Hack#15

CustomCombineFileInputFormat.java

package org.hadoophacks.mapreduce.lib.input;

import java.io.IOException;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.RecordReader;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.mapreduce.lib.input.CombineFileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.CombineFileRecordReader;
import org.apache.hadoop.mapreduce.lib.input.CombineFileSplit;
import org.apache.hadoop.conf.Configuration;

public class CustomCombineFileInputFormat extends
	    CombineFileInputFormat<Text, Text> {
    
    public RecordReader<Text, Text> createRecordReader(
	    InputSplit split, TaskAttemptContext context) {

	try {
	    Configuration conf = context.getConfiguration();
	
	    CombineFileRecordReader<Text, Text> reader = new CombineFileRecordReader<Text, Text>(
		              (CombineFileSplit) split, context, CombineFileLineRecordReader.class);
	    	    
	    return reader;
	} catch (IOException e) {
	    e.printStackTrace();
	    return null;
	}
    }
}