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    
019    package org.apache.hadoop.mapred;
020    
021    import java.io.IOException;
022    
023    import org.apache.hadoop.classification.InterfaceAudience;
024    import org.apache.hadoop.classification.InterfaceStability;
025    import org.apache.hadoop.fs.FileSystem;
026    import org.apache.hadoop.fs.Path;
027    import org.apache.hadoop.io.Text;
028    import org.apache.hadoop.io.compress.CompressionCodec;
029    import org.apache.hadoop.io.compress.CompressionCodecFactory;
030    import org.apache.hadoop.io.compress.SplittableCompressionCodec;
031    
032    /**
033     * An {@link InputFormat} for plain text files. Files are broken into lines.
034     * Either linefeed or carriage-return are used to signal end of line. Each line
035     * is divided into key and value parts by a separator byte. If no such a byte
036     * exists, the key will be the entire line and value will be empty.
037     */
038    @InterfaceAudience.Public
039    @InterfaceStability.Stable
040    public class KeyValueTextInputFormat extends FileInputFormat<Text, Text>
041      implements JobConfigurable {
042    
043      private CompressionCodecFactory compressionCodecs = null;
044      
045      public void configure(JobConf conf) {
046        compressionCodecs = new CompressionCodecFactory(conf);
047      }
048      
049      protected boolean isSplitable(FileSystem fs, Path file) {
050        final CompressionCodec codec = compressionCodecs.getCodec(file);
051        if (null == codec) {
052          return true;
053        }
054        return codec instanceof SplittableCompressionCodec;
055      }
056      
057      public RecordReader<Text, Text> getRecordReader(InputSplit genericSplit,
058                                                      JobConf job,
059                                                      Reporter reporter)
060        throws IOException {
061        
062        reporter.setStatus(genericSplit.toString());
063        return new KeyValueLineRecordReader(job, (FileSplit) genericSplit);
064      }
065    
066    }