1、配置maven
注意:提交到spark集群中执行时是不需要spark-core和hadoop、scala的依赖包的,如果生要打进去也可以,但jar包太大,没有必要,只要在依赖处将范围限定一下即可:
<dependency>
<groupId>org.scala-lang</groupId>
<artifactId>scala-library</artifactId>
<version>${scala.version}</version>
<!--打包时不要加进去-->
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_2.12</artifactId>
<version>${spark.version}</version>
<!--打包时不要加进去-->
<scope>provided</scope>
</dependency>
<!--定义常量-->
<properties>
<maven.compiler.source>1.8</maven.compiler.source>
<maven.compiler.target>1.8</maven.compiler.target>
<scala.version>2.12.10</scala.version>
<spark.version>3.0.1</spark.version>
<hadoop.version>3.2.1</hadoop.version>
<encoding>UTF-8</encoding>
</properties>
<dependencies>
<dependency>
<groupId>org.scala-lang</groupId>
<artifactId>scala-library</artifactId>
<version>${scala.version}</version>
<!--打包时不要加进去-->