package cn.testdemo.dstream.socket
import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.streaming.{Seconds, StreamingContext}
import org.apache.spark.streaming.dstream.{DStream, ReceiverInputDStream}
//todo:利用sparkStreaming接受socket数据,实现所有批次数据单词出现次数的总和
//historyValue:表示之前所有批次中单词出现的总次数
def updateFunc(currentValues:Seq[Int], historyValue:Option[Int]):Option[Int] ={
val newValues: Int = currentValues.sum + historyValue.getOrElse(0)
Some(newValues)
}
def main(args: Array[String]): Unit = {
//1、创建sparkConf
val sparkConf: SparkConf = new SparkConf().setAppName("SparkStreamingSocketTotal").setMaster("local[2]")
//2、创建sparkContext
val sc = new SparkContext(sparkConf)
sc.setLogLevel("WARN")
//3、创建streamingContext
val ssc = new StreamingContext(sc,Seconds(5))
//设置checkpoint,用于保存中间结果数据
ssc.checkpoint("./ck2018")
//4、获取socket数据
val stream: ReceiverInputDStream[String] = ssc.socketTextStream("192.168.216.121",9999)
//5、操作数据流
val wordAndOne: DStream[(String, Int)] = stream.flatMap(_.split(" ")).map((_,1))
//6、相同单词出现的次数累加---updateStateByKey方法,它会记录下上一个批次key的结果
val result: DStream[(String, Int)] = wordAndOne.updateStateByKey(updateFunc)
//7、打印结果数据
result.print()
//8、开启计算
ssc.start()
ssc.awaitTermination()
}
}
import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.streaming.{Seconds, StreamingContext}
import org.apache.spark.streaming.dstream.{DStream, ReceiverInputDStream}
//todo:利用sparkStreaming接受socket数据,实现所有批次数据单词出现次数的总和
object SparkStreamingSocketTotal {
//currentValues:表示的是当前批次中相同单词出现所有的1 (hadoop,1)(hadoop,1)(hadoop,1)//historyValue:表示之前所有批次中单词出现的总次数
def updateFunc(currentValues:Seq[Int], historyValue:Option[Int]):Option[Int] ={
val newValues: Int = currentValues.sum + historyValue.getOrElse(0)
Some(newValues)
}
def main(args: Array[String]): Unit = {
//1、创建sparkConf
val sparkConf: SparkConf = new SparkConf().setAppName("SparkStreamingSocketTotal").setMaster("local[2]")
//2、创建sparkContext
val sc = new SparkContext(sparkConf)
sc.setLogLevel("WARN")
//3、创建streamingContext
val ssc = new StreamingContext(sc,Seconds(5))
//设置checkpoint,用于保存中间结果数据
ssc.checkpoint("./ck2018")
//4、获取socket数据
val stream: ReceiverInputDStream[String] = ssc.socketTextStream("192.168.216.121",9999)
//5、操作数据流
val wordAndOne: DStream[(String, Int)] = stream.flatMap(_.split(" ")).map((_,1))
//6、相同单词出现的次数累加---updateStateByKey方法,它会记录下上一个批次key的结果
val result: DStream[(String, Int)] = wordAndOne.updateStateByKey(updateFunc)
//7、打印结果数据
result.print()
//8、开启计算
ssc.start()
ssc.awaitTermination()
}
}