二十五、GroupingComparator分组

一、GroupingComparator介绍

GroupingComparator是对Reduce阶段的数据根据某一个或几个字段进行分组；
如果是自定义类型的key，可以按照自定义的bean对象设置分组规则。

1、分组排序步骤

（1）自定义类继承WritableComparator
（2）重写compare()方法
 @Override
 public int compare(WritableComparable a, WritableComparable b) {
		// 比较的业务逻辑
		return result;
 }
（3）创建一个构造将比较对象的类传给父类
protected OrderGroupingComparator() {
		super(OrderBean.class, true);
}

二、分组实操

1、分析需求

如下订单数据，取出每个订单的最贵商品

0000001	Pdt_01	222.8
0000002	Pdt_05	722.4
0000001	Pdt_02	33.8
0000003	Pdt_06	232.8
0000003	Pdt_02	33.8
0000002	Pdt_03	522.8
0000002	Pdt_04	122.4

2、实现方式

第一种：

按照 \t 分割字符串，取订单id与价格，将订单id作为key，价格为value；
reduce端获取同一id所有价格，循环比较获取其最大的金额输出即可

第二种：reduce端分组方式

1.map端
将id与价格封装一个bean类型
按照id升序，价格降序方式排序
将封装bean作为key输出

2.reduce端
将接收的key按照id分组；
分组规则默认相同key只取其第一个值，由于map端已经排序，所以取到的第一个值就是最大值。
直接输出key即可，就是此订单组最大金额

3、分组方式代码

3.1 bean类型

package com.cjy.mr.group;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import org.apache.hadoop.io.WritableComparable;

public class OrderBean implements WritableComparable<OrderBean> {

    private int order_id; // 订单id号
    private double price; // 价格

    public OrderBean() {
        super();
    }

    public OrderBean(int order_id, double price) {
        super();
        this.order_id = order_id;
        this.price = price;
    }

    @Override
    public void write(DataOutput out) throws IOException {
        out.writeInt(order_id);
        out.writeDouble(price);
    }

    @Override
    public void readFields(DataInput in) throws IOException {
        order_id = in.readInt();
        price = in.readDouble();
    }

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

    public int getOrder_id() {
        return order_id;
    }

    public void setOrder_id(int order_id) {
        this.order_id = order_id;
    }

    public double getPrice() {
        return price;
    }

    public void setPrice(double price) {
        this.price = price;
    }

    // 二次排序：即第一个比较条件相等情况下，比较第二的条件
    @Override
    public int compareTo(OrderBean o) {

        int result;
        //一次比较id
        if (order_id > o.getOrder_id()) {
            result = 1;
        } else if (order_id < o.getOrder_id()) {
            result = -1;
        } else {
            //二次比较价格
            // 价格倒序排序
            result = price > o.getPrice() ? -1 : 1;
        }

        return result;
    }
}

3.2 mapper

package com.cjy.mr.group;

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

public class OrderMapper extends Mapper<LongWritable, Text, OrderBean, NullWritable> {

    OrderBean k = new OrderBean();

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

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

        // 2 截取
        String[] fields = line.split("\t");

        // 3 封装对象
        k.setOrder_id(Integer.parseInt(fields[0]));
        k.setPrice(Double.parseDouble(fields[2]));

        // 4 写出--只写出key即可
        context.write(k, NullWritable.get());
    }
}

3.3 自定义分组规则

package com.cjy.mr.group;
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.WritableComparator;

public class OrderGroupingComparator extends WritableComparator {

    protected OrderGroupingComparator() {
        super(OrderBean.class, true);
    }

    @Override
    public int compare(WritableComparable a, WritableComparable b) {

        OrderBean aBean = (OrderBean) a;
        OrderBean bBean = (OrderBean) b;

        int result;
        //只比较id，id相同的就分为一组数据
        if (aBean.getOrder_id() > bBean.getOrder_id()) {
            result = 1;
        } else if (aBean.getOrder_id() < bBean.getOrder_id()) {
            result = -1;
        } else {
            result = 0;
        }

        return result;
    }
}

3.4 reducer

package com.cjy.mr.group;

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

public class OrderReducer extends Reducer<OrderBean, NullWritable, OrderBean, NullWritable> {

    @Override
    protected void reduce(OrderBean key, Iterable<NullWritable> values, Context context)		throws IOException, InterruptedException {
        //由于map端key已经排序，所以取第一个key的值就是当前组内最大值
        context.write(key, NullWritable.get());
    }
}

3.5 Driver

package com.cjy.mr.group;

import java.io.IOException;
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;

public class OrderDriver {

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

// 输入输出路径需要根据自己电脑上实际的输入输出路径设置
//        args  = new String[]{"e:/input/inputorder" , "e:/output1"};

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

        // 2 设置jar包加载路径
        job.setJarByClass(OrderDriver.class);

        // 3 加载map/reduce类
        job.setMapperClass(OrderMapper.class);
        job.setReducerClass(OrderReducer.class);

        // 4 设置map输出数据key和value类型
        job.setMapOutputKeyClass(OrderBean.class);
        job.setMapOutputValueClass(NullWritable.class);

        // 5 设置最终输出数据的key和value类型
        job.setOutputKeyClass(OrderBean.class);
        job.setOutputValueClass(NullWritable.class);

        // 6 设置输入数据和输出数据路径

        FileInputFormat.setInputPaths(job, new Path("/Users/chenjunying/Downloads/input/order.txt"));
        FileOutputFormat.setOutputPath(job, new Path("/Users/chenjunying/Downloads/out1"));

        // 8 设置reduce端的分组规则--
        job.setGroupingComparatorClass(OrderGroupingComparator.class);

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