你可以用一个 Try monad并返回原始Dataframe，如果 withColumn 失败。

import scala.util.Try
val df2 = Try(df1.withColumn("new_calc", expr("Rpt2/Rpt3")))
  .getOrElse(df1)
  .alias("d1")

如果要重用，也可以将其定义为方法：

import org.apache.spark.sql.Column
def withColumnIfExist(df: DataFrame, colName: String, col: Column) =
  Try(df.withColumn("new_calc",expr("Rpt2/Rpt3"))).getOrElse(df)
val df3 = withColumnIfExist(df1, "new_calc", expr("Rpt2/Rpt3"))
  .alias("d1")

如果需要链接多个转换，可以将其与 transform :

val df4 = df1.alias("d1")
  .transform(withColumnIfExist(_, "new_calc", expr("Rpt2/Rpt3")))
  .transform(withColumnIfExist(_, "new_calc_2", expr("Rpt1/Rpt2")))

或者可以将其实现为 implicit class :

implicit class RichDataFrame(df: DataFrame) {
  def withColumnIfExist(colName: String, col: Column): DataFrame =
    Try(df.withColumn("new_calc", expr("Rpt2/Rpt3"))).getOrElse(df)
}
val df5 = df1.alias("d1")
  .withColumnIfExist("new_calc", expr("Rpt2/Rpt3"))
  .withColumnIfExist("new_calc_2", expr("Rpt1/Rpt2"))

自 withColumn 适用于所有数据集，如果需要 withColumnIfExist 要对所有数据集（包括dataframe）进行常规操作，请执行以下操作：

implicit class RichDataset[A](ds: Dataset[A]) {
  def withColumnIfExist(colName: String, col: Column): DataFrame =
    Try(ds.withColumn("new_calc", expr("Rpt2/Rpt3"))).getOrElse(ds.toDF)
}