spark streaming + kafka整合二（Direct Approach (No Receiver)）

Direct Approach消费模型代码实战模拟：

模拟一个消费者–Direct

/**
  * Consumers messages from one or more topics in Kafka and does wordcount.
  * Usage: DirectKafkaWordCount <brokers> <topics>
  *   <brokers> is a list of one or more Kafka brokers
  *   <topics> is a list of one or more kafka topics to consume from
  *
  * Example:
  *    $ bin/run-example streaming.DirectKafkaWordCount broker1-host:port,broker2-host:port \
  *    topic1,topic2
  */
object DirectKafkaWordCount {
  def main(args: Array[String]) {
    if (args.length < 2) {
      System.err.println(s"""
                            |Usage: DirectKafkaWordCount <brokers> <topics>
                            |  <brokers> is a list of one or more Kafka brokers
                            |  <topics> is a list of one or more kafka topics to consume from
                            |
        """.stripMargin)
      System.exit(1)
    }
    
    val Array(brokers, topics) = args

    // Create context with 2 second batch interval
    val sparkConf = new SparkConf().setAppName("DirectKafkaWordCount").setMaster("local[2]")
    val ssc = new StreamingContext(sparkConf, Seconds(2))

    // Create direct kafka stream with brokers and topics
    val topicsSet = topics.split(",").toSet
    val kafkaParams = Map[String, String]("metadata.broker.list" -> brokers)
    val messages = KafkaUtils.createDirectStream[String, String, StringDecoder, StringDecoder](
      ssc, kafkaParams, topicsSet)

    // Get the lines, split them into words, count the words and print
    val lines = messages.map(_._2)
    val words = lines.flatMap(_.split(" "))
    val wordCounts = words.map(x => (x, 1L)).reduceByKey(_ + _)
    wordCounts.print()

    // Start the computation
    ssc.start()
    ssc.awaitTermination()
  }
}