Skip to content

[SPARK-31977][SQL] Returns the plan directly from NestedColumnAliasing #28812

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
HyukjinKwon wants to merge 1 commit into from
Closed

[SPARK-31977][SQL] Returns the plan directly from NestedColumnAliasing #28812

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 12 additions & 7 deletions ...atalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/NestedColumnAliasing.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,24 +30,29 @@ import org.apache.spark.sql.types._
*/
object NestedColumnAliasing {

def unapply(plan: LogicalPlan)
: Option[(Map[ExtractValue, Alias], Map[ExprId, Seq[Alias]])] = plan match {
def unapply(plan: LogicalPlan): Option[LogicalPlan] = plan match {
case Project(projectList, child)
if SQLConf.get.nestedSchemaPruningEnabled && canProjectPushThrough(child) =>
val exprCandidatesToPrune = projectList ++ child.expressions
getAliasSubMap(exprCandidatesToPrune, child.producedAttributes.toSeq)
getAliasSubMap(exprCandidatesToPrune, child.producedAttributes.toSeq).map {
case (nestedFieldToAlias, attrToAliases) =>
NestedColumnAliasing.replaceToAliases(plan, nestedFieldToAlias, attrToAliases)
}

case plan if SQLConf.get.nestedSchemaPruningEnabled && canPruneOn(plan) =>
val exprCandidatesToPrune = plan.expressions
getAliasSubMap(exprCandidatesToPrune, plan.producedAttributes.toSeq)
case p if SQLConf.get.nestedSchemaPruningEnabled && canPruneOn(p) =>
val exprCandidatesToPrune = p.expressions
getAliasSubMap(exprCandidatesToPrune, p.producedAttributes.toSeq).map {
case (nestedFieldToAlias, attrToAliases) =>
NestedColumnAliasing.replaceToAliases(p, nestedFieldToAlias, attrToAliases)
}

case _ => None
}

/**
* Replace nested columns to prune unused nested columns later.
*/
def replaceToAliases(
private def replaceToAliases(
plan: LogicalPlan,
nestedFieldToAlias: Map[ExtractValue, Alias],
attrToAliases: Map[ExprId, Seq[Alias]]): LogicalPlan = plan match {
Expand Down
3 changes: 1 addition & 2 deletions sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -649,8 +649,7 @@ object ColumnPruning extends Rule[LogicalPlan] {
// Can't prune the columns on LeafNode
case p @ Project(_, _: LeafNode) => p

case p @ NestedColumnAliasing(nestedFieldToAlias, attrToAliases) =>
NestedColumnAliasing.replaceToAliases(p, nestedFieldToAlias, attrToAliases)
case NestedColumnAliasing(p) => p

// for all other logical plans that inherits the output from it's children
// Project over project is handled by the first case, skip it here.
Expand Down