uros-db commented on code in PR #47154:
URL: https://github.com/apache/spark/pull/47154#discussion_r1700168116
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Mode.scala:
##########
@@ -86,6 +88,57 @@ case class Mode(
buffer
}
+ private def getCollationAwareBuffer(
+ childDataType: DataType,
+ buffer: OpenHashMap[AnyRef, Long]): Iterable[(AnyRef, Long)] = {
+ def getBuffer(groupingFunction: AnyRef => _): Iterable[(AnyRef, Long)] = {
+ buffer.groupMapReduce(t =>
+ groupingFunction(t._1))(x => x)((x, y) => (x._1, x._2 + y._2)).values
+ }
+ def getMyBuffer(
+ childDataType: DataType): Option[AnyRef => _] = {
+ childDataType match {
+ case _ if UnsafeRowUtils.isBinaryStable(child.dataType) => None
+ case _ => Some(f(_, childDataType))
+ }
+ }
+ getMyBuffer(childDataType).map(getBuffer).getOrElse(buffer)
+ }
+
+ private def f(myData: AnyRef, myElementType: DataType): AnyRef = {
Review Comment:
let's be a bit more mindful about naming, and give this method a more
meaningful /descriptive name?
--
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: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
