合并两个数据集。两个数据集的类型要一致。
union 生成RDD的分区个数是父RDD的分区数之和

  1. java实现
package transformations;

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

import java.util.Arrays;

/**
 * @Author yqq
 * @Date 2021/12/09 17:10
 * @Version 1.0
 */
public class UnionTest {
    public static void main(String[] args) {
        JavaSparkContext context = new JavaSparkContext(
                new SparkConf()
                        .setAppName("union")
                        .setMaster("local")
        );
        context.setLogLevel("Error");
        JavaRDD<String> rdd = context.parallelize(Arrays.asList("a", "b", "c", "e", "f"),2);
        JavaRDD<String> rdd1 = context.parallelize(Arrays.asList("a", "b", "f", "h", "g"),3);
        JavaRDD<String> union = rdd.union(rdd1);
        System.out.println("rdd partition length = "+rdd.getNumPartitions());
        System.out.println("rdd1 partition length = "+rdd1.getNumPartitions());
        System.out.println("union partition length = "+union.getNumPartitions());
        union.foreach(e-> System.out.print(e+"\t"));
    }
}

Spark Transformation算子-＞union_apache
2. scala实现

package transformation

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

/**
 * @Author yqq
 * @Date 2021/12/09 17:33
 * @Version 1.0
 */
object UnionTest {
  def main(args: Array[String]): Unit = {
    val context = new SparkContext(
      new SparkConf()
        .setMaster("local")
        .setAppName("union")
    )
    context.setLogLevel("Error")
    val rdd: RDD[String] = context.makeRDD(Array[String]("a", "b", "c", "d", "e"))
    val rdd1: RDD[String] = context.parallelize(Array[String]("a", "b", "f", "g", "h"))
    val value: RDD[String] = rdd.union(rdd1)
    value.foreach(print)

  }
}

Spark Transformation算子-＞union_apache_02