MapReduce WritableComparable自定义排序案例实操（全排序&区内排序）

一、全排序

1. 需求

根据序列化案例产生的结果再次对总流量进行倒序排序。
（链接:https://blog.csdn.net/mengxianglong123/article/details/119341747）

2. 操作步骤

（1）FlowBean对象在原先基础上增加了比较功能

package com.atguigu.mapreduce.writablecompable;

import org.apache.hadoop.io.WritableComparable;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
// 实现的接口有所变化WritableComparable
public class FlowBean implements WritableComparable<FlowBean> {

    private long upFlow; //上行流量
    private long downFlow; //下行流量
    private long sumFlow; //总流量

    //提供无参构造
    public FlowBean() {
    }

    //生成三个属性的getter和setter方法
    public long getUpFlow() {
        return upFlow;
    }

    public void setUpFlow(long upFlow) {
        this.upFlow = upFlow;
    }

    public long getDownFlow() {
        return downFlow;
    }

    public void setDownFlow(long downFlow) {
        this.downFlow = downFlow;
    }

    public long getSumFlow() {
        return sumFlow;
    }

    public void setSumFlow(long sumFlow) {
        this.sumFlow = sumFlow;
    }

    public void setSumFlow() {
        this.sumFlow = this.upFlow + this.downFlow;
    }

    //实现序列化和反序列化方法,注意顺序一定要一致
    @Override
    public void write(DataOutput out) throws IOException {
        out.writeLong(this.upFlow);
        out.writeLong(this.downFlow);
        out.writeLong(this.sumFlow);

    }

    @Override
    public void readFields(DataInput in) throws IOException {
        this.upFlow = in.readLong();
        this.downFlow = in.readLong();
        this.sumFlow = in.readLong();
    }

    //重写ToString,最后要输出FlowBean
    @Override
    public String toString() {
        return upFlow + "\t" + downFlow + "\t" + sumFlow;
    }

    @Override
    public int compareTo(FlowBean o) {

        //按照总流量比较,倒序排列
        if(this.sumFlow > o.sumFlow){
            return -1;
        }else if(this.sumFlow < o.sumFlow){
            return 1;
        }else {
            return 0;
        }
    }
}

关键：

  @Override
    public int compareTo(FlowBean o) {

        //按照总流量比较,倒序排列
        if(this.sumFlow > o.sumFlow){
            return -1;
        }else if(this.sumFlow < o.sumFlow){
            return 1;
        }else {
            return 0;
        }
    }

（2）编写Mapper类

package com.atguigu.mapreduce.writablecompable;

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

public class FlowMapper extends Mapper<LongWritable, Text, FlowBean, Text> {
    private FlowBean outK = new FlowBean();
    private Text outV = new Text();

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

        //1 获取一行数据
        String line = value.toString();

        //2 按照"\t",切割数据
        String[] split = line.split("\t");

        //3 封装outK outV
        outK.setUpFlow(Long.parseLong(split[1]));
        outK.setDownFlow(Long.parseLong(split[2]));
        outK.setSumFlow();
        outV.set(split[0]);

        //4 写出outK outV
        context.write(outK,outV);
    }
}

（3）编写Reducer类

package com.atguigu.mapreduce.writablecompable;

import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;

public class FlowReducer extends Reducer<FlowBean, Text, Text, FlowBean> {
    @Override
    protected void reduce(FlowBean key, Iterable<Text> values, Context context) throws IOException, InterruptedException {

        //遍历values集合,循环写出,避免总流量相同的情况
        for (Text value : values) {
            //调换KV位置,反向写出
            context.write(value,key);
        }
    }
}

（4）编写Driver类

package com.atguigu.mapreduce.writablecompable;

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 FlowDriver {

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

        //1 获取job对象
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        //2 关联本Driver类
        job.setJarByClass(FlowDriver.class);

        //3 关联Mapper和Reducer
        job.setMapperClass(FlowMapper.class);
        job.setReducerClass(FlowReducer.class);

        //4 设置Map端输出数据的KV类型
        job.setMapOutputKeyClass(FlowBean.class);
        job.setMapOutputValueClass(Text.class);

        //5 设置程序最终输出的KV类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FlowBean.class);

        //6 设置输入输出路径
        FileInputFormat.setInputPaths(job, new Path("D:\\inputflow2"));
        FileOutputFormat.setOutputPath(job, new Path("D:\\comparout"));

        //7 提交Job
        boolean b = job.waitForCompletion(true);
        System.exit(b ? 0 : 1);
    }
}

二、区内排序

1. 需求

要求每个省份手机号输出的文件中按照总流量内部排序。

2. 需求分析

基于前一个全排序的需求，增加自定义分区类，分区按照省份手机号设置。

3. 步骤

（1）增加自定义分区类

package com.atguigu.mapreduce.partitionercompable;

import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Partitioner;

public class ProvincePartitioner2 extends Partitioner<FlowBean, Text> {

    @Override
    public int getPartition(FlowBean flowBean, Text text, int numPartitions) {
        //获取手机号前三位
        String phone = text.toString();
        String prePhone = phone.substring(0, 3);

        //定义一个分区号变量partition,根据prePhone设置分区号
        int partition;
        if("136".equals(prePhone)){
            partition = 0;
        }else if("137".equals(prePhone)){
            partition = 1;
        }else if("138".equals(prePhone)){
            partition = 2;
        }else if("139".equals(prePhone)){
            partition = 3;
        }else {
            partition = 4;
        }

        //最后返回分区号partition
        return partition;
    }
}

（2）在驱动类中添加分区类

// 设置自定义分区器
job.setPartitionerClass(ProvincePartitioner2.class);

// 设置对应的ReduceTask的个数
job.setNumReduceTasks(5);