Scala ConsumerConfig类代码示例

//设置package包名称以及导入依赖的类
package com.packt.chapter8

import akka.actor.ActorSystem
import akka.kafka.scaladsl.{Consumer, Producer}
import akka.kafka.{ConsumerSettings, ProducerSettings, Subscriptions}
import akka.stream.{ActorMaterializer, ClosedShape}
import akka.stream.scaladsl.{Flow, GraphDSL, RunnableGraph, Sink, Source}
import org.apache.kafka.clients.consumer.{ConsumerConfig, ConsumerRecord}
import org.apache.kafka.clients.producer.ProducerRecord
import org.apache.kafka.common.TopicPartition
import org.apache.kafka.common.serialization.{ByteArrayDeserializer, ByteArraySerializer, StringDeserializer, StringSerializer}

import scala.concurrent.duration._

object ProcessingKafkaApplication extends App {
  implicit val actorSystem = ActorSystem("SimpleStream")
  implicit val actorMaterializer = ActorMaterializer()

  val bootstrapServers = "localhost:9092"
  val kafkaTopic = "akka_streams_topic"
  val partition = 0
  val subscription = Subscriptions.assignment(new TopicPartition(kafkaTopic, partition))

  val consumerSettings = ConsumerSettings(actorSystem, new ByteArrayDeserializer, new StringDeserializer)
    .withBootstrapServers(bootstrapServers)
    .withGroupId("akka_streams_group")
    .withProperty(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG, "earliest")

  val producerSettings = ProducerSettings(actorSystem, new ByteArraySerializer, new StringSerializer)
    .withBootstrapServers(bootstrapServers)

  val runnableGraph = RunnableGraph.fromGraph(GraphDSL.create() { implicit builder =>
    import GraphDSL.Implicits._

    val tickSource = Source.tick(0 seconds, 5 seconds, "Hello from Akka Streams using Kafka!")
    val kafkaSource = Consumer.plainSource(consumerSettings, subscription)
    val kafkaSink = Producer.plainSink(producerSettings)
    val printlnSink = Sink.foreach(println)

    val mapToProducerRecord = Flow[String].map(elem => new ProducerRecord[Array[Byte], String](kafkaTopic, elem))
    val mapFromConsumerRecord = Flow[ConsumerRecord[Array[Byte], String]].map(record => record.value())

    tickSource  ~> mapToProducerRecord   ~> kafkaSink
    kafkaSource ~> mapFromConsumerRecord ~> printlnSink

    ClosedShape
  })

  runnableGraph.run()
} 

//设置package包名称以及导入依赖的类
package com.scalaio.kafka.consumer

import akka.actor.ActorSystem
import akka.kafka.ConsumerMessage.CommittableMessage
import akka.kafka.scaladsl.Consumer
import akka.kafka.{ConsumerSettings, ProducerSettings, Subscriptions}
import akka.stream.ActorMaterializer
import akka.stream.scaladsl.Sink
import com.scalaio.kafka.consumer.Settings.consumerSettings
import org.apache.kafka.clients.consumer.ConsumerConfig
import org.apache.kafka.common.serialization.{ByteArrayDeserializer, ByteArraySerializer, StringDeserializer, StringSerializer}

import scala.concurrent.Future

object Settings {
  def consumerSettings(implicit system: ActorSystem) =
    ConsumerSettings(system, new ByteArrayDeserializer, new StringDeserializer)
      .withBootstrapServers("localhost:9092")
      .withGroupId("CommittableSourceConsumer")
      .withProperty(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG, "earliest")

  def producerSettings(implicit system: ActorSystem) =
    ProducerSettings(system, new ByteArraySerializer, new StringSerializer)
      .withBootstrapServers("localhost:9092")
}

object CommittableSource extends App {

  type KafkaMessage = CommittableMessage[Array[Byte], String]

  implicit val system = ActorSystem("CommittableSourceConsumerMain")
  implicit val materializer = ActorMaterializer()

  implicit val ec = system.dispatcher

  // explicit commit
  Consumer
    .committableSource(consumerSettings, Subscriptions.topics("topic1"))
    .mapAsync(1) { msg =>
      BusinessController.handleMessage(msg.record.value)
        .flatMap(response => msg.committableOffset.commitScaladsl())
        .recoverWith { case e => msg.committableOffset.commitScaladsl() }
    }
    .runWith(Sink.ignore)

}

object BusinessController {

  type Service[A, B] = A => Future[B]

  val handleMessage: Service[String, String] =
    (message) => Future.successful(message.toUpperCase)

} 

//设置package包名称以及导入依赖的类
package com.landoop.kafka.ws.core.operations

import java.util.Properties

import com.landoop.kafka.ws.KafkaConstants
import io.confluent.kafka.serializers.KafkaAvroDeserializer
import kafka.utils.VerifiableProperties
import org.apache.kafka.clients.consumer.{ConsumerConfig, KafkaConsumer}
import org.apache.kafka.common.serialization.StringDeserializer

object SimpleConsumer {

  // Get a simple string consumer
  def getConsumer[T](kafkaBrokers: String, maxRecords: Option[Int] = None): KafkaConsumer[T, T] = {
    val props = new Properties()
    props.put(KafkaConstants.BOOTSTRAP_SERVER, kafkaBrokers)
    props.put(KafkaConstants.KEY_DESERIALIZER, "org.apache.kafka.common.serialization.StringDeserializer")
    props.put(KafkaConstants.VALUE_DESERIALIZER, "org.apache.kafka.common.serialization.StringDeserializer")
    maxRecords.find(_ > 0).map { max =>
      props.put(KafkaConstants.MAX_POLL_RECORDS, max.toString)
    }
    val vProps = new VerifiableProperties(props)

    val consumer = new KafkaConsumer[T, T](props)
    consumer
  }

  def createNewConsumerWithConsumerGroup(kafkaBrokers: String, group: String): KafkaConsumer[String, String] = {
    assert(group.length > 1, "Invalid group length")
    val properties = new Properties()
    properties.put(ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG, kafkaBrokers)
    properties.put(ConsumerConfig.GROUP_ID_CONFIG, group)
    properties.put(ConsumerConfig.ENABLE_AUTO_COMMIT_CONFIG, "false")
    properties.put(ConsumerConfig.SESSION_TIMEOUT_MS_CONFIG, "30000")
    properties.put(ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG, (new StringDeserializer).getClass.getName)
    properties.put(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG, (new StringDeserializer).getClass.getName)
    new KafkaConsumer(properties)
  }


  def getStringAvroConsumer[T](kafkaBrokers: String, schemaRegistry: String, maxRecords: Option[Int] = None): KafkaConsumer[String, T] = {
    val props = new Properties()
    props.put(KafkaConstants.BOOTSTRAP_SERVER, kafkaBrokers)
    props.put(KafkaConstants.KEY_DESERIALIZER, "org.apache.kafka.common.serialization.StringDeserializer")
    props.put(KafkaConstants.VALUE_DESERIALIZER, classOf[KafkaAvroDeserializer].getCanonicalName)
    props.put(KafkaConstants.SCHEMA_REGISTRY_URL, schemaRegistry)

    maxRecords.find(_ > 0).map { max =>
      props.put(KafkaConstants.MAX_POLL_RECORDS, max.toString)
    }
    val vProps = new VerifiableProperties(props)

    val consumer = new KafkaConsumer[String, T](props)
    consumer
  }

} 

//设置package包名称以及导入依赖的类
package edu.uw.at.iroberts.wirefugue.kafka.consumer

import akka.actor.ActorSystem
import akka.kafka.scaladsl.Consumer
import akka.kafka.{ConsumerSettings, Subscriptions}
import akka.stream.ActorMaterializer
import akka.stream.scaladsl.{Keep, Sink, Source}
import com.typesafe.config.ConfigFactory
import edu.uw.at.iroberts.wirefugue.kafka.producer.KafkaKey
import edu.uw.at.iroberts.wirefugue.kafka.serdes.{PacketDeserializer, PacketSerde}
import edu.uw.at.iroberts.wirefugue.pcap.Packet
import org.apache.kafka.clients.consumer.{ConsumerConfig, ConsumerRecord}
import org.apache.kafka.common.serialization.IntegerDeserializer

import scala.concurrent.Await
import scala.concurrent.duration._


object PacketConsumer extends App {
  type PacketRecord = ConsumerRecord[KafkaKey, Array[Byte]]
  val config = ConfigFactory.load("application.conf")

  implicit val system = ActorSystem("stream-consumer-system", config)
  implicit val materializer = ActorMaterializer()

  val consumerSettings = ConsumerSettings(system, new IntegerDeserializer, new PacketDeserializer)
    .withGroupId("group1")
    .withProperty(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG, "latest")

  // Separate streams for each partition
  val maxPartitions = 100
  val consumerGroup = Consumer.plainPartitionedSource(consumerSettings, Subscriptions.topics("packets"))

  val done = consumerGroup.map {
    case (topicPartition, source) =>
      val p: Int = topicPartition.partition
      source
        .map { (cr: ConsumerRecord[Integer, Packet]) => cr.value() }
        .filter(_.ip.isDefined)
        .toMat(Sink.foreach(packet => println(s"[$p] $packet")))(Keep.both)
        .run()
  }
    .mapAsyncUnordered(maxPartitions)(_._2)
    .runWith(Sink.ignore)

  Await.result(done, Duration.Inf)

  system.terminate()
} 

//设置package包名称以及导入依赖的类
package consumers

import akka.Done
import akka.actor.ActorSystem
import akka.kafka.scaladsl.Consumer
import akka.kafka.{ConsumerSettings, Subscriptions}
import akka.stream.scaladsl.Sink
import akka.stream.{ActorMaterializer, ActorMaterializerSettings}
import cats.data.Xor
import com.typesafe.config.ConfigFactory
import org.apache.kafka.clients.consumer.{ConsumerConfig, ConsumerRecord}
import org.apache.kafka.clients.consumer.internals.PartitionAssignor.Subscription
import org.apache.kafka.common.serialization.{ByteArrayDeserializer, StringDeserializer}
import io.circe._
import io.circe.generic.auto._
import cats.data.Xor.{Left, Right}
import model.Employee

import scala.concurrent.Future

object StreamConsumer  extends App{
  implicit val actorSystem = ActorSystem("consumer-actors", ConfigFactory.load())
  implicit val materializer = ActorMaterializer(ActorMaterializerSettings(actorSystem))

  lazy val consumerSettings = ConsumerSettings(actorSystem, new ByteArrayDeserializer, new StringDeserializer)
    .withBootstrapServers("localhost:9092")
    .withGroupId("group13")
    .withProperty(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG, "earliest")//"latest")
    .withProperty(ConsumerConfig.ENABLE_AUTO_COMMIT_CONFIG, "true")
    .withProperty(ConsumerConfig.AUTO_COMMIT_INTERVAL_MS_CONFIG, "1000")

  lazy val subscription = Subscriptions.topics("raw-data-1")
  lazy val db = new Processor()
  Consumer.plainSource(consumerSettings, subscription)
      .mapAsync(4){
        db.processMessage
      }
    .runWith(Sink.ignore)

}

class Processor {
  def processMessage(record: ConsumerRecord[Array[Byte], String]): Future[Done] ={
    println(s"DB.save: ${record.value()}")

    Option(record.value()).foreach{ jsonString =>
      val mayBeEmp: Xor[Error, Employee] = jawn.decode[Employee](jsonString)
      mayBeEmp match {
        case Left(error) => println(error)
        case Right(emp) => println(s"employee name: ${emp.name}")
      }
    }
    Future.successful(Done)  }
} 

//设置package包名称以及导入依赖的类
package org.hpi.esb.datavalidator.kafka

import akka.actor.ActorSystem
import akka.kafka.scaladsl.Consumer
import akka.kafka.{ConsumerSettings, Subscriptions}
import akka.stream.scaladsl.Source
import org.apache.kafka.clients.consumer.{ConsumerConfig, ConsumerRecord}
import org.apache.kafka.common.TopicPartition
import org.apache.kafka.common.serialization.StringDeserializer
import org.hpi.esb.util.OffsetManagement

case class TopicHandler(topicName: String, numberOfMessages: Long, topicSource: Source[ConsumerRecord[String, String], Consumer.Control])

object TopicHandler {

  def create(topicName: String, system: ActorSystem): TopicHandler = {

    val uuid = java.util.UUID.randomUUID.toString
    val consumerSettings: ConsumerSettings[String, String] = ConsumerSettings(system, new StringDeserializer, new StringDeserializer)
      .withBootstrapServers("192.168.30.208:9092,192.168.30.207:9092,192.168.30.141:9092")
      .withGroupId(uuid)
      .withProperty(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG, "earliest")
      .withProperty(ConsumerConfig.MAX_POLL_RECORDS_CONFIG, Int.MaxValue.toString)
      .withProperty(ConsumerConfig.FETCH_MAX_BYTES_CONFIG, Int.MaxValue.toString)
      .withProperty(ConsumerConfig.FETCH_MIN_BYTES_CONFIG, "20485000")

    val partition = 0
    val topicSource = createSource(consumerSettings, topicName, partition)
    val numberOfMessages = OffsetManagement.getNumberOfMessages(topicName, partition)

    new TopicHandler(topicName, numberOfMessages, topicSource)
  }

  def createSource(consumerSettings: ConsumerSettings[String, String], topicName: String, partition: Int) = {

    val subscription = Subscriptions.assignmentWithOffset(
      new TopicPartition(topicName, partition) -> 0L
    )
    Consumer.plainSource(consumerSettings, subscription)
  }
} 

//设置package包名称以及导入依赖的类
import akka.actor.ActorSystem
import akka.kafka.{ConsumerSettings, Subscriptions}
import akka.kafka.scaladsl.Consumer
import akka.stream.ActorMaterializer
import org.apache.kafka.clients.consumer.ConsumerConfig
import org.apache.kafka.common.serialization.{ByteArrayDeserializer, StringDeserializer}

import scala.concurrent.Future

object Main {
  def main(args: Array[String]): Unit = {
    implicit val system = ActorSystem.apply("akka-stream-kafka")
    implicit val materializer = ActorMaterializer()

    val consumerSettings = ConsumerSettings(system, new ByteArrayDeserializer, new StringDeserializer)
      .withBootstrapServers("localhost:9092;localhost:9093")
      .withGroupId("group1")
      .withProperty(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG, "earliest")

    Consumer.committableSource(consumerSettings, Subscriptions.topics("topic1"))
      .mapAsync(1)(msg => {
        msg.committableOffset.commitScaladsl
        Future.successful(msg)
      })
      .runForeach(msg => println(s"partition: ${msg.record.partition}; value: ${msg.record.value}"))
  }
} 

//设置package包名称以及导入依赖的类
package org.rgcase.reactivekafka

import akka.actor.ActorSystem
import akka.kafka.ConsumerMessage.{ CommittableMessage, CommittableOffsetBatch }
import akka.kafka.ProducerMessage.Message
import akka.kafka.scaladsl.{ Consumer, Producer }
import akka.kafka.{ ConsumerSettings, ProducerSettings, Subscriptions }
import akka.stream.ActorMaterializer
import akka.stream.scaladsl.{ Flow, Sink }
import org.apache.kafka.clients.consumer.ConsumerConfig
import org.apache.kafka.clients.producer.ProducerRecord
import org.apache.kafka.common.serialization.{ ByteArrayDeserializer, ByteArraySerializer, StringDeserializer, StringSerializer }

class ReactiveKafkaSingleConsumerMultipleProducerScala extends App {

  implicit val system = ActorSystem("reactivekafkascala")
  implicit val mat = ActorMaterializer()

  val consumerSettings = ConsumerSettings(system, new ByteArrayDeserializer, new StringDeserializer)
    .withBootstrapServers("localhost:9092")
    .withGroupId("group1")
    .withProperty(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG, "earliest")

  val producerSettings = ProducerSettings(system, new ByteArraySerializer, new StringSerializer)
    .withBootstrapServers("localhost:9093")

  val kafkaSource =
    Consumer.committableSource(consumerSettings, Subscriptions.topics("sourcetopic"))

  def toProducerMessage(topic: String) = (msg: CommittableMessage[Array[Byte], String]) ?
    Message[Array[Byte], String, CommittableMessage[Array[Byte], String]](new ProducerRecord(topic, msg.record.value), msg)

  val producerFlow1 =
    Flow.fromFunction(toProducerMessage("targettopic1")).via(Producer.flow(producerSettings)).map(_.message.passThrough)

  val producerFlow2 =
    Flow.fromFunction(toProducerMessage("targettopic2")).via(Producer.flow(producerSettings)).map(_.message.passThrough)

  val producerFlow3 =
    Flow.fromFunction(toProducerMessage("targettopic3")).via(Producer.flow(producerSettings)).map(_.message.passThrough)

  kafkaSource
    .via(producerFlow1)
    .via(producerFlow2)
    .via(producerFlow3)
    .batch(max = 20, first ? CommittableOffsetBatch.empty.updated(first.committableOffset)) { (batch, elem) ?
      batch.updated(elem.committableOffset)
    }.mapAsync(3)(_.commitScaladsl())
    .runWith(Sink.ignore)

} 

//设置package包名称以及导入依赖的类
package com.github.mmolimar.asks.streaming

import java.util.UUID

import com.github.mmolimar.askss.common.implicits._
import com.typesafe.scalalogging.LazyLogging
import org.apache.kafka.clients.consumer.{ConsumerConfig, ConsumerRecord}
import org.apache.kafka.common.serialization.StringDeserializer
import org.apache.spark.SparkConf
import org.apache.spark.streaming._
import org.apache.spark.streaming.dstream.InputDStream
import org.apache.spark.streaming.kafka010.{ConsumerStrategies, KafkaUtils, LocationStrategies}


object RsvpStreaming extends App with LazyLogging {

  val filter = config.getString("spark.filter").toLowerCase.split(",").toList
  val ssc = new StreamingContext(buildSparkConfig, Seconds(5))

  //TODO
  kafkaStream(ssc)
    .map(_.value())
    .map(_.toEvent)
    .filter(rsvp => {
      filter.exists(rsvp.event.get.event_name.contains(_))
    })
    .print()

  ssc.start()
  ssc.awaitTermination()

  def buildSparkConfig(): SparkConf = {
    new SparkConf()
      .setMaster(config.getString("spark.master"))
      .setAppName("RsvpStreaming")
      .set("spark.streaming.ui.retainedBatches", "5")
      .set("spark.streaming.backpressure.enabled", "true")
      .set("spark.sql.parquet.compression.codec", "snappy")
      .set("spark.sql.parquet.mergeSchema", "true")
      .set("spark.sql.parquet.binaryAsString", "true")
  }

  def kafkaStream(ssc: StreamingContext): InputDStream[ConsumerRecord[String, String]] = {
    val topics = Set(config.getString("kafka.topic"))

    val kafkaParams = Map[String, Object](
      "metadata.broker.list" -> config.getString("kafka.brokerList"),
      "enable.auto.commit" -> config.getBoolean("kafka.autoCommit").toString,
      "auto.offset.reset" -> config.getString("kafka.autoOffset"),
      ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG -> config.getString("kafka.brokerList"),
      ConsumerConfig.GROUP_ID_CONFIG -> s"consumer-${UUID.randomUUID}",
      "key.deserializer" -> classOf[StringDeserializer],
      "value.deserializer" -> classOf[StringDeserializer]
    )

    val consumerStrategy = ConsumerStrategies.Subscribe[String, String](topics, kafkaParams)
    KafkaUtils.createDirectStream[String, String](ssc, LocationStrategies.PreferConsistent, consumerStrategy)
  }

} 

//设置package包名称以及导入依赖的类
package co.s4n.infrastructure.kafka

import java.util.concurrent._
import java.util.{ Collections, Properties }

import org.apache.kafka.clients.consumer.{ ConsumerConfig, KafkaConsumer }

import scala.collection.JavaConverters._


object Consumer {

  def createConsumerConfig(): Properties = {
    val props = new Properties()
    props.put(ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG, "localhost:9092")
    props.put(ConsumerConfig.GROUP_ID_CONFIG, "KafkaProducerExample")
    props.put(ConsumerConfig.ENABLE_AUTO_COMMIT_CONFIG, "true")
    props.put(ConsumerConfig.AUTO_COMMIT_INTERVAL_MS_CONFIG, "1000")
    props.put(ConsumerConfig.SESSION_TIMEOUT_MS_CONFIG, "30000")
    props.put(ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG, "org.apache.kafka.common.serialization.StringDeserializer")
    props.put(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG, "org.apache.kafka.common.serialization.StringDeserializer")
    props
  }

  def run(): Unit = {
    val consumer = new KafkaConsumer[String, String](createConsumerConfig())
    consumer.subscribe(Collections.singletonList("UsersTopic"))

    Executors.newSingleThreadExecutor.execute(() => {
      while (true) {
        val records = consumer.poll(1000)

        for (record <- records.iterator().asScala) {
          println("\n\n Received message: (" + record.key() + ", " + record.value() + ") at offset " + record.offset())
        }
      }
    })
  }

} 

//设置package包名称以及导入依赖的类
package org.hpi.esb.datavalidator.consumer

import java.util.Properties

import org.apache.kafka.clients.consumer.{ConsumerConfig, ConsumerRecord, ConsumerRecords, KafkaConsumer}
import org.apache.kafka.common.TopicPartition
import org.hpi.esb.datavalidator.config.KafkaConsumerConfig
import org.hpi.esb.datavalidator.util.Logging

import scala.collection.JavaConversions._
import scala.collection.mutable.ListBuffer

class ConsumerLoop(topic: String, config: KafkaConsumerConfig, results: ListBuffer[ConsumerRecord[String, String]]) extends Runnable with Logging {

  private val props = createConsumerProps()
  private val consumer = new KafkaConsumer(props)

  initializeConsumer()

  override def run(): Unit = {

    var running = true
    var zeroCount = 0

    while (running) {
      val records = consumer.poll(1000).asInstanceOf[ConsumerRecords[String, String]]

      if (records.count() == 0) {
        logger.debug(s"Received 0 records from Kafka.")
        zeroCount += 1
        if (zeroCount == 3) {
          logger.debug("Received 0 records from Kafka for the third time. We assume the stream has finished and terminate.")
          running = false
        }
      }

      for (record <- records) {
        results.append(record)
      }
    }
    consumer.close()
  }

  private def initializeConsumer(): Unit = {
    val topicPartitions = List(new TopicPartition(topic, 0))
    consumer.assign(topicPartitions)
    consumer.seekToBeginning(topicPartitions)
  }

  private def createConsumerProps(): Properties = {
    val props = new Properties()
    props.put(ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG, config.bootstrapServers)
    props.put(ConsumerConfig.GROUP_ID_CONFIG, s"Validator")
    props.put(ConsumerConfig.ENABLE_AUTO_COMMIT_CONFIG, config.autoCommit)
    props.put(ConsumerConfig.AUTO_COMMIT_INTERVAL_MS_CONFIG, config.autoCommitInterval)
    props.put(ConsumerConfig.SESSION_TIMEOUT_MS_CONFIG, config.sessionTimeout)
    props.put(ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG, config.keyDeserializerClass)
    props.put(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG, config.valueDeserializerClass)
    props
  }
} 

//设置package包名称以及导入依赖的类
package com.example.consumer

import akka.Done
import akka.actor.ActorSystem
import akka.kafka.ConsumerMessage.CommittableOffsetBatch
import akka.kafka.scaladsl.Consumer
import akka.kafka.{ConsumerSettings, Subscriptions}
import akka.stream.ActorMaterializer
import akka.stream.scaladsl.Sink
import org.apache.kafka.clients.consumer.ConsumerConfig
import org.apache.kafka.common.serialization.{ByteArrayDeserializer, StringDeserializer}

import scala.concurrent.ExecutionContext.Implicits.global
import scala.concurrent.Future

object BatchCommittableSourceConsumerMain extends App {
  implicit val system = ActorSystem("BatchCommittableSourceConsumerMain")
  implicit val materializer = ActorMaterializer()

  //TODO: move to configuration application.conf
  val consumerSettings = ConsumerSettings(system, new ByteArrayDeserializer, new StringDeserializer)
    .withBootstrapServers("localhost:9092")
    .withGroupId("BatchCommittableSourceConsumer")
    .withProperty(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG, "earliest")

  val done =
    Consumer.committableSource(consumerSettings, Subscriptions.topics("topic1"))
      .mapAsync(1) { msg =>
        println(s"BatchCommittableConsumer consume: $msg")
        Future.successful(Done).map(_ => msg.committableOffset)
      }
      .batch(max = 20, first => CommittableOffsetBatch.empty.updated(first)) { (batch, elem) =>
        batch.updated(elem)
      }
      .mapAsync(3)(_.commitScaladsl())
      .runWith(Sink.ignore)

} 

//设置package包名称以及导入依赖的类
package com.example.consumer

import java.util.concurrent.atomic.AtomicLong

import akka.Done
import akka.actor.ActorSystem
import akka.kafka.scaladsl.Consumer
import akka.kafka.{ConsumerSettings, Subscriptions}
import akka.stream.ActorMaterializer
import akka.stream.scaladsl.Sink
import org.apache.kafka.clients.consumer.{ConsumerConfig, ConsumerRecord}
import org.apache.kafka.common.TopicPartition
import org.apache.kafka.common.serialization.{ByteArrayDeserializer, StringDeserializer}

import scala.concurrent.ExecutionContext.Implicits.global
import scala.concurrent.Future


object PlainSourceConsumerMain extends App {
  implicit val system = ActorSystem("PlainSourceConsumerMain")
  implicit val materializer = ActorMaterializer()

  //TODO: move to configuration application.conf
  val consumerSettings = ConsumerSettings(system, new ByteArrayDeserializer, new StringDeserializer)
    .withBootstrapServers("localhost:9092")
    .withGroupId("PlainSourceConsumer")
    .withProperty(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG, "earliest")

  val db = new DB
  db.loadOffset().foreach { fromOffset =>
    val partition = 0
    val subscription = Subscriptions.assignmentWithOffset(
      new TopicPartition("topic1", partition) -> fromOffset
    )
    val done =
      Consumer.plainSource(consumerSettings, subscription)
        .mapAsync(1)(db.save)
        .runWith(Sink.ignore)
  }

}

//External Offset Storage
class DB {

  private val offset = new AtomicLong(2)

  def save(record: ConsumerRecord[Array[Byte], String]): Future[Done] = {
    println(s"DB.save: ${record.value}")
    offset.set(record.offset)
    Future.successful(Done)
  }

  def loadOffset(): Future[Long] =
    Future.successful(offset.get)

  def update(data: String): Future[Done] = {
    println(s"DB.update: $data")
    Future.successful(Done)
  }
} 

//设置package包名称以及导入依赖的类
package com.example.producer

import akka.actor.ActorSystem
import akka.kafka.scaladsl.{Consumer, Producer}
import akka.kafka.{ConsumerSettings, ProducerMessage, ProducerSettings, Subscriptions}
import akka.stream.ActorMaterializer
import akka.stream.scaladsl.Sink
import org.apache.kafka.clients.consumer.ConsumerConfig
import org.apache.kafka.clients.producer.ProducerRecord
import org.apache.kafka.common.serialization.{ByteArrayDeserializer, ByteArraySerializer, StringDeserializer, StringSerializer}


object CommitConsumerToFlowProducerMain extends App {
  implicit val system = ActorSystem("CommitConsumerToFlowProducerMain")
  implicit val materializer = ActorMaterializer()

  val consumerSettings =
    ConsumerSettings(system, new ByteArrayDeserializer, new StringDeserializer)
      .withBootstrapServers("localhost:9092")
      .withGroupId("CommitConsumerToFlowProducer")
      .withProperty(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG, "earliest")

  val producerSettings = ProducerSettings(system, new ByteArraySerializer, new StringSerializer)
    .withBootstrapServers("localhost:9092")

  val done =
    Consumer.committableSource(consumerSettings, Subscriptions.topics("topic1"))
      .map { msg =>
        println(s"topic1 -> topic2: $msg")
        ProducerMessage.Message(new ProducerRecord[Array[Byte], String](
          "topic2",
          msg.record.value
        ), msg.committableOffset)
      }
      .via(Producer.flow(producerSettings))
      .mapAsync(producerSettings.parallelism) { result =>
        result.message.passThrough.commitScaladsl()
      }
      .runWith(Sink.ignore)
} 

//设置package包名称以及导入依赖的类
package com.example.producer

import akka.actor.ActorSystem
import akka.kafka.ConsumerMessage.CommittableOffsetBatch
import akka.kafka.scaladsl.{Consumer, Producer}
import akka.kafka.{ConsumerSettings, ProducerMessage, ProducerSettings, Subscriptions}
import akka.stream.ActorMaterializer
import akka.stream.scaladsl.Sink
import org.apache.kafka.clients.consumer.ConsumerConfig
import org.apache.kafka.clients.producer.ProducerRecord
import org.apache.kafka.common.serialization.{ByteArrayDeserializer, ByteArraySerializer, StringDeserializer, StringSerializer}


object ConsumerToCommitableSinkProducerMain extends App {

  implicit val system = ActorSystem("Consumer2ProducerMain")
  implicit val materializer = ActorMaterializer()

  //TODO: move to configuration application.conf
  val consumerSettings =
    ConsumerSettings(system, new ByteArrayDeserializer, new StringDeserializer)
      .withBootstrapServers("localhost:9092")
      .withGroupId("Consumer2Producer")
      .withProperty(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG, "earliest")

  //TODO: move to configuration application.conf
  val producerSettings =
    ProducerSettings(system, new ByteArraySerializer, new StringSerializer)
      .withBootstrapServers("localhost:9092")

  Consumer.committableSource(consumerSettings, Subscriptions.topics("topic1"))
    .map { msg =>
      println(s"topic1 -> topic2: $msg")
      ProducerMessage.Message(new ProducerRecord[Array[Byte], String](
        "topic2",
        msg.record.value
      ), msg.committableOffset)
    }
    .runWith(Producer.commitableSink(producerSettings))

}