本文整理汇总了Scala中org.apache.kafka.common.serialization.ByteArrayDeserializer类的典型用法代码示例。如果您正苦于以下问题:Scala ByteArrayDeserializer类的具体用法?Scala ByteArrayDeserializer怎么用?Scala ByteArrayDeserializer使用的例子?那么, 这里精选的类代码示例或许可以为您提供帮助。
在下文中一共展示了ByteArrayDeserializer类的15个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Scala代码示例。
示例1: ProcessingKafkaApplication
//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()
}
示例2: Settings
//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)
}
示例3: StreamConsumer
//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) }
}
示例4: Main
//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}"))
}
}
示例5: ReactiveKafkaSingleConsumerMultipleProducerScala
//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)
}
开发者ID:rgcase,项目名称:testplayground,代码行数:52,代码来源:ReactiveKafkaSingleConsumerMultipleProducerScala.scala
示例6: CommitConsumerToFlowProducerMain
//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)
}
示例7: ConsumerToCommitableSinkProducerMain
//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))
}
开发者ID:makersu,项目名称:reactive-kafka-scala-example,代码行数:42,代码来源:ConsumerToCommitableSinkProducerMain.scala
示例8: Config
//设置package包名称以及导入依赖的类
package com.kissthinker.kafka
import java.util.Properties
import org.apache.kafka.common.serialization.{ByteArrayDeserializer, ByteArraySerializer}
abstract class Config(kafkaAddress: String) extends Properties {
put("bootstrap.servers", kafkaAddress)
}
class PublisherConfig(kafkaAddress: String) extends Config(kafkaAddress) {
put("metadata.broker.list", kafkaAddress)
//put("client.id", "kafka-publisher")
put("key.serializer", classOf[ByteArraySerializer].getName)
put("value.serializer", classOf[ByteArraySerializer].getName)
put("producer.type", "async")
}
class SubscriberConfig(zookeeperAddress: String, kafkaAddress: String) extends Config(kafkaAddress) {
//put("zookeeper.connect", "127.0.0.1:2181")
put("zookeeper.connect", zookeeperAddress)
//put("group.id", "1")
put("group.id", "2")
put("auto.offset.reset", "largest")
put("zookeeper.session.timeout.ms", "400")
put("zookeeper.sync.time.ms", "200")
put("auto.commit.interval.ms", "1000")
put("key.deserializer", classOf[ByteArrayDeserializer].getName)
put("value.deserializer", classOf[ByteArrayDeserializer].getName)
}
示例9: Main
//设置package包名称以及导入依赖的类
package connector
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, ConsumerRecord}
import org.apache.kafka.common.serialization.{ByteArrayDeserializer, StringDeserializer}
import scala.concurrent.duration._
object Main {
def main(args: Array[String]): Unit = {
implicit val system = ActorSystem("QuickStart")
implicit val materializer = ActorMaterializer()
val kafkaConsumerSettings = ConsumerSettings(system, new ByteArrayDeserializer, new StringDeserializer)
.withBootstrapServers("localhost:9092")
.withGroupId("group1")
.withProperty(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG, "latest")
.withProperty(ConsumerConfig.ENABLE_AUTO_COMMIT_CONFIG, "true")
val kafkaSubscription = Subscriptions.topics("input")
val maxItemsInBatch = 10
Consumer.plainSource(kafkaConsumerSettings, kafkaSubscription)
.groupedWithin(maxItemsInBatch, 10000.milliseconds)
.runForeach(batch => persist(batch))
}
// TODO: Sent batch to ElasticSearch
def persist(batch: Seq[ConsumerRecord[Array[Byte], String]]): Unit = {
batch foreach println
}
}
示例10: throttolableConsumerFlow
//设置package包名称以及导入依赖的类
package com.github.everpeace
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.scaladsl.Source
import akka.stream.{ActorMaterializer, ThrottleMode}
import org.apache.kafka.clients.consumer.ConsumerConfig
import org.apache.kafka.common.serialization.{ByteArrayDeserializer, StringDeserializer}
import scala.concurrent.duration.Duration
package object reactive_kafka {
def throttolableConsumerFlow(implicit system: ActorSystem, mat: ActorMaterializer): Source[Done, Consumer.Control] = {
val c = system.settings.config.getConfig("throttolable-consumer")
implicit val ec = system.dispatcher
val bootstrapServers = c getString "bootstrap-servers"
val topic = c getString "topic"
val autoRestConfig = c getString "auto-offset-reset"
val groupId = c getString "group-id"
val throttle = c getInt "throttle"
val throttlePer = Duration.fromNanos((c getDuration "throttle-per").toNanos)
val throttleBurst = c getInt "throttle-burst"
val logPer = c getInt "log-per"
val offsetCommitBatchSize = c getInt "offset-commit-batch-size"
val offsetCommitParallelism = c getInt "offset-commit-parallelism"
val consumerSettings =
ConsumerSettings(system, new ByteArrayDeserializer, new StringDeserializer)
.withBootstrapServers(bootstrapServers)
.withGroupId(groupId)
.withProperty(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG, autoRestConfig)
val source = Consumer.committableSource(consumerSettings, Subscriptions.topics(Set(topic)))
val throttled = if (throttle > 0)
source.throttle(throttle, throttlePer, throttleBurst, ThrottleMode.shaping)
else source
throttled.statefulMapConcat(() => {
var counter = 0
msg => {
if (counter % logPer == 0) {
system.log.info(s"FakeConsumer consume: $msg")
counter = 0
}
counter += 1
msg :: Nil
}
}).batch(max = offsetCommitBatchSize, m => CommittableOffsetBatch.empty.updated(m.committableOffset))((batch, m) => batch.updated(m.committableOffset))
.mapAsync(offsetCommitParallelism) { batch =>
batch.commitScaladsl()
}
}
}
示例11: FutureToTry
//设置package包名称以及导入依赖的类
package com.github.dnvriend
import akka.NotUsed
import akka.actor._
import akka.event.{Logging, LoggingAdapter}
import akka.kafka.{ConsumerSettings, ProducerSettings}
import org.apache.kafka.common.serialization.StringDeserializer
import org.apache.kafka.common.serialization.ByteArrayDeserializer
import org.apache.kafka.clients.consumer.ConsumerConfig
import akka.stream.scaladsl.Source
import akka.stream.{ActorMaterializer, Materializer}
import org.apache.kafka.common.serialization.{ByteArraySerializer, StringSerializer}
import org.scalatest.concurrent.ScalaFutures
import org.scalatest.{BeforeAndAfterAll, FlatSpec, Matchers}
import scala.concurrent.duration._
import scala.concurrent.{ExecutionContext, Future}
import scala.util.Try
trait TestSpec extends FlatSpec with Matchers with ScalaFutures with BeforeAndAfterAll {
implicit val system: ActorSystem = ActorSystem()
implicit val ec: ExecutionContext = system.dispatcher
implicit val mat: Materializer = ActorMaterializer()
implicit val log: LoggingAdapter = Logging(system, this.getClass)
implicit val pc: PatienceConfig = PatienceConfig(timeout = 50.seconds)
val producerSettings = ProducerSettings(system, new ByteArraySerializer, new StringSerializer)
.withBootstrapServers("boot2docker:9092")
val consumerSettings = ConsumerSettings(system, new ByteArrayDeserializer, new StringDeserializer,
Set("topic1"))
.withBootstrapServers("boot2docker:9092")
.withGroupId("group1")
.withProperty(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG, "earliest")
implicit class FutureToTry[T](f: Future[T]) {
def toTry: Try[T] = Try(f.futureValue)
}
def withIterator[T](start: Int = 0)(f: Source[Int, NotUsed] ? T): T =
f(Source.fromIterator(() ? Iterator from start))
override protected def afterAll(): Unit = {
system.terminate()
system.whenTerminated.toTry should be a 'success
}
}
示例12: AnalyzerRunner
//设置package包名称以及导入依赖的类
package io.scalac.newspaper.analyzer
import akka.actor.ActorSystem
import akka.kafka.ProducerMessage
import akka.kafka.scaladsl.{Consumer, Producer}
import akka.kafka.{Subscriptions, ConsumerSettings, ProducerSettings}
import akka.stream.ActorMaterializer
import akka.stream.scaladsl.{Source, Sink}
import org.apache.kafka.clients.consumer.ConsumerConfig
import org.apache.kafka.clients.producer.{ProducerRecord}
import org.apache.kafka.common.serialization.{ByteArrayDeserializer, ByteArraySerializer}
import io.scalac.newspaper.events._
object AnalyzerRunner extends App {
implicit val system = ActorSystem("Newspaper-Analyzer-System")
implicit val materializer = ActorMaterializer()
val consumerSettings = ConsumerSettings(system, new ByteArrayDeserializer, new ContentFetchedDeserializer)
.withGroupId("Newspaper-Analyzer")
.withProperty(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG, "earliest")
val producerSettings = ProducerSettings(system, new ByteArraySerializer, new ChangeDetectedSerializer)
val subscription = Subscriptions.topics("newspaper-content")
Consumer.committableSource(consumerSettings, subscription)
.map { msg =>
// Do sth with msg.record.value
println(s"[ANALYZING] ${msg.record.value}")
val input = msg.record.value
val output = ChangeDetected(input.pageUrl, input.pageContent)
val record = new ProducerRecord[Array[Byte], ChangeDetected]("newspaper", output)
ProducerMessage.Message(record, msg.committableOffset)
}
.via(Producer.flow(producerSettings))
.map(_.message.passThrough)
.mapAsync(1)(_.commitScaladsl())
.runWith(Sink.ignore)
}
示例13: KafkaPublisherConfig
//设置package包名称以及导入依赖的类
package com.pragmasoft.eventaggregator.streams
import akka.kafka.scaladsl.Consumer
import akka.kafka.scaladsl.Consumer.Control
import akka.kafka.{ConsumerSettings, Subscriptions}
import akka.stream.scaladsl.Source
import com.pragmasoft.eventaggregator.ActorSystemProvider
import com.typesafe.scalalogging.LazyLogging
import org.apache.kafka.clients.consumer.{ConsumerConfig, ConsumerRecord}
import org.apache.kafka.common.serialization.ByteArrayDeserializer
case class KafkaPublisherConfig(reactiveKafkaDispatcher: String, bootstrapBrokers: String, topicRegex: String, groupId: String, readFromBeginning: Boolean)
trait SourceProvider[T, Mat] {
def source: Source[T, Mat]
}
trait KafkaSourceProvider extends SourceProvider[ConsumerRecord[Array[Byte], Array[Byte]], Control] with LazyLogging {
self: ActorSystemProvider =>
def kafkaConfig: KafkaPublisherConfig
lazy val consumerProperties = {
ConsumerSettings(actorSystem, new ByteArrayDeserializer, new ByteArrayDeserializer)
.withBootstrapServers(kafkaConfig.bootstrapBrokers)
.withGroupId(kafkaConfig.groupId)
.withProperty(
ConsumerConfig.AUTO_OFFSET_RESET_CONFIG,
if (kafkaConfig.readFromBeginning)
"earliest"
else
"latest"
)
.withProperty(
ConsumerConfig.ENABLE_AUTO_COMMIT_CONFIG,
"true"
)
.withDispatcher(kafkaConfig.reactiveKafkaDispatcher)
}
override lazy val source: Source[ConsumerRecord[Array[Byte], Array[Byte]], Control] =
Consumer.atMostOnceSource(consumerProperties, Subscriptions.topicPattern(kafkaConfig.topicRegex))
}
示例14: KafkaEventBus
//设置package包名称以及导入依赖的类
package io.corbel.event.kafka
import akka.NotUsed
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.{Flow, Sink, Source}
import grizzled.slf4j.Logging
import io.corbel.event.{Event, EventBus, SubscriptionProperties}
import org.apache.kafka.clients.consumer.ConsumerConfig
import org.apache.kafka.clients.producer.ProducerRecord
import org.apache.kafka.common.serialization.{ByteArrayDeserializer, ByteArraySerializer, StringDeserializer, StringSerializer}
import org.json4s.DefaultFormats
import org.json4s.JsonAST.JObject
import org.json4s.native.Serialization._
class KafkaEventBus(kafkaServers: String)(implicit system: ActorSystem) extends EventBus with Logging {
implicit val materializer = ActorMaterializer()
implicit val format = DefaultFormats
val producerSettings = ProducerSettings(system, new ByteArraySerializer, new StringSerializer)
.withBootstrapServers(kafkaServers)
val consumerSettings = ConsumerSettings(system, new ByteArrayDeserializer, new StringDeserializer)
.withBootstrapServers(kafkaServers)
.withProperty(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG, "latest")
override def dispatcher(event: Event): Sink[JObject, NotUsed] = {
Flow[JObject]
.map(e => ProducerMessage.Message(new ProducerRecord[Array[Byte], String](event.id, write(e)), e))
.via(Producer.flow(producerSettings))
.map(result => {
val record = result.message.record
println(s"${record.topic}/${record.partition} ${result.offset}: ${record.value} (${result.message.passThrough}")
result
})
.recover({
case e: Throwable => e.printStackTrace()
})
.to(Sink.last)
}
override def subscribe(event: Event, props: SubscriptionProperties): Source[(Event, JObject), _] = {
val settings = props.toConsumerSettings(consumerSettings)
val subscription = Subscriptions.topics(event.id)
Consumer.atMostOnceSource(settings, subscription).map(message => (event, deserialize(message.value)))
}
def deserialize(data:String): JObject = {
read[JObject](data)
}
}
示例15: SparkStreamMain
//设置package包名称以及导入依赖的类
package io.bigfast.tracking.grpc
import io.bigfast.tracking.Event
import org.apache.kafka.common.serialization.ByteArrayDeserializer
import org.apache.spark.SparkConf
import org.apache.spark.streaming.kafka010.ConsumerStrategies.Subscribe
import org.apache.spark.streaming.kafka010.LocationStrategies.PreferConsistent
import org.apache.spark.streaming.kafka010._
import org.apache.spark.streaming.{Seconds, StreamingContext}
object SparkStreamMain {
def main(args:Array[String]) = {
val conf = new SparkConf().setMaster("spark://spark-master:7077").setAppName("SparkStreamMain")
val ssc = new StreamingContext(conf, Seconds(1))
val kafkaParams = Map[String, Object](
"bootstrap.servers" -> "kafka:9092",
"key.deserializer" -> classOf[ByteArrayDeserializer],
"value.deserializer" -> classOf[ByteArrayDeserializer],
"group.id" -> "my.spark.stream",
"auto.offset.reset" -> "earliest",
"enable.auto.commit" -> (false: java.lang.Boolean)
)
val topics = Array("event")
val stream = KafkaUtils.createDirectStream[Array[Byte], Array[Byte]](
ssc,
PreferConsistent,
Subscribe[Array[Byte], Array[Byte]](topics, kafkaParams)
)
stream.map(record => {
val id = if (record != null && record.key != null) new String(record.key) else "empty"
val event = Event.parseFrom(record.value)
println(s"id: ${id} event: ${event.toString}")
(id, event)
}).print()
ssc.start()
ssc.awaitTermination()
}
}