Skip to content

[SPARK-2366] [SQL] Add column pruning for the right side of LeftSemi join. #1301

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
wants to merge 3 commits into from
Closed

[SPARK-2366] [SQL] Add column pruning for the right side of LeftSemi join. #1301

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
e0957b1
Add column pruning for the right side of LeftSemi join.
ueshin Jul 4, 2014
786d3a0
Rename method name.
ueshin Jul 5, 2014
7677a39
Update comments.
ueshin Jul 5, 2014
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
28 changes: 20 additions & 8 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 @@ -52,6 +52,7 @@ object Optimizer extends RuleExecutor[LogicalPlan] {
* - Inserting Projections beneath the following operators:
* - Aggregate
* - Project <- Join
* - LeftSemiJoin
* - Collapse adjacent projections, performing alias substitution.
*/
object ColumnPruning extends Rule[LogicalPlan] {
Expand All @@ -62,19 +63,22 @@ object ColumnPruning extends Rule[LogicalPlan] {

// Eliminate unneeded attributes from either side of a Join.
case Project(projectList, Join(left, right, joinType, condition)) =>
// Collect the list of off references required either above or to evaluate the condition.
// Collect the list of all references required either above or to evaluate the condition.
val allReferences: Set[Attribute] =
projectList.flatMap(_.references).toSet ++ condition.map(_.references).getOrElse(Set.empty)

/** Applies a projection only when the child is producing unnecessary attributes */
def prunedChild(c: LogicalPlan) =
if ((c.outputSet -- allReferences.filter(c.outputSet.contains)).nonEmpty) {
Project(allReferences.filter(c.outputSet.contains).toSeq, c)
} else {
c
}
def pruneJoinChild(c: LogicalPlan) = prunedChild(c, allReferences)

Project(projectList, Join(prunedChild(left), prunedChild(right), joinType, condition))
Project(projectList, Join(pruneJoinChild(left), pruneJoinChild(right), joinType, condition))

// Eliminate unneeded attributes from right side of a LeftSemiJoin.
case Join(left, right, LeftSemi, condition) =>
// Collect the list of all references required to evaluate the condition.
val allReferences: Set[Attribute] =
condition.map(_.references).getOrElse(Set.empty)

Join(left, prunedChild(right, allReferences), LeftSemi, condition)

// Combine adjacent Projects.
case Project(projectList1, Project(projectList2, child)) =>
Expand All @@ -97,6 +101,14 @@ object ColumnPruning extends Rule[LogicalPlan] {
// Eliminate no-op Projects
case Project(projectList, child) if child.output == projectList => child
}

/** Applies a projection only when the child is producing unnecessary attributes */
private def prunedChild(c: LogicalPlan, allReferences: Set[Attribute]) =
if ((c.outputSet -- allReferences.filter(c.outputSet.contains)).nonEmpty) {
Project(allReferences.filter(c.outputSet.contains).toSeq, c)
} else {
c
}
}

/**
Expand Down