java+web+pv+uv+统计_网站日志实时分析之Flink处理实时热门和PVUV统计

package com.ongbo.hotAnalysisimport java.sql.Timestampimport java.util.Propertiesimport org.apache.flink.api.common.functions.AggregateFunctionimport org.apache.flink.api.common.serialization.SimpleStringSchemaimport org.apache.flink.api.common.state.{ListState, ListStateDescriptor}import org.apache.flink.api.java.tuple.Tupleimport org.apache.flink.configuration.Configurationimport org.apache.flink.streaming.api.TimeCharacteristicimport org.apache.flink.streaming.api.functions.KeyedProcessFunctionimport org.apache.flink.streaming.api.scala._import org.apache.flink.streaming.api.scala.function.WindowFunctionimport org.apache.flink.streaming.api.windowing.time.Timeimport org.apache.flink.streaming.api.windowing.windows.TimeWindowimport org.apache.flink.streaming.connectors.kafka.FlinkKafkaConsumerimport org.apache.flink.util.Collectorimport scala.collection.mutable.ListBuffer/**定义输入数据的样例类*/case class UserBehavior(userId: Long, itemId: Long, cateGoryId: Int,behavior: String, timestamp: Long)//定义窗口聚合结果样例类case class ItemViewCount(itemId: Long, windowEnd: Long, count: Long)object HotItems {def main(args: Array[String]): Unit = {//1:创建执行环境val env = StreamExecutionEnvironment.getExecutionEnvironmentenv.setParallelism(1)//设置为事件事件env.setStreamTimeCharacteristic(TimeCharacteristic.EventTime)//2:读取数据/*kafka源*/val properties = new Properties()properties.setProperty("bootstrap.servers","114.116.219.197:5008,114.116.220.98:5008,114.116.199.154:5008")properties.setProperty("group.id","web-consumer-group")properties.setProperty("key.deserializer","org.apache.kafka.common.serialization.StringDeserializer")properties.setProperty("value.deserializer","org.apache.kafka.common.serialization.StringDeserializer")properties.setProperty("auto.offset.reset","latest")val dataStream = env.addSource(new FlinkKafkaConsumer[String]("weblog", new SimpleStringSchema(),properties))// val dataStream = env.readTextFile("/Users/ongbo/Maven/bin/UserBehaviorAnalysis/HotItemAnalysis/src/main/resources/UserBehavior.csv").map(data =>{System.out.println("data:"+data)val dataArray = data.split(",")// if(dataArray(0).equals("ij"))UserBehavior(dataArray(0).trim.toLong, dataArray(1).trim.toLong, dataArray(2).trim.toInt, dataArray(3).trim, dataArray(4).trim.toLong)}).assignAscendingTimestamps(_.timestamp * 1000L)//3:transform处理数据val processStream = dataStream//筛选出埋点pv数据.filter(_.behavior.equals("pv"))//先对itemID进行分组.keyBy(_.itemId)//然后设置timeWindow，size为1小时，步长为5分钟的滑动窗口.timeWindow(Time.seconds(20), Time.seconds(10))//窗口聚合，按道理说应该不用窗口聚合，但是因为达到的数据可能时间顺序会扰乱，所以聚合后要keyby.aggregate(new CountAgg(), new WindowResult()).keyBy(_.windowEnd) //按照窗口分组.process(new TopNHotItems(10))//sink：输出数据processStream.print("processStream::")// dataStream.print()//执行env.execute("hot Items Job")}}/*自定义预聚合函数*/class CountAgg() extends AggregateFunction[UserBehavior, Long, Long]{//累加器初始值override def createAccumulator(): Long = 0//每来一次就加一override def add(in: UserBehavior, acc: Long): Long = acc+1//override def getResult(acc: Long): Long = accoverride def merge(acc: Long, acc1: Long): Long = acc + acc1}//自定义窗口函数，输出ItemViewCountclass WindowResult() extends WindowFunction[Long,ItemViewCount, Long, TimeWindow]{override def apply(key: Long, window: TimeWindow, input: Iterable[Long], out: Collector[ItemViewCount]): Unit = {out.collect(ItemViewCount(key,window.getEnd,input.iterator.next()))}}//自定义处理函数class TopNHotItems(topsize: Int) extends KeyedProcessFunction[Long, ItemViewCount, String] {private var itemState: ListState[ItemViewCount] = _override def open(parameters: Configuration): Unit = {itemState = getRuntimeContext.getListState(new ListStateDescriptor[ItemViewCount]("item-state", classOf[ItemViewCount]))}override def processElement(value: ItemViewCount, ctx: KeyedProcessFunction[Long, ItemViewCount, String]#Context, out: Collector[String]): Unit = {//把每条数据存入状态列表itemState.add(value)//注册一个定时器ctx.timerService().registerEventTimeTimer(value.windowEnd + 1)}//定时器触发时，对所有的数据排序，并输出结果override def onTimer(timestamp: Long, ctx: _root_.org.apache.flink.streaming.api.functions.KeyedProcessFunction[Long, _root_.com.ongbo.hotAnalysis.ItemViewCount, _root_.scala.Predef.String]#OnTimerContext, out: _root_.org.apache.flink.util.Collector[_root_.scala.Predef.String]): Unit = {//将所有state中的数据取出，放到一个list Buffer中val allItems: ListBuffer[ItemViewCount] = new ListBuffer()import scala.collection.JavaConversions._for(item