码迷,mamicode.com
首页 > 其他好文 > 详细

标准wordcount

时间:2014-06-05 09:12:55      阅读:203      评论:0      收藏:0      [点我收藏+]

标签:c   class   java   a   ext   int   

package wordcount;


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{
 public static class WordMap extends Mapper<Object,Text,Text,IntWritable>{
  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{
   String line=value.toString();
   StringTokenizer tokenizer = new StringTokenizer(line);
   while(tokenizer.hasMoreTokens()){
    word.set(tokenizer.nextToken());
    context.write(word, one);
   }
  }
 }
 
 public static class WordReduce extends Reducer<Text,IntWritable,Text,IntWritable>{
  private IntWritable result =new IntWritable();
  public 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();
 
  Job job =new Job(conf,"WordCount");
  
  job.setJarByClass(WordMap.class);
  job.setMapperClass(WordMap.class);
        job.setReducerClass(WordReduce.class);
  
  job.setOutputKeyClass(Text.class);
  job.setOutputValueClass(IntWritable.class);
  
  FileInputFormat.addInputPath(job,new Path(args[0]));
  FileOutputFormat.setOutputPath(job,new Path(args[1]));//setOutputPath(job,new Path(args[1]));
  
  System.exit(job.waitForCompletion(true)?0:1);
  
  
  
 }

}

标准wordcount,布布扣,bubuko.com

标准wordcount

标签:c   class   java   a   ext   int   

原文地址:http://blog.csdn.net/huaweitman/article/details/27340031

(0)
(0)
   
举报
评论 一句话评论(0
登录后才能评论!
© 2014 mamicode.com 版权所有  联系我们:gaon5@hotmail.com
迷上了代码!