编写我的第一个MapReducer程序

环境 :

   hadoop集群

 

1、编写Mapper类

package com.xue.mapreducer;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

/**
 * @author 薛向毅
 * @create 2018-09-01 19:33
 **/
public class WordCountMapper extends Mapper<LongWritable,Text,Text,LongWritable> {

    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

        /*
        * key : 输入的key
        * value: 数据
        * context: map上下文
        * */

        String  data = value.toString();
        //分词
        String[] words = data.split(" ");
        //输出每个单词
        for (String word : words) {
            context.write(new Text(word),new LongWritable(1));
        }


    }
}

2、编写Reducer类

package com.xue.mapreducer;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.mapreduce.Reducer;

import javax.xml.soap.Text;
import java.io.IOException;

/**
 * @author 薛向毅
 * @create 2018-09-01 19:30
 **/
public class WordCountReducer extends Reducer<Text,LongWritable,Text,LongWritable>{

    protected void reduce(Text k3, Iterable<LongWritable> v3, Context context) throws IOException, InterruptedException {
        //v3 是一个集合。 每个元素就是v2.
        long total = 0;
        for (LongWritable l : v3) {
            total+=l.get();
        }
        context.write(k3,new LongWritable(total));
    }
}

3、编写启动类

package com.xue.mapreducer;


import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
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;

/**
 * @author 薛向毅
 * @create 2018-09-01 19:44
 **/
public class WordCountMain {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        //创建一个job = map + reduce
        Configuration conf = new Configuration();

        //创建一个job
        Job job = Job.getInstance(conf);
        //指定程序的入口
        job.setJarByClass(WordCountMain.class);


        //指定job的mapper 和 reducer
        job.setMapperClass(WordCountMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(LongWritable.class);

        job.setReducerClass(WordCountReducer.class);
        job.setOutputValueClass(Text.class);
        job.setOutputValueClass(LongWritable.class);

        //指定任务的输入和输出
        FileInputFormat.setInputPaths(job,new Path(args[0]));
        FileOutputFormat.setOutputPath(job,new Path(args[1]));
        //提交任务
        job.waitForCompletion(true);


    }
}

4、打jar包运行