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-42851][SQL] Guard EquivalentExpressions.addExpr() with supportedExpression() #40473

Closed
wants to merge 3 commits 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.
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 @@ -40,7 +40,11 @@ class EquivalentExpressions {
* Returns true if there was already a matching expression.
*/
def addExpr(expr: Expression): Boolean = {
updateExprInMap(expr, equivalenceMap)
if (supportedExpression(expr)) {
updateExprInMap(expr, equivalenceMap)
} else {
false
}
}

/**
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,7 @@ import org.apache.spark.sql.catalyst.InternalRow
import org.apache.spark.sql.catalyst.expressions.codegen._
import org.apache.spark.sql.catalyst.plans.logical.LocalRelation
import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.types.{BinaryType, DataType, IntegerType}
import org.apache.spark.sql.types.{BinaryType, DataType, IntegerType, ObjectType}

class SubexpressionEliminationSuite extends SparkFunSuite with ExpressionEvalHelper {
test("Semantic equals and hash") {
Expand Down Expand Up @@ -449,6 +449,22 @@ class SubexpressionEliminationSuite extends SparkFunSuite with ExpressionEvalHel
assert(e2.getCommonSubexpressions.size == 1)
assert(e2.getCommonSubexpressions.head == add)
}

test("SPARK-42851: Handle supportExpression consistently across add and get") {
val expr = {
val function = (lambda: Expression) => Add(lambda, Literal(1))
val elementType = IntegerType
val colClass = classOf[Array[Int]]
val inputType = ObjectType(colClass)
val inputObject = BoundReference(0, inputType, nullable = true)
objects.MapObjects(function, inputObject, elementType, true, Option(colClass))
}
val equivalence = new EquivalentExpressions
equivalence.addExpr(expr)
val hasMatching = equivalence.addExpr(expr)
val cseState = equivalence.getExprState(expr)
assert(hasMatching == cseState.isDefined)
}
}

case class CodegenFallbackExpression(child: Expression)
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -1538,6 +1538,13 @@ class DataFrameAggregateSuite extends QueryTest
)
checkAnswer(res, Row(1, 1, 1) :: Row(4, 1, 2) :: Nil)
}

test("SPARK-42851: common subexpression should consistently handle aggregate and result exprs") {
val res = sql(
"select max(transform(array(id), x -> x)), max(transform(array(id), x -> x)) from range(2)"
)
checkAnswer(res, Row(Array(1), Array(1)))
}
}

case class B(c: Option[Double])
Expand Down