sparkstreaming transform筛选每批次前N位

sparkStreaming接受socket数据实现所有批次的单词次数累加

import org.apache.log4j.{Level, Logger}
import org.apache.spark.SparkConf
import org.apache.spark.rdd.RDD
import org.apache.spark.streaming.dstream.{DStream, ReceiverInputDStream}
import org.apache.spark.streaming.{Seconds, StreamingContext}

/**
  * 获取每一个批次中单词出现次数最多的前3位
  */
object transform {
  def main(args: Array[String]): Unit = {
    Logger.getLogger("org").setLevel(Level.ERROR)
    val sparkConf: SparkConf = new SparkConf().setAppName("MapWithStateWordCount").setMaster("local[2]")
    val ssc = new StreamingContext(sparkConf,Seconds(2))
    ssc.checkpoint("hdfs://node01:8020/ck")
    val socketTextStream: ReceiverInputDStream[String] = ssc.socketTextStream("node01",9999)
    val result: DStream[(String, Int)] = socketTextStream.flatMap(_.split(" ")).map((_,1)).reduceByKey(_+_)

    val sortedDstream: DStream[(String, Int)] = result.transform(rdd=>{
      val sortedRDD: RDD[(String, Int)] = rdd.sortBy(_._2,false)
      val top3: Array[(String, Int)] = sortedRDD.take(3)
      println("top3 start printing")
      top3.foreach(println)
      println("top3 print ended")
      sortedRDD
    })
    //打印该批次中所有单词按照次数降序的结果
    sortedDstream.print()
    //开启流式计算
    ssc.start()
    ssc.awaitTermination()
  }
}

输入

结果