Hadoop对输出的数据进行排序另外分组

Hadoop对输出的数据进行排序另外分组

数据

如果没有数据的话可以点开

https://blog.csdn.net/qq_17623363/article/details/104146939
对我这个案例进行做出来

然后

这是上一个案例另外加的一个分组

代码

MyPartitioner2.java

package com.zhenghui.writablecomparable2;

import com.zhenghui.writablecomparable.FlowBean;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Partitioner;

//按Value（Text）进行分区
public class MyPartitioner2  extends Partitioner<FlowBean, Text> {
    /**
     * 返回分区号
     * @param text
     * @param flowBean
     * @param numPartitions
     * @return
     */
    @Override
    public int getPartition(FlowBean flowBean, Text text, int numPartitions) {
        String phone = text.toString();//获取手机号

        switch (phone.substring(0,3)){
            case "136":
                return 0;
            case "137":
                return 1;
            case "138":
                return 2;
            case "139":
                return 3;
            default:
                return 4;
        }
    }
}

SortDriver.java

package com.zhenghui.writablecomparable2;

import com.zhenghui.writablecomparable.FlowBean;
import com.zhenghui.writablecomparable.SortMapper;
import com.zhenghui.writablecomparable.SortReducer;
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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;

public class SortDriver {

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
//        conf.set("mapreduce.output.key.field.separator", ",");

        Job job = Job.getInstance(conf);
        // 输出结果key val 分隔符修改为空 直接输出结果

        job.setJarByClass(SortDriver.class);
        job.setMapperClass(SortMapper.class);
        job.setReducerClass(SortReducer.class);

        job.setMapOutputKeyClass(FlowBean.class);
        job.setMapOutputValueClass(Text.class);

        //设置分区
        job.setNumReduceTasks(5);
        job.setPartitionerClass(MyPartitioner2.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FlowBean.class);

//        FileInputFormat.setInputPaths(job,new Path("E:\\file\\p.txt"));
        FileInputFormat.setInputPaths(job,new Path("E:\\outputa1"));
        FileOutputFormat.setOutputPath(job,new Path("E:\\output4"));

        boolean b = job.waitForCompletion(true);
        System.exit( b ? 0 : 1);
    }
}

测试结果