cloud-fan commented on a change in pull request #35214:
URL: https://github.com/apache/spark/pull/35214#discussion_r791350062
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala
##########
@@ -1300,16 +1300,22 @@ object InferFiltersFromConstraints extends
Rule[LogicalPlan]
* Combines all adjacent [[Union]] operators into a single [[Union]].
*/
object CombineUnions extends Rule[LogicalPlan] {
- def apply(plan: LogicalPlan): LogicalPlan = plan.transformDownWithPruning(
- _.containsAnyPattern(UNION, DISTINCT_LIKE), ruleId) {
- case u: Union => flattenUnion(u, false)
- case Distinct(u: Union) => Distinct(flattenUnion(u, true))
- // Only handle distinct-like 'Deduplicate', where the keys == output
- case Deduplicate(keys: Seq[Attribute], u: Union) if AttributeSet(keys) ==
u.outputSet =>
- Deduplicate(keys, flattenUnion(u, true))
+ import CollapseProject.{buildCleanedProjectList, canCollapseExpressions}
+ import PushProjectionThroughUnion.pushProjectionThroughUnion
+
+ def apply(plan: LogicalPlan): LogicalPlan = {
+ val alwaysInline = conf.getConf(SQLConf.COLLAPSE_PROJECT_ALWAYS_INLINE)
Review comment:
This is a new optimization. I don't think we need to respect this config
for keeping legacy behaviors.
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
