spark--transform算子--cogroup

import org.apache.spark.{SparkConf, SparkContext}

/**
  * Created by yz02 on 2017/6/16.
  */
object T_cogroup {
  System.setProperty("hadoop.home.dir","F:\\hadoop-2.6.5")

  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName("cogroup_test").setMaster("local")
    val sc = new SparkContext(conf)

    val rdd = sc.parallelize(List(("A",1), ("B", 2), ("C", 3)))
    val rdd1 = sc.parallelize(List(("A", 4)))
    val rdd2 = sc.parallelize(List(("A", 4), ("A", 5)))
    //在类型为（K,V)和（K,W)的数据集上调用，返回一个 (K, (Seq[V], Seq[W]))元组的数据集。
    val sum = rdd.cogroup(rdd1)
      .foreach(println)
    val sum1 = rdd.cogroup(rdd2)
      .foreach(println)
  }

}

运行结果：

(B,(CompactBuffer(2),CompactBuffer()))
(A,(CompactBuffer(1),CompactBuffer(4)))
(C,(CompactBuffer(3),CompactBuffer()))

(B,(CompactBuffer(2),CompactBuffer()))
(A,(CompactBuffer(1),CompactBuffer(4, 5)))
(C,(CompactBuffer(3),CompactBuffer()))