1.在IDEA下新建工程,选择from Mevan

GroupId:WordCount

ArtifactId:com.hadoop.1st

Project name:WordCount

2.pom.xml文件

     
         
      
       4.0.0
          
      
       WordCount
          
      
       com.hadoop.1st
          
      
       1.0-SNAPSHOT
          
              
                   
        
         apache
                    
        
         http://maven.apache.org
                
           
          
              
                   
        
         org.apache.hadoop
                    
        
         hadoop-core
                    
        
         1.2.1
                
               
                   
        
         org.apache.hadoop
                    
        
         hadoop-common
                    
        
         2.7.1
                
           
          
              
                   
                        
         
          maven-dependency-plugin
                         
                             
          
           false
                              
          
           true
                              
          
           ./lib
                          
                     
                
           
      
     

 3.main/java目录下新建WordCount.java文件

import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.fs.Path;import org.apache.hadoop.io.IntWritable;import org.apache.hadoop.io.LongWritable;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.input.TextInputFormat;import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;import java.io.IOException;import java.util.StringTokenizer;/** * Created by common on 17-3-26. */public class WordCount {    public static class WordCountMap extends            Mapper
     
       {        private final IntWritable one = new IntWritable(1);        private Text word = new Text();        public void map(LongWritable key, Text value, Context context)                throws IOException, InterruptedException {            String line = value.toString();            StringTokenizer token = new StringTokenizer(line);            while (token.hasMoreTokens()) {                word.set(token.nextToken());                context.write(word, one);            }        }    }    public static class WordCountReduce extends            Reducer
      
        {        public void reduce(Text key, Iterable
       
         values,                           Context context) throws IOException, InterruptedException {            int sum = 0;            for (IntWritable val : values) {                sum += val.get();            }            context.write(key, new IntWritable(sum));        }    }    public static void main(String[] args) throws Exception {        Configuration conf = new Configuration();        Job job = new Job(conf);        job.setJarByClass(WordCount.class);        job.setJobName("wordcount");        job.setOutputKeyClass(Text.class);        job.setOutputValueClass(IntWritable.class);        job.setMapperClass(WordCountMap.class);        job.setReducerClass(WordCountReduce.class);        job.setInputFormatClass(TextInputFormat.class);        job.setOutputFormatClass(TextOutputFormat.class);        FileInputFormat.addInputPath(job, new Path(args[0]));        FileOutputFormat.setOutputPath(job, new Path(args[1]));        job.waitForCompletion(true);    }}
       
      
     

 4.在src同级目录下新建input目录,以及下面的test.segmented文件

test.segmented文件内容

aabbccddaacceeffffgghhaa

4.在run configuration下设置运行方式为Application

5.运行java文件,将会生成output目录,part-r-00000为运行的结果,下次运行必须删除output目录,否则会报错