学习笔记Flink（七）—— Flink Kafka插件

在pom.xml添加：

    org.apache.flink
    flink-connector-kafka_2.11
    1.10.1

代码：

package flink_kafka

import java.util.Properties
import org.apache.flink.api.common.serialization.SimpleStringSchema
import org.apache.flink.streaming.api.scala._
import org.apache.flink.streaming.connectors.kafka.FlinkKafkaConsumer

object MyFlinkKafkaConsumer {
  def main(args: Array[String]): Unit = {
    val properties = new Properties()
    properties.put("bootstrap.servers", "node110:9092,node111:9092,node112:9092")
    properties.put("group.id", "test")
    val env = StreamExecutionEnvironment.getExecutionEnvironment
    //create kafka source
    val kafkaSource = env.addSource(
      new FlinkKafkaConsumer[String](
        "demo02",//topic
        new SimpleStringSchema(),//seriable
        properties//kafka cluster configuration
      )
    )
    //Sink
    kafkaSource.print()
    //execute
    env.execute("read from kafka demo02")
  }
}

运行测试：
① 创建demo02话题，并在demo02写入数据

② 执行代码

package flink_kafka

import java.util.Properties

import org.apache.flink.api.common.serialization.SimpleStringSchema
import org.apache.flink.streaming.api.scala._
import org.apache.flink.streaming.api.windowing.time.Time
import org.apache.flink.streaming.connectors.kafka.internals.KeyedSerializationSchemaWrapper
import org.apache.flink.streaming.connectors.kafka.{FlinkKafkaConsumer, FlinkKafkaProducer}

object MyFlinkKafkaConsumerAndProducer {
  def main(args: Array[String]): Unit = {
    val properties = new Properties()
    properties.put("bootstrap.servers", "node110:9092,node111:9092,node112:9092")
    properties.put("group.id", "test")
    val env = StreamExecutionEnvironment.getExecutionEnvironment
    //create kafka source
    val kafkaSource = env.addSource(
      new FlinkKafkaConsumer[String](
        "demo02",//topic
        new SimpleStringSchema(),//seriable
        properties//kafka cluster configuration
      )
    )
    //transformation
    val processed = kafkaSource
      .flatMap(_.split("\w+"))
      .map((_,1))
      .keyBy(0)
      .timeWindow(Time.seconds(5))
      .sum(1)
      .filter(_._2>=3)
      .map(row => row._1+"->"+row._2)
    //kafka Sink
    val kafkaProducer = new FlinkKafkaProducer[String](
      "demo01",//target topic
      new KeyedSerializationSchemaWrapper[String](new SimpleStringSchema()),//seriablization schema
      properties,
      FlinkKafkaProducer.Semantic.EXACTLY_onCE
    )
    processed.addSink(kafkaProducer)
    //execute
    env.execute("read from kafka demo02 and write to demo01")

  }
}

测试：