spark--transform算子--join

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

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

  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName("join_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)))
    //join方法为(K,V)和(K,W)的数据集调用，返回相同的K所组成的数据集
    val sum = rdd.join(rdd1)
      .foreach(println)
    val sum1 = rdd.join(rdd2)
      .foreach(println)
  }
}

运行结果：

(A,(1,4))

(A,(1,4))
(A,(1,5))