【无标题】

1.基于埋点日志数据的网络流量统计
网站总浏览量（PV）的统计
网站独立访客数（UV）的统计

package com.chuangyan.network35

import java.time.Duration

import org.apache.flink.api.common.RuntimeExecutionMode
import org.apache.flink.api.common.eventtime.{SerializableTimestampAssigner, WatermarkStrategy}
import org.apache.flink.streaming.api.scala._
import org.apache.flink.streaming.api.windowing.time.Time

case class UserBehavior(userId: Long, itemId: Long, categoryId: Long, behavior: String, timestamp: Long)
object PageView {

  def main(args: Array[String]): Unit = {
    val env = StreamExecutionEnvironment.getExecutionEnvironment
    env.setRuntimeMode(RuntimeExecutionMode.AUTOMATIC)
    env.setParallelism(1)

    val source: DataStream[String] = env.readTextFile("D:\study\Code\UserBehavior\NetworkFlowAnalysis\src\main\resources\UserBehavior.csv")

    val dataStream: DataStream[UserBehavior] = source.map(line => {
      val split = line.split(",")
      val userId = split(0).trim.toLong
      val itemId = split(1).trim.toLong
      val categoryId = split(2).trim.toLong
      val behavior = split(3).trim
      val timestamp = split(4).trim.toLong
      UserBehavior(userId, itemId, categoryId, behavior, timestamp)
    })
      .assignTimestampsAndWatermarks(WatermarkStrategy.forBoundedOutOfOrderness(Duration.ofSeconds(2))
        .withTimestampAssigner(new SerializableTimestampAssigner[UserBehavior] {
          override def extractTimestamp(element: UserBehavior, recordTimestamp: Long): Long = element.timestamp * 1000L
        }))

    //求PV：每隔1h计算一次p
    

    val ds: DataStream[(String, Int)] = dataStream.filter(_.behavior == "pv")
      .map(i => ("pv", 1))

    ds.keyBy(_._1)
      .timeWindow(Time.hours(1))
      .sum(1)
      .print()
    env.execute("pv job")

  }
}

package com.chuangyan.network35

import java.time.Duration

import org.apache.flink.api.common.RuntimeExecutionMode
import org.apache.flink.api.common.eventtime.{SerializableTimestampAssigner, WatermarkStrategy}
import org.apache.flink.streaming.api.scala._
import org.apache.flink.streaming.api.scala.function.AllWindowFunction
import org.apache.flink.streaming.api.windowing.time.Time
import org.apache.flink.streaming.api.windowing.windows.TimeWindow
import org.apache.flink.util.Collector

case class UserBehavior(userId:Long,itemId:Long,categoryId:Long,behavior:String,timestamp:Long )

object UniqueVisitor {
  def main(args: Array[String]): Unit = {

    val env = StreamExecutionEnvironment.getExecutionEnvironment
    env.setRuntimeMode(RuntimeExecutionMode.AUTOMATIC)
    env.setParallelism(1)

    val source = env.readTextFile("D:\study\Code\UserBehavior\NetworkFlowAnalysis\src\main\resources\UserBehavior.csv")

    val dataStream: DataStream[UserBehavior] = source.map(line => {
      val split = line.split(",")
      val userId = split(0).trim.toLong
      val itemId = split(1).trim.toLong
      val categoryId = split(2).trim.toLong
      val behavior = split(3).trim
      val timestamp = split(4).trim.toLong
      UserBehavior(userId, itemId, categoryId, behavior, timestamp)
    })
      .assignTimestampsAndWatermarks(WatermarkStrategy.forBoundedOutOfOrderness(Duration.ofSeconds(2))
        .withTimestampAssigner(new SerializableTimestampAssigner[UserBehavior] {
          override def extractTimestamp(element: UserBehavior, recordTimestamp: Long): Long = element.timestamp * 1000L
        }))
    //求uv

    dataStream.filter(_.behavior == "pv")
      .timeWindowAll(Time.hours(1))//滚动窗口
    //计算窗口 独立访客数
      .apply(new UvCountByWindow())
      .print()

    env.execute("pv job")

  }
}

case class UvCount(windowEnd:Long,count:Long)

class UvCountByWindow() extends AllWindowFunction[UserBehavior,UvCount,TimeWindow]{
  override def apply(window: TimeWindow, input: Iterable[UserBehavior], out: Collector[UvCount]): Unit = {
    //对窗口内  所有数据   去重
    

    import scala.collection.mutable

    val set=mutable.Set[Long]()

    val it=input.iterator
    while(it.hasNext){
      set+=it.next().userId
    }

    val windowEnd=window.getEnd
    val count=set.size

    out.collect(UvCount(windowEnd,count))

  }
}