Github user hvanhovell commented on a diff in the pull request: https://github.com/apache/spark/pull/17993#discussion_r116792863 --- Diff: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/expressions.scala --- @@ -54,6 +54,59 @@ object ConstantFolding extends Rule[LogicalPlan] { } } +/** + * Substitutes [[Attribute Attributes]] which can be statically evaluated with their corresponding + * value in conjunctive [[Expression Expressions]] + * eg. + * {{{ + * SELECT * FROM table WHERE i = 5 AND j = i + 3 + * ==> SELECT * FROM table WHERE i = 5 AND j = 8 + * }}} + */ +object ConstantPropagation extends Rule[LogicalPlan] with PredicateHelper { + + def containsNonConjunctionPredicates(expression: Expression): Boolean = expression match { + case Not(_) => true + case Or(_, _) => true + case _ => + var result = false + expression.children.foreach { + case Not(_) => result = true + case Or(_, _) => result = true + case other => result = result || containsNonConjunctionPredicates(other) + } + result + } + + def apply(plan: LogicalPlan): LogicalPlan = plan transform { + case q: LogicalPlan => q transformExpressionsUp { + case and @ (left And right) + if !containsNonConjunctionPredicates(left) && !containsNonConjunctionPredicates(right) => + + val leftEntries = left.collect { + case e @ EqualTo(left: AttributeReference, right: Literal) => ((left, right), e) + case e @ EqualTo(left: Literal, right: AttributeReference) => ((right, left), e) + } + val rightEntries = right.collect { + case e @ EqualTo(left: AttributeReference, right: Literal) => ((left, right), e) + case e @ EqualTo(left: Literal, right: AttributeReference) => ((right, left), e) + } + val constantsMap = AttributeMap(leftEntries.map(_._1) ++ rightEntries.map(_._1)) + val predicates = (leftEntries.map(_._2) ++ rightEntries.map(_._2)).toSet + + def replaceConstants(expression: Expression) = expression transform { + case a: AttributeReference if constantsMap.contains(a) => --- End diff -- I don't think the double lookup is necessary. `constantsMap.get(a).getOrElse(a)` should cover this.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org