MapReduce ----数据去重-白红宇

MapReduce ----数据去重

阅读量：6374 次

发布时间：2019-06-23

本文共 2113 字，大约阅读时间需要 7 分钟。

三个文件

2017-03-10 a

2017-03-11 b

2017-03-12 d

2017-03-13 d

2017-03-14

2017-03-15 a

2017-03-10 e

2017-03-11 b

2017-03-12 c

2017-03-13

2017-03-14 h

2017-03-15 a

2017-03-17 p

2017-03-10

2017-03-11 b

2017-03-12

2017-03-13 d

2017-03-14

2017-03-15 f

2017-03-16 o

import java.io.IOException;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 Deup{    public static class Map extends Mapper
     
      {
            @Override        protected void map(Object key, Text value, Mapper
      
       .Context context)                throws IOException, InterruptedException {
                context.write(value, new Text(""));        }    }        public static class Reduce extends Reducer
       
        {        @Override        protected void reduce(Text key, Iterable
        
          values, Reducer
         
          .Context context)                throws IOException, InterruptedException {
                context.write(key, new Text(""));        }    }    public static void main(String[] args) throws Exception {        Configuration conf=new Configuration();        @SuppressWarnings("deprecation")        Job job=new Job(conf);        job.setJarByClass(Deup.class);        job.setMapperClass(Map.class);        job.setCombinerClass(Reduce.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);            }}