Scala StringDeserializer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.knoldus.streaming.kafka

import org.apache.kafka.clients.consumer.ConsumerRecord
import org.apache.kafka.common.serialization.StringDeserializer
import org.apache.spark.streaming.StreamingContext
import org.apache.spark.streaming.dstream.InputDStream
import org.apache.spark.streaming.kafka010.{ConsumerStrategies, KafkaUtils, LocationStrategies}


object KafkaUtility {

  //TODO It should read from config
  private val kafkaParams = Map(
    "bootstrap.servers" -> "localhost:9092",
    "key.deserializer" -> classOf[StringDeserializer],
    "value.deserializer" -> classOf[StringDeserializer],
    "auto.offset.reset" -> "earliest",
    "group.id" -> "tweet-consumer"
  )

  private val preferredHosts = LocationStrategies.PreferConsistent


  def createDStreamFromKafka(ssc: StreamingContext, topics: List[String]): InputDStream[ConsumerRecord[String, String]] =
    KafkaUtils.createDirectStream[String, String](
      ssc,
      preferredHosts,
      ConsumerStrategies.Subscribe[String, String](topics.distinct, kafkaParams)
    )

} 

//设置package包名称以及导入依赖的类
import org.apache.spark.streaming.kafka010.KafkaUtils
import org.apache.kafka.common.serialization.StringDeserializer
import org.apache.spark.SparkConf
import org.apache.spark.streaming.{Seconds, StreamingContext}
import org.apache.spark.streaming.kafka010.LocationStrategies.PreferConsistent
import org.apache.spark.streaming.kafka010.ConsumerStrategies.Subscribe
import org.apache.spark.mllib.classification.SVMModel
import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.sql.SparkSession

object Consumer {

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

    val kafkaParams = Map[String, Object](
      "bootstrap.servers" -> "localhost:9092",
      "key.deserializer" -> classOf[StringDeserializer],
      "value.deserializer" -> classOf[StringDeserializer],
      "group.id" -> "use_a_separate_group_id_for_each_stream",
      "auto.offset.reset" -> "latest",
      "enable.auto.commit" -> (false: java.lang.Boolean)
    )

    val topics = Array("streaming")

    val sparkConf = new SparkConf().setMaster("local[8]").setAppName("KafkaTest")
    val streamingContext = new StreamingContext(sparkConf, Seconds(1))
    // Create a input direct stream
    val kafkaStream = KafkaUtils.createDirectStream[String, String](
      streamingContext,
      PreferConsistent,
      Subscribe[String, String](topics, kafkaParams)
    )

    val sc = SparkSession.builder().master("local[8]").appName("KafkaTest").getOrCreate()
    val model = SVMModel.load(sc.sparkContext, "/home/xiaoyu/model")
    val result = kafkaStream.map(record => (record.key, record.value))
    result.foreachRDD(
      patient => {
        patient.collect().toBuffer.foreach(
          (x: (Any, String)) => {
            val features = x._2.split(',').map(x => x.toDouble).tail
            println(model.predict(Vectors.dense(features)))

          }
        )
      }
    )

    streamingContext.start()
    streamingContext.awaitTermination()

  }
} 

//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.bencassedy.readykafka.producer

import java.util.Properties
import java.util.concurrent.TimeUnit

import org.apache.kafka.clients.producer.{ProducerRecord, KafkaProducer}
import org.apache.kafka.common.serialization.{StringSerializer, StringDeserializer}


class ReadyKafkaProducer {
  case class KafkaProducerConfigs(brokerList: String = "127.0.0.1:9092") {
    val properties = new Properties()
    properties.put("bootstrap.servers", brokerList)
    properties.put("key.serializer", classOf[StringSerializer])
    properties.put("value.serializer", classOf[StringSerializer])
//    properties.put("serializer.class", classOf[StringDeserializer])
//    properties.put("batch.size", 16384)
//    properties.put("linger.ms", 1)
//    properties.put("buffer.memory", 33554432)
  }

  val producer = new KafkaProducer[String, String](KafkaProducerConfigs().properties)

  def produce(topic: String, messages: Iterable[String]): Unit = {
    messages.foreach { m =>
      producer.send(new ProducerRecord[String, String](topic, m))
    }
    producer.close(100L, TimeUnit.MILLISECONDS)
  }
} 

//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 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
package serialisation

import java.util

import model.Event
import org.apache.kafka.common.serialization.{Deserializer, StringDeserializer}
import org.json4s.native.Serialization
import org.json4s.native.Serialization.read
import org.json4s.{Formats, NoTypeHints}

class EventDeserialiser extends Deserializer[Event] {

  implicit val formats: Formats = Serialization.formats(NoTypeHints)

  val stringDeserialiser = new StringDeserializer

  override def configure(configs: util.Map[String, _], isKey: Boolean): Unit = {
    stringDeserialiser.configure(configs, isKey)
  }

  override def deserialize(topic: String, data: Array[Byte]): Event = {
    val stringValue = stringDeserialiser.deserialize(topic, data)
    read[Event](stringValue)
  }

  override def close(): Unit = {
    stringDeserialiser.close()
  }
} 

//设置package包名称以及导入依赖的类
package com.blazedb.spark


import org.apache.kafka.clients.consumer.ConsumerRecord
import org.apache.kafka.common.serialization.StringDeserializer
import org.apache.spark.sql.SparkSession
import org.apache.spark.streaming.{Duration, StreamingContext}
import org.apache.spark.streaming.kafka010._
import org.apache.spark.streaming.kafka010.LocationStrategies.PreferConsistent
import org.apache.spark.streaming.kafka010.ConsumerStrategies.Subscribe

object KafkaTest {
  val kafkaParams = Map[String, Object](
    "bootstrap.servers" -> "localhost:9092,anotherhost:9092",
    "key.deserializer" -> classOf[StringDeserializer],
    "value.deserializer" -> classOf[StringDeserializer],
    "group.id" -> "use_a_separate_group_id_for_each_stream",
    "auto.offset.reset" -> "latest",
    "enable.auto.commit" -> (false: java.lang.Boolean)
  )

  val sess = SparkSession.builder.master("local").getOrCreate
  val sc = sess.sparkContext
  val ssc = new StreamingContext(sc, Duration(1000L))
  val topics = Array("topicA", "topicB")
  val stream = KafkaUtils.createDirectStream[String, String](
    ssc,
    PreferConsistent,
    Subscribe[String, String](topics, kafkaParams)
  )

  stream.map(record => (record.key, record.value))

} 

//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.example

import akka.actor.Actor
import akka.event.LoggingAdapter
import cakesolutions.kafka.akka.KafkaConsumerActor.Subscribe
import cakesolutions.kafka.akka.{ConsumerRecords, KafkaConsumerActor, KafkaProducerActor, ProducerRecords}
import cakesolutions.kafka.{KafkaProducer, KafkaProducerRecord}
import com.example.PingPongProtocol.PingPongMessage
import com.typesafe.config.Config
import org.apache.kafka.common.serialization.{StringDeserializer, StringSerializer}

import scala.util.Random
trait KafkaConfig{
  def config:Config
  def log: LoggingAdapter
  def randomString(len: Int= 5): String = Random.alphanumeric.take(len).mkString("")
}

trait PingPongConsumer extends KafkaConfig{
  this: Actor =>

  //for pattern matching in our receive method
  val msgExtractor = ConsumerRecords.extractor[java.lang.String, PingPongMessage]

  val kafkaConsumerActor = context.actorOf(
    KafkaConsumerActor.props(config,new StringDeserializer(), new JsonDeserializer[PingPongMessage], self),
    "PingKafkaConsumerActor"
  )

  def subscribe(topics: List[String]) =
     kafkaConsumerActor ! Subscribe.AutoPartition(topics)

}

trait PingPongProducer  extends KafkaConfig{
  this: Actor =>

  val kafkaProducerConf = KafkaProducer.Conf(
    bootstrapServers = config.getString("bootstrap.servers"),
    keySerializer = new StringSerializer(),
    valueSerializer = new JsonSerializer[PingPongMessage])


  val kafkaProducerActor = context.actorOf(KafkaProducerActor.props( kafkaProducerConf))

  def submitMsg(topics: List[String], msg: PingPongMessage) = {
    log.info(s"Placing $msg on ${topics.mkString(",")}")
    topics.foreach(topic => kafkaProducerActor ! ProducerRecords(List(KafkaProducerRecord(topic, randomString(3), msg))))
  }
} 

//设置package包名称以及导入依赖的类
package tech.elephant.spark

import grizzled.slf4j.Logger
import org.apache.kafka.common.serialization.{ByteArrayDeserializer, StringDeserializer}
import org.apache.spark.streaming.kafka010.ConsumerStrategies._
import org.apache.spark.streaming.kafka010.KafkaUtils
import org.apache.spark.streaming.kafka010.LocationStrategies._
import org.apache.spark.streaming.{Seconds, StreamingContext}
import org.apache.spark.sql.types.{StringType, StructField, StructType}
import org.apache.spark.sql.{DataFrame, Row, SQLContext, SparkSession}

object SimplestStreaming {
  val logger = Logger[this.type]

  def main(args: Array[String]): Unit = {
    val spark = SparkSession
      .builder()
      .appName("Simplest streaming (spark 2.0) from Kafka SSL")
      .enableHiveSupport()
      .getOrCreate()
    val sparkContext = spark.sparkContext

    val streamingContext = new StreamingContext(sparkContext, Seconds(10))
    // expects jaas.conf, appropriate keytab, and kafka.client.truststore.jks passed in as part of spark-submit
    val kafkaParams = Map[String, Object](
      "bootstrap.servers" -> "<fqdn of kafka broker>:9092",
      "key.deserializer" -> classOf[StringDeserializer],
      "value.deserializer" -> classOf[StringDeserializer],
      "group.id" -> "test1",
      "auto.offset.reset" -> "latest",
      "enable.auto.commit" -> (false: java.lang.Boolean),
      "security.protocol" -> "SASL_SSL",
      "ssl.truststore.location" -> "./kafka.client.truststore.jks",
      "ssl.truststore.password" -> "change-me-to-something-safe"
    )
    val topic = Set("simplest")

    val stream = KafkaUtils.createDirectStream[String, String](
      streamingContext,
      PreferConsistent,
      Subscribe[String, String](topic, kafkaParams)
    )

    stream.foreachRDD { rdd =>
      // Get the singleton instance of SparkSession
      val spark = SparkSession.builder.config(rdd.sparkContext.getConf).getOrCreate()
      import spark.implicits._

      val df = rdd.map( consumerRecord => {
        consumerRecord.value()
      }).toDF()

      df.show()
    }

    // start the computation
    streamingContext.start()
    streamingContext.awaitTermination()
  }
} 

//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)
  }

}