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

gistfile1.java

package info.moaikids.mapred.map;

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

import java.io.IOException;
import java.util.HashMap;
import java.util.Map;
import java.util.Map.Entry;

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 Figure33Mapper extends
		Mapper<LongWritable, Text, Text, IntWritable> {

	Map<String, Integer> associativeArray;
	Chunker chunker = new KuromojiChunker();

	@Override
	protected void setup(Context context) throws IOException,
			InterruptedException {
		super.setup(context);
		associativeArray = new HashMap<String, Integer>();
	}

	@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;
			}
			if (associativeArray.containsKey(chunk)) {
				associativeArray.put(chunk, associativeArray.get(chunk) + 1);
			} else {
				associativeArray.put(chunk, 1);
			}
		}
	}

	@Override
	protected void cleanup(Context context) throws IOException,
			InterruptedException {
		for (Entry<String, Integer> entry : associativeArray.entrySet()) {
			context.write(new Text(entry.getKey()),
					new IntWritable(entry.getValue()));
		}
		super.cleanup(context);
	}

}