Hadoop MapReduce 在某一列上自连接(self join)

package mapreduce;    
    
import java.util.List;  
import java.io.IOException;  
import java.util.ArrayList;  
import java.util.Iterator;  
  
import org.apache.hadoop.conf.Configuration;    
import org.apache.hadoop.fs.Path;    
import org.apache.hadoop.io.Text;    
import org.apache.hadoop.mapreduce.Job;    
import org.apache.hadoop.mapreduce.Mapper;    
import org.apache.hadoop.mapreduce.Reducer;    
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;    
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;    
    
    
public class Self_join {    
    public static class Map extends Mapper<Object, Text, Text, Text>{    
        public void map(Object key,Text value, Context context) throws IOException,InterruptedException{    
            String line = value.toString();    
            String[] ss = line.split(" ", 2);  
            context.write(new Text(ss[1]), new Text("left_"+ss[0]));  
            context.write(new Text(ss[0]), new Text("right_"+ss[1]));  
        }    
    }    
        
    public static class Reduce extends Reducer<Text, Text, Text, Text>{    
        private static int time =0;  
        private static List<String> ch = new ArrayList<String>();  
        private static List<String> g = new ArrayList<String>();  
          
        public void reduce(Text key,Iterable<Text> values,Context context) throws IOException,InterruptedException{    
            if(time == 0){  
                context.write(new Text("grandchild"), new Text("grandparent"));  
                time ++;  
            }  
            Iterator<Text> ite = values.iterator();  
            ch.clear();  
            g.clear();  
            while(ite.hasNext()){
                String p = ite.next().toString();
                if(p.startsWith("left_")){  
                    ch.add(p.replaceFirst("^left_", ""));  
                }  
                if(p.startsWith("right_")){  
                    g.add(p.replaceFirst("^right_", ""));  
                }  
            }           
            Iterator<String> chi = ch.iterator();  
            Iterator<String> gi = g.iterator();  
              
            while(chi.hasNext()){  
            	String c = chi.next();
                while(gi.hasNext()){  
                    context.write(new Text(c), new Text(gi.next()));  
                }  
            }
        }    
    }    
              
    public static void main(String[] args) throws Exception{    
        Configuration conf = new Configuration();    
        Job job = Job.getInstance(conf, "Selfjoin");    
        job.setJarByClass(Self_join.class);    
        job.setMapperClass(Map.class);    
        job.setReducerClass(Reduce.class);    
        job.setOutputKeyClass(Text.class);    
        job.setOutputValueClass(Text.class);    
        FileInputFormat.addInputPath(job, new Path(args[0]));    
        FileOutputFormat.setOutputPath(job, new Path(args[1]));    
        System.exit(job.waitForCompletion(true) ? 0 : 1);    
    }    
        
}