Data Intensive Text Processing with MapReduce #3 SecondarySort (Reduce Side) Mapper

gistfile1.java

package info.moaikids.mapred.map;

import java.io.IOException;

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

public class ReduceSecondarySortMapper extends
		Mapper<LongWritable, Text, Text, Text> {

	@Override
	protected void map(LongWritable key, Text value, Context context)
			throws IOException, InterruptedException {
		// format
		// 0:year
		// 1:month
		// 2:day
		// 3:place
		// 4:title
		// 5:description
		String tsv = value.toString().trim();
		if (tsv.isEmpty()) {
			return;
		}
		String[] params = tsv.split("\t");

		context.write(new Text(params[3].trim()), new Text(tsv));
	}

}