Skip to content
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.

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

[SPARK-45920][SQL][3.4] group by ordinal should be idempotent #43838

Closed
wants to merge 1 commit into from
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.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
Expand Up @@ -1993,7 +1993,19 @@ 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)
case _ => ordinalExpr
}
}
} else {
throw QueryCompilationErrors.groupByPositionRangeError(index, aggs.size)
Expand Down
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"))
)
}
}