Skip to content

[WIP][SPARK-31114][SQL] Constraints inferred from equality constraints with cast #27874

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 1 commit into from
Closed

[WIP][SPARK-31114][SQL] Constraints inferred from equality constraints with cast #27874

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
24 changes: 17 additions & 7 deletions ...yst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/QueryPlanConstraints.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,13 +66,21 @@ trait ConstraintHelper {
val predicates = constraints.filterNot(_.isInstanceOf[IsNotNull])
predicates.foreach {
case eq @ EqualTo(l: Attribute, r: Attribute) =>
val candidateConstraints = predicates - eq
inferredConstraints ++= replaceConstraints(candidateConstraints, l, r)
inferredConstraints ++= replaceConstraints(candidateConstraints, r, l)
case eq @ EqualTo(l @ Cast(_: Attribute, _, _), r: Attribute) =>
inferredConstraints ++= replaceConstraints(predicates - eq, r, l)
case eq @ EqualTo(l: Attribute, r @ Cast(_: Attribute, _, _)) =>
inferredConstraints ++= replaceConstraints(predicates - eq, l, r)
val candidates = predicates - eq
inferredConstraints ++= replaceConstraints(candidates, l, r)
inferredConstraints ++= replaceConstraints(candidates, r, l)
case eq @ EqualTo(l @ Cast(la: Attribute, _, tz), r: Attribute) =>
val candidates = predicates - eq
inferredConstraints ++= replaceConstraints(candidates, la, Cast(r, la.dataType, tz))
inferredConstraints ++= replaceConstraints(candidates, r, l)
case eq @ EqualTo(l: Attribute, r @ Cast(ra: Attribute, _, tz)) =>
val candidates = predicates - eq
inferredConstraints ++= replaceConstraints(candidates, l, r)
inferredConstraints ++= replaceConstraints(candidates, ra, Cast(l, ra.dataType, tz))
case eq @ EqualTo(Cast(la: Attribute, _, ltz), Cast(ra: Attribute, _, rtz)) =>
val candidates = predicates - eq
inferredConstraints ++= replaceConstraints(candidates, la, Cast(ra, la.dataType, ltz))
inferredConstraints ++= replaceConstraints(candidates, ra, Cast(la, ra.dataType, rtz))
case _ => // No inference
}
inferredConstraints -- constraints
Expand All @@ -83,6 +91,8 @@ trait ConstraintHelper {
source: Expression,
destination: Expression): Set[Expression] = constraints.map(_ transform {
case e: Expression if e.semanticEquals(source) => destination
}).map(_ transform {
case Cast(cast @ Cast(e, _, _), dt, _) if cast == destination && dt == e.dataType => e
})

/**
Expand Down
74 changes: 48 additions & 26 deletions ...test/scala/org/apache/spark/sql/catalyst/optimizer/InferFiltersFromConstraintsSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,7 @@ import org.apache.spark.sql.catalyst.plans._
import org.apache.spark.sql.catalyst.plans.logical._
import org.apache.spark.sql.catalyst.rules._
import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.types.{IntegerType, LongType}
import org.apache.spark.sql.types.{DecimalType, IntegerType, LongType, ShortType}

class InferFiltersFromConstraintsSuite extends PlanTest {

Expand All @@ -36,6 +36,7 @@ class InferFiltersFromConstraintsSuite extends PlanTest {
InferFiltersFromConstraints,
CombineFilters,
SimplifyBinaryComparison,
SimplifyCasts,
BooleanSimplification,
PruneFilters) :: Nil
}
Expand Down Expand Up @@ -265,7 +266,7 @@ class InferFiltersFromConstraintsSuite extends PlanTest {
testConstraintsAfterJoin(x, y, x.where(IsNotNull('a)), y, RightOuter)
}

test("Constraints should be inferred from cast equality constraint(filter higher data type)") {
test("Constraints inferred from cast equality constraint(filter higher data type)") {
val testRelation1 = LocalRelation('a.int)
val testRelation2 = LocalRelation('b.long)
val originalLeft = testRelation1.subquery('left)
Expand All @@ -275,45 +276,66 @@ class InferFiltersFromConstraintsSuite extends PlanTest {
val right = testRelation2.where(IsNotNull('b) && 'b === 1L).subquery('right)

Seq(Some("left.a".attr.cast(LongType) === "right.b".attr),
Some("right.b".attr === "left.a".attr.cast(LongType))).foreach { condition =>
testConstraintsAfterJoin(originalLeft, originalRight, left, right, Inner, condition)
}

Seq(Some("left.a".attr === "right.b".attr.cast(IntegerType)),
Some("right.b".attr === "left.a".attr.cast(LongType)),
Some("left.a".attr === "right.b".attr.cast(IntegerType)),
Some("right.b".attr.cast(IntegerType) === "left.a".attr)).foreach { condition =>
testConstraintsAfterJoin(
originalLeft,
originalRight,
testRelation1.where(IsNotNull('a)).subquery('left),
right,
Inner,
condition)
testConstraintsAfterJoin(originalLeft, originalRight, left, right, Inner, condition)
}
}

test("Constraints shouldn't be inferred from cast equality constraint(filter lower data type)") {
test("Constraints inferred from cast equality constraint(filter lower data type)") {
val testRelation1 = LocalRelation('a.int)
val testRelation2 = LocalRelation('b.long)
val originalLeft = testRelation1.where('a === 1).subquery('left)
val originalRight = testRelation2.subquery('right)

val left = testRelation1.where(IsNotNull('a) && 'a === 1).subquery('left)
val right = testRelation2.where(IsNotNull('b)).subquery('right)
val right = testRelation2.where(IsNotNull('b) && 'b.cast(IntegerType) === 1).subquery('right)

Seq(Some("left.a".attr.cast(LongType) === "right.b".attr),
Some("right.b".attr === "left.a".attr.cast(LongType))).foreach { condition =>
Some("right.b".attr === "left.a".attr.cast(LongType)),
Some("left.a".attr === "right.b".attr.cast(IntegerType)),
Some("right.b".attr.cast(IntegerType) === "left.a".attr)).foreach { condition =>
testConstraintsAfterJoin(originalLeft, originalRight, left, right, Inner, condition)
}
}

Seq(Some("left.a".attr === "right.b".attr.cast(IntegerType)),
Some("right.b".attr.cast(IntegerType) === "left.a".attr)).foreach { condition =>
testConstraintsAfterJoin(
originalLeft,
originalRight,
left,
testRelation2.where(IsNotNull('b) && 'b.attr.cast(IntegerType) === 1).subquery('right),
Inner,
condition)
test("Constraints inferred from cast equality constraint(filter decimal type)") {
val testRelation1 = LocalRelation('a.decimal(18, 0))
val testRelation2 = LocalRelation('b.long)
val originalLeft = testRelation1.where('a === 1).subquery('left)
val originalRight = testRelation2.subquery('right)

val decimalOne = Literal(1).cast(DecimalType(1, 0)).cast(DecimalType(18, 0))

val left = testRelation1.where(IsNotNull('a) && 'a === decimalOne).subquery('left)
val right = testRelation2.where(IsNotNull('b)
&& 'b.cast(DecimalType(18, 0)) === decimalOne).subquery('right)

Seq(Some("left.a".attr.cast(DecimalType(20, 0)) === "right.b".attr.cast(DecimalType(20, 0))),
Some("right.b".attr.cast(DecimalType(20, 0)) === "left.a".attr.cast(DecimalType(20, 0))),
Some("right.b".attr.cast(IntegerType) === "left.a".attr.cast(IntegerType)),
Some("left.a".attr === "right.b".attr.cast(DecimalType(18, 0))),
Some("left.a".attr.cast(LongType) === "right.b".attr)).foreach { condition =>
testConstraintsAfterJoin(originalLeft, originalRight, left, right, Inner, condition)
}
}

test("Constraints inferred from cast equality constraint(filter bigint type)") {
val testRelation1 = LocalRelation('a.decimal(18, 0))
val testRelation2 = LocalRelation('b.long)
val originalLeft = testRelation1.subquery('left)
val originalRight = testRelation2.where('b === 1L).subquery('right)

val left = testRelation1.where(IsNotNull('a) && 'a.cast(LongType) === 1L).subquery('left)
val right = testRelation2.where(IsNotNull('b) && 'b === 1L).subquery('right)

Seq(Some("left.a".attr.cast(DecimalType(20, 0)) === "right.b".attr.cast(DecimalType(20, 0))),
Some("right.b".attr.cast(DecimalType(20, 0)) === "left.a".attr.cast(DecimalType(20, 0))),
Some("right.b".attr.cast(IntegerType) === "left.a".attr.cast(IntegerType)),
Some("left.a".attr === "right.b".attr.cast(DecimalType(18, 0))),
Some("left.a".attr.cast(LongType) === "right.b".attr)).foreach { condition =>
testConstraintsAfterJoin(originalLeft, originalRight, left, right, Inner, condition)
}
}
}