bhollis-dbx commented on code in PR #59283:
URL: https://github.com/apache/spark/pull/59283#discussion_r4273023104
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/UpdateFields.scala:
##########
@@ -39,37 +39,54 @@ object OptimizeUpdateFields extends Rule[LogicalPlan] {
}
}
+ private def optimizeFieldOps(
+ fieldOps: Seq[StructFieldsOperation]): Seq[StructFieldsOperation] = {
+ val operations = fieldOps.map {
+ case nested: UpdateNestedField =>
+ nested.copy(fieldOps = optimizeFieldOps(nested.fieldOps))
+ case other => other
+ }
+ if (!operations.forall {
+ case _: WithField | _: UpdateNestedField => true
+ case _ => false
+ }) {
+ operations
+ } else {
+ val combined = mutable.LinkedHashMap.empty[String, StructFieldsOperation]
+ operations.foreach { operation =>
+ val name = operation match {
+ case WithField(name, _) => name
+ case UpdateNestedField(name, _) => name
+ }
+ val key = if (conf.caseSensitiveAnalysis) name else
name.toLowerCase(Locale.ROOT)
+ val updated = operation match {
+ case nested: UpdateNestedField => combined.get(key) match {
+ case Some(previous: UpdateNestedField) =>
+ nested.copy(fieldOps = optimizeFieldOps(previous.fieldOps ++
nested.fieldOps))
Review Comment:
Fixed in 3fe6dd456. Same-parent operations accumulate before merge
optimization, preserving overwrite order, drop barriers, and casing. The
2,000-update regression previously recorded roughly 8 million operation visits;
it now stays below 40,000.
--
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]
