001/**
002 * Licensed to the Apache Software Foundation (ASF) under one
003 * or more contributor license agreements.  See the NOTICE file
004 * distributed with this work for additional information
005 * regarding copyright ownership.  The ASF licenses this file
006 * to you under the Apache License, Version 2.0 (the
007 * "License"); you may not use this file except in compliance
008 * with the License.  You may obtain a copy of the License at
009 *
010 *     http://www.apache.org/licenses/LICENSE-2.0
011 *
012 * Unless required by applicable law or agreed to in writing, software
013 * distributed under the License is distributed on an "AS IS" BASIS,
014 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
015 * See the License for the specific language governing permissions and
016 * limitations under the License.
017 */
018
019package org.apache.hadoop.mapreduce.lib.input;
020
021import java.io.IOException;
022
023import org.apache.hadoop.classification.InterfaceAudience;
024import org.apache.hadoop.classification.InterfaceStability;
025import org.apache.hadoop.fs.Path;
026import org.apache.hadoop.io.Text;
027import org.apache.hadoop.io.compress.CompressionCodec;
028import org.apache.hadoop.io.compress.CompressionCodecFactory;
029import org.apache.hadoop.io.compress.SplittableCompressionCodec;
030import org.apache.hadoop.mapreduce.InputFormat;
031import org.apache.hadoop.mapreduce.InputSplit;
032import org.apache.hadoop.mapreduce.JobContext;
033import org.apache.hadoop.mapreduce.RecordReader;
034import org.apache.hadoop.mapreduce.TaskAttemptContext;
035
036/**
037 * An {@link InputFormat} for plain text files. Files are broken into lines.
038 * Either line feed or carriage-return are used to signal end of line. 
039 * Each line is divided into key and value parts by a separator byte. If no
040 * such a byte exists, the key will be the entire line and value will be empty.
041 * The separator byte can be specified in config file under the attribute name
042 * mapreduce.input.keyvaluelinerecordreader.key.value.separator. The default
043 * is the tab character ('\t').
044 */
045@InterfaceAudience.Public
046@InterfaceStability.Stable
047public class KeyValueTextInputFormat extends FileInputFormat<Text, Text> {
048
049  @Override
050  protected boolean isSplitable(JobContext context, Path file) {
051    final CompressionCodec codec =
052      new CompressionCodecFactory(context.getConfiguration()).getCodec(file);
053    if (null == codec) {
054      return true;
055    }
056    return codec instanceof SplittableCompressionCodec;
057  }
058
059  public RecordReader<Text, Text> createRecordReader(InputSplit genericSplit,
060      TaskAttemptContext context) throws IOException {
061    
062    context.setStatus(genericSplit.toString());
063    return new KeyValueLineRecordReader(context.getConfiguration());
064  }
065
066}