1、创建一个maven工程

2、POM文件

<?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.sogou</groupId>
    <artifactId>teemo-dc-etl</artifactId>
    <version>1.0.0</version>
    <packaging>jar</packaging>

    <name>teemo-dc-etl</name>
    <url>http://maven.apache.org</url>

    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <mahout.version>0.5</mahout.version>
        <mahout.groupid>org.apache.mahout</mahout.groupid>
        <spring.version>3.0.6.RELEASE</spring.version>
    </properties>

    <repositories>
    <repository>
        <id>maven-ali</id>
        <url>http://maven.twttr.com/</url>
        <releases>
            <enabled>true</enabled>
        </releases>
        <snapshots>
            <enabled>true</enabled>
            <updatePolicy>always</updatePolicy>
            <checksumPolicy>fail</checksumPolicy>
        </snapshots>
    </repository>
    </repositories>

    <dependencies>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>3.8.1</version>
            <scope>test</scope>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.5.0</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.5.1</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.5.0</version>
        </dependency>

        <dependency>
            <groupId>com.hadoop.gplcompression</groupId>
            <artifactId>hadoop-lzo</artifactId>
            <version>0.4.19</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-yarn-common</artifactId>
            <version>2.5.2</version>
        </dependency>

        <dependency>
            <groupId>com.alibaba</groupId>
            <artifactId>fastjson</artifactId>
            <version>1.2.4</version>
        </dependency>

    </dependencies>


    <build>
        <plugins>
            <!--
            bind the maven-assembly-plugin to the package phase
            this will create a jar file without the storm dependencies
            suitable for deployment to a cluster.
             -->
            <plugin>
                <artifactId>maven-assembly-plugin</artifactId>
                <configuration>
                    <archive>
                        <manifest>
                            <mainClass></mainClass>
                        </manifest>
                    </archive>
                    <descriptorRefs>
                        <descriptorRef>jar-with-dependencies</descriptorRef>
                    </descriptorRefs>
                &