dbtsai commented on a change in pull request #33930: URL: https://github.com/apache/spark/pull/33930#discussion_r707796357
########## File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/expressions.scala ########## @@ -441,6 +456,25 @@ object BooleanSimplification extends Rule[LogicalPlan] with PredicateHelper { case Not(IsNull(e)) => IsNotNull(e) case Not(IsNotNull(e)) => IsNull(e) + + // Move `Not` from one side of `EqualTo`/`EqualNullSafe` to the other side if it's beneficial. + // E.g. `EqualTo(Not(a), b)` where `b = Not(c)`, it will become + // `EqualTo(a, Not(b))` => `EqualTo(a, Not(Not(c)))` => `EqualTo(a, c)` + // In addition, `if canSimplifyNot(b)` checks if the optimization can converge + // that avoids the situation two conditions are returning to each other. + case EqualTo(Not(a), b) if canSimplifyNot(b) => EqualTo(a, Not(b)) + case EqualTo(a, Not(b)) if canSimplifyNot(a) => EqualTo(Not(a), b) + case EqualNullSafe(Not(a), b) if canSimplifyNot(b) => EqualNullSafe(a, Not(b)) + case EqualNullSafe(a, Not(b)) if canSimplifyNot(a) => EqualNullSafe(Not(a), b) + + // Push `Not` to one side of `EqualTo`/`EqualNullSafe` if it's beneficial. + // E.g. Not(EqualTo(x, false)) => EqualTo(x, true) + case Not(EqualTo(a, b)) if canSimplifyNot(b) => EqualTo(a, Not(b)) + case Not(EqualTo(a, b)) if canSimplifyNot(a) => EqualTo(Not(a), b) Review comment: agree, it's a NP-hard problem :) -- 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: reviews-unsubscr...@spark.apache.org 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