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.tap.hadoop.io;
022    
023    import java.io.IOException;
024    
025    import cascading.flow.FlowProcess;
026    import cascading.flow.SliceCounters;
027    import cascading.tap.Tap;
028    import cascading.tap.hadoop.util.MeasuredOutputCollector;
029    import cascading.tuple.TupleEntrySchemeCollector;
030    import org.apache.hadoop.mapred.JobConf;
031    import org.apache.hadoop.mapred.OutputCollector;
032    import org.apache.hadoop.mapred.RecordReader;
033    
034    /**
035     * Class HadoopTupleEntrySchemeCollector is a kind of {@link cascading.tuple.TupleEntryCollector} that writes tuples to the resource managed by
036     * a particular {@link cascading.tap.Tap} instance.
037     */
038    public class HadoopTupleEntrySchemeCollector extends TupleEntrySchemeCollector<JobConf, OutputCollector>
039      {
040      private MeasuredOutputCollector measuredOutputCollector;
041    
042      public HadoopTupleEntrySchemeCollector( FlowProcess<JobConf> flowProcess, Tap<JobConf, RecordReader, OutputCollector> tap ) throws IOException
043        {
044        super( flowProcess, tap.getScheme(), makeCollector( flowProcess, tap, null ), tap.getIdentifier() );
045        }
046    
047      public HadoopTupleEntrySchemeCollector( FlowProcess<JobConf> flowProcess, Tap<JobConf, RecordReader, OutputCollector> tap, OutputCollector outputCollector ) throws IOException
048        {
049        super( flowProcess, tap.getScheme(), makeCollector( flowProcess, tap, outputCollector ), tap.getIdentifier() );
050        }
051    
052      private static OutputCollector makeCollector( FlowProcess<JobConf> flowProcess, Tap<JobConf, RecordReader, OutputCollector> tap, OutputCollector outputCollector ) throws IOException
053        {
054        if( outputCollector != null )
055          return outputCollector;
056    
057        return new TapOutputCollector( flowProcess, tap );
058        }
059    
060      @Override
061      protected OutputCollector<?, ?> wrapOutput( OutputCollector outputCollector )
062        {
063        if( measuredOutputCollector == null )
064          measuredOutputCollector = new MeasuredOutputCollector( getFlowProcess(), SliceCounters.Write_Duration );
065    
066        measuredOutputCollector.setOutputCollector( outputCollector );
067    
068        return measuredOutputCollector;
069        }
070      }