Hadoop实战学习（1）-WordCount

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
package com.hadoop;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

import java.io.IOException;
import java.util.StringTokenizer;

/**
 * @Author Administrator
 * @Date 2018/5/27 14:31
 */
public class HDFSDemo {

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf=new Configuration();
        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
        if (otherArgs.length != 2) {
            System.err.println("Usage: wordcount <in> <out>");
            System.exit(2);
        }else {
            FileSystem.get(conf).delete(new Path(otherArgs[1]));
        }
        //设置作业名称
        Job job=Job.getInstance(conf,"wordcount");
        //设置搜索类
        job.setJarByClass(HDFSDemo.class);
        //设置输入格式,TextInputFormat是默认输入格式,不能设置成FileInputFormat.Class,该惨数在当前情况下可以不设置
        job.setInputFormatClass(TextInputFormat.class);
        //设置Mapper类
        job.setMapperClass(TokenizerMapper.class);
        //设置Reducer类
        job.setReducerClass(IntSumReducer.class);
        //设置Reducer个数
        job.setNumReduceTasks(1);
        //设置maper端单词输出格式
        job.setMapOutputKeyClass(Text.class);
        //设置mapper端单词输出个数格式
        job.setMapOutputValueClass(IntWritable.class);
        //设置Reducer端单词输出格式
        job.setOutputKeyClass(Text.class);
        //设置Reducer单词输出个数格式
        job.setOutputValueClass(IntWritable.class);
        //设置job的输入路径,多次add可以设置多个输入路径
        FileInputFormat.addInputPath(job,new Path(otherArgs[0]));
        //设置输出路径
        FileOutputFormat.setOutputPath(job,new Path(otherArgs[1]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }

    public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {

        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();

        public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            StringTokenizer itr = new StringTokenizer(value.toString());
            while (itr.hasMoreTokens()) {
                word.set(itr.nextToken());
                context.write(word, one);
            }
        }
    }

    public static class IntSumReducer
            extends Reducer<Text, IntWritable, Text, IntWritable> {
        private IntWritable result = new IntWritable();

        public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
            int sum = 0;
            for (IntWritable val : values) {
                sum += val.get();
            }
            result.set(sum);
            context.write(key, result);
        }
    }

}