eclipse 编写mapreduce程序(wordCount)

package com.hadoop.senior.mapreduce;

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.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.output.FileOutputFormat;

public class wordCount {

	//step 1: Map class 
	public static class WordCountMapper extends
			Mapper<LongWritable,Text,Text,IntWritable>{
		
		private Text mapOutputkey = new Text();
		private final static IntWritable mapOutputvalue= new IntWritable(1);
		
		
		@Override
		public void map(LongWritable key, Text value, Context context)
				throws IOException, InterruptedException {
			//line value
			String lineValue= value.toString();
			
			//split 
			//String[] strs =lineValue.split(" ");
			StringTokenizer stringTokenizer= new StringTokenizer(lineValue);
			
			//Iterator
			while(stringTokenizer.hasMoreTokens()){
				//get wordvalue
				String wordValue=stringTokenizer.nextToken();
				//set value
				mapOutputkey.set(wordValue);
				context.write(mapOutputkey,mapOutputvalue);
			}
		}	
	}
	
	//step 2: Reduce class
	public static class WordCountReducer extends 
			Reducer<Text,IntWritable,Text,IntWritable>{
		
		private IntWritable outputValue = new IntWritable();
		
		@Override
		public void reduce(Text key, Iterable<IntWritable> values,Context context)
				throws IOException, InterruptedException {
			//sum tmp
			int sum =0;
			for(IntWritable value:values){
				sum+=value.get();
			}
			//set value
			outputValue.set(sum);
			//output
			context.write(key, outputValue);
		}
	}
	
	//step 3: Driver component job
	public  int run(String[] args) throws IOException, ClassNotFoundException, InterruptedException{
		//1 get Configuration
		Configuration configuration= new Configuration();
		//create job
		Job job = Job.getInstance(configuration, this.getClass().getSimpleName());
		
		//run jar
		job.setJarByClass(this.getClass());
		
		//3 set Job
		//input	->map 	->reduce	->output
		//3.1 input 
		Path inpath = new Path(args[1]);
		FileInputFormat.addInputPath(job, inpath);
		//3.2 map
		job.setMapperClass(WordCountMapper.class);
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(IntWritable.class);
		//3.3 reduce
		job.setReducerClass(WordCountReducer.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(IntWritable.class);
		//3.4 output
		Path outPath = new Path(args[2]);
		FileOutputFormat.setOutputPath(job, outPath);
		//3.5 submit job
		boolean isSuccess =job.waitForCompletion(true);
		return isSuccess ? 0 : 1;
	}
	
	//run program
	public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
              //String[] args2 = new String[3];
              //String[0]="wordCount";//类名
        //args2[1]="/usr/css/mapreduce/wordcount/input";
        //args2[2]="/usr/css/mapreduce/wordcount/output3";
              int status= new wordCount().run(args);
		System.exit(status);
	}	
	
}


程序可以运行  本地/yarn
打包运行在yarn上运行
将程序打包参考链接:
http://jingyan.baidu.com/article/5bbb5a1b280d0113eba179ce.html
在hadoop上运行
1.jar包打包位置/opt/modules/hadoop-2.5.0-cdh5.3.6/jars(jar包命名example-stududy.jar)
2.运行这个wordCount程序要启动hadoop的集群
3.[root@VTU-01 hadoop-2.5.0-cdh5.3.6]# bin/yarn jar jars/example-stududy.jar wordCount /usr/css/mapreduce/wordcount/input /usr/css/mapreduce/wordcount/output

wordCount 是类的名字
/usr/css/mapreduce/wordcount/input 输入路径
/usr/css/mapreduce/wordcount/output 输出路径 不能存在
上述程序运行在yarn上,路径也是hdfs文件系统路径
/usr/css/mapreduce/wordcount/input 路径下要有写有单词的文件

阅读更多
想对作者说点什么? 我来说一句

没有更多推荐了,返回首页