Hadoop-4、Mapred数据去重

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;

import org.apache.hadoop.util.GenericOptionsParser;
public class DelRep {

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

        private static Text line = new Text();

        public void map(Object key,Text value,Context context) throws IOException, InterruptedException{

            line = value;

            context.write(line, new Text(""));

        }

    }
public static class Reduce extends Reducer<Text,Text,Text,Text>{

        public 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();

        conf.addResource(new Path("/usr/hadoop-1.0.3/conf/core-site.xml"));
String[] otherArgs = new GenericOptionsParser(conf,Args).getRemainingArgs();
Job job = new Job(conf,"DelRep");
job.setJarByClass(DelRep.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(otherArgs[0]));

        FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);

    }

}

File1：

?

File2

?

结果：

?