SparkRDD之cartesian

计算两个RDD之间的笛卡尔积（即第一个RDD的每个项与第二个RDD的每个项连接）并将它们作为新的RDD返回。 （警告：使用此功能时要小心。！内存消耗很快就会成为问题！）

java示例如下：

package com.cb.spark.sparkrdd;

import java.util.Arrays;

import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;

public class CartesianExample {
	public static void main(String[] args) {
		SparkConf conf = new SparkConf().setAppName("Cartesian").setMaster("local");
		JavaSparkContext jsc = new JavaSparkContext(conf);
		JavaRDD<Integer> javaRDD = jsc.parallelize(Arrays.asList(1, 2, 3, 4, 5));
		JavaRDD<Integer> javaRDD1 = jsc.parallelize(Arrays.asList(6, 7, 8, 9, 10));
		JavaPairRDD<Integer, Integer> cartesianRDD = javaRDD.cartesian(javaRDD1);
		cartesianRDD.foreach(x->System.out.println(x));
		
		jsc.stop();
	}
}

scala示例如下：

package com.cb.spark.core

import org.apache.spark.SparkConf
import org.apache.spark.SparkContext

object Cartesian {
  def main(args: Array[String]): Unit = {
    val conf = new SparkConf()
      .setAppName("Aggregate")
      .setMaster("local")
    val sc = new SparkContext(conf)
    val z = sc.parallelize(List("a", "b", "c", "d", "e", "f"), 2)
    val y = sc.parallelize(List("1", "2", "3"))
    val zy = z.cartesian(y);

    val x = sc.parallelize(List(1, 2, 3))
    val zx = z.cartesian(x)
    zy.foreach(println)
    zx.foreach(print)
    sc.stop()
  }
}