Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
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
Original file line number Diff line number Diff line change
Expand Up @@ -1999,7 +1999,19 @@ class Analyzer(override val catalogManager: CatalogManager) extends RuleExecutor
throw QueryCompilationErrors.groupByPositionRefersToAggregateFunctionError(
index, ordinalExpr)
} else {
ordinalExpr
trimAliases(ordinalExpr) match {
// HACK ALERT: If the ordinal expression is also an integer literal, don't use it
// but still keep the ordinal literal. The reason is we may repeatedly
// analyze the plan. Using a different integer literal may lead to
// a repeat GROUP BY ordinal resolution which is wrong. GROUP BY
// constant is meaningless so whatever value does not matter here.
// TODO: (SPARK-45932) GROUP BY ordinal should pull out grouping expressions to
// a Project, then the resolved ordinal expression is always
// `AttributeReference`.
case Literal(_: Int, IntegerType) =>
Literal(index)
Comment on lines +2011 to +2012
Copy link
Member

Choose a reason for hiding this comment

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

Is this only for IntegerType? If ordinalExpr is something like cast(long as int) that is foldable?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

I'm only fixing repeated analysis (analyzing an analyzed plan). It's a much bigger topic to support analyzing an optimized plan, so constant folding is not considered here.

case _ => ordinalExpr
}
}
} else {
throw QueryCompilationErrors.groupByPositionRangeError(index, aggs.size)
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -17,10 +17,11 @@

package org.apache.spark.sql.catalyst.analysis

import org.apache.spark.sql.catalyst.analysis.TestRelations.testRelation2
import org.apache.spark.sql.catalyst.analysis.TestRelations.{testRelation, testRelation2}
import org.apache.spark.sql.catalyst.dsl.expressions._
import org.apache.spark.sql.catalyst.dsl.plans._
import org.apache.spark.sql.catalyst.expressions.Literal
import org.apache.spark.sql.catalyst.expressions.{GenericInternalRow, Literal}
import org.apache.spark.sql.catalyst.plans.logical.LocalRelation
import org.apache.spark.sql.internal.SQLConf

class SubstituteUnresolvedOrdinalsSuite extends AnalysisTest {
Expand Down Expand Up @@ -67,4 +68,22 @@ class SubstituteUnresolvedOrdinalsSuite extends AnalysisTest {
testRelation2.groupBy(Literal(1), Literal(2))($"a", $"b"))
}
}

test("SPARK-45920: group by ordinal repeated analysis") {
val plan = testRelation.groupBy(Literal(1))(Literal(100).as("a")).analyze
comparePlans(
plan,
testRelation.groupBy(Literal(1))(Literal(100).as("a"))
)

val testRelationWithData = testRelation.copy(data = Seq(new GenericInternalRow(Array(1: Any))))
// Copy the plan to reset its `analyzed` flag, so that analyzer rules will re-apply.
val copiedPlan = plan.transform {
case _: LocalRelation => testRelationWithData
}
comparePlans(
copiedPlan.analyze, // repeated analysis
testRelationWithData.groupBy(Literal(1))(Literal(100).as("a"))
)
}
}
Original file line number Diff line number Diff line change
Expand Up @@ -61,7 +61,7 @@ Aggregate [a#x, a#x], [a#x, 1 AS 1#x, sum(b#x) AS sum(b)#xL]
-- !query
select a, 1, sum(b) from data group by 1, 2
-- !query analysis
Aggregate [a#x, 1], [a#x, 1 AS 1#x, sum(b#x) AS sum(b)#xL]
Aggregate [a#x, 2], [a#x, 1 AS 1#x, sum(b#x) AS sum(b)#xL]
+- SubqueryAlias data
+- View (`data`, [a#x,b#x])
+- Project [cast(a#x as int) AS a#x, cast(b#x as int) AS b#x]
Expand Down