- 新建项目选择Gradle项目
- build.gradle
group 'org.fashj'
version '1.2'
apply plugin: 'idea'
apply plugin: 'scala'
sourceCompatibility = 1.8
repositories {
maven {
url 'http://maven.aliyun.com/nexus/content/groups/public/'
}
mavenCentral()
}
dependencies {
testCompile group: 'junit', name: 'junit', version: '4.11'
compile group: 'org.scala-lang', name: 'scala-library', version: '2.10.4'
testCompile "org.scala-lang:scala-library:2.11.8"
compile group: 'org.apache.spark', name: 'spark-core_2.10', version: '2.0.1'
}
3.编写代码
package org.fashj.spark
import org.apache.spark.{SparkConf, SparkContext}
/**
- @author zhengsd
*/
object SparkPi {
def main(args: Array[String]) {
val conf = new SparkConf()
val sc = new SparkContext(conf)
val text = sc.textFile("file:///usr/local/spark/README.md")
val result = text.flatMap(_.split(' ')).map((_, 1)).reduceByKey(_ + _).collect()
result.foreach(println)
}
}
- 生成Jar
- 在linux服务器上运行
./spark-submit --class "org.fashj.spark.SparkPi" /home/hadoop/spark-simple-1.2.jar