Github user davies commented on a diff in the pull request: https://github.com/apache/spark/pull/11235#discussion_r55398759 --- Diff: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala --- @@ -146,6 +147,56 @@ object EliminateSerialization extends Rule[LogicalPlan] { } /** + * Add Filter to left and right of a EquiJoin to filter out rows with null keys. + * So we may not need to check nullability of keys while joining. Besides, by filtering + * out keys with null, we can also reduce data size in Join. + */ +object AddNullFilterForEquiJoin extends Rule[LogicalPlan] with PredicateHelper { + def apply(plan: LogicalPlan): LogicalPlan = plan transform { + case ExtractEquiJoinKeys(Inner, leftKeys, rightKeys, condition, left, right) => + val leftConditions = leftKeys.distinct.map { l => + IsNotNull(l) + }.reduceLeft(And) + + val rightConditions = rightKeys.distinct.map { r => + IsNotNull(r) + }.reduceLeft(And) + + val keysConditions = ExpressionSet(leftKeys.zip(rightKeys).map { lr => + EqualTo(lr._2, lr._1) + }).reduceLeft(And) + + val finalConditions = if (condition.isDefined) { + And(keysConditions, condition.get) + } else { + keysConditions + } + + val leftHasAllNotNullPredicate = left.constraints.nonEmpty && + left.constraints.filter(_.isInstanceOf[IsNotNull]) + .forall(expr => leftConditions.references.intersect(expr.references).nonEmpty) + + val rightHasAllNotNullPredicate = right.constraints.nonEmpty && + right.constraints.filter(_.isInstanceOf[IsNotNull]) + .forall(expr => rightConditions.references.intersect(expr.references).nonEmpty) + + val newLeft = if (leftHasAllNotNullPredicate) { + left + } else { + Filter(leftConditions, left) + } + + val newRight = if (rightHasAllNotNullPredicate) { + right + } else { + Filter(rightConditions, right) + } + + Join(newLeft, newRight, Inner, Some(finalConditions)) --- End diff -- If no filter added, we should return the original join.
--- 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