Hadoop で日本語のワードカウント

形態素解析エンジンとして Gomoku を使っている。

WordCount.java

package org.holidayworking.hadoop.japanese;

import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class WordCount extends Configured implements Tool {

    @Override
    public int run(String[] args) throws Exception {
        if (args.length != 2) {
            System.err.println("Usage: WordCount <input path> <output path>");
            return -1;
        }

        Job job = new Job(getConf(), "WordCount");
        job.setJarByClass(WordCount.class);

        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);

        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputKeyClass(IntWritable.class);

        return job.waitForCompletion(true) ? 0 : 1;
    }

    public static void main(String[] args) throws Exception {
        System.exit(ToolRunner.run(new WordCount(), args));
    }

}

WordCountMapper.java

package org.holidayworking.hadoop.japanese;

import java.io.IOException;

import net.reduls.gomoku.Morpheme;
import net.reduls.gomoku.Tagger;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String line = value.toString();
        for (Morpheme m : Tagger.parse(line)) {
            if (m.feature.startsWith("名詞")) {
                context.write(new Text(m.surface), new IntWritable(1));
            }
        }
    }

}

WordCountReducer.java

package org.holidayworking.hadoop.japanese;

import java.io.IOException;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {

    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        int count = 0;
        for (IntWritable value : values) {
            count += value.get();
        }
        context.write(key, new IntWritable(count));
    }

}