MapReduce快速入門系列(10) | Shuffle之GroupingComparator分組（輔助排序）

Hello，大家好！博主上篇講解了合併，這篇要講的是輔助排序。如何講解這個章節呢？首先先對什麼是合併進行解釋，然後通過案例進行證明。

---

一. GroupingComparator分組的簡介

什麼是GroupingComparator分組（輔助排序）？
  對Reduce階段的數據根據某一個或幾個字段進行分組。

分組排序的步驟：

• 1. 自定義類繼承WritableComparator
• 2. 重寫compare()方法

@Override
public int compare(WritableComparable a, WritableComparable b) {
		// 比較的業務邏輯
		return result;
}

• 3. 創建一個構造將比較對象的類傳給父類

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

二. 根據案例分析

2.1 需求

• 1. 有如下訂單數據

訂單id	商品id	成交金額
0000001	Pdt_01	222.8
	Pdt_02	33.8
0000001	Pdt_03	522.8
	Pdt_04	122.4
	Pdt_05	722.4
0000001	Pdt_06	232.8
	Pdt_02	33.8

現在需要求出每一個訂單中最貴的商品。

• 2. 輸入的數據
  
• 3. 期望輸出數據

1	222.8
2	722.4
3	232.8

2.2 需求分析

（1）利用“訂單id和成交金額”作爲key，可以將Map階段讀取到的所有訂單數據按照id升序排序，如果id相同再按照金額降序排序，發送到Reduce。
（2）在Reduce端利用groupingComparator將訂單id相同的kv聚合成組，然後取第一個即是該訂單中最貴商品，如下圖所示所示。

2.3 代碼實現

1. 定義訂單信息OrderBean類

package com.buwenbuhuo.groupingcomparator;

import org.apache.hadoop.io.WritableComparable;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
/**
 * @author 卜溫不火
 * @create 2020-04-24 23:43
 * com.buwenbuhuo.groupingcomparator - the name of the target package where the new class or interface will be created.
 * mapreduce0422 - the name of the current project.
 */
public class OrderBean implements WritableComparable<OrderBean> {

    private String orderId;
    private String productId;
    private double price;

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

    public String getOrderId() {
        return orderId;
    }

    public void setOrderId(String orderId) {
        this.orderId = orderId;
    }

    public String getProductId() {
        return productId;
    }

    public void setProductId(String productId) {
        this.productId = productId;
    }

    public double getPrice() {
        return price;
    }

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

    @Override
    public int compareTo(OrderBean o) {

        int compare = this.orderId.compareTo(o.orderId);

        if (compare == 0) {
            return Double.compare(o.price, this.price);
        } else {
            return compare;
        }
    }

    @Override
    public void write(DataOutput out) throws IOException {
        out.writeUTF(orderId);
        out.writeUTF(productId);
        out.writeDouble(price);
    }

    @Override
    public void readFields(DataInput in) throws IOException {
        this.orderId = in.readUTF();
        this.productId = in.readUTF();
        this.price = in.readDouble();
    }
}

2. 編寫OrderSortMapper類

package com.buwenbuhuo.groupingcomparator;

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 卜溫不火
 * @create 2020-04-24 23:43
 * com.buwenbuhuo.groupingcomparator - the name of the target package where the new class or interface will be created.
 * mapreduce0422 - the name of the current project.
 */
public class OrderMapper extends Mapper<LongWritable, Text, OrderBean, NullWritable> {


    private OrderBean orderBean = new OrderBean();

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String[] fields = value.toString().split("\t");
        orderBean.setOrderId(fields[0]);
        orderBean.setProductId(fields[1]);
        orderBean.setPrice(Double.parseDouble(fields[2]));
        context.write(orderBean, NullWritable.get());
    }
}

3. 編寫OrderSortGroupingComparator類

package com.buwenbuhuo.groupingcomparator;

import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.WritableComparator;
/**
 * @author 卜溫不火
 * @create 2020-04-24 23:43
 * com.buwenbuhuo.groupingcomparator - the name of the target package where the new class or interface will be created.
 * mapreduce0422 - the name of the current project.
 */
public class OrderComparator extends WritableComparator {

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

    @Override
    public int compare(WritableComparable a, WritableComparable b) {
        OrderBean oa = (OrderBean) a;
        OrderBean ob = (OrderBean) b;

        return oa.getOrderId().compareTo(ob.getOrderId());
    }
}

4. 編寫OrderSortReducer類

package com.buwenbuhuo.groupingcomparator;

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

import java.io.IOException;
import java.util.Iterator;
/**
 * @author 卜溫不火
 * @create 2020-04-24 23:43
 * com.buwenbuhuo.groupingcomparator - the name of the target package where the new class or interface will be created.
 * mapreduce0422 - the name of the current project.
 */
public class OrderReducer extends Reducer<OrderBean, NullWritable, OrderBean, NullWritable> {

    @Override
    protected void reduce(OrderBean key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
        Iterator<NullWritable> iterator = values.iterator();
        for (int i = 0; i < 2; i++) {
            if (iterator.hasNext()) {
                context.write(key, iterator.next());
            }
        }
    }
}

5. 編寫OrderSortDriver類

package com.buwenbuhuo.groupingcomparator;

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 卜溫不火
 * @create 2020-04-24 23:43
 * com.buwenbuhuo.groupingcomparator - the name of the target package where the new class or interface will be created.
 * mapreduce0422 - the name of the current project.
 */
public class OrderDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Job job = Job.getInstance(new Configuration());

        job.setJarByClass(OrderDriver.class);

        job.setMapperClass(OrderMapper.class);
        job.setReducerClass(OrderReducer.class);

        job.setMapOutputKeyClass(OrderBean.class);
        job.setMapOutputValueClass(NullWritable.class);

        job.setGroupingComparatorClass(OrderComparator.class);

        job.setOutputKeyClass(OrderBean.class);
        job.setOutputValueClass(NullWritable.class);

        FileInputFormat.setInputPaths(job, new Path("d:\\input"));
        FileOutputFormat.setOutputPath(job, new Path("d:\\output"));

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

2.4 運行與結果實現

• 1. 運行
  
• 2. 結果與對比
  

---

本次的分享就到這裏了,大家有什麼疑惑或者好的建議可以在評論區積極留言。受益的小夥伴們不要忘了點贊關注我呀！！！