0%

Hadoop MapReduce 编写例子

编写一个简单的WordCount例子

WordCount.java

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
/**
* 简单的单词计数器
*/

/**
*
* @author Neo neosfung_gmail_com
* @version 1.0 2012-11-11
*/
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;

public class WordCount {

public static class Map extends MapReduceBase implements
Mapper<LongWritable, Text, Text, IntWritable> {
private final static IntWritable one = new IntWritable(1);
private final Text word = new Text();

/**
* map函数继承自MapReduceBase, 并且实现了Mapper接口, 此接口是一个泛型类型,它有4种形式的参数,
* 分别用来指定map的输入key类型, 输入value值类型, 输出key值类型和输出value值类型.
* 在本例中,输入使用的是TextInputFormat, 它的输出key值是LongWritable类型, 输出value值是Text类型.
* 根据本例, 需要输出的是<Text, IntWritable>的形式, 所以输出的key值类型是Text,
* 输出的value类型是IntWritable.
*/
@Override
public void map(LongWritable key, Text value,
OutputCollector<Text, IntWritable> output, Reporter reporter)
throws IOException {
String line = value.toString();
StringTokenizer tokenizer = new StringTokenizer(line);
while (tokenizer.hasMoreTokens()) {
word.set(tokenizer.nextToken());
output.collect(word, one);
}

}
}

public static class Reduce extends MapReduceBase implements
Reducer<Text, IntWritable, Text, IntWritable> {

/**
* reduce函数的输入以map的输出作对应, 因此reduce的输入类型是<Text, IntWritable>.
*/
@Override
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));

}
}

/**
* @param args
* @throws IOException
*/
public static void main(String[] args) throws IOException {
// TODO Auto-generated method stub
JobConf conf = new JobConf(WordCount.class);
conf.setJobName("wordcount");

// 设定输出的key和value类型
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(IntWritable.class);

// 设定各个作业的类
conf.setMapperClass(Map.class);
conf.setCombinerClass(Reduce.class);
conf.setReducerClass(Reduce.class);

// 设定输入输出的格式
conf.setInputFormat(TextInputFormat.class);
conf.setOutputFormat(TextOutputFormat.class);

FileInputFormat.setInputPaths(conf, new Path(args[0]));
FileOutputFormat.setOutputPath(conf, new Path(args[1]));

JobClient.runJob(conf);
}

}

编译:

-classpath ~/hadoop/hadoop-core-1.0.3.jar WordCount.java```
1
2
3
4
5
6



打包:

```jar -cvf WordCount.jar -C ./ .

运行,其中input为hdfs上的输入文件夹:

hadoop jar WordCount.jar WordCount input output