春城无处不飞花，小白带你侃SparkStreaming(实战应用篇)

object Streaming01 {
  def main(args: Array[String]): Unit = {

    // 1. 创建SC
    val conf: SparkConf = new SparkConf().setMaster("local[*]").setAppName("wc")
    val sc: SparkContext = new SparkContext(conf)
    // 设置日志级别
    sc.setLogLevel("WARN")

    // 2. 创建sc 指定【每个批次的时间】
    val ssc: StreamingContext = new StreamingContext(sc,Seconds(5))

    // 3. 接收数据，并处理
    val socketDatas: ReceiverInputDStream[String] = ssc.socketTextStream("node01",9999)

    val WCS: DStream[(String, Int)] = socketDatas.flatMap(a=>a.split(" ")).map(a=>(a,1)).reduceByKey(_+_)

    // 遍历每个RDD
    WCS.foreachRDD(RDD=>RDD.foreach(println))

    // 4. 开始streaming
    ssc.start()

    // 5. 等待关闭
    ssc.awaitTermination()
  }
}

object WordCount2 {
  def main(args: Array[String]): Unit = {
    //1.创建StreamingContext
    //spark.master should be set as local[n], n > 1
    val conf = new SparkConf().setAppName("wc").setMaster("local[*]")
    val sc = new SparkContext(conf)
    //设置日志级别
    sc.setLogLevel("WARN")
    val ssc = new StreamingContext(sc,Seconds(5))//5表示5秒中对数据进行切分形成一个RDD
    //requirement failed: ....Please set it by StreamingContext.checkpoint().
    //注意:我们在下面使用到了updateStateByKey对当前数据和历史数据进行累加
    //那么历史数据存在哪?我们需要给他设置一个checkpoint目录
    ssc.checkpoint("./wc")   //开发中这里需要设置成HDFS
    //2.监听Socket接收数据
    //ReceiverInputDStream就是接收到的所有的数据组成的RDD,封装成了DStream,接下来对DStream进行操作就是对RDD进行操作
    val dataDStream: ReceiverInputDStream[String] = ssc.socketTextStream("node01",9999)
    //3.操作数据
    val wordDStream: DStream[String] = dataDStream.flatMap(_.split(" "))
    val wordAndOneDStream: DStream[(String, Int)] = wordDStream.map((_,1))
    //val wordAndCount: DStream[(String, Int)] = wordAndOneDStream.reduceByKey(_+_)
    //====================使用updateStateByKey对当前数据和历史数据进行累加====================
    val wordAndCount: DStream[(String, Int)] =wordAndOneDStream.updateStateByKey(updateFunc)
    wordAndCount.print()
    ssc.start()//开启
    ssc.awaitTermination()//等待优雅停止

  }
  //currentValues:当前批次的value值,如:1,1,1 (以测试数据中的hadoop为例)
  //historyValue:之前累计的历史值,第一次没有值是0,第二次是3
  //目标是把当前数据+历史数据返回作为新的结果(下次的历史数据)
  def updateFunc(currentValues:Seq[Int], historyValue:Option[Int] ):Option[Int] ={
// currentValues当前值
// historyValue历史值
    val result: Int = currentValues.sum + historyValue.getOrElse(0)
    Some(result)
  }
}

import org.apache.spark.streaming.dstream.{DStream, ReceiverInputDStream}
import org.apache.spark.streaming.{Seconds, StreamingContext}
import org.apache.spark.{SparkConf, SparkContext}

object WordCount3 {
  def main(args: Array[String]): Unit = {
    //1.创建StreamingContext
    //spark.master should be set as local[n], n > 1
    val conf = new SparkConf().setAppName("wc").setMaster("local[*]")
    val sc = new SparkContext(conf)
    sc.setLogLevel("WARN")
    val ssc = new StreamingContext(sc,Seconds(5))//5表示5秒中对数据进行切分形成一个RDD
    //2.监听Socket接收数据
    //ReceiverInputDStream就是接收到的所有的数据组成的RDD,封装成了DStream,接下来对DStream进行操作就是对RDD进行操作
    val dataDStream: ReceiverInputDStream[String] = ssc.socketTextStream("node01",9999)
    //3.操作数据
    val wordDStream: DStream[String] = dataDStream.flatMap(_.split(" "))
    val wordAndOneDStream: DStream[(String, Int)] = wordDStream.map((_,1))

    val wordAndCount: DStream[(String, Int)] = wordAndOneDStream.reduceByKeyAndWindow((a:Int,b:Int)=>a+b,Seconds(10),Seconds(5))
   //4.使用窗口函数进行WordCount计数
    //reduceFunc: (V, V) => V,集合函数
    //windowDuration: Duration,窗口长度/宽度
    //slideDuration: Duration,窗口滑动间隔
    //注意:windowDuration和slideDuration必须是batchDuration的倍数
    //windowDuration=slideDuration:数据不会丢失也不会重复计算==开发中会使用
    //windowDuration>slideDuration:数据会重复计算==开发中会使用
    //windowDuration<slideDuration:数据会丢失
    //代码表示:
    //windowDuration=10
    //slideDuration=5
    //那么执行结果就是每隔5s计算最近10s的数据

    wordAndCount.print()
    ssc.start()//开启
    ssc.awaitTermination()//等待优雅停止
  }
}