WordCount.java

package net.kzk9;

import java.io.IOException;
import java.util.StringTokenizer;

import org.apache.hadoop.util.GenericOptionsParser;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;

public class WordCount {
    // Mapperの実装
    public static class Map extends Mapper<LongWritable, Text, Text, IntWritable> {
        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();
        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            String line = value.toString();
            StringTokenizer tokenizer = new StringTokenizer(line);
            while (tokenizer.hasMoreTokens()) {
                word.set(tokenizer.nextToken());
                context.write(word, one);
            }
        }
    }

    // Reducerの実装
    public static class Reduce extends Reducer<Text, IntWritable, Text, IntWritable> {
        private IntWritable value = new IntWritable(0);
        @Override
        protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
            int sum = 0;
            for (IntWritable value : values)
                sum += value.get();
            value.set(sum);
            context.write(key, value);
        }
    }

    public static void main(String[] args) throws Exception {
        // 設定情報の読み込み
        Configuration conf = new Configuration();

        // 引数のパース
        GenericOptionsParser parser = new GenericOptionsParser(conf, args);
        args = parser.getRemainingArgs();
        
        // ジョブの作成
        Job job = new Job(conf, "wordcount");
        job.setJarByClass(WordCount.class);

        // Mapper/Reducerに使用するクラスを指定
        job.setMapperClass(Map.class);
        job.setReducerClass(Reduce.class);

        // ジョブ中の各種型を設定
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        // 入力/出力フォーマットを設定
        job.setInputFormatClass(TextInputFormat.class);
        job.setOutputFormatClass(TextOutputFormat.class);
        job.setNumReduceTasks(1);

        // 入力/出力パスを設定
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        // ジョブをJobTrackerにサブミット
        boolean success = job.waitForCompletion(true);
        System.out.println(success);
    }
}

Great