sparkStreaming整合flume实现单词统计 poll模式

**

• sparkStreaming整合flume 拉模式Poll
• spark-streaming-flume-sink_2.11-2.0.2.jar放入到flume的lib目录下
  配置文件 flume-poll.conf
  a1.sources = r1
  a1.sinks = k1
  a1.channels = c1
  #source
  a1.sources.r1.channels = c1
  a1.sources.r1.type = spooldir
  a1.sources.r1.spoolDir = /opt/flume-1.7.0/data
  a1.sources.r1.fileHeader = true
  #channel
  a1.channels.c1.type =memory
  a1.channels.c1.capacity = 20000
  a1.channels.c1.transactionCapacity=5000
  #sinks
  a1.sinks.k1.channel = c1
  a1.sinks.k1.type = org.apache.spark.streaming.flume.sink.SparkSink
  a1.sinks.k1.hostname=虚拟机ip

a1.sinks.k1.port = 8888
a1.sinks.k1.batchSize= 2000

开启flume bin/flume-ng agent -n a1 -c /opt/flume-1.7.0/conf/ -f /opflume-1.7.0/conf/flume-poll.conf -Dflume.root.logger=INFO.console
*/

object SparkStreamingFlumePoll {
  //newValues 表示当前批次汇总成的(word,1)中相同单词的所有的1
  //runningCount 历史的所有相同key的value总和
  def updateFunction(newValues: Seq[Int], runningCount: Option[Int]): Option[Int] = {
    val newCount =runningCount.getOrElse(0)+newValues.sum
    Some(newCount)
  }


  def main(args: Array[String]): Unit = {
    //配置sparkConf参数
    val sparkConf = new SparkConf().setAppName("SparkStreaming_Flume_Poll").setMaster("local[2]")
    //构建sparkContext对象
    val sc = new SparkContext(sparkConf)
    sc.setLogLevel("WARN")
    //构建StreamingContext对象，每个批处理的时间间隔
    val scc = new StreamingContext(sc, Seconds(5))

    //设置checkpoint
    scc.checkpoint("./")
    //设置flume的地址，可以设置多台
    val address = Seq(new InetSocketAddress("ip地址",8888))
    // 从flume中拉取数据
    val flumeStream = FlumeUtils.createPollingStream(scc,address,StorageLevel.MEMORY_AND_DISK)

    //获取flume中数据，数据存在event的body中，转化为String
    val lineStream = flumeStream.map(x=>new String(x.event.getBody.array()))
    //实现单词汇总
    val result = lineStream.flatMap(_.split(" ")).map((_,1)).updateStateByKey(updateFunction)

    result.print()
    scc.start()
    scc.awaitTermination()
  }

}