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>]]>
- </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="not deprecated">
- <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>]]>
- </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="not deprecated">
- <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]]>
- </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="not deprecated">
- <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]]>
- </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="not deprecated">
- <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>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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()}.]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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}]]>
- </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="not deprecated">
- <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).]]>
- </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="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.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.]]>
- </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="not deprecated">
- <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.]]>
- </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="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="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]]>
- </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="not deprecated">
- <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,]]>
- </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="not deprecated">
- <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>]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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>]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregator"/>
- <doc>
- <![CDATA[This interface defines the minimal protocol for value aggregators.]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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.]]>
- </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="not deprecated">
- <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>
- </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="not deprecated">
- <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>
- </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="not deprecated">
- <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>
- </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="not deprecated">
- <implements name="org.apache.hadoop.mapreduce.lib.db.DBWritable"/>
- </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="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="not deprecated">
- <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]]>
- </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.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.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="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">
- <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.
-
- @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.
-
- @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="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="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"/>
- </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">
- </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>
- <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="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>
- <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="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>
- <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>
- <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="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="addSecretKey"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="alias" type="org.apache.hadoop.io.Text"/>
- <param name="key" type="byte[]"/>
- <doc>
- <![CDATA[auxiliary methods to store user' s secret keys
- @param alias
- @param key]]>
- </doc>
- </method>
- <method name="addDelegationToken"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="namenode" type="java.lang.String"/>
- <param name="t" type="org.apache.hadoop.security.token.Token"/>
- <doc>
- <![CDATA[auxiliary method to add a delegation token]]>
- </doc>
- </method>
- <method name="getAllTokens" return="java.util.Collection"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[auxiliary method
- @return all the available tokens]]>
- </doc>
- </method>
- <method name="obtainTokensForNamenodes"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <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 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="namenode" type="java.lang.String"/>
- <doc>
- <![CDATA[@param namenode
- @return delegation token]]>
- </doc>
- </method>
- <method name="getTokenStorage" return="org.apache.hadoop.security.TokenStorage"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return TokenStore object]]>
- </doc>
- </method>
- <method name="setTokenStorage"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="ts" type="org.apache.hadoop.security.TokenStorage"/>
- <doc>
- <![CDATA[sets TokenStorage
- @param ts]]>
- </doc>
- </method>
- <method name="loadTaskTokenStorage" return="org.apache.hadoop.security.TokenStorage"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="fileName" type="java.lang.String"/>
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[load token storage and stores it
- @param conf
- @return Loaded TokenStorage object
- @throws IOException]]>
- </doc>
- </method>
- <method name="loadTokens" return="org.apache.hadoop.security.TokenStorage"
- 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="ts" type="org.apache.hadoop.security.TokenStorage"/>
- <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="ts" type="org.apache.hadoop.security.TokenStorage"/>
- <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="not deprecated">
- <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]]>
- </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 {@line 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 {@line 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 skewBufferSize
- [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 find 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 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
- {@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 TaskStatus.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>
|
