WholeFileInputFormat.java

package com.caseystella.util.common.hadoop.input.whole;

import java.io.IOException;


import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.BytesWritable;
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.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;

/**
 * This is pretty much just from Tom White's book.  I needed it so I could wrap it in a
 * Pig Loader.
 */
public class WholeFileInputFormat extends FileInputFormat<Text, BytesWritable> {

    @Override
    public RecordReader<Text, BytesWritable> createRecordReader(InputSplit inputSplit, TaskAttemptContext taskAttemptContext) throws IOException, InterruptedException {
        RecordReader<Text, BytesWritable> ret = new WholeFileRecordReader();
        ret.initialize((FileSplit)inputSplit, taskAttemptContext);
        return ret;
    }
}