Flink自定義Source：SourceFunction、ParallelSourceFunction、RichParallelSourceFunction

我們這裏講這三類自定義Source
SourceFunction、ParallelSourceFunction、RichParallelSourceFunction
先定義一個Class類，分別集成上面三個接口，實現裏面方法

package com.ruozedata.flink

import org.apache.flink.streaming.api.functions.source.SourceFunction

//依次extends成SourceFunction、ParallelSourceFunction、RichParallelSourceFunction
class CustomerSource extends SourceFunction[Long]{

  var count=0L
  var isRunning=true
  override def run(ctx: SourceFunction.SourceContext[Long]): Unit = {
    while(isRunning) {
      ctx.collect(count)
      count += 1
      Thread.sleep(1000)
    }
  }

  override def cancel(): Unit = {

    isRunning=false
  }
}

調用、測試

package com.ruozedata.flink

import org.apache.flink.streaming.api.scala.StreamExecutionEnvironment
import org.apache.flink.api.scala._
import org.apache.flink.streaming.api.windowing.time.Time
object CustomerSourceStreamingApp {
    def main(args: Array[String]): Unit = {

      val env=StreamExecutionEnvironment.getExecutionEnvironment
	//通過前面依次exten不同的source
      val text=env.addSource(new CustomerSource).setParallelism(2) //2個併發

      val rusult=text.map(x=>{
        println("CustomerSourceStreamingApp接收到的數據時："+x)
        x
      }).timeWindowAll(Time.seconds(2))  //統計最近兩秒內的數據
          .sum(0)

      rusult.print()setParallelism(1) //表示並行度有2core


      env.execute("CustomerSourceApp")
    }

}