利用sparkStreaming接受kafak中的消息，采用的是低层次Api-- direct （kafka 10版本）

package com.spark.streaming

import org.apache.kafka.common.serialization.StringDeserializer
import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.streaming.{Seconds, StreamingContext}


//todo:利用sparkStreaming接受kafak中的消息，采用的是低层次Api-- direct
object SparkStreamingKafkaDirectCheckpoint {

    System.setProperty("hadoop.home.dir", "d://software/hadoop-2.9.2")
  def updateFunc(a: Seq[Int], b: Option[Int]): Option[Int] = {
    Some(a.sum + b.getOrElse(0))
  }

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

    val checkpointPath = "./"

    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_direct_checkpoint")
      .setMaster("local[4]")

    //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、kafka的参数配置
    val kafkaParams = Map(
      "bootstrap.servers" -> "hadoop-senior.test.com:9092",
      "key.deserializer" -> classOf[StringDeserializer],
      "value.deserializer" -> classOf[StringDeserializer],
      "group.id" -> "kafka-direct01",
      "auto.offset.reset" -> "latest",
      "enable.auto.commit" -> "false"
    )


    //todo:5、定义一个topics ，是一个集合，可以存放多个topic
    val topics = Set("kafka_spark")

    //todo:6、利用KafkaUtils.createDirectStream构建Dstream
    val kafkaTopicDS = KafkaUtils.createDirectStream[String, String](
      ssc,
      PreferConsistent,
      Subscribe[String, String](topics, kafkaParams)
    )

    //todo:7、获取kafka中topic的数据
    val kafkaData = kafkaTopicDS.map(x => x.value)

    //todo:8、切分每一行，每个单词记为1
    val wordAndOne = kafkaData.flatMap(_.split(" ")).map((_,1))

    //todo:9、相同单词出现次数累加
    val result = wordAndOne.updateStateByKey(updateFunc)

    kafkaTopicDS.foreachRDD { rdd =>
      val offsetRanges = rdd.asInstanceOf[HasOffsetRanges].offsetRanges

      // some time later, after outputs have completed
      kafkaTopicDS.asInstanceOf[CanCommitOffsets].commitAsync(offsetRanges)
    }
    //todo:打印
    result.print()
    ssc
  }

}

配置版本：

<dependency>
    <groupId>org.apache.spark</groupId>
    <artifactId>spark-streaming-kafka-0-10_2.11</artifactId>
    <version>2.4.5</version>
</dependency>