spark实例9:Spark Streaming小例子

在服务端安装nc

yum install nmap-ncat.x86_64

并启动

nc -lk 9999

 

客户端代码如下:

import java.io.{BufferedReader, InputStreamReader}
import java.net.Socket
import java.nio.charset.StandardCharsets

import org.apache.spark.SparkConf
import org.apache.spark.internal.Logging
import org.apache.spark.storage.StorageLevel
import org.apache.spark.streaming.{Seconds, StreamingContext}
import org.apache.spark.streaming.receiver.Receiver

/**
 * Custom Receiver that receives data over a socket. Received bytes are interpreted as
 * text and \n delimited lines are considered as records. They are then counted and printed.
 *
 * To run this on your local machine, you need to first run a Netcat server
 *    `$ nc -lk 9999`
 * and then run the example
 *    `$ bin/run-example org.apache.spark.examples.streaming.CustomReceiver localhost 9999`
 */
object CustomReceiver {
  def main(args: Array[String]) {
    if (args.length < 2) {
      System.err.println("Usage: CustomReceiver <hostname> <port>")
      System.exit(1)
    }

    StreamingExamples.setStreamingLogLevels()

    // Create the context with a 1 second batch size
    val sparkConf = new SparkConf().setAppName("CustomReceiver").setMaster("local[*]")
    val ssc = new StreamingContext(sparkConf, Seconds(1))

    // Create an input stream with the custom receiver on target ip:port and count the
    // words in input stream of \n delimited text (eg. generated by 'nc')
    val lines = ssc.receiverStream(new CustomReceiver(args(0), args(1).toInt))
    val words = lines.flatMap(_.split(" "))
    val wordCounts = words.map(x => (x, 1)).reduceByKey(_ + _)
    wordCounts.print()
    ssc.start()
    ssc.awaitTermination()
  }
}


class CustomReceiver(host: String, port: Int)
  extends Receiver[String](StorageLevel.MEMORY_AND_DISK_2) with Logging {

  def onStart() {
    // Start the thread that receives data over a connection
    new Thread("Socket Receiver") {
      override def run() { receive() }
    }.start()
  }

  def onStop() {
   // There is nothing much to do as the thread calling receive()
   // is designed to stop by itself isStopped() returns false
  }

  /** Create a socket connection and receive data until receiver is stopped */
  private def receive() {
   var socket: Socket = null
   var userInput: String = null
   try {
     logInfo(s"Connecting to $host : $port")
     socket = new Socket(host, port)
     logInfo(s"Connected to $host : $port")
     val reader = new BufferedReader(
       new InputStreamReader(socket.getInputStream(), StandardCharsets.UTF_8))
     userInput = reader.readLine()
     while(!isStopped && userInput != null) {
       store(userInput)
       userInput = reader.readLine()
     }
     reader.close()
     socket.close()
     logInfo("Stopped receiving")
     restart("Trying to connect again")
   } catch {
     case e: java.net.ConnectException =>
       restart(s"Error connecting to $host : $port", e)
     case t: Throwable =>
       restart("Error receiving data", t)
   }
  }
}

关注公众号“大模型全栈程序员”回复“小程序”获取1000个小程序打包源码。更多免费资源在http://www.gitweixin.com/?p=2627

发表评论

邮箱地址不会被公开。 必填项已用*标注