Hadoop概述/MapReduce/实例/WordCount

package com.run.ayena.distributed.test;

import java.io.IOException;

import java.util.StringTokenizer;

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 org.apache.hadoop.util.GenericOptionsParser;

//hadoop自带的例子,统计文本中每个单词出现的次数

public class WordCount {

	public static class TokenizerMapper extends

			Mapper {

		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 {

		private IntWritable result = new IntWritable();

		public void reduce(Text key, Iterable 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();

		String[] otherArgs = new GenericOptionsParser(conf, args)

				.getRemainingArgs();

		if (otherArgs.length != 2) {

			System.err.println("Usage: wordcount");

			System.exit(2);

		}

		// 指定系统路

		conf.set("mapred.system.dir", "/hadoopdata/mapred/system");

		// 设置运行的job名称

		Job job = new Job(conf, "word count");

		// 设置运行的job类

		job.setJarByClass(WordCount.class);

		// 设置Mapper

		job.setMapperClass(TokenizerMapper.class);

		// 设置本地聚合类，该例本地聚合类同Reduer类

		job.setCombinerClass(IntSumReducer.class);

		// 设置Reduer

		job.setReducerClass(IntSumReducer.class);

		// 设置Map的输出

		job.setMapOutputKeyClass(Text.class);

		job.setMapOutputValueClass(IntWritable.class);

		// 设置Reducer输出的key类型

		job.setOutputKeyClass(Text.class);

		// 设置Reducer输出的value类型

		job.setOutputValueClass(IntWritable.class);

		// 设置输入和输出的目录

		FileInputFormat.addInputPath(job, new Path(otherArgs[0]));

		FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));

		// 执行，直到结束就退出

		System.exit(job.waitForCompletion(true) ? 0 : 1);

	}

}