001 /* 002 * Copyright (c) 2007-2014 Concurrent, Inc. All Rights Reserved. 003 * 004 * Project and contact information: http://www.cascading.org/ 005 * 006 * This file is part of the Cascading project. 007 * 008 * Licensed under the Apache License, Version 2.0 (the "License"); 009 * you may not use this file except in compliance with the License. 010 * You may obtain a copy of the License at 011 * 012 * http://www.apache.org/licenses/LICENSE-2.0 013 * 014 * Unless required by applicable law or agreed to in writing, software 015 * distributed under the License is distributed on an "AS IS" BASIS, 016 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 017 * See the License for the specific language governing permissions and 018 * limitations under the License. 019 */ 020 021 package cascading.flow.hadoop.stream; 022 023 import java.util.IdentityHashMap; 024 import java.util.Map; 025 026 import cascading.CascadingException; 027 import cascading.flow.FlowProcess; 028 import cascading.flow.SliceCounters; 029 import cascading.flow.hadoop.HadoopCoGroupClosure; 030 import cascading.flow.stream.Duct; 031 import cascading.flow.stream.DuctException; 032 import cascading.flow.stream.SpliceGate; 033 import cascading.flow.stream.StreamGraph; 034 import cascading.pipe.CoGroup; 035 import cascading.tuple.Tuple; 036 import cascading.tuple.TupleEntry; 037 import cascading.tuple.io.IndexTuple; 038 import cascading.tuple.io.TuplePair; 039 040 /** 041 * 042 */ 043 public class HadoopCoGroupGate extends HadoopGroupGate 044 { 045 private final Map<Duct, Integer> posMap = new IdentityHashMap<Duct, Integer>(); 046 047 public HadoopCoGroupGate( FlowProcess flowProcess, CoGroup coGroup, SpliceGate.Role role ) 048 { 049 super( flowProcess, coGroup, role ); 050 } 051 052 @Override 053 public void bind( StreamGraph streamGraph ) 054 { 055 super.bind( streamGraph ); 056 057 if( role == Role.sink ) 058 orderDucts( streamGraph ); 059 } 060 061 @Override 062 public void prepare() 063 { 064 super.prepare(); 065 066 if( role != Role.sink ) 067 closure = new HadoopCoGroupClosure( flowProcess, splice.getNumSelfJoins(), keyFields, valuesFields ); 068 else 069 makePosMap( posMap ); 070 071 if( grouping != null && splice.getJoinDeclaredFields() != null && splice.getJoinDeclaredFields().isNone() ) 072 grouping.joinerClosure = closure; 073 } 074 075 @Override 076 public void receive( Duct previous, TupleEntry incomingEntry ) 077 { 078 Integer pos = posMap.get( previous ); 079 080 Tuple groupTuple = keyBuilder[ pos ].makeResult( incomingEntry.getTuple(), null ); 081 Tuple sortTuple = sortFields == null ? null : sortBuilder[ pos ].makeResult( incomingEntry.getTuple(), null ); 082 Tuple valuesTuple = valuesBuilder[ pos ].makeResult( incomingEntry.getTuple(), null ); 083 084 Tuple groupKey = sortTuple == null ? groupTuple : new TuplePair( groupTuple, sortTuple ); 085 086 try 087 { 088 collector.collect( new IndexTuple( pos, groupKey ), new IndexTuple( pos, valuesTuple ) ); 089 flowProcess.increment( SliceCounters.Tuples_Written, 1 ); 090 } 091 catch( OutOfMemoryError error ) 092 { 093 handleReThrowableException( "out of memory, try increasing task memory allocation", error ); 094 } 095 catch( CascadingException exception ) 096 { 097 handleException( exception, incomingEntry ); 098 } 099 catch( Throwable throwable ) 100 { 101 handleException( new DuctException( "internal error: " + incomingEntry.getTuple().print(), throwable ), incomingEntry ); 102 } 103 } 104 105 @Override 106 protected Tuple unwrapGrouping( Tuple key ) 107 { 108 return ( (IndexTuple) key ).getTuple(); 109 } 110 }