hadoop计算单词出现次数

WCJob.java

程序执行的入口，主要设置一些配置文件和指定map类和reduce类

package com.wang.wc;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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.output.FileOutputFormat;

public class WCJob {

	public static void main(String[] args) throws Exception {
		// TODO Auto-generated method stub
		//默认为src目录下的配置文件
		Configuration conf = new Configuration();
		//其他方法设置conf
//		conf.set("fs.defaultFS", "hdfs://namenode:9000");
//		conf.set("yarn.resourcemanager.hostname", "namenode");
		//该方法需要将项目打包成jar包，放入hadoop集群中执行
//		conf.set("mapred.jar","C:\\Users\\Adminstrator\\Desktop\\WorldCount.jar");
		
		Job job = Job.getInstance(conf);
		//在hadoop集群上运行这个作业时，要把代码打包成jar文件，
		//hadoop利用这个类来查找包含它的jar文件，进而找到相关的jar文件
		job.setJarByClass(WCJob.class);
		
		//指定map类型和reduce类型
		job.setMapperClass(WCMapper.class);
		job.setReducerClass(WCReducer.class);
		
		//setMapOutputKeyClass和setMapOutputValueClass控制map和reduce函数的输出类型
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(IntWritable.class);
		
		//使用FileInputFormat类制定输入数据和输出数据的文件地址
		FileInputFormat.addInputPath(job, new Path("/wc/input/wc"));
		Path outpath = new Path("/wc/output");
		
		FileSystem fs = FileSystem.get(conf);
		//-----
		if(fs.exists(outpath)){
			fs.delete(outpath, true);
		}
		
		
		FileOutputFormat.setOutputPath(job, outpath);
		
		boolean flag = job.waitForCompletion(true);
		if(flag){
			System.out.println("success!");
		}
	}
}

该类指定map方法
WCMapper.java

map类是一个泛型类型，有四个形参类型，分别指定map函数的输入key类型，输入value类型，输出key类型，输出value类型。

package com.wang.wc;

import java.io.IOException;

import org.apache.commons.lang.StringUtils;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
//LongWritable相当于java的Long类型，Text相当于java中的String类型，这些类都在org.apache.hadoop.io包中
public class WCMapper extends Mapper<LongWritable, Text, Text, IntWritable>{
	@Override
	protected void map(LongWritable key,Text value,Context context) throws IOException, InterruptedException{
               //将Text类型转换为String类型
                String str = value.toString();
		String[] strs = StringUtils.split(str,' ');
                Context实例用于输出内容的写入
               for(String s:strs){
			context.write(new Text(s), new IntWritable(1));
		}
	}
}

该类指定reduce方法

package com.wang.wc;

import java.io.IOException;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

public class WCReducer extends Reducer<Text, IntWritable, Text, IntWritable>{

	@Override
	protected void reduce(Text text, Iterable<IntWritable> iterable,
			Context context)
			throws IOException, InterruptedException {
		int sum = 0;
		for(IntWritable i :iterable){
			sum += i.get();
		}
		context.write(text, new IntWritable(sum));
	}
 
}