ResourceInputFormat.java

package org.archive.hadoop;

import java.io.IOException;

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.JobContext;
import org.apache.hadoop.mapreduce.RecordReader;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.archive.resource.MetaData;

public class ResourceInputFormat extends FileInputFormat<ResourceContext, MetaData>{

	@Override
	public RecordReader<ResourceContext, MetaData> createRecordReader(InputSplit inputSplit,
			TaskAttemptContext context) throws IOException, InterruptedException {
		
		return new ResourceRecordReader();
	}

	/* (non-Javadoc)
	 * @see org.apache.hadoop.mapreduce.lib.input.FileInputFormat#isSplitable(org.apache.hadoop.mapreduce.JobContext, org.apache.hadoop.fs.Path)
	 */
	@Override
	protected boolean isSplitable(JobContext context, Path filename) {
		// TODO: ensure this works... it should be may be losing records between..
		return false;
	}
}