package com.shujia.spark.streaming

import org.apache.spark.SparkContext
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.SparkSession
import org.apache.spark.streaming.{Durations, StreamingContext}
import org.apache.spark.streaming.dstream.{DStream, ReceiverInputDStream}

object Demo3RDDToDS {
  def main(args: Array[String]): Unit = {
    val spark: SparkSession = SparkSession.builder()
      .appName("streaming")
      .master("local[2]")
      .config("spark.sql.shuffle.partitions", 1)
      .getOrCreate()

    import spark.implicits._
    import org.apache.spark.sql.functions._

    val sc: SparkContext = spark.sparkContext

    /**
      * 创建streaming 上下文对象，指定batch的间隔时间,多久计算一次
      *
      */
    val ssc = new StreamingContext(sc, Durations.seconds(5))

    val linesDS: ReceiverInputDStream[String] = ssc.socketTextStream("master", 8888)

    /**
      * transform: 将ds 转换成rdd ，将将rdd转换成ds
      *
      */
    val ds1: DStream[(String, Int)] =linesDS.transform(rdd => {
      val resultRDD: RDD[(String, Int)] = rdd.flatMap(_.split(","))
        .map((_, 1))
        .reduceByKey(_ + _)

      //返回一个新的RDD
      resultRDD

    })
    ds1.print()


    //启动spark streaming
    ssc.start()
    ssc.awaitTermination()
    ssc.stop()


  }
}