Flink开发五步之第四步：Sink

一、用于测试的自定义SourceFunction

package com.fouth_sink
import org.apache.flink.streaming.api.functions.source.{RichSourceFunction, SourceFunction}
import scala.util.Random
/**
  * 自定义sourceFunction
  */
class CustomSourceFunction extends RichSourceFunction[(String, Long)]{
  var flag = true
  override def run(ctx: SourceFunction.SourceContext[(String, Long)]): Unit = {
    val arr: Array[String] = Array("a", "b", "c", "d", "e", "f", "g")
    val random: Random = new Random()
    while (flag) {
      Thread.sleep(100)
      // 随机取一个数组中的值
      val key: String = arr(random.nextInt(arr.length))
      val rightNow: Long = System.currentTimeMillis()
      ctx.collect((key, rightNow))
    }
  }
  override def cancel(): Unit = {
    flag = false
  }
}

二、Sink To Kafka

package com.fouth_sink
import org.apache.flink.api.common.serialization.SimpleStringSchema
import org.apache.flink.streaming.api.scala._
import org.apache.flink.streaming.connectors.kafka.FlinkKafkaProducer011
/**
  * 写入到Kafka
  */
object SinkToKafka {
  def main(args: Array[String]): Unit = {
    val env: StreamExecutionEnvironment = StreamExecutionEnvironment.getExecutionEnvironment
    val ds: DataStream[(String, Long)] = env.addSource(new CustomSourceFunction)
    val resultDS: DataStream[String] = ds.map(r => {
      r._1 + r._2
    })
    val flinkKafkaProduce: FlinkKafkaProducer011[String] = getKafkaProducer()
    resultDS.addSink(flinkKafkaProduce)
    env.execute()
  }
  /**
    * 获取FlinkKafkaProducer
    * @return
    */
  def getKafkaProducer(): FlinkKafkaProducer011[String] ={
    new FlinkKafkaProducer011[String]("master:9092","produce_test",new SimpleStringSchema())
  }
}