第一個Spark程序之Spark本地程序

程序和源數據均爲本地

源數據和程序代碼

{"name":"Michael"}
{"name":"Andy", "age":30}
{"name":"Justin", "age":19}

import org.apache.spark.sql.SQLContext
import org.apache.spark.{SparkConf, SparkContext}

object SQLContextApp {

  def main(args: Array[String]){

    val path = args(0)
    val sparkConf = new SparkConf()
    //此代碼在linu環境上由腳本命令指定
    sparkConf.setAppName("SQLContextApp").setMaster("local[2]")
    val sc = new SparkContext(sparkConf)
    val sqlcontext = new SQLContext(sc)

    val people = sqlcontext.read.format("json").load(path)

    people.printSchema()
    people.show()

    sc.stop()

  }
}

args在configuration中指定

運行結果