hadoop_worddistinct_1030

.xml

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>cn.siit</groupId>
    <artifactId>countdelete</artifactId>
    <version>1.0-SNAPSHOT</version>

    <dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.7.4</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.7.4</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-core</artifactId>
            <version>2.7.4</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-jobclient</artifactId>
            <version>2.7.4</version>
        </dependency>

    </dependencies>
</project>

MyMap

package s26;

import java.io.IOException;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
public class MyMap extends Mapper<LongWritable, Text, Text, NullWritable> {

    public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        context.write(value, NullWritable.get());
    }
}

MyRed

package s26;

import java.io.IOException;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class MyRed extends Reducer<Text, NullWritable, Text, NullWritable> {
    public void reduce(Text key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
        context.write(key, NullWritable.get());
    }
}

MyJob

package s26;

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.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;

public class MyJob {

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {

        //1.conf
        Configuration conf = new Configuration();
        conf.set("fs.defaultFS","hdfs://master:9000");

        //2.job
        Job job = Job.getInstance(conf);
        // jar-package
        job.setJarByClass(MyJob.class);
        //
        job.setMapperClass(MyMap.class);
        //
        job.setReducerClass(MyRed.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);


        //3.io
        Path pin = new Path("/sjw");
        Path pout = new Path("/out");
        //
        FileSystem fs = FileSystem.get(conf);
        if(fs.exists(pout)){
            fs.delete(pout,true);
        }
        FileInputFormat.setInputPaths(job,pin);
        FileOutputFormat.setOutputPath(job,pout);

        //4.run
        job.waitForCompletion(true);


    }
}