cloud-fan commented on a change in pull request #28575:
URL: https://github.com/apache/spark/pull/28575#discussion_r434399611
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala
##########
@@ -1372,6 +1376,108 @@ object PushPredicateThroughJoin extends
Rule[LogicalPlan] with PredicateHelper {
}
}
+/**
+ * Rewriting join condition to conjunctive normal form expression so that we
can push
+ * more predicate.
+ */
+object PushPredicateThroughJoinByCNF extends Rule[LogicalPlan] with
PredicateHelper {
+ /**
+ * Rewrite pattern:
+ * 1. (a && b) || c --> (a || c) && (b || c)
+ * 2. a || (b && c) --> (a || b) && (a || c)
+ *
+ * To avoid generating too many predicates, we first group the filter
columns from the same table.
+ */
+ private def toCNF(condition: Expression, depth: Int = 0): Expression = {
+ if (depth < SQLConf.get.maxRewritingCNFDepth) {
+ condition match {
+ case or @ Or(left: And, right: And) =>
+ val lhs =
splitConjunctivePredicates(left).groupBy(_.references.map(_.qualifier))
+ val rhs =
splitConjunctivePredicates(right).groupBy(_.references.map(_.qualifier))
+ if (lhs.size > 1) {
+ lhs.values.map(_.reduceLeft(And)).map { c =>
+ toCNF(Or(toCNF(c, depth + 1), toCNF(right, depth + 1)), depth +
1)
+ }.reduce(And)
+ } else if (rhs.size > 1) {
+ rhs.values.map(_.reduceLeft(And)).map { c =>
+ toCNF(Or(toCNF(left, depth + 1), toCNF(c, depth + 1)), depth + 1)
+ }.reduce(And)
+ } else {
+ or
+ }
+
+ case or @ Or(left: And, right) =>
+ val lhs =
splitConjunctivePredicates(left).groupBy(_.references.map(_.qualifier))
+ if (lhs.size > 1) {
+ lhs.values.map(_.reduceLeft(And)).map {
+ c => toCNF(Or(toCNF(c, depth + 1), toCNF(right, depth + 1)),
depth + 1)
+ }.reduce(And)
+ } else {
+ or
+ }
+
+ case or @ Or(left, right: And) =>
+ val rhs =
splitConjunctivePredicates(right).groupBy(_.references.map(_.qualifier))
+ if (rhs.size > 1) {
+ rhs.values.map(_.reduceLeft(And)).map { c =>
+ toCNF(Or(toCNF(left, depth + 1), toCNF(c, depth + 1)), depth + 1)
+ }.reduce(And)
+ } else {
+ or
+ }
+
+ case And(left, right) =>
+ And(toCNF(left, depth + 1), toCNF(right, depth + 1))
+
+ case other =>
+ other
+ }
+ } else {
+ condition
+ }
+ }
+
+ private def maybeWithFilter(joinCondition: Option[Expression], plan:
LogicalPlan) = {
+ (joinCondition, plan) match {
+ // Avoid adding the same filter.
+ case (Some(condition), filter: Filter) if
condition.semanticEquals(filter.condition) =>
+ plan
+ case (Some(condition), _) =>
+ Filter(condition, plan)
+ case _ =>
+ plan
+ }
+ }
+
+ def apply(plan: LogicalPlan): LogicalPlan = plan transform applyLocally
Review comment:
why do we create `applyLocally` instead of inline it?
----------------------------------------------------------------
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
