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.mapred; |
---|
20 | |
---|
21 | import java.util.Random; |
---|
22 | import java.util.Stack; |
---|
23 | |
---|
24 | import org.apache.hadoop.fs.FileStatus; |
---|
25 | import org.apache.hadoop.fs.FileSystem; |
---|
26 | import org.apache.hadoop.fs.Path; |
---|
27 | import org.apache.hadoop.io.LongWritable; |
---|
28 | import org.apache.hadoop.io.SequenceFile; |
---|
29 | import org.apache.hadoop.io.Text; |
---|
30 | import org.apache.hadoop.mapred.GenericMRLoadGenerator; |
---|
31 | import org.apache.hadoop.mapred.lib.NullOutputFormat; |
---|
32 | import org.apache.hadoop.mapred.JobConf; |
---|
33 | |
---|
34 | public class GenericMRLoadJobCreator extends GenericMRLoadGenerator { |
---|
35 | |
---|
36 | public static JobConf createJob(String[] argv, boolean mapoutputCompressed, |
---|
37 | boolean outputCompressed) throws Exception { |
---|
38 | |
---|
39 | JobConf job = new JobConf(); |
---|
40 | job.setJarByClass(GenericMRLoadGenerator.class); |
---|
41 | job.setMapperClass(SampleMapper.class); |
---|
42 | job.setReducerClass(SampleReducer.class); |
---|
43 | if (!parseArgs(argv, job)) { |
---|
44 | return null; |
---|
45 | } |
---|
46 | |
---|
47 | if (null == FileOutputFormat.getOutputPath(job)) { |
---|
48 | // No output dir? No writes |
---|
49 | job.setOutputFormat(NullOutputFormat.class); |
---|
50 | } |
---|
51 | |
---|
52 | if (0 == FileInputFormat.getInputPaths(job).length) { |
---|
53 | // No input dir? Generate random data |
---|
54 | System.err.println("No input path; ignoring InputFormat"); |
---|
55 | confRandom(job); |
---|
56 | } else if (null != job.getClass("mapred.indirect.input.format", null)) { |
---|
57 | // specified IndirectInputFormat? Build src list |
---|
58 | JobClient jClient = new JobClient(job); |
---|
59 | Path sysdir = jClient.getSystemDir(); |
---|
60 | Random r = new Random(); |
---|
61 | Path indirInputFile = new Path(sysdir, Integer.toString(r |
---|
62 | .nextInt(Integer.MAX_VALUE), 36) |
---|
63 | + "_files"); |
---|
64 | job.set("mapred.indirect.input.file", indirInputFile.toString()); |
---|
65 | SequenceFile.Writer writer = SequenceFile.createWriter(sysdir |
---|
66 | .getFileSystem(job), job, indirInputFile, LongWritable.class, |
---|
67 | Text.class, SequenceFile.CompressionType.NONE); |
---|
68 | try { |
---|
69 | for (Path p : FileInputFormat.getInputPaths(job)) { |
---|
70 | FileSystem fs = p.getFileSystem(job); |
---|
71 | Stack<Path> pathstack = new Stack<Path>(); |
---|
72 | pathstack.push(p); |
---|
73 | while (!pathstack.empty()) { |
---|
74 | for (FileStatus stat : fs.listStatus(pathstack.pop())) { |
---|
75 | if (stat.isDir()) { |
---|
76 | if (!stat.getPath().getName().startsWith("_")) { |
---|
77 | pathstack.push(stat.getPath()); |
---|
78 | } |
---|
79 | } else { |
---|
80 | writer.sync(); |
---|
81 | writer.append(new LongWritable(stat.getLen()), new Text(stat |
---|
82 | .getPath().toUri().toString())); |
---|
83 | } |
---|
84 | } |
---|
85 | } |
---|
86 | } |
---|
87 | } finally { |
---|
88 | writer.close(); |
---|
89 | } |
---|
90 | } |
---|
91 | |
---|
92 | job.setCompressMapOutput(mapoutputCompressed); |
---|
93 | job.setBoolean("mapred.output.compress", outputCompressed); |
---|
94 | return job; |
---|
95 | |
---|
96 | } |
---|
97 | |
---|
98 | } |
---|