FlinkCEP(02)--kafka数据源

需求：用户点击完立刻购买的信息
数据源kafka，这里比较重要的一点设置水位Watermarks

import com.alibaba.fastjson.JSON

import java.util.Properties
import org.apache.flink.api.common.serialization.SimpleStringSchema
import org.apache.flink.cep.pattern.conditions.SimpleCondition
import org.apache.flink.cep.scala.CEP
import org.apache.flink.cep.scala.pattern.Pattern
import org.apache.flink.streaming.api.TimeCharacteristic
import org.apache.flink.streaming.api.scala.{DataStream, StreamExecutionEnvironment}
import org.apache.flink.streaming.connectors.kafka.FlinkKafkaConsumer010
import org.apache.flink.api.scala._
import org.apache.flink.cep.PatternSelectFunction
import org.apache.flink.streaming.api.functions.timestamps.BoundedOutOfOrdernessTimestampExtractor
import org.apache.flink.streaming.api.windowing.time.Time


object Model01 {

  def main(args: Array[String]): Unit = {
    val env = StreamExecutionEnvironment.getExecutionEnvironment
    env.setStreamTimeCharacteristic(TimeCharacteristic.EventTime)
    env.setParallelism(1)
    val properties = new Properties()
    properties.setProperty("bootstrap.servers", "xxxx:9092")
    properties.setProperty("group.id", "test")
    properties.setProperty("key.deserializer", "org.apache.kafka.common.serialization.StringDeserializer")
    properties.setProperty("value.deserializer", "org.apache.kafka.common.serialization.StringDeserializer")

    val consumer = new FlinkKafkaConsumer010("topic", new SimpleStringSchema(), properties)
    consumer.setStartFromLatest()
    val sourceStream = env.addSource(consumer)

    val input: DataStream[UserAction] = sourceStream.map(line=>{
      val data = JSON.parseObject(line)
      val distinct_id = data.getString("distinct_id")
      val event = data.getString("event")
      val time = data.getLong("time")
      val project_id = data.getString("project_id")
      UserAction(project_id, time, distinct_id, event)
    })
      .assignTimestampsAndWatermarks(new BoundedOutOfOrdernessTimestampExtractor[UserAction](Time.seconds(10)) {
      override def extractTimestamp(t: UserAction): Long = t.timestamp
    }).keyBy(k=>k.name)

    val pattern = Pattern.begin[UserAction]("start").where(new SimpleCondition[UserAction] {
        override def filter(t: UserAction): Boolean = {
          t.action.equals("click")
        }
      }).next("end").where(new SimpleCondition[UserAction] {
        override def filter(t: UserAction): Boolean = {
          t.action.equals("buy")
        }
      }).within(Time.seconds(10))

    val patternStream = CEP.pattern(input, pattern)

    val result = patternStream.select(new PatternSelectFunction[UserAction, String] {
      override def select(map: java.util.Map[String, java.util.List[UserAction]]): String = {
        val start: UserAction = map.get("start").iterator().next()
        val end: UserAction = map.get("end").iterator().next()
        s"name: ${start.name}, project_id: ${end.project_id}, timestamp: ${end.timestamp}"
      }
    })

    result.print()
    env.execute("CEPTestJson")
  }

  case class UserAction(project_id: String, timestamp: Long, name: String, action: String)
}