大数据培训EvnetTimeWindow API之会话窗口

会话窗口（EventTimeSessionWindows）

相邻两次数据的EventTime的时间差超过指定的时间间隔就会触发执行。如果加入Watermark， 会在符合窗口触发的情况下进行延迟。到达延迟水位再进行窗口触发。

def main(args: Array[String]): Unit = { // 环境 val env: StreamExecutionEnvironment = StreamExecutionEnvironment.getExecutionEnvironment env.setStreamTimeCharacteristic(TimeCharacteristic.EventTime) env.setParallelism(1) val dstream: DataStream[String] = env.socketTextStream(“hadoop1”,7777) val textWithTsDstream: DataStream[(String, Long, Int)] = dstream.map { text => val arr: Array[String] = text.split(” “) (arr(0), arr(1).toLong, 1) } val textWithEventTimeDstream: DataStream[(String, Long, Int)] = textWithTsDstream.assignTimestampsAndWatermarks(new BoundedOutOfOrdernessTimestampExtractor[(String, Long, Int)](Time.milliseconds(1000)) { override def extractTimestamp(element: (String, Long, Int)): Long = { return element._2 } }) val textKeyStream: KeyedStream[(String, Long, Int), Tuple] = textWithEventTimeDstream.keyBy(0) textKeyStream.print(“textkey:”) val windowStream: WindowedStream[(String, Long, Int), Tuple, TimeWindow] = textKeyStream.window(EventTimeSessionWindows.withGap(Time.milliseconds(500)) ) windowStream.reduce((text1,text2)=> ( text1._1,0L,text1._3+text2._3) ) .map(_._3).print(“windows:::”).setParallelism(1) env.execute() }