Join

package cn.kgc.day0819.test02

import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.streaming.{Seconds, StreamingContext}

object JoinDemo extends App {
val conf: SparkConf = new SparkConf().setMaster(“local[*]”).setAppName(“hdfsDemo”)
val ssc = new StreamingContext(conf,Seconds(5))
val sc: SparkContext = ssc.sparkContext
val input1 = List((1, true), (2, false), (3, false), (4, true), (5, false))
val input2 = List((1, false), (2, false), (3, true), (4, true), (5, true))

val rdd1 = sc.parallelize(input1)
val rdd2 = sc.parallelize(input2)

import scala.collection.mutable
val ds1 = ssc.queueStream[(Int, Boolean)](mutable.Queue(rdd1))
val ds2 = ssc.queueStream[(Int, Boolean)](mutable.Queue(rdd2))

val ds = ds1.join(ds2)
ds.print()
ssc.start()
ssc.awaitTerminationOrTimeout(5000)

}