cloud-fan commented on a change in pull request #27937: [SPARK-30127][SQL]
Support case class parameter for typed Scala UDF
URL: https://github.com/apache/spark/pull/27937#discussion_r395492216
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/ScalaUDF.scala
##########
@@ -48,25 +46,87 @@ case class ScalaUDF(
function: AnyRef,
dataType: DataType,
children: Seq[Expression],
- inputPrimitives: Seq[Boolean],
- inputTypes: Seq[AbstractDataType] = Nil,
+ inputEncoders: Seq[Option[ExpressionEncoder[_]]] = Nil,
udfName: Option[String] = None,
nullable: Boolean = true,
udfDeterministic: Boolean = true)
extends Expression with NonSQLExpression with UserDefinedExpression {
override lazy val deterministic: Boolean = udfDeterministic &&
children.forall(_.deterministic)
+ private lazy val resolvedEnc = mutable.HashMap[Int, ExpressionEncoder[_]]()
+
override def toString: String =
s"${udfName.getOrElse("UDF")}(${children.mkString(", ")})"
+ /**
+ * The analyzer should be aware of Scala primitive types so as to make the
+ * UDF return null if there is any null input value of these types. On the
+ * other hand, Java UDFs can only have boxed types, thus this parameter will
+ * always be all false.
+ */
+ def inputPrimitives: Seq[Boolean] = {
Review comment:
I think need to return `children.map(_ => false)` if `inputEncoders` is
empty.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
