PYMK Stage1 Mapper

import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reporter;
 
public class pymk_mapper extends MapReduceBase implements
    Mapper<LongWritable, Text, Text, Text> {

  @Override
  public void map(LongWritable key, Text value,
      OutputCollector<Text, Text> output, Reporter reporter)
      throws IOException {
      String[] s = value.toString().split("\t");
        output.collect(new Text(s[0]), new Text(s[1]));
  }
}

PYMK Stage1 Reducer

import java.io.IOException;
import java.util.Iterator;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;

public class pymk_reducer extends MapReduceBase implements
    Reducer<Text, Text, Text, Text> {

  @Override
  public void reduce(Text key, Iterator<Text> values,
      OutputCollector<Text, Text> output, Reporter reporter)
      throws IOException {
    String out = "";
    while (values.hasNext()) {
      Text value = values.next();
      if (out == "") {
out = value.toString();
}
else {
          String out_tmp = "," + out + ",";
          String value_tmp = "," + value.toString() + ",";
if (out_tmp.lastIndexOf(value_tmp) <0 ) {
       out = out + "," + value.toString();
       }
}
    }
    output.collect(key, new Text(out));
  }
}