cloud-fan commented on a change in pull request #30504: URL: https://github.com/apache/spark/pull/30504#discussion_r531413076
########## File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala ########## @@ -873,24 +873,30 @@ object InferFiltersFromGenerate extends Rule[LogicalPlan] { if !e.deterministic || e.children.forall(_.foldable) => generate case generate @ Generate(g, _, false, _, _, _) if canInferFilters(g) => - // Exclude child's constraints to guarantee idempotency - val inferredFilters = ExpressionSet( - Seq( - GreaterThan(Size(g.children.head), Literal(0)), - IsNotNull(g.children.head) - ) - ) -- generate.child.constraints - - if (inferredFilters.nonEmpty) { - generate.copy(child = Filter(inferredFilters.reduce(And), generate.child)) - } else { - generate + g.children.head match { + case _: CreateNonEmptyNonNullCollection => + // we don't need to add filters when creating an array because we know its size + // is > 0 and its not null + generate + case _ => + // Exclude child's constraints to guarantee idempotency + val inferredFilters = ExpressionSet( + Seq( + GreaterThan(Size(g.children.head), Literal(0)), + IsNotNull(g.children.head) Review comment: I mean, this rule can add redundant predicates, and we just need another rule to optimize them out. This is how catalyst rules should interact: be orthogonal and focus on one thing. Actually, `CreateArray.nullable` is false, so `IsNotNull(CreateArray(...))` will be optimized to `true` already, in rule `NullPropagation`. We can probably update `SimplifyBinaryComparison` and add ``` case GreaterThan(Size(_: CreateNonNullCollection), IntegerLiteral(0)) => TrueLiteral ``` ########## File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala ########## @@ -873,24 +873,30 @@ object InferFiltersFromGenerate extends Rule[LogicalPlan] { if !e.deterministic || e.children.forall(_.foldable) => generate case generate @ Generate(g, _, false, _, _, _) if canInferFilters(g) => - // Exclude child's constraints to guarantee idempotency - val inferredFilters = ExpressionSet( - Seq( - GreaterThan(Size(g.children.head), Literal(0)), - IsNotNull(g.children.head) - ) - ) -- generate.child.constraints - - if (inferredFilters.nonEmpty) { - generate.copy(child = Filter(inferredFilters.reduce(And), generate.child)) - } else { - generate + g.children.head match { + case _: CreateNonEmptyNonNullCollection => + // we don't need to add filters when creating an array because we know its size + // is > 0 and its not null + generate + case _ => + // Exclude child's constraints to guarantee idempotency + val inferredFilters = ExpressionSet( + Seq( + GreaterThan(Size(g.children.head), Literal(0)), + IsNotNull(g.children.head) Review comment: I mean, this rule can add redundant predicates, and we just need another rule to optimize them out. This is how catalyst rules should interact: be orthogonal and focus on one thing. Actually, `CreateArray.nullable` is false, so `IsNotNull(CreateArray(...))` will be optimized to `true` already, in rule `NullPropagation`. We can probably update `SimplifyBinaryComparison` and add ``` case GreaterThan(Size(_: CreateNonNullCollection), IntegerLiteral(0)) => TrueLiteral ``` ---------------------------------------------------------------- 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