MapReduce WordCount程序

最新推荐文章于 2025-05-14 09:30:00 发布

原创最新推荐文章于 2025-05-14 09:30:00 发布 · 399 阅读

0 ·

CC 4.0 BY-SA版权

Hadoop 同时被 2 个专栏收录

6 篇文章

订阅专栏

Hadoop系列

4 篇文章

订阅专栏

本文介绍了一个基于Hadoop的WordCount程序实现过程，包括pom.xml配置、Mapper与Reducer类编写、作业提交及结果验证等步骤。

pom.xml

      <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-common</artifactId>
        <version>${hadoop.version}</version>
      </dependency>
      <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-hdfs</artifactId>
        <version>${hadoop.version}</version>
      </dependency>
      <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-client</artifactId>
        <version>${hadoop.version}</version>
      </dependency>

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

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

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

    @Override
    public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        StringTokenizer iter = new StringTokenizer(value.toString());
        while(iter.hasMoreElements()) {
            String word = iter.nextToken();
            context.write(new Text(word), new IntWritable(1));
        }
    }
}

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


import java.io.IOException;

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

    @Override
    public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        int sum = 0;
        for(IntWritable val : values) {
            sum += val.get();
        }
        context.write(key, new IntWritable(sum));
    }
}

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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.Job;


public class WordCount {

    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "word count");

        job.setJarByClass(WordCount.class);
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        FileInputFormat.addInputPath(job, new Path("/user/root/input"));
        FileOutputFormat.setOutputPath(job, new Path("/user/root/output"));

        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

使用Maven打jar包，上传至服务器/usr/local目录下

hadoop jar /usr/local/demo01-wordcount-1.0-SNAPSHOT.jar

运行结果如下，可在hdfs的/user/root/output目录下生成part-r-00000 文件，可下载下来查看运行结果