GitHub
https://github.com/SmallScorpion/flink-tutorial.git
側輸出流(SideOutput)
大部分的DataStream API的算子的輸出是單一輸出,也就是某種數據類型的流。除了split算子,可以將一條流分成多條流,這些流的數據類型也都相同。process function的side outputs功能可以產生多條流,並且這些流的數據類型可以不一樣。一個side output可以定義爲OutputTag[X]對象,X是輸出流的數據類型。process function可以通過Context對象發射一個事件到一個或者多個side outputs。
測試
import com.atguigu.bean.SensorReading
import org.apache.flink.streaming.api.functions.ProcessFunction
import org.apache.flink.streaming.api.scala._
import org.apache.flink.util.Collector
/**
* 用側輸出流實現一個分流操作
*/
object SideOutputTest {
def main(args: Array[String]): Unit = {
val env = StreamExecutionEnvironment.getExecutionEnvironment
env.setParallelism(1)
val inputDStream: DataStream[String] = env.socketTextStream("hadoop102", 7777)
val dataDstream: DataStream[SensorReading] = inputDStream.map(
data => {
val dataArray: Array[String] = data.split(",")
SensorReading(dataArray(0), dataArray(1).toLong, dataArray(2).toDouble)
})
val resultDStrem: DataStream[SensorReading] = dataDstream
.process( SideOutputTest(30.0) )
dataDstream.print("data")
// 主流爲高於30.0度
resultDStrem.print( "high" )
// 側輸出流需要進行獲取
resultDStrem.getSideOutput( new OutputTag[SensorReading]("low-temp") ).print("low")
env.execute("SideOutput test job")
}
}
/**
* 自定義一個方法,判斷溫度是否大於30度,小於30度輸出到測輸出流,大於30主流
* @param tpr
*/
case class SideOutputTest(tpr: Double) extends ProcessFunction[SensorReading, SensorReading]{
override def processElement(value: SensorReading, ctx: ProcessFunction[SensorReading, SensorReading]#Context, out: Collector[SensorReading]): Unit = {
if( value.temperature >= tpr ){
out.collect( value )
}else{
ctx.output( new OutputTag[SensorReading]("low-temp"), value)
}
}
}