Hadoop示例WordCount代码编写

1）需求

在给定的文本文件中统计输出每一个单词出现的总次数

（1）输入数据

mischen mischen
ss ss
cls cls
jiao
banzhang
xue
hadoop
jiao 宋运辉  蒋介石
宋运辉

（2）期望输出数据

banzhang    1
cls    2
hadoop    1
jiao    2
mischen    2
ss    2
xue    1
宋运辉    2
蒋介石    1

2）需求分析

按照MapReduce编程规范，分别编写Mapper，Reducer，Driver。

3）环境准备

（1）创建maven工程，MapReduceDemo

（2）在pom.xml文件中添加如下依赖

 <dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>3.1.3</version>
        </dependency>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.12</version>
        </dependency>
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-log4j12</artifactId>
            <version>1.7.30</version>
        </dependency>
    </dependencies>

（2）在项目的src/main/resources目录下，新建一个文件，命名为“log4j.properties”，在文件中填入。

log4j.rootLogger=INFO, stdout  
log4j.appender.stdout=org.apache.log4j.ConsoleAppender  
log4j.appender.stdout.layout=org.apache.log4j.PatternLayout  
log4j.appender.stdout.layout.ConversionPattern=%d %p [%c] - %m%n  
log4j.appender.logfile=org.apache.log4j.FileAppender  
log4j.appender.logfile.File=target/spring.log  
log4j.appender.logfile.layout=org.apache.log4j.PatternLayout  
log4j.appender.logfile.layout.ConversionPattern=%d %p [%c] - %m%n

（3）创建包名：com.mischen.mapreduce.wordcount

4）编写程序

（1）编写Mapper类

package com.mischen.mapreduce.wordcount;

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;

/**
 * @ClassName WordCountMapper
 * @Description DOTO
 * @Author mischen
 * @Date 2021/5/5 0005 15:18
 * @Version 1.0
 **/
public class WordCountMapper  extends Mapper<LongWritable, Text, Text, IntWritable> {
    Text k = new Text();
    IntWritable v = new IntWritable(1);

    @Override
    protected void map(LongWritable key, Text value, Context context)	throws IOException, InterruptedException {

        // 1 获取一行
        String line = value.toString();

        // 2 切割
        String[] words = line.split(" ");

        // 3 输出
        for (String word : words) {
            k.set(word);
            context.write(k, v);
        }
    }
}

（2）编写Reducer类

package com.mischen.mapreduce.wordcount;

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

import java.io.IOException;

/**
 * @ClassName WordCountReducer
 * @Description DOTO
 * @Author mischen
 * @Date 2021/5/5 0005 15:21
 * @Version 1.0
 **/
public class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
    int sum;
    IntWritable v = new IntWritable();

    @Override
    protected void reduce(Text key, Iterable<IntWritable> values,Context context) throws IOException, InterruptedException {

        // 1 累加求和
        sum = 0;
        for (IntWritable count : values) {
            sum += count.get();
        }
        // 2 输出
        v.set(sum);
        context.write(key,v);
    }
}

（3）编写Driver驱动类

package com.mischen.mapreduce.wordcount;

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

import java.io.IOException;

/**
 * @ClassName WordCountDriver
 * @Description DOTO
 * @Author mischen
 * @Date 2021/5/5 0005 15:23
 * @Version 1.0
 **/
public class WordCountDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException{
        //System.out.println(System.getenv("HADOOP_USER_NAME"));
        System.out.println(System.getenv("HADOOP_HOME"));
        // 1 获取配置信息以及获取job对象
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        // 2 关联本Driver程序的jar
        job.setJarByClass(WordCountDriver.class);

        // 3 关联Mapper和Reducer的jar
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);

        // 4 设置Mapper输出的kv类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        // 5 设置最终输出kv类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        // 6 设置输入和输出路径
        FileInputFormat.setInputPaths(job, new Path("E:\\factory\\input\\inputword"));
        FileOutputFormat.setOutputPath(job, new Path("E:\\factory\\input\\output"));
        // 7 提交job
        boolean result = job.waitForCompletion(true);
        System.exit(result ? 0 : 1);
    }
}

5）本地测试

（1）需要首先配置好HADOOP_HOME变量以及Windows运行依赖

（2）在IDEA/Eclipse上运行程序