LineDereferencingInputFormat.java

/*
 *  This file is part of the Wayback archival access software
 *   (http://archive-access.sourceforge.net/projects/wayback/).
 *
 *  Licensed to the Internet Archive (IA) by one or more individual 
 *  contributors. 
 *
 *  The IA licenses this file to You under the Apache License, Version 2.0
 *  (the "License"); you may not use this file except in compliance with
 *  the License.  You may obtain a copy of the License at
 *
 *      http://www.apache.org/licenses/LICENSE-2.0
 *
 *  Unless required by applicable law or agreed to in writing, software
 *  distributed under the License is distributed on an "AS IS" BASIS,
 *  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 *  See the License for the specific language governing permissions and
 *  limitations under the License.
 */
package org.archive.hadoop.mapreduce;

import java.io.IOException;
import java.util.List;

import org.apache.hadoop.io.Text;
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.apache.hadoop.mapreduce.lib.input.TextInputFormat;

/**
 * FileInputFormat subclass which assumes the configured input files are lines
 * containing hdfs:// pointers to the actual Text data.
 * 
 * @author brad
 *
 */
public class LineDereferencingInputFormat extends FileInputFormat<Text, Text>{
	TextInputFormat tif = null;

	@Override
	public List<InputSplit> getSplits(JobContext context) throws IOException {
		if(tif == null) {
			tif = new TextInputFormat();
		}
		return tif.getSplits(context);
	}

	@Override
	public RecordReader<Text, Text> createRecordReader(InputSplit split,
			TaskAttemptContext context) throws IOException,
			InterruptedException {
		return new LineDereferencingRecordReader();
	}
}