利用sparkStreaming接受kafka中的数据实现单词计数----采用receivers

最新推荐文章于 2024-05-03 17:08:17 发布

star5610

最新推荐文章于 2024-05-03 17:08:17 发布

阅读量213

点赞数

分类专栏： Spark 文章标签： spark

本文链接：https://blog.csdn.net/star5610/article/details/106580062

版权

Spark 专栏收录该内容

31 篇文章 1 订阅

订阅专栏

package com.spark.streaming

import org.apache.spark.streaming.dstream.DStream
import org.apache.spark.streaming.kafka.KafkaUtils
import org.apache.spark.streaming.{Seconds, StreamingContext}
import org.apache.spark.{SparkConf, SparkContext}

import scala.collection.immutable

//todo:利用sparkStreaming接受kafka中的数据实现单词计数----采用receivers
object SparkStreamingKafkaReceiverCheckpoint {

  System.setProperty("hadoop.home.dir", "d://soft/hadoop/hadoop-2.7.3")
  def updateFunc(a:Seq[Int], b:Option[Int]) :Option[Int] ={
    Some(a.sum+b.getOrElse(0))
  }
  def main(args: Array[String]): Unit = {
    val checkpointPath = "./kafka-receiver"

    val ssc = StreamingContext.getOrCreate(checkpointPath, () => {
      createFunc(checkpointPath)
    })
    ssc.start()
    ssc.awaitTermination()
  }
  def createFunc(checkpointPath:String): StreamingContext = {

    //todo:1、创建sparkConf
    val sparkConf: SparkConf = new SparkConf()
      .setAppName("SparkStreamingKafka_Receiver_checkpoint")
      .setMaster("local[4]")
      //todo:开启wal预写日志
      .set("spark.streaming.receiver.writeAheadLog.enable","true")
    //todo:2、创建sparkContext
    val sc = new SparkContext(sparkConf)

    sc.setLogLevel("WARN")

    //todo:3、创建StreamingContext
    val ssc = new StreamingContext(sc,Seconds(5))
    ssc.checkpoint(checkpointPath)
    //todo:4、指定zkServer
    val zkServer="star.com:2181"

    //todo:5、指定groupId
    val groupId="spark-kafka-receiver01"

    //todo:6、指定topics 这个可以利用一个消费者组来消费多个topic,
    //(topic_name -> numPartitions)  指定topic消费的线程数
    val topics=Map("kafka_spark"->1)

    //todo:7、并行运行更多的接收器读取kafak topic中的数据，这里设置3个
    val resultDStream = (1 to 3).map(x => {
      //todo:8、通过使用KafkaUtils的createStream接受kafka topic中的数据，生成DStream
      val kafkaDataDStream = KafkaUtils.createStream(ssc, zkServer, groupId, topics).map(x => x._2)
      kafkaDataDStream
    }
    )
    //todo:利用StreamContext将所有的DStream组合在一起
    val kafkaDStream = ssc.union(resultDStream)

    //todo:8、获取kafka中topic的内容

    //todo:9、切分每一行。每个单词记为1
    val wordAndOne = kafkaDStream.flatMap(_.split(" ")).map((_,1))

    //todo:10、相同单词出现的次数累加
    val result = wordAndOne.updateStateByKey(updateFunc)

    //todo:打印
    result.print()
    ssc

  }

}

配置信息：

<dependency>
    <groupId>org.apache.spark</groupId>
    <artifactId>spark-streaming-kafka-0-8_2.11</artifactId>
    <version>2.4.5</version>
</dependency>