完全解析Hadoop WordCount案例

需求：在一堆给定的文本文件中统计每个单词出现的次数

3.1 过程分析

1. 将文件上传到HDFS文件系统中
2. 使用InputFormat的子类TextInputFormat，一行一行的读取文本内容，生成(K1，V1)，K1为偏移量，V1为行内容
3. 自定义map逻辑，将(K1，V1)生成(K2，V2)，K2为单词，V2是1
4. 默认的shuffle阶段，包括分区、排序、规约、分组，生成新的(K2，V2)
5. 自定义Reduce逻辑，将新的(K2，V2)生成(K3，V3)，K3是单词，V3是该单词出现的次数
6. 使用OutputFormat的子类TextOutputFormat，一行一行的输出内容

3.2 pom.xml

<?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>E001WordCount</artifactId>
    <version>1.0-SNAPSHOT</version>

    <dependencies>
        <!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-common -->
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>3.3.5</version>
        </dependency>

        <!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-client -->
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>3.3.5</version>
        </dependency>

        <!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-hdfs -->
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>3.3.5</version>
            <scope>test</scope>
        </dependency>

        <!-- https://mvnrepository.com/artifact/commons-logging/commons-logging -->
        <dependency>
            <groupId>commons-logging</groupId>
            <artifactId>commons-logging</artifactId>
            <version>1.2</version>
        </dependency>

        <!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-common -->
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>3.3.5</version>
        </dependency>

    </dependencies>
    <build>
        <plugins>
            <plugin>
                <artifactId>maven-compiler-plugin</artifactId>