Flink_继承TableAggregateFunction实现topN

Flink中的UDF,UDAF,UDTF,以及多进多出
基于TableAPI sql暂时用Rank就可以
package com.atguigu.sqlfunction

import com.atguigu.sourceandsink.SensorReading
import org.apache.flink.streaming.api.TimeCharacteristic
import org.apache.flink.streaming.api.functions.timestamps.BoundedOutOfOrdernessTimestampExtractor
import org.apache.flink.streaming.api.scala._
import org.apache.flink.streaming.api.windowing.time.Time
import org.apache.flink.table.api.Table
import org.apache.flink.table.api.scala._
import org.apache.flink.table.functions.{AggregateFunction, ScalarFunction, TableAggregateFunction, TableFunction}
import org.apache.flink.types.Row
import org.apache.flink.util.Collector

object TableAggregateFunctionTest {
def main(args: Array[String]): Unit = {
val streamEnv: StreamExecutionEnvironment = StreamExecutionEnvironment.getExecutionEnvironment
streamEnv.setStreamTimeCharacteristic(TimeCharacteristic.EventTime)
val tableEnv: StreamTableEnvironment = StreamTableEnvironment.create(streamEnv)//默认blinkplanner
//读取数据
val inputStream: DataStream[String] = streamEnv.readTextFile(“in/sensor.txt”)
val dataStream: DataStream[SensorReading] = inputStream.map(data => {
val strings: Array[String] = data.split(",")
SensorReading(strings(0), strings(1).toLong, strings(2).toDouble)
}).assignTimestampsAndWatermarks(new BoundedOutOfOrdernessTimestampExtractorSensorReading {
override def extractTimestamp(element: SensorReading): Long = element.timestamp * 1000L
})
val sensorTable: Table = tableEnv.fromDataStream(dataStream,'id,'temperature,'timestamp.rowtime as 'ts)
//调用自定义函数 对id进行hash运算
//tableAPI
val top2Temp = new Top2Temp
val resultApiTable: Table = sensorTable
.groupBy('id)
.flatAggregate(top2Temp('temperature) as ('temp,'rank))
.select('id, 'temp,'rank)
//sql实现

resultApiTable.toRetractStream[Row].print("resultApiTable")
streamEnv.execute()

}
}
//自定义表聚合函数 提取每个传感器所有温度值中最高的两个温度 输出（temp,rank)
class Top2Temp extends TableAggregateFunction[(Double,Int),Top2TempAcc] {
override def createAccumulator(): Top2TempAcc = {
new Top2TempAcc
}
//改变状态
def accumulate(acc:Top2TempAcc,temp:Double)={
//判断当前温度是否比当前温度值大
if(temp>acc.highestTemp){
acc.secondHighTemp = acc.highestTemp
acc.highestTemp = temp
}else if(temp > acc.secondHighTemp){
//如果在最高和第二高之间 替换第二高温度
acc.secondHighTemp = temp
}
}
def emitValue(acc:Top2TempAcc,out:Collector[(Double,Int)])={
out.collect(acc.highestTemp,1)
out.collect(acc.secondHighTemp,2)
}
}
//定义一个类用来表示表聚合函数的状态
class Top2TempAcc{
var highestTemp: Double = Double.MinValue
var secondHighTemp: Double = Double.MinValue
}