Hadoop中去重

import java.io.IOException;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.NullWritable;
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;


class Map extends Mapper<LongWritable,Text,Text,NullWritable>{
    public void  map (LongWritable key, Text value, Context context)
            throws IOException, InterruptedException{
         Text line = value;
        context.write(line,NullWritable.get());
        
    }
    
}

class Reduce extends Reducer<Text,NullWritable,Text,NullWritable>{
    public void reduce (Text key,Iterable<NullWritable> values, Context context)
        throws IOException, InterruptedException{
        context.write(key,NullWritable.get());
    }
}

public class  QuChong{
    public static void main(String[] args) throws Exception{
        if (args.length != 2){
            System.err.println("args are not tow");
            System.exit(-1);
        }
        Job job = new Job();
        job.setJarByClass(QuChong.class);
        job.setMapperClass(Map.class);
        job.setReducerClass(Reduce.class);
        
        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);
        
        System.exit(job.waitForCompletion(true)?0:1);
        
    }
}