ahshahid commented on code in PR #38714:
URL: https://github.com/apache/spark/pull/38714#discussion_r1029760100
##########
sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/ResolveSubquerySuite.scala:
##########
@@ -270,4 +277,66 @@ class ResolveSubquerySuite extends AnalysisTest {
), Seq(a, b)).as("sub") :: Nil, t1)
)
}
+
+ test("SPARK-41141 aggregates of outer query referenced in subquery should
not create" +
+ " new aggregates if possible") {
+ withSQLConf(SQLConf.OPTIMIZER_EXCLUDED_RULES.key ->
s"${PropagateEmptyRelation.ruleName}") {
+ val a = 'a.int
+ val b = 'b.int
+ val c = 'c.int
+ val d = 'd.int
+
+ val t1 = LocalRelation(a, b)
+ val t2 = LocalRelation(c, d)
+ val optimizer = new SimpleTestOptimizer()
+
+ val plansToTest = Seq(
+ t1.select($"a", $"b").
+ having($"b")(Cos(sum($"a")))(Exists(t2.select($"c").
+ where($"d" === Cos(sum($"a"))))) -> 1,
+
+ t1.select($"a", $"b").
+ having($"b")(sum($"a"))(Exists(t2.select($"c").
+ where($"d" === Cos(sum($"a"))))) -> 1,
+ t1.select($"a", $"b").
+ having($"b")(Cos(sum($"a")))(Exists(t2.select($"c").
+ where($"d" === sum($"a")))) -> 2,
+ t1.select($"a", $"b").
+ having($"b")(sum($"a"), Cos(sum($"b")))(Exists(t2.select($"c").
+ where($"d" === Cos(sum($"a")) + sum($"a") + sum($"b") +
Cos(sum($"b"))))) -> 3
+ )
+
+ plansToTest.foreach {
+ case (logicalPlan: LogicalPlan, numAggFunctions) =>
+ assertAnalysis(logicalPlan, numAggFunctions)
+ }
+
+ def assertAnalysis(logicalPlan: LogicalPlan, expectedAggregateFunctions:
Int): Unit = {
+ val analyzedQuery = logicalPlan.analyze
+ Assert.assertTrue(analyzedQuery.analyzed)
+ val optimizedQuery = optimizer.execute(analyzedQuery)
Review Comment:
I recently experienced in different work ( about DataSourceV2 non required
projects ) that even though the analyzed plan's analyzed boolean was true, but
the plan did not have correct resolution and exception showed up during
optimization. so this is just a safety check..
--
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]
