SparkStraming版本的wordcount

package sparkstreamday01.SparkStream

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

object SparkStreamTest3 {

//设置日志级别为WARN

Logger.getLogger("org").setLevel(Level.WARN)

  def main(args: Array[String]): Unit = {
    //本地运行的设置
    val conf: SparkConf = new SparkConf()
      .setMaster("local[3]")//至少是两个cores(运行一个，接收一个)
      .setAppName(this.getClass.getSimpleName)
    //时间间隔需要根据我们的业务需要设置，不是随意设置的
    val ssc: StreamingContext = new StreamingContext(conf,Seconds(5))
    //从socket获取数据连接，创建一个将要连接到host:port的Dstream

   //从这里读取数据的Receiver 需要一个core
    val text: ReceiverInputDStream[String] = ssc.socketTextStream("Linux00",9999)
    //处理业务逻辑(wordcount)
    val ds: DStream[(String, Int)] = text.flatMap(_.split(" ")).map((_,1)).reduceByKey(_+_)
//默认打印十行   

 ds.print()
 //启动主程序，去连接socket 

  ssc.start()
  //阻塞 等待主程序被关闭

  ssc.awaitTermination()
  }
}