Scala KafkaUtils类代码示例

//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.test.spark

import org.apache.spark.SparkConf
import org.apache.spark.streaming.StreamingContext
import org.apache.spark.streaming.Seconds
import org.apache.spark.streaming.kafka010.ConsumerStrategies
import org.apache.spark.streaming.kafka010.LocationStrategies
import org.apache.spark.streaming.kafka010.KafkaUtils

object StatefulWordcount extends App {
  val conf = new SparkConf().setAppName("Stateful Wordcount").setMaster("local[2]")
  val ssc = new StreamingContext(conf, Seconds(10))
  val kafkaParams = Map[String, String]("bootstrap.servers" -> "localhost:9092", "key.deserializer" -> "org.apache.kafka.common.serialization.StringDeserializer", "value.deserializer" -> "org.apache.kafka.common.serialization.StringDeserializer", "group.id" -> "mygroup", "auto.offset.reset" -> "earliest")
  val topics = Set("widas")
  val inputKafkaStream = KafkaUtils.createDirectStream(ssc, LocationStrategies.PreferConsistent, ConsumerStrategies.Subscribe[String, String](topics, kafkaParams))
  val words = inputKafkaStream.transform { rdd =>
    rdd.flatMap(record => (record.value().toString.split(" ")))
  }
  val wordpairs = words.map(word => (word, 1))
  ssc.checkpoint("/Users/nagainelu/bigdata/jobs/WordCount_checkpoint")
  val updateFunc = (values: Seq[Int], state: Option[Int]) => {
    val currentCount = values.foldLeft(0)(_ + _)
    val previousCount = state.getOrElse(0)
    Some(currentCount + previousCount)
  }
  val wordCounts = wordpairs.reduceByKey(_ + _).updateStateByKey(updateFunc)
  wordCounts.print()
  ssc.start()
  ssc.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)
  }

}