Spark Transformation算子-＞subtract

取两个数据集的差集，结果 RDD 的分区数与 subtract 前面的 RDD 的 分区数一致。

1. java

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;


public class SubtractTest {
    public static void main(String[] args) {
        JavaSparkContext context = new JavaSparkContext(
                new SparkConf()
                        .setMaster("local")
                        .setAppName("subtract")
        );
        context.setLogLevel("Error");
        JavaRDD rdd = context.parallelize(Arrays.asList("a", "b", "c", "e", "f"),2);
        JavaRDD rdd1 = context.parallelize(Arrays.asList("a", "b", "g", "h", "f"),3);
        JavaRDD subtract = rdd.subtract(rdd1);
        System.out.println("rdd partition length = "+rdd.getNumPartitions());
        System.out.println("rdd1 partition length = "+rdd1.getNumPartitions());
        System.out.println("subtract partition length = "+subtract.getNumPartitions());
        subtract.foreach(e-> System.out.print(e+"t"));
    }
}

2. scala

package transformation

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


object SubtractTest {
  def main(args: Array[String]): Unit = {
    val context = new SparkContext(
      new SparkConf()
        .setMaster("local")
        .setAppName("subtract")
    )
    context.setLogLevel("Error")
    val rdd: RDD[String] = context.parallelize(Array[String]("a", "b", "c", "e", "f"))
    val rdd1: RDD[String] = context.parallelize(Array[String]("a", "b", "g", "h", "f"))
    val value: RDD[String] = rdd.subtract(rdd1)
    value.foreach(print)
  }
}