mihailom-db commented on code in PR #45383:
URL: https://github.com/apache/spark/pull/45383#discussion_r1533863046
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercion.scala:
##########
@@ -764,6 +773,184 @@ abstract class TypeCoercionBase {
}
}
+ object CollationTypeCasts extends TypeCoercionRule {
+ override val transform: PartialFunction[Expression, Expression] = {
+ case e if !e.childrenResolved => e
+
+ case checkCastWithIndeterminate: Concat
+ if shouldCast(checkCastWithIndeterminate.children) =>
+ val newChildren =
+ collateToSingleType(checkCastWithIndeterminate.children,
failOnIndeterminate = false)
+ checkCastWithIndeterminate.withNewChildren(newChildren)
+
+ case checkCastWithoutIndeterminate@(_: BinaryExpression | _: In | _:
SortOrder)
+ if shouldCast(checkCastWithoutIndeterminate.children) =>
+ val newChildren =
collateToSingleType(checkCastWithoutIndeterminate.children)
+ checkCastWithoutIndeterminate.withNewChildren(newChildren)
+
+ case checkIndeterminate@(_: BinaryExpression | _: In | _: SortOrder)
+ if hasIndeterminate(checkIndeterminate.children
+ .filter(e => hasStringType(e.dataType))
+ .map(e => extractStringType(e.dataType))) =>
+ throw QueryCompilationErrors.indeterminateCollationError()
+
+ case checkImplicitCastInputTypes: ImplicitCastInputTypes
+ if checkImplicitCastInputTypes.children.exists(e =>
hasStringType(e.dataType))
+ && checkImplicitCastInputTypes.inputTypes.nonEmpty =>
+ val collationId: Int =
+ getOutputCollation(checkImplicitCastInputTypes
+ .children.filter { e => hasStringType(e.dataType) })
+ val children: Seq[Expression] = checkImplicitCastInputTypes
+ .children.zip(checkImplicitCastInputTypes.inputTypes).map {
+ case (e, st) if hasStringType(st) =>
+ castStringType(e, collationId, Some(st)).getOrElse(e)
+ case (e, TypeCollection(types)) if types.exists(hasStringType) =>
+ types.flatMap{ dt =>
+ if (hasStringType(dt)) {
+ castStringType(e, collationId, Some(dt))
+ } else {
+ implicitCast(e, dt)
+ }
+ }.headOption.getOrElse(e)
+ case (in, expected) => implicitCast(in, expected).getOrElse(in)
+ }
+ checkImplicitCastInputTypes.withNewChildren(children)
+
+ case checkExpectsInputType: ExpectsInputTypes
+ if checkExpectsInputType.children.exists(e =>
hasStringType(e.dataType))
+ && checkExpectsInputType.inputTypes.nonEmpty =>
+ val collationId: Int = getOutputCollation(
+ checkExpectsInputType.children.filter {e =>
hasStringType(e.dataType)})
+ val children: Seq[Expression] = checkExpectsInputType
+ .children.zip(checkExpectsInputType.inputTypes).map {
+ case (st, _) if hasStringType(st.dataType) =>
+ castStringType(st, collationId).getOrElse(st)
+ case (nt, e)
+ if hasStringType(e) && nt.dataType == NullType =>
+ castStringType(nt, collationId, Some(e)).getOrElse(nt)
+ case (nt, e: TypeCollection)
+ if hasStringType(e.defaultConcreteType) && nt.dataType ==
NullType =>
+ castStringType(nt, collationId,
Some(e.defaultConcreteType)).getOrElse(nt)
+ case (in, _) => in
+ }
+ checkExpectsInputType.withNewChildren(children)
+ }
+
+ def shouldCast(types: Seq[Expression]): Boolean = {
+ types.filter(e => hasStringType(e.dataType))
+ .map(e => extractStringType(e.dataType).collationId).distinct.size > 1
+ }
+
+ /**
+ * Whether the data type contains StringType.
+ */
+ @tailrec
Review Comment:
This is not possible for now. I think this PR is already too big and if I
change it to this I need to deal with StructType and MapType. I suggest we
leave those two for follow-up PR.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
