win10中spark开发环境搭建

win10中spark开发环境搭建

• hadoop安装
• spark安装
• 安装scala
• 安装idea-scala插件

• 配置项目

  配置文件
  
  读取文件

package com.hikvision.spark

import org.apache.spark.rdd.RDD
import org.apache.spark.{SparkConf, SparkContext}

object Test {
    def main(args: Array[String]): Unit = {
        val sparkConf: SparkConf = new SparkConf().setAppName("name").setMaster("local")
        val sc: SparkContext = new SparkContext(sparkConf)
        val file: RDD[String] = sc.textFile("d://a.txt")
        for (x <- file) {
            println(x)
        }
    }
}

maven配置

<?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.hikvision.sparkTry</groupId>
    <artifactId>sparkTry</artifactId>
    <version>1.0-SNAPSHOT</version>
    <dependencies>
        <!-- https://mvnrepository.com/artifact/org.apache.spark/spark-core -->
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.11</artifactId>
            <version>2.3.1</version>
        </dependency>
        <!-- https://mvnrepository.com/artifact/org.apache.spark/spark-streaming -->
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming_2.11</artifactId>
            <version>2.3.1</version>
            <scope>provided</scope>
        </dependency>
        <!-- https://mvnrepository.com/artifact/org.apache.spark/spark-sql -->
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_2.11</artifactId>
            <version>2.3.1</version>
        </dependency>
        <!-- https://mvnrepository.com/artifact/org.apache.spark/spark-mllib -->
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-mllib_2.11</artifactId>
            <version>2.3.1</version>
            <scope>runtime</scope>
        </dependency>
        <!-- https://mvnrepository.com/artifact/com.sparkjava/spark-core -->
        <dependency>
            <groupId>com.sparkjava</groupId>
            <artifactId>spark-core</artifactId>
            <version>2.7.2</version>
        </dependency>
        <!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-common -->
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.7.6</version>
        </dependency>
        <!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-hdfs -->
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.7.6</version>
        </dependency>
        <!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-yarn-common -->
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-yarn-common</artifactId>
            <version>2.7.6</version>
        </dependency>
        <!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-yarn-api -->
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-yarn-api</artifactId>
            <version>2.7.6</version>
        </dependency>
        <!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-client -->
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.7.6</version>
        </dependency>

    </dependencies>
</project>