cloud-fan commented on a change in pull request #33286:
URL: https://github.com/apache/spark/pull/33286#discussion_r670115469
##########
File path:
sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/statsEstimation/FilterEstimationSuite.scala
##########
@@ -822,6 +822,41 @@ class FilterEstimationSuite extends
StatsEstimationTestBase {
expectedRowCount = 3)
}
+ test("SPARK-36079: Null count should be no higher than row count after
filter") {
+ val colStatNullableString = colStatString.copy(nullCount = Some(10))
+ val condition = Filter(EqualTo(attrBool, Literal(true)),
+ childStatsTestPlan(Seq(attrBool, attrString), tableRowCount = 10L,
+ attributeMap = AttributeMap(Seq(
+ attrBool -> colStatBool, attrString -> colStatNullableString))))
+ validateEstimatedStats(
+ condition,
+ Seq(attrBool -> colStatBool.copy(distinctCount = Some(1), min =
Some(true)),
+ attrString -> colStatNullableString.copy(distinctCount = Some(5),
nullCount = Some(5))),
+ expectedRowCount = 5)
+ }
+
+ test("SPARK-36079: Null count higher than row count") {
Review comment:
what's the difference between this test and the one above?
--
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]
