Hadoop--map/reduce实现单词计数

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

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

 public class WordCount {

     /*
      * 实现输入内容单词的计数功能
      * 一、mapper方法将输入内容处理为<key1,value1>形式
      * 二、reduce方法接收mapper的结果，将相同key1的value值相加得到单词的个数
      * 三、输出得到的结果到hdfs中
      *
      * */

     //main函数
     public static void main(String[] args) throws Exception{
         JobConf conf=new JobConf(WordCount.class);
         conf.setJobName("WordCount");
         conf.setOutputKeyClass(Text.class);
         conf.setOutputValueClass(IntWritable.class);

         conf.setMapperClass(Map.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);

     }

     //map函数
     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);

             }

         }

     }

     //reduce函数
     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 repoter) throws IOException{
             int sum=0;
             while(values.hasNext()){
                 sum+=values.next().get();
             }
             output.collect(key,new IntWritable(sum));
         }
     }

 }