join

产生shuffle.

作用：在类型为(K,V)和(K,W)的RDD上调用，返回一个相同key对应的所有元素对在一起的(K,(V,W))的RDD

源码：

  def join[W](other: RDD[(K, W)]): RDD[(K, (V, W))] = self.withScope {
    join(other, defaultPartitioner(self, other))
  }

作用：在类型为(K,V)和(K,W)的RDD上调用，返回一个相同key对应的所有元素对在一起的(K,(V,W))的RDD

package com.atguigu

import org.apache.spark.rdd.RDD
import org.apache.spark.{HashPartitioner, Partitioner, SparkConf, SparkContext}

object Trans {
  def main(args: Array[String]): Unit = {

    val conf: SparkConf = new SparkConf().setMaster("local[*]").setAppName("Spark01_Partition")
    //构建spark上下文对象
    val sc = new SparkContext(conf)

    val rdd: RDD[(Int, String)] = sc.makeRDD(Array((3,"aa"),(6,"bb"),(1,"cc"),(4,"dd")))
    val rdd1: RDD[(Int, String)] = sc.makeRDD(Array((3,"aa"),(6,"bb"),(1,"cc")))
    val rdd2: RDD[(Int, (String, String))] = rdd.join(rdd1)
    rdd2.foreach(println)

    sc.stop()
  }
}

(1,(cc,cc))
(3,(aa,aa))
(6,(bb,bb))

结论：key匹配上才会join。