Skip to content

[SPARK-35636][SQL] Lambda keys should not be referenced outside of the lambda function #32773

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
karenfeng wants to merge 1 commit into from
Closed

[SPARK-35636][SQL] Lambda keys should not be referenced outside of the lambda function #32773

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
10 changes: 10 additions & 0 deletions ...alyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,6 +88,9 @@ case class NamedLambdaVariable(
AttributeReference(name, dataType, nullable, Metadata.empty)(exprId, Seq.empty)
}

// Check if this lambda variable is referenced outside the lambda function it is bound to
override def references: AttributeSet = AttributeSet(toAttribute)

override def eval(input: InternalRow): Any = value.get

override def toString: String = s"lambda $name#${exprId.id}$typeSuffix"
Expand All @@ -113,6 +116,13 @@ case class LambdaFunction(
override def nullable: Boolean = function.nullable
final override val nodePatterns: Seq[TreePattern] = Seq(LAMBDA_FUNCTION)

// Check if lambda variables bound to this lambda function are referenced in the wrong scope
override def references: AttributeSet = if (resolved) {
function.references -- AttributeSet(arguments.flatMap(_.references))
} else {
super.references
}

lazy val bound: Boolean = arguments.forall(_.resolved)

override def eval(input: InternalRow): Any = function.eval(input)
Expand Down
32 changes: 31 additions & 1 deletion ...st/src/test/scala/org/apache/spark/sql/catalyst/optimizer/NestedColumnAliasingSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,9 +23,10 @@ import org.apache.spark.sql.catalyst.SchemaPruningTest
import org.apache.spark.sql.catalyst.dsl.expressions._
import org.apache.spark.sql.catalyst.dsl.plans._
import org.apache.spark.sql.catalyst.expressions._
import org.apache.spark.sql.catalyst.plans.Cross
import org.apache.spark.sql.catalyst.plans.logical._
import org.apache.spark.sql.catalyst.rules.RuleExecutor
import org.apache.spark.sql.types.{StringType, StructField, StructType}
import org.apache.spark.sql.types.{IntegerType, StringType, StructField, StructType}

class NestedColumnAliasingSuite extends SchemaPruningTest {

Expand Down Expand Up @@ -708,6 +709,35 @@ class NestedColumnAliasingSuite extends SchemaPruningTest {
.analyze
comparePlans(optimized, expected)
}

test("SPARK-35636: do not push lambda key out of lambda function") {
val rel = LocalRelation(
'kvs.map(StringType, new StructType().add("v1", IntegerType)), 'keys.array(StringType))
val key = UnresolvedNamedLambdaVariable("key" :: Nil)
val lambda = LambdaFunction('kvs.getItem(key).getField("v1"), key :: Nil)
val query = rel
.limit(5)
.select('keys, 'kvs)
.limit(5)
.select(ArrayTransform('keys, lambda).as("a"))
.analyze
val optimized = Optimize.execute(query)
comparePlans(optimized, query)
}

test("SPARK-35636: do not push down extract value in higher order " +
"function that references both sides of a join") {
val left = LocalRelation('kvs.map(StringType, new StructType().add("v1", IntegerType)))
val right = LocalRelation('keys.array(StringType))
val key = UnresolvedNamedLambdaVariable("key" :: Nil)
val lambda = LambdaFunction('kvs.getItem(key).getField("v1"), key :: Nil)
val query = left
.join(right, Cross, None)
.select(ArrayTransform('keys, lambda).as("a"))
.analyze
val optimized = Optimize.execute(query)
comparePlans(optimized, query)
}
}

object NestedColumnAliasingSuite {
Expand Down