package bdqn.sparkdemp.day0309

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

object WordCount extends App {
  if (args.length != 3) {
    println("需要三个参数：1、spark的集群地址，2、要读取的文件地址，3、数据存储地址")
    sys.exit(1)
  }
  val conf = new SparkConf()
    .setMaster(args(0))
    .setAppName(WordCount.getClass.getSimpleName)
  val sc = new SparkContext(conf)
  val rdd: RDD[String] = sc.textFile(args(1))

  rdd.flatMap(_.split(" ")).map((_, 1)).reduceByKey(_ + _).saveAsTextFile(args(2))

  sc.stop()
}