二次排序案例（GroupingComparator）

-------------------------------------------------------------

一、原始版本：

1.需求：

求出每一个订单中最贵的商品

2.输入数据：

0000001 Pdt_01 222.8
0000002 Pdt_06 722.4
0000001 Pdt_05 25.8
0000003 Pdt_01 222.8
0000003 Pdt_01 33.8
0000002 Pdt_03 522.8
0000002 Pdt_04 122.4

3.分析：

（1）利用“订单id和成交金额”作为key，可以将map阶段读取到的所有订单数据按照id分区，按照金额排序，发送到reduce。
（2）在reduce端利用groupingcomparator将订单id相同的kv聚合成组，然后取第一个即是最大值。

4.代码实现：

（1）FlowBean类：

import org.apache.hadoop.io.WritableComparable;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

/**
 * Author : 若清 and wgh
 * Version : 2020/4/14 & 1.0
 */
public class FlowBean implements WritableComparable<FlowBean> {
private long id;
private double price;

//二次排序
public int compareTo(FlowBean o) {
//按照订单id升序
if (this.id > o.id){
return 1;
}else if (this.id < o.id){
return -1;
}else {
//价格倒序
return this.price > o.price ? -1:1;
}
}

//反序列化用的空参构造器
public FlowBean(){

}

//重载  赋值
public FlowBean(long id,double price){
this.id = id;
this.price = price;
}
//序列化
public void write(DataOutput dataOutput) throws IOException {
    dataOutput.writeLong(id);
    dataOutput.writeDouble(price);
}
//反序列化
public void readFields(DataInput dataInput) throws IOException {
this.id = dataInput.readLong();
this.price = dataInput.readDouble();
}

@Override
public String toString() {
return this.id +"\t"+this.price;
}
}

（2）SortMapper类：

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

import java.io.IOException;

/**
 * Author : 若清 and wgh
 * Version : 2020/4/14 & 1.0
 */
public class SortMapper extends Mapper<LongWritable, Text,FlowBean, NullWritable> {
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
//获取数据
        String line = value.toString();

//切分
        String[] splits = line.split("\t");

//输出，封装数据
        context.write(new FlowBean(Long.parseLong(splits[0]),Double.parseDouble(splits[2])),NullWritable.get());
}
}

（3）SortReducer类：

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

import java.io.IOException;

/**
 * Author : 若清 and wgh
 * Version : 2020/4/14 & 1.0
 */
public class SortReducer extends Reducer<FlowBean, NullWritable,FlowBean,NullWritable> {
@Override
protected void reduce(FlowBean key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
//输出
        context.write(key,NullWritable.get());
}
}

（4）SortDriver类：

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
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 : 若清 and wgh
 * Version : 2020/4/14 & 1.0
 */
public class SortDriver {
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        args = new String[]{"D:\\input\\plus\\input\\GroupingComparator.txt","D:\\input\\plus\\output\\0821"};

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

//2.加载jar包
        job.setJarByClass(SortDriver.class);

//3.关联map和reduce
        job.setMapperClass(SortMapper.class);
        job.setReducerClass(SortReducer.class);

// 4 设置最终输出类型
        job.setMapOutputKeyClass(FlowBean.class);
        job.setMapOutputValueClass(NullWritable.class);
        job.setOutputKeyClass(FlowBean.class);
        job.setOutputValueClass(NullWritable.class);

// 5 设置输入和输出路径
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

//6.提交job任务
        job.waitForCompletion(true);
}
}

5.运行结果：

---------------------------------------------------------------------------------

二、程序优化：

1.代码实现：

（1）增加一个Group类：

import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.WritableComparator;
/**
 * Author : 若清 and wgh
 * Version : 2020/4/14 & 1.0
 */

public class Group  extends WritableComparator {
    //mapper类中的默认分组，Key
    public Group(){
        super(FlowBean.class,true);
    }
    @Override
    public int compare(WritableComparable a, WritableComparable b) {
        FlowBean a1 = (FlowBean) a;
        FlowBean b1 = (FlowBean) b;
        //按照FlowBean里面id重新分组
        if(a1.getId()>b1.getId()){
            return 1;
        }else if (a1.getId()<b1.getId()){
            return -1;
        }else {
            return 0;
        }

    }
}

（2）FlowBean类：

扫描二维码关注公众号，回复： 10972578 查看本文章

import lombok.Getter;
import org.apache.hadoop.io.WritableComparable;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
/**
 * Author : 若清 and wgh
 * Version : 2020/4/14 & 1.0
 */
@Getter
public class FlowBean implements WritableComparable<FlowBean>{
    private long id;
    private double price;
    //二次排序
    public int compareTo(FlowBean o) {
        //按照订单id升序
        if (this.id>o.id){
            return 1;
        }else if (this.id<o.id){
            return -1;
        }else {
            //价格倒序
            return this.price>o.price? -1:1;

        }
    }
    //反序列化用的空参构造器
    public FlowBean(){

    }
    //重载  赋值
    public FlowBean(long id,double price){
        this.id = id;
        this.price = price;
    }
    //序列化
    public void write(DataOutput dataOutput) throws IOException {
        dataOutput.writeLong(id);
        dataOutput.writeDouble(price);
    }
    //反序列化
    public void readFields(DataInput dataInput) throws IOException {
        this.id = dataInput.readLong();
        this.price = dataInput.readDouble();
    }

    @Override
    public String toString() {
        return this.id+"\t"+this.price;
    }
}

（3）SortMapper类：

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

import java.io.IOException;
/**
 * Author : 若清 and wgh
 * Version : 2020/4/14 & 1.0
 */
public class SortMapper extends Mapper<LongWritable, Text,FlowBean, NullWritable> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //获取数据
        String line = value.toString();
        //切分
        String[] splits = line.split("\t");
        //输出,封装数据
        context.write(new FlowBean(Long.parseLong(splits[0]),Double.parseDouble(splits[2])),NullWritable.get());

    }

}

（4）SortReducer类：

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

import java.io.IOException;
/**
 * Author : 若清 and wgh
 * Version : 2020/4/14 & 1.0
 */
public class SortReducer extends Reducer<FlowBean, NullWritable,FlowBean, NullWritable> {
    @Override
    protected void reduce(FlowBean key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {

        //输出
        context.write(key,NullWritable.get());
    }
}

（5）SortDriver类：

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
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 : 若清 and wgh
 * Version : 2020/4/14 & 1.0
 */
public class SortDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        args = new String[]{"D:\\input\\plus\\input\\GroupingComparator.txt", "D:\\input\\plus\\output\\0822"};
        // 1 获取job信息
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        // 2 加载jar包
        job.setJarByClass(SortDriver.class);

        // 3 关联map和reduce
        job.setMapperClass(SortMapper.class);
        job.setReducerClass(SortReducer.class);
        // 4 设置最终输出类型
        job.setMapOutputKeyClass(FlowBean.class);
        job.setMapOutputValueClass(NullWritable.class);
        job.setOutputKeyClass(FlowBean.class);
        job.setOutputValueClass(NullWritable.class);

        //5 自定义分组，辅助排序分组的key
        job.setGroupingComparatorClass(Group.class);

        // 6 设置输入和输出路径
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        // 7 提交
        job.waitForCompletion(true);
    }
}

2.运行结果：

如图所示，优化后的程序真正做到了求出每一个订单中最贵的商品。