Spark Streaming基础学习【二】数值累加

package day05.d

import org.apache.spark.{HashPartitioner, SparkConf, SparkContext}
import org.apache.spark.streaming.{Seconds, StreamingContext}

object StateFulWordCount {
  
  //分好组的数据
  val updateFunc = (iter: Iterator[(String, Seq[Int], Option[Int])]) => {
    //iter.flatMap(it=>Some(it._2.sum + it._3.getOrElse(0)).map(x=>(it._1,x)))
    //iter.map{case(x,y,z)=>Some(y.sum + z.getOrElse(0)).map(m=>(x, m))}
    //iter.map(t => (t._1, t._2.sum + t._3.getOrElse(0)))
    iter.map{ case(word, current_count, history_count) => (word, current_count.sum + history_count.getOrElse(0)) }
  }
  def main(args: Array[String]): Unit = {
    LoggerLevels.setStreamingLogLevels()
    //StreamingContext
    val conf=new SparkConf().setAppName("StreamingWordCount").setMaster("local[2]")
    val sc=new SparkContext(conf)
    sc.setCheckpointDir("f://ss")
    val ssc=new StreamingContext(sc,Seconds(5))
    //接收数据
    val ds=ssc.socketTextStream("192.168.123.151",8888)
    //DStream是一个特殊的RDD
    val result=ds.flatMap(_.split(" ")).map((_,1)).updateStateByKey(updateFunc,new HashPartitioner(sc.defaultParallelism),true)
    result.print()
    ssc.start()
    //等待结束
    ssc.awaitTermination()
  }
}