MaxGekk commented on code in PR #48598:
URL: https://github.com/apache/spark/pull/48598#discussion_r1812765147
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/predicates.scala:
##########
@@ -767,6 +777,35 @@ case class InSet(child: Expression, hset: Set[Any])
extends UnaryExpression with
override protected def withNewChildInternal(newChild: Expression): InSet =
copy(child = newChild)
}
+object InSet {
+ class LCaseSet(inputSet: Set[Any]) extends immutable.Set[Any] with
Serializable {
+ private val strSet = inputSet.map { s =>
+ if (s == null) null
+ else
CollationAwareUTF8String.lowerCaseCodePoints(s.asInstanceOf[UTF8String])
+ }
+ override def incl(elem: Any): Set[Any] = inputSet.incl(elem)
+ override def excl(elem: Any): Set[Any] = inputSet.excl(elem)
+ override def iterator: Iterator[Any] = inputSet.iterator
+ override def contains(elem: Any): Boolean = {
+ assert(elem != null, "InSet guarantees non-null input")
+
strSet.contains(CollationAwareUTF8String.lowerCaseCodePoints(elem.asInstanceOf[UTF8String]))
+ }
+ }
+ class CollationSet(inputSet: Set[Any], collationId: Int)
+ extends immutable.Set[Any] with Serializable {
+ override def incl(elem: Any): Set[Any] = inputSet.incl(elem)
+ override def excl(elem: Any): Set[Any] = inputSet.excl(elem)
+ override def iterator: Iterator[Any] = inputSet.iterator
+ override def contains(elem: Any): Boolean = {
+ assert(elem != null, "InSet guarantees non-null input")
+ val collation = CollationFactory.fetchCollation(collationId)
+ inputSet.exists { p =>
Review Comment:
> This seems pretty inefficient
It depends on the cost of key calculation, size of the input set, how much
are comparisons of the particular collation heavy. This could seems like
"premature optimizations", but maybe you are right.
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
