yhuang-db commented on code in PR #51505:
URL: https://github.com/apache/spark/pull/51505#discussion_r2430822628
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/ApproxTopKAggregates.scala:
##########
@@ -317,8 +322,51 @@ object ApproxTopK {
def getSketchStateDataType(itemDataType: DataType): StructType =
StructType(
StructField("sketch", BinaryType, nullable = false) ::
+ StructField("maxItemsTracked", IntegerType, nullable = false) ::
StructField("itemDataType", itemDataType) ::
- StructField("maxItemsTracked", IntegerType, nullable = false) :: Nil)
+ StructField("itemDataTypeDDL", StringType, nullable = false) :: Nil)
+
+ def dataTypeToDDL(dataType: DataType): String = dataType match {
+ case _: StringType =>
+ // Hide collation information in DDL format
Review Comment:
There is a short skip list
https://github.com/apache/spark/blob/master/sql/core/src/test/scala/org/apache/spark/sql/collation/CollationExpressionWalkerSuite.scala#L375.
Or maybe we can add accumulate and combine to the list.
--
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]
