Hadoop示例程序之单词统计MapReduce

在eclipse下新建一个map/reduce Project

1,新建文件MyMap.java

import java.io.IOException;  
 import java.util.StringTokenizer;  
   
import org.apache.hadoop.io.IntWritable;  
 import org.apache.hadoop.io.Text;  
 import org.apache.hadoop.mapreduce.Mapper;  
   
public class MyMap extends Mapper<Object, Text, Text, IntWritable> {  
     private final static IntWritable one = new IntWritable(1);  
   
    private Text word;  
   
    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 = new Text();  
             word.set(tokenizer.nextToken());  
             context.write(word, one);  
         }  
     }  
 }

2，新建文件MyReduce.java:2，新建文件MyReduce.java:

import java.io.IOException;  
   
import org.apache.hadoop.io.IntWritable;  
 import org.apache.hadoop.io.Text;  
 import org.apache.hadoop.mapreduce.Reducer;  
   
public class MyReduce extends  
         Reducer<Text, IntWritable, Text, IntWritable> {  
     public void reduce(Text key, Iterable<IntWritable> values, Context context)  
             throws IOException, InterruptedException {  
         int sum = 0;  
         for (IntWritable val : values) {  
             sum += val.get();  
         }  
         context.write(key, new IntWritable(sum));  
     }  
 }  

3，新建一个文件MyDriver.java3，新建一个文件MyDriver.java

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.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;  
   
public class MyDriver {  
   
      
     public static void main(String[] args) throws Exception,InterruptedException {  
         Configuration conf=new Configuration();  
           
        Job job=new Job(conf,"Hello Hadoop World");  
          
        job.setJarByClass(MyDriver.class);           
         
        job.setMapOutputKeyClass(Text.class);      
        job.setMapOutputValueClass(IntWritable.class);  
          
        job.setOutputKeyClass(Text.class);  
        job.setOutputValueClass(IntWritable.class);  
          
        job.setMapperClass(MyMap.class);  
         job.setCombinerClass(MyReduce.class);  
         job.setReducerClass(MyReduce.class);  
           
         job.setInputFormatClass(TextInputFormat.class);            
         job.setOutputFormatClass(TextOutputFormat.class);          
           
         FileInputFormat.setInputPaths(job, new Path("./input/555.txt"));  
           
         FileOutputFormat.setOutputPath(job, new Path("./input/out.txt"));  
 
       job.waitForCompletion(true);  
        }  
   
}