Skip to content

[GLUTEN-10963][VL] Fix the validation for merge_extract companion function #10976

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

Merged
jinchengchenghh merged 1 commit into from
Oct 29, 2025
Merged

[GLUTEN-10963][VL] Fix the validation for merge_extract companion function #10976

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
2 changes: 1 addition & 1 deletion backends-velox/src/test/scala/org/apache/gluten/execution/VeloxAggregateFunctionsSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -116,7 +116,7 @@ abstract class VeloxAggregateFunctionsSuite extends VeloxWholeStageTransformerSu
getExecutedPlan(df).count(
plan => {
plan.isInstanceOf[HashAggregateExecTransformer]
}) == 3)
}) == 4)
}
}
}
Expand Down
18 changes: 16 additions & 2 deletions cpp/velox/substrait/SubstraitToVeloxPlanValidator.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1167,8 +1167,22 @@ bool SubstraitToVeloxPlanValidator::validateAggRelFunctionType(const ::substrait
for (const auto& signature : signaturesOpt.value()) {
exec::SignatureBinder binder(*signature, types);
if (binder.tryBind()) {
auto resolveType = binder.tryResolveType(
exec::isPartialOutput(funcStep) ? signature->intermediateType() : signature->returnType());
TypePtr resolveType = nullptr;
try {
resolveType = binder.tryResolveType(
exec::isPartialOutput(funcStep) ? signature->intermediateType() : signature->returnType());
} catch (const VeloxException& e) {
if (!exec::isPartialOutput(funcStep) && funcName.find("merge_extract") != std::string::npos) {
// For the merge_extract companion function, result
// types may not always be inferable from the intermediate types. As a
// result, an exception might be thrown during the type resolution process. More
// details can be found in
// https://github.com/facebookincubator/velox/pull/11999#issuecomment-3274577979
// and https://github.com/facebookincubator/velox/issues/12830.
return true;
}
}

if (resolveType == nullptr) {
LOG_VALIDATION_MSG("Validation failed for function " + funcName + " resolve type in AggregateRel.");
return false;
Expand Down
2 changes: 0 additions & 2 deletions gluten-ut/spark32/src/test/scala/org/apache/gluten/utils/velox/VeloxTestSettings.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -139,8 +139,6 @@ class VeloxTestSettings extends BackendTestSettings {
.exclude("SPARK-22271: mean overflows and returns null for some decimal variables")
// Rewrite this test since it checks the physical operator which is changed in Gluten
.exclude("SPARK-27439: Explain result should match collected result after view change")
// https://github.com/apache/incubator-gluten/issues/10963
.exclude("SPARK-35955: Aggregate avg should not return wrong results for decimal overflow")

enableSuite[GlutenDataFrameNaFunctionsSuite]
.exclude(
Expand Down
2 changes: 0 additions & 2 deletions gluten-ut/spark33/src/test/scala/org/apache/gluten/utils/velox/VeloxTestSettings.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -721,8 +721,6 @@ class VeloxTestSettings extends BackendTestSettings {
.excludeGlutenTest("describe")
// Rewrite this test since it checks the physical operator which is changed in Gluten
.exclude("SPARK-27439: Explain result should match collected result after view change")
// https://github.com/apache/incubator-gluten/issues/10963
.exclude("SPARK-35955: Aggregate avg should not return wrong results for decimal overflow")
enableSuite[GlutenDataFrameTimeWindowingSuite]
enableSuite[GlutenDataFrameTungstenSuite]
enableSuite[GlutenDataFrameWindowFunctionsSuite]
Expand Down
2 changes: 0 additions & 2 deletions gluten-ut/spark34/src/test/scala/org/apache/gluten/utils/velox/VeloxTestSettings.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -770,8 +770,6 @@ class VeloxTestSettings extends BackendTestSettings {
.exclude("SPARK-41048: Improve output partitioning and ordering with AQE cache")
// Rewrite this test since it checks the physical operator which is changed in Gluten
.exclude("SPARK-27439: Explain result should match collected result after view change")
// https://github.com/apache/incubator-gluten/issues/10963
.exclude("SPARK-35955: Aggregate avg should not return wrong results for decimal overflow")
enableSuite[GlutenDataFrameTimeWindowingSuite]
enableSuite[GlutenDataFrameTungstenSuite]
enableSuite[GlutenDataFrameWindowFunctionsSuite]
Expand Down
2 changes: 0 additions & 2 deletions gluten-ut/spark35/src/test/scala/org/apache/gluten/utils/velox/VeloxTestSettings.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -790,8 +790,6 @@ class VeloxTestSettings extends BackendTestSettings {
.exclude("SPARK-41048: Improve output partitioning and ordering with AQE cache")
// Rewrite this test since it checks the physical operator which is changed in Gluten
.exclude("SPARK-27439: Explain result should match collected result after view change")
// https://github.com/apache/incubator-gluten/issues/10963
.exclude("SPARK-35955: Aggregate avg should not return wrong results for decimal overflow")
enableSuite[GlutenDataFrameTimeWindowingSuite]
enableSuite[GlutenDataFrameTungstenSuite]
enableSuite[GlutenDataFrameWindowFunctionsSuite]
Expand Down