上一篇博文讲了Shuffle排序的相关概念以及全排序的操作，这篇博文继续分享的是排序的另一种操作：区内排序。

一. 需求分析

  基于前一个需求，增加自定义分区类，分区按照省份手机号设置。

• 1. 把原数据排序后
  
• 2. 期望数据输出
  

二. 代码实现

2.1 增加自定义分区类MyPartitioner2

package com.buwenbuhuo.WritableComparable2;

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

/**
 * @author 卜温不火
 * @create 2020-04-24 18:14
 * com.buwenbuhuo.WritableComparable2 - the name of the target package where the new class or interface will be created.
 * mapreduce0422 - the name of the current project.
 */
public class MyPartitioner2 extends Partitioner<com.buwenbuhuo.WritableComparable.FlowBean, Text> { @Override public int getPartition(com.buwenbuhuo.WritableComparable.FlowBean flowBean, Text text, int numPartitions) { switch (text.toString().substring(0, 3)) { case "136": return 0; case "137": return 1; case "138": return 2; case "139": return 3; default: return 4; } }
}


  

 

  
1
  
2
  
3
  
4
  
5
  
6
  
7
  
8
  
9
  
10
  
11
  
12
  
13
  
14
  
15
  
16
  
17
  
18
  
19
  
20
  
21
  
22
  
23
  
24
  
25
  
26
  
27
  
28
  
29
 

2.2 在驱动类中添加分区类

// 加载自定义分区类
job.setPartitionerClass(ProvincePartitioner.class);

// 设置Reducetask个数
job.setNumReduceTasks(5);


  

 

  
1
  
2
  
3
  
4
  
5
  
6
 

• 此部分的完整代码如下:

package com.buwenbuhuo.WritableComparable2;

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;

/**
 * @author 卜温不火
 * @create 2020-04-24 18:19
 * com.buwenbuhuo.WritableComparable2 - the name of the target package where the new class or interface will be created.
 * mapreduce0422 - the name of the current project.
 */
public class SortDriver { public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException { Job job = Job.getInstance(new Configuration()); job.setJarByClass(com.buwenbuhuo.WritableComparable2.SortDriver.class); job.setMapperClass(com.buwenbuhuo.WritableComparable.SortMapper.class); job.setReducerClass(com.buwenbuhuo.WritableComparable.SortReducer.class); job.setMapOutputKeyClass(com.buwenbuhuo.WritableComparable.FlowBean.class); job.setMapOutputValueClass(Text.class); job.setPartitionerClass(MyPartitioner2.class); job.setNumReduceTasks(5); job.setOutputKeyClass(Text.class); job.setOutputValueClass(com.buwenbuhuo.WritableComparable.FlowBean.class); FileInputFormat.setInputPaths(job, new Path("d:\\output")); FileOutputFormat.setOutputPath(job, new Path("d:\\output2")); boolean b = job.waitForCompletion(true); System.exit(b ? 0 : 1); }
}

  

 

  
1
  
2
  
3
  
4
  
5
  
6
  
7
  
8
  
9
  
10
  
11
  
12
  
13
  
14
  
15
  
16
  
17
  
18
  
19
  
20
  
21
  
22
  
23
  
24
  
25
  
26
  
27
  
28
  
29
  
30
  
31
  
32
  
33
  
34
  
35
  
36
  
37
  
38
  
39
  
40
  
41
  
42
 

三. 运行及其结果

• 1. 运行
  
• 2. 结果
  
  
  
  
  
• 3. 与设想的对比
  
  可以看到是一样的。

本期的分享就到这里了,小伙伴们有什么疑惑或好的建议可以积极在评论区留言~，博主会持续更新新鲜好玩的技术,喜欢的小伙伴们不要忘了点赞，记得要关注博主呐ヾ(◍°∇°◍)ﾉﾞ。

文章来源: buwenbuhuo.blog.csdn.net，作者：不温卜火，版权归原作者所有，如需转载，请联系作者。

原文链接：buwenbuhuo.blog.csdn.net/article/details/105736481