MapReduce Java API实例-排序

场景

MapReduce Java API实例-统计单词出现频率：

https://blog.csdn.net/BADAO_LIUMANG_QIZHI/article/details/119410169

上面进行项目环境搭建的基础上。

怎样实现对下面这组数据进行排序

 

 

注：

博客：
https://blog.csdn.net/badao_liumang_qizhi
关注公众号
霸道的程序猿
获取编程相关电子书、教程推送与免费下载。

实现

输入数据格式为每行有一数值，通过MapReduce实现数据的排序功能。

利用Map阶段的Sort功能将要排序的数值作为map函数的key输出，

并在reduce函数设置一个计数器。

1、Map代码实现

package com.badao.sort;


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

import java.io.IOException;
import java.util.StringTokenizer;

public class SortMapper extends Mapper<Object,Text,IntWritable,IntWritable> {


    public static IntWritable data = new IntWritable();

    //map将输入中value化成IntWritable类型，作为输出的key
    @Override
    public void map(Object key, Text value, Context context) throws IOException, InterruptedException {

        String line = value.toString();
        data.set(Integer.parseInt(line));
        //通过write函数写入到本地文件
        context.write(data,new IntWritable(1));

    }
}

2、Reduce代码实现

package com.badao.sort;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;


public class SortReducer extends Reducer<IntWritable, IntWritable,IntWritable,IntWritable> {


    public static IntWritable linenum = new IntWritable(1);
    public static int i =1;

    @Override
    public void reduce(IntWritable key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {

        context.write(new IntWritable(i),key);
        ++i;
    }
}

3、Job实现

package com.badao.sort;


import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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 org.apache.hadoop.mapreduce.lib.reduce.IntSumReducer;

import java.io.IOException;

public class SortJob {
    public static void main(String[] args) throws InterruptedException, IOException, ClassNotFoundException {
        jobLocal();
    }

    public static void jobLocal()throws IOException, ClassNotFoundException, InterruptedException
    {
        Configuration conf = new Configuration();
        //实例化一个作业，word count是作业的名字
        Job job = Job.getInstance(conf, "jobsort");
        //指定通过哪个类找到对应的jar包
        job.setJarByClass(SortJob.class);

        //为job设置Mapper类
        job.setMapperClass(SortMapper.class);
        //为job设置reduce类
        job.setReducerClass(SortReducer.class);

        //为job的输出数据设置key类
        job.setOutputKeyClass(IntWritable.class);
        //为job输出设置value类
        job.setOutputValueClass(IntWritable.class);

        //为job设置输入路径，输入路径是存在的文件夹/文件
        FileInputFormat.addInputPath(job,new Path("D:\\sortData\\sort.txt"));
        //为job设置输出路径
        FileOutputFormat.setOutputPath(job,new Path("D:\\sortdataout"));
        job.waitForCompletion(true);
    }

}

运行后查看输出文件结果