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 | package org.apache.hadoop.mapred; |
---|
19 | |
---|
20 | import junit.framework.TestCase; |
---|
21 | |
---|
22 | import org.apache.hadoop.fs.FileStatus; |
---|
23 | import org.apache.hadoop.fs.FileSystem; |
---|
24 | import org.apache.hadoop.fs.Path; |
---|
25 | import org.apache.hadoop.fs.PathFilter; |
---|
26 | |
---|
27 | import java.io.IOException; |
---|
28 | import java.io.Writer; |
---|
29 | import java.io.OutputStreamWriter; |
---|
30 | import java.util.Set; |
---|
31 | import java.util.HashSet; |
---|
32 | |
---|
33 | public class TestFileInputFormatPathFilter extends TestCase { |
---|
34 | |
---|
35 | public static class DummyFileInputFormat extends FileInputFormat { |
---|
36 | |
---|
37 | public RecordReader getRecordReader(InputSplit split, JobConf job, |
---|
38 | Reporter reporter) throws IOException { |
---|
39 | return null; |
---|
40 | } |
---|
41 | |
---|
42 | } |
---|
43 | |
---|
44 | private static FileSystem localFs = null; |
---|
45 | |
---|
46 | static { |
---|
47 | try { |
---|
48 | localFs = FileSystem.getLocal(new JobConf()); |
---|
49 | } catch (IOException e) { |
---|
50 | throw new RuntimeException("init failure", e); |
---|
51 | } |
---|
52 | } |
---|
53 | |
---|
54 | private static Path workDir = |
---|
55 | new Path(new Path(System.getProperty("test.build.data", "."), "data"), |
---|
56 | "TestFileInputFormatPathFilter"); |
---|
57 | |
---|
58 | |
---|
59 | public void setUp() throws Exception { |
---|
60 | tearDown(); |
---|
61 | localFs.mkdirs(workDir); |
---|
62 | } |
---|
63 | |
---|
64 | public void tearDown() throws Exception { |
---|
65 | if (localFs.exists(workDir)) { |
---|
66 | localFs.delete(workDir, true); |
---|
67 | } |
---|
68 | } |
---|
69 | |
---|
70 | protected Path createFile(String fileName) throws IOException { |
---|
71 | Path file = new Path(workDir, fileName); |
---|
72 | Writer writer = new OutputStreamWriter(localFs.create(file)); |
---|
73 | writer.write(""); |
---|
74 | writer.close(); |
---|
75 | return localFs.makeQualified(file); |
---|
76 | } |
---|
77 | |
---|
78 | protected Set<Path> createFiles() throws IOException { |
---|
79 | Set<Path> files = new HashSet<Path>(); |
---|
80 | files.add(createFile("a")); |
---|
81 | files.add(createFile("b")); |
---|
82 | files.add(createFile("aa")); |
---|
83 | files.add(createFile("bb")); |
---|
84 | files.add(createFile("_hello")); |
---|
85 | files.add(createFile(".hello")); |
---|
86 | return files; |
---|
87 | } |
---|
88 | |
---|
89 | |
---|
90 | public static class TestPathFilter implements PathFilter { |
---|
91 | |
---|
92 | public boolean accept(Path path) { |
---|
93 | String name = path.getName(); |
---|
94 | return name.equals("TestFileInputFormatPathFilter") || name.length() == 1; |
---|
95 | } |
---|
96 | } |
---|
97 | |
---|
98 | private void _testInputFiles(boolean withFilter, boolean withGlob) throws Exception { |
---|
99 | Set<Path> createdFiles = createFiles(); |
---|
100 | JobConf conf = new JobConf(); |
---|
101 | |
---|
102 | Path inputDir = (withGlob) ? new Path(workDir, "a*") : workDir; |
---|
103 | FileInputFormat.setInputPaths(conf, inputDir); |
---|
104 | conf.setInputFormat(DummyFileInputFormat.class); |
---|
105 | |
---|
106 | if (withFilter) { |
---|
107 | FileInputFormat.setInputPathFilter(conf, TestPathFilter.class); |
---|
108 | } |
---|
109 | |
---|
110 | DummyFileInputFormat inputFormat = |
---|
111 | (DummyFileInputFormat) conf.getInputFormat(); |
---|
112 | Set<Path> computedFiles = new HashSet<Path>(); |
---|
113 | for (FileStatus file : inputFormat.listStatus(conf)) { |
---|
114 | computedFiles.add(file.getPath()); |
---|
115 | } |
---|
116 | |
---|
117 | createdFiles.remove(localFs.makeQualified(new Path(workDir, "_hello"))); |
---|
118 | createdFiles.remove(localFs.makeQualified(new Path(workDir, ".hello"))); |
---|
119 | |
---|
120 | if (withFilter) { |
---|
121 | createdFiles.remove(localFs.makeQualified(new Path(workDir, "aa"))); |
---|
122 | createdFiles.remove(localFs.makeQualified(new Path(workDir, "bb"))); |
---|
123 | } |
---|
124 | |
---|
125 | if (withGlob) { |
---|
126 | createdFiles.remove(localFs.makeQualified(new Path(workDir, "b"))); |
---|
127 | createdFiles.remove(localFs.makeQualified(new Path(workDir, "bb"))); |
---|
128 | } |
---|
129 | assertEquals(createdFiles, computedFiles); |
---|
130 | } |
---|
131 | |
---|
132 | public void testWithoutPathFilterWithoutGlob() throws Exception { |
---|
133 | _testInputFiles(false, false); |
---|
134 | } |
---|
135 | |
---|
136 | public void testWithoutPathFilterWithGlob() throws Exception { |
---|
137 | _testInputFiles(false, true); |
---|
138 | } |
---|
139 | |
---|
140 | public void testWithPathFilterWithoutGlob() throws Exception { |
---|
141 | _testInputFiles(true, false); |
---|
142 | } |
---|
143 | |
---|
144 | public void testWithPathFilterWithGlob() throws Exception { |
---|
145 | _testInputFiles(true, true); |
---|
146 | } |
---|
147 | } |
---|