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 java.io.IOException; |
---|
22 | import java.util.List; |
---|
23 | |
---|
24 | import org.apache.hadoop.fs.FileStatus; |
---|
25 | import org.apache.hadoop.fs.FileSystem; |
---|
26 | import org.apache.hadoop.fs.Path; |
---|
27 | |
---|
28 | import org.apache.hadoop.io.SequenceFile; |
---|
29 | import org.apache.hadoop.io.MapFile; |
---|
30 | import org.apache.hadoop.mapreduce.InputFormat; |
---|
31 | import org.apache.hadoop.mapreduce.InputSplit; |
---|
32 | import org.apache.hadoop.mapreduce.JobContext; |
---|
33 | import org.apache.hadoop.mapreduce.RecordReader; |
---|
34 | import org.apache.hadoop.mapreduce.TaskAttemptContext; |
---|
35 | |
---|
36 | /** An {@link InputFormat} for {@link SequenceFile}s. */ |
---|
37 | public class SequenceFileInputFormat<K, V> extends FileInputFormat<K, V> { |
---|
38 | |
---|
39 | @Override |
---|
40 | public RecordReader<K, V> createRecordReader(InputSplit split, |
---|
41 | TaskAttemptContext context |
---|
42 | ) throws IOException { |
---|
43 | return new SequenceFileRecordReader<K,V>(); |
---|
44 | } |
---|
45 | |
---|
46 | @Override |
---|
47 | protected long getFormatMinSplitSize() { |
---|
48 | return SequenceFile.SYNC_INTERVAL; |
---|
49 | } |
---|
50 | |
---|
51 | @Override |
---|
52 | protected List<FileStatus> listStatus(JobContext job |
---|
53 | )throws IOException { |
---|
54 | |
---|
55 | List<FileStatus> files = super.listStatus(job); |
---|
56 | int len = files.size(); |
---|
57 | for(int i=0; i < len; ++i) { |
---|
58 | FileStatus file = files.get(i); |
---|
59 | if (file.isDir()) { // it's a MapFile |
---|
60 | Path p = file.getPath(); |
---|
61 | FileSystem fs = p.getFileSystem(job.getConfiguration()); |
---|
62 | // use the data file |
---|
63 | files.set(i, fs.getFileStatus(new Path(p, MapFile.DATA_FILE_NAME))); |
---|
64 | } |
---|
65 | } |
---|
66 | return files; |
---|
67 | } |
---|
68 | } |
---|
69 | |
---|