Spark2.x学习笔记：6、在Windows平台下搭建Spark开发环境（Intellij IDEA）

<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/maven-v4_0_0.xsd">
  <modelVersion>4.0.0</modelVersion>
  <groupId>cn.hadron</groupId>
  <artifactId>simpleSpark</artifactId>
  <packaging>jar</packaging>
  <version>1.0-SNAPSHOT</version>
  <properties>
    <spark.version>2.2.0</spark.version>
  </properties>

  <repositories>
    <repository>
      <id>nexus-aliyun</id>
      <name>Nexus aliyun</name>
      <url>http://maven.aliyun.com/nexus/content/groups/public</url>
    </repository>
  </repositories>

  <dependencies>
    <!-- https://mvnrepository.com/artifact/org.apache.spark/spark-core_2.10 -->
    <dependency>
      <groupId>org.apache.spark</groupId>
      <artifactId>spark-core_2.10</artifactId>
      <version>${spark.version}</version>
    </dependency>
  </dependencies>

  <build>
    <plugins>
      <plugin>
        <artifactId>maven-assembly-plugin</artifactId>
        <version>2.3</version>
        <configuration>
          <classifier>dist</classifier>
          <appendAssemblyId>true</appendAssemblyId>
          <descriptorRefs>
            <descriptor>jar-with-dependencies</descriptor>
          </descriptorRefs>
        </configuration>
        <executions>
          <execution>
            <id>make-assembly</id>
            <phase>package</phase>
            <goals>
              <goal>single</goal>
            </goals>
          </execution>
        </executions>
      </plugin>
    </plugins>
  </build>
</project>

package cn.hadron

import org.apache.spark._

object WordCount {
  def main(args: Array[String]) {
    var masterUrl = "local[1]"
    var inputPath = "D:\\data\\Hamlet.txt"
    var outputPath = "D:\\output"

    if (args.length == 1) {
      masterUrl = args(0)
    } else if (args.length == 3) {
      masterUrl = args(0)
      inputPath = args(1)
      outputPath = args(2)
    }

    println(s"masterUrl:${masterUrl}, inputPath: ${inputPath}, outputPath: ${outputPath}")

    val sparkConf = new SparkConf().setMaster(masterUrl).setAppName("WordCount")
    val sc = new SparkContext(sparkConf)

    val rowRdd = sc.textFile(inputPath)
    val resultRdd = rowRdd.flatMap(line => line.split("\\s+"))
        .map(word => (word, 1)).reduceByKey(_ + _)

    resultRdd.saveAsTextFile(outputPath)
  }
}