- 下载spark-2.2.2-bin-hadoop2.7,解压到目录
- 下载hadoop-2.7.7
- scala-2.11.8.msi下载安装,尽量自定义路径,避免类似于C:\Program Files存在路径包含空格的情况
- 下载jdk1.8+
- 配置环境变量
![在这里插入图片描述](https://i-blog.csdnimg.cn/blog_migrate/fe4d66a0aa853fdc651b4fba7958b33a.png)
- idea–settings—plugins找到scala插件下载安装
- 建立scala项目
- 添加maven框架支持
- 添加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.scalatest</groupId>
<artifactId>scalatest</artifactId>
<version>1.0-SNAPSHOT</version>
<properties>
<spark.version>2.2.2</spark.version>
<scala.version>2.11</scala.version>
</properties>
<dependencies>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_${scala.version}</artifactId>
<version>${spark.version}</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming_${scala.version}</artifactId>
<version>${spark.version}</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_${scala.version}</artifactId>
<version>${spark.version}</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-hive_${scala.version}</artifactId>
<version>${spark.version}</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-mllib_${scala.version}</artifactId>
<version>${spark.version}</version>
</dependency>
</dependencies>
<build>
<plugins>
<plugin>
<groupId>org.scala-tools</groupId>
<artifactId>maven-scala-plugin</artifactId>
<version>2.15.2</version>
<executions>
<execution>
<goals>
<goal>compile</goal>
<goal>testCompile</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.6.0</version>
<configuration>
<source>1.8</source>
<target>1.8</target>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-surefire-plugin</artifactId>
<version>2.19</version>
<configuration>
<skip>true</skip>
</configuration>
</plugin>
</plugins>
</build>
</project>
- 新建scala类
package myscala
import org.apache.spark.SparkContext
import org.apache.spark.SparkContext._
import org.apache.spark.SparkConf
object wordCount {
def main(args: Array[String]) {
val inputFile = "D:\\mysqld.log"
val conf = new SparkConf().setAppName("WordCount").setMaster("local")
val sc = new SparkContext(conf)
val textFile = sc.textFile(inputFile)
val wordCount = textFile.flatMap(line => line.split(" ")).map(word => (word, 1)).reduceByKey((a, b) => a + b)
wordCount.foreach(println)
}
}