Skip to content

YQ-3011 fix parquet type validation #3595

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
merged 1 commit into from
Apr 9, 2024
Merged

YQ-3011 fix parquet type validation #3595

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
28 changes: 27 additions & 1 deletion ydb/library/yql/providers/s3/provider/yql_s3_datasource_type_ann.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -282,6 +282,18 @@ bool ExtractSettingValue(const TExprNode& value, TStringBuf settingName, TString

}

bool EnsureParquetTypeSupported(TPositionHandle position, const TTypeAnnotationNode* type, TExprContext& ctx, const IArrowResolver::TPtr& arrowResolver) {
auto resolveStatus = arrowResolver->AreTypesSupported(ctx.GetPosition(position), { type }, ctx);
YQL_ENSURE(resolveStatus != IArrowResolver::ERROR);

if (resolveStatus != IArrowResolver::OK) {
ctx.AddError(TIssue(ctx.GetPosition(position), TStringBuilder() << "Type " << *type << " is not supported for parquet"));
return false;
}

return true;
}

class TS3DataSourceTypeAnnotationTransformer : public TVisitorTransformerBase {
public:
TS3DataSourceTypeAnnotationTransformer(TS3State::TPtr state)
Expand Down Expand Up @@ -407,7 +419,8 @@ class TS3DataSourceTypeAnnotationTransformer : public TVisitorTransformerBase {
return TStatus::Error;
}

if (!TS3Object::Match(input->Child(TS3ReadObject::idx_Object))) {
const auto& objectNode = input->Child(TS3ReadObject::idx_Object);
if (!TS3Object::Match(objectNode)) {
ctx.AddError(TIssue(ctx.GetPosition(input->Child(TS3ReadObject::idx_Object)->Pos()), "Expected S3 object."));
return TStatus::Error;
}
Expand Down Expand Up @@ -467,6 +480,19 @@ class TS3DataSourceTypeAnnotationTransformer : public TVisitorTransformerBase {
return TStatus::Error;
}

if (objectNode->Child(TS3Object::idx_Format)->Content() == "parquet") {
YQL_ENSURE(State_->Types->ArrowResolver);
bool allTypesSupported = true;
for (const auto& item : rowType->Cast<TStructExprType>()->GetItems()) {
if (!EnsureParquetTypeSupported(input->Pos(), item->GetItemType(), ctx, State_->Types->ArrowResolver)) {
allTypesSupported = false;
}
}
if (!allTypesSupported) {
return TStatus::Error;
}
}

input->SetTypeAnn(ctx.MakeType<TTupleExprType>(TTypeAnnotationNode::TListType{
input->Child(TS3ReadObject::idx_World)->GetTypeAnn(),
ctx.MakeType<TListExprType>(rowType)
Expand Down
9 changes: 0 additions & 9 deletions ydb/library/yql/providers/s3/provider/yql_s3_dq_integration.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -259,15 +259,6 @@ class TS3DqIntegration: public TDqIntegrationBase {

auto format = s3ReadObject.Object().Format().Ref().Content();
if (const auto useCoro = State_->Configuration->SourceCoroActor.Get(); (!useCoro || *useCoro) && format != "raw" && format != "json_list") {
if (format == "parquet") {
YQL_ENSURE(State_->Types->ArrowResolver);
TVector<const TTypeAnnotationNode*> allTypes;
for (const auto& x : rowType->Cast<TStructExprType>()->GetItems()) {
allTypes.push_back(x->GetItemType());
}
auto resolveStatus = State_->Types->ArrowResolver->AreTypesSupported(ctx.GetPosition(read->Pos()), allTypes, ctx);
YQL_ENSURE(resolveStatus == IArrowResolver::OK);
}
return Build<TDqSourceWrap>(ctx, read->Pos())
.Input<TS3ParseSettings>()
.Paths(s3ReadObject.Object().Paths())
Expand Down