| /** |
| * 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 org.apache.hadoop.fs.Path; |
| import org.apache.hadoop.io.LongWritable; |
| import org.apache.hadoop.io.Text; |
| import org.apache.hadoop.io.compress.CompressionCodec; |
| import org.apache.hadoop.io.compress.CompressionCodecFactory; |
| 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 linefeed or carriage-return are used to signal end of line. Keys are |
| * the position in the file, and values are the line of text.. */ |
| public class TextInputFormat extends FileInputFormat<LongWritable, Text> { |
| |
| @Override |
| public RecordReader<LongWritable, Text> |
| createRecordReader(InputSplit split, |
| TaskAttemptContext context) { |
| return new LineRecordReader(); |
| } |
| |
| @Override |
| protected boolean isSplitable(JobContext context, Path file) { |
| CompressionCodec codec = |
| new CompressionCodecFactory(context.getConfiguration()).getCodec(file); |
| return codec == null; |
| } |
| |
| } |