MapReduce列子WordCount-优快云博客

写程序MyWordCount.java

package org.myorg;

import java.io.IOException;
import java.util.*;

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.conf.*;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapred.*;
import org.apache.hadoop.util.*;

public class WordCount {
	public static void main(String[] args) throws Exception {
		JobConf conf = new JobConf(WordCount.class);
		conf.setJobName("wordcount");

		//conf.setNumReduceTasks(0);		
		
		conf.setOutputKeyClass(Text.class);
		conf.setOutputValueClass(IntWritable.class);
		
		conf.setMapperClass(Map.class);
		conf.setCombinerClass(Reduce.class);
		//conf.setReducerClass(Reduce.class);
	
		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);
	}

	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 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> {
		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));
		}
	}
}

源文档 <http://hadoop.apache.org/docs/r0.18.3/mapred_tutorial.html>

注：conf.setInputFormat(TextInputFormat.class); //TextInputFormat是默认的InputFormat。这说明Map类的键是LongWritable类型，存储整个文件的字节偏移量，值是Text类型，是一行内容。StringTokenizer 把行按空格拆分成单词。
conf.setOutputFormat(TextOutputFormat.class); //输出格式为TextOutputFormat，把输出记录写成文本行。键值可以使任何类型，因为可以用toString()方法转成字符串。这里的输出键是Text类型，值是IntWritable类型。

2. 编译

Mkdir wordcountsource

hduser@ubuntu:/usr/local/hadoop$ javac -classpath hadoop-core-1.1.1.jar -d wordcountsource MyWordCount.java
编译java到wordcountsource文件夹下
如果出现错误：error while writing Map: could not create parent directories
说明没有写入input文件的权限

3.生成jar

hduser@ubuntu:/usr/local/hadoop$ sudo jar -cvf MyWordCount.jar -C wordcountsource/ .

在当前目录下生成MyWordCount.jar

4.在input文件夹下创建file0和file1

hduser@ubuntu:/usr/local/hadoop/input$ mkdir input //input文件夹为输入

hduser@ubuntu:/usr/local/hadoop/input$ sudo gedit file0
hduser@ubuntu:/usr/local/hadoop/input$ sudo gedit file1

5.运行MyWordCount.jar

hduser@ubuntu:/usr/local/hadoop$ sudo bin/hadoop jar MyWordCount.jar org.myorg.MyWordCount input output

确保有创建output的权限

6.查看结果

hduser@ubuntu:/usr/local/hadoop$ cat output/part-00000

Bye 1
Hello 1
World 2