1 | import java.io.IOException; |
---|
2 | import java.util.StringTokenizer; |
---|
3 | |
---|
4 | import org.apache.hadoop.conf.Configuration; |
---|
5 | import org.apache.hadoop.fs.Path; |
---|
6 | import org.apache.hadoop.io.IntWritable; |
---|
7 | import org.apache.hadoop.io.Text; |
---|
8 | import org.apache.hadoop.mapreduce.Job; |
---|
9 | import org.apache.hadoop.mapreduce.Mapper; |
---|
10 | import org.apache.hadoop.mapreduce.Reducer; |
---|
11 | import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; |
---|
12 | import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; |
---|
13 | import org.apache.hadoop.util.GenericOptionsParser; |
---|
14 | //WordCount |
---|
15 | //說明: |
---|
16 | // 用於字數統計 |
---|
17 | // |
---|
18 | //測試方法: |
---|
19 | // 將此程式運作在hadoop 0.20 平台上,執行: |
---|
20 | // --------------------------- |
---|
21 | // hadoop jar WordCount.jar <input> <output> |
---|
22 | // --------------------------- |
---|
23 | // |
---|
24 | //注意: |
---|
25 | //1. 在hdfs 上來源檔案的路徑為 你所指定的 <input> |
---|
26 | //請注意必須先放資料到此hdfs上的資料夾內,且此資料夾內只能放檔案,不可再放資料夾 |
---|
27 | //2. 運算完後,程式將執行結果放在hdfs 的輸出路徑為 你所指定的 <output> |
---|
28 | // |
---|
29 | public class WordCount { |
---|
30 | |
---|
31 | public static class TokenizerMapper extends |
---|
32 | Mapper<Object, Text, Text, IntWritable> { |
---|
33 | |
---|
34 | private final static IntWritable one = new IntWritable(1); |
---|
35 | private Text word = new Text(); |
---|
36 | |
---|
37 | public void map(Object key, Text value, Context context) |
---|
38 | throws IOException, InterruptedException { |
---|
39 | StringTokenizer itr = new StringTokenizer(value.toString()); |
---|
40 | while (itr.hasMoreTokens()) { |
---|
41 | word.set(itr.nextToken()); |
---|
42 | context.write(word, one); |
---|
43 | } |
---|
44 | } |
---|
45 | } |
---|
46 | |
---|
47 | public static class IntSumReducer extends |
---|
48 | Reducer<Text, IntWritable, Text, IntWritable> { |
---|
49 | private IntWritable result = new IntWritable(); |
---|
50 | |
---|
51 | public void reduce(Text key, Iterable<IntWritable> values, |
---|
52 | Context context) throws IOException, InterruptedException { |
---|
53 | int sum = 0; |
---|
54 | for (IntWritable val : values) { |
---|
55 | sum += val.get(); |
---|
56 | } |
---|
57 | result.set(sum); |
---|
58 | context.write(key, result); |
---|
59 | } |
---|
60 | } |
---|
61 | |
---|
62 | public static void main(String[] args) throws Exception { |
---|
63 | // debug using |
---|
64 | // String[] argv = { "input", "output-wc" }; |
---|
65 | // args = argv; |
---|
66 | |
---|
67 | Configuration conf = new Configuration(); |
---|
68 | Job job = new Job(conf, "Word Count"); |
---|
69 | job.setJarByClass(WordCount.class); |
---|
70 | job.setMapperClass(TokenizerMapper.class); |
---|
71 | job.setCombinerClass(IntSumReducer.class); |
---|
72 | job.setReducerClass(IntSumReducer.class); |
---|
73 | job.setOutputKeyClass(Text.class); |
---|
74 | job.setOutputValueClass(IntWritable.class); |
---|
75 | FileInputFormat.addInputPath(job, new Path(args[0])); |
---|
76 | FileOutputFormat.setOutputPath(job, new Path(args[1])); |
---|
77 | System.exit(job.waitForCompletion(true) ? 0 : 1); |
---|
78 | } |
---|
79 | } |
---|
80 | |
---|