Github user scwf commented on a diff in the pull request:
https://github.com/apache/spark/pull/4090#discussion_r23129765
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala
---
@@ -302,89 +302,100 @@ object OptimizeIn extends Rule[LogicalPlan] {
object BooleanSimplification extends Rule[LogicalPlan] with
PredicateHelper {
def apply(plan: LogicalPlan): LogicalPlan = plan transform {
case q: LogicalPlan => q transformExpressionsUp {
- case and @ And(left, right) =>
- (left, right) match {
- case (Literal(true, BooleanType), r) => r
- case (l, Literal(true, BooleanType)) => l
- case (Literal(false, BooleanType), _) => Literal(false)
- case (_, Literal(false, BooleanType)) => Literal(false)
- // a && a => a
- case (l, r) if l fastEquals r => l
- case (_, _) =>
- /* Do optimize for predicates using formula (a || b) && (a ||
c) => a || (b && c)
- * 1. Split left and right to get the disjunctive predicates,
- * i.e. lhsSet = (a, b), rhsSet = (a, c)
- * 2. Find the common predict between lhsSet and rhsSet, i.e.
common = (a)
- * 3. Remove common predict from lhsSet and rhsSet, i.e. ldiff
= (b), rdiff = (c)
- * 4. Apply the formula, get the optimized predict: common ||
(ldiff && rdiff)
- */
- val lhsSet = splitDisjunctivePredicates(left).toSet
- val rhsSet = splitDisjunctivePredicates(right).toSet
- val common = lhsSet.intersect(rhsSet)
- val ldiff = lhsSet.diff(common)
- val rdiff = rhsSet.diff(common)
- if (ldiff.size == 0 || rdiff.size == 0) {
- // a && (a || b) => a
- common.reduce(Or)
- } else {
- // (a || b || c || ...) && (a || b || d || ...) && (a || b
|| e || ...) ... =>
- // (a || b) || ((c || ...) && (f || ...) && (e || ...) &&
...)
- (ldiff.reduceOption(Or) ++ rdiff.reduceOption(Or))
- .reduceOption(And)
- .map(_ :: common.toList)
- .getOrElse(common.toList)
- .reduce(Or)
- }
- }
-
- case or @ Or(left, right) =>
- (left, right) match {
- case (Literal(true, BooleanType), _) => Literal(true)
- case (_, Literal(true, BooleanType)) => Literal(true)
- case (Literal(false, BooleanType), r) => r
- case (l, Literal(false, BooleanType)) => l
- // a || a => a
- case (l, r) if l fastEquals r => l
- case (_, _) =>
- /* Do optimize for predicates using formula (a && b) || (a &&
c) => a && (b || c)
- * 1. Split left and right to get the conjunctive predicates,
- * i.e. lhsSet = (a, b), rhsSet = (a, c)
- * 2. Find the common predict between lhsSet and rhsSet, i.e.
common = (a)
- * 3. Remove common predict from lhsSet and rhsSet, i.e. ldiff
= (b), rdiff = (c)
- * 4. Apply the formula, get the optimized predict: common &&
(ldiff || rdiff)
- */
- val lhsSet = splitConjunctivePredicates(left).toSet
- val rhsSet = splitConjunctivePredicates(right).toSet
- val common = lhsSet.intersect(rhsSet)
- val ldiff = lhsSet.diff(common)
- val rdiff = rhsSet.diff(common)
- if ( ldiff.size == 0 || rdiff.size == 0) {
- // a || (b && a) => a
- common.reduce(And)
- } else {
- // (a && b && c && ...) || (a && b && d && ...) || (a && b
&& e && ...) ... =>
- // a && b && ((c && ...) || (d && ...) || (e && ...) || ...)
- (ldiff.reduceOption(And) ++ rdiff.reduceOption(And))
- .reduceOption(Or)
- .map(_ :: common.toList)
- .getOrElse(common.toList)
- .reduce(And)
- }
- }
-
- case not @ Not(exp) =>
- exp match {
- case Literal(true, BooleanType) => Literal(false)
- case Literal(false, BooleanType) => Literal(true)
- case GreaterThan(l, r) => LessThanOrEqual(l, r)
- case GreaterThanOrEqual(l, r) => LessThan(l, r)
- case LessThan(l, r) => GreaterThanOrEqual(l, r)
- case LessThanOrEqual(l, r) => GreaterThan(l, r)
- case Not(e) => e
- case _ => not
- }
-
- // Turn "if (true) a else b" into "a", and if (false) a else b" into
"b".
+ case and @ And(left, right) => (left, right) match {
+ // true && r => r
+ case (Literal(true, BooleanType), r) => r
+ // l && true => l
+ case (l, Literal(true, BooleanType)) => l
+ // false && r => false
+ case (Literal(false, BooleanType), _) => Literal(false)
+ // l && false => false
+ case (_, Literal(false, BooleanType)) => Literal(false)
+ // a && a => a
+ case (l, r) if l fastEquals r => l
+ // (a || b) && (a || c) => a || (b && c)
+ case (_, _) =>
+ // 1. Split left and right to get the disjunctive predicates,
+ // i.e. lhsSet = (a, b), rhsSet = (a, c)
+ // 2. Find the common predict between lhsSet and rhsSet, i.e.
common = (a)
+ // 3. Remove common predict from lhsSet and rhsSet, i.e. ldiff =
(b), rdiff = (c)
+ // 4. Apply the formula, get the optimized predicate: common ||
(ldiff && rdiff)
+ val lhsSet = splitDisjunctivePredicates(left).toSet
--- End diff --
yes,get it, there is a bug for case ```(a && b) || (a && b && c)```
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]