1 | package org.apache.hadoop.examples; |
---|
2 | |
---|
3 | import java.io.IOException; |
---|
4 | import java.util.StringTokenizer; |
---|
5 | |
---|
6 | import org.apache.hadoop.conf.Configuration; |
---|
7 | import org.apache.hadoop.fs.Path; |
---|
8 | import org.apache.hadoop.io.IntWritable; |
---|
9 | import org.apache.hadoop.io.Text; |
---|
10 | import org.apache.hadoop.mapreduce.Job; |
---|
11 | import org.apache.hadoop.mapreduce.Mapper; |
---|
12 | import org.apache.hadoop.mapreduce.Reducer; |
---|
13 | import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; |
---|
14 | import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; |
---|
15 | import org.apache.hadoop.util.GenericOptionsParser; |
---|
16 | |
---|
17 | public class WordCount { |
---|
18 | |
---|
19 | public static class TokenizerMapper |
---|
20 | extends Mapper<Object, Text, Text, IntWritable>{ |
---|
21 | |
---|
22 | private final static IntWritable one = new IntWritable(1); |
---|
23 | private Text word = new Text(); |
---|
24 | |
---|
25 | public void map(Object key, Text value, Context context |
---|
26 | ) throws IOException, InterruptedException { |
---|
27 | StringTokenizer itr = new StringTokenizer(value.toString()); |
---|
28 | while (itr.hasMoreTokens()) { |
---|
29 | word.set(itr.nextToken()); |
---|
30 | context.write(word, one); |
---|
31 | } |
---|
32 | } |
---|
33 | } |
---|
34 | |
---|
35 | public static class IntSumReducer |
---|
36 | extends Reducer<Text,IntWritable,Text,IntWritable> { |
---|
37 | private IntWritable result = new IntWritable(); |
---|
38 | |
---|
39 | public void reduce(Text key, Iterable<IntWritable> values, |
---|
40 | Context context |
---|
41 | ) throws IOException, InterruptedException { |
---|
42 | int sum = 0; |
---|
43 | for (IntWritable val : values) { |
---|
44 | sum += val.get(); |
---|
45 | } |
---|
46 | result.set(sum); |
---|
47 | context.write(key, result); |
---|
48 | } |
---|
49 | } |
---|
50 | |
---|
51 | public static void main(String[] args) throws Exception { |
---|
52 | Configuration conf = new Configuration(); |
---|
53 | String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); |
---|
54 | if (otherArgs.length != 2) { |
---|
55 | System.err.println("Usage: wordcount <in> <out>"); |
---|
56 | System.exit(2); |
---|
57 | } |
---|
58 | Job job = new Job(conf, "word count"); |
---|
59 | job.setJarByClass(WordCount.class); |
---|
60 | job.setMapperClass(TokenizerMapper.class); |
---|
61 | job.setCombinerClass(IntSumReducer.class); |
---|
62 | job.setReducerClass(IntSumReducer.class); |
---|
63 | job.setOutputKeyClass(Text.class); |
---|
64 | job.setOutputValueClass(IntWritable.class); |
---|
65 | FileInputFormat.addInputPath(job, new Path(otherArgs[0])); |
---|
66 | FileOutputFormat.setOutputPath(job, new Path(otherArgs[1])); |
---|
67 | System.exit(job.waitForCompletion(true) ? 0 : 1); |
---|
68 | } |
---|
69 | } |
---|