| /** |
| * Licensed to the Apache Software Foundation (ASF) under one |
| * or more contributor license agreements. See the NOTICE file |
| * distributed with this work for additional information |
| * regarding copyright ownership. The ASF 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.apache.hadoop.mapreduce.lib.input; |
| |
| import java.io.IOException; |
| |
| import org.apache.hadoop.classification.InterfaceAudience; |
| import org.apache.hadoop.classification.InterfaceStability; |
| import org.apache.hadoop.fs.Path; |
| import org.apache.hadoop.io.Text; |
| import org.apache.hadoop.io.compress.CompressionCodec; |
| import org.apache.hadoop.io.compress.CompressionCodecFactory; |
| import org.apache.hadoop.io.compress.SplittableCompressionCodec; |
| import org.apache.hadoop.mapreduce.InputFormat; |
| import org.apache.hadoop.mapreduce.InputSplit; |
| import org.apache.hadoop.mapreduce.JobContext; |
| import org.apache.hadoop.mapreduce.RecordReader; |
| import org.apache.hadoop.mapreduce.TaskAttemptContext; |
| |
| /** |
| * An {@link InputFormat} for plain text files. Files are broken into lines. |
| * Either line feed or carriage-return are used to signal end of line. |
| * Each line is divided into key and value parts by a separator byte. If no |
| * such a byte exists, the key will be the entire line and value will be empty. |
| * The separator byte can be specified in config file under the attribute name |
| * mapreduce.input.keyvaluelinerecordreader.key.value.separator. The default |
| * is the tab character ('\t'). |
| */ |
| @InterfaceAudience.Public |
| @InterfaceStability.Stable |
| public class KeyValueTextInputFormat extends FileInputFormat<Text, Text> { |
| |
| @Override |
| protected boolean isSplitable(JobContext context, Path file) { |
| final CompressionCodec codec = |
| new CompressionCodecFactory(context.getConfiguration()).getCodec(file); |
| if (null == codec) { |
| return true; |
| } |
| return codec instanceof SplittableCompressionCodec; |
| } |
| |
| public RecordReader<Text, Text> createRecordReader(InputSplit genericSplit, |
| TaskAttemptContext context) throws IOException { |
| |
| context.setStatus(genericSplit.toString()); |
| return new KeyValueLineRecordReader(context.getConfiguration()); |
| } |
| |
| } |