Skip to content

fix(manifest): validate struct child lengths #1054

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
wgtmac merged 2 commits into from
Oct 28, 2026
Merged

fix(manifest): validate struct child lengths #1054

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
daf5377
fix(manifest): reject struct children longer than their parent length
gty404 Oct 23, 2026
6c04427
fix(manifest): validate struct child lengths
wgtmac Oct 28, 2026
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
14 changes: 14 additions & 0 deletions src/iceberg/manifest/manifest_reader.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,6 +57,16 @@ namespace {
return InvalidArgument("Required field '{}' is null at row {}", field_name, row_idx);
}

[[nodiscard]] Status ValidateStructLength(const ArrowArrayView* view,
std::string_view field_name) {
for (int64_t i = 0; i < view->n_children; ++i) {
ICEBERG_CHECK(view->children[i]->length == view->length,
"Field '{}' child {} should have length {} matching its parent, got {}",
field_name, i, view->length, view->children[i]->length);
}
return {};
}

[[nodiscard]] Status AssertViewType(const ArrowArrayView* view, ArrowType expected_type,
std::string_view field_name) {
if (view->storage_type != expected_type) {
Expand Down Expand Up @@ -318,6 +328,7 @@ Result<std::vector<ManifestFile>> ParseManifestList(ArrowSchema* arrow_schema,

ICEBERG_RETURN_UNEXPECTED(AssertViewTypeAndChildren(
&view, ArrowType::NANOARROW_TYPE_STRUCT, schema.fields().size(), "manifest_list"));
ICEBERG_RETURN_UNEXPECTED(ValidateStructLength(&view, "manifest_list"));

std::vector<ManifestFile> manifest_files;
manifest_files.resize(array->length);
Expand Down Expand Up @@ -476,6 +487,7 @@ Status ParseDataFile(const std::shared_ptr<StructType>& data_file_schema,
ICEBERG_RETURN_UNEXPECTED(
AssertViewTypeAndChildren(view, ArrowType::NANOARROW_TYPE_STRUCT,
data_file_schema->fields().size(), "data_file"));
ICEBERG_RETURN_UNEXPECTED(ValidateStructLength(view, "data_file"));

for (int64_t col_idx = 0; col_idx < view->n_children; ++col_idx) {
ICEBERG_ASSIGN_OR_RAISE(auto field, data_file_schema->GetFieldByIndex(col_idx));
Expand Down Expand Up @@ -515,6 +527,7 @@ Status ParseDataFile(const std::shared_ptr<StructType>& data_file_schema,
case DataFile::kPartitionFieldId: {
ICEBERG_RETURN_UNEXPECTED(
AssertViewType(field_view, ArrowType::NANOARROW_TYPE_STRUCT, field_name));
ICEBERG_RETURN_UNEXPECTED(ValidateStructLength(field_view, field_name));
const auto& partition_type =
internal::checked_cast<const StructType&>(*field->get().type());
for (int64_t part_idx = 0; part_idx < field_view->n_children; part_idx++) {
Expand Down Expand Up @@ -647,6 +660,7 @@ Result<std::vector<ManifestEntry>> ParseManifestEntry(

ICEBERG_RETURN_UNEXPECTED(AssertViewTypeAndChildren(
&view, ArrowType::NANOARROW_TYPE_STRUCT, schema.fields().size(), "manifest_entry"));
ICEBERG_RETURN_UNEXPECTED(ValidateStructLength(&view, "manifest_entry"));

std::vector<ManifestEntry> manifest_entries;
manifest_entries.resize(array->length);
Expand Down
Loading