MapReduce编程案例——数据去重

MapReduce编程案例——数据去重

描述：在原始数据中出现次数超过一次的数据在输出文件中只出现一次

方法：哪个不能重复哪个设置成Key

原始数据：

file1：

2012-3-1 a

2012-3-2 b

2012-3-3 c

2012-3-4 d

2012-3-5 a

2012-3-6 b

2012-3-7 c

2012-3-3 c

 

file2：

2012-3-1 b

2012-3-2 a

2012-3-3 b

2012-3-4 d

2012-3-5 a

2012-3-6 c

2012-3-7 d

2012-3-3 c

   

数据输出：

2012-3-1 a

2012-3-1 b

2012-3-2 a

2012-3-2 b

2012-3-3 b

2012-3-3 c

2012-3-4 d

2012-3-5 a

2012-3-6 b

2012-3-6 c

2012-3-7 c

2012-3-7 d

package org.apache.hadoop.mapreduce;

import java.io.IOException;
import java.net.URI;
import java.util.Iterator;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
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;
 
public class RemoveRepeat {
	final static String INPUT_PATH="hdfs://localhost:9000/user/hadoop/input1";
	final static String OUTPUT_PATH="hdfs://localhost:9000/output";
	public static void main(String[] args) throws Exception {
		// TODO Auto-generated method stub
		Configuration configuration = new Configuration();
		FileSystem fileSystem =FileSystem.get(new URI(INPUT_PATH),configuration);
		if (fileSystem.exists(new Path(OUTPUT_PATH))) {
			fileSystem.delete(new Path(OUTPUT_PATH),true);
		}
		Job job = new Job(configuration,"RemoveRepeat");
		FileInputFormat.setInputPaths(job, INPUT_PATH);
		FileOutputFormat.setOutputPath(job,new Path(OUTPUT_PATH));
		job.setJarByClass(RemoveRepeat.class);
		job.setMapperClass(ReMapper.class);
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(NullWritable.class);
		job.setReducerClass(ReReducer.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(NullWritable.class);
		job.waitForCompletion(true);
	}


 
    public static class ReReducer extends Reducer<Text,NullWritable, Text,NullWritable> {
        private IntWritable result = new IntWritable();
 
        public ReReducer() {
        }
 
        protected void reduce(Text key2, Iterable<NullWritable> value2, Reducer<Text,NullWritable, Text,NullWritable>.Context context) throws IOException, InterruptedException {
        	
            context.write(key2,NullWritable.get());
            			
        }
    }
 
    public static class ReMapper extends Mapper<LongWritable, Text, Text,NullWritable> {
        private static final int FAIL_DATA=9999;
        public void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, NullWritable>.Context context) throws IOException, InterruptedException {
            
        	context.write(value,NullWritable.get());
 
        }
    }
}

NullWritable是Writable的一个特殊类，实现方法为空实现，不从数据流中读数据，也不写入数据，只充当占位符，如在MapReduce中，如果你不需要使用键或值，你就可以将键或值声明为NullWritable,NullWritable是一个不可变的单实例类型。