jiwen624 commented on code in PR #56360:
URL: https://github.com/apache/spark/pull/56360#discussion_r3376416640
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/collect.scala:
##########
@@ -222,13 +225,26 @@ case class CollectSet(
buffer
}
+ @transient private lazy val complexNormalizer: Any => Any = {
+ val ref = BoundReference(0, child.dataType, nullable = true)
+ val proj = UnsafeProjection.create(NormalizeFloatingNumbers.normalize(ref))
+ (value: Any) => InternalRow.copyValue(proj(InternalRow(value)).get(0,
child.dataType))
+ }
+
override def convertToBufferElement(value: Any): Any = child.dataType match {
/*
* collect_set() of BinaryType should not return duplicate elements,
* Java byte arrays use referential equality and identity hash codes
* so we need to use a different catalyst value for arrays
*/
case BinaryType =>
UnsafeArrayData.fromPrimitiveArray(value.asInstanceOf[Array[Byte]])
+ case DoubleType =>
+ java.lang.Double.doubleToLongBits(
Review Comment:
Thanks. Comments added to explain keying on bit pattern.
--
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]
