使用 when+otherwise 这种情况下的声明是非常有效的Spark。

//sample data
df.show()
//+-----+-----+------+------+
//| name| type| item1| item2|
//+-----+-----+------+------+
//|apple|fruit|apple1|apple2|
//|beans| vege|beans1|beans2|
//| beef| meat| beef1| beef2|
//| kiwi|fruit| kiwi1| kiwi2|
//| pork| meat| pork1| pork2|
//+-----+-----+------+------+
//using isin function
df.withColumn("prop",when((col("type").isin(Seq("vege","fruit"):_*)),col("item1")).when(col("type") === "meat",col("item2")).otherwise(col("type"))).show()
df.withColumn("prop",when((col("type") === "fruit") ||(col("type") === "vege"),col("item1")).when(col("type") === "meat",col("item2")).
otherwise(col("type"))).
show()
//+-----+-----+------+------+------+
//| name| type| item1| item2|  prop|
//+-----+-----+------+------+------+
//|apple|fruit|apple1|apple2|apple1|
//|beans| vege|beans1|beans2|beans1|
//| beef| meat| beef1| beef2| beef2|
//| kiwi|fruit| kiwi1| kiwi2| kiwi1|
//| pork| meat| pork1| pork2| pork2|
//+-----+-----+------+------+------+

它可以通过链接来完成 when 以及 otherwise 如下所示

import org.apache.spark.sql.functions._
object WhenThen {
  def main(args: Array[String]): Unit = {
    val spark = Constant.getSparkSess
    import spark.implicits._
    val df = List(("apple","fruit","apple1","apple2"),
      ("beans","vege","beans1","beans2"),
      ("beef","meat","beef1","beans2"),
      ("kiwi","fruit","kiwi1","beef2"),
      ("pork","meat","pork1","pork2")
    ).toDF("name","type","item1","item2" )
   df.withColumn("prop",
      when($"type" === "fruit", $"item1").otherwise(
        when($"type" === "vege", $"item1").otherwise(
          when($"type" === "meat", $"item2").otherwise("")
        )
      )).show()
  }
}