Data Intensive Text Processing with MapReduce #3 figure3.1 Mapper

gistfile1.java

package info.moaikids.mapred.map;

import info.moaikids.chunker.Chunker;
import info.moaikids.chunker.KuromojiChunker;

import java.io.IOException;

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

public class Figure31Mapper extends
		Mapper<LongWritable, Text, Text, IntWritable> {
	static final IntWritable ONE = new IntWritable(1);
	Chunker chunker = new KuromojiChunker();

	@Override
	protected void map(LongWritable key, Text value, Context context)
			throws IOException, InterruptedException {

		for (String chunk : chunker.chunking(value.toString())) {
			if (chunk.trim().isEmpty()) {
				continue;
			}
			context.write(new Text(chunk), ONE);
		}
	}

}