spark.streaming.examples.NetworkWordCount.scala Maven / Gradle / Ivy

Go to download
package spark.streaming.examples

import spark.streaming.{Seconds, StreamingContext}
import spark.streaming.StreamingContext._

/**
 * Counts words in UTF8 encoded, '\n' delimited text received from the network every second.
 * Usage: NetworkWordCount   
 *    is the Spark master URL. In local mode,  should be 'local[n]' with n > 1.
 *    and  describe the TCP server that Spark Streaming would connect to receive data.
 *
 * To run this on your local machine, you need to first run a Netcat server
 *    `$ nc -lk 9999`
 * and then run the example
 *    `$ ./run spark.streaming.examples.NetworkWordCount local[2] localhost 9999`
 */
object NetworkWordCount {
  def main(args: Array[String]) {
    if (args.length < 3) {
      System.err.println("Usage: NetworkWordCount   \n" +
        "In local mode,  should be 'local[n]' with n > 1")
      System.exit(1)
    }

    // Create the context with a 1 second batch size
    val ssc = new StreamingContext(args(0), "NetworkWordCount", Seconds(1),
      System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR")))

    // Create a NetworkInputDStream on target ip:port and count the
    // words in input stream of \n delimited test (eg. generated by 'nc') 
    val lines = ssc.socketTextStream(args(1), args(2).toInt)
    val words = lines.flatMap(_.split(" "))
    val wordCounts = words.map(x => (x, 1)).reduceByKey(_ + _)
    wordCounts.print()
    ssc.start()
  }
}