[120] | 1 | /** |
---|
| 2 | * Licensed to the Apache Software Foundation (ASF) under one |
---|
| 3 | * or more contributor license agreements. See the NOTICE file |
---|
| 4 | * distributed with this work for additional information |
---|
| 5 | * regarding copyright ownership. The ASF licenses this file |
---|
| 6 | * to you under the Apache License, Version 2.0 (the |
---|
| 7 | * "License"); you may not use this file except in compliance |
---|
| 8 | * with the License. You may obtain a copy of the License at |
---|
| 9 | * |
---|
| 10 | * http://www.apache.org/licenses/LICENSE-2.0 |
---|
| 11 | * |
---|
| 12 | * Unless required by applicable law or agreed to in writing, software |
---|
| 13 | * distributed under the License is distributed on an "AS IS" BASIS, |
---|
| 14 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
---|
| 15 | * See the License for the specific language governing permissions and |
---|
| 16 | * limitations under the License. |
---|
| 17 | */ |
---|
| 18 | |
---|
| 19 | package org.apache.hadoop.mapreduce.lib.input; |
---|
| 20 | |
---|
| 21 | import org.apache.hadoop.fs.Path; |
---|
| 22 | import org.apache.hadoop.io.LongWritable; |
---|
| 23 | import org.apache.hadoop.io.Text; |
---|
| 24 | import org.apache.hadoop.io.compress.CompressionCodec; |
---|
| 25 | import org.apache.hadoop.io.compress.CompressionCodecFactory; |
---|
| 26 | import org.apache.hadoop.mapreduce.InputFormat; |
---|
| 27 | import org.apache.hadoop.mapreduce.InputSplit; |
---|
| 28 | import org.apache.hadoop.mapreduce.JobContext; |
---|
| 29 | import org.apache.hadoop.mapreduce.RecordReader; |
---|
| 30 | import org.apache.hadoop.mapreduce.TaskAttemptContext; |
---|
| 31 | |
---|
| 32 | /** An {@link InputFormat} for plain text files. Files are broken into lines. |
---|
| 33 | * Either linefeed or carriage-return are used to signal end of line. Keys are |
---|
| 34 | * the position in the file, and values are the line of text.. */ |
---|
| 35 | public class TextInputFormat extends FileInputFormat<LongWritable, Text> { |
---|
| 36 | |
---|
| 37 | @Override |
---|
| 38 | public RecordReader<LongWritable, Text> |
---|
| 39 | createRecordReader(InputSplit split, |
---|
| 40 | TaskAttemptContext context) { |
---|
| 41 | return new LineRecordReader(); |
---|
| 42 | } |
---|
| 43 | |
---|
| 44 | @Override |
---|
| 45 | protected boolean isSplitable(JobContext context, Path file) { |
---|
| 46 | CompressionCodec codec = |
---|
| 47 | new CompressionCodecFactory(context.getConfiguration()).getCodec(file); |
---|
| 48 | return codec == null; |
---|
| 49 | } |
---|
| 50 | |
---|
| 51 | } |
---|