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; |
---|
20 | |
---|
21 | import java.io.IOException; |
---|
22 | |
---|
23 | import org.apache.hadoop.fs.FileSystem; |
---|
24 | |
---|
25 | /** |
---|
26 | * <code>OutputFormat</code> describes the output-specification for a |
---|
27 | * Map-Reduce job. |
---|
28 | * |
---|
29 | * <p>The Map-Reduce framework relies on the <code>OutputFormat</code> of the |
---|
30 | * job to:<p> |
---|
31 | * <ol> |
---|
32 | * <li> |
---|
33 | * Validate the output-specification of the job. For e.g. check that the |
---|
34 | * output directory doesn't already exist. |
---|
35 | * <li> |
---|
36 | * Provide the {@link RecordWriter} implementation to be used to write out |
---|
37 | * the output files of the job. Output files are stored in a |
---|
38 | * {@link FileSystem}. |
---|
39 | * </li> |
---|
40 | * </ol> |
---|
41 | * |
---|
42 | * @see RecordWriter |
---|
43 | */ |
---|
44 | public abstract class OutputFormat<K, V> { |
---|
45 | |
---|
46 | /** |
---|
47 | * Get the {@link RecordWriter} for the given task. |
---|
48 | * |
---|
49 | * @param context the information about the current task. |
---|
50 | * @return a {@link RecordWriter} to write the output for the job. |
---|
51 | * @throws IOException |
---|
52 | */ |
---|
53 | public abstract RecordWriter<K, V> |
---|
54 | getRecordWriter(TaskAttemptContext context |
---|
55 | ) throws IOException, InterruptedException; |
---|
56 | |
---|
57 | /** |
---|
58 | * Check for validity of the output-specification for the job. |
---|
59 | * |
---|
60 | * <p>This is to validate the output specification for the job when it is |
---|
61 | * a job is submitted. Typically checks that it does not already exist, |
---|
62 | * throwing an exception when it already exists, so that output is not |
---|
63 | * overwritten.</p> |
---|
64 | * |
---|
65 | * @param context information about the job |
---|
66 | * @throws IOException when output should not be attempted |
---|
67 | */ |
---|
68 | public abstract void checkOutputSpecs(JobContext context |
---|
69 | ) throws IOException, |
---|
70 | InterruptedException; |
---|
71 | |
---|
72 | /** |
---|
73 | * Get the output committer for this output format. This is responsible |
---|
74 | * for ensuring the output is committed correctly. |
---|
75 | * @param context the task context |
---|
76 | * @return an output committer |
---|
77 | * @throws IOException |
---|
78 | * @throws InterruptedException |
---|
79 | */ |
---|
80 | public abstract |
---|
81 | OutputCommitter getOutputCommitter(TaskAttemptContext context |
---|
82 | ) throws IOException, InterruptedException; |
---|
83 | } |
---|
84 | |
---|