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 org.apache.hadoop.fs.*; |
---|
21 | import org.apache.hadoop.io.*; |
---|
22 | import org.apache.hadoop.mapred.lib.*; |
---|
23 | import junit.framework.TestCase; |
---|
24 | import java.text.NumberFormat; |
---|
25 | |
---|
26 | public class TestFieldSelection extends TestCase { |
---|
27 | |
---|
28 | private static NumberFormat idFormat = NumberFormat.getInstance(); |
---|
29 | static { |
---|
30 | idFormat.setMinimumIntegerDigits(4); |
---|
31 | idFormat.setGroupingUsed(false); |
---|
32 | } |
---|
33 | |
---|
34 | public void testFieldSelection() throws Exception { |
---|
35 | launch(); |
---|
36 | } |
---|
37 | |
---|
38 | public static void launch() throws Exception { |
---|
39 | JobConf conf = new JobConf(TestFieldSelection.class); |
---|
40 | FileSystem fs = FileSystem.get(conf); |
---|
41 | int numOfInputLines = 10; |
---|
42 | |
---|
43 | Path OUTPUT_DIR = new Path("build/test/output_for_field_selection_test"); |
---|
44 | Path INPUT_DIR = new Path("build/test/input_for_field_selection_test"); |
---|
45 | String inputFile = "input.txt"; |
---|
46 | fs.delete(INPUT_DIR, true); |
---|
47 | fs.mkdirs(INPUT_DIR); |
---|
48 | fs.delete(OUTPUT_DIR, true); |
---|
49 | |
---|
50 | StringBuffer inputData = new StringBuffer(); |
---|
51 | StringBuffer expectedOutput = new StringBuffer(); |
---|
52 | |
---|
53 | FSDataOutputStream fileOut = fs.create(new Path(INPUT_DIR, inputFile)); |
---|
54 | for (int i = 0; i < numOfInputLines; i++) { |
---|
55 | inputData.append(idFormat.format(i)); |
---|
56 | inputData.append("-").append(idFormat.format(i+1)); |
---|
57 | inputData.append("-").append(idFormat.format(i+2)); |
---|
58 | inputData.append("-").append(idFormat.format(i+3)); |
---|
59 | inputData.append("-").append(idFormat.format(i+4)); |
---|
60 | inputData.append("-").append(idFormat.format(i+5)); |
---|
61 | inputData.append("-").append(idFormat.format(i+6)); |
---|
62 | inputData.append("\n"); |
---|
63 | |
---|
64 | |
---|
65 | expectedOutput.append(idFormat.format(i+3)); |
---|
66 | expectedOutput.append("-" ).append (idFormat.format(i+2)); |
---|
67 | expectedOutput.append("-" ).append (idFormat.format(i+1)); |
---|
68 | expectedOutput.append("-" ).append (idFormat.format(i+5)); |
---|
69 | expectedOutput.append("-" ).append (idFormat.format(i+6)); |
---|
70 | |
---|
71 | expectedOutput.append("-" ).append (idFormat.format(i+6)); |
---|
72 | expectedOutput.append("-" ).append (idFormat.format(i+5)); |
---|
73 | expectedOutput.append("-" ).append (idFormat.format(i+1)); |
---|
74 | expectedOutput.append("-" ).append (idFormat.format(i+2)); |
---|
75 | expectedOutput.append("-" ).append (idFormat.format(i+3)); |
---|
76 | |
---|
77 | expectedOutput.append("-" ).append (idFormat.format(i+0)); |
---|
78 | expectedOutput.append("-" ).append (idFormat.format(i+1)); |
---|
79 | expectedOutput.append("-" ).append (idFormat.format(i+2)); |
---|
80 | expectedOutput.append("-" ).append (idFormat.format(i+3)); |
---|
81 | expectedOutput.append("-" ).append (idFormat.format(i+4)); |
---|
82 | expectedOutput.append("-" ).append (idFormat.format(i+5)); |
---|
83 | expectedOutput.append("-" ).append (idFormat.format(i+6)); |
---|
84 | expectedOutput.append("\n"); |
---|
85 | } |
---|
86 | fileOut.write(inputData.toString().getBytes("utf-8")); |
---|
87 | fileOut.close(); |
---|
88 | |
---|
89 | System.out.println("inputData:"); |
---|
90 | System.out.println(inputData.toString()); |
---|
91 | JobConf job = new JobConf(conf, TestFieldSelection.class); |
---|
92 | FileInputFormat.setInputPaths(job, INPUT_DIR); |
---|
93 | job.setInputFormat(TextInputFormat.class); |
---|
94 | job.setMapperClass(FieldSelectionMapReduce.class); |
---|
95 | job.setReducerClass(FieldSelectionMapReduce.class); |
---|
96 | |
---|
97 | FileOutputFormat.setOutputPath(job, OUTPUT_DIR); |
---|
98 | job.setOutputKeyClass(Text.class); |
---|
99 | job.setOutputValueClass(Text.class); |
---|
100 | job.setOutputFormat(TextOutputFormat.class); |
---|
101 | job.setNumReduceTasks(1); |
---|
102 | |
---|
103 | job.set("mapred.data.field.separator", "-"); |
---|
104 | job.set("map.output.key.value.fields.spec", "6,5,1-3:0-"); |
---|
105 | job.set("reduce.output.key.value.fields.spec", ":4,3,2,1,0,0-"); |
---|
106 | |
---|
107 | JobClient.runJob(job); |
---|
108 | |
---|
109 | // |
---|
110 | // Finally, we compare the reconstructed answer key with the |
---|
111 | // original one. Remember, we need to ignore zero-count items |
---|
112 | // in the original key. |
---|
113 | // |
---|
114 | boolean success = true; |
---|
115 | Path outPath = new Path(OUTPUT_DIR, "part-00000"); |
---|
116 | String outdata = TestMiniMRWithDFS.readOutput(outPath,job); |
---|
117 | |
---|
118 | assertEquals(expectedOutput.toString(),outdata); |
---|
119 | fs.delete(OUTPUT_DIR, true); |
---|
120 | fs.delete(INPUT_DIR, true); |
---|
121 | } |
---|
122 | |
---|
123 | /** |
---|
124 | * Launches all the tasks in order. |
---|
125 | */ |
---|
126 | public static void main(String[] argv) throws Exception { |
---|
127 | launch(); |
---|
128 | } |
---|
129 | } |
---|