Hadoop MapReduce入门

一:配置pom

<dependency>
    <groupId>org.apache.hadoop</groupId>
    <artifactId>hadoop-core</artifactId>
    <version>1.0.1</version>
</dependency>

二:测试代码

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
package com.jachs.hadoop;
 
import java.io.IOException;
import java.util.Iterator;
import java.util.StringTokenizer;
 
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.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.mapred.TextInputFormat;
import org.apache.hadoop.mapred.TextOutputFormat;
 
/***
 *
 * @author zhanchaohan
 *
 */
public class WordCount {
    /*输入文件地址,测试内容如下:
     * ------------------------
      Hello Workd Bye World
      Hello Hadoop Goodbye Hadoop
      Hello Workd Bye World And Hello Hadoop Goodbye Hadoop
     ------------------------
      */
    private static final String InputFile="/usr/jachs/hadoop/A";
     
    //输出路径
    private static final String OutDir="/usr/jachs/hadoop/B";
     
    //将读取文件的内容切割出每个单词,标记数量为1,<word,1>形式,然后交给Reduce处理
    public static class Map extends MapReduceBase implements Mapper<LongWritable,Text,Text,IntWritable>{
        private final static IntWritable one=new IntWritable(1);
        private Text word=new Text();
         
        public void map(LongWritable key, Text value, OutputCollector<Text, IntWritable> output, Reporter reporter)
                throws IOException {
            String line=value.toString();
            StringTokenizer token=new StringTokenizer(line);
             
            while(token.hasMoreTokens()) {
                word.set(token.nextToken());
                output.collect(value, one);
            }
             
        }
    }
    //Reduce简单将数值累计求和
    public static class Reduce extends MapReduceBase implements Reducer<Text, IntWritable, Text, IntWritable>{
        public void reduce(Text key, Iterator<IntWritable> values, OutputCollector<Text, IntWritable> output,
                Reporter reporter) throws IOException {
            int sum=0;
            while (values.hasNext()) {
                sum+=values.next().get();
            }
            output.collect(key, new IntWritable(sum));
        }
    }
     
    public static void main(String[] args) throws IOException {
        JobConf conf=new JobConf(WordCount.class);
        conf.setJobName("wordCount");
         
        conf.setOutputKeyClass(Text.class);
        conf.setOutputValueClass(IntWritable.class);
         
        conf.setMapperClass(Map.class);
        conf.setReducerClass(Reduce.class);
         
        conf.setInputFormat(TextInputFormat.class);
        conf.setOutputFormat(TextOutputFormat.class);
         
        FileInputFormat.setInputPaths(conf, new Path(InputFile));
        FileOutputFormat.setOutputPath(conf, new Path(OutDir));
         
        JobClient.runJob(conf);
    }
}

 三:执行windows下执行会报异常需要修改源码。返回结构如下图打印每行单词个数

 

 

posted @   Jachs  阅读(34)  评论(0编辑  收藏  举报
相关博文:
阅读排行:
· DeepSeek “源神”启动!「GitHub 热点速览」
· 微软正式发布.NET 10 Preview 1:开启下一代开发框架新篇章
· C# 集成 DeepSeek 模型实现 AI 私有化(本地部署与 API 调用教程)
· DeepSeek R1 简明指南:架构、训练、本地部署及硬件要求
· 2 本地部署DeepSeek模型构建本地知识库+联网搜索详细步骤
点击右上角即可分享
微信分享提示
桃之夭夭,灼灼其华。