简单的wordcout的MapReduce学习实现

最新推荐文章于 2024-01-11 16:12:06 发布

原创最新推荐文章于 2024-01-11 16:12:06 发布 · 909 阅读

0 ·

CC 4.0 BY-SA版权

hadoop 专栏收录该内容

0 篇文章

订阅专栏

本文介绍了一个使用Hadoop实现的WordCount程序，该程序通过MapReduce框架处理文本文件，统计每个单词出现的次数。首先定义了Mapper类来读取输入文件并拆分单词，接着定义了Reducer类来聚合相同单词的计数。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

package com.hadoop.wordcount;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
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;

import com.hadoop.mapper.Mapper;
import com.hadoop.reducer.Reducer;


public class WordCount {
    public static void main(String[] args) throws IOException {
        //创建任务
        Job job=Job.getInstance(new Configuration());
        job.setJarByClass(WordCount.class);
        
        //Map
        job.setMapperClass(Mapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(LongWritable.class);
        FileInputFormat.setInputPaths(job, "/word.txt");
        job.setReducerClass(Reducer.class);
        //Reduce
        job.setReducerClass(Reducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);
        FileOutputFormat.setOutputPath(job, new Path("/wcount"));
        
    }
}

package com.hadoop.mapper;

import java.io.IOException;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;

public class Mapper extends org.apache.hadoop.mapreduce.Mapper<LongWritable, Text, Text, LongWritable>{

    @Override
    protected void map(LongWritable key, Text value,
            org.apache.hadoop.mapreduce.Mapper<LongWritable, Text, Text, LongWritable>.Context context)
            throws IOException, InterruptedException {
        String line=value.toString();
        String[] words=line.split(" ");
        for(String w:words){
            context.write(new Text(w), new LongWritable(1));
        }
    }
}

package com.hadoop.reducer;

import java.io.IOException;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;

public class Reducer extends org.apache.hadoop.mapreduce.Reducer<Text, LongWritable, Text, LongWritable>{

    @Override
    protected void reduce(Text key, Iterable<LongWritable> value,
            org.apache.hadoop.mapreduce.Reducer<Text, LongWritable, Text, LongWritable>.Context context)
            throws IOException, InterruptedException {
        long counter=0;
        for(LongWritable i:value){
            counter+=i.get();
        }
        context.write(key, new LongWritable(counter));
    }

}

将上述工程打成jar包，在hadoop上运行： hadoop -jar 相应的包既可得到wordcount计算结果