1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374757677787980818283848586878889909192939495969798991001011021031041051061071081091101111121131141151161171181191201211221231241251261271281291301311321331341351361371381391401411421431441451461471481491501511521531541551561571581591601611621631641651661671681691701711721731741751761771781791801811821831841851861871881891901911921931941951961971981992002012022032042052062072082092102112122132142152162172182192202212222232242252262272282292302312322332342352362372382392402412422432442452462472482492502512522532542552562572582592602612622632642652662672682692702712722732742752762772782792802812822832842852862872882892902912922932942952962972982993003013023033043053063073083093103113123133143153163173183193203213223233243253263273283293303313323333343353363373383393403413423433443453463473483493503513523533543553563573583593603613623633643653663673683693703713723733743753763773783793803813823833843853863873883893903913923933943953963973983994004014024034044054064074084094104114124134144154164174184194204214224234244254264274284294304314324334344354364374384394404414424434444454464474484494504514524534544554564574584594604614624634644654664674684694704714724734744754764774784794804814824834844854864874884894904914924934944954964974984995005015025035045055065075085095105115125135145155165175185195205215225235245255265275285295305315325335345355365375385395405415425435445455465475485495505515525535545555565575585595605615625635645655665675685695705715725735745755765775785795805815825835845855865875885895905915925935945955965975985996006016026036046056066076086096106116126136146156166176186196206216226236246256266276286296306316326336346356366376386396406416426436446456466476486496506516526536546556566576586596606616626636646656666676686696706716726736746756766776786796806816826836846856866876886896906916926936946956966976986997007017027037047057067077087097107117127137147157167177187197207217227237247257267277287297307317327337347357367377387397407417427437447457467477487497507517527537547557567577587597607617627637647657667677687697707717727737747757767777787797807817827837847857867877887897907917927937947957967977987998008018028038048058068078088098108118128138148158168178188198208218228238248258268278288298308318328338348358368378388398408418428438448458468478488498508518528538548558568578588598608618628638648658668678688698708718728738748758768778788798808818828838848858868878888898908918928938948958968978988999009019029039049059069079089099109119129139149159169179189199209219229239249259269279289299309319329339349359369379389399409419429439449459469479489499509519529539549559569579589599609619629639649659669679689699709719729739749759769779789799809819829839849859869879889899909919929939949959969979989991000100110021003100410051006100710081009101010111012101310141015101610171018101910201021102210231024102510261027102810291030103110321033103410351036103710381039104010411042104310441045104610471048104910501051105210531054105510561057105810591060106110621063106410651066106710681069107010711072107310741075107610771078107910801081108210831084108510861087108810891090109110921093109410951096109710981099110011011102110311041105110611071108110911101111111211131114111511161117111811191120112111221123112411251126112711281129113011311132113311341135113611371138113911401141114211431144114511461147114811491150115111521153115411551156115711581159116011611162116311641165116611671168116911701171117211731174117511761177117811791180118111821183118411851186118711881189119011911192119311941195119611971198119912001201120212031204120512061207120812091210121112121213121412151216121712181219122012211222122312241225122612271228122912301231123212331234123512361237123812391240124112421243124412451246124712481249125012511252125312541255125612571258125912601261126212631264126512661267126812691270127112721273127412751276127712781279128012811282128312841285128612871288128912901291129212931294129512961297129812991300130113021303130413051306130713081309131013111312131313141315131613171318131913201321132213231324132513261327132813291330133113321333133413351336133713381339134013411342134313441345134613471348134913501351135213531354135513561357135813591360136113621363136413651366136713681369137013711372137313741375137613771378137913801381138213831384138513861387138813891390139113921393139413951396139713981399140014011402140314041405140614071408140914101411141214131414141514161417141814191420142114221423142414251426142714281429143014311432143314341435143614371438143914401441144214431444144514461447144814491450145114521453145414551456145714581459146014611462146314641465146614671468146914701471147214731474147514761477147814791480148114821483148414851486148714881489149014911492149314941495149614971498149915001501150215031504150515061507150815091510151115121513151415151516151715181519152015211522152315241525152615271528152915301531153215331534153515361537153815391540154115421543154415451546154715481549155015511552155315541555155615571558155915601561156215631564156515661567156815691570157115721573157415751576157715781579158015811582158315841585158615871588158915901591159215931594159515961597159815991600160116021603160416051606160716081609161016111612161316141615161616171618161916201621162216231624162516261627162816291630163116321633163416351636163716381639164016411642164316441645164616471648164916501651165216531654165516561657165816591660166116621663166416651666166716681669167016711672167316741675167616771678167916801681168216831684168516861687168816891690169116921693169416951696169716981699170017011702170317041705170617071708170917101711171217131714171517161717171817191720172117221723172417251726172717281729173017311732173317341735173617371738173917401741174217431744174517461747174817491750175117521753175417551756175717581759176017611762176317641765176617671768176917701771177217731774177517761777177817791780178117821783178417851786178717881789179017911792179317941795179617971798179918001801180218031804180518061807180818091810181118121813181418151816181718181819182018211822182318241825182618271828182918301831183218331834183518361837183818391840184118421843184418451846184718481849185018511852185318541855185618571858185918601861186218631864186518661867186818691870187118721873187418751876187718781879188018811882188318841885188618871888188918901891189218931894189518961897189818991900190119021903190419051906190719081909191019111912191319141915191619171918191919201921192219231924192519261927192819291930193119321933193419351936193719381939194019411942194319441945194619471948194919501951195219531954195519561957195819591960196119621963196419651966196719681969197019711972197319741975197619771978197919801981198219831984198519861987198819891990199119921993199419951996199719981999200020012002200320042005200620072008200920102011201220132014201520162017201820192020202120222023202420252026202720282029203020312032203320342035203620372038203920402041204220432044204520462047204820492050205120522053205420552056205720582059206020612062206320642065206620672068206920702071207220732074207520762077207820792080208120822083208420852086208720882089209020912092209320942095209620972098209921002101210221032104210521062107210821092110211121122113211421152116211721182119212021212122212321242125212621272128212921302131213221332134213521362137213821392140214121422143214421452146214721482149215021512152215321542155215621572158215921602161216221632164216521662167216821692170217121722173217421752176217721782179218021812182218321842185218621872188218921902191219221932194219521962197219821992200220122022203220422052206220722082209221022112212221322142215221622172218221922202221222222232224222522262227222822292230223122322233223422352236223722382239224022412242224322442245224622472248224922502251225222532254225522562257225822592260226122622263226422652266226722682269227022712272227322742275227622772278227922802281228222832284228522862287228822892290229122922293229422952296229722982299230023012302230323042305230623072308230923102311231223132314231523162317231823192320232123222323232423252326232723282329233023312332233323342335233623372338233923402341234223432344234523462347234823492350235123522353235423552356235723582359236023612362236323642365236623672368236923702371237223732374237523762377237823792380238123822383238423852386238723882389239023912392239323942395239623972398239924002401240224032404240524062407240824092410241124122413241424152416241724182419242024212422242324242425242624272428242924302431243224332434243524362437243824392440244124422443244424452446244724482449245024512452245324542455245624572458245924602461246224632464246524662467246824692470247124722473247424752476247724782479248024812482248324842485248624872488248924902491249224932494249524962497249824992500250125022503250425052506250725082509251025112512251325142515251625172518251925202521252225232524252525262527252825292530253125322533253425352536253725382539254025412542254325442545254625472548254925502551255225532554255525562557255825592560256125622563256425652566256725682569257025712572257325742575257625772578257925802581258225832584258525862587258825892590259125922593259425952596259725982599260026012602260326042605260626072608260926102611261226132614261526162617261826192620262126222623262426252626262726282629263026312632263326342635263626372638263926402641264226432644264526462647264826492650265126522653265426552656265726582659266026612662266326642665266626672668266926702671267226732674267526762677267826792680268126822683268426852686268726882689269026912692269326942695269626972698269927002701270227032704270527062707270827092710271127122713271427152716271727182719272027212722272327242725272627272728272927302731273227332734273527362737273827392740274127422743274427452746274727482749275027512752275327542755275627572758275927602761276227632764276527662767276827692770277127722773277427752776277727782779278027812782278327842785278627872788278927902791279227932794279527962797279827992800280128022803280428052806280728082809281028112812281328142815281628172818281928202821282228232824282528262827282828292830283128322833283428352836283728382839284028412842284328442845284628472848284928502851285228532854285528562857285828592860286128622863286428652866286728682869287028712872287328742875287628772878287928802881288228832884288528862887288828892890289128922893289428952896289728982899290029012902290329042905290629072908290929102911291229132914291529162917291829192920292129222923292429252926292729282929293029312932293329342935293629372938293929402941294229432944294529462947294829492950295129522953295429552956295729582959296029612962296329642965296629672968296929702971297229732974297529762977297829792980298129822983298429852986298729882989299029912992299329942995299629972998299930003001300230033004300530063007300830093010301130123013301430153016301730183019302030213022302330243025302630273028302930303031303230333034303530363037303830393040304130423043304430453046304730483049305030513052305330543055305630573058305930603061306230633064306530663067306830693070307130723073307430753076307730783079308030813082308330843085308630873088308930903091309230933094309530963097309830993100310131023103310431053106310731083109311031113112311331143115311631173118311931203121312231233124312531263127312831293130313131323133313431353136313731383139314031413142314331443145314631473148314931503151315231533154315531563157315831593160316131623163316431653166316731683169317031713172317331743175317631773178317931803181318231833184318531863187318831893190319131923193319431953196319731983199320032013202320332043205320632073208320932103211321232133214321532163217321832193220322132223223322432253226322732283229323032313232323332343235323632373238323932403241324232433244324532463247324832493250325132523253325432553256325732583259326032613262326332643265326632673268326932703271327232733274327532763277327832793280328132823283328432853286328732883289329032913292329332943295329632973298329933003301330233033304330533063307330833093310331133123313331433153316331733183319332033213322332333243325332633273328332933303331333233333334333533363337333833393340334133423343334433453346334733483349335033513352335333543355335633573358335933603361336233633364336533663367336833693370337133723373337433753376337733783379338033813382338333843385338633873388338933903391339233933394339533963397339833993400340134023403340434053406340734083409341034113412341334143415341634173418341934203421342234233424342534263427342834293430343134323433343434353436343734383439344034413442344334443445344634473448344934503451345234533454345534563457345834593460346134623463346434653466346734683469347034713472347334743475347634773478347934803481348234833484348534863487348834893490349134923493349434953496349734983499350035013502350335043505350635073508350935103511351235133514351535163517351835193520352135223523352435253526352735283529353035313532353335343535353635373538353935403541354235433544354535463547354835493550355135523553355435553556355735583559356035613562356335643565356635673568356935703571357235733574357535763577357835793580358135823583358435853586358735883589359035913592359335943595359635973598359936003601360236033604360536063607360836093610361136123613361436153616361736183619362036213622362336243625362636273628362936303631363236333634363536363637363836393640364136423643364436453646364736483649365036513652365336543655365636573658365936603661366236633664366536663667366836693670367136723673367436753676367736783679368036813682368336843685368636873688368936903691369236933694369536963697369836993700370137023703370437053706370737083709371037113712371337143715371637173718371937203721372237233724372537263727372837293730373137323733373437353736373737383739374037413742374337443745374637473748374937503751375237533754375537563757375837593760376137623763376437653766376737683769377037713772377337743775377637773778377937803781378237833784378537863787378837893790379137923793379437953796379737983799380038013802380338043805380638073808380938103811381238133814381538163817381838193820382138223823382438253826382738283829383038313832383338343835383638373838383938403841384238433844384538463847384838493850385138523853385438553856385738583859386038613862386338643865386638673868386938703871387238733874387538763877387838793880388138823883388438853886388738883889389038913892389338943895389638973898389939003901390239033904390539063907390839093910391139123913391439153916391739183919392039213922392339243925392639273928392939303931393239333934393539363937393839393940394139423943394439453946394739483949395039513952395339543955395639573958395939603961396239633964396539663967396839693970397139723973397439753976397739783979398039813982398339843985398639873988398939903991399239933994399539963997399839994000400140024003400440054006400740084009401040114012401340144015401640174018401940204021402240234024402540264027402840294030403140324033403440354036403740384039404040414042404340444045404640474048404940504051405240534054405540564057405840594060406140624063406440654066406740684069407040714072407340744075407640774078407940804081408240834084408540864087408840894090409140924093409440954096409740984099410041014102410341044105410641074108410941104111411241134114411541164117411841194120412141224123412441254126412741284129413041314132413341344135413641374138413941404141414241434144414541464147414841494150415141524153415441554156415741584159416041614162416341644165416641674168416941704171417241734174417541764177417841794180418141824183418441854186418741884189419041914192419341944195419641974198419942004201420242034204420542064207420842094210421142124213421442154216421742184219422042214222422342244225422642274228422942304231423242334234423542364237423842394240424142424243424442454246424742484249425042514252425342544255425642574258425942604261426242634264426542664267426842694270427142724273427442754276427742784279428042814282428342844285428642874288428942904291429242934294429542964297429842994300430143024303430443054306430743084309431043114312431343144315431643174318431943204321432243234324432543264327432843294330433143324333433443354336433743384339434043414342434343444345434643474348434943504351435243534354435543564357435843594360436143624363436443654366436743684369437043714372437343744375437643774378437943804381438243834384438543864387438843894390439143924393439443954396439743984399440044014402440344044405440644074408440944104411441244134414441544164417441844194420442144224423442444254426442744284429443044314432443344344435443644374438443944404441444244434444444544464447444844494450445144524453445444554456445744584459446044614462446344644465446644674468446944704471447244734474447544764477447844794480448144824483448444854486448744884489449044914492449344944495449644974498449945004501450245034504450545064507450845094510451145124513451445154516451745184519452045214522452345244525452645274528452945304531453245334534453545364537453845394540454145424543454445454546454745484549455045514552455345544555455645574558455945604561456245634564456545664567456845694570457145724573457445754576457745784579458045814582458345844585458645874588458945904591459245934594459545964597459845994600460146024603460446054606460746084609461046114612461346144615461646174618461946204621462246234624462546264627462846294630463146324633463446354636463746384639464046414642464346444645464646474648464946504651465246534654465546564657465846594660466146624663466446654666466746684669467046714672467346744675467646774678467946804681468246834684468546864687468846894690469146924693469446954696469746984699470047014702470347044705470647074708470947104711471247134714471547164717471847194720472147224723472447254726472747284729473047314732473347344735473647374738473947404741474247434744474547464747474847494750475147524753475447554756475747584759476047614762476347644765476647674768476947704771477247734774477547764777477847794780478147824783478447854786478747884789479047914792479347944795479647974798479948004801480248034804480548064807480848094810481148124813481448154816481748184819482048214822482348244825482648274828482948304831483248334834483548364837483848394840484148424843484448454846484748484849485048514852485348544855485648574858485948604861486248634864486548664867486848694870487148724873487448754876487748784879488048814882488348844885488648874888488948904891489248934894489548964897489848994900490149024903490449054906490749084909491049114912491349144915491649174918491949204921492249234924492549264927492849294930493149324933493449354936493749384939494049414942494349444945494649474948494949504951495249534954495549564957495849594960496149624963496449654966496749684969497049714972497349744975497649774978497949804981498249834984498549864987498849894990499149924993499449954996499749984999500050015002500350045005500650075008500950105011501250135014501550165017501850195020502150225023502450255026502750285029503050315032503350345035503650375038503950405041504250435044504550465047504850495050505150525053505450555056505750585059506050615062506350645065506650675068506950705071507250735074507550765077507850795080508150825083508450855086508750885089509050915092509350945095509650975098509951005101510251035104510551065107510851095110511151125113511451155116511751185119512051215122512351245125512651275128512951305131513251335134513551365137513851395140514151425143514451455146514751485149515051515152515351545155515651575158515951605161516251635164516551665167516851695170517151725173517451755176517751785179518051815182518351845185518651875188518951905191519251935194519551965197519851995200520152025203520452055206520752085209521052115212521352145215521652175218521952205221522252235224522552265227522852295230523152325233523452355236523752385239524052415242524352445245524652475248524952505251525252535254525552565257525852595260526152625263526452655266526752685269527052715272527352745275527652775278527952805281528252835284528552865287528852895290529152925293529452955296529752985299530053015302530353045305530653075308530953105311531253135314531553165317531853195320532153225323532453255326532753285329533053315332533353345335533653375338533953405341534253435344534553465347534853495350535153525353535453555356535753585359536053615362536353645365536653675368536953705371537253735374537553765377537853795380538153825383538453855386538753885389539053915392539353945395539653975398539954005401540254035404540554065407540854095410541154125413541454155416541754185419542054215422542354245425542654275428542954305431543254335434543554365437543854395440544154425443544454455446544754485449545054515452545354545455545654575458545954605461546254635464546554665467546854695470547154725473547454755476547754785479548054815482548354845485548654875488548954905491549254935494549554965497549854995500550155025503550455055506550755085509551055115512551355145515551655175518551955205521552255235524552555265527552855295530553155325533553455355536553755385539554055415542554355445545554655475548554955505551555255535554555555565557555855595560556155625563556455655566556755685569557055715572557355745575557655775578557955805581558255835584558555865587558855895590559155925593559455955596559755985599560056015602560356045605560656075608560956105611561256135614561556165617561856195620562156225623562456255626562756285629563056315632563356345635563656375638563956405641564256435644564556465647564856495650565156525653565456555656565756585659566056615662566356645665566656675668566956705671567256735674567556765677567856795680568156825683568456855686568756885689569056915692569356945695569656975698569957005701570257035704570557065707570857095710571157125713571457155716571757185719572057215722572357245725572657275728572957305731573257335734573557365737573857395740574157425743574457455746574757485749575057515752575357545755575657575758575957605761576257635764576557665767576857695770577157725773577457755776577757785779578057815782578357845785578657875788578957905791579257935794579557965797579857995800580158025803580458055806580758085809581058115812581358145815581658175818581958205821582258235824582558265827582858295830583158325833583458355836583758385839584058415842584358445845584658475848584958505851585258535854585558565857585858595860586158625863586458655866586758685869587058715872587358745875587658775878587958805881588258835884588558865887588858895890589158925893589458955896589758985899590059015902590359045905590659075908590959105911591259135914591559165917591859195920592159225923592459255926592759285929593059315932593359345935593659375938593959405941594259435944594559465947594859495950595159525953595459555956595759585959596059615962596359645965596659675968596959705971597259735974597559765977597859795980598159825983598459855986598759885989599059915992599359945995599659975998599960006001600260036004600560066007600860096010601160126013601460156016601760186019602060216022602360246025602660276028602960306031603260336034603560366037603860396040604160426043604460456046604760486049605060516052605360546055605660576058605960606061606260636064606560666067606860696070607160726073607460756076607760786079608060816082608360846085608660876088608960906091609260936094609560966097609860996100610161026103610461056106610761086109611061116112611361146115611661176118611961206121612261236124612561266127612861296130613161326133613461356136613761386139614061416142614361446145614661476148614961506151615261536154615561566157615861596160616161626163616461656166616761686169617061716172617361746175617661776178617961806181618261836184618561866187618861896190619161926193619461956196619761986199620062016202620362046205620662076208620962106211621262136214621562166217621862196220622162226223622462256226622762286229623062316232623362346235623662376238623962406241624262436244624562466247624862496250625162526253625462556256625762586259626062616262626362646265626662676268626962706271627262736274627562766277627862796280628162826283628462856286628762886289629062916292629362946295629662976298629963006301630263036304630563066307630863096310631163126313631463156316631763186319632063216322632363246325632663276328632963306331633263336334633563366337633863396340634163426343634463456346634763486349635063516352635363546355635663576358635963606361636263636364636563666367636863696370637163726373637463756376637763786379638063816382638363846385638663876388638963906391639263936394639563966397639863996400640164026403640464056406640764086409641064116412641364146415641664176418641964206421642264236424642564266427642864296430643164326433643464356436643764386439644064416442644364446445644664476448644964506451645264536454645564566457645864596460646164626463646464656466646764686469647064716472647364746475647664776478647964806481648264836484648564866487648864896490649164926493649464956496649764986499650065016502650365046505650665076508650965106511651265136514651565166517651865196520652165226523652465256526652765286529653065316532653365346535653665376538653965406541654265436544654565466547654865496550655165526553655465556556655765586559656065616562656365646565656665676568656965706571657265736574657565766577657865796580658165826583658465856586658765886589659065916592659365946595659665976598659966006601660266036604660566066607660866096610661166126613661466156616661766186619662066216622662366246625662666276628662966306631663266336634663566366637663866396640664166426643664466456646664766486649665066516652665366546655665666576658665966606661666266636664666566666667666866696670667166726673667466756676667766786679668066816682668366846685668666876688668966906691669266936694669566966697669866996700670167026703670467056706670767086709671067116712671367146715671667176718671967206721672267236724672567266727672867296730673167326733673467356736673767386739674067416742674367446745674667476748674967506751675267536754675567566757675867596760676167626763676467656766676767686769677067716772677367746775677667776778677967806781678267836784678567866787678867896790679167926793679467956796679767986799680068016802680368046805680668076808680968106811681268136814681568166817681868196820682168226823682468256826682768286829683068316832683368346835683668376838683968406841684268436844684568466847684868496850685168526853685468556856685768586859686068616862686368646865686668676868686968706871687268736874687568766877687868796880688168826883688468856886688768886889689068916892689368946895689668976898689969006901690269036904690569066907690869096910691169126913691469156916691769186919692069216922692369246925692669276928692969306931693269336934693569366937693869396940694169426943694469456946694769486949695069516952695369546955695669576958695969606961696269636964696569666967696869696970697169726973697469756976697769786979698069816982698369846985698669876988698969906991699269936994699569966997699869997000700170027003700470057006700770087009701070117012701370147015701670177018701970207021702270237024702570267027702870297030703170327033703470357036703770387039704070417042704370447045704670477048704970507051705270537054705570567057705870597060706170627063706470657066706770687069707070717072707370747075707670777078707970807081708270837084708570867087708870897090709170927093709470957096709770987099710071017102710371047105710671077108710971107111711271137114711571167117711871197120712171227123712471257126712771287129713071317132713371347135713671377138713971407141714271437144714571467147714871497150715171527153715471557156715771587159716071617162716371647165716671677168716971707171717271737174717571767177717871797180718171827183718471857186718771887189719071917192719371947195719671977198719972007201720272037204720572067207720872097210721172127213721472157216721772187219722072217222722372247225722672277228722972307231723272337234723572367237723872397240724172427243724472457246724772487249725072517252725372547255725672577258725972607261726272637264726572667267726872697270727172727273727472757276727772787279728072817282728372847285728672877288728972907291729272937294729572967297729872997300730173027303730473057306730773087309731073117312731373147315731673177318731973207321732273237324732573267327732873297330733173327333733473357336733773387339734073417342734373447345734673477348734973507351735273537354735573567357735873597360736173627363736473657366736773687369737073717372737373747375737673777378737973807381738273837384738573867387738873897390739173927393739473957396739773987399740074017402740374047405740674077408740974107411741274137414741574167417741874197420742174227423742474257426742774287429743074317432743374347435743674377438743974407441744274437444744574467447744874497450745174527453745474557456745774587459746074617462746374647465746674677468746974707471747274737474747574767477747874797480748174827483748474857486748774887489749074917492749374947495749674977498749975007501750275037504750575067507750875097510751175127513751475157516751775187519752075217522752375247525752675277528752975307531753275337534753575367537753875397540754175427543754475457546754775487549755075517552755375547555755675577558755975607561756275637564756575667567756875697570757175727573757475757576757775787579758075817582758375847585758675877588758975907591759275937594759575967597759875997600760176027603760476057606760776087609761076117612761376147615761676177618761976207621762276237624762576267627762876297630763176327633763476357636763776387639764076417642764376447645764676477648764976507651765276537654765576567657765876597660766176627663766476657666766776687669767076717672767376747675767676777678767976807681768276837684768576867687768876897690769176927693769476957696769776987699770077017702770377047705770677077708770977107711771277137714771577167717771877197720772177227723772477257726772777287729773077317732773377347735773677377738773977407741774277437744774577467747774877497750775177527753775477557756775777587759776077617762776377647765776677677768776977707771777277737774777577767777777877797780778177827783778477857786778777887789779077917792779377947795779677977798779978007801780278037804780578067807780878097810781178127813781478157816781778187819782078217822782378247825782678277828782978307831783278337834783578367837783878397840784178427843784478457846784778487849785078517852785378547855785678577858785978607861786278637864786578667867786878697870787178727873787478757876787778787879788078817882788378847885788678877888788978907891789278937894789578967897789878997900790179027903790479057906790779087909791079117912791379147915791679177918791979207921792279237924792579267927792879297930793179327933793479357936793779387939794079417942794379447945794679477948794979507951795279537954795579567957795879597960796179627963796479657966796779687969797079717972797379747975797679777978797979807981798279837984798579867987798879897990799179927993799479957996799779987999800080018002800380048005800680078008800980108011801280138014801580168017801880198020802180228023802480258026802780288029803080318032803380348035803680378038803980408041804280438044804580468047804880498050805180528053805480558056805780588059806080618062806380648065806680678068806980708071807280738074807580768077807880798080808180828083808480858086808780888089809080918092809380948095809680978098809981008101810281038104810581068107810881098110811181128113811481158116811781188119812081218122812381248125812681278128812981308131813281338134813581368137813881398140814181428143814481458146814781488149815081518152815381548155815681578158815981608161816281638164816581668167816881698170817181728173817481758176817781788179818081818182818381848185818681878188818981908191819281938194819581968197819881998200820182028203820482058206820782088209821082118212821382148215821682178218821982208221822282238224822582268227822882298230823182328233823482358236823782388239824082418242824382448245824682478248824982508251825282538254825582568257825882598260826182628263826482658266826782688269827082718272827382748275827682778278827982808281828282838284828582868287828882898290829182928293829482958296829782988299830083018302830383048305830683078308830983108311831283138314831583168317831883198320832183228323832483258326832783288329833083318332833383348335833683378338833983408341834283438344834583468347834883498350835183528353835483558356835783588359836083618362836383648365836683678368836983708371837283738374837583768377837883798380838183828383838483858386838783888389839083918392839383948395839683978398839984008401840284038404840584068407840884098410841184128413841484158416841784188419842084218422842384248425842684278428842984308431843284338434843584368437843884398440844184428443844484458446844784488449845084518452845384548455845684578458845984608461846284638464846584668467846884698470847184728473847484758476847784788479848084818482848384848485848684878488848984908491849284938494849584968497849884998500850185028503850485058506850785088509851085118512851385148515851685178518851985208521852285238524852585268527852885298530853185328533853485358536853785388539854085418542854385448545854685478548854985508551855285538554855585568557855885598560856185628563856485658566856785688569857085718572857385748575857685778578857985808581858285838584858585868587858885898590859185928593859485958596859785988599860086018602860386048605860686078608860986108611861286138614861586168617861886198620862186228623862486258626862786288629863086318632863386348635863686378638863986408641864286438644864586468647864886498650865186528653865486558656865786588659866086618662866386648665866686678668866986708671867286738674867586768677867886798680868186828683868486858686868786888689869086918692869386948695869686978698869987008701870287038704870587068707870887098710871187128713871487158716871787188719872087218722872387248725872687278728872987308731873287338734873587368737873887398740874187428743874487458746874787488749875087518752875387548755875687578758875987608761876287638764876587668767876887698770877187728773877487758776877787788779878087818782878387848785878687878788878987908791879287938794879587968797879887998800880188028803880488058806880788088809881088118812881388148815881688178818881988208821882288238824882588268827882888298830883188328833883488358836883788388839884088418842884388448845884688478848884988508851885288538854885588568857885888598860886188628863886488658866886788688869887088718872887388748875887688778878887988808881888288838884888588868887888888898890889188928893889488958896889788988899890089018902890389048905890689078908890989108911891289138914891589168917891889198920892189228923892489258926892789288929893089318932893389348935893689378938893989408941894289438944894589468947894889498950895189528953895489558956895789588959896089618962896389648965896689678968896989708971897289738974897589768977897889798980898189828983898489858986898789888989899089918992899389948995899689978998899990009001900290039004900590069007900890099010901190129013901490159016901790189019902090219022902390249025902690279028902990309031903290339034903590369037903890399040904190429043904490459046904790489049905090519052905390549055905690579058905990609061906290639064906590669067906890699070907190729073907490759076907790789079908090819082908390849085908690879088908990909091909290939094909590969097909890999100910191029103910491059106910791089109911091119112911391149115911691179118911991209121912291239124912591269127912891299130913191329133913491359136913791389139914091419142914391449145914691479148914991509151915291539154915591569157915891599160916191629163916491659166916791689169917091719172917391749175917691779178917991809181918291839184918591869187918891899190919191929193919491959196919791989199920092019202920392049205920692079208920992109211921292139214921592169217921892199220922192229223922492259226922792289229923092319232923392349235923692379238923992409241924292439244924592469247924892499250925192529253925492559256925792589259926092619262926392649265926692679268926992709271927292739274927592769277927892799280928192829283928492859286928792889289929092919292929392949295929692979298929993009301930293039304930593069307930893099310931193129313931493159316931793189319932093219322932393249325932693279328932993309331933293339334933593369337933893399340934193429343934493459346934793489349935093519352935393549355935693579358935993609361936293639364936593669367936893699370937193729373937493759376937793789379938093819382938393849385938693879388938993909391939293939394939593969397939893999400940194029403940494059406940794089409941094119412941394149415941694179418941994209421942294239424942594269427942894299430943194329433943494359436943794389439944094419442944394449445944694479448944994509451945294539454945594569457945894599460946194629463946494659466946794689469947094719472947394749475947694779478947994809481948294839484948594869487948894899490949194929493949494959496949794989499950095019502950395049505950695079508950995109511951295139514951595169517951895199520952195229523952495259526952795289529953095319532953395349535953695379538953995409541954295439544954595469547954895499550955195529553955495559556955795589559956095619562956395649565956695679568956995709571957295739574957595769577957895799580958195829583958495859586958795889589959095919592959395949595959695979598959996009601960296039604960596069607960896099610961196129613961496159616961796189619962096219622962396249625962696279628962996309631963296339634963596369637963896399640964196429643964496459646964796489649965096519652965396549655965696579658965996609661966296639664966596669667966896699670967196729673967496759676967796789679968096819682968396849685968696879688968996909691969296939694969596969697969896999700970197029703970497059706970797089709971097119712971397149715971697179718971997209721972297239724972597269727972897299730973197329733973497359736973797389739974097419742974397449745974697479748974997509751975297539754975597569757975897599760976197629763976497659766976797689769977097719772977397749775977697779778977997809781978297839784978597869787978897899790979197929793979497959796979797989799980098019802980398049805980698079808980998109811981298139814981598169817981898199820982198229823982498259826982798289829983098319832983398349835983698379838983998409841984298439844984598469847984898499850985198529853985498559856985798589859986098619862986398649865986698679868986998709871987298739874987598769877987898799880988198829883988498859886988798889889989098919892989398949895989698979898989999009901990299039904990599069907990899099910991199129913991499159916991799189919992099219922992399249925992699279928992999309931993299339934993599369937993899399940994199429943994499459946994799489949995099519952995399549955995699579958995999609961996299639964996599669967996899699970997199729973997499759976997799789979998099819982998399849985998699879988998999909991999299939994999599969997999899991000010001100021000310004100051000610007100081000910010100111001210013100141001510016100171001810019100201002110022100231002410025100261002710028100291003010031100321003310034100351003610037100381003910040100411004210043100441004510046100471004810049100501005110052100531005410055100561005710058100591006010061100621006310064100651006610067100681006910070100711007210073100741007510076100771007810079100801008110082100831008410085100861008710088100891009010091100921009310094100951009610097100981009910100101011010210103101041010510106101071010810109101101011110112101131011410115101161011710118101191012010121101221012310124101251012610127101281012910130101311013210133101341013510136101371013810139101401014110142101431014410145101461014710148101491015010151101521015310154101551015610157101581015910160101611016210163101641016510166101671016810169101701017110172101731017410175101761017710178101791018010181101821018310184101851018610187101881018910190101911019210193101941019510196101971019810199102001020110202102031020410205102061020710208102091021010211102121021310214102151021610217102181021910220102211022210223102241022510226102271022810229102301023110232102331023410235102361023710238102391024010241102421024310244102451024610247102481024910250102511025210253102541025510256102571025810259102601026110262102631026410265102661026710268102691027010271102721027310274102751027610277102781027910280102811028210283102841028510286102871028810289102901029110292102931029410295102961029710298102991030010301103021030310304103051030610307103081030910310103111031210313103141031510316103171031810319103201032110322103231032410325103261032710328103291033010331103321033310334103351033610337103381033910340103411034210343103441034510346103471034810349103501035110352103531035410355103561035710358103591036010361103621036310364103651036610367103681036910370103711037210373103741037510376103771037810379103801038110382103831038410385103861038710388103891039010391103921039310394103951039610397103981039910400104011040210403104041040510406104071040810409104101041110412104131041410415104161041710418104191042010421104221042310424104251042610427104281042910430104311043210433104341043510436104371043810439104401044110442104431044410445104461044710448104491045010451104521045310454104551045610457104581045910460104611046210463104641046510466104671046810469104701047110472104731047410475104761047710478104791048010481104821048310484104851048610487104881048910490104911049210493104941049510496104971049810499105001050110502105031050410505105061050710508105091051010511105121051310514105151051610517105181051910520105211052210523105241052510526105271052810529105301053110532105331053410535105361053710538105391054010541105421054310544105451054610547105481054910550105511055210553105541055510556105571055810559105601056110562105631056410565105661056710568105691057010571105721057310574105751057610577105781057910580105811058210583105841058510586105871058810589105901059110592105931059410595105961059710598105991060010601106021060310604106051060610607106081060910610106111061210613106141061510616106171061810619106201062110622106231062410625106261062710628106291063010631106321063310634106351063610637106381063910640106411064210643106441064510646106471064810649106501065110652106531065410655106561065710658106591066010661106621066310664106651066610667106681066910670106711067210673106741067510676106771067810679106801068110682106831068410685106861068710688106891069010691106921069310694106951069610697106981069910700107011070210703107041070510706107071070810709107101071110712107131071410715107161071710718107191072010721107221072310724107251072610727107281072910730107311073210733107341073510736107371073810739107401074110742107431074410745107461074710748107491075010751107521075310754107551075610757107581075910760107611076210763107641076510766107671076810769107701077110772107731077410775107761077710778107791078010781107821078310784107851078610787107881078910790107911079210793107941079510796107971079810799108001080110802108031080410805108061080710808108091081010811108121081310814108151081610817108181081910820108211082210823108241082510826108271082810829108301083110832108331083410835108361083710838108391084010841108421084310844108451084610847108481084910850108511085210853108541085510856108571085810859108601086110862108631086410865108661086710868108691087010871108721087310874108751087610877108781087910880108811088210883108841088510886108871088810889108901089110892108931089410895108961089710898108991090010901109021090310904109051090610907109081090910910109111091210913109141091510916109171091810919109201092110922109231092410925109261092710928109291093010931109321093310934109351093610937109381093910940109411094210943109441094510946109471094810949109501095110952109531095410955109561095710958109591096010961109621096310964109651096610967109681096910970109711097210973109741097510976109771097810979109801098110982109831098410985109861098710988109891099010991109921099310994109951099610997109981099911000110011100211003110041100511006110071100811009110101101111012110131101411015110161101711018110191102011021110221102311024110251102611027110281102911030110311103211033110341103511036110371103811039110401104111042110431104411045110461104711048110491105011051110521105311054110551105611057110581105911060110611106211063110641106511066110671106811069110701107111072110731107411075110761107711078110791108011081110821108311084110851108611087110881108911090110911109211093110941109511096110971109811099111001110111102111031110411105111061110711108111091111011111111121111311114111151111611117111181111911120111211112211123111241112511126111271112811129111301113111132111331113411135111361113711138111391114011141111421114311144111451114611147111481114911150111511115211153111541115511156111571115811159111601116111162111631116411165111661116711168111691117011171111721117311174111751117611177111781117911180111811118211183111841118511186111871118811189111901119111192111931119411195111961119711198111991120011201112021120311204112051120611207112081120911210112111121211213112141121511216112171121811219112201122111222112231122411225112261122711228112291123011231112321123311234112351123611237112381123911240112411124211243112441124511246112471124811249112501125111252112531125411255112561125711258112591126011261112621126311264112651126611267112681126911270112711127211273112741127511276112771127811279112801128111282112831128411285112861128711288112891129011291112921129311294112951129611297112981129911300113011130211303113041130511306113071130811309113101131111312113131131411315113161131711318113191132011321113221132311324113251132611327113281132911330113311133211333113341133511336113371133811339113401134111342113431134411345113461134711348113491135011351113521135311354113551135611357113581135911360113611136211363113641136511366113671136811369113701137111372113731137411375113761137711378113791138011381113821138311384113851138611387113881138911390113911139211393113941139511396113971139811399114001140111402114031140411405114061140711408114091141011411114121141311414114151141611417114181141911420114211142211423114241142511426114271142811429114301143111432114331143411435114361143711438114391144011441114421144311444114451144611447114481144911450114511145211453114541145511456114571145811459114601146111462114631146411465114661146711468114691147011471114721147311474114751147611477114781147911480114811148211483114841148511486114871148811489114901149111492114931149411495114961149711498114991150011501115021150311504115051150611507115081150911510115111151211513115141151511516115171151811519115201152111522115231152411525115261152711528115291153011531115321153311534115351153611537115381153911540115411154211543115441154511546115471154811549115501155111552115531155411555115561155711558115591156011561115621156311564115651156611567115681156911570115711157211573115741157511576115771157811579115801158111582115831158411585115861158711588115891159011591115921159311594115951159611597115981159911600116011160211603116041160511606116071160811609116101161111612116131161411615116161161711618116191162011621116221162311624116251162611627116281162911630116311163211633116341163511636116371163811639116401164111642116431164411645116461164711648116491165011651116521165311654116551165611657116581165911660116611166211663116641166511666116671166811669116701167111672116731167411675116761167711678116791168011681116821168311684116851168611687116881168911690116911169211693116941169511696116971169811699117001170111702117031170411705117061170711708117091171011711117121171311714117151171611717117181171911720117211172211723117241172511726117271172811729117301173111732117331173411735117361173711738117391174011741117421174311744117451174611747117481174911750117511175211753117541175511756117571175811759117601176111762117631176411765117661176711768117691177011771117721177311774117751177611777117781177911780117811178211783117841178511786117871178811789117901179111792117931179411795117961179711798117991180011801118021180311804118051180611807118081180911810118111181211813118141181511816118171181811819118201182111822118231182411825118261182711828118291183011831118321183311834118351183611837118381183911840118411184211843118441184511846118471184811849118501185111852118531185411855118561185711858118591186011861118621186311864118651186611867118681186911870118711187211873118741187511876118771187811879118801188111882118831188411885118861188711888118891189011891118921189311894118951189611897118981189911900119011190211903119041190511906119071190811909119101191111912119131191411915119161191711918119191192011921119221192311924119251192611927119281192911930119311193211933119341193511936119371193811939119401194111942119431194411945119461194711948119491195011951119521195311954119551195611957119581195911960119611196211963119641196511966119671196811969119701197111972119731197411975119761197711978119791198011981119821198311984119851198611987119881198911990119911199211993119941199511996119971199811999120001200112002120031200412005120061200712008120091201012011120121201312014120151201612017120181201912020120211202212023120241202512026120271202812029120301203112032120331203412035120361203712038120391204012041120421204312044120451204612047120481204912050120511205212053120541205512056120571205812059120601206112062120631206412065120661206712068120691207012071120721207312074120751207612077120781207912080120811208212083120841208512086120871208812089120901209112092120931209412095120961209712098120991210012101121021210312104121051210612107121081210912110121111211212113121141211512116121171211812119121201212112122121231212412125121261212712128121291213012131121321213312134121351213612137121381213912140121411214212143121441214512146121471214812149121501215112152121531215412155121561215712158121591216012161121621216312164121651216612167121681216912170121711217212173121741217512176121771217812179121801218112182121831218412185121861218712188121891219012191121921219312194121951219612197121981219912200122011220212203122041220512206122071220812209122101221112212122131221412215122161221712218122191222012221122221222312224122251222612227122281222912230122311223212233122341223512236122371223812239122401224112242122431224412245122461224712248122491225012251122521225312254122551225612257122581225912260122611226212263122641226512266122671226812269122701227112272122731227412275122761227712278122791228012281122821228312284122851228612287122881228912290122911229212293122941229512296122971229812299123001230112302123031230412305123061230712308123091231012311123121231312314123151231612317123181231912320123211232212323123241232512326123271232812329123301233112332123331233412335123361233712338123391234012341123421234312344123451234612347123481234912350123511235212353123541235512356123571235812359123601236112362123631236412365123661236712368123691237012371123721237312374123751237612377123781237912380123811238212383123841238512386123871238812389123901239112392123931239412395123961239712398123991240012401124021240312404124051240612407124081240912410124111241212413124141241512416124171241812419124201242112422124231242412425124261242712428124291243012431124321243312434124351243612437124381243912440124411244212443124441244512446124471244812449124501245112452124531245412455124561245712458124591246012461124621246312464124651246612467124681246912470124711247212473124741247512476124771247812479124801248112482124831248412485124861248712488124891249012491124921249312494124951249612497124981249912500125011250212503125041250512506125071250812509125101251112512125131251412515125161251712518125191252012521125221252312524125251252612527125281252912530125311253212533125341253512536125371253812539125401254112542125431254412545125461254712548125491255012551125521255312554125551255612557125581255912560125611256212563125641256512566125671256812569125701257112572125731257412575125761257712578125791258012581125821258312584125851258612587125881258912590125911259212593125941259512596125971259812599126001260112602126031260412605126061260712608126091261012611126121261312614126151261612617126181261912620126211262212623126241262512626126271262812629126301263112632126331263412635126361263712638126391264012641126421264312644126451264612647126481264912650126511265212653126541265512656126571265812659126601266112662126631266412665126661266712668126691267012671126721267312674126751267612677126781267912680126811268212683126841268512686126871268812689126901269112692126931269412695126961269712698126991270012701127021270312704127051270612707127081270912710127111271212713127141271512716127171271812719127201272112722127231272412725127261272712728127291273012731127321273312734127351273612737127381273912740127411274212743127441274512746127471274812749127501275112752127531275412755127561275712758127591276012761127621276312764127651276612767127681276912770127711277212773127741277512776127771277812779127801278112782127831278412785127861278712788127891279012791127921279312794127951279612797127981279912800128011280212803128041280512806128071280812809128101281112812128131281412815128161281712818128191282012821128221282312824128251282612827128281282912830128311283212833128341283512836128371283812839128401284112842128431284412845128461284712848128491285012851128521285312854128551285612857128581285912860128611286212863128641286512866128671286812869128701287112872128731287412875128761287712878128791288012881128821288312884128851288612887128881288912890128911289212893128941289512896128971289812899129001290112902129031290412905129061290712908129091291012911129121291312914129151291612917129181291912920129211292212923129241292512926129271292812929129301293112932129331293412935129361293712938129391294012941129421294312944129451294612947129481294912950129511295212953129541295512956129571295812959129601296112962129631296412965129661296712968129691297012971129721297312974129751297612977129781297912980129811298212983129841298512986129871298812989129901299112992129931299412995129961299712998129991300013001130021300313004130051300613007130081300913010130111301213013130141301513016130171301813019130201302113022130231302413025130261302713028130291303013031130321303313034130351303613037130381303913040130411304213043130441304513046130471304813049130501305113052130531305413055130561305713058130591306013061130621306313064130651306613067130681306913070130711307213073130741307513076130771307813079130801308113082130831308413085130861308713088130891309013091130921309313094130951309613097130981309913100131011310213103131041310513106131071310813109131101311113112131131311413115131161311713118131191312013121131221312313124131251312613127131281312913130131311313213133131341313513136131371313813139131401314113142131431314413145131461314713148131491315013151131521315313154131551315613157131581315913160131611316213163131641316513166131671316813169131701317113172131731317413175131761317713178131791318013181131821318313184131851318613187131881318913190131911319213193131941319513196131971319813199132001320113202132031320413205132061320713208132091321013211132121321313214132151321613217132181321913220132211322213223132241322513226132271322813229132301323113232132331323413235132361323713238132391324013241132421324313244132451324613247132481324913250132511325213253132541325513256132571325813259132601326113262132631326413265132661326713268132691327013271132721327313274132751327613277132781327913280132811328213283132841328513286132871328813289132901329113292132931329413295132961329713298132991330013301133021330313304133051330613307133081330913310133111331213313133141331513316133171331813319133201332113322133231332413325133261332713328133291333013331133321333313334133351333613337133381333913340133411334213343133441334513346133471334813349133501335113352133531335413355133561335713358133591336013361133621336313364133651336613367133681336913370133711337213373133741337513376133771337813379133801338113382133831338413385133861338713388133891339013391133921339313394133951339613397133981339913400134011340213403134041340513406134071340813409134101341113412134131341413415134161341713418134191342013421134221342313424134251342613427134281342913430134311343213433134341343513436134371343813439134401344113442134431344413445134461344713448134491345013451134521345313454134551345613457134581345913460134611346213463134641346513466134671346813469134701347113472134731347413475134761347713478134791348013481134821348313484134851348613487134881348913490134911349213493134941349513496134971349813499135001350113502135031350413505135061350713508135091351013511135121351313514135151351613517135181351913520135211352213523135241352513526135271352813529135301353113532135331353413535135361353713538135391354013541135421354313544135451354613547135481354913550135511355213553135541355513556135571355813559135601356113562135631356413565135661356713568135691357013571135721357313574135751357613577135781357913580135811358213583135841358513586135871358813589135901359113592135931359413595135961359713598135991360013601136021360313604136051360613607136081360913610136111361213613136141361513616136171361813619136201362113622136231362413625136261362713628136291363013631136321363313634136351363613637136381363913640136411364213643136441364513646136471364813649136501365113652136531365413655136561365713658136591366013661136621366313664136651366613667136681366913670136711367213673136741367513676136771367813679136801368113682136831368413685136861368713688136891369013691136921369313694136951369613697136981369913700137011370213703137041370513706137071370813709137101371113712137131371413715137161371713718137191372013721137221372313724137251372613727137281372913730137311373213733137341373513736137371373813739137401374113742137431374413745137461374713748137491375013751137521375313754137551375613757137581375913760137611376213763137641376513766137671376813769137701377113772137731377413775137761377713778137791378013781137821378313784137851378613787137881378913790137911379213793137941379513796137971379813799138001380113802138031380413805138061380713808138091381013811138121381313814138151381613817138181381913820138211382213823138241382513826138271382813829138301383113832138331383413835138361383713838138391384013841138421384313844138451384613847138481384913850138511385213853138541385513856138571385813859138601386113862138631386413865138661386713868138691387013871138721387313874138751387613877138781387913880138811388213883138841388513886138871388813889138901389113892138931389413895138961389713898138991390013901139021390313904139051390613907139081390913910139111391213913139141391513916139171391813919139201392113922139231392413925139261392713928139291393013931139321393313934139351393613937139381393913940139411394213943139441394513946139471394813949139501395113952139531395413955139561395713958139591396013961139621396313964139651396613967139681396913970139711397213973139741397513976139771397813979139801398113982139831398413985139861398713988139891399013991139921399313994139951399613997139981399914000140011400214003140041400514006140071400814009140101401114012140131401414015140161401714018140191402014021140221402314024140251402614027140281402914030140311403214033140341403514036140371403814039140401404114042140431404414045140461404714048140491405014051140521405314054140551405614057140581405914060140611406214063140641406514066140671406814069140701407114072140731407414075140761407714078140791408014081140821408314084140851408614087140881408914090140911409214093140941409514096140971409814099141001410114102141031410414105141061410714108141091411014111141121411314114141151411614117141181411914120141211412214123141241412514126141271412814129141301413114132141331413414135141361413714138141391414014141141421414314144141451414614147141481414914150141511415214153141541415514156141571415814159141601416114162141631416414165141661416714168141691417014171141721417314174141751417614177141781417914180141811418214183141841418514186141871418814189141901419114192141931419414195141961419714198141991420014201142021420314204142051420614207142081420914210142111421214213142141421514216142171421814219142201422114222142231422414225142261422714228142291423014231142321423314234142351423614237142381423914240142411424214243142441424514246142471424814249142501425114252142531425414255142561425714258142591426014261142621426314264142651426614267142681426914270142711427214273142741427514276142771427814279142801428114282142831428414285142861428714288142891429014291142921429314294142951429614297142981429914300143011430214303143041430514306143071430814309143101431114312143131431414315143161431714318143191432014321143221432314324143251432614327143281432914330143311433214333143341433514336143371433814339143401434114342143431434414345143461434714348143491435014351143521435314354143551435614357143581435914360143611436214363143641436514366143671436814369143701437114372143731437414375143761437714378143791438014381143821438314384143851438614387143881438914390143911439214393143941439514396143971439814399144001440114402144031440414405144061440714408144091441014411144121441314414144151441614417144181441914420144211442214423144241442514426144271442814429144301443114432144331443414435144361443714438144391444014441144421444314444144451444614447144481444914450144511445214453144541445514456144571445814459144601446114462144631446414465144661446714468144691447014471144721447314474144751447614477144781447914480144811448214483144841448514486144871448814489144901449114492144931449414495144961449714498144991450014501145021450314504145051450614507145081450914510145111451214513145141451514516145171451814519145201452114522145231452414525145261452714528145291453014531145321453314534145351453614537145381453914540145411454214543145441454514546145471454814549145501455114552145531455414555145561455714558145591456014561145621456314564145651456614567145681456914570145711457214573145741457514576145771457814579145801458114582145831458414585145861458714588145891459014591145921459314594145951459614597145981459914600146011460214603146041460514606146071460814609146101461114612146131461414615146161461714618146191462014621146221462314624146251462614627146281462914630146311463214633146341463514636146371463814639146401464114642146431464414645146461464714648146491465014651146521465314654146551465614657146581465914660146611466214663146641466514666146671466814669146701467114672146731467414675146761467714678146791468014681146821468314684146851468614687146881468914690146911469214693146941469514696146971469814699147001470114702147031470414705147061470714708147091471014711147121471314714147151471614717147181471914720147211472214723147241472514726147271472814729147301473114732147331473414735147361473714738147391474014741147421474314744147451474614747147481474914750147511475214753147541475514756147571475814759147601476114762147631476414765147661476714768147691477014771147721477314774147751477614777147781477914780147811478214783147841478514786147871478814789147901479114792147931479414795147961479714798147991480014801148021480314804148051480614807148081480914810148111481214813148141481514816148171481814819148201482114822148231482414825148261482714828148291483014831148321483314834148351483614837148381483914840148411484214843148441484514846148471484814849148501485114852148531485414855148561485714858148591486014861148621486314864148651486614867148681486914870148711487214873148741487514876148771487814879148801488114882148831488414885148861488714888148891489014891148921489314894148951489614897148981489914900149011490214903149041490514906149071490814909149101491114912149131491414915149161491714918149191492014921149221492314924149251492614927149281492914930149311493214933149341493514936149371493814939149401494114942149431494414945149461494714948149491495014951149521495314954149551495614957149581495914960149611496214963149641496514966149671496814969149701497114972149731497414975149761497714978149791498014981149821498314984149851498614987149881498914990149911499214993149941499514996149971499814999150001500115002150031500415005150061500715008150091501015011150121501315014150151501615017150181501915020150211502215023150241502515026150271502815029150301503115032150331503415035150361503715038150391504015041150421504315044150451504615047150481504915050150511505215053150541505515056150571505815059150601506115062150631506415065150661506715068150691507015071150721507315074150751507615077150781507915080150811508215083150841508515086150871508815089150901509115092150931509415095150961509715098150991510015101151021510315104151051510615107151081510915110151111511215113151141511515116151171511815119151201512115122151231512415125151261512715128151291513015131151321513315134151351513615137151381513915140151411514215143151441514515146151471514815149151501515115152151531515415155151561515715158151591516015161151621516315164151651516615167151681516915170151711517215173151741517515176151771517815179151801518115182151831518415185151861518715188151891519015191151921519315194151951519615197151981519915200152011520215203152041520515206152071520815209152101521115212152131521415215152161521715218152191522015221152221522315224152251522615227152281522915230152311523215233152341523515236152371523815239152401524115242152431524415245152461524715248152491525015251152521525315254152551525615257152581525915260152611526215263152641526515266152671526815269152701527115272152731527415275152761527715278152791528015281152821528315284152851528615287152881528915290152911529215293152941529515296152971529815299153001530115302153031530415305153061530715308153091531015311153121531315314153151531615317153181531915320153211532215323153241532515326153271532815329153301533115332153331533415335153361533715338153391534015341153421534315344153451534615347153481534915350153511535215353153541535515356153571535815359153601536115362153631536415365153661536715368153691537015371153721537315374153751537615377153781537915380153811538215383153841538515386153871538815389153901539115392153931539415395153961539715398153991540015401154021540315404154051540615407154081540915410154111541215413154141541515416154171541815419154201542115422154231542415425154261542715428154291543015431154321543315434154351543615437154381543915440154411544215443154441544515446154471544815449154501545115452154531545415455154561545715458154591546015461154621546315464154651546615467154681546915470154711547215473154741547515476154771547815479154801548115482154831548415485154861548715488154891549015491154921549315494154951549615497154981549915500155011550215503155041550515506155071550815509155101551115512155131551415515155161551715518155191552015521155221552315524155251552615527155281552915530155311553215533155341553515536155371553815539155401554115542155431554415545155461554715548155491555015551155521555315554155551555615557155581555915560155611556215563155641556515566155671556815569155701557115572155731557415575155761557715578155791558015581155821558315584155851558615587155881558915590155911559215593155941559515596155971559815599156001560115602156031560415605156061560715608156091561015611156121561315614156151561615617156181561915620156211562215623156241562515626156271562815629156301563115632156331563415635156361563715638156391564015641156421564315644156451564615647156481564915650156511565215653156541565515656156571565815659156601566115662156631566415665156661566715668156691567015671156721567315674156751567615677156781567915680156811568215683156841568515686156871568815689156901569115692156931569415695156961569715698156991570015701157021570315704157051570615707157081570915710157111571215713157141571515716157171571815719157201572115722157231572415725157261572715728157291573015731157321573315734157351573615737157381573915740157411574215743157441574515746157471574815749157501575115752157531575415755157561575715758157591576015761157621576315764157651576615767157681576915770157711577215773157741577515776157771577815779157801578115782157831578415785157861578715788157891579015791157921579315794157951579615797157981579915800158011580215803158041580515806158071580815809158101581115812158131581415815158161581715818158191582015821158221582315824158251582615827158281582915830158311583215833158341583515836158371583815839158401584115842158431584415845158461584715848158491585015851158521585315854158551585615857158581585915860158611586215863158641586515866158671586815869158701587115872158731587415875158761587715878158791588015881158821588315884158851588615887158881588915890158911589215893158941589515896158971589815899159001590115902159031590415905159061590715908159091591015911159121591315914159151591615917159181591915920159211592215923159241592515926159271592815929159301593115932159331593415935159361593715938159391594015941159421594315944159451594615947159481594915950159511595215953159541595515956159571595815959159601596115962159631596415965159661596715968159691597015971159721597315974159751597615977159781597915980159811598215983159841598515986159871598815989159901599115992159931599415995159961599715998159991600016001160021600316004160051600616007160081600916010160111601216013160141601516016160171601816019160201602116022160231602416025160261602716028160291603016031160321603316034160351603616037160381603916040160411604216043160441604516046160471604816049160501605116052160531605416055160561605716058160591606016061160621606316064160651606616067160681606916070160711607216073160741607516076160771607816079160801608116082160831608416085160861608716088160891609016091160921609316094160951609616097160981609916100161011610216103161041610516106161071610816109161101611116112161131611416115161161611716118161191612016121161221612316124161251612616127161281612916130161311613216133161341613516136161371613816139161401614116142161431614416145161461614716148161491615016151161521615316154161551615616157161581615916160161611616216163161641616516166161671616816169161701617116172161731617416175161761617716178161791618016181161821618316184161851618616187161881618916190161911619216193161941619516196161971619816199162001620116202162031620416205162061620716208162091621016211162121621316214162151621616217162181621916220162211622216223162241622516226162271622816229162301623116232162331623416235162361623716238162391624016241162421624316244162451624616247162481624916250162511625216253162541625516256162571625816259162601626116262162631626416265162661626716268162691627016271162721627316274162751627616277162781627916280162811628216283162841628516286162871628816289162901629116292162931629416295162961629716298162991630016301163021630316304163051630616307163081630916310163111631216313163141631516316163171631816319163201632116322163231632416325163261632716328163291633016331163321633316334163351633616337163381633916340163411634216343163441634516346163471634816349163501635116352163531635416355163561635716358163591636016361163621636316364163651636616367163681636916370163711637216373163741637516376163771637816379163801638116382163831638416385163861638716388163891639016391163921639316394163951639616397163981639916400164011640216403164041640516406164071640816409164101641116412164131641416415164161641716418164191642016421164221642316424164251642616427164281642916430164311643216433164341643516436164371643816439164401644116442164431644416445164461644716448164491645016451164521645316454164551645616457164581645916460164611646216463164641646516466164671646816469164701647116472164731647416475164761647716478164791648016481164821648316484164851648616487164881648916490164911649216493164941649516496164971649816499165001650116502165031650416505165061650716508165091651016511165121651316514165151651616517165181651916520165211652216523165241652516526165271652816529165301653116532165331653416535165361653716538165391654016541165421654316544165451654616547165481654916550165511655216553165541655516556165571655816559165601656116562165631656416565165661656716568165691657016571165721657316574165751657616577165781657916580165811658216583165841658516586165871658816589165901659116592165931659416595165961659716598165991660016601166021660316604166051660616607166081660916610166111661216613166141661516616166171661816619166201662116622166231662416625166261662716628166291663016631166321663316634166351663616637166381663916640166411664216643166441664516646166471664816649166501665116652166531665416655166561665716658166591666016661166621666316664166651666616667166681666916670166711667216673166741667516676166771667816679166801668116682166831668416685166861668716688166891669016691166921669316694166951669616697166981669916700167011670216703167041670516706167071670816709167101671116712167131671416715167161671716718167191672016721167221672316724167251672616727167281672916730167311673216733167341673516736167371673816739167401674116742167431674416745167461674716748167491675016751167521675316754167551675616757167581675916760167611676216763167641676516766167671676816769167701677116772167731677416775167761677716778167791678016781167821678316784167851678616787167881678916790167911679216793167941679516796167971679816799168001680116802168031680416805168061680716808168091681016811168121681316814168151681616817168181681916820168211682216823168241682516826168271682816829168301683116832168331683416835168361683716838168391684016841168421684316844168451684616847168481684916850168511685216853168541685516856168571685816859168601686116862168631686416865168661686716868168691687016871168721687316874168751687616877168781687916880168811688216883168841688516886168871688816889168901689116892168931689416895168961689716898168991690016901169021690316904169051690616907169081690916910169111691216913169141691516916169171691816919169201692116922169231692416925169261692716928169291693016931169321693316934169351693616937169381693916940169411694216943169441694516946169471694816949169501695116952169531695416955169561695716958169591696016961169621696316964169651696616967169681696916970169711697216973169741697516976169771697816979169801698116982169831698416985169861698716988169891699016991169921699316994169951699616997169981699917000170011700217003170041700517006170071700817009170101701117012170131701417015170161701717018170191702017021170221702317024170251702617027170281702917030170311703217033170341703517036170371703817039170401704117042170431704417045170461704717048170491705017051170521705317054170551705617057170581705917060170611706217063170641706517066170671706817069170701707117072170731707417075170761707717078170791708017081170821708317084170851708617087170881708917090170911709217093170941709517096170971709817099171001710117102171031710417105171061710717108171091711017111171121711317114171151711617117171181711917120171211712217123171241712517126171271712817129171301713117132171331713417135171361713717138171391714017141171421714317144171451714617147171481714917150171511715217153171541715517156171571715817159171601716117162171631716417165171661716717168171691717017171171721717317174171751717617177171781717917180171811718217183171841718517186171871718817189171901719117192171931719417195171961719717198171991720017201172021720317204172051720617207172081720917210172111721217213172141721517216172171721817219172201722117222172231722417225172261722717228172291723017231172321723317234172351723617237172381723917240172411724217243172441724517246172471724817249172501725117252172531725417255172561725717258172591726017261172621726317264172651726617267172681726917270172711727217273172741727517276172771727817279172801728117282172831728417285172861728717288172891729017291172921729317294172951729617297172981729917300173011730217303173041730517306173071730817309173101731117312173131731417315173161731717318173191732017321173221732317324173251732617327173281732917330173311733217333173341733517336173371733817339173401734117342173431734417345173461734717348173491735017351173521735317354173551735617357173581735917360173611736217363173641736517366173671736817369173701737117372173731737417375173761737717378173791738017381173821738317384173851738617387173881738917390173911739217393173941739517396173971739817399174001740117402174031740417405174061740717408174091741017411174121741317414174151741617417174181741917420174211742217423174241742517426174271742817429174301743117432174331743417435174361743717438174391744017441174421744317444174451744617447174481744917450174511745217453174541745517456174571745817459174601746117462174631746417465174661746717468174691747017471174721747317474174751747617477174781747917480174811748217483174841748517486174871748817489174901749117492174931749417495174961749717498174991750017501175021750317504175051750617507175081750917510175111751217513175141751517516175171751817519175201752117522175231752417525175261752717528175291753017531175321753317534175351753617537175381753917540175411754217543175441754517546175471754817549175501755117552175531755417555175561755717558175591756017561175621756317564175651756617567175681756917570175711757217573175741757517576175771757817579175801758117582175831758417585175861758717588175891759017591175921759317594175951759617597175981759917600176011760217603176041760517606176071760817609176101761117612176131761417615176161761717618176191762017621176221762317624176251762617627176281762917630176311763217633176341763517636176371763817639176401764117642176431764417645176461764717648176491765017651176521765317654176551765617657176581765917660176611766217663176641766517666176671766817669176701767117672176731767417675176761767717678176791768017681176821768317684176851768617687176881768917690176911769217693176941769517696176971769817699177001770117702177031770417705177061770717708177091771017711177121771317714177151771617717177181771917720177211772217723177241772517726177271772817729177301773117732177331773417735177361773717738177391774017741177421774317744177451774617747177481774917750177511775217753177541775517756177571775817759177601776117762177631776417765177661776717768177691777017771177721777317774177751777617777177781777917780177811778217783177841778517786177871778817789177901779117792177931779417795177961779717798177991780017801178021780317804178051780617807178081780917810178111781217813178141781517816178171781817819178201782117822178231782417825178261782717828178291783017831178321783317834178351783617837178381783917840178411784217843178441784517846178471784817849178501785117852178531785417855178561785717858178591786017861178621786317864178651786617867178681786917870178711787217873178741787517876178771787817879178801788117882178831788417885178861788717888178891789017891178921789317894178951789617897178981789917900179011790217903179041790517906179071790817909179101791117912179131791417915179161791717918179191792017921179221792317924179251792617927179281792917930179311793217933179341793517936179371793817939179401794117942179431794417945179461794717948179491795017951179521795317954179551795617957179581795917960179611796217963179641796517966179671796817969179701797117972179731797417975179761797717978179791798017981179821798317984179851798617987179881798917990179911799217993179941799517996179971799817999180001800118002180031800418005180061800718008180091801018011180121801318014180151801618017180181801918020180211802218023180241802518026180271802818029180301803118032180331803418035180361803718038180391804018041180421804318044180451804618047180481804918050180511805218053180541805518056180571805818059180601806118062180631806418065180661806718068180691807018071180721807318074180751807618077180781807918080180811808218083180841808518086180871808818089180901809118092180931809418095180961809718098180991810018101181021810318104181051810618107181081810918110181111811218113181141811518116181171811818119181201812118122181231812418125181261812718128181291813018131181321813318134181351813618137181381813918140181411814218143181441814518146181471814818149181501815118152181531815418155181561815718158181591816018161181621816318164181651816618167181681816918170181711817218173181741817518176181771817818179181801818118182181831818418185181861818718188181891819018191181921819318194181951819618197181981819918200182011820218203182041820518206182071820818209182101821118212182131821418215182161821718218182191822018221182221822318224182251822618227182281822918230182311823218233182341823518236182371823818239182401824118242182431824418245182461824718248182491825018251182521825318254182551825618257182581825918260182611826218263182641826518266182671826818269182701827118272182731827418275182761827718278182791828018281182821828318284182851828618287182881828918290182911829218293182941829518296182971829818299183001830118302183031830418305183061830718308183091831018311183121831318314183151831618317183181831918320183211832218323183241832518326183271832818329183301833118332183331833418335183361833718338183391834018341183421834318344183451834618347183481834918350183511835218353183541835518356183571835818359183601836118362183631836418365183661836718368183691837018371183721837318374183751837618377183781837918380183811838218383183841838518386183871838818389183901839118392183931839418395183961839718398183991840018401184021840318404184051840618407184081840918410184111841218413184141841518416184171841818419184201842118422184231842418425184261842718428184291843018431184321843318434184351843618437184381843918440184411844218443184441844518446184471844818449184501845118452184531845418455184561845718458184591846018461184621846318464184651846618467184681846918470184711847218473184741847518476184771847818479184801848118482184831848418485184861848718488184891849018491184921849318494184951849618497184981849918500185011850218503185041850518506185071850818509185101851118512185131851418515185161851718518185191852018521185221852318524185251852618527185281852918530185311853218533185341853518536185371853818539185401854118542185431854418545185461854718548185491855018551185521855318554185551855618557185581855918560185611856218563185641856518566185671856818569185701857118572185731857418575185761857718578185791858018581185821858318584185851858618587185881858918590185911859218593185941859518596185971859818599186001860118602186031860418605186061860718608186091861018611186121861318614186151861618617186181861918620186211862218623186241862518626186271862818629186301863118632186331863418635186361863718638186391864018641186421864318644186451864618647186481864918650186511865218653186541865518656186571865818659186601866118662186631866418665186661866718668186691867018671186721867318674186751867618677186781867918680186811868218683186841868518686186871868818689186901869118692186931869418695186961869718698186991870018701187021870318704187051870618707187081870918710187111871218713187141871518716187171871818719187201872118722187231872418725187261872718728187291873018731187321873318734187351873618737187381873918740187411874218743187441874518746187471874818749187501875118752187531875418755187561875718758187591876018761187621876318764187651876618767187681876918770187711877218773187741877518776187771877818779187801878118782187831878418785187861878718788187891879018791187921879318794187951879618797187981879918800188011880218803188041880518806188071880818809188101881118812188131881418815188161881718818188191882018821188221882318824188251882618827188281882918830188311883218833188341883518836188371883818839188401884118842188431884418845188461884718848188491885018851188521885318854188551885618857188581885918860188611886218863188641886518866188671886818869188701887118872188731887418875188761887718878188791888018881188821888318884188851888618887188881888918890188911889218893188941889518896188971889818899189001890118902189031890418905189061890718908189091891018911189121891318914189151891618917189181891918920189211892218923189241892518926189271892818929189301893118932189331893418935189361893718938189391894018941189421894318944189451894618947189481894918950189511895218953189541895518956189571895818959189601896118962189631896418965189661896718968189691897018971189721897318974189751897618977189781897918980189811898218983189841898518986189871898818989189901899118992189931899418995189961899718998189991900019001190021900319004190051900619007190081900919010190111901219013190141901519016190171901819019190201902119022190231902419025190261902719028190291903019031190321903319034190351903619037190381903919040190411904219043190441904519046190471904819049190501905119052190531905419055190561905719058190591906019061190621906319064190651906619067190681906919070190711907219073190741907519076190771907819079190801908119082190831908419085190861908719088190891909019091190921909319094190951909619097190981909919100191011910219103191041910519106191071910819109191101911119112191131911419115191161911719118191191912019121191221912319124191251912619127191281912919130191311913219133191341913519136191371913819139191401914119142191431914419145191461914719148191491915019151191521915319154191551915619157191581915919160191611916219163191641916519166191671916819169191701917119172191731917419175191761917719178191791918019181191821918319184191851918619187191881918919190191911919219193191941919519196191971919819199192001920119202192031920419205192061920719208192091921019211192121921319214192151921619217192181921919220192211922219223192241922519226192271922819229192301923119232192331923419235192361923719238192391924019241192421924319244192451924619247192481924919250192511925219253192541925519256192571925819259192601926119262192631926419265192661926719268192691927019271192721927319274192751927619277192781927919280192811928219283192841928519286192871928819289192901929119292192931929419295192961929719298192991930019301193021930319304193051930619307193081930919310193111931219313193141931519316193171931819319193201932119322193231932419325193261932719328193291933019331193321933319334193351933619337193381933919340193411934219343193441934519346193471934819349193501935119352193531935419355193561935719358193591936019361193621936319364193651936619367193681936919370193711937219373193741937519376193771937819379193801938119382193831938419385193861938719388193891939019391193921939319394193951939619397193981939919400194011940219403194041940519406194071940819409194101941119412194131941419415194161941719418194191942019421194221942319424194251942619427194281942919430194311943219433194341943519436194371943819439194401944119442194431944419445194461944719448194491945019451194521945319454194551945619457194581945919460194611946219463194641946519466194671946819469194701947119472194731947419475194761947719478194791948019481194821948319484194851948619487194881948919490194911949219493194941949519496194971949819499195001950119502195031950419505195061950719508195091951019511195121951319514195151951619517195181951919520195211952219523195241952519526195271952819529195301953119532195331953419535195361953719538195391954019541195421954319544195451954619547195481954919550195511955219553195541955519556195571955819559195601956119562195631956419565195661956719568195691957019571195721957319574195751957619577195781957919580195811958219583195841958519586195871958819589195901959119592195931959419595195961959719598195991960019601196021960319604196051960619607196081960919610196111961219613196141961519616196171961819619196201962119622196231962419625196261962719628196291963019631196321963319634196351963619637196381963919640196411964219643196441964519646196471964819649196501965119652196531965419655196561965719658196591966019661196621966319664196651966619667196681966919670196711967219673196741967519676196771967819679196801968119682196831968419685196861968719688196891969019691196921969319694196951969619697196981969919700197011970219703197041970519706197071970819709197101971119712197131971419715197161971719718197191972019721197221972319724197251972619727197281972919730197311973219733197341973519736197371973819739197401974119742197431974419745197461974719748197491975019751197521975319754197551975619757197581975919760197611976219763197641976519766197671976819769197701977119772197731977419775197761977719778197791978019781197821978319784197851978619787197881978919790197911979219793197941979519796197971979819799198001980119802198031980419805198061980719808198091981019811198121981319814198151981619817198181981919820198211982219823198241982519826198271982819829198301983119832198331983419835198361983719838198391984019841198421984319844198451984619847198481984919850198511985219853198541985519856198571985819859198601986119862198631986419865198661986719868198691987019871198721987319874198751987619877198781987919880198811988219883198841988519886198871988819889198901989119892198931989419895198961989719898198991990019901199021990319904199051990619907199081990919910199111991219913199141991519916199171991819919199201992119922199231992419925199261992719928199291993019931199321993319934199351993619937199381993919940199411994219943199441994519946199471994819949199501995119952199531995419955199561995719958199591996019961199621996319964199651996619967199681996919970199711997219973199741997519976199771997819979199801998119982199831998419985199861998719988199891999019991199921999319994199951999619997199981999920000200012000220003200042000520006200072000820009200102001120012200132001420015200162001720018200192002020021200222002320024200252002620027200282002920030200312003220033200342003520036200372003820039200402004120042200432004420045200462004720048200492005020051200522005320054200552005620057200582005920060200612006220063200642006520066200672006820069200702007120072200732007420075200762007720078200792008020081200822008320084200852008620087200882008920090200912009220093200942009520096200972009820099201002010120102201032010420105201062010720108201092011020111201122011320114201152011620117201182011920120201212012220123201242012520126201272012820129201302013120132201332013420135201362013720138201392014020141201422014320144201452014620147201482014920150201512015220153201542015520156201572015820159201602016120162201632016420165201662016720168201692017020171201722017320174201752017620177201782017920180201812018220183201842018520186201872018820189201902019120192201932019420195201962019720198201992020020201202022020320204202052020620207202082020920210202112021220213202142021520216202172021820219202202022120222202232022420225202262022720228202292023020231202322023320234202352023620237202382023920240202412024220243202442024520246202472024820249202502025120252202532025420255202562025720258202592026020261202622026320264202652026620267202682026920270202712027220273202742027520276202772027820279202802028120282202832028420285202862028720288202892029020291202922029320294202952029620297202982029920300203012030220303203042030520306203072030820309203102031120312203132031420315203162031720318203192032020321203222032320324203252032620327203282032920330203312033220333203342033520336203372033820339203402034120342203432034420345203462034720348203492035020351203522035320354203552035620357203582035920360203612036220363203642036520366203672036820369203702037120372203732037420375203762037720378203792038020381203822038320384203852038620387203882038920390203912039220393203942039520396203972039820399204002040120402204032040420405204062040720408204092041020411204122041320414204152041620417204182041920420204212042220423204242042520426204272042820429204302043120432204332043420435204362043720438204392044020441204422044320444204452044620447204482044920450204512045220453204542045520456204572045820459204602046120462204632046420465204662046720468204692047020471204722047320474204752047620477204782047920480204812048220483204842048520486204872048820489204902049120492204932049420495204962049720498204992050020501205022050320504205052050620507205082050920510205112051220513205142051520516205172051820519205202052120522205232052420525205262052720528205292053020531205322053320534205352053620537205382053920540205412054220543205442054520546205472054820549205502055120552205532055420555205562055720558205592056020561205622056320564205652056620567205682056920570205712057220573205742057520576205772057820579205802058120582205832058420585205862058720588205892059020591205922059320594205952059620597205982059920600206012060220603206042060520606206072060820609206102061120612206132061420615206162061720618206192062020621206222062320624206252062620627206282062920630206312063220633206342063520636206372063820639206402064120642206432064420645206462064720648206492065020651206522065320654206552065620657206582065920660206612066220663206642066520666206672066820669206702067120672206732067420675206762067720678206792068020681206822068320684206852068620687206882068920690206912069220693206942069520696206972069820699207002070120702207032070420705207062070720708207092071020711207122071320714207152071620717207182071920720207212072220723207242072520726207272072820729207302073120732207332073420735207362073720738207392074020741207422074320744207452074620747207482074920750207512075220753207542075520756207572075820759207602076120762207632076420765207662076720768207692077020771207722077320774207752077620777207782077920780207812078220783207842078520786207872078820789207902079120792207932079420795207962079720798207992080020801208022080320804208052080620807208082080920810208112081220813208142081520816208172081820819208202082120822208232082420825208262082720828208292083020831208322083320834208352083620837208382083920840208412084220843208442084520846208472084820849208502085120852208532085420855208562085720858208592086020861208622086320864208652086620867208682086920870208712087220873208742087520876208772087820879208802088120882208832088420885208862088720888208892089020891208922089320894208952089620897208982089920900209012090220903209042090520906209072090820909209102091120912209132091420915209162091720918209192092020921209222092320924209252092620927209282092920930209312093220933209342093520936209372093820939209402094120942209432094420945209462094720948209492095020951209522095320954209552095620957209582095920960209612096220963209642096520966209672096820969209702097120972209732097420975209762097720978209792098020981209822098320984209852098620987209882098920990209912099220993209942099520996209972099820999210002100121002210032100421005210062100721008210092101021011210122101321014210152101621017210182101921020210212102221023210242102521026210272102821029210302103121032 |
- <?xml version="1.0" encoding="iso-8859-1" standalone="no"?>
- <!-- Generated by the JDiff Javadoc doclet -->
- <!-- (http://www.jdiff.org) -->
- <!-- on Sun May 31 20:42:50 PDT 2009 -->
- <api
- xmlns:xsi='http://www.w3.org/2001/XMLSchema-instance'
- xsi:noNamespaceSchemaLocation='api.xsd'
- name="hadoopp-mapred 0.20.0"
- jdversion="1.0.9">
- <!-- Command line arguments = -doclet jdiff.JDiff -docletpath /home/gkesavan/release-0.20.0/build/ivy/lib/Hadoop/jdiff/jdiff-1.0.9.jar:/home/gkesavan/release-0.20.0/build/ivy/lib/Hadoop/jdiff/xerces-1.4.4.jar -classpath /home/gkesavan/release-0.20.0/build/classes:/home/gkesavan/release-0.20.0/lib/commons-cli-2.0-SNAPSHOT.jar:/home/gkesavan/release-0.20.0/lib/hsqldb-1.8.0.10.jar:/home/gkesavan/release-0.20.0/lib/jsp-2.1/jsp-2.1.jar:/home/gkesavan/release-0.20.0/lib/jsp-2.1/jsp-api-2.1.jar:/home/gkesavan/release-0.20.0/lib/kfs-0.2.2.jar:/home/gkesavan/release-0.20.0/conf:/home/gkesavan/.ivy2/cache/commons-logging/commons-logging/jars/commons-logging-1.0.4.jar:/home/gkesavan/.ivy2/cache/log4j/log4j/jars/log4j-1.2.15.jar:/home/gkesavan/.ivy2/cache/commons-httpclient/commons-httpclient/jars/commons-httpclient-3.0.1.jar:/home/gkesavan/.ivy2/cache/commons-codec/commons-codec/jars/commons-codec-1.3.jar:/home/gkesavan/.ivy2/cache/xmlenc/xmlenc/jars/xmlenc-0.52.jar:/home/gkesavan/.ivy2/cache/net.java.dev.jets3t/jets3t/jars/jets3t-0.6.1.jar:/home/gkesavan/.ivy2/cache/commons-net/commons-net/jars/commons-net-1.4.1.jar:/home/gkesavan/.ivy2/cache/org.mortbay.jetty/servlet-api-2.5/jars/servlet-api-2.5-6.1.14.jar:/home/gkesavan/.ivy2/cache/oro/oro/jars/oro-2.0.8.jar:/home/gkesavan/.ivy2/cache/org.mortbay.jetty/jetty/jars/jetty-6.1.14.jar:/home/gkesavan/.ivy2/cache/org.mortbay.jetty/jetty-util/jars/jetty-util-6.1.14.jar:/home/gkesavan/.ivy2/cache/tomcat/jasper-runtime/jars/jasper-runtime-5.5.12.jar:/home/gkesavan/.ivy2/cache/tomcat/jasper-compiler/jars/jasper-compiler-5.5.12.jar:/home/gkesavan/.ivy2/cache/commons-el/commons-el/jars/commons-el-1.0.jar:/home/gkesavan/.ivy2/cache/junit/junit/jars/junit-3.8.1.jar:/home/gkesavan/.ivy2/cache/commons-logging/commons-logging-api/jars/commons-logging-api-1.0.4.jar:/home/gkesavan/.ivy2/cache/org.slf4j/slf4j-api/jars/slf4j-api-1.4.3.jar:/home/gkesavan/.ivy2/cache/org.eclipse.jdt/core/jars/core-3.1.1.jar:/home/gkesavan/.ivy2/cache/org.slf4j/slf4j-log4j12/jars/slf4j-log4j12-1.4.3.jar:/home/gkesavan/.ivy2/cache/jdiff/jdiff/jars/jdiff-1.0.9.jar:/home/gkesavan/.ivy2/cache/xerces/xerces/jars/xerces-1.4.4.jar:/home/gkesavan/tools/apache-ant-1.7.1/lib/ant-launcher.jar:/home/gkesavan/tools/apache-ant-1.7.1/lib/ant-apache-resolver.jar:/home/gkesavan/tools/apache-ant-1.7.1/lib/ant-starteam.jar:/home/gkesavan/tools/apache-ant-1.7.1/lib/ant-netrexx.jar:/home/gkesavan/tools/apache-ant-1.7.1/lib/ant-testutil.jar:/home/gkesavan/tools/apache-ant-1.7.1/lib/ant-jai.jar:/home/gkesavan/tools/apache-ant-1.7.1/lib/ant-swing.jar:/home/gkesavan/tools/apache-ant-1.7.1/lib/ant-jmf.jar:/home/gkesavan/tools/apache-ant-1.7.1/lib/ant-apache-bcel.jar:/home/gkesavan/tools/apache-ant-1.7.1/lib/ant-jdepend.jar:/home/gkesavan/tools/apache-ant-1.7.1/lib/ant-jsch.jar:/home/gkesavan/tools/apache-ant-1.7.1/lib/ant-apache-bsf.jar:/home/gkesavan/tools/apache-ant-1.7.1/lib/ant-antlr.jar:/home/gkesavan/tools/apache-ant-1.7.1/lib/ant-weblogic.jar:/home/gkesavan/tools/apache-ant-1.7.1/lib/ant-junit.jar:/home/gkesavan/tools/apache-ant-1.7.1/lib/ant-apache-log4j.jar:/home/gkesavan/tools/apache-ant-1.7.1/lib/xercesImpl.jar:/home/gkesavan/tools/apache-ant-1.7.1/lib/ant-apache-oro.jar:/home/gkesavan/tools/apache-ant-1.7.1/lib/ant.jar:/home/gkesavan/tools/apache-ant-1.7.1/lib/ant-trax.jar:/home/gkesavan/tools/apache-ant-1.7.1/lib/ant-nodeps.jar:/home/gkesavan/tools/apache-ant-1.7.1/lib/ant-commons-logging.jar:/home/gkesavan/tools/apache-ant-1.7.1/lib/ant-apache-regexp.jar:/home/gkesavan/tools/apache-ant-1.7.1/lib/ant-stylebook.jar:/home/gkesavan/tools/apache-ant-1.7.1/lib/ant-javamail.jar:/home/gkesavan/tools/apache-ant-1.7.1/lib/ant-commons-net.jar:/home/gkesavan/tools/apache-ant-1.7.1/lib/xml-apis.jar:/home/gkesavan/tools/jdk1.6.0_07-32bit/lib/tools.jar -sourcepath /home/gkesavan/release-0.20.0/src/mapred:/home/gkesavan/release-0.20.0/src/tools -apidir /home/gkesavan/release-0.20.0/lib/jdiff -apiname hadoop-mapred 0.20.0 -->
- <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="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="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>
- </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.Counters -->
- <class name="Counters" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.Counters} instead.">
- <implements name="org.apache.hadoop.io.Writable"/>
- <implements name="java.lang.Iterable"/>
- <constructor name="Counters"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getGroupNames" return="java.util.Collection"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns the names of all counter classes.
- @return Set of counter names.]]>
- </doc>
- </method>
- <method name="iterator" return="java.util.Iterator"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getGroup" return="org.apache.hadoop.mapred.Counters.Group"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="groupName" type="java.lang.String"/>
- <doc>
- <![CDATA[Returns the named counter group, or an empty group if there is none
- with the specified name.]]>
- </doc>
- </method>
- <method name="findCounter" return="org.apache.hadoop.mapred.Counters.Counter"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="java.lang.Enum"/>
- <doc>
- <![CDATA[Find the counter for the given enum. The same enum will always return the
- same counter.
- @param key the counter key
- @return the matching counter object]]>
- </doc>
- </method>
- <method name="findCounter" return="org.apache.hadoop.mapred.Counters.Counter"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="group" type="java.lang.String"/>
- <param name="name" type="java.lang.String"/>
- <doc>
- <![CDATA[Find a counter given the group and the name.
- @param group the name of the group
- @param name the internal name of the counter
- @return the counter for that name]]>
- </doc>
- </method>
- <method name="findCounter" return="org.apache.hadoop.mapred.Counters.Counter"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="deprecated, no comment">
- <param name="group" type="java.lang.String"/>
- <param name="id" type="int"/>
- <param name="name" type="java.lang.String"/>
- <doc>
- <![CDATA[Find a counter by using strings
- @param group the name of the group
- @param id the id of the counter within the group (0 to N-1)
- @param name the internal name of the counter
- @return the counter for that name
- @deprecated]]>
- </doc>
- </method>
- <method name="incrCounter"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="java.lang.Enum"/>
- <param name="amount" type="long"/>
- <doc>
- <![CDATA[Increments the specified counter by the specified amount, creating it if
- it didn't already exist.
- @param key identifies a counter
- @param amount amount by which counter is to be incremented]]>
- </doc>
- </method>
- <method name="incrCounter"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="group" type="java.lang.String"/>
- <param name="counter" type="java.lang.String"/>
- <param name="amount" type="long"/>
- <doc>
- <![CDATA[Increments the specified counter by the specified amount, creating it if
- it didn't already exist.
- @param group the name of the group
- @param counter the internal name of the counter
- @param amount amount by which counter is to be incremented]]>
- </doc>
- </method>
- <method name="getCounter" return="long"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="java.lang.Enum"/>
- <doc>
- <![CDATA[Returns current value of the specified counter, or 0 if the counter
- does not exist.]]>
- </doc>
- </method>
- <method name="incrAllCounters"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="other" type="org.apache.hadoop.mapred.Counters"/>
- <doc>
- <![CDATA[Increments multiple counters by their amounts in another Counters
- instance.
- @param other the other Counters instance]]>
- </doc>
- </method>
- <method name="sum" return="org.apache.hadoop.mapred.Counters"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="a" type="org.apache.hadoop.mapred.Counters"/>
- <param name="b" type="org.apache.hadoop.mapred.Counters"/>
- <doc>
- <![CDATA[Convenience method for computing the sum of two sets of counters.]]>
- </doc>
- </method>
- <method name="size" return="int"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns the total number of counters, by summing the number of counters
- in each group.]]>
- </doc>
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="out" type="java.io.DataOutput"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Write the set of groups.
- The external format is:
- #groups (groupName group)*
- i.e. the number of groups followed by 0 or more groups, where each
- group is of the form:
- groupDisplayName #counters (false | true counter)*
- where each counter is of the form:
- name (false | true displayName) value]]>
- </doc>
- </method>
- <method name="readFields"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="in" type="java.io.DataInput"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Read a set of groups.]]>
- </doc>
- </method>
- <method name="log"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="log" type="org.apache.commons.logging.Log"/>
- <doc>
- <![CDATA[Logs the current counter values.
- @param log The log to use.]]>
- </doc>
- </method>
- <method name="toString" return="java.lang.String"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Return textual representation of the counter values.]]>
- </doc>
- </method>
- <method name="makeCompactString" return="java.lang.String"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Convert a counters object into a single line that is easy to parse.
- @return the string with "name=value" for each counter and separated by ","]]>
- </doc>
- </method>
- <method name="makeEscapedCompactString" return="java.lang.String"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Represent the counter in a textual format that can be converted back to
- its object form
- @return the string in the following format
- {(groupname)(group-displayname)[(countername)(displayname)(value)][][]}{}{}]]>
- </doc>
- </method>
- <method name="fromEscapedCompactString" return="org.apache.hadoop.mapred.Counters"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="compactString" type="java.lang.String"/>
- <exception name="ParseException" type="java.text.ParseException"/>
- <doc>
- <![CDATA[Convert a stringified counter representation into a counter object. Note
- that the counter can be recovered if its stringified using
- {@link #makeEscapedCompactString()}.
- @return a Counter]]>
- </doc>
- </method>
- <method name="hashCode" return="int"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="equals" return="boolean"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="obj" type="java.lang.Object"/>
- </method>
- <doc>
- <![CDATA[A set of named counters.
-
- <p><code>Counters</code> represent global counters, defined either by the
- Map-Reduce framework or applications. Each <code>Counter</code> can be of
- any {@link Enum} type.</p>
-
- <p><code>Counters</code> are bunched into {@link Group}s, each comprising of
- counters from a particular <code>Enum</code> class.
- @deprecated Use {@link org.apache.hadoop.mapreduce.Counters} instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.Counters -->
- <!-- start class org.apache.hadoop.mapred.Counters.Counter -->
- <class name="Counters.Counter" extends="org.apache.hadoop.mapreduce.Counter"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <method name="setDisplayName"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="newName" type="java.lang.String"/>
- </method>
- <method name="makeEscapedCompactString" return="java.lang.String"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns the compact stringified version of the counter in the format
- [(actual-name)(display-name)(value)]]]>
- </doc>
- </method>
- <method name="getCounter" return="long"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[What is the current value of this counter?
- @return the current value]]>
- </doc>
- </method>
- <doc>
- <![CDATA[A counter record, comprising its name and value.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.Counters.Counter -->
- <!-- start class org.apache.hadoop.mapred.Counters.Group -->
- <class name="Counters.Group" extends="java.lang.Object"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.io.Writable"/>
- <implements name="java.lang.Iterable"/>
- <method name="getName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns raw name of the group. This is the name of the enum class
- for this group of counters.]]>
- </doc>
- </method>
- <method name="getDisplayName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns localized name of the group. This is the same as getName() by
- default, but different if an appropriate ResourceBundle is found.]]>
- </doc>
- </method>
- <method name="setDisplayName"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="displayName" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the display name]]>
- </doc>
- </method>
- <method name="makeEscapedCompactString" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns the compact stringified version of the group in the format
- {(actual-name)(display-name)(value)[][][]} where [] are compact strings for the
- counters within.]]>
- </doc>
- </method>
- <method name="hashCode" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="equals" return="boolean"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="obj" type="java.lang.Object"/>
- <doc>
- <![CDATA[Checks for (content) equality of Groups]]>
- </doc>
- </method>
- <method name="getCounter" return="long"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="counterName" type="java.lang.String"/>
- <doc>
- <![CDATA[Returns the value of the specified counter, or 0 if the counter does
- not exist.]]>
- </doc>
- </method>
- <method name="getCounter" return="org.apache.hadoop.mapred.Counters.Counter"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="use {@link #getCounter(String)} instead">
- <param name="id" type="int"/>
- <param name="name" type="java.lang.String"/>
- <doc>
- <![CDATA[Get the counter for the given id and create it if it doesn't exist.
- @param id the numeric id of the counter within the group
- @param name the internal counter name
- @return the counter
- @deprecated use {@link #getCounter(String)} instead]]>
- </doc>
- </method>
- <method name="getCounterForName" return="org.apache.hadoop.mapred.Counters.Counter"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- <doc>
- <![CDATA[Get the counter for the given name and create it if it doesn't exist.
- @param name the internal counter name
- @return the counter]]>
- </doc>
- </method>
- <method name="size" return="int"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns the number of counters in this group.]]>
- </doc>
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="out" type="java.io.DataOutput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="readFields"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="in" type="java.io.DataInput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="iterator" return="java.util.Iterator"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <doc>
- <![CDATA[<code>Group</code> of counters, comprising of counters from a particular
- counter {@link Enum} class.
- <p><code>Group</code>handles localization of the class name and the
- counter names.</p>]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.Counters.Group -->
- <!-- start class org.apache.hadoop.mapred.DefaultJobHistoryParser -->
- <class name="DefaultJobHistoryParser" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="DefaultJobHistoryParser"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="parseJobTasks"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobHistoryFile" type="java.lang.String"/>
- <param name="job" type="org.apache.hadoop.mapred.JobHistory.JobInfo"/>
- <param name="fs" type="org.apache.hadoop.fs.FileSystem"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Populates a JobInfo object from the job's history log file.
- @param jobHistoryFile history file for this job.
- @param job a precreated JobInfo object, should be non-null.
- @param fs FileSystem where historyFile is present.
- @throws IOException]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Default parser for job history files. It creates object model from
- job history file.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.DefaultJobHistoryParser -->
- <!-- start class org.apache.hadoop.mapred.FileAlreadyExistsException -->
- <class name="FileAlreadyExistsException" extends="java.io.IOException"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="FileAlreadyExistsException"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <constructor name="FileAlreadyExistsException" type="java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <doc>
- <![CDATA[Used when target file already exists for any operation and
- is not configured to be overwritten.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.FileAlreadyExistsException -->
- <!-- start class org.apache.hadoop.mapred.FileInputFormat -->
- <class name="FileInputFormat" extends="java.lang.Object"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.lib.input.FileInputFormat}
- instead.">
- <implements name="org.apache.hadoop.mapred.InputFormat"/>
- <constructor name="FileInputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setMinSplitSize"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="minSplitSize" type="long"/>
- </method>
- <method name="isSplitable" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="fs" type="org.apache.hadoop.fs.FileSystem"/>
- <param name="filename" type="org.apache.hadoop.fs.Path"/>
- <doc>
- <![CDATA[Is the given filename splitable? Usually, true, but if the file is
- stream compressed, it will not be.
-
- <code>FileInputFormat</code> implementations can override this and return
- <code>false</code> to ensure that individual input files are never split-up
- so that {@link Mapper}s process entire files.
-
- @param fs the file system that the file is on
- @param filename the file name to check
- @return is this file splitable?]]>
- </doc>
- </method>
- <method name="getRecordReader" return="org.apache.hadoop.mapred.RecordReader"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapred.InputSplit"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="setInputPathFilter"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="filter" type="java.lang.Class"/>
- <doc>
- <![CDATA[Set a PathFilter to be applied to the input paths for the map-reduce job.
- @param filter the PathFilter class use for filtering the input paths.]]>
- </doc>
- </method>
- <method name="getInputPathFilter" return="org.apache.hadoop.fs.PathFilter"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[Get a PathFilter instance of the filter set for the input paths.
- @return the PathFilter instance set for the job, NULL if none has been set.]]>
- </doc>
- </method>
- <method name="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="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>
- <doc>
- <![CDATA[A base class for file-based {@link InputFormat}.
-
- <p><code>FileInputFormat</code> is the base class for all file-based
- <code>InputFormat</code>s. This provides a generic implementation of
- {@link #getSplits(JobConf, int)}.
- Subclasses of <code>FileInputFormat</code> can also override the
- {@link #isSplitable(FileSystem, Path)} method to ensure input-files are
- not split-up and are processed as a whole by {@link Mapper}s.
- @deprecated Use {@link org.apache.hadoop.mapreduce.lib.input.FileInputFormat}
- instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.FileInputFormat -->
- <!-- start class org.apache.hadoop.mapred.FileOutputCommitter -->
- <class name="FileOutputCommitter" extends="org.apache.hadoop.mapred.OutputCommitter"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="FileOutputCommitter"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setupJob"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="context" type="org.apache.hadoop.mapred.JobContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="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="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>
- <doc>
- <![CDATA[An {@link OutputCommitter} that commits files specified
- in job output directory i.e. ${mapred.output.dir}.]]>
- </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>${mapred.output.dir}$</tt></p>
-
- <p>Some applications need to create/write-to side-files, which differ from
- the actual job-outputs.
-
- <p>In such cases there could be issues with 2 instances of the same TIP
- (running simultaneously e.g. speculative tasks) trying to open/write-to the
- same file (path) on HDFS. Hence the application-writer will have to pick
- unique names per task-attempt (e.g. using the attemptid, say
- <tt>attempt_200709221812_0001_m_000000_0</tt>), not just per TIP.</p>
-
- <p>To get around this the Map-Reduce framework helps the application-writer
- out by maintaining a special
- <tt>${mapred.output.dir}/_temporary/_${taskid}</tt>
- sub-directory for each task-attempt on HDFS where the output of the
- task-attempt goes. On successful completion of the task-attempt the files
- in the <tt>${mapred.output.dir}/_temporary/_${taskid}</tt> (only)
- are <i>promoted</i> to <tt>${mapred.output.dir}</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>${mapred.work.output.dir}</tt> during execution
- of his reduce-task i.e. via {@link #getWorkOutputPath(JobConf)}, and the
- framework will move them out similarly - thus she doesn't have to pick
- unique paths per task-attempt.</p>
-
- <p><i>Note</i>: the value of <tt>${mapred.work.output.dir}</tt> during
- execution of a particular task-attempt is actually
- <tt>${mapred.output.dir}/_temporary/_{$taskid}</tt>, and this value is
- set by the map-reduce framework. So, just create any side-files in the
- path returned by {@link #getWorkOutputPath(JobConf)} from map/reduce
- task to take advantage of this feature.</p>
-
- <p>The entire discussion holds true for maps of jobs with
- reducer=NONE (i.e. 0 reduces) since output of the map, in that case,
- goes directly to HDFS.</p>
-
- @return the {@link Path} to the task's temporary output directory
- for the map-reduce job.]]>
- </doc>
- </method>
- <method name="getTaskOutputPath" return="org.apache.hadoop.fs.Path"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="name" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Helper function to create the task's temporary output directory and
- return the path to the task's output file.
-
- @param conf job-configuration
- @param name temporary task-output filename
- @return path to the task's temporary output file
- @throws IOException]]>
- </doc>
- </method>
- <method name="getUniqueName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="name" type="java.lang.String"/>
- <doc>
- <![CDATA[Helper function to generate a name that is unique for the task.
- <p>The generated name can be used to create custom files from within the
- different tasks for the job, the names for different tasks will not collide
- with each other.</p>
- <p>The given name is postfixed with the task type, 'm' for maps, 'r' for
- reduces and the task partition number. For example, give a name 'test'
- running on the first map o the job the generated name will be
- 'test-m-00000'.</p>
- @param conf the configuration for the job.
- @param name the name to make unique.
- @return a unique name accross all tasks of the job.]]>
- </doc>
- </method>
- <method name="getPathForCustomFile" return="org.apache.hadoop.fs.Path"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="name" type="java.lang.String"/>
- <doc>
- <![CDATA[Helper function to generate a {@link Path} for a file that is unique for
- the task within the job output directory.
- <p>The path can be used to create custom files from within the map and
- reduce tasks. The path name will be unique for each task. The path parent
- will be the job output directory.</p>ls
- <p>This method uses the {@link #getUniqueName} method to make the file name
- unique for the task.</p>
- @param conf the configuration for the job.
- @param name the name for the file.
- @return a unique path accross all tasks of the job.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[A base class for {@link OutputFormat}.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.FileOutputFormat -->
- <!-- start class org.apache.hadoop.mapred.FileSplit -->
- <class name="FileSplit" extends="org.apache.hadoop.mapreduce.InputSplit"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.lib.input.FileSplit}
- instead.">
- <implements name="org.apache.hadoop.mapred.InputSplit"/>
- <constructor name="FileSplit" 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>
- <method name="getPath" return="org.apache.hadoop.fs.Path"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[The file containing this split's data.]]>
- </doc>
- </method>
- <method name="getStart" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[The position of the first byte in the file to process.]]>
- </doc>
- </method>
- <method name="getLength" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[The number of bytes in the file to process.]]>
- </doc>
- </method>
- <method name="toString" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="write"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="out" type="java.io.DataOutput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="readFields"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="in" type="java.io.DataInput"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getLocations" return="java.lang.String[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[A section of an input file. Returned by {@link
- InputFormat#getSplits(JobConf, int)} and passed to
- {@link InputFormat#getRecordReader(InputSplit,JobConf,Reporter)}.
- @deprecated Use {@link org.apache.hadoop.mapreduce.lib.input.FileSplit}
- instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.FileSplit -->
- <!-- start class org.apache.hadoop.mapred.ID -->
- <class name="ID" extends="org.apache.hadoop.mapreduce.ID"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="ID" type="int"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[constructs an ID object from the given int]]>
- </doc>
- </constructor>
- <constructor name="ID"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </constructor>
- <doc>
- <![CDATA[A general identifier, which internally stores the id
- as an integer. This is the super class of {@link JobID},
- {@link TaskID} and {@link TaskAttemptID}.
-
- @see JobID
- @see TaskID
- @see TaskAttemptID]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.ID -->
- <!-- start interface org.apache.hadoop.mapred.InputFormat -->
- <interface name="InputFormat" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.InputFormat} instead.">
- <method name="getSplits" return="org.apache.hadoop.mapred.InputSplit[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="numSplits" type="int"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Logically split the set of input files for the job.
-
- <p>Each {@link InputSplit} is then assigned to an individual {@link Mapper}
- for processing.</p>
- <p><i>Note</i>: The split is a <i>logical</i> split of the inputs and the
- input files are not physically split into chunks. For e.g. a split could
- be <i><input-file-path, start, offset></i> tuple.
-
- @param job job configuration.
- @param numSplits the desired number of splits, a hint.
- @return an array of {@link InputSplit}s for the job.]]>
- </doc>
- </method>
- <method name="getRecordReader" return="org.apache.hadoop.mapred.RecordReader"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapred.InputSplit"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get the {@link RecordReader} for the given {@link InputSplit}.
- <p>It is the responsibility of the <code>RecordReader</code> to respect
- record boundaries while processing the logical split to present a
- record-oriented view to the individual task.</p>
-
- @param split the {@link InputSplit}
- @param job the job that this split belongs to
- @return a {@link RecordReader}]]>
- </doc>
- </method>
- <doc>
- <![CDATA[<code>InputFormat</code> describes the input-specification for a
- Map-Reduce job.
-
- <p>The Map-Reduce framework relies on the <code>InputFormat</code> of the
- job to:<p>
- <ol>
- <li>
- Validate the input-specification of the job.
- <li>
- Split-up the input file(s) into logical {@link InputSplit}s, each of
- which is then assigned to an individual {@link Mapper}.
- </li>
- <li>
- Provide the {@link RecordReader} implementation to be used to glean
- input records from the logical <code>InputSplit</code> for processing by
- the {@link Mapper}.
- </li>
- </ol>
-
- <p>The default behavior of file-based {@link InputFormat}s, typically
- sub-classes of {@link FileInputFormat}, is to split the
- input into <i>logical</i> {@link InputSplit}s based on the total size, in
- bytes, of the input files. However, the {@link FileSystem} blocksize of
- the input files is treated as an upper bound for input splits. A lower bound
- on the split size can be set via
- <a href="{@docRoot}/../mapred-default.html#mapred.min.split.size">
- mapred.min.split.size</a>.</p>
-
- <p>Clearly, logical splits based on input-size is insufficient for many
- applications since record boundaries are to respected. In such cases, the
- application has to also implement a {@link RecordReader} on whom lies the
- responsibilty to respect record-boundaries and present a record-oriented
- view of the logical <code>InputSplit</code> to the individual task.
- @see InputSplit
- @see RecordReader
- @see JobClient
- @see FileInputFormat
- @deprecated Use {@link org.apache.hadoop.mapreduce.InputFormat} instead.]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.InputFormat -->
- <!-- start interface org.apache.hadoop.mapred.InputSplit -->
- <interface name="InputSplit" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.InputSplit} instead.">
- <implements name="org.apache.hadoop.io.Writable"/>
- <method name="getLength" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get the total number of bytes in the data of the <code>InputSplit</code>.
-
- @return the number of bytes in the input split.
- @throws IOException]]>
- </doc>
- </method>
- <method name="getLocations" return="java.lang.String[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get the list of hostnames where the input split is located.
-
- @return list of hostnames where data of the <code>InputSplit</code> is
- located as an array of <code>String</code>s.
- @throws IOException]]>
- </doc>
- </method>
- <doc>
- <![CDATA[<code>InputSplit</code> represents the data to be processed by an
- individual {@link Mapper}.
- <p>Typically, it presents a byte-oriented view on the input and is the
- responsibility of {@link RecordReader} of the job to process this and present
- a record-oriented view.
-
- @see InputFormat
- @see RecordReader
- @deprecated Use {@link org.apache.hadoop.mapreduce.InputSplit} instead.]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.InputSplit -->
- <!-- start class org.apache.hadoop.mapred.InvalidFileTypeException -->
- <class name="InvalidFileTypeException" extends="java.io.IOException"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="InvalidFileTypeException"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <constructor name="InvalidFileTypeException" type="java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <doc>
- <![CDATA[Used when file type differs from the desired file type. like
- getting a file when a directory is expected. Or a wrong file type.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.InvalidFileTypeException -->
- <!-- start class org.apache.hadoop.mapred.InvalidInputException -->
- <class name="InvalidInputException" extends="java.io.IOException"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="InvalidInputException" type="java.util.List"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Create the exception with the given list.
- @param probs the list of problems to report. this list is not copied.]]>
- </doc>
- </constructor>
- <method name="getProblems" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the complete list of the problems reported.
- @return the list of problems, which must not be modified]]>
- </doc>
- </method>
- <method name="getMessage" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get a summary message of the problems found.
- @return the concatenated messages from all of the problems.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[This class wraps a list of problems with the input, so that the user
- can get a list of problems together instead of finding and fixing them one
- by one.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.InvalidInputException -->
- <!-- start class org.apache.hadoop.mapred.InvalidJobConfException -->
- <class name="InvalidJobConfException" extends="java.io.IOException"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="InvalidJobConfException"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <constructor name="InvalidJobConfException" type="java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <doc>
- <![CDATA[This exception is thrown when jobconf misses some mendatory attributes
- or value of some attributes is invalid.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.InvalidJobConfException -->
- <!-- start class org.apache.hadoop.mapred.IsolationRunner -->
- <class name="IsolationRunner" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="IsolationRunner"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="main"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="args" type="java.lang.String[]"/>
- <exception name="ClassNotFoundException" type="java.lang.ClassNotFoundException"/>
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Run a single task
- @param args the first argument is the task directory]]>
- </doc>
- </method>
- </class>
- <!-- end class org.apache.hadoop.mapred.IsolationRunner -->
- <!-- start class org.apache.hadoop.mapred.JobClient -->
- <class name="JobClient" extends="org.apache.hadoop.conf.Configured"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapred.MRConstants"/>
- <implements name="org.apache.hadoop.util.Tool"/>
- <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="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="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="job" 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 job 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="submitJobInternal" return="org.apache.hadoop.mapred.RunningJob"
- 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="FileNotFoundException" type="java.io.FileNotFoundException"/>
- <exception name="ClassNotFoundException" type="java.lang.ClassNotFoundException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Internal method for submitting jobs to the system.
- @param job the configuration to submit
- @return a proxy object for the running job
- @throws FileNotFoundException
- @throws ClassNotFoundException
- @throws InterruptedException
- @throws IOException]]>
- </doc>
- </method>
- <method name="isJobDirValid" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobDirPath" type="org.apache.hadoop.fs.Path"/>
- <param name="fs" type="org.apache.hadoop.fs.FileSystem"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Checks if the job directory is clean and has all the required components
- for (re) starting the job]]>
- </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="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="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="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="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>
- <field name="NONE" type="org.apache.hadoop.mapred.JobClient.TaskStatusFilter"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="KILLED" type="org.apache.hadoop.mapred.JobClient.TaskStatusFilter"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="FAILED" type="org.apache.hadoop.mapred.JobClient.TaskStatusFilter"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="SUCCEEDED" type="org.apache.hadoop.mapred.JobClient.TaskStatusFilter"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="ALL" type="org.apache.hadoop.mapred.JobClient.TaskStatusFilter"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- </class>
- <!-- end class org.apache.hadoop.mapred.JobClient.TaskStatusFilter -->
- <!-- start class org.apache.hadoop.mapred.JobConf -->
- <class name="JobConf" extends="org.apache.hadoop.conf.Configuration"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link Configuration} instead">
- <constructor name="JobConf"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Construct a map/reduce job configuration.]]>
- </doc>
- </constructor>
- <constructor name="JobConf" type="java.lang.Class"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Construct a map/reduce job configuration.
-
- @param exampleClass a class whose containing jar is used as the job's jar.]]>
- </doc>
- </constructor>
- <constructor name="JobConf" type="org.apache.hadoop.conf.Configuration"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Construct a map/reduce job configuration.
-
- @param conf a Configuration whose settings will be inherited.]]>
- </doc>
- </constructor>
- <constructor name="JobConf" type="org.apache.hadoop.conf.Configuration, java.lang.Class"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Construct a map/reduce job configuration.
-
- @param conf a Configuration whose settings will be inherited.
- @param exampleClass a class whose containing jar is used as the job's jar.]]>
- </doc>
- </constructor>
- <constructor name="JobConf" type="java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Construct a map/reduce configuration.
- @param config a Configuration-format XML job description file.]]>
- </doc>
- </constructor>
- <constructor name="JobConf" type="org.apache.hadoop.fs.Path"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Construct a map/reduce configuration.
- @param config a Configuration-format XML job description file.]]>
- </doc>
- </constructor>
- <constructor name="JobConf" type="boolean"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[A new map/reduce configuration where the behavior of reading from the
- default resources can be turned off.
- <p/>
- If the parameter {@code loadDefaults} is false, the new instance
- will not load resources from the default files.
- @param loadDefaults specifies whether to load from the default files]]>
- </doc>
- </constructor>
- <method name="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="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"/>
- </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#mapred.min.split.size">
- mapred.min.split.size</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#mapred.tasktracker.reduce.tasks.maximum">
- mapred.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>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="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>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>
- <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>
- ${mapred.local.dir}/taskTracker/jobcache/$jobid/work/ </code>.
- This directory is exposed to the users through
- <code>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="getMaxVirtualMemoryForTask" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[The maximum amount of memory any task of this job will use. See
- {@link #MAPRED_TASK_MAXVMEM_PROPERTY}
-
- @return The maximum amount of memory any task of this job will use, in
- bytes.
- @see #setMaxVirtualMemoryForTask(long)]]>
- </doc>
- </method>
- <method name="setMaxVirtualMemoryForTask"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <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}
-
- @param vmem Maximum amount of virtual memory in bytes any task of this job
- can use.
- @see #getMaxVirtualMemoryForTask()]]>
- </doc>
- </method>
- <method name="getMaxPhysicalMemoryForTask" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[The maximum amount of physical memory any task of this job will use. See
- {@link #MAPRED_TASK_MAXPMEM_PROPERTY}
-
- @return The maximum amount of physical memory any task of this job will
- use, in bytes.
- @see #setMaxPhysicalMemoryForTask(long)]]>
- </doc>
- </method>
- <method name="setMaxPhysicalMemoryForTask"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="pmem" type="long"/>
- <doc>
- <![CDATA[Set the maximum amount of physical memory any task of this job can use. See
- {@link #MAPRED_TASK_MAXPMEM_PROPERTY}
-
- @param pmem Maximum amount of physical memory in bytes any task of this job
- can use.
- @see #getMaxPhysicalMemoryForTask()]]>
- </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[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>
- <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="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="MAPRED_TASK_DEFAULT_MAXVMEM_PROPERTY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Cluster-wide configuration to be set by the administrators that provides
- default amount of maximum virtual memory for job's tasks. This has to be
- set on both the JobTracker node for the sake of scheduling decisions and on
- the TaskTracker nodes for the sake of memory management.
-
- <p>
-
- If a job doesn't specify its virtual memory requirement by setting
- {@link #MAPRED_TASK_MAXVMEM_PROPERTY} to {@link #DISABLED_MEMORY_LIMIT},
- tasks are assured a memory limit set to this property. This property is
- disabled by default, and if not explicitly set to a valid value by the
- administrators and if a job doesn't specify its virtual memory
- requirements, the job's tasks will not be assured anything and may be
- killed by a TT that intends to control the total memory usage of the tasks
- via memory management functionality.
-
- <p>
-
- This value should in general be less than the cluster-wide configuration
- {@link #UPPER_LIMIT_ON_TASK_VMEM_PROPERTY} . If not or if it not set,
- TaskTracker's memory management may be disabled and a scheduler's memory
- based scheduling decisions will be affected. Please refer to the
- documentation of the configured scheduler to see how this property is used.]]>
- </doc>
- </field>
- <field name="MAPRED_TASK_MAXVMEM_PROPERTY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[The maximum amount of memory any task of this job will use.
-
- <p>
-
- This value will be used by TaskTrackers for monitoring the memory usage of
- tasks of this jobs. If a TaskTracker's memory management functionality is
- enabled, each task of this job will be allowed to use a maximum virtual
- memory specified by this property. If the task's memory usage goes over
- this value, the task will be failed by the TT. If not set, the cluster-wide
- configuration {@link #MAPRED_TASK_DEFAULT_MAXVMEM_PROPERTY} is used as the
- default value for memory requirements. If this property cascaded with
- {@link #MAPRED_TASK_DEFAULT_MAXVMEM_PROPERTY} becomes equal to -1, job's
- tasks will not be assured anything and may be killed by a TT that intends
- to control the total memory usage of the tasks via memory management
- functionality. If the memory management functionality is disabled on a TT,
- this value is ignored.
-
- <p>
-
- This value should also be not more than the cluster-wide configuration
- {@link #UPPER_LIMIT_ON_TASK_VMEM_PROPERTY} which has to be set by the site
- administrators.
-
- <p>
-
- This value may be used by schedulers that support scheduling based on job's
- memory requirements. In general, a task of this job will be scheduled on a
- TaskTracker only if the amount of virtual memory still unoccupied on the
- TaskTracker is greater than or equal to this value. But different
- schedulers can take different decisions. Please refer to the documentation
- of the scheduler being configured to see if it does memory based scheduling
- and if it does, how this property is used by that scheduler.
-
- @see #setMaxVirtualMemoryForTask(long)
- @see #getMaxVirtualMemoryForTask()]]>
- </doc>
- </field>
- <field name="MAPRED_TASK_MAXPMEM_PROPERTY" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[The maximum amount of physical memory any task of a job will use.
-
- <p>
-
- This value may be used by schedulers that support scheduling based on job's
- memory requirements. In general, a task of this job will be scheduled on a
- TaskTracker, only if the amount of physical memory still unoccupied on the
- TaskTracker is greater than or equal to this value. But different
- schedulers can take different decisions. Please refer to the documentation
- of the scheduler being configured to see how it does memory based
- scheduling and how this variable is used by that scheduler.
-
- @see #setMaxPhysicalMemoryForTask(long)
- @see #getMaxPhysicalMemoryForTask()]]>
- </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="not deprecated">
- <doc>
- <![CDATA[Cluster-wide configuration to be set by the site administrators that
- provides an upper limit on the maximum virtual memory that can be specified
- by a job. The job configuration {@link #MAPRED_TASK_MAXVMEM_PROPERTY} and
- the cluster-wide configuration
- {@link #MAPRED_TASK_DEFAULT_MAXVMEM_PROPERTY} should, by definition, be
- less than this value. If the job configuration
- {@link #MAPRED_TASK_DEFAULT_MAXVMEM_PROPERTY} is more than this value,
- depending on the scheduler being configured, the job may be rejected or the
- job configuration may just be ignored.
-
- <p>
-
- If it is not set on a TaskTracker, TaskTracker's memory management will be
- disabled.]]>
- </doc>
- </field>
- <doc>
- <![CDATA[A map/reduce job configuration.
-
- <p><code>JobConf</code> is the primary interface for a user to describe a
- map-reduce job to the Hadoop framework for execution. The framework tries to
- faithfully execute the job as-is described by <code>JobConf</code>, however:
- <ol>
- <li>
- Some configuration parameters might have been marked as
- <a href="{@docRoot}/org/apache/hadoop/conf/Configuration.html#FinalParams">
- final</a> by administrators and hence cannot be altered.
- </li>
- <li>
- While some job parameters are straight-forward to set
- (e.g. {@link #setNumReduceTasks(int)}), some parameters interact subtly
- rest of the framework and/or job-configuration and is relatively more
- complex for the user to control finely (e.g. {@link #setNumMapTasks(int)}).
- </li>
- </ol></p>
-
- <p><code>JobConf</code> typically specifies the {@link Mapper}, combiner
- (if any), {@link Partitioner}, {@link Reducer}, {@link InputFormat} and
- {@link OutputFormat} implementations to be used etc.
- <p>Optionally <code>JobConf</code> is used to specify other advanced facets
- of the job such as <code>Comparator</code>s to be used, files to be put in
- the {@link DistributedCache}, whether or not intermediate and/or job outputs
- are to be compressed (and how), debugability via user-provided scripts
- ( {@link #setMapDebugScript(String)}/{@link #setReduceDebugScript(String)}),
- for doing post-processing on task logs, task's stdout, stderr, syslog.
- and etc.</p>
-
- <p>Here is an example on how to configure a job via <code>JobConf</code>:</p>
- <p><blockquote><pre>
- // Create a new JobConf
- JobConf job = new JobConf(new Configuration(), MyJob.class);
-
- // Specify various job-specific parameters
- job.setJobName("myjob");
-
- FileInputFormat.setInputPaths(job, new Path("in"));
- FileOutputFormat.setOutputPath(job, new Path("out"));
-
- job.setMapperClass(MyJob.MyMapper.class);
- job.setCombinerClass(MyJob.MyReducer.class);
- job.setReducerClass(MyJob.MyReducer.class);
-
- job.setInputFormat(SequenceFileInputFormat.class);
- job.setOutputFormat(SequenceFileOutputFormat.class);
- </pre></blockquote></p>
-
- @see JobClient
- @see ClusterStatus
- @see Tool
- @see DistributedCache
- @deprecated Use {@link Configuration} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.JobConf -->
- <!-- start interface org.apache.hadoop.mapred.JobConfigurable -->
- <interface name="JobConfigurable" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <method name="configure"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[Initializes a new instance from a {@link JobConf}.
- @param job the configuration]]>
- </doc>
- </method>
- <doc>
- <![CDATA[That what may be configured.]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.JobConfigurable -->
- <!-- start class org.apache.hadoop.mapred.JobContext -->
- <class name="JobContext" extends="org.apache.hadoop.mapreduce.JobContext"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.JobContext} instead.">
- <method name="getJobConf" return="org.apache.hadoop.mapred.JobConf"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the job Configuration
-
- @return JobConf]]>
- </doc>
- </method>
- <method name="getProgressible" return="org.apache.hadoop.util.Progressable"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the progress mechanism for reporting progress.
-
- @return progress mechanism]]>
- </doc>
- </method>
- <doc>
- <![CDATA[@deprecated Use {@link org.apache.hadoop.mapreduce.JobContext} instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.JobContext -->
- <!-- start class org.apache.hadoop.mapred.JobEndNotifier -->
- <class name="JobEndNotifier" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="JobEndNotifier"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="startNotifier"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="stopNotifier"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="registerNotification"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobConf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="status" type="org.apache.hadoop.mapred.JobStatus"/>
- </method>
- <method name="localRunnerNotification"
- 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="status" type="org.apache.hadoop.mapred.JobStatus"/>
- </method>
- </class>
- <!-- end class org.apache.hadoop.mapred.JobEndNotifier -->
- <!-- start class org.apache.hadoop.mapred.JobHistory -->
- <class name="JobHistory" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="JobHistory"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="init" 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="hostname" type="java.lang.String"/>
- <param name="jobTrackerStartTime" type="long"/>
- <doc>
- <![CDATA[Initialize JobHistory files.
- @param conf Jobconf of the job tracker.
- @param hostname jobtracker's hostname
- @param jobTrackerStartTime jobtracker's start time
- @return true if intialized properly
- false otherwise]]>
- </doc>
- </method>
- <method name="parseHistoryFromFS"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="path" type="java.lang.String"/>
- <param name="l" type="org.apache.hadoop.mapred.JobHistory.Listener"/>
- <param name="fs" type="org.apache.hadoop.fs.FileSystem"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Parses history file and invokes Listener.handle() for
- each line of history. It can be used for looking through history
- files for specific items without having to keep whole history in memory.
- @param path path to history file
- @param l Listener for history events
- @param fs FileSystem where history file is present
- @throws IOException]]>
- </doc>
- </method>
- <method name="isDisableHistory" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns history disable status. by default history is enabled so this
- method returns false.
- @return true if history logging is disabled, false otherwise.]]>
- </doc>
- </method>
- <method name="setDisableHistory"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="disableHistory" type="boolean"/>
- <doc>
- <![CDATA[Enable/disable history logging. Default value is false, so history
- is enabled by default.
- @param disableHistory true if history should be disabled, false otherwise.]]>
- </doc>
- </method>
- <method name="getTaskLogsUrl" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="attempt" type="org.apache.hadoop.mapred.JobHistory.TaskAttempt"/>
- <doc>
- <![CDATA[Return the TaskLogsUrl of a particular TaskAttempt
-
- @param attempt
- @return the taskLogsUrl. null if http-port or tracker-name or
- task-attempt-id are unavailable.]]>
- </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="JOB_NAME_TRIM_LENGTH" type="int"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[Provides methods for writing to and reading from job history.
- Job History works in an append mode, JobHistory and its inner classes provide methods
- to log job events.
-
- JobHistory is split into multiple files, format of each file is plain text where each line
- is of the format [type (key=value)*], where type identifies the type of the record.
- Type maps to UID of one of the inner classes of this class.
-
- Job history is maintained in a master index which contains star/stop times of all jobs with
- a few other job level properties. Apart from this each job's history is maintained in a seperate history
- file. name of job history files follows the format jobtrackerId_jobid
-
- For parsing the job history it supports a listener based interface where each line is parsed
- and passed to listener. The listener can create an object model of history or look for specific
- events and discard rest of the history.
-
- CHANGE LOG :
- Version 0 : The history has the following format :
- TAG KEY1="VALUE1" KEY2="VALUE2" and so on.
- TAG can be Job, Task, MapAttempt or ReduceAttempt.
- Note that a '"' is the line delimiter.
- Version 1 : Changes the line delimiter to '.'
- Values are now escaped for unambiguous parsing.
- Added the Meta tag to store version info.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.JobHistory -->
- <!-- start class org.apache.hadoop.mapred.JobHistory.HistoryCleaner -->
- <class name="JobHistory.HistoryCleaner" extends="java.lang.Object"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="java.lang.Runnable"/>
- <constructor name="JobHistory.HistoryCleaner"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="run"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Cleans up history data.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Delete history files older than one month. Update master index and remove all
- jobs older than one month. Also if a job tracker has no jobs in last one month
- remove reference to the job tracker.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.JobHistory.HistoryCleaner -->
- <!-- start class org.apache.hadoop.mapred.JobHistory.JobInfo -->
- <class name="JobHistory.JobInfo" extends="org.apache.hadoop.mapred.JobHistory.KeyValuePair"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="JobHistory.JobInfo" type="java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Create new JobInfo]]>
- </doc>
- </constructor>
- <method name="getAllTasks" return="java.util.Map"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns all map and reduce tasks <taskid-Task>.]]>
- </doc>
- </method>
- <method name="getLocalJobFilePath" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobId" type="org.apache.hadoop.mapred.JobID"/>
- <doc>
- <![CDATA[Get the path of the locally stored job file
- @param jobId id of the job
- @return the path of the job file on the local file system]]>
- </doc>
- </method>
- <method name="encodeJobHistoryFilePath" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="logFile" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Helper function to encode the URL of the path of the job-history
- log file.
-
- @param logFile path of the job-history file
- @return URL encoded path
- @throws IOException]]>
- </doc>
- </method>
- <method name="encodeJobHistoryFileName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="logFileName" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Helper function to encode the URL of the filename of the job-history
- log file.
-
- @param logFileName file name of the job-history file
- @return URL encoded filename
- @throws IOException]]>
- </doc>
- </method>
- <method name="decodeJobHistoryFileName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="logFileName" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Helper function to decode the URL of the filename of the job-history
- log file.
-
- @param logFileName file name of the job-history file
- @return URL decoded filename
- @throws IOException]]>
- </doc>
- </method>
- <method name="getUserName" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobConf" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[Get the user name from the job conf]]>
- </doc>
- </method>
- <method name="getJobHistoryLogLocation" return="org.apache.hadoop.fs.Path"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="logFileName" type="java.lang.String"/>
- <doc>
- <![CDATA[Get the job history file path given the history filename]]>
- </doc>
- </method>
- <method name="getJobHistoryLogLocationForUser" return="org.apache.hadoop.fs.Path"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="logFileName" type="java.lang.String"/>
- <param name="jobConf" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[Get the user job history file path]]>
- </doc>
- </method>
- <method name="getJobHistoryFileName" return="java.lang.String"
- abstract="false" native="false" synchronized="true"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobConf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="id" type="org.apache.hadoop.mapred.JobID"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Recover the job history filename from the history folder.
- Uses the following pattern
- $jt-hostname_[0-9]*_$job-id_$user-$job-name*
- @param jobConf the job conf
- @param id job id]]>
- </doc>
- </method>
- <method name="recoverJobHistoryFile" return="org.apache.hadoop.fs.Path"
- abstract="false" native="false" synchronized="true"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="logFilePath" type="org.apache.hadoop.fs.Path"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Selects one of the two files generated as a part of recovery.
- The thumb rule is that always select the oldest file.
- This call makes sure that only one file is left in the end.
- @param conf job conf
- @param logFilePath Path of the log file
- @throws IOException]]>
- </doc>
- </method>
- <method name="logSubmitted"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobId" type="org.apache.hadoop.mapred.JobID"/>
- <param name="jobConf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="jobConfPath" type="java.lang.String"/>
- <param name="submitTime" type="long"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Log job submitted event to history. Creates a new file in history
- for the job. if history file creation fails, it disables history
- for all other events.
- @param jobId job id assigned by job tracker.
- @param jobConf job conf of the job
- @param jobConfPath path to job conf xml file in HDFS.
- @param submitTime time when job tracker received the job
- @throws IOException]]>
- </doc>
- </method>
- <method name="logInited"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobId" type="org.apache.hadoop.mapred.JobID"/>
- <param name="startTime" type="long"/>
- <param name="totalMaps" type="int"/>
- <param name="totalReduces" type="int"/>
- <doc>
- <![CDATA[Logs launch time of job.
-
- @param jobId job id, assigned by jobtracker.
- @param startTime start time of job.
- @param totalMaps total maps assigned by jobtracker.
- @param totalReduces total reduces.]]>
- </doc>
- </method>
- <method name="logStarted"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="Use {@link #logInited(JobID, long, int, int)} and
- {@link #logStarted(JobID)}">
- <param name="jobId" type="org.apache.hadoop.mapred.JobID"/>
- <param name="startTime" type="long"/>
- <param name="totalMaps" type="int"/>
- <param name="totalReduces" type="int"/>
- <doc>
- <![CDATA[Logs the job as RUNNING.
- @param jobId job id, assigned by jobtracker.
- @param startTime start time of job.
- @param totalMaps total maps assigned by jobtracker.
- @param totalReduces total reduces.
- @deprecated Use {@link #logInited(JobID, long, int, int)} and
- {@link #logStarted(JobID)}]]>
- </doc>
- </method>
- <method name="logStarted"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobId" type="org.apache.hadoop.mapred.JobID"/>
- <doc>
- <![CDATA[Logs job as running
- @param jobId job id, assigned by jobtracker.]]>
- </doc>
- </method>
- <method name="logFinished"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobId" type="org.apache.hadoop.mapred.JobID"/>
- <param name="finishTime" type="long"/>
- <param name="finishedMaps" type="int"/>
- <param name="finishedReduces" type="int"/>
- <param name="failedMaps" type="int"/>
- <param name="failedReduces" type="int"/>
- <param name="counters" type="org.apache.hadoop.mapred.Counters"/>
- <doc>
- <![CDATA[Log job finished. closes the job file in history.
- @param jobId job id, assigned by jobtracker.
- @param finishTime finish time of job in ms.
- @param finishedMaps no of maps successfully finished.
- @param finishedReduces no of reduces finished sucessfully.
- @param failedMaps no of failed map tasks.
- @param failedReduces no of failed reduce tasks.
- @param counters the counters from the job]]>
- </doc>
- </method>
- <method name="logFailed"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobid" type="org.apache.hadoop.mapred.JobID"/>
- <param name="timestamp" type="long"/>
- <param name="finishedMaps" type="int"/>
- <param name="finishedReduces" type="int"/>
- <doc>
- <![CDATA[Logs job failed event. Closes the job history log file.
- @param jobid job id
- @param timestamp time when job failure was detected in ms.
- @param finishedMaps no finished map tasks.
- @param finishedReduces no of finished reduce tasks.]]>
- </doc>
- </method>
- <method name="logKilled"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobid" type="org.apache.hadoop.mapred.JobID"/>
- <param name="timestamp" type="long"/>
- <param name="finishedMaps" type="int"/>
- <param name="finishedReduces" type="int"/>
- <doc>
- <![CDATA[Logs job killed event. Closes the job history log file.
-
- @param jobid
- job id
- @param timestamp
- time when job killed was issued in ms.
- @param finishedMaps
- no finished map tasks.
- @param finishedReduces
- no of finished reduce tasks.]]>
- </doc>
- </method>
- <method name="logJobPriority"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobid" type="org.apache.hadoop.mapred.JobID"/>
- <param name="priority" type="org.apache.hadoop.mapred.JobPriority"/>
- <doc>
- <![CDATA[Log job's priority.
- @param jobid job id
- @param priority Jobs priority]]>
- </doc>
- </method>
- <method name="logJobInfo"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="Use {@link #logJobInfo(JobID, long, long)} instead.">
- <param name="jobid" type="org.apache.hadoop.mapred.JobID"/>
- <param name="submitTime" type="long"/>
- <param name="launchTime" type="long"/>
- <param name="restartCount" type="int"/>
- <doc>
- <![CDATA[Log job's submit-time/launch-time
- @param jobid job id
- @param submitTime job's submit time
- @param launchTime job's launch time
- @param restartCount number of times the job got restarted
- @deprecated Use {@link #logJobInfo(JobID, long, long)} instead.]]>
- </doc>
- </method>
- <method name="logJobInfo"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobid" type="org.apache.hadoop.mapred.JobID"/>
- <param name="submitTime" type="long"/>
- <param name="launchTime" type="long"/>
- </method>
- <doc>
- <![CDATA[Helper class for logging or reading back events related to job start, finish or failure.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.JobHistory.JobInfo -->
- <!-- start class org.apache.hadoop.mapred.JobHistory.Keys -->
- <class name="JobHistory.Keys" extends="java.lang.Enum"
- abstract="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <method name="values" return="org.apache.hadoop.mapred.JobHistory.Keys[]"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="valueOf" return="org.apache.hadoop.mapred.JobHistory.Keys"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- </method>
- <field name="JOBTRACKERID" type="org.apache.hadoop.mapred.JobHistory.Keys"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="START_TIME" type="org.apache.hadoop.mapred.JobHistory.Keys"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="FINISH_TIME" type="org.apache.hadoop.mapred.JobHistory.Keys"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="JOBID" type="org.apache.hadoop.mapred.JobHistory.Keys"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="JOBNAME" type="org.apache.hadoop.mapred.JobHistory.Keys"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="USER" type="org.apache.hadoop.mapred.JobHistory.Keys"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="JOBCONF" type="org.apache.hadoop.mapred.JobHistory.Keys"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="SUBMIT_TIME" type="org.apache.hadoop.mapred.JobHistory.Keys"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="LAUNCH_TIME" type="org.apache.hadoop.mapred.JobHistory.Keys"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="TOTAL_MAPS" type="org.apache.hadoop.mapred.JobHistory.Keys"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="TOTAL_REDUCES" type="org.apache.hadoop.mapred.JobHistory.Keys"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="FAILED_MAPS" type="org.apache.hadoop.mapred.JobHistory.Keys"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="FAILED_REDUCES" type="org.apache.hadoop.mapred.JobHistory.Keys"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="FINISHED_MAPS" type="org.apache.hadoop.mapred.JobHistory.Keys"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="FINISHED_REDUCES" type="org.apache.hadoop.mapred.JobHistory.Keys"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="JOB_STATUS" type="org.apache.hadoop.mapred.JobHistory.Keys"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="TASKID" type="org.apache.hadoop.mapred.JobHistory.Keys"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="HOSTNAME" type="org.apache.hadoop.mapred.JobHistory.Keys"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="TASK_TYPE" type="org.apache.hadoop.mapred.JobHistory.Keys"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="ERROR" type="org.apache.hadoop.mapred.JobHistory.Keys"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="TASK_ATTEMPT_ID" type="org.apache.hadoop.mapred.JobHistory.Keys"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="TASK_STATUS" type="org.apache.hadoop.mapred.JobHistory.Keys"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="COPY_PHASE" type="org.apache.hadoop.mapred.JobHistory.Keys"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="SORT_PHASE" type="org.apache.hadoop.mapred.JobHistory.Keys"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="REDUCE_PHASE" type="org.apache.hadoop.mapred.JobHistory.Keys"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="SHUFFLE_FINISHED" type="org.apache.hadoop.mapred.JobHistory.Keys"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="SORT_FINISHED" type="org.apache.hadoop.mapred.JobHistory.Keys"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="COUNTERS" type="org.apache.hadoop.mapred.JobHistory.Keys"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="SPLITS" type="org.apache.hadoop.mapred.JobHistory.Keys"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="JOB_PRIORITY" type="org.apache.hadoop.mapred.JobHistory.Keys"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="HTTP_PORT" type="org.apache.hadoop.mapred.JobHistory.Keys"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="TRACKER_NAME" type="org.apache.hadoop.mapred.JobHistory.Keys"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="STATE_STRING" type="org.apache.hadoop.mapred.JobHistory.Keys"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="VERSION" type="org.apache.hadoop.mapred.JobHistory.Keys"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[Job history files contain key="value" pairs, where keys belong to this enum.
- It acts as a global namespace for all keys.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.JobHistory.Keys -->
- <!-- start interface org.apache.hadoop.mapred.JobHistory.Listener -->
- <interface name="JobHistory.Listener" abstract="true"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <method name="handle"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="recType" type="org.apache.hadoop.mapred.JobHistory.RecordTypes"/>
- <param name="values" type="java.util.Map"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Callback method for history parser.
- @param recType type of record, which is the first entry in the line.
- @param values a map of key-value pairs as thry appear in history.
- @throws IOException]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Callback interface for reading back log events from JobHistory. This interface
- should be implemented and passed to JobHistory.parseHistory()]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.JobHistory.Listener -->
- <!-- start class org.apache.hadoop.mapred.JobHistory.MapAttempt -->
- <class name="JobHistory.MapAttempt" extends="org.apache.hadoop.mapred.JobHistory.TaskAttempt"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="JobHistory.MapAttempt"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="logStarted"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="Use
- {@link #logStarted(TaskAttemptID, long, String, int, String)}">
- <param name="taskAttemptId" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <param name="startTime" type="long"/>
- <param name="hostName" type="java.lang.String"/>
- <doc>
- <![CDATA[Log start time of this map task attempt.
- @param taskAttemptId task attempt id
- @param startTime start time of task attempt as reported by task tracker.
- @param hostName host name of the task attempt.
- @deprecated Use
- {@link #logStarted(TaskAttemptID, long, String, int, String)}]]>
- </doc>
- </method>
- <method name="logStarted"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskAttemptId" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <param name="startTime" type="long"/>
- <param name="trackerName" type="java.lang.String"/>
- <param name="httpPort" type="int"/>
- <param name="taskType" type="java.lang.String"/>
- <doc>
- <![CDATA[Log start time of this map task attempt.
-
- @param taskAttemptId task attempt id
- @param startTime start time of task attempt as reported by task tracker.
- @param trackerName name of the tracker executing the task attempt.
- @param httpPort http port of the task tracker executing the task attempt
- @param taskType Whether the attempt is cleanup or setup or map]]>
- </doc>
- </method>
- <method name="logFinished"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="Use
- {@link #logFinished(TaskAttemptID, long, String, String, String, Counters)}">
- <param name="taskAttemptId" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <param name="finishTime" type="long"/>
- <param name="hostName" type="java.lang.String"/>
- <doc>
- <![CDATA[Log finish time of map task attempt.
- @param taskAttemptId task attempt id
- @param finishTime finish time
- @param hostName host name
- @deprecated Use
- {@link #logFinished(TaskAttemptID, long, String, String, String, Counters)}]]>
- </doc>
- </method>
- <method name="logFinished"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskAttemptId" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <param name="finishTime" type="long"/>
- <param name="hostName" type="java.lang.String"/>
- <param name="taskType" type="java.lang.String"/>
- <param name="stateString" type="java.lang.String"/>
- <param name="counter" type="org.apache.hadoop.mapred.Counters"/>
- <doc>
- <![CDATA[Log finish time of map task attempt.
-
- @param taskAttemptId task attempt id
- @param finishTime finish time
- @param hostName host name
- @param taskType Whether the attempt is cleanup or setup or map
- @param stateString state string of the task attempt
- @param counter counters of the task attempt]]>
- </doc>
- </method>
- <method name="logFailed"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="Use
- {@link #logFailed(TaskAttemptID, long, String, String, String)}">
- <param name="taskAttemptId" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <param name="timestamp" type="long"/>
- <param name="hostName" type="java.lang.String"/>
- <param name="error" type="java.lang.String"/>
- <doc>
- <![CDATA[Log task attempt failed event.
- @param taskAttemptId task attempt id
- @param timestamp timestamp
- @param hostName hostname of this task attempt.
- @param error error message if any for this task attempt.
- @deprecated Use
- {@link #logFailed(TaskAttemptID, long, String, String, String)}]]>
- </doc>
- </method>
- <method name="logFailed"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskAttemptId" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <param name="timestamp" type="long"/>
- <param name="hostName" type="java.lang.String"/>
- <param name="error" type="java.lang.String"/>
- <param name="taskType" type="java.lang.String"/>
- <doc>
- <![CDATA[Log task attempt failed event.
-
- @param taskAttemptId task attempt id
- @param timestamp timestamp
- @param hostName hostname of this task attempt.
- @param error error message if any for this task attempt.
- @param taskType Whether the attempt is cleanup or setup or map]]>
- </doc>
- </method>
- <method name="logKilled"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="Use
- {@link #logKilled(TaskAttemptID, long, String, String, String)}">
- <param name="taskAttemptId" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <param name="timestamp" type="long"/>
- <param name="hostName" type="java.lang.String"/>
- <param name="error" type="java.lang.String"/>
- <doc>
- <![CDATA[Log task attempt killed event.
- @param taskAttemptId task attempt id
- @param timestamp timestamp
- @param hostName hostname of this task attempt.
- @param error error message if any for this task attempt.
- @deprecated Use
- {@link #logKilled(TaskAttemptID, long, String, String, String)}]]>
- </doc>
- </method>
- <method name="logKilled"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskAttemptId" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <param name="timestamp" type="long"/>
- <param name="hostName" type="java.lang.String"/>
- <param name="error" type="java.lang.String"/>
- <param name="taskType" type="java.lang.String"/>
- <doc>
- <![CDATA[Log task attempt killed event.
-
- @param taskAttemptId task attempt id
- @param timestamp timestamp
- @param hostName hostname of this task attempt.
- @param error error message if any for this task attempt.
- @param taskType Whether the attempt is cleanup or setup or map]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Helper class for logging or reading back events related to start, finish or failure of
- a Map Attempt on a node.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.JobHistory.MapAttempt -->
- <!-- start class org.apache.hadoop.mapred.JobHistory.RecordTypes -->
- <class name="JobHistory.RecordTypes" extends="java.lang.Enum"
- abstract="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <method name="values" return="org.apache.hadoop.mapred.JobHistory.RecordTypes[]"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="valueOf" return="org.apache.hadoop.mapred.JobHistory.RecordTypes"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- </method>
- <field name="Jobtracker" type="org.apache.hadoop.mapred.JobHistory.RecordTypes"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="Job" type="org.apache.hadoop.mapred.JobHistory.RecordTypes"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="Task" type="org.apache.hadoop.mapred.JobHistory.RecordTypes"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="MapAttempt" type="org.apache.hadoop.mapred.JobHistory.RecordTypes"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="ReduceAttempt" type="org.apache.hadoop.mapred.JobHistory.RecordTypes"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="Meta" type="org.apache.hadoop.mapred.JobHistory.RecordTypes"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[Record types are identifiers for each line of log in history files.
- A record type appears as the first token in a single line of log.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.JobHistory.RecordTypes -->
- <!-- start class org.apache.hadoop.mapred.JobHistory.ReduceAttempt -->
- <class name="JobHistory.ReduceAttempt" extends="org.apache.hadoop.mapred.JobHistory.TaskAttempt"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="JobHistory.ReduceAttempt"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="logStarted"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="Use
- {@link #logStarted(TaskAttemptID, long, String, int, String)}">
- <param name="taskAttemptId" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <param name="startTime" type="long"/>
- <param name="hostName" type="java.lang.String"/>
- <doc>
- <![CDATA[Log start time of Reduce task attempt.
- @param taskAttemptId task attempt id
- @param startTime start time
- @param hostName host name
- @deprecated Use
- {@link #logStarted(TaskAttemptID, long, String, int, String)}]]>
- </doc>
- </method>
- <method name="logStarted"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskAttemptId" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <param name="startTime" type="long"/>
- <param name="trackerName" type="java.lang.String"/>
- <param name="httpPort" type="int"/>
- <param name="taskType" type="java.lang.String"/>
- <doc>
- <![CDATA[Log start time of Reduce task attempt.
-
- @param taskAttemptId task attempt id
- @param startTime start time
- @param trackerName tracker name
- @param httpPort the http port of the tracker executing the task attempt
- @param taskType Whether the attempt is cleanup or setup or reduce]]>
- </doc>
- </method>
- <method name="logFinished"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="Use
- {@link #logFinished(TaskAttemptID, long, long, long, String, String, String, Counters)}">
- <param name="taskAttemptId" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <param name="shuffleFinished" type="long"/>
- <param name="sortFinished" type="long"/>
- <param name="finishTime" type="long"/>
- <param name="hostName" type="java.lang.String"/>
- <doc>
- <![CDATA[Log finished event of this task.
- @param taskAttemptId task attempt id
- @param shuffleFinished shuffle finish time
- @param sortFinished sort finish time
- @param finishTime finish time of task
- @param hostName host name where task attempt executed
- @deprecated Use
- {@link #logFinished(TaskAttemptID, long, long, long, String, String, String, Counters)}]]>
- </doc>
- </method>
- <method name="logFinished"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskAttemptId" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <param name="shuffleFinished" type="long"/>
- <param name="sortFinished" type="long"/>
- <param name="finishTime" type="long"/>
- <param name="hostName" type="java.lang.String"/>
- <param name="taskType" type="java.lang.String"/>
- <param name="stateString" type="java.lang.String"/>
- <param name="counter" type="org.apache.hadoop.mapred.Counters"/>
- <doc>
- <![CDATA[Log finished event of this task.
-
- @param taskAttemptId task attempt id
- @param shuffleFinished shuffle finish time
- @param sortFinished sort finish time
- @param finishTime finish time of task
- @param hostName host name where task attempt executed
- @param taskType Whether the attempt is cleanup or setup or reduce
- @param stateString the state string of the attempt
- @param counter counters of the attempt]]>
- </doc>
- </method>
- <method name="logFailed"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="Use
- {@link #logFailed(TaskAttemptID, long, String, String, String)}">
- <param name="taskAttemptId" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <param name="timestamp" type="long"/>
- <param name="hostName" type="java.lang.String"/>
- <param name="error" type="java.lang.String"/>
- <doc>
- <![CDATA[Log failed reduce task attempt.
- @param taskAttemptId task attempt id
- @param timestamp time stamp when task failed
- @param hostName host name of the task attempt.
- @param error error message of the task.
- @deprecated Use
- {@link #logFailed(TaskAttemptID, long, String, String, String)}]]>
- </doc>
- </method>
- <method name="logFailed"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskAttemptId" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <param name="timestamp" type="long"/>
- <param name="hostName" type="java.lang.String"/>
- <param name="error" type="java.lang.String"/>
- <param name="taskType" type="java.lang.String"/>
- <doc>
- <![CDATA[Log failed reduce task attempt.
-
- @param taskAttemptId task attempt id
- @param timestamp time stamp when task failed
- @param hostName host name of the task attempt.
- @param error error message of the task.
- @param taskType Whether the attempt is cleanup or setup or reduce]]>
- </doc>
- </method>
- <method name="logKilled"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="Use
- {@link #logKilled(TaskAttemptID, long, String, String, String)}">
- <param name="taskAttemptId" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <param name="timestamp" type="long"/>
- <param name="hostName" type="java.lang.String"/>
- <param name="error" type="java.lang.String"/>
- <doc>
- <![CDATA[Log killed reduce task attempt.
- @param taskAttemptId task attempt id
- @param timestamp time stamp when task failed
- @param hostName host name of the task attempt.
- @param error error message of the task.
- @deprecated Use
- {@link #logKilled(TaskAttemptID, long, String, String, String)}]]>
- </doc>
- </method>
- <method name="logKilled"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskAttemptId" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <param name="timestamp" type="long"/>
- <param name="hostName" type="java.lang.String"/>
- <param name="error" type="java.lang.String"/>
- <param name="taskType" type="java.lang.String"/>
- <doc>
- <![CDATA[Log killed reduce task attempt.
-
- @param taskAttemptId task attempt id
- @param timestamp time stamp when task failed
- @param hostName host name of the task attempt.
- @param error error message of the task.
- @param taskType Whether the attempt is cleanup or setup or reduce]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Helper class for logging or reading back events related to start, finish or failure of
- a Map Attempt on a node.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.JobHistory.ReduceAttempt -->
- <!-- start class org.apache.hadoop.mapred.JobHistory.Task -->
- <class name="JobHistory.Task" extends="org.apache.hadoop.mapred.JobHistory.KeyValuePair"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="JobHistory.Task"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="logStarted"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskId" type="org.apache.hadoop.mapred.TaskID"/>
- <param name="taskType" type="java.lang.String"/>
- <param name="startTime" type="long"/>
- <param name="splitLocations" type="java.lang.String"/>
- <doc>
- <![CDATA[Log start time of task (TIP).
- @param taskId task id
- @param taskType MAP or REDUCE
- @param startTime startTime of tip.]]>
- </doc>
- </method>
- <method name="logFinished"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskId" type="org.apache.hadoop.mapred.TaskID"/>
- <param name="taskType" type="java.lang.String"/>
- <param name="finishTime" type="long"/>
- <param name="counters" type="org.apache.hadoop.mapred.Counters"/>
- <doc>
- <![CDATA[Log finish time of task.
- @param taskId task id
- @param taskType MAP or REDUCE
- @param finishTime finish timeof task in ms]]>
- </doc>
- </method>
- <method name="logUpdates"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskId" type="org.apache.hadoop.mapred.TaskID"/>
- <param name="finishTime" type="long"/>
- <doc>
- <![CDATA[Update the finish time of task.
- @param taskId task id
- @param finishTime finish time of task in ms]]>
- </doc>
- </method>
- <method name="logFailed"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskId" type="org.apache.hadoop.mapred.TaskID"/>
- <param name="taskType" type="java.lang.String"/>
- <param name="time" type="long"/>
- <param name="error" type="java.lang.String"/>
- <doc>
- <![CDATA[Log job failed event.
- @param taskId task id
- @param taskType MAP or REDUCE.
- @param time timestamp when job failed detected.
- @param error error message for failure.]]>
- </doc>
- </method>
- <method name="logFailed"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskId" type="org.apache.hadoop.mapred.TaskID"/>
- <param name="taskType" type="java.lang.String"/>
- <param name="time" type="long"/>
- <param name="error" type="java.lang.String"/>
- <param name="failedDueToAttempt" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <doc>
- <![CDATA[@param failedDueToAttempt The attempt that caused the failure, if any]]>
- </doc>
- </method>
- <method name="getTaskAttempts" return="java.util.Map"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns all task attempts for this task. <task attempt id - TaskAttempt>]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Helper class for logging or reading back events related to Task's start, finish or failure.
- All events logged by this class are logged in a separate file per job in
- job tracker history. These events map to TIPs in jobtracker.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.JobHistory.Task -->
- <!-- start class org.apache.hadoop.mapred.JobHistory.TaskAttempt -->
- <class name="JobHistory.TaskAttempt" extends="org.apache.hadoop.mapred.JobHistory.Task"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="JobHistory.TaskAttempt"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <doc>
- <![CDATA[Base class for Map and Reduce TaskAttempts.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.JobHistory.TaskAttempt -->
- <!-- start class org.apache.hadoop.mapred.JobHistory.Values -->
- <class name="JobHistory.Values" extends="java.lang.Enum"
- abstract="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <method name="values" return="org.apache.hadoop.mapred.JobHistory.Values[]"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="valueOf" return="org.apache.hadoop.mapred.JobHistory.Values"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- </method>
- <field name="SUCCESS" type="org.apache.hadoop.mapred.JobHistory.Values"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="FAILED" type="org.apache.hadoop.mapred.JobHistory.Values"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="KILLED" type="org.apache.hadoop.mapred.JobHistory.Values"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="MAP" type="org.apache.hadoop.mapred.JobHistory.Values"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="REDUCE" type="org.apache.hadoop.mapred.JobHistory.Values"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="CLEANUP" type="org.apache.hadoop.mapred.JobHistory.Values"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="RUNNING" type="org.apache.hadoop.mapred.JobHistory.Values"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="PREP" type="org.apache.hadoop.mapred.JobHistory.Values"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="SETUP" type="org.apache.hadoop.mapred.JobHistory.Values"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <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.mapred.JobHistory.Values -->
- <!-- 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>
- <field name="VERY_HIGH" type="org.apache.hadoop.mapred.JobPriority"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="HIGH" type="org.apache.hadoop.mapred.JobPriority"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="NORMAL" type="org.apache.hadoop.mapred.JobPriority"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="LOW" type="org.apache.hadoop.mapred.JobPriority"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="VERY_LOW" type="org.apache.hadoop.mapred.JobPriority"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <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.JobProfile -->
- <class name="JobProfile" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.io.Writable"/>
- <constructor name="JobProfile"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Construct an empty {@link JobProfile}.]]>
- </doc>
- </constructor>
- <constructor name="JobProfile" type="java.lang.String, org.apache.hadoop.mapreduce.JobID, java.lang.String, java.lang.String, java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Construct a {@link JobProfile} the userid, jobid,
- job config-file, job-details url and job name.
-
- @param user userid of the person who submitted the job.
- @param jobid id of the job.
- @param jobFile job configuration file.
- @param url link to the web-ui for details of the job.
- @param name user-specified job name.]]>
- </doc>
- </constructor>
- <constructor name="JobProfile" type="java.lang.String, org.apache.hadoop.mapreduce.JobID, java.lang.String, java.lang.String, java.lang.String, java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Construct a {@link JobProfile} the userid, jobid,
- job config-file, job-details url and job name.
-
- @param user userid of the person who submitted the job.
- @param jobid id of the job.
- @param jobFile job configuration file.
- @param url link to the web-ui for details of the job.
- @param name user-specified job name.
- @param queueName name of the queue to which the job is submitted]]>
- </doc>
- </constructor>
- <constructor name="JobProfile" type="java.lang.String, java.lang.String, java.lang.String, java.lang.String, java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="use JobProfile(String, JobID, String, String, String) instead">
- <doc>
- <![CDATA[@deprecated use JobProfile(String, JobID, String, String, String) instead]]>
- </doc>
- </constructor>
- <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 id.]]>
- </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[Get the job id.]]>
- </doc>
- </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="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="getURL" return="java.net.URL"
- abstract="false" native="false" synchronized="false"
- 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="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="getQueueName" 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 queue to which the job is submitted.
- @return name of the queue.]]>
- </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[A JobProfile is a MapReduce primitive. Tracks a job,
- whether living or dead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.JobProfile -->
- <!-- start class org.apache.hadoop.mapred.JobQueueInfo -->
- <class name="JobQueueInfo" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.io.Writable"/>
- <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="public"
- 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="public"
- 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="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.mapred.JobQueueInfo -->
- <!-- start class org.apache.hadoop.mapred.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.mapred.JobID, float, float, float, int"
- 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]]>
- </doc>
- </constructor>
- <constructor name="JobStatus" type="org.apache.hadoop.mapred.JobID, float, float, int"
- 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]]>
- </doc>
- </constructor>
- <constructor name="JobStatus" type="org.apache.hadoop.mapred.JobID, float, float, float, int, org.apache.hadoop.mapred.JobPriority"
- 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.]]>
- </doc>
- </constructor>
- <constructor name="JobStatus" type="org.apache.hadoop.mapred.JobID, float, float, float, float, int, org.apache.hadoop.mapred.JobPriority"
- 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.]]>
- </doc>
- </constructor>
- <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="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>
- <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="setRunState"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="state" type="int"/>
- <doc>
- <![CDATA[Change the current run 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="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="setSchedulingInfo"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- 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="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="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="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>
- <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.JobTracker -->
- <class name="JobTracker" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapred.MRConstants"/>
- <implements name="org.apache.hadoop.mapred.InterTrackerProtocol"/>
- <implements name="org.apache.hadoop.mapred.JobSubmissionProtocol"/>
- <implements name="org.apache.hadoop.mapred.TaskTrackerManager"/>
- <implements name="org.apache.hadoop.security.authorize.RefreshAuthorizationPolicyProtocol"/>
- <method name="startTracker" return="org.apache.hadoop.mapred.JobTracker"
- 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"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Start the JobTracker with given configuration.
-
- The conf will be modified to reflect the actual ports on which
- the JobTracker is up and running if the user passes the port as
- <code>zero</code>.
-
- @param conf configuration for the JobTracker.
- @throws IOException]]>
- </doc>
- </method>
- <method name="stopTracker"
- 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="getProtocolVersion" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="protocol" type="java.lang.String"/>
- <param name="clientVersion" type="long"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="hasRestarted" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Whether the JT has restarted]]>
- </doc>
- </method>
- <method name="hasRecovered" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Whether the JT has recovered upon restart]]>
- </doc>
- </method>
- <method name="getRecoveryDuration" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[How long the jobtracker took to recover from restart.]]>
- </doc>
- </method>
- <method name="getInstrumentationClass" 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.conf.Configuration"/>
- </method>
- <method name="setInstrumentationClass"
- 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="t" type="java.lang.Class"/>
- </method>
- <method name="getAddress" return="java.net.InetSocketAddress"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- </method>
- <method name="offerService"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Run forever]]>
- </doc>
- </method>
- <method name="getTotalSubmissions" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getJobTrackerMachine" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getTrackerIdentifier" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the unique identifier (ie. timestamp) of this job tracker start.
- @return a string with a unique identifier]]>
- </doc>
- </method>
- <method name="getTrackerPort" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getInfoPort" return="int"
- 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="runningJobs" return="java.util.Vector"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getRunningJobs" return="java.util.List"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Version that is called from a timer thread, and therefore needs to be
- careful to synchronize.]]>
- </doc>
- </method>
- <method name="failedJobs" return="java.util.Vector"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="completedJobs" return="java.util.Vector"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="taskTrackers" return="java.util.Collection"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get all the task trackers in the cluster
-
- @return {@link Collection} of {@link TaskTrackerStatus}]]>
- </doc>
- </method>
- <method name="activeTaskTrackers" return="java.util.Collection"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the active task tracker statuses in the cluster
-
- @return {@link Collection} of active {@link TaskTrackerStatus}]]>
- </doc>
- </method>
- <method name="taskTrackerNames" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the active and blacklisted task tracker names in the cluster. The first
- element in the returned list contains the list of active tracker names.
- The second element in the returned list contains the list of blacklisted
- tracker names.]]>
- </doc>
- </method>
- <method name="blacklistedTaskTrackers" return="java.util.Collection"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the blacklisted task tracker statuses in the cluster
-
- @return {@link Collection} of blacklisted {@link TaskTrackerStatus}]]>
- </doc>
- </method>
- <method name="isBlacklisted" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="trackerID" type="java.lang.String"/>
- <doc>
- <![CDATA[Whether the tracker is blacklisted or not
-
- @param trackerID
-
- @return true if blacklisted, false otherwise]]>
- </doc>
- </method>
- <method name="getTaskTracker" return="org.apache.hadoop.mapred.TaskTrackerStatus"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="trackerID" type="java.lang.String"/>
- </method>
- <method name="resolveAndAddToTopology" return="org.apache.hadoop.net.Node"
- 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="getNodesAtMaxLevel" return="java.util.Collection"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns a collection of nodes at the max level]]>
- </doc>
- </method>
- <method name="getParentNode" return="org.apache.hadoop.net.Node"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="node" type="org.apache.hadoop.net.Node"/>
- <param name="level" type="int"/>
- </method>
- <method name="getNode" return="org.apache.hadoop.net.Node"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- <doc>
- <![CDATA[Return the Node in the network topology that corresponds to the hostname]]>
- </doc>
- </method>
- <method name="getNumTaskCacheLevels" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getNumResolvedTaskTrackers" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getNumberOfUniqueHosts" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="addJobInProgressListener"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="listener" type="org.apache.hadoop.mapred.JobInProgressListener"/>
- </method>
- <method name="removeJobInProgressListener"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="listener" type="org.apache.hadoop.mapred.JobInProgressListener"/>
- </method>
- <method name="getQueueManager" return="org.apache.hadoop.mapred.QueueManager"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Return the {@link QueueManager} associated with the JobTracker.]]>
- </doc>
- </method>
- <method name="getBuildVersion" 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="heartbeat" return="org.apache.hadoop.mapred.HeartbeatResponse"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="status" type="org.apache.hadoop.mapred.TaskTrackerStatus"/>
- <param name="restarted" type="boolean"/>
- <param name="initialContact" type="boolean"/>
- <param name="acceptNewTasks" type="boolean"/>
- <param name="responseId" type="short"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[The periodic heartbeat mechanism between the {@link TaskTracker} and
- the {@link JobTracker}.
-
- The {@link JobTracker} processes the status information sent by the
- {@link TaskTracker} and responds with instructions to start/stop
- tasks or jobs, and also 'reset' instructions during contingencies.]]>
- </doc>
- </method>
- <method name="getNextHeartbeatInterval" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Calculates next heartbeat interval using cluster size.
- Heartbeat interval is incremented 1second for every 50 nodes.
- @return next heartbeat interval.]]>
- </doc>
- </method>
- <method name="getFilesystemName" return="java.lang.String"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Grab the local fs name]]>
- </doc>
- </method>
- <method name="reportTaskTrackerError"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskTracker" type="java.lang.String"/>
- <param name="errorClass" type="java.lang.String"/>
- <param name="errorMessage" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getNewJobId" return="org.apache.hadoop.mapred.JobID"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Allocates a new JobId string.]]>
- </doc>
- </method>
- <method name="submitJob" return="org.apache.hadoop.mapred.JobStatus"
- abstract="false" native="false" synchronized="true"
- 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[JobTracker.submitJob() kicks off a new job.
- Create a 'JobInProgress' object, which contains both JobProfile
- and JobStatus. Those two sub-objects are sometimes shipped outside
- of the JobTracker. But JobInProgress adds info that's useful for
- the JobTracker alone.]]>
- </doc>
- </method>
- <method name="getClusterStatus" return="org.apache.hadoop.mapred.ClusterStatus"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="use {@link #getClusterStatus(boolean)}">
- <doc>
- <![CDATA[@deprecated use {@link #getClusterStatus(boolean)}]]>
- </doc>
- </method>
- <method name="getClusterStatus" return="org.apache.hadoop.mapred.ClusterStatus"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="detailed" type="boolean"/>
- </method>
- <method name="killJob"
- abstract="false" native="false" synchronized="true"
- 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"/>
- </method>
- <method name="setJobPriority"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobid" type="org.apache.hadoop.mapred.JobID"/>
- <param name="priority" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Set the priority of a job
- @param jobid id of the job
- @param priority new priority of the job]]>
- </doc>
- </method>
- <method name="getJobProfile" return="org.apache.hadoop.mapred.JobProfile"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobid" type="org.apache.hadoop.mapred.JobID"/>
- </method>
- <method name="getJobStatus" return="org.apache.hadoop.mapred.JobStatus"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobid" type="org.apache.hadoop.mapred.JobID"/>
- </method>
- <method name="getJobCounters" return="org.apache.hadoop.mapred.Counters"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobid" type="org.apache.hadoop.mapred.JobID"/>
- </method>
- <method name="getMapTaskReports" return="org.apache.hadoop.mapred.TaskReport[]"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobid" type="org.apache.hadoop.mapred.JobID"/>
- </method>
- <method name="getReduceTaskReports" return="org.apache.hadoop.mapred.TaskReport[]"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobid" type="org.apache.hadoop.mapred.JobID"/>
- </method>
- <method name="getCleanupTaskReports" return="org.apache.hadoop.mapred.TaskReport[]"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobid" type="org.apache.hadoop.mapred.JobID"/>
- </method>
- <method name="getSetupTaskReports" return="org.apache.hadoop.mapred.TaskReport[]"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobid" type="org.apache.hadoop.mapred.JobID"/>
- </method>
- <method name="getTaskCompletionEvents" return="org.apache.hadoop.mapred.TaskCompletionEvent[]"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobid" type="org.apache.hadoop.mapred.JobID"/>
- <param name="fromEventId" type="int"/>
- <param name="maxEvents" type="int"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getTaskDiagnostics" return="java.lang.String[]"
- abstract="false" native="false" synchronized="true"
- 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[Get the diagnostics for a given task
- @param taskId the id of the task
- @return an array of the diagnostic messages]]>
- </doc>
- </method>
- <method name="getTip" return="org.apache.hadoop.mapred.TaskInProgress"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="tipid" type="org.apache.hadoop.mapred.TaskID"/>
- <doc>
- <![CDATA[Returns specified TaskInProgress, or null.]]>
- </doc>
- </method>
- <method name="killTask" return="boolean"
- abstract="false" native="false" synchronized="true"
- 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[Mark a Task to be killed]]>
- </doc>
- </method>
- <method name="getAssignedTracker" return="java.lang.String"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskId" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <doc>
- <![CDATA[Get tracker name for a given task id.
- @param taskId the name of the task
- @return The name of the task tracker]]>
- </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">
- </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">
- </method>
- <method name="getSystemDir" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@see org.apache.hadoop.mapred.JobSubmissionProtocol#getSystemDir()]]>
- </doc>
- </method>
- <method name="getJob" return="org.apache.hadoop.mapred.JobInProgress"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobid" type="org.apache.hadoop.mapred.JobID"/>
- </method>
- <method name="getLocalJobFilePath" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobId" type="org.apache.hadoop.mapred.JobID"/>
- <doc>
- <![CDATA[Get the localized job file path on the job trackers local file system
- @param jobId id of the job
- @return the path of the job conf file on the local file system]]>
- </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="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <doc>
- <![CDATA[Start the JobTracker process. This is used only for debugging. As a rule,
- JobTracker should be run as part of the DFS Namenode process.]]>
- </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"/>
- </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="queue" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- </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="queue" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="refreshServiceAcl"
- 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="LOG" type="org.apache.commons.logging.Log"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[JobTracker is the central location for submitting and
- tracking MR jobs in a network environment.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.JobTracker -->
- <!-- start class org.apache.hadoop.mapred.JobTracker.IllegalStateException -->
- <class name="JobTracker.IllegalStateException" extends="java.io.IOException"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="JobTracker.IllegalStateException" type="java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <doc>
- <![CDATA[A client tried to submit a job before the Job Tracker was ready.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.JobTracker.IllegalStateException -->
- <!-- start class org.apache.hadoop.mapred.JobTracker.State -->
- <class name="JobTracker.State" extends="java.lang.Enum"
- abstract="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <method name="values" return="org.apache.hadoop.mapred.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.mapred.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>
- <field name="INITIALIZING" type="org.apache.hadoop.mapred.JobTracker.State"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="RUNNING" type="org.apache.hadoop.mapred.JobTracker.State"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- </class>
- <!-- end class org.apache.hadoop.mapred.JobTracker.State -->
- <!-- 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">
- </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 key.value.separator.in.input.line. 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 -->
- <class name="LineRecordReader" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.input.LineRecordReader} instead.">
- <implements name="org.apache.hadoop.mapred.RecordReader"/>
- <constructor name="LineRecordReader" 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>
- <constructor name="LineRecordReader" type="java.io.InputStream, long, long, int"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <constructor name="LineRecordReader" type="java.io.InputStream, long, long, org.apache.hadoop.conf.Configuration"
- 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.LongWritable"
- 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.LongWritable"/>
- <param name="value" type="org.apache.hadoop.io.Text"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Read a line.]]>
- </doc>
- </method>
- <method name="getProgress" return="float"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the progress within the split]]>
- </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="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[Treats keys as offset in file and value as line.
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.input.LineRecordReader} instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.LineRecordReader -->
- <!-- start class org.apache.hadoop.mapred.LineRecordReader.LineReader -->
- <class name="LineRecordReader.LineReader" extends="org.apache.hadoop.util.LineReader"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.util.LineReader} instead.">
- <constructor name="LineRecordReader.LineReader" type="java.io.InputStream, org.apache.hadoop.conf.Configuration"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </constructor>
- <doc>
- <![CDATA[A class that provides a line reader from an input stream.
- @deprecated Use {@link org.apache.hadoop.util.LineReader} instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.LineRecordReader.LineReader -->
- <!-- start class org.apache.hadoop.mapred.MapFileOutputFormat -->
- <class name="MapFileOutputFormat" extends="org.apache.hadoop.mapred.FileOutputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="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="org.apache.hadoop.io.WritableComparable"/>
- <param name="value" type="org.apache.hadoop.io.Writable"/>
- <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="Use {@link org.apache.hadoop.mapreduce.Mapper} instead.">
- <implements name="org.apache.hadoop.mapred.JobConfigurable"/>
- <implements name="org.apache.hadoop.io.Closeable"/>
- <method name="map"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="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[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#mapred.task.timeout">
- mapred.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("mapred.task.id");
- inputFile = job.get("map.input.file");
- }
-
- public void map(K key, V val,
- OutputCollector<K, V> output, Reporter reporter)
- throws IOException {
- // Process the <key, value> pair (assume this takes a while)
- // ...
- // ...
-
- // Let the framework know that we are alive, and kicking!
- // reporter.progress();
-
- // Process some more
- // ...
- // ...
-
- // Increment the no. of <key, value> pairs processed
- ++noRecords;
- // Increment counters
- reporter.incrCounter(NUM_RECORDS, 1);
-
- // Every 100 records update application-level status
- if ((noRecords%100) == 0) {
- reporter.setStatus(mapTaskId + " processed " + noRecords +
- " from input-file: " + inputFile);
- }
-
- // Output the result
- output.collect(key, val);
- }
- }
- </pre></blockquote></p>
- <p>Applications may write a custom {@link MapRunnable} to exert greater
- control on map processing e.g. multi-threaded <code>Mapper</code>s etc.</p>
-
- @see JobConf
- @see InputFormat
- @see Partitioner
- @see Reducer
- @see MapReduceBase
- @see MapRunnable
- @see SequenceFile
- @deprecated Use {@link org.apache.hadoop.mapreduce.Mapper} instead.]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.Mapper -->
- <!-- start class org.apache.hadoop.mapred.MapReduceBase -->
- <class name="MapReduceBase" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.io.Closeable"/>
- <implements name="org.apache.hadoop.mapred.JobConfigurable"/>
- <constructor name="MapReduceBase"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Default implementation that does nothing.]]>
- </doc>
- </method>
- <method name="configure"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[Default implementation that does nothing.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Base class for {@link Mapper} and {@link Reducer} implementations.
-
- <p>Provides default no-op implementations for a few methods, most non-trivial
- applications need to override some of them.</p>]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.MapReduceBase -->
- <!-- start class org.apache.hadoop.mapred.MapReducePolicyProvider -->
- <class name="MapReducePolicyProvider" extends="org.apache.hadoop.security.authorize.PolicyProvider"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="MapReducePolicyProvider"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getServices" return="org.apache.hadoop.security.authorize.Service[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <doc>
- <![CDATA[{@link PolicyProvider} for Map-Reduce protocols.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.MapReducePolicyProvider -->
- <!-- start interface org.apache.hadoop.mapred.MapRunnable -->
- <interface name="MapRunnable" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.Mapper} instead.">
- <implements name="org.apache.hadoop.mapred.JobConfigurable"/>
- <method name="run"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="input" type="org.apache.hadoop.mapred.RecordReader"/>
- <param name="output" type="org.apache.hadoop.mapred.OutputCollector"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Start mapping input <tt><key, value></tt> pairs.
-
- <p>Mapping of input records to output records is complete when this method
- returns.</p>
-
- @param input the {@link RecordReader} to read the input records.
- @param output the {@link OutputCollector} to collect the outputrecords.
- @param reporter {@link Reporter} to report progress, status-updates etc.
- @throws IOException]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Expert: Generic interface for {@link Mapper}s.
-
- <p>Custom implementations of <code>MapRunnable</code> can exert greater
- control on map processing e.g. multi-threaded, asynchronous mappers etc.</p>
-
- @see Mapper
- @deprecated Use {@link org.apache.hadoop.mapreduce.Mapper} instead.]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.MapRunnable -->
- <!-- start class org.apache.hadoop.mapred.MapRunner -->
- <class name="MapRunner" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapred.MapRunnable"/>
- <constructor name="MapRunner"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="configure"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- </method>
- <method name="run"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="input" type="org.apache.hadoop.mapred.RecordReader"/>
- <param name="output" type="org.apache.hadoop.mapred.OutputCollector"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getMapper" return="org.apache.hadoop.mapred.Mapper"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </method>
- <doc>
- <![CDATA[Default {@link MapRunnable} implementation.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.MapRunner -->
- <!-- start class org.apache.hadoop.mapred.MultiFileInputFormat -->
- <class name="MultiFileInputFormat" extends="org.apache.hadoop.mapred.FileInputFormat"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapred.lib.CombineFileInputFormat} instead">
- <constructor name="MultiFileInputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getSplits" return="org.apache.hadoop.mapred.InputSplit[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="numSplits" type="int"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getRecordReader" return="org.apache.hadoop.mapred.RecordReader"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapred.InputSplit"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[An abstract {@link InputFormat} that returns {@link MultiFileSplit}'s
- in {@link #getSplits(JobConf, int)} method. Splits are constructed from
- the files under the input paths. Each split returned contains <i>nearly</i>
- equal content length. <br>
- Subclasses implement {@link #getRecordReader(InputSplit, JobConf, Reporter)}
- to construct <code>RecordReader</code>'s for <code>MultiFileSplit</code>'s.
- @see MultiFileSplit
- @deprecated Use {@link org.apache.hadoop.mapred.lib.CombineFileInputFormat} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.MultiFileInputFormat -->
- <!-- start class org.apache.hadoop.mapred.MultiFileSplit -->
- <class name="MultiFileSplit" extends="org.apache.hadoop.mapred.lib.CombineFileSplit"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapred.lib.CombineFileSplit} instead">
- <constructor name="MultiFileSplit" type="org.apache.hadoop.mapred.JobConf, org.apache.hadoop.fs.Path[], long[]"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getLocations" return="java.lang.String[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="toString" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <doc>
- <![CDATA[A sub-collection of input files. Unlike {@link FileSplit}, MultiFileSplit
- class does not represent a split of a file, but a split of input files
- into smaller sets. The atomic unit of split is a file. <br>
- MultiFileSplit can be used to implement {@link RecordReader}'s, with
- reading one record per file.
- @see FileSplit
- @see MultiFileInputFormat
- @deprecated Use {@link org.apache.hadoop.mapred.lib.CombineFileSplit} instead]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.MultiFileSplit -->
- <!-- start interface org.apache.hadoop.mapred.OutputCollector -->
- <interface name="OutputCollector" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <method name="collect"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="java.lang.Object"/>
- <param name="value" type="java.lang.Object"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Adds a key/value pair to the output.
- @param key the key to collect.
- @param value to value to collect.
- @throws IOException]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Collects the <code><key, value></code> pairs output by {@link Mapper}s
- and {@link Reducer}s.
-
- <p><code>OutputCollector</code> is the generalization of the facility
- provided by the Map-Reduce framework to collect data output by either the
- <code>Mapper</code> or the <code>Reducer</code> i.e. intermediate outputs
- or the output of the job.</p>]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.OutputCollector -->
- <!-- start class org.apache.hadoop.mapred.OutputCommitter -->
- <class name="OutputCommitter" extends="org.apache.hadoop.mapreduce.OutputCommitter"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.OutputCommitter} instead.">
- <constructor name="OutputCommitter"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="setupJob"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobContext" type="org.apache.hadoop.mapred.JobContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[For the framework to setup the job output during initialization
-
- @param jobContext Context of the job whose output is being written.
- @throws IOException if temporary output could not be created]]>
- </doc>
- </method>
- <method name="cleanupJob"
- abstract="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 cleaning up the job's output after job completion
-
- @param jobContext Context of the job whose output is being written.
- @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="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="setupTask"
- abstract="false" native="false" synchronized="false"
- static="false" final="true" visibility="public"
- deprecated="not deprecated">
- <param name="taskContext" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[This method implements the new interface by calling the old method. Note
- that the input types are different between the new and old apis and this
- is a bridge between the two.]]>
- </doc>
- </method>
- <method name="needsTaskCommit" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="true" visibility="public"
- deprecated="not deprecated">
- <param name="taskContext" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[This method implements the new interface by calling the old method. Note
- that the input types are different between the new and old apis and this
- is a bridge between the two.]]>
- </doc>
- </method>
- <method name="commitTask"
- abstract="false" native="false" synchronized="false"
- static="false" final="true" visibility="public"
- deprecated="not deprecated">
- <param name="taskContext" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[This method implements the new interface by calling the old method. Note
- that the input types are different between the new and old apis and this
- is a bridge between the two.]]>
- </doc>
- </method>
- <method name="abortTask"
- abstract="false" native="false" synchronized="false"
- static="false" final="true" visibility="public"
- deprecated="not deprecated">
- <param name="taskContext" type="org.apache.hadoop.mapreduce.TaskAttemptContext"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[This method implements the new interface by calling the old method. Note
- that the input types are different between the new and old apis and this
- is a bridge between the two.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[<code>OutputCommitter</code> describes the commit of task output for a
- Map-Reduce job.
- <p>The Map-Reduce framework relies on the <code>OutputCommitter</code> of
- the job to:<p>
- <ol>
- <li>
- Setup the job during initialization. For example, create the temporary
- output directory for the job during the initialization of the job.
- </li>
- <li>
- Cleanup the job after the job completion. For example, remove the
- temporary output directory after the job completion.
- </li>
- <li>
- Setup the task temporary output.
- </li>
- <li>
- Check whether a task needs a commit. This is to avoid the commit
- procedure if a task does not need commit.
- </li>
- <li>
- Commit of the task output.
- </li>
- <li>
- Discard the task commit.
- </li>
- </ol>
-
- @see FileOutputCommitter
- @see JobContext
- @see TaskAttemptContext
- @deprecated Use {@link org.apache.hadoop.mapreduce.OutputCommitter} instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.OutputCommitter -->
- <!-- start interface org.apache.hadoop.mapred.OutputFormat -->
- <interface name="OutputFormat" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.OutputFormat} instead.">
- <method name="getRecordWriter" return="org.apache.hadoop.mapred.RecordWriter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="name" type="java.lang.String"/>
- <param name="progress" type="org.apache.hadoop.util.Progressable"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get the {@link RecordWriter} for the given job.
- @param ignored
- @param job configuration for the job whose output is being written.
- @param name the unique name for this part of the output.
- @param progress mechanism for reporting progress while writing to file.
- @return a {@link RecordWriter} to write the output for the job.
- @throws IOException]]>
- </doc>
- </method>
- <method name="checkOutputSpecs"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Check for validity of the output-specification for the job.
-
- <p>This is to validate the output specification for the job when it is
- a job is submitted. Typically checks that it does not already exist,
- throwing an exception when it already exists, so that output is not
- overwritten.</p>
- @param ignored
- @param job job configuration.
- @throws IOException when output should not be attempted]]>
- </doc>
- </method>
- <doc>
- <![CDATA[<code>OutputFormat</code> describes the output-specification for a
- Map-Reduce job.
- <p>The Map-Reduce framework relies on the <code>OutputFormat</code> of the
- job to:<p>
- <ol>
- <li>
- Validate the output-specification of the job. For e.g. check that the
- output directory doesn't already exist.
- <li>
- Provide the {@link RecordWriter} implementation to be used to write out
- the output files of the job. Output files are stored in a
- {@link FileSystem}.
- </li>
- </ol>
-
- @see RecordWriter
- @see JobConf
- @deprecated Use {@link org.apache.hadoop.mapreduce.OutputFormat} instead.]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.OutputFormat -->
- <!-- start class org.apache.hadoop.mapred.OutputLogFilter -->
- <class name="OutputLogFilter" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <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()));]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.OutputLogFilter -->
- <!-- start interface org.apache.hadoop.mapred.Partitioner -->
- <interface name="Partitioner" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.Partitioner} instead.">
- <implements name="org.apache.hadoop.mapred.JobConfigurable"/>
- <method name="getPartition" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="java.lang.Object"/>
- <param name="value" type="java.lang.Object"/>
- <param name="numPartitions" type="int"/>
- <doc>
- <![CDATA[Get the paritition number for a given key (hence record) given the total
- number of partitions i.e. number of reduce-tasks for the job.
-
- <p>Typically a hash function on a all or a subset of the key.</p>
- @param key the key to be paritioned.
- @param value the entry value.
- @param numPartitions the total number of partitions.
- @return the partition number for the <code>key</code>.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Partitions the key space.
-
- <p><code>Partitioner</code> controls the partitioning of the keys of the
- intermediate map-outputs. The key (or a subset of the key) is used to derive
- the partition, typically by a hash function. The total number of partitions
- is the same as the number of reduce tasks for the job. Hence this controls
- which of the <code>m</code> reduce tasks the intermediate key (and hence the
- record) is sent for reduction.</p>
-
- @see Reducer
- @deprecated Use {@link org.apache.hadoop.mapreduce.Partitioner} instead.]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.Partitioner -->
- <!-- start interface org.apache.hadoop.mapred.RawKeyValueIterator -->
- <interface name="RawKeyValueIterator" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <method name="getKey" return="org.apache.hadoop.io.DataInputBuffer"
- 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 current raw key.
-
- @return Gets the current raw key as a DataInputBuffer
- @throws IOException]]>
- </doc>
- </method>
- <method name="getValue" return="org.apache.hadoop.io.DataInputBuffer"
- 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 current raw value.
-
- @return Gets the current raw value as a DataInputBuffer
- @throws IOException]]>
- </doc>
- </method>
- <method name="next" 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[Sets up the current key and value (for getKey and getValue).
-
- @return <code>true</code> if there exists a key/value,
- <code>false</code> otherwise.
- @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[Closes the iterator so that the underlying streams can be closed.
-
- @throws IOException]]>
- </doc>
- </method>
- <method name="getProgress" return="org.apache.hadoop.util.Progress"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Gets the Progress object; this has a float (0.0 - 1.0)
- indicating the bytes processed by the iterator so far]]>
- </doc>
- </method>
- <doc>
- <![CDATA[<code>RawKeyValueIterator</code> is an iterator used to iterate over
- the raw keys and values during sort/merge of intermediate data.]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.RawKeyValueIterator -->
- <!-- 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="java.lang.Object"/>
- <param name="value" type="java.lang.Object"/>
- <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="java.lang.Object"
- 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="java.lang.Object"
- 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="java.lang.Object"/>
- <param name="value" type="java.lang.Object"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Writes a key/value pair.
- @param key the key to write.
- @param value the value to write.
- @throws IOException]]>
- </doc>
- </method>
- <method name="close"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Close this <code>RecordWriter</code> to future operations.
-
- @param reporter facility to report progress.
- @throws IOException]]>
- </doc>
- </method>
- <doc>
- <![CDATA[<code>RecordWriter</code> writes the output <key, value> pairs
- to an output file.
- <p><code>RecordWriter</code> implementations write the job outputs to the
- {@link FileSystem}.
-
- @see OutputFormat]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.RecordWriter -->
- <!-- start interface org.apache.hadoop.mapred.Reducer -->
- <interface name="Reducer" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.Reducer} instead.">
- <implements name="org.apache.hadoop.mapred.JobConfigurable"/>
- <implements name="org.apache.hadoop.io.Closeable"/>
- <method name="reduce"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="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[<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#mapred.task.timeout">
- mapred.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("mapred.task.id");
- }
-
- public void reduce(K key, Iterator<V> values,
- OutputCollector<K, V> output,
- Reporter reporter)
- throws IOException {
-
- // Process
- int noValues = 0;
- while (values.hasNext()) {
- V value = values.next();
-
- // Increment the no. of values for this key
- ++noValues;
-
- // Process the <key, value> pair (assume this takes a while)
- // ...
- // ...
-
- // Let the framework know that we are alive, and kicking!
- if ((noValues%10) == 0) {
- reporter.progress();
- }
-
- // Process some more
- // ...
- // ...
-
- // Output the <key, value>
- output.collect(key, value);
- }
-
- // Increment the no. of <key, list of values> pairs processed
- ++noKeys;
-
- // Increment counters
- reporter.incrCounter(NUM_RECORDS, 1);
-
- // Every 100 keys update application-level status
- if ((noKeys%100) == 0) {
- reporter.setStatus(reduceTaskId + " processed " + noKeys);
- }
- }
- }
- </pre></blockquote></p>
-
- @see Mapper
- @see Partitioner
- @see Reporter
- @see MapReduceBase
- @deprecated Use {@link org.apache.hadoop.mapreduce.Reducer} instead.]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.Reducer -->
- <!-- start interface org.apache.hadoop.mapred.Reporter -->
- <interface name="Reporter" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.util.Progressable"/>
- <method name="setStatus"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="status" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the status description for the task.
-
- @param status brief description of the current status.]]>
- </doc>
- </method>
- <method name="getCounter" return="org.apache.hadoop.mapred.Counters.Counter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.Enum"/>
- <doc>
- <![CDATA[Get the {@link Counter} of the given group with the given name.
-
- @param name counter name
- @return the <code>Counter</code> of the given group/name.]]>
- </doc>
- </method>
- <method name="getCounter" return="org.apache.hadoop.mapred.Counters.Counter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="group" type="java.lang.String"/>
- <param name="name" type="java.lang.String"/>
- <doc>
- <![CDATA[Get the {@link Counter} of the given group with the given name.
-
- @param group counter group
- @param name counter name
- @return the <code>Counter</code> of the given group/name.]]>
- </doc>
- </method>
- <method name="incrCounter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="java.lang.Enum"/>
- <param name="amount" type="long"/>
- <doc>
- <![CDATA[Increments the counter identified by the key, which can be of
- any {@link Enum} type, by the specified amount.
-
- @param key key to identify the counter to be incremented. The key can be
- be any <code>Enum</code>.
- @param amount A non-negative amount by which the counter is to
- be incremented.]]>
- </doc>
- </method>
- <method name="incrCounter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="group" type="java.lang.String"/>
- <param name="counter" type="java.lang.String"/>
- <param name="amount" type="long"/>
- <doc>
- <![CDATA[Increments the counter identified by the group and counter name
- by the specified amount.
-
- @param group name to identify the group of the counter to be incremented.
- @param counter name to identify the counter within the group.
- @param amount A non-negative amount by which the counter is to
- be incremented.]]>
- </doc>
- </method>
- <method name="getInputSplit" return="org.apache.hadoop.mapred.InputSplit"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="UnsupportedOperationException" type="java.lang.UnsupportedOperationException"/>
- <doc>
- <![CDATA[Get the {@link InputSplit} object for a map.
-
- @return the <code>InputSplit</code> that the map is reading from.
- @throws UnsupportedOperationException if called outside a mapper]]>
- </doc>
- </method>
- <field name="NULL" type="org.apache.hadoop.mapred.Reporter"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[A constant of Reporter type that does nothing.]]>
- </doc>
- </field>
- <doc>
- <![CDATA[A facility for Map-Reduce applications to report progress and update
- counters, status information etc.
-
- <p>{@link Mapper} and {@link Reducer} can use the <code>Reporter</code>
- provided to report progress or just indicate that they are alive. In
- scenarios where the application takes an insignificant amount of time to
- process individual key/value pairs, this is crucial since the framework
- might assume that the task has timed-out and kill that task.
- <p>Applications can also update {@link Counters} via the provided
- <code>Reporter</code> .</p>
-
- @see Progressable
- @see Counters]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.Reporter -->
- <!-- start interface org.apache.hadoop.mapred.RunningJob -->
- <interface name="RunningJob" abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <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>
- <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="java.lang.Object"
- abstract="false"
- static="true" final="false" visibility="protected"
- 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.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.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.mapred.SequenceFileInputFilter.Filter -->
- <!-- start class org.apache.hadoop.mapred.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.mapred.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.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"/>
- <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 org.apache.hadoop.mapred.SequenceFileInputFilter.Filter#accept(Object)]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Records filter by matching key to regex]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.SequenceFileInputFilter.RegexFilter -->
- <!-- start class org.apache.hadoop.mapred.SequenceFileInputFormat -->
- <class name="SequenceFileInputFormat" extends="org.apache.hadoop.mapred.FileInputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFormat}
- instead.">
- <constructor name="SequenceFileInputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="listStatus" return="org.apache.hadoop.fs.FileStatus[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getRecordReader" return="org.apache.hadoop.mapred.RecordReader"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="split" type="org.apache.hadoop.mapred.InputSplit"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[An {@link InputFormat} for {@link SequenceFile}s.
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFormat}
- instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.SequenceFileInputFormat -->
- <!-- start class org.apache.hadoop.mapred.SequenceFileOutputFormat -->
- <class name="SequenceFileOutputFormat" extends="org.apache.hadoop.mapred.FileOutputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat}
- instead.">
- <constructor name="SequenceFileOutputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getRecordWriter" return="org.apache.hadoop.mapred.RecordWriter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="name" type="java.lang.String"/>
- <param name="progress" type="org.apache.hadoop.util.Progressable"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getReaders" return="org.apache.hadoop.io.SequenceFile.Reader[]"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.conf.Configuration"/>
- <param name="dir" type="org.apache.hadoop.fs.Path"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Open the output generated by this format.]]>
- </doc>
- </method>
- <method name="getOutputCompressionType" return="org.apache.hadoop.io.SequenceFile.CompressionType"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[Get the {@link CompressionType} for the output {@link SequenceFile}.
- @param conf the {@link JobConf}
- @return the {@link CompressionType} for the output {@link SequenceFile},
- defaulting to {@link CompressionType#RECORD}]]>
- </doc>
- </method>
- <method name="setOutputCompressionType"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="style" type="org.apache.hadoop.io.SequenceFile.CompressionType"/>
- <doc>
- <![CDATA[Set the {@link CompressionType} for the output {@link SequenceFile}.
- @param conf the {@link JobConf} to modify
- @param style the {@link CompressionType} for the output
- {@link SequenceFile}]]>
- </doc>
- </method>
- <doc>
- <![CDATA[An {@link OutputFormat} that writes {@link SequenceFile}s.
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat}
- instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.SequenceFileOutputFormat -->
- <!-- start class org.apache.hadoop.mapred.SequenceFileRecordReader -->
- <class name="SequenceFileRecordReader" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapred.RecordReader"/>
- <constructor name="SequenceFileRecordReader" type="org.apache.hadoop.conf.Configuration, org.apache.hadoop.mapred.FileSplit"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- </constructor>
- <method name="getKeyClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[The class of key that must be passed to {@link
- #next(Object, Object)}..]]>
- </doc>
- </method>
- <method name="getValueClass" return="java.lang.Class"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[The class of value that must be passed to {@link
- #next(Object, Object)}..]]>
- </doc>
- </method>
- <method name="createKey" return="java.lang.Object"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="createValue" return="java.lang.Object"
- 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="java.lang.Object"/>
- <param name="value" type="java.lang.Object"/>
- <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="java.lang.Object"/>
- <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="java.lang.Object"/>
- <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 class org.apache.hadoop.mapred.TaskAttemptContext -->
- <class name="TaskAttemptContext" extends="org.apache.hadoop.mapreduce.TaskAttemptContext"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.TaskAttemptContext}
- instead.">
- <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[Get the taskAttemptID.
-
- @return TaskAttemptID]]>
- </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">
- </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>
- <method name="progress"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <doc>
- <![CDATA[@deprecated Use {@link org.apache.hadoop.mapreduce.TaskAttemptContext}
- instead.]]>
- </doc>
- </class>
- <!-- end class 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="not deprecated">
- <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]]>
- </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>
- <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="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.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="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="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="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="public"
- 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="public"
- 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="setTaskId"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="use {@link #setTaskID(TaskAttemptID)} instead.">
- <param name="taskId" type="java.lang.String"/>
- <doc>
- <![CDATA[Sets task id.
- @param taskId
- @deprecated use {@link #setTaskID(TaskAttemptID)} instead.]]>
- </doc>
- </method>
- <method name="setTaskID"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- 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="public"
- deprecated="not deprecated">
- <param name="status" type="org.apache.hadoop.mapred.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="public"
- 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.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>
- <field name="FAILED" type="org.apache.hadoop.mapred.TaskCompletionEvent.Status"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="KILLED" type="org.apache.hadoop.mapred.TaskCompletionEvent.Status"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="SUCCEEDED" type="org.apache.hadoop.mapred.TaskCompletionEvent.Status"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="OBSOLETE" type="org.apache.hadoop.mapred.TaskCompletionEvent.Status"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="TIPFAILED" type="org.apache.hadoop.mapred.TaskCompletionEvent.Status"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- </class>
- <!-- end class org.apache.hadoop.mapred.TaskCompletionEvent.Status -->
- <!-- start class org.apache.hadoop.mapred.TaskGraphServlet -->
- <class name="TaskGraphServlet" extends="javax.servlet.http.HttpServlet"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="TaskGraphServlet"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="doGet"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="request" type="javax.servlet.http.HttpServletRequest"/>
- <param name="response" type="javax.servlet.http.HttpServletResponse"/>
- <exception name="ServletException" type="javax.servlet.ServletException"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <field name="width" type="int"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[height of the graph w/o margins]]>
- </doc>
- </field>
- <field name="height" type="int"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[height of the graph w/o margins]]>
- </doc>
- </field>
- <field name="ymargin" type="int"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[margin space on y axis]]>
- </doc>
- </field>
- <field name="xmargin" type="int"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[margin space on x axis]]>
- </doc>
- </field>
- <doc>
- <![CDATA[The servlet that outputs svg graphics for map / reduce task
- statuses]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.TaskGraphServlet -->
- <!-- 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="not deprecated">
- <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]]>
- </doc>
- </constructor>
- <constructor name="TaskID" type="java.lang.String, int, boolean, 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 isMap whether the tip is a map
- @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="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"/>
- <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]]>
- </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 -->
- <class name="TaskLog" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="TaskLog"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getTaskLogFile" return="java.io.File"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskid" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <param name="filter" type="org.apache.hadoop.mapred.TaskLog.LogName"/>
- </method>
- <method name="getRealTaskLogFileLocation" return="java.io.File"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskid" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <param name="filter" type="org.apache.hadoop.mapred.TaskLog.LogName"/>
- </method>
- <method name="getIndexFile" return="java.io.File"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskid" type="java.lang.String"/>
- </method>
- <method name="getIndexFile" return="java.io.File"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskid" type="java.lang.String"/>
- <param name="isCleanup" type="boolean"/>
- </method>
- <method name="syncLogs"
- abstract="false" native="false" synchronized="true"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="firstTaskid" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <param name="taskid" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="syncLogs"
- abstract="false" native="false" synchronized="true"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="firstTaskid" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <param name="taskid" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <param name="isCleanup" type="boolean"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="cleanup"
- abstract="false" native="false" synchronized="true"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="logsRetainHours" type="int"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Purge old user logs.
-
- @throws IOException]]>
- </doc>
- </method>
- <method name="getTaskLogLength" return="long"
- 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 desired maximum length of task's logs.
- @param conf the job to look in
- @return the number of bytes to cap the log files at]]>
- </doc>
- </method>
- <method name="captureOutAndError" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="cmd" type="java.util.List"/>
- <param name="stdoutFilename" type="java.io.File"/>
- <param name="stderrFilename" type="java.io.File"/>
- <param name="tailLength" type="long"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Wrap a command in a shell to capture stdout and stderr to files.
- If the tailLength is 0, the entire output will be saved.
- @param cmd The command and the arguments that should be run
- @param stdoutFilename The filename that stdout should be saved to
- @param stderrFilename The filename that stderr should be saved to
- @param tailLength The length of the tail to be saved.
- @return the modified command that should be run]]>
- </doc>
- </method>
- <method name="captureOutAndError" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="setup" type="java.util.List"/>
- <param name="cmd" type="java.util.List"/>
- <param name="stdoutFilename" type="java.io.File"/>
- <param name="stderrFilename" type="java.io.File"/>
- <param name="tailLength" type="long"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Wrap a command in a shell to capture stdout and stderr to files.
- Setup commands such as setting memory limit can be passed which
- will be executed before exec.
- If the tailLength is 0, the entire output will be saved.
- @param setup The setup commands for the execed process.
- @param cmd The command and the arguments that should be run
- @param stdoutFilename The filename that stdout should be saved to
- @param stderrFilename The filename that stderr should be saved to
- @param tailLength The length of the tail to be saved.
- @return the modified command that should be run]]>
- </doc>
- </method>
- <method name="captureOutAndError" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="setup" type="java.util.List"/>
- <param name="cmd" type="java.util.List"/>
- <param name="stdoutFilename" type="java.io.File"/>
- <param name="stderrFilename" type="java.io.File"/>
- <param name="tailLength" type="long"/>
- <param name="pidFileName" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Wrap a command in a shell to capture stdout and stderr to files.
- Setup commands such as setting memory limit can be passed which
- will be executed before exec.
- If the tailLength is 0, the entire output will be saved.
- @param setup The setup commands for the execed process.
- @param cmd The command and the arguments that should be run
- @param stdoutFilename The filename that stdout should be saved to
- @param stderrFilename The filename that stderr should be saved to
- @param tailLength The length of the tail to be saved.
- @param pidFileName The name of the pid-file
- @return the modified command that should be run]]>
- </doc>
- </method>
- <method name="addCommand" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="cmd" type="java.util.List"/>
- <param name="isExecutable" type="boolean"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Add quotes to each of the command strings and
- return as a single string
- @param cmd The command to be quoted
- @param isExecutable makes shell path if the first
- argument is executable
- @return returns The quoted string.
- @throws IOException]]>
- </doc>
- </method>
- <method name="captureDebugOut" return="java.util.List"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="cmd" type="java.util.List"/>
- <param name="debugoutFilename" type="java.io.File"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Wrap a command in a shell to capture debug script's
- stdout and stderr to debugout.
- @param cmd The command and the arguments that should be run
- @param debugoutFilename The filename that stdout and stderr
- should be saved to.
- @return the modified command that should be run
- @throws IOException]]>
- </doc>
- </method>
- <doc>
- <![CDATA[A simple logger to handle the task-specific user logs.
- This class uses the system property <code>hadoop.log.dir</code>.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.TaskLog -->
- <!-- start class org.apache.hadoop.mapred.TaskLog.LogName -->
- <class name="TaskLog.LogName" extends="java.lang.Enum"
- abstract="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <method name="values" return="org.apache.hadoop.mapred.TaskLog.LogName[]"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="valueOf" return="org.apache.hadoop.mapred.TaskLog.LogName"
- 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="toString" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <field name="STDOUT" type="org.apache.hadoop.mapred.TaskLog.LogName"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Log on the stdout of the task.]]>
- </doc>
- </field>
- <field name="STDERR" type="org.apache.hadoop.mapred.TaskLog.LogName"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Log on the stderr of the task.]]>
- </doc>
- </field>
- <field name="SYSLOG" type="org.apache.hadoop.mapred.TaskLog.LogName"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Log on the map-reduce system logs of the task.]]>
- </doc>
- </field>
- <field name="PROFILE" type="org.apache.hadoop.mapred.TaskLog.LogName"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[The java profiler information.]]>
- </doc>
- </field>
- <field name="DEBUGOUT" type="org.apache.hadoop.mapred.TaskLog.LogName"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Log the debug script's stdout]]>
- </doc>
- </field>
- <doc>
- <![CDATA[The filter for userlogs.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.TaskLog.LogName -->
- <!-- 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>
- <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.TaskLogServlet -->
- <class name="TaskLogServlet" extends="javax.servlet.http.HttpServlet"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="TaskLogServlet"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getTaskLogUrl" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskTrackerHostName" type="java.lang.String"/>
- <param name="httpPort" type="java.lang.String"/>
- <param name="taskAttemptID" type="java.lang.String"/>
- <doc>
- <![CDATA[Construct the taskLogUrl
- @param taskTrackerHostName
- @param httpPort
- @param taskAttemptID
- @return the taskLogUrl]]>
- </doc>
- </method>
- <method name="doGet"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="request" type="javax.servlet.http.HttpServletRequest"/>
- <param name="response" type="javax.servlet.http.HttpServletResponse"/>
- <exception name="ServletException" type="javax.servlet.ServletException"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Get the logs via http.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[A servlet that is run by the TaskTrackers to provide the task logs via http.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.TaskLogServlet -->
- <!-- start class org.apache.hadoop.mapred.TaskReport -->
- <class name="TaskReport" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.io.Writable"/>
- <constructor name="TaskReport"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getTaskId" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="use {@link #getTaskID()} instead">
- <doc>
- <![CDATA[@deprecated use {@link #getTaskID()} instead]]>
- </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">
- <doc>
- <![CDATA[The id of the task.]]>
- </doc>
- </method>
- <method name="getProgress" return="float"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[The amount completed, between zero and one.]]>
- </doc>
- </method>
- <method name="getState" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[The most recent state, reported by a {@link Reporter}.]]>
- </doc>
- </method>
- <method name="getDiagnostics" return="java.lang.String[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[A list of error messages.]]>
- </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">
- <doc>
- <![CDATA[A table of counters.]]>
- </doc>
- </method>
- <method name="getCurrentStatus" return="org.apache.hadoop.mapred.TIPStatus"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[The current status]]>
- </doc>
- </method>
- <method name="getFinishTime" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get finish time of task.
- @return 0, if finish time was not set else returns finish time.]]>
- </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 task.
- @return 0 if start time was not set, else start time.]]>
- </doc>
- </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="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="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[A report on the state of a task.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.TaskReport -->
- <!-- start class org.apache.hadoop.mapred.TaskTracker -->
- <class name="TaskTracker" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapred.MRConstants"/>
- <implements name="org.apache.hadoop.mapred.TaskUmbilicalProtocol"/>
- <implements name="java.lang.Runnable"/>
- <constructor name="TaskTracker" type="org.apache.hadoop.mapred.JobConf"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Start with the local machine name, and the default JobTracker]]>
- </doc>
- </constructor>
- <method name="getTaskTrackerInstrumentation" return="org.apache.hadoop.mapred.TaskTrackerInstrumentation"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getProtocolVersion" return="long"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="protocol" type="java.lang.String"/>
- <param name="clientVersion" type="long"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="getInstrumentationClass" 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.conf.Configuration"/>
- </method>
- <method name="setInstrumentationClass"
- 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="t" type="java.lang.Class"/>
- </method>
- <method name="cleanupStorage"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Removes all contents of temporary storage. Called upon
- startup, to remove any leftovers from previous run.]]>
- </doc>
- </method>
- <method name="shutdown"
- 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"/>
- <doc>
- <![CDATA[Close down the TaskTracker and all its components. We must also shutdown
- any running tasks or threads, and cleanup disk space. A new TaskTracker
- within the same process space might be restarted, so everything must be
- clean.]]>
- </doc>
- </method>
- <method name="getJobClient" return="org.apache.hadoop.mapred.InterTrackerProtocol"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[The connection to the JobTracker, used by the TaskRunner
- for locating remote files.]]>
- </doc>
- </method>
- <method name="getTaskTrackerReportAddress" return="java.net.InetSocketAddress"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Return the port at which the tasktracker bound to]]>
- </doc>
- </method>
- <method name="getJvmManagerInstance" return="org.apache.hadoop.mapred.JvmManager"
- abstract="false" native="false" synchronized="false"
- 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 server retry loop.
- This while-loop attempts to connect to the JobTracker. It only
- loops when the old TaskTracker has gone bad (its state is
- stale somehow) and we need to reinitialize everything.]]>
- </doc>
- </method>
- <method name="getTask" return="org.apache.hadoop.mapred.JvmTask"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jvmId" type="org.apache.hadoop.mapred.JVMId"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Called upon startup by the child process, to fetch Task data.]]>
- </doc>
- </method>
- <method name="statusUpdate" return="boolean"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskid" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <param name="taskStatus" type="org.apache.hadoop.mapred.TaskStatus"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Called periodically to report Task progress, from 0.0 to 1.0.]]>
- </doc>
- </method>
- <method name="reportDiagnosticInfo"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskid" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <param name="info" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Called when the task dies before completion, and we want to report back
- diagnostic info]]>
- </doc>
- </method>
- <method name="reportNextRecordRange"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskid" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <param name="range" type="org.apache.hadoop.mapred.SortedRanges.Range"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="ping" return="boolean"
- abstract="false" native="false" synchronized="true"
- 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[Child checking to see if we're alive. Normally does nothing.]]>
- </doc>
- </method>
- <method name="commitPending"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskid" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <param name="taskStatus" type="org.apache.hadoop.mapred.TaskStatus"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Task is reporting that it is in commit_pending
- and it is waiting for the commit Response]]>
- </doc>
- </method>
- <method name="canCommit" return="boolean"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskid" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <doc>
- <![CDATA[Child checking whether it can commit]]>
- </doc>
- </method>
- <method name="done"
- abstract="false" native="false" synchronized="true"
- 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[The task is done.]]>
- </doc>
- </method>
- <method name="shuffleError"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskId" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <param name="message" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[A reduce-task failed to shuffle the map-outputs. Kill the task.]]>
- </doc>
- </method>
- <method name="fsError"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskId" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <param name="message" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[A child task had a local filesystem error. Kill the task.]]>
- </doc>
- </method>
- <method name="getMapCompletionEvents" return="org.apache.hadoop.mapred.MapTaskCompletionEventsUpdate"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="jobId" type="org.apache.hadoop.mapred.JobID"/>
- <param name="fromEventId" type="int"/>
- <param name="maxLocs" type="int"/>
- <param name="id" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="mapOutputLost"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="taskid" type="org.apache.hadoop.mapred.TaskAttemptID"/>
- <param name="errorMsg" type="java.lang.String"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[A completed map task's output has been lost.]]>
- </doc>
- </method>
- <method name="isIdle" return="boolean"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Is this task tracker idle?
- @return has this task tracker finished and cleaned up all of its tasks?]]>
- </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"/>
- <doc>
- <![CDATA[Start the TaskTracker, point toward the indicated JobTracker]]>
- </doc>
- </method>
- <method name="isTaskMemoryManagerEnabled" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Is the TaskMemoryManager Enabled on this system?
- @return true if enabled, false otherwise.]]>
- </doc>
- </method>
- <method name="getTaskMemoryManager" return="org.apache.hadoop.mapred.TaskMemoryManagerThread"
- abstract="false" native="false" synchronized="false"
- static="false" 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>
- <field name="MR_CLIENTTRACE_FORMAT" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="ClientTraceLog" type="org.apache.commons.logging.Log"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[TaskTracker is a process that starts and tracks MR Tasks
- in a networked environment. It contacts the JobTracker
- for Task assignments and reporting results.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.TaskTracker -->
- <!-- start class org.apache.hadoop.mapred.TaskTracker.MapOutputServlet -->
- <class name="TaskTracker.MapOutputServlet" extends="javax.servlet.http.HttpServlet"
- abstract="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="TaskTracker.MapOutputServlet"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="doGet"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="request" type="javax.servlet.http.HttpServletRequest"/>
- <param name="response" type="javax.servlet.http.HttpServletResponse"/>
- <exception name="ServletException" type="javax.servlet.ServletException"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[This class is used in TaskTracker's Jetty to serve the map outputs
- to other nodes.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.TaskTracker.MapOutputServlet -->
- <!-- start class org.apache.hadoop.mapred.TextInputFormat -->
- <class name="TextInputFormat" extends="org.apache.hadoop.mapred.FileInputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.lib.input.TextInputFormat}
- instead.">
- <implements name="org.apache.hadoop.mapred.JobConfigurable"/>
- <constructor name="TextInputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="configure"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
- </method>
- <method name="isSplitable" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="fs" type="org.apache.hadoop.fs.FileSystem"/>
- <param name="file" type="org.apache.hadoop.fs.Path"/>
- </method>
- <method name="getRecordReader" return="org.apache.hadoop.mapred.RecordReader"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="genericSplit" type="org.apache.hadoop.mapred.InputSplit"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[An {@link InputFormat} for plain text files. Files are broken into lines.
- Either linefeed or carriage-return are used to signal end of line. Keys are
- the position in the file, and values are the line of text..
- @deprecated Use {@link org.apache.hadoop.mapreduce.lib.input.TextInputFormat}
- instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.TextInputFormat -->
- <!-- start class org.apache.hadoop.mapred.TextOutputFormat -->
- <class name="TextOutputFormat" extends="org.apache.hadoop.mapred.FileOutputFormat"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.output.TextOutputFormat} instead.">
- <constructor name="TextOutputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getRecordWriter" return="org.apache.hadoop.mapred.RecordWriter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="name" type="java.lang.String"/>
- <param name="progress" type="org.apache.hadoop.util.Progressable"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[An {@link OutputFormat} that writes plain text files.
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.output.TextOutputFormat} instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.TextOutputFormat -->
- <!-- start class org.apache.hadoop.mapred.TextOutputFormat.LineRecordWriter -->
- <class name="TextOutputFormat.LineRecordWriter" extends="java.lang.Object"
- abstract="false"
- static="true" final="false" visibility="protected"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapred.RecordWriter"/>
- <constructor name="TextOutputFormat.LineRecordWriter" type="java.io.DataOutputStream, java.lang.String"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <constructor name="TextOutputFormat.LineRecordWriter" type="java.io.DataOutputStream"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="write"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="java.lang.Object"/>
- <param name="value" type="java.lang.Object"/>
- <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.TIPStatus -->
- <class name="TIPStatus" extends="java.lang.Enum"
- abstract="false"
- static="false" final="true" visibility="public"
- deprecated="not deprecated">
- <method name="values" return="org.apache.hadoop.mapred.TIPStatus[]"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="valueOf" return="org.apache.hadoop.mapred.TIPStatus"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.String"/>
- </method>
- <field name="PENDING" type="org.apache.hadoop.mapred.TIPStatus"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="RUNNING" type="org.apache.hadoop.mapred.TIPStatus"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="COMPLETE" type="org.apache.hadoop.mapred.TIPStatus"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="KILLED" type="org.apache.hadoop.mapred.TIPStatus"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="FAILED" type="org.apache.hadoop.mapred.TIPStatus"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[The states of a {@link TaskInProgress} as seen by the JobTracker.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.TIPStatus -->
- </package>
- <package name="org.apache.hadoop.mapred.jobcontrol">
- <!-- start class org.apache.hadoop.mapred.jobcontrol.Job -->
- <class name="Job" extends="java.lang.Object"
- 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"/>
- <doc>
- <![CDATA[Construct a job.
-
- @param jobConf 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="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="use {@link #getAssignedJobID()} instead">
- <doc>
- <![CDATA[@return the mapred ID of this job
- @deprecated use {@link #getAssignedJobID()} instead]]>
- </doc>
- </method>
- <method name="setMapredJobID"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="use {@link #setAssignedJobID(JobID)} instead">
- <param name="mapredJobID" type="java.lang.String"/>
- <doc>
- <![CDATA[Set the mapred ID for this job.
- @param mapredJobID the mapred job ID for this job.
- @deprecated use {@link #setAssignedJobID(JobID)} instead]]>
- </doc>
- </method>
- <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="not deprecated">
- <param name="mapredJobID" type="org.apache.hadoop.mapred.JobID"/>
- <doc>
- <![CDATA[Set the mapred ID for this job as assigned by the
- mapred framework.
- @param mapredJobID the mapred job ID for this job.]]>
- </doc>
- </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">
- <doc>
- <![CDATA[@return the mapred job conf of this job]]>
- </doc>
- </method>
- <method name="setJobConf"
- abstract="false" native="false" synchronized="false"
- 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="setState"
- abstract="false" native="false" synchronized="true"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="state" type="int"/>
- <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="false"
- 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="false"
- 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="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>
- <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.mapred.jobcontrol.Job"/>
- <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="false"
- 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="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[@return true if this job is in READY state]]>
- </doc>
- </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="SUCCESS" type="int"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="WAITING" type="int"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="RUNNING" type="int"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="READY" type="int"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="FAILED" type="int"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="DEPENDENT_FAILED" type="int"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[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.mapred.jobcontrol.Job -->
- <!-- start class org.apache.hadoop.mapred.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="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="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.mapred.jobcontrol.Job"/>
- <doc>
- <![CDATA[Add a new job.
- @param aJob the new job]]>
- </doc>
- </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>
- <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.mapred.jobcontrol.JobControl -->
- </package>
- <package name="org.apache.hadoop.mapred.join">
- <!-- start class org.apache.hadoop.mapred.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.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>
- <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.io.Writable"/>
- <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.io.Writable"/>
- <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.io.Writable"/>
- <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.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="org.apache.hadoop.io.WritableComparable"
- 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="org.apache.hadoop.io.WritableComparable"/>
- <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="org.apache.hadoop.io.WritableComparable"/>
- <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="org.apache.hadoop.io.WritableComparable"/>
- <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="org.apache.hadoop.io.WritableComparable"
- 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="org.apache.hadoop.io.WritableComparable"/>
- <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="org.apache.hadoop.io.WritableComparable"/>
- <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="org.apache.hadoop.io.WritableComparable"/>
- <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="org.apache.hadoop.io.WritableComparable"/>
- <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="org.apache.hadoop.io.WritableComparable"
- 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="org.apache.hadoop.io.WritableComparable"/>
- <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="org.apache.hadoop.io.Writable"
- 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="org.apache.hadoop.io.WritableComparable"/>
- <param name="value" type="org.apache.hadoop.io.Writable"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </doc>
- </method>
- <method name="createValue" return="org.apache.hadoop.io.Writable"
- 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="org.apache.hadoop.io.Writable"/>
- <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.io.Writable"/>
- <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.io.Writable"/>
- <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="org.apache.hadoop.io.Writable"
- 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="org.apache.hadoop.io.WritableComparable"/>
- <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>
- <field name="CIF" type="org.apache.hadoop.mapred.join.Parser.TType"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="IDENT" type="org.apache.hadoop.mapred.join.Parser.TType"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="COMMA" type="org.apache.hadoop.mapred.join.Parser.TType"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="LPAREN" type="org.apache.hadoop.mapred.join.Parser.TType"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="RPAREN" type="org.apache.hadoop.mapred.join.Parser.TType"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="QUOT" type="org.apache.hadoop.mapred.join.Parser.TType"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="NUM" type="org.apache.hadoop.mapred.join.Parser.TType"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- </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">
- <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="org.apache.hadoop.io.Writable"/>
- <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="org.apache.hadoop.io.Writable"/>
- <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="org.apache.hadoop.io.Writable"/>
- <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.mapred.join.ResetableIterator -->
- <!-- start class org.apache.hadoop.mapred.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.mapred.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="org.apache.hadoop.io.Writable"/>
- <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.io.Writable"/>
- <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="org.apache.hadoop.io.Writable"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- </class>
- <!-- end class org.apache.hadoop.mapred.join.ResetableIterator.EMPTY -->
- <!-- start class org.apache.hadoop.mapred.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.mapred.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="org.apache.hadoop.io.Writable"/>
- <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.io.Writable"/>
- <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.io.Writable"/>
- <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.mapred.join.StreamBackedIterator -->
- <!-- start class org.apache.hadoop.mapred.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>
- <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="org.apache.hadoop.io.WritableComparable"
- 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="org.apache.hadoop.io.WritableComparable"/>
- <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="org.apache.hadoop.io.WritableComparable"/>
- <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="org.apache.hadoop.io.WritableComparable"/>
- <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="org.apache.hadoop.io.WritableComparable"/>
- <param name="value" type="org.apache.hadoop.io.Writable"/>
- <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="org.apache.hadoop.io.WritableComparable"
- 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="org.apache.hadoop.io.Writable"
- 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.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.mapred.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="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.]]>
- </doc>
- </method>
- <method name="createPool"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <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.]]>
- </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"/>
- </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>
- <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="java.lang.Object"/>
- <param name="value" type="java.lang.Object"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <method name="createKey" return="java.lang.Object"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="createValue" return="java.lang.Object"
- 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="java.lang.Object"
- 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">
- <doc>
- <![CDATA[default constructor]]>
- </doc>
- </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>
- <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 startoffsets 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 org.apache.hadoop.mapred.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 org.apache.hadoop.mapred.RecordReader}'s,
- with reading one record per file.
- @see org.apache.hadoop.mapred.FileSplit
- @see CombineFileInputFormat]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.CombineFileSplit -->
- <!-- start class org.apache.hadoop.mapred.lib.DelegatingInputFormat -->
- <class name="DelegatingInputFormat" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapred.InputFormat"/>
- <constructor name="DelegatingInputFormat"
- 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="conf" 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="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="conf" 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} that delegates behaviour of paths to multiple other
- InputFormats.
-
- @see MultipleInputs#addInputPath(JobConf, Path, Class, Class)]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.DelegatingInputFormat -->
- <!-- start class org.apache.hadoop.mapred.lib.DelegatingMapper -->
- <class name="DelegatingMapper" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.mapred.Mapper"/>
- <constructor name="DelegatingMapper"
- 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="java.lang.Object"/>
- <param name="outputCollector" 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="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="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[An {@link Mapper} that delegates behaviour of paths to multiple other
- mappers.
-
- @see MultipleInputs#addInputPath(JobConf, Path, Class, Class)]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.DelegatingMapper -->
- <!-- 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="java.lang.Object"/>
- <param name="val" 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[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 "mapred.data.field.separator"
-
- The map output field list spec is under attribute "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 "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.HashPartitioner -->
- <class name="HashPartitioner" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use
- {@link org.apache.hadoop.mapreduce.lib.partition.HashPartitioner} instead.">
- <implements name="org.apache.hadoop.mapred.Partitioner"/>
- <constructor name="HashPartitioner"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="configure"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- </method>
- <method name="getPartition" return="int"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="java.lang.Object"/>
- <param name="value" type="java.lang.Object"/>
- <param name="numReduceTasks" type="int"/>
- <doc>
- <![CDATA[Use {@link Object#hashCode()} to partition.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Partition keys by their {@link Object#hashCode()}.
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.partition.HashPartitioner} instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.HashPartitioner -->
- <!-- start class org.apache.hadoop.mapred.lib.IdentityMapper -->
- <class name="IdentityMapper" extends="org.apache.hadoop.mapred.MapReduceBase"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.Mapper} instead.">
- <implements name="org.apache.hadoop.mapred.Mapper"/>
- <constructor name="IdentityMapper"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="map"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="java.lang.Object"/>
- <param name="val" 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[The identify function. Input key/value pair is written directly to
- output.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Implements the identity function, mapping inputs directly to outputs.
- @deprecated Use {@link org.apache.hadoop.mapreduce.Mapper} instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.IdentityMapper -->
- <!-- start class org.apache.hadoop.mapred.lib.IdentityReducer -->
- <class name="IdentityReducer" extends="org.apache.hadoop.mapred.MapReduceBase"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.Reducer} instead.">
- <implements name="org.apache.hadoop.mapred.Reducer"/>
- <constructor name="IdentityReducer"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="reduce"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="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[Writes all keys and values directly to output.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[Performs no reduction, writing all input values directly to the output.
- @deprecated Use {@link org.apache.hadoop.mapreduce.Reducer} instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.IdentityReducer -->
- <!-- start class org.apache.hadoop.mapred.lib.InputSampler -->
- <class name="InputSampler" extends="java.lang.Object"
- 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.mapred.JobConf"
- 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>
- <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="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.mapred.lib.InputSampler.Sampler"/>
- <exception name="IOException" type="java.io.IOException"/>
- <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
- org.apache.hadoop.mapred.lib.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 org.apache.hadoop.mapred.lib.TotalOrderPartitioner}.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.InputSampler -->
- <!-- start class org.apache.hadoop.mapred.lib.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.mapred.lib.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="java.lang.Object[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="inf" type="org.apache.hadoop.mapred.InputFormat"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <exception name="IOException" type="java.io.IOException"/>
- <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.mapred.lib.InputSampler.IntervalSampler -->
- <!-- start class org.apache.hadoop.mapred.lib.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.mapred.lib.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="java.lang.Object[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="inf" type="org.apache.hadoop.mapred.InputFormat"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <exception name="IOException" type="java.io.IOException"/>
- <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.mapred.lib.InputSampler.RandomSampler -->
- <!-- start interface org.apache.hadoop.mapred.lib.InputSampler.Sampler -->
- <interface name="InputSampler.Sampler" abstract="true"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <method name="getSample" return="java.lang.Object[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="inf" type="org.apache.hadoop.mapred.InputFormat"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <exception name="IOException" type="java.io.IOException"/>
- <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.mapred.InputFormat}.]]>
- </doc>
- </interface>
- <!-- end interface org.apache.hadoop.mapred.lib.InputSampler.Sampler -->
- <!-- start class org.apache.hadoop.mapred.lib.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.mapred.lib.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="java.lang.Object[]"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="inf" type="org.apache.hadoop.mapred.InputFormat"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <exception name="IOException" type="java.io.IOException"/>
- <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.mapred.lib.InputSampler.SplitSampler -->
- <!-- start class org.apache.hadoop.mapred.lib.InverseMapper -->
- <class name="InverseMapper" extends="org.apache.hadoop.mapred.MapReduceBase"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.lib.map.InverseMapper}
- instead.">
- <implements name="org.apache.hadoop.mapred.Mapper"/>
- <constructor name="InverseMapper"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="map"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="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[The inverse function. Input keys and values are swapped.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[A {@link Mapper} that swaps keys and values.
- @deprecated Use {@link org.apache.hadoop.mapreduce.lib.map.InverseMapper}
- instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.InverseMapper -->
- <!-- start class org.apache.hadoop.mapred.lib.KeyFieldBasedComparator -->
- <class name="KeyFieldBasedComparator" extends="org.apache.hadoop.io.WritableComparator"
- 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>
- <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[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
- map.output.key.field.separator.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.KeyFieldBasedComparator -->
- <!-- start class org.apache.hadoop.mapred.lib.KeyFieldBasedPartitioner -->
- <class name="KeyFieldBasedPartitioner" extends="java.lang.Object"
- 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>
- <method name="getPartition" return="int"
- 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="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>
- <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.LongSumReducer -->
- <class name="LongSumReducer" extends="org.apache.hadoop.mapred.MapReduceBase"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="Use {@link org.apache.hadoop.mapreduce.lib.reduce.LongSumReducer}
- instead.">
- <implements name="org.apache.hadoop.mapred.Reducer"/>
- <constructor name="LongSumReducer"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="reduce"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="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"/>
- </method>
- <doc>
- <![CDATA[A {@link Reducer} that sums long values.
- @deprecated Use {@link org.apache.hadoop.mapreduce.lib.reduce.LongSumReducer}
- instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.LongSumReducer -->
- <!-- start class org.apache.hadoop.mapred.lib.MultipleInputs -->
- <class name="MultipleInputs" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="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="java.lang.Object"/>
- <param name="value" type="java.lang.Object"/>
- <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="java.lang.Object"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="key" type="java.lang.Object"/>
- <param name="value" type="java.lang.Object"/>
- <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="java.lang.Object"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="key" type="java.lang.Object"/>
- <param name="value" type="java.lang.Object"/>
- <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 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="Use
- {@link org.apache.hadoop.mapreduce.lib.output.NullOutputFormat} instead.">
- <implements name="org.apache.hadoop.mapred.OutputFormat"/>
- <constructor name="NullOutputFormat"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getRecordWriter" return="org.apache.hadoop.mapred.RecordWriter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="name" type="java.lang.String"/>
- <param name="progress" type="org.apache.hadoop.util.Progressable"/>
- </method>
- <method name="checkOutputSpecs"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/>
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- </method>
- <doc>
- <![CDATA[Consume all outputs and put them in /dev/null.
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.output.NullOutputFormat} instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.NullOutputFormat -->
- <!-- start class org.apache.hadoop.mapred.lib.RegexMapper -->
- <class name="RegexMapper" extends="org.apache.hadoop.mapred.MapReduceBase"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="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="java.lang.Object"/>
- <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="Use
- {@link org.apache.hadoop.mapreduce.lib.map.TokenCounterMapper} instead.">
- <implements name="org.apache.hadoop.mapred.Mapper"/>
- <constructor name="TokenCountMapper"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="map"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="java.lang.Object"/>
- <param name="value" type="org.apache.hadoop.io.Text"/>
- <param name="output" type="org.apache.hadoop.mapred.OutputCollector"/>
- <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
- <exception name="IOException" type="java.io.IOException"/>
- </method>
- <doc>
- <![CDATA[A {@link Mapper} that maps text values into <token,freq> pairs. Uses
- {@link StringTokenizer} to break text into tokens.
- @deprecated Use
- {@link org.apache.hadoop.mapreduce.lib.map.TokenCounterMapper} instead.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.TokenCountMapper -->
- <!-- start class org.apache.hadoop.mapred.lib.TotalOrderPartitioner -->
- <class name="TotalOrderPartitioner" extends="java.lang.Object"
- 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"/>
- <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
- org.apache.hadoop.mapred.JobConf#getNumReduceTasks} - 1 keys.]]>
- </doc>
- </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.WritableComparable"/>
- <param name="value" type="java.lang.Object"/>
- <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="job" type="org.apache.hadoop.mapred.JobConf"/>
- <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="job" type="org.apache.hadoop.mapred.JobConf"/>
- <doc>
- <![CDATA[Get the path to the SequenceFile storing the sorted partition keyset.
- @see #setPartitionFile(JobConf,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>
- <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="java.lang.Object"
- 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">
- <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.mapred.lib.aggregate.DoubleValueSum -->
- <!-- start class org.apache.hadoop.mapred.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.mapred.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.mapred.lib.aggregate.LongValueMax -->
- <!-- start class org.apache.hadoop.mapred.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.mapred.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.mapred.lib.aggregate.LongValueMin -->
- <!-- start class org.apache.hadoop.mapred.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.mapred.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.mapred.lib.aggregate.LongValueSum -->
- <!-- start class org.apache.hadoop.mapred.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.mapred.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.mapred.lib.aggregate.StringValueMax -->
- <!-- start class org.apache.hadoop.mapred.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.mapred.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.mapred.lib.aggregate.StringValueMin -->
- <!-- start class org.apache.hadoop.mapred.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.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>
- <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>
- <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="java.lang.Object"
- 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="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="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">
- <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.mapred.lib.aggregate.ValueAggregator -->
- <!-- start class org.apache.hadoop.mapred.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.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="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="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>
- <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.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="org.apache.hadoop.io.WritableComparable"/>
- <param name="arg1" type="org.apache.hadoop.io.Writable"/>
- <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">
- <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="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="org.apache.hadoop.io.WritableComparable"/>
- <param name="value" type="org.apache.hadoop.io.Writable"/>
- <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="org.apache.hadoop.io.WritableComparable"/>
- <param name="arg1" type="org.apache.hadoop.io.Writable"/>
- <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="java.lang.Object"
- 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>
- <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.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="java.lang.Object"
- 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>
- <doc>
- <![CDATA[A container for configuration property names for jobs with DB input/output.
- <br>
- The job can be configured using the static methods in this class,
- {@link DBInputFormat}, and {@link DBOutputFormat}.
- <p>
- Alternatively, the properties can be set in the configuration with proper
- values.
-
- @see DBConfiguration#configureDB(JobConf, String, String, String, String)
- @see DBInputFormat#setInput(JobConf, Class, String, String)
- @see DBInputFormat#setInput(JobConf, Class, String, String, String, String...)
- @see DBOutputFormat#setOutput(JobConf, String, String...)]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.lib.db.DBConfiguration -->
- <!-- start class org.apache.hadoop.mapred.lib.db.DBInputFormat -->
- <class name="DBInputFormat" extends="java.lang.Object"
- 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="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.mapred.JobConf"/>
- <param name="inputClass" type="java.lang.Class"/>
- <param name="tableName" type="java.lang.String"/>
- <param name="conditions" type="java.lang.String"/>
- <param name="orderBy" type="java.lang.String"/>
- <param name="fieldNames" type="java.lang.String[]"/>
- <doc>
- <![CDATA[Initializes the map-part of the job with the appropriate input settings.
-
- @param job The job
- @param inputClass the class object implementing DBWritable, which is the
- Java object holding tuple fields.
- @param tableName The table to read data from
- @param conditions The condition which to select data with, eg. '(updated >
- 20070101 AND length > 0)'
- @param orderBy the fieldNames in the orderBy clause.
- @param fieldNames The field names in the table
- @see #setInput(JobConf, Class, String, String)]]>
- </doc>
- </method>
- <method name="setInput"
- abstract="false" native="false" synchronized="false"
- static="true" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
- <param name="inputClass" type="java.lang.Class"/>
- <param name="inputQuery" type="java.lang.String"/>
- <param name="inputCountQuery" type="java.lang.String"/>
- <doc>
- <![CDATA[Initializes the map-part of the job with the appropriate input settings.
-
- @param job The job
- @param inputClass the class object implementing DBWritable, which is the
- Java object holding tuple fields.
- @param inputQuery the input query to select fields. Example :
- "SELECT f1, f2, f3 FROM Mytable ORDER BY f1"
- @param inputCountQuery the input query that returns the number of records in
- the table.
- Example : "SELECT COUNT(f1) FROM Mytable"
- @see #setInput(JobConf, Class, String, String, String, String...)]]>
- </doc>
- </method>
- <doc>
- <![CDATA[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.mapred.lib.db.DBInputFormat -->
- <!-- start class org.apache.hadoop.mapred.lib.db.DBInputFormat.DBInputSplit -->
- <class name="DBInputFormat.DBInputSplit" extends="java.lang.Object"
- 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>
- <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.mapred.lib.db.DBInputFormat.DBInputSplit -->
- <!-- start class org.apache.hadoop.mapred.lib.db.DBInputFormat.DBRecordReader -->
- <class name="DBInputFormat.DBRecordReader" extends="java.lang.Object"
- 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"
- 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="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="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="org.apache.hadoop.mapred.lib.db.DBWritable"
- 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"/>
- <doc>
- <![CDATA[{@inheritDoc}]]>
- </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="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="org.apache.hadoop.mapred.lib.db.DBWritable"/>
- <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="java.lang.Object"
- 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>
- <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.mapred.lib.db.DBInputFormat.NullDBWritable -->
- <!-- start class org.apache.hadoop.mapred.lib.db.DBOutputFormat -->
- <class name="DBOutputFormat" extends="java.lang.Object"
- 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="constructQuery" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- 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="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. If unknown, supply the appropriate
- number of nulls.]]>
- </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.mapred.lib.db.DBOutputFormat -->
- <!-- start class org.apache.hadoop.mapred.lib.db.DBOutputFormat.DBRecordWriter -->
- <class name="DBOutputFormat.DBRecordWriter" extends="java.lang.Object"
- 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>
- <method name="write"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="key" type="org.apache.hadoop.mapred.lib.db.DBWritable"/>
- <param name="value" type="java.lang.Object"/>
- <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">
- <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.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
- "hadoop.pipes.command.file" 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>
- <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 refresh the service-level authorization policy.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapred.tools.MRAdmin -->
- </package>
- <package name="org.apache.hadoop.mapreduce">
- <!-- 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>
- <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="protected"
- deprecated="not deprecated">
- </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="findCounter" return="org.apache.hadoop.mapreduce.Counter"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <param name="counterName" type="java.lang.String"/>
- <param name="displayName" type="java.lang.String"/>
- <doc>
- <![CDATA[Internal to 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>
- <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#mapred.min.split.size">
- mapred.min.split.size</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.JobContext"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <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="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="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="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="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="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="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="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.mapreduce.TaskAttemptID"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Kill indicated task attempt.
-
- @param taskId the id of the task to be terminated.
- @throws IOException]]>
- </doc>
- </method>
- <method name="failTask"
- 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"/>
- <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"/>
- <doc>
- <![CDATA[Gets the counters for this job.
-
- @return the counters for this job.
- @throws IOException]]>
- </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>
- <doc>
- <![CDATA[The job submitter's view of the Job. 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.]]>
- </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>
- <field name="DEFINE" type="org.apache.hadoop.mapreduce.Job.JobState"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- <field name="RUNNING" type="org.apache.hadoop.mapreduce.Job.JobState"
- transient="false" volatile="false"
- static="true" final="true" visibility="public"
- deprecated="not deprecated">
- </field>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.Job.JobState -->
- <!-- start class org.apache.hadoop.mapreduce.JobContext -->
- <class name="JobContext" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="JobContext" type="org.apache.hadoop.conf.Configuration, org.apache.hadoop.mapreduce.JobID"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <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>
- <field name="INPUT_FORMAT_CLASS_ATTR" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="MAP_CLASS_ATTR" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="COMBINE_CLASS_ATTR" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="REDUCE_CLASS_ATTR" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="OUTPUT_FORMAT_CLASS_ATTR" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="PARTITIONER_CLASS_ATTR" type="java.lang.String"
- transient="false" volatile="false"
- static="true" final="true" visibility="protected"
- deprecated="not deprecated">
- </field>
- <field name="conf" type="org.apache.hadoop.mapred.JobConf"
- transient="false" volatile="false"
- static="false" final="true" visibility="protected"
- deprecated="not deprecated">
- </field>
- <doc>
- <![CDATA[A read-only view of the job that is provided to the tasks while they
- are running.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.JobContext -->
- <!-- 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.MapContext -->
- <class name="MapContext" extends="org.apache.hadoop.mapreduce.TaskInputOutputContext"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="MapContext" type="org.apache.hadoop.conf.Configuration, org.apache.hadoop.mapreduce.TaskAttemptID, org.apache.hadoop.mapreduce.RecordReader, org.apache.hadoop.mapreduce.RecordWriter, org.apache.hadoop.mapreduce.OutputCommitter, org.apache.hadoop.mapreduce.StatusReporter, org.apache.hadoop.mapreduce.InputSplit"
- 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="java.lang.Object"
- 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="java.lang.Object"
- 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>
- <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>
- </class>
- <!-- end class 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="java.lang.Object"/>
- <param name="value" type="java.lang.Object"/>
- <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 {
- StringTokenizer itr = new StringTokenizer(value.toString());
- while (itr.hasMoreTokens()) {
- word.set(itr.nextToken());
- context.collect(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="org.apache.hadoop.mapreduce.MapContext"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="Mapper.Context" type="org.apache.hadoop.conf.Configuration, org.apache.hadoop.mapreduce.TaskAttemptID, org.apache.hadoop.mapreduce.RecordReader, org.apache.hadoop.mapreduce.RecordWriter, org.apache.hadoop.mapreduce.OutputCommitter, org.apache.hadoop.mapreduce.StatusReporter, org.apache.hadoop.mapreduce.InputSplit"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </constructor>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.Mapper.Context -->
- <!-- 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="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 cleaning up the job's output after job completion
-
- @param jobContext Context of the job whose output is being written.
- @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="java.lang.Object"/>
- <param name="value" type="java.lang.Object"/>
- <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.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="java.lang.Object"
- 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="java.lang.Object"
- 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="java.lang.Object"/>
- <param name="value" type="java.lang.Object"/>
- <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 class org.apache.hadoop.mapreduce.ReduceContext -->
- <class name="ReduceContext" extends="org.apache.hadoop.mapreduce.TaskInputOutputContext"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="ReduceContext" type="org.apache.hadoop.conf.Configuration, org.apache.hadoop.mapreduce.TaskAttemptID, org.apache.hadoop.mapred.RawKeyValueIterator, org.apache.hadoop.mapreduce.Counter, org.apache.hadoop.mapreduce.RecordWriter, org.apache.hadoop.mapreduce.OutputCommitter, org.apache.hadoop.mapreduce.StatusReporter, org.apache.hadoop.io.RawComparator, java.lang.Class, java.lang.Class"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- <exception name="IOException" type="java.io.IOException"/>
- </constructor>
- <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="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.]]>
- </doc>
- </method>
- <method name="getCurrentKey" return="java.lang.Object"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getCurrentValue" return="java.lang.Object"
- 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"/>
- <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>
- <field name="reporter" type="org.apache.hadoop.util.Progressable"
- transient="false" volatile="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </field>
- <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>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.ReduceContext -->
- <!-- start class org.apache.hadoop.mapreduce.ReduceContext.ValueIterable -->
- <class name="ReduceContext.ValueIterable" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <implements name="java.lang.Iterable"/>
- <constructor name="ReduceContext.ValueIterable"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- </constructor>
- <method name="iterator" return="java.util.Iterator"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.ReduceContext.ValueIterable -->
- <!-- start class org.apache.hadoop.mapreduce.ReduceContext.ValueIterator -->
- <class name="ReduceContext.ValueIterator" extends="java.lang.Object"
- abstract="false"
- static="false" final="false" visibility="protected"
- deprecated="not deprecated">
- <implements name="java.util.Iterator"/>
- <constructor name="ReduceContext.ValueIterator"
- 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="java.lang.Object"
- 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>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.ReduceContext.ValueIterator -->
- <!-- start class org.apache.hadoop.mapreduce.Reducer -->
- <class name="Reducer" extends="java.lang.Object"
- abstract="true"
- 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="java.lang.Object"/>
- <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 {
- int sum = 0;
- for (IntWritable val : values) {
- sum += val.get();
- }
- result.set(sum);
- context.collect(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="org.apache.hadoop.mapreduce.ReduceContext"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="Reducer.Context" type="org.apache.hadoop.conf.Configuration, org.apache.hadoop.mapreduce.TaskAttemptID, org.apache.hadoop.mapred.RawKeyValueIterator, org.apache.hadoop.mapreduce.Counter, org.apache.hadoop.mapreduce.RecordWriter, org.apache.hadoop.mapreduce.OutputCommitter, org.apache.hadoop.mapreduce.StatusReporter, org.apache.hadoop.io.RawComparator, java.lang.Class, java.lang.Class"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <exception name="IOException" type="java.io.IOException"/>
- <exception name="InterruptedException" type="java.lang.InterruptedException"/>
- </constructor>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.Reducer.Context -->
- <!-- start class org.apache.hadoop.mapreduce.StatusReporter -->
- <class name="StatusReporter" extends="java.lang.Object"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="StatusReporter"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <method name="getCounter" return="org.apache.hadoop.mapreduce.Counter"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="name" type="java.lang.Enum"/>
- </method>
- <method name="getCounter" return="org.apache.hadoop.mapreduce.Counter"
- abstract="true" 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"/>
- </method>
- <method name="progress"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="setStatus"
- abstract="true" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="status" type="java.lang.String"/>
- </method>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.StatusReporter -->
- <!-- start class org.apache.hadoop.mapreduce.TaskAttemptContext -->
- <class name="TaskAttemptContext" extends="org.apache.hadoop.mapreduce.JobContext"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.util.Progressable"/>
- <constructor name="TaskAttemptContext" type="org.apache.hadoop.conf.Configuration, org.apache.hadoop.mapreduce.TaskAttemptID"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <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"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[Set the current status of the task to the given string.]]>
- </doc>
- </method>
- <method name="getStatus" return="java.lang.String"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Get the last set status message.
- @return the current status message]]>
- </doc>
- </method>
- <method name="progress"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Report progress. The subtypes actually do work in this method.]]>
- </doc>
- </method>
- <doc>
- <![CDATA[The context for task attempts.]]>
- </doc>
- </class>
- <!-- end class 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, boolean, 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 isMap whether the tip is a map
- @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="isMap" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns whether this TaskAttemptID is a map ID]]>
- </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.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, boolean, 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 isMap whether the tip is a map
- @param id the tip number]]>
- </doc>
- </constructor>
- <constructor name="TaskID" type="java.lang.String, int, boolean, 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 isMap whether the tip is a map
- @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="isMap" return="boolean"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <doc>
- <![CDATA[Returns whether this TaskID is a map ID]]>
- </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>
- <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 class org.apache.hadoop.mapreduce.TaskInputOutputContext -->
- <class name="TaskInputOutputContext" extends="org.apache.hadoop.mapreduce.TaskAttemptContext"
- abstract="true"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <implements name="org.apache.hadoop.util.Progressable"/>
- <constructor name="TaskInputOutputContext" type="org.apache.hadoop.conf.Configuration, org.apache.hadoop.mapreduce.TaskAttemptID, org.apache.hadoop.mapreduce.RecordWriter, org.apache.hadoop.mapreduce.OutputCommitter, org.apache.hadoop.mapreduce.StatusReporter"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </constructor>
- <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[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="java.lang.Object"
- 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 object or null if there isn't one
- @throws IOException
- @throws InterruptedException]]>
- </doc>
- </method>
- <method name="getCurrentValue" return="java.lang.Object"
- 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 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="java.lang.Object"/>
- <param name="value" type="java.lang.Object"/>
- <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"/>
- </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="progress"
- 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="status" 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>
- <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>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.TaskInputOutputContext -->
- </package>
- <package name="org.apache.hadoop.mapreduce.lib.input">
- <!-- 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="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.]]>
- </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>
- <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" 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.LineRecordReader -->
- <class name="LineRecordReader" extends="org.apache.hadoop.mapreduce.RecordReader"
- abstract="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <constructor name="LineRecordReader"
- 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="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="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"/>
- </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">
- </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">
- <doc>
- <![CDATA[Get the progress within the split]]>
- </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>
- <doc>
- <![CDATA[Treats keys as offset in file and value as line.]]>
- </doc>
- </class>
- <!-- end class org.apache.hadoop.mapreduce.lib.input.LineRecordReader -->
- <!-- 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="java.lang.Object"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- </method>
- <method name="getCurrentValue" return="java.lang.Object"
- 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.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="java.lang.Object"/>
- <param name="value" type="java.lang.Object"/>
- <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>
- <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.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 -->
- </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="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"/>
- <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"/>
- <doc>
- <![CDATA[Delete the work directory]]>
- </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>
- <doc>
- <![CDATA[An {@link OutputCommitter} that commits files specified
- in job output directory i.e. ${mapred.output.dir}.]]>
- </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.mapred.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>${mapred.output.dir}/_temporary/_${taskid}</tt>
- sub-directory for each task-attempt on HDFS where the output of the
- task-attempt goes. On successful completion of the task-attempt the files
- in the <tt>${mapred.output.dir}/_temporary/_${taskid}</tt> (only)
- are <i>promoted</i> to <tt>${mapred.output.dir}</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 $name-[mr]-$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="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>
- <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.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.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="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>
- <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="java.lang.Object"/>
- <param name="value" type="java.lang.Object"/>
- <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.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="java.lang.Object"/>
- <param name="value" type="java.lang.Object"/>
- <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 -->
- </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="java.lang.Object"/>
- <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="java.lang.Object"/>
- <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 -->
- </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="archive"
- abstract="false" native="false" synchronized="false"
- static="false" final="false" visibility="public"
- deprecated="not deprecated">
- <param name="srcPaths" type="java.util.List"/>
- <param name="archiveName" type="java.lang.String"/>
- <param name="dest" type="org.apache.hadoop.fs.Path"/>
- <exception name="IOException" type="java.io.IOException"/>
- <doc>
- <![CDATA[archive the given source paths into
- the dest
- @param srcPaths the src paths to be archived
- @param dest the dest dir that will contain the archive]]>
- </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[the main driver for creating the archives
- it takes at least two command line parameters. 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>
- <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>
- <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="org.apache.hadoop.io.WritableComparable"/>
- <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>
- </api>
|