wordcount

最基本的,需要手动写出。

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
package com.qr.mr.wordcount;

import org.apache.hadoop.conf.Configuration;
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.output.FileOutputFormat;
import java.io.IOException;
import java.util.StringTokenizer;

/**
* StringTokenizer
* https://www.cnblogs.com/gnivor/p/4509268.html
*
*
* http://hadoop.apache.org/docs/r1.0.4/cn/mapred_tutorial.html#Map%2FReduce+-+%E7%94%A8%E6%88%B7%E7%95%8C%E9%9D%A2
* http://hadoop.apache.org/docs/stable/hadoop-mapreduce-client/hadoop-mapreduce-client-core/MapReduceTutorial.html#Payload
*
*/

public class WordCount {

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());//StringTokenizer
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);
}
}

public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf,"word count");
job.setJarByClass(WordCount.class);

job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumReducer.class);
job.setReducerClass(IntSumReducer.class);

job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);

FileInputFormat.addInputPath(job,new Path("/Users/lifei/Desktop/ab/a.txt"));
FileOutputFormat.setOutputPath(job,new Path("/Users/lifei/Desktop/ab_out"));
System.exit(job.waitForCompletion(true)? 0 : 1);
}
}