前提準備：

MapReduce程式設計例項：

輸入：

2013-11-01 aa
2013-11-02 bb
2013-11-03 cc
2013-11-04 aa
2013-11-05 dd
2013-11-06 dd
2013-11-07 aa
2013-11-09 cc
2013-11-10 ee

2013-11-01 bb 
2013-11-02 33 
2013-11-03 cc
2013-11-04 bb
2013-11-05 23 
2013-11-06 dd
2013-11-07 99 
2013-11-09 99
2013-11-10 ee

.....

.....

.....

資料重複，map中每一行做為一個key，value值任意，經過shuffle之後輸入到reduce中利用key的唯一性直接輸出key

程式碼太簡單，不解釋，上程式碼：

package com.t.hadoop;

import java.io.IOException;
import java.util.HashSet;
import java.util.StringTokenizer;

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;
import org.apache.hadoop.util.GenericOptionsParser;

/**
 * 資料去重
 * @author daT 
 
[email protected]
 *
 */
public class Dedup {

	public static class MyMapper extends Mapper<Object, Text, Text, Text>{

		@Override
		protected void map(Object key, Text value, Context context)
				throws IOException, InterruptedException {
				context.write(value, new Text(""));
		}
	}
	
	public static class MyReducer extends Reducer<Text, Text, Text, Text>{

		@Override
		protected void reduce(Text key, Iterable<Text> value,
				Context context)
				throws IOException, InterruptedException {
			context.write(key, new Text(""));
		}
	}
	
	
	public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException{
		Configuration conf = new Configuration();
		String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
		
		if(otherArgs.length<2){
			System.out.println("parameter errors!");
			System.exit(2);
		}
		
		Job job = new org.apache.hadoop.mapreduce.Job(conf, "Dedup");
		job.setJarByClass(Dedup.class);
		job.setMapperClass(MyMapper.class);
		job.setCombinerClass(MyReducer.class);
		job.setReducerClass(MyReducer.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(Text.class);
		
		FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
		FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
		
		System.exit(job.waitForCompletion(true)?0:1);
		
	}
	
}
 

輸出結果
2013-11-01 aa
2013-11-01 bb
2013-11-02 33
2013-11-02 bb
2013-11-03 cc
2013-11-03 cc
2013-11-04 98
2013-11-04 aa
2013-11-04 bb
2013-11-05 23
2013-11-05 93
2013-11-05 dd
2013-11-06 99
2013-11-06 dd
2013-11-07 92
2013-11-07 99
2013-11-07 aa
2013-11-09 99
2013-11-09 aa
2013-11-09 cc
2013-11-10 ee