sparkStreaming整合kafka生产者 实现单词统计

开启zookeeper，kafka，生产者，
$ bin/kafka-console-producer.sh --broker-list ip:9092 --topic 主题名

    //创建sparkConf
    val conf: SparkConf = new SparkConf().setAppName("kafka_receiver").setMaster("local[4]")
    //创建sparkcontext
    val sc: SparkContext = new SparkContext(conf)
    //设置日志输出级别
    sc.setLogLevel("WARN")

    //创建StreamingContext
    val ssc: StreamingContext = new StreamingContext(sc,Seconds(5))
    //检查点
    ssc.checkpoint("./kafka-receiver")

    //receiver方式：一个接收线程---》一个topic中的分区
   /* val stream = (1 to 3).map(x => {
      KafkaUtils.createStream(ssc,"ip:2181","group01",Map("spark_kafka1" -> 1))
    })
    val inputStream = ssc.union(stream)*/

    val inputstream = KafkaUtils.createStream(ssc, "虚拟机ip:2181", "group_01", Map("检测的主题" -> 1))

    val result = inputstream.map(tuple => tuple._2).flatMap(_.split(" ")).map((_,1)).updateStateByKey(updateFunc)
    result.print()

    ssc.start()
    ssc.awaitTermination()
  }

  def updateFunc(aa:Seq[Int],bb:Option[Int]): Option[Int] ={
    Some(aa.sum + bb.getOrElse(0))
  }