FileStreamInputFormat.java

/**
 * Copyright 2010 Nube Technologies
 * 
 * Licensed 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 co.nubetech.hiho.mapreduce.lib.input;

import java.io.IOException;

import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.Path;
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.FileSplit;

/**
 * This class returns file streams as records which can be used directly for
 * load data infile operations of databases The key is the filename
 * 
 * @author sgoyal
 * 
 */

public class FileStreamInputFormat extends
		FileInputFormat<Text, FSDataInputStream> {

	@Override
	protected boolean isSplitable(JobContext context, Path filename) {
		return false;
	}

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

}