单词计数

输入实例：

hello world

hello hadoop

hello mr

输出实例

hadoop 1

hello 3

mr 1

package mapreduce.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;

public class WordCount {

	//继承Mapper接口，设置map的输入类型为<Object,Text>
	//输出类型为<Text,IntWritable>
	public static class WordCountMapper extends Mapper<Object, Text, Text, IntWritable>{
		//one表示单词出现一次
		private final static IntWritable one = new IntWritable(1);
		//word用于存储切下的单词
		private Text word = new Text();
		
		protected 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);
			}
		}
	}
	
	//继承Reducer接口，设置reduce的输入类型为<Text,IntWritable>
	//输出类型为<Text,IntWritable>
	public static class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable>{
		//result表示记录单词的总数
		private IntWritable result = new IntWritable();

		protected 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();
		//配置作业名
		Job job = new Job(conf,"Word count");
		//配置作业的各个类
		job.setJarByClass(WordCount.class);
		job.setMapperClass(WordCountMapper.class);
		job.setCombinerClass(WordCountReducer.class);
		job.setReducerClass(WordCountReducer.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);
	}
	
}