环境

maven 3.3.9
hadoop 2.6.5
jdk8

POM

一般都是本地开发，然后将jar包拷贝到hadoop服务器，执行hadoop jar这样的命令开始一个mapreduce作业的。原始的开发是将hadoop-2.6.5/share/hadoop/中的一些模块jar包拷到项目的classpath中，但是每次新建一个项目都这样拷贝太low了。直接使用Maven的形式就好啦。

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>com.infosys</groupId>
    <artifactId>hadoop-wordcount</artifactId>
    <version>1.0.0</version>

    <packaging>jar</packaging>

    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <hadoop.version>2.6.5</hadoop.version>
    </properties>

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

        <!-- Test -->
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.12</version>
            <scope>test</scope>
        </dependency>

        <dependency>
            <groupId>org.apache.mrunit</groupId>
            <artifactId>mrunit</artifactId>
            <version>1.1.0</version>
            <classifier>hadoop2</classifier>
            <scope>test</scope>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-minicluster</artifactId>
            <version>${hadoop.version}</version>
            <scope>test</scope>
        </dependency>
    </dependencies>


    <build>
        <finalName>example-wordcount</finalName>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.1</version>

                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                </configuration>
            </plugin>

            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-jar-plugin</artifactId>
                <version>2.5</version>
                <configuration>
                    <outputDirectory>${basedir}</outputDirectory>
                </configuration>
            </plugin>
        </plugins>
    </build>
</project>