WordCount案例实操

一、需求

1. 在给定的文本文件中统计输出每一个单词出现的总次数
2. 输入数据：hello.txt文本文件
3. 期望输出：
   

atguigu 2
banzhang 1
cls 2
hadoop 1
jiao 1
ss 2
xue 1

二、需求分析

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

三、准备

(1) 创建maven工程

(2) 在pom.xml中添加依赖

xml
<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>

(3) 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。

properties
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

(4) 创建包名 com.example.mapreduce.wordcount

四、编写程序

1.编写mapper类

java
package org.example.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;

public class WordCountMapper extends Mapper<LongWritable, Text,Text, IntWritable> {
    private Text outKey = new Text();
    private IntWritable outValue = new IntWritable(1);

    @Override
    protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, IntWritable>.Context context) throws IOException, InterruptedException {
        //1.读取每一行
        String line = value.toString();

        //2.分割出单词
        String[] words = line.split(" ");

        //3.生成key

        for (String word : words) {
            outKey.set(word);
            //4.写入context
            context.write(outKey, outValue);
        }


    }
}

2.编写Reducer类

java
package org.example.mapreduce.wordcount;

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

        context.write(key,outValue);
    }
}

3.编写Driver类

java
package org.example.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.FileInputStream;
import java.io.IOException;

public class WordCountDriver {
    public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
        //1.获取Job对象连接
        Configuration config = new Configuration();
        Job job = Job.getInstance(config);

        //2.设置jar包路径
        job.setJarByClass(WordCountDriver.class);

        //3.关联mapper和reducer
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);

        //4.设置mapper输出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.输入输出路径
        FileInputFormat.setInputPaths(job, new Path("E:\\zhuanye\\大数据相关文件\\hadoop\\资料\\11_input\\inputword"));
        FileOutputFormat.setOutputPath(job, new Path("E:\\zhuanye\\大数据相关文件\\hadoop\\资料\\11_input\\outputwordcount\\output1"));

        //7.提交job

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