Skip to content
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

[SPARK-32360][SQL] Add MaxMinBy to support eliminate sorts #29142

Closed
wants to merge 4 commits into from
Closed

[SPARK-32360][SQL] Add MaxMinBy to support eliminate sorts #29142

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
e544ca3
init
ulysses-you Jul 17, 2020
bc454b6
fix
ulysses-you Jul 18, 2020
8aee8a5
add ut
ulysses-you Jul 20, 2020
cd93b70
fix
ulysses-you Jul 20, 2020
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
2 changes: 1 addition & 1 deletion sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1004,7 +1004,7 @@ object EliminateSorts extends Rule[LogicalPlan] {

private def isOrderIrrelevantAggs(aggs: Seq[NamedExpression]): Boolean = {
def isOrderIrrelevantAggFunction(func: AggregateFunction): Boolean = func match {
case _: Min | _: Max | _: Count => true
case _: Min | _: Max | _: Count | _: MaxMinBy => true
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Adding this itself looks fine to me.

// Arithmetic operations for floating-point values are order-sensitive
// (they are not associative).
case _: Sum | _: Average | _: CentralMomentAgg =>
Expand Down
12 changes: 12 additions & 0 deletions ...catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/EliminateSortsSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,7 @@ import org.apache.spark.sql.catalyst.dsl.expressions._
import org.apache.spark.sql.catalyst.dsl.plans._
import org.apache.spark.sql.catalyst.encoders.ExpressionEncoder
import org.apache.spark.sql.catalyst.expressions._
import org.apache.spark.sql.catalyst.expressions.aggregate.{MaxBy, MinBy}
import org.apache.spark.sql.catalyst.plans._
import org.apache.spark.sql.catalyst.plans.logical._
import org.apache.spark.sql.catalyst.rules._
Expand Down Expand Up @@ -319,4 +320,15 @@ class EliminateSortsSuite extends PlanTest {
val correctAnswer = PushDownOptimizer.execute(noOrderByPlan.analyze)
comparePlans(optimized, correctAnswer)
}

test("SPARK-32360: Add MaxMinBy to support eliminate sorts") {
Seq(MaxBy(Symbol("a"), Symbol("b")), MinBy(Symbol("a"), Symbol("b"))).foreach { agg =>
val projectPlan = testRelation.select(Symbol("a"), Symbol("b"))
val unnecessaryOrderByPlan = projectPlan.orderBy(Symbol("a").asc)
val groupByPlan = unnecessaryOrderByPlan.groupBy(Symbol("a"), Symbol("b"))(agg)
val optimized = Optimize.execute(groupByPlan.analyze)
val correctAnswer = projectPlan.groupBy(Symbol("a"), Symbol("b"))(agg).analyze
comparePlans(optimized, correctAnswer)
}
}
}