MapReducer实现单词计算

最新推荐文章于 2024-04-30 07:30:00 发布

原创最新推荐文章于 2024-04-30 07:30:00 发布 · 581 阅读

0 ·

CC 4.0 BY-SA版权

hadoop 专栏收录该内容

9 篇文章

订阅专栏

本文介绍了一个基于Hadoop的WordCount实现案例，包括Mapper、Reducer及JobRunner的编写过程。通过对文本文件进行分词计数，展示了MapReduce编程模型的具体应用。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

package com.zjs.mr;


import java.io.IOException;
import java.util.StringTokenizer;


import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;


public class WordCountMap extends Mapper<LongWritable, Text, Text, IntWritable>{


	Text outKey = new Text(); //设置变量存储每次分隔出的单词
	IntWritable num =  new IntWritable();
	
	@Override
	protected void map(LongWritable key, Text value,
			Context context)
			throws IOException, InterruptedException {
		
		//取得一行记录
		String line = value.toString();
		//从一行中获取每个单词
		StringTokenizer st = new StringTokenizer(line);
		//循环遍历取出每个单词，并设置出现一次
		while(st.hasMoreTokens()){
			String word  = st.nextToken();
			outKey.set(word);
			num.set(1);//只要单词出现一次就设置1，然后交给reducer叠加
			context.write(outKey, num);//以单词位key值
		}
		
	}
	
	


}

package com.zjs.mr;

import java.io.IOException;

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

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

	@Override
	protected void reduce(Text key, Iterable<IntWritable> iter,
			Context context)
			throws IOException, InterruptedException {
		int sum = 0 ;//用来叠加每个单词出现的次数
		for(IntWritable i : iter){
			sum = sum + i.get();
		}
		context.write(key, new IntWritable(sum));
	}

	
}

package com.zjs.mr;

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 JobRun {
	
	public boolean run() throws Exception{
		Configuration config = new Configuration();
		config.set("fs.defaultFS", "hdfs://node6:8020");
		config.set("yarn.resourcemanager.hostname", "node7");
		
		//取得文件系统
		FileSystem fs = FileSystem.get(config);
		Job job = Job.getInstance(config);
		//设置任务调度类
		job.setJarByClass(JobRun.class);
		//设置mapper
		job.setMapperClass(WordCountMap.class);
		job.setReducerClass(WordCountReducer.class);
		
		//执行Combiner程序
		job.setCombinerClass(WordCountReducer.class);
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(IntWritable.class);
		
		//指定MR的输入数据（文件）
		FileInputFormat.addInputPath(job, new Path("/usr/input/wc/test"));
		//指定MR输出数据目录，该目录不能存在，MR在启动之处要检查该目录是否存在，如果存在报错。
		
		Path outpath =new Path("/usr/output/wc");
		if(fs.exists(outpath)){
			fs.delete(outpath, true);
		}
		FileOutputFormat.setOutputPath(job, outpath);
		//执行该任务（MR），并等待MR完成
		return job.waitForCompletion(true);
	}

	public static void main(String[] args) {
		JobRun jr =new JobRun();
		try {
			System.out.println(jr.run() ?"执行成功":"执行失败");
		} catch (Exception e) {
			e.printStackTrace();
		}
	}

}