Skip to content

[SPARK-16644][SQL] Aggregate should not propagate constraints containing aggregate expressions #14281

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
cloud-fan wants to merge 2 commits into from
Closed

[SPARK-16644][SQL] Aggregate should not propagate constraints containing aggregate expressions #14281

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
bc0157f
Aggregate should not propagate constraints containing aggregate expre…
cloud-fan Jul 20, 2016
48d81c8
Also test it in ConstraintPropagationSuite
yhuai Jul 20, 2016
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
6 changes: 4 additions & 2 deletions ...st/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/basicLogicalOperators.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -483,8 +483,10 @@ case class Aggregate(
override def output: Seq[Attribute] = aggregateExpressions.map(_.toAttribute)
override def maxRows: Option[Long] = child.maxRows

override def validConstraints: Set[Expression] =
child.constraints.union(getAliasedConstraints(aggregateExpressions))
override def validConstraints: Set[Expression] = {
val nonAgg = aggregateExpressions.filter(_.find(_.isInstanceOf[AggregateExpression]).isEmpty)
child.constraints.union(getAliasedConstraints(nonAgg))
}

override lazy val statistics: Statistics = {
if (groupingExpressions.isEmpty) {
Expand Down
6 changes: 4 additions & 2 deletions ...alyst/src/test/scala/org/apache/spark/sql/catalyst/plans/ConstraintPropagationSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -79,13 +79,15 @@ class ConstraintPropagationSuite extends SparkFunSuite {
assert(tr.analyze.constraints.isEmpty)

val aliasedRelation = tr.where('c.attr > 10 && 'a.attr < 5)
.groupBy('a, 'c, 'b)('a, 'c.as("c1"), count('a).as("a3")).select('c1, 'a).analyze
.groupBy('a, 'c, 'b)('a, 'c.as("c1"), count('a).as("a3")).select('c1, 'a, 'a3).analyze
Copy link
Copy Markdown
Contributor

@yhuai yhuai Jul 20, 2016

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@sameeragarwal How's this one?

Copy link
Copy Markdown
Member

@sameeragarwal sameeragarwal Jul 20, 2016

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

looks good


// SPARK-16644: aggregate expression count(a) should not appear in the constraints.
verifyConstraints(aliasedRelation.analyze.constraints,
ExpressionSet(Seq(resolveColumn(aliasedRelation.analyze, "c1") > 10,
IsNotNull(resolveColumn(aliasedRelation.analyze, "c1")),
resolveColumn(aliasedRelation.analyze, "a") < 5,
IsNotNull(resolveColumn(aliasedRelation.analyze, "a")))))
IsNotNull(resolveColumn(aliasedRelation.analyze, "a")),
IsNotNull(resolveColumn(aliasedRelation.analyze, "a3")))))
}

test("propagating constraints in expand") {
Expand Down
17 changes: 17 additions & 0 deletions sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2965,4 +2965,21 @@ class SQLQuerySuite extends QueryTest with SharedSQLContext {
}
}
}

test("SPARK-16644: Aggregate should not put aggregate expressions to constraints") {
withTable("tbl") {
sql("CREATE TABLE tbl(a INT, b INT) USING parquet")
checkAnswer(sql(
"""
|SELECT
| a,
| MAX(b) AS c1,
| b AS c2
|FROM tbl
|WHERE a = b
|GROUP BY a, b
|HAVING c1 = 1
""".stripMargin), Nil)
}
}
}