shahidki31 commented on a change in pull request #32494:
URL: https://github.com/apache/spark/pull/32494#discussion_r633896347
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/UnionEstimation.scala
##########
@@ -70,8 +70,20 @@ object UnionEstimation {
None
}
- val unionOutput = union.output
+ val (attrToComputeMinMaxStats, attrToComputeNullCount) =
getAttributeToComputeStats(union)
+ val attrStatsWithMinMax = computeMinMaxAttributeStatsMap(union,
attrToComputeMinMaxStats)
+ val newAttrStats = updateAttributeStatsMapWithNullCount(union,
attrStatsWithMinMax,
+ attrToComputeNullCount)
+
+ Some(
+ Statistics(
+ sizeInBytes = sizeInBytes,
+ rowCount = outputRows,
+ attributeStats = newAttrStats))
+ }
+ private def getAttributeToComputeStats(union: Union) = {
Review comment:
Removed the extra method and updated the code.
--
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
