MapReduce ----数据去重

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

---

结果

2017-03-10    
2017-03-10 a    
2017-03-10 e    
2017-03-11 b    
2017-03-12    
2017-03-12 c    
2017-03-12 d    
2017-03-13    
2017-03-13 d    
2017-03-14    
2017-03-14 h    
2017-03-15 a    
2017-03-15 f    
2017-03-16 o    
2017-03-17 p