maropu commented on a change in pull request #32494:
URL: https://github.com/apache/spark/pull/32494#discussion_r630797948
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/UnionEstimation.scala
##########
@@ -88,9 +88,18 @@ object UnionEstimation {
case (attrs, outputIndex) =>
val dataType = unionOutput(outputIndex).dataType
val statComparator = createStatComparator(dataType)
- val minMaxValue = attrs.zipWithIndex.foldLeft[(Option[Any],
Option[Any])]((None, None)) {
- case ((minVal, maxVal), (attr, childIndex)) =>
+ val colStatValues = attrs.zipWithIndex
+ .foldLeft[(Option[Any], Option[Any], Option[BigInt])]((None, None,
None)) {
+ case ((minVal, maxVal, totalNullCount), (attr, childIndex)) =>
val colStat =
union.children(childIndex).stats.attributeStats(attr)
+ // Update null count
+ val nullCount = if (totalNullCount.isDefined &&
colStat.nullCount.isDefined) {
+ Some(totalNullCount.get + colStat.nullCount.get)
+ } else if (colStat.nullCount.isDefined) {
+ colStat.nullCount
Review comment:
If some of `colStat.nullCount`s are missing, we can update the null
count in output?
--
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:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
