Skip to content

[SPARK-36194][SQL][FOLLOWUP] Propagate distinct keys more precisely #36100

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
cloud-fan wants to merge 1 commit into from
Closed

[SPARK-36194][SQL][FOLLOWUP] Propagate distinct keys more precisely #36100

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 18 additions & 2 deletions ...alyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/DistinctKeyVisitor.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,11 +50,27 @@ object DistinctKeyVisitor extends LogicalPlanVisitor[Set[ExpressionSet]] {
}.filter(_.nonEmpty)
}

/**
* Add a new ExpressionSet S into distinctKeys D.
* To minimize the size of D:
* 1. If there is a subset of S in D, return D.
* 2. Otherwise, remove all the ExpressionSet containing S from D, and add the new one.
*/
private def addDistinctKey(
keys: Set[ExpressionSet],
newExpressionSet: ExpressionSet): Set[ExpressionSet] = {
if (keys.exists(_.subsetOf(newExpressionSet))) {
keys
} else {
keys.filterNot(s => newExpressionSet.subsetOf(s)) + newExpressionSet
}
}

override def default(p: LogicalPlan): Set[ExpressionSet] = Set.empty[ExpressionSet]

override def visitAggregate(p: Aggregate): Set[ExpressionSet] = {
val groupingExps = ExpressionSet(p.groupingExpressions) // handle group by a, a
projectDistinctKeys(Set(groupingExps), p.aggregateExpressions)
projectDistinctKeys(addDistinctKey(p.child.distinctKeys, groupingExps), p.aggregateExpressions)
}

override def visitDistinct(p: Distinct): Set[ExpressionSet] = Set(ExpressionSet(p.output))
Expand All @@ -70,7 +86,7 @@ object DistinctKeyVisitor extends LogicalPlanVisitor[Set[ExpressionSet]] {

override def visitGlobalLimit(p: GlobalLimit): Set[ExpressionSet] = {
p.maxRows match {
case Some(value) if value <= 1 => Set(ExpressionSet(p.output))
case Some(value) if value <= 1 => p.output.map(attr => ExpressionSet(Seq(attr))).toSet
case _ => p.child.distinctKeys
}
}
Expand Down
7 changes: 6 additions & 1 deletion .../src/test/scala/org/apache/spark/sql/catalyst/plans/logical/DistinctKeyVisitorSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,6 +66,10 @@ class DistinctKeyVisitorSuite extends PlanTest {
Set(ExpressionSet(Seq(a)), ExpressionSet(Seq(d.toAttribute))))
checkDistinctAttributes(t1.groupBy(f.child, $"b")(f, $"b", sum($"c")),
Set(ExpressionSet(Seq(f.toAttribute, b))))

// Aggregate should also propagate distinct keys from child
checkDistinctAttributes(t1.limit(1).groupBy($"a", $"b")($"a", $"b"),
Set(ExpressionSet(Seq(a)), ExpressionSet(Seq(b))))
}

test("Distinct's distinct attributes") {
Expand All @@ -86,7 +90,8 @@ class DistinctKeyVisitorSuite extends PlanTest {
test("Limit's distinct attributes") {
checkDistinctAttributes(Distinct(t1).limit(10), Set(ExpressionSet(Seq(a, b, c))))
checkDistinctAttributes(LocalLimit(10, Distinct(t1)), Set(ExpressionSet(Seq(a, b, c))))
checkDistinctAttributes(t1.limit(1), Set(ExpressionSet(Seq(a, b, c))))
checkDistinctAttributes(t1.limit(1),
Set(ExpressionSet(Seq(a)), ExpressionSet(Seq(b)), ExpressionSet(Seq(c))))
}

test("Intersect's distinct attributes") {
Expand Down