Flink window Function - ProcessWindowFunction

package window

import org.apache.flink.api.common.functions.AggregateFunction
import org.apache.flink.api.scala._
import org.apache.flink.streaming.api.functions.source.SourceFunction
import org.apache.flink.streaming.api.scala.StreamExecutionEnvironment
import org.apache.flink.streaming.api.scala.function.ProcessWindowFunction
import org.apache.flink.streaming.api.windowing.time.Time
import org.apache.flink.streaming.api.windowing.windows.TimeWindow
import org.apache.flink.util.Collector

/**
 * @author: create by maoxiangyi
 * @version: v1.0
 * @description: window
 * @date:2019 /6/4
 */
object ProcessWordCount {
 def main(args: Array[String]): Unit = {
  //设置环境
  val env: StreamExecutionEnvironment = StreamExecutionEnvironment.createLocalEnvironment()
  //设置数据源
  env.addSource(new SourceFunction[String] {
   override def run(ctx: SourceFunction.SourceContext[String]): Unit = {
    while (true) {
     ctx.collect("hello hadoop hello storm hello spark")
     Thread.sleep(1000)
    }
   }

   override def cancel(): Unit = {}
  })
   //计算逻辑
   .flatMap(_.split(" "))
   .map((_, 1))
   .keyBy(_._1)
   .timeWindow(Time.seconds(10), Time.seconds(10))

   .process(new ProcessWindowFunction[(String, Int), (String, Int), String, TimeWindow] {
    override def process(key: String, context: Context, elements: Iterable[(String, Int)], out: Collector[(String, Int)]): Unit = {
     var value = 0;
     elements.foreach(kv => {
      value = value + kv._2
     })
     out.collect(key, value)
    }
   })
   .print().setParallelism(1)
  env.execute("word count")
 }
}

转载于:https://www.cnblogs.com/maoxiangyi/p/10977967.html