hadoop 学习：mapreduce 入门案例一：WordCount 统计一个文本中单词的个数

一 需求

这个案例的需求很简单

现在这里有一个文本wordcount.txt，内容如下

现要求你使用 mapreduce 框架统计每个单词的出现个数

这样一个案例虽然简单但可以让新学习大数据的同学熟悉 mapreduce 框架

二 准备工作

（1）创建一个 maven 工程，maven 工程框架可以选择quickstart

（2）在properties中添加 hadoop.version，导入依赖，pom.xml内容如下

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>org.example</groupId>
    <artifactId>maven_hadoop</artifactId>
    <version>1.0-SNAPSHOT</version>

    <dependencies>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.11</version>
            <scope>test</scope>
        </dependency>
        <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-mapreduce-client-core</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-common</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
    </dependencies>

    <properties>
        <maven.compiler.source>8</maven.compiler.source>
        <maven.compiler.target>8</maven.compiler.target>
        <hadoop.version>3.1.3</hadoop.version>
    </properties>

</project>

（3）准备数据，创建两个文件夹 in，out（一个是输入文件，一个是输出文件），输入文件放在 in 文件夹中

三 编写 WordCountMapper 类

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;

//                                              <0,       hello java, hello, 1       >
//                                              <0,       hello java, java, 1       >
//  alt + ins
public class WordCountMapper extends Mapper<LongWritable, Text,Text, IntWritable> {

    Text text = new Text();
    IntWritable intWritable =  new IntWritable();

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        System.out.println("WordCountMap stage Key:"+key+"  Value:"+value);
        String[] words = value.toString().split(" ");  // "hello java"--->[hello,java]
        for (String word :
                words) {
            text.set(word);
            intWritable.set(1);
            context.write(text,intWritable);   //<hello,1>,<java,1>
        }
    }
}

四 编写 WordCountReducer 类

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

import java.io.IOException;

public class WordCountReduce extends Reducer<Text, IntWritable, Text, LongWritable> {
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        System.out.println("Reduce stage Key:" + key + "  Values:" + values.toString());
        int count = 0;
        for (IntWritable intWritable :
                values) {
            count+=intWritable.get();
        }

        LongWritable longWritable = new LongWritable(count);
        System.out.println("ReduceResult key:"+key+" resultValue:"+longWritable.get());
        context.write(key,longWritable);
    }
}

五 编写WordCountDriver 类

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.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 java.io.IOException;

public class WordCountDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        job.setJarByClass(WordCountDriver.class);

        // 设置job的map阶段 工作任务
        job.setMapperClass(WordCountMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        // 设置job的reduce阶段 工作任务
        job.setReducerClass(WordCountReduce.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);

        // 指定job map阶段的输入文件的路径
        FileInputFormat.setInputPaths(job, new Path("D:\\bigdataworkspace\\kb23\\hadoopstu\\in\\wordcount.txt"));

        // 指定job reduce阶段的输出文件路径
        Path path = new Path("D:\\bigdataworkspace\\kb23\\hadoopstu\\out1");
        FileSystem fileSystem = FileSystem.get(path.toUri(), conf);
        if (fileSystem.exists(path))
            fileSystem.delete(path,true);
        FileOutputFormat.setOutputPath(job, path);

        // 启动job
        job.waitForCompletion(true);

    }
}