MapReduce-多个Mapper

MapReduce的多输入、多mapper

虽然一个MapReduce作业的输入可能包含多个输入文件(由文件glob、过滤器和路径组成),但所有文件都由同一个InputFormat和同一个Mapper来解释。然而,数据格式往往会随时间而演变,所以必须写自己的mapper来处理应用中的遗留数据格式问题。或者,有些数据源会提供相同的数据,但是格式不同。
这些问题可以用MultipleInputs类来妥善处理,它允许为每条输入路径指定InputFormat和Mapper。

代码如下

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
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
package com.zhen.mapreduce.multipleInput;
 
import java.io.IOException;
 
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.MultipleInputs;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
 
/**
 * @author FengZhen
 * @date 2018年8月25日
 * 多输入、多mapper
 */
public class MultipleInputsTest extends Configured implements Tool{
 
    /**
     * 根据 ` 分隔字符串
     * @author FengZhen
     *
     */
    static class SplitMapper1 extends Mapper<LongWritable, Text, Text, IntWritable>{
        @Override
        protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, IntWritable>.Context context)
                throws IOException, InterruptedException {
            String[] values = value.toString().split("`");
            for (String string : values) {
                context.write(new Text(string), new IntWritable(1));
            }
        }
    }
     
    /**
     * 根据 , 分隔字符串
     * @author FengZhen
     *
     */
    static class SplitMapper2 extends Mapper<LongWritable, Text, Text, IntWritable>{
        @Override
        protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, IntWritable>.Context context)
                throws IOException, InterruptedException {
            String[] values = value.toString().split(",");
            for (String string : values) {
                context.write(new Text(string), new IntWritable(1));
            }
        }
    }
 
    /**
     * 同一个reduce
     * @author FengZhen
     *
     */
    static class SplitReducer extends Reducer<Text, IntWritable, Text, IntWritable>{
        @Override
        protected void reduce(Text key, Iterable<IntWritable> value,
                Reducer<Text, IntWritable, Text, IntWritable>.Context context) throws IOException, InterruptedException {
            int sum = 0;
            for (IntWritable intWritable : value) {
                sum += intWritable.get();
            }
            context.write(key, new IntWritable(sum));
        }
    }
 
    public int run(String[] args) throws Exception {
         
        Configuration configuration = new Configuration();
         
        Job job = Job.getInstance(configuration);
        job.setJobName("MultipleInputs");
        job.setJarByClass(MultipleInputsTest.class);
         
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
 
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
         
        job.setReducerClass(SplitReducer.class);
         
        //设置多输入、多mapper
        MultipleInputs.addInputPath(job, new Path(args[0]), TextInputFormat.class, SplitMapper1.class);
        MultipleInputs.addInputPath(job, new Path(args[1]), TextInputFormat.class, SplitMapper2.class);
         
        job.setOutputFormatClass(TextOutputFormat.class);
        TextOutputFormat.setOutputPath(job, new Path(args[2]));
         
        return job.waitForCompletion(true) ? 0 : 1;
    }
     
    public static void main(String[] args) {
        try {
            String[] params = {"hdfs://fz/user/hdfs/MapReduce/data/multipleInputs/test1","hdfs://fz/user/hdfs/MapReduce/data/multipleInputs/test2", "hdfs://fz/user/hdfs/MapReduce/data/multipleInputs/output"};
            int exitCode = ToolRunner.run(new MultipleInputsTest(), params);
            System.exit(exitCode);
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
     
}

  

posted on   嘣嘣嚓  阅读(824)  评论(0编辑  收藏  举报

编辑推荐:
· 记一次.NET内存居高不下排查解决与启示
· 探究高空视频全景AR技术的实现原理
· 理解Rust引用及其生命周期标识(上)
· 浏览器原生「磁吸」效果!Anchor Positioning 锚点定位神器解析
· 没有源码,如何修改代码逻辑?
阅读排行:
· 分享4款.NET开源、免费、实用的商城系统
· 全程不用写代码,我用AI程序员写了一个飞机大战
· MongoDB 8.0这个新功能碉堡了,比商业数据库还牛
· 白话解读 Dapr 1.15:你的「微服务管家」又秀新绝活了
· 记一次.NET内存居高不下排查解决与启示

导航

< 2025年3月 >
23 24 25 26 27 28 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 1 2 3 4 5
点击右上角即可分享
微信分享提示