hadoop记录topk

标签：des   class   code   java   c   ext   

lk@lk-virtual-machine:~/hadoop-1.0.1/bin$

package top;

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

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 Top {
	public static class topMap extends Mapper<Text, Text,  IntWritable,Text>{  

		          

		         private TreeMap<Integer, String> topMap = new TreeMap<Integer,String>();  

		         private int topNum = 1;  

		         public void map(Text key,Text value,Context context){  

		             topMap.put(Integer.parseInt(value.toString()), key.toString());  

		    

		             while(topMap.size()>topNum)  

		                 topMap.remove(topMap.firstKey());  

		         }  

		            

		         protected void cleanup(Context context) throws IOException, InterruptedException{  

		             for(Integer entry:topMap.keySet()){  

		                 context.write(new IntWritable(entry),new Text(topMap.get(entry)));  

		             }  

		         }  

		     }  

		        

		     //瀹炵幇闄嶅簭  

		     private static class descendComparator implements Comparator{  

		    

		         @Override 

		         public int compare(Object o1, Object o2) {  

		             // TODO Auto-generated method stub  

		             Integer a=(Integer) o1;  

		             Integer b=(Integer) o2;  

		                

		             return -a.compareTo(b);  

		         }  

		            

		     }  

		     public static class topReduce extends Reducer<IntWritable,Text , IntWritable,Text>{  

		            

		         private TreeMap<Integer, String> topMap =new TreeMap<Integer,String>(new descendComparator());  

		         private int topNum = 1;  

		         public void reduce(IntWritable key,Iterable<Text> values,Context context){  

		                

		             for(Text text:values)  

		                 topMap.put(key.get(),text.toString());  

		             while(topMap.size()>topNum){  

		                 topMap.remove(topMap.firstKey());  

		             }  

		        

		         }  

		            

		         protected void cleanup(Context context) throws IOException, InterruptedException{  

		             for(Integer integer:topMap.keySet()){  

		                context.write(new IntWritable(integer),new Text(topMap.get(integer)));  

		             }  

		         }  

		     }  
		     
		     public static void main(String[]args)throws Exception
		 	{
		 		Configuration conf =new Configuration();
		 	
		 		Job job =new Job(conf,"Top");
		 		
		 		job.setJarByClass(topMap.class);
		 		job.setMapperClass(topMap.class);
		         job.setReducerClass(topReduce.class);
		 		
		 		job.setOutputKeyClass(IntWritable.class);
		 		job.setOutputValueClass(Text.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);
		 		
		 		
		 		
		 	}

		    



}

hadoop记录topk,布布扣,bubuko.com

hadoop记录topk

标签：des   class   code   java   c   ext   

原文地址：http://blog.csdn.net/huaweitman/article/details/25559181