Hadoop的第一个程序 wordcount

Hadoop的第一个程序 wordcount

package com.songguoliang.hadoop.chapter05;

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;

/**
 * 单词计数demo
 * @date 2015-05-01 12:51:29
 * @author sgl
 */
public class WordCount {
	/**
	 * 继承Mapper接口
	 * @date 2015-05-01 12:53:03
	 * @author sgl
	 */
	public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable>{
		//one表示单词出现一次
		private final static IntWritable one=new IntWritable(1);
		//存储分割的单词
		private Text word=new Text();
		@Override
		protected void map(Object key, Text value, Mapper<Object, Text, Text, IntWritable>.Context context) throws IOException, InterruptedException {
			StringTokenizer itr=new StringTokenizer(value.toString());
			while (itr.hasMoreElements()) {
				word.set(itr.nextToken());
				context.write(word, one);
			}
		}
		
		
	}
	/**
	 * Reduce方法
	 * @date 2015-05-03 19:05:21
	 * @author sgl
	 */
	public static class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable>{
		private IntWritable result=new IntWritable();

		@Override
		protected void reduce(Text key, Iterable<IntWritable> values, Reducer<Text, IntWritable, Text, IntWritable>.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 IOException, InterruptedException, ClassNotFoundException {
		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);
		}
		Job job=new org.apache.hadoop.mapreduce.Job(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(args[0]));
		FileOutputFormat.setOutputPath(job, new Path(args[1]));
		System.exit(job.waitForCompletion(true)?0:1);
		
	}
}