如何使用Spark检查两个HDFS数据集是否相等？

import org.apache.spark.SparkConf
import org.apache.spark.SparkContext
import org.apache.spark.sql.SparkSession

val spark = SparkSession.builder()
  .appName("Data Comparison")
  .master("local")
  .getOrCreate()

val dataset1 = spark.read.format("csv").load("hdfs://path/to/dataset1.csv")
val dataset2 = spark.read.format("csv").load("hdfs://path/to/dataset2.csv")

val diff = dataset1.except(dataset2).union(dataset2.except(dataset1))

if (diff.isEmpty) {
  println("The datasets are equal.")
} else {
  println("The datasets are not equal.")
  diff.show()
}