Question

我用BroadcastProcessFunction实现了flink流。从processBroadcastElement中获取模型，并将其应用于processElement中的事件。

我没有找到对流进行单元测试的方法，因为我没有找到确保模型在第一个事件之前调度的解决方案。我想说有两种实现方法：
1.找到一种解决方案，以将模型先放入流中
2.使广播状态充满模型prio来执行流，以便将其恢复

我可能错过了一些东西，但是我没有找到一种简单的方法来完成此操作。

这是我的问题的简单单元测试：

import org.apache.flink.api.common.state.MapStateDescriptor
import org.apache.flink.streaming.api.functions.co.BroadcastProcessFunction
import org.apache.flink.streaming.api.functions.sink.SinkFunction
import org.apache.flink.streaming.api.scala._
import org.apache.flink.util.Collector
import org.scalatest.Matchers._
import org.scalatest.{BeforeAndAfter, FunSuite}

import scala.collection.mutable


class BroadCastProcessor extends BroadcastProcessFunction[Int, (Int, String), String] {

  import BroadCastProcessor._

  override def processElement(value: Int,
                              ctx: BroadcastProcessFunction[Int, (Int, String), String]#ReadOnlyContext,
                              out: Collector[String]): Unit = {
    val broadcastState = ctx.getBroadcastState(broadcastStateDescriptor)

    if (broadcastState.contains(value)) {
      out.collect(broadcastState.get(value))
    }
  }

  override def processBroadcastElement(value: (Int, String),
                                       ctx: BroadcastProcessFunction[Int, (Int, String), String]#Context,
                                       out: Collector[String]): Unit = {
    ctx.getBroadcastState(broadcastStateDescriptor).put(value._1, value._2)
  }
}

object BroadCastProcessor {
  val broadcastStateDescriptor: MapStateDescriptor[Int, String] = new MapStateDescriptor[Int, String]("int_to_string", classOf[Int], classOf[String])
}

class CollectSink extends SinkFunction[String] {

  import CollectSink._

  override def invoke(value: String): Unit = {
    values += value
  }
}

object CollectSink { // must be static
  val values: mutable.MutableList[String] = mutable.MutableList[String]()
}

class BroadCastProcessTest extends FunSuite with BeforeAndAfter {

  before {
    CollectSink.values.clear()
  }

  test("add_elem_to_broadcast_and_process_should_apply_broadcast_rule") {
    val env = StreamExecutionEnvironment.getExecutionEnvironment
    env.setParallelism(1)

    val dataToProcessStream = env.fromElements(1)

    val ruleToBroadcastStream = env.fromElements(1 -> "1", 2 -> "2", 3 -> "3")

    val broadcastStream = ruleToBroadcastStream.broadcast(BroadCastProcessor.broadcastStateDescriptor)

    dataToProcessStream
      .connect(broadcastStream)
      .process(new BroadCastProcessor)
      .addSink(new CollectSink())

    // execute
    env.execute()

    CollectSink.values should contain("1")
  }
}

感谢David Anderson的更新
我去了缓冲溶液。我为同步定义了一个过程函数：

class SynchronizeModelAndEvent(modelNumberToWaitFor: Int) extends CoProcessFunction[Int, (Int, String), Int] {
  val eventBuffer: mutable.MutableList[Int] = mutable.MutableList[Int]()
  var modelEventsNumber = 0

  override def processElement1(value: Int, ctx: CoProcessFunction[Int, (Int, String), Int]#Context, out: Collector[Int]): Unit = {
    if (modelEventsNumber < modelNumberToWaitFor) {
      eventBuffer += value
      return
    }
    out.collect(value)
  }

  override def processElement2(value: (Int, String), ctx: CoProcessFunction[Int, (Int, String), Int]#Context, out: Collector[Int]): Unit = {
    modelEventsNumber += 1

    if (modelEventsNumber >= modelNumberToWaitFor) {
      eventBuffer.foreach(event => out.collect(event))
    }
  }
}

所以我需要将其添加到我的流中：

dataToProcessStream
  .connect(ruleToBroadcastStream)
  .process(new SynchronizeModelAndEvent(3))
  .connect(broadcastStream)
  .process(new BroadCastProcessor)
  .addSink(new CollectSink())

谢谢

Answer 1

没有简单的方法可以做到这一点。您可以让processElement缓冲其所有输入，直到processBroadcastElement收到模型为止。或在没有事件流量的情况下运行一次作业，并在广播模型后获取保存点。然后将该保存点还原到同一作业中，但连接其事件输入。

顺便说一句，您正在寻找的功能在Flink社区中通常称为“辅助输入”。

当processElement依赖于广播的数据时，如何在flink中对BroadcastProcessFunction进行单元测试

1 个答案: