Skip to content

GH-54908: [C++] Reject non-empty union arrays with missing type ids or offsets buffers #54913

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

Open
JonSnow1807 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

GH-54908: [C++] Reject non-empty union arrays with missing type ids or offsets buffers #54913

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
47 changes: 47 additions & 0 deletions cpp/src/arrow/array/array_union_test.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -211,6 +211,53 @@ TEST(TestSparseUnionArray, Validate) {
ASSERT_RAISES(Invalid, arr->ValidateFull());
}

TEST(TestSparseUnionArray, ValidateMissingTypeIds) {
auto type = sparse_union({field("a", int32())});
auto children = ArrayDataVector{ArrayFromJSON(int32(), "[4, 5]")->data()};

auto data = ArrayData::Make(type, /*length=*/2, {nullptr, nullptr}, children);
ASSERT_RAISES_WITH_MESSAGE(Invalid,
"Invalid: Non-empty union array but type ids are null",
MakeArray(data)->Validate());
ASSERT_RAISES_WITH_MESSAGE(Invalid,
"Invalid: Non-empty union array but type ids are null",
MakeArray(data)->ValidateFull());

// An empty array does not need a type ids buffer
data = ArrayData::Make(type, /*length=*/0, {nullptr, nullptr}, children);
ASSERT_OK(MakeArray(data)->ValidateFull());
}

TEST(TestDenseUnionArray, ValidateMissingBuffers) {
auto type = dense_union({field("a", int32())});
auto children = ArrayDataVector{ArrayFromJSON(int32(), "[7]")->data()};
auto type_ids = ArrayFromJSON(int8(), "[0]")->data()->buffers[1];
auto offsets = ArrayFromJSON(int32(), "[0]")->data()->buffers[1];

auto data = ArrayData::Make(type, /*length=*/1, {nullptr, nullptr, offsets}, children);
ASSERT_RAISES_WITH_MESSAGE(Invalid,
"Invalid: Non-empty union array but type ids are null",
MakeArray(data)->Validate());
ASSERT_RAISES_WITH_MESSAGE(Invalid,
"Invalid: Non-empty union array but type ids are null",
MakeArray(data)->ValidateFull());

data = ArrayData::Make(type, /*length=*/1, {nullptr, type_ids, nullptr}, children);
ASSERT_RAISES_WITH_MESSAGE(Invalid,
"Invalid: Non-empty dense union array but offsets are null",
MakeArray(data)->Validate());
ASSERT_RAISES_WITH_MESSAGE(Invalid,
"Invalid: Non-empty dense union array but offsets are null",
MakeArray(data)->ValidateFull());

data = ArrayData::Make(type, /*length=*/1, {nullptr, type_ids, offsets}, children);
ASSERT_OK(MakeArray(data)->ValidateFull());

// An empty array does not need type ids or offsets buffers
data = ArrayData::Make(type, /*length=*/0, {nullptr, nullptr, nullptr}, children);
ASSERT_OK(MakeArray(data)->ValidateFull());
}

TEST(TestSparseUnionArray, Comparison) {
auto ints1 = ArrayFromJSON(int32(), "[1, 2, 3, 4, 5, 6]");
auto ints2 = ArrayFromJSON(int32(), "[1, 2, -3, 4, -5, 6]");
Expand Down
9 changes: 9 additions & 0 deletions cpp/src/arrow/array/validate.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -334,6 +334,15 @@ struct ValidateArrayImpl {
}

Status Visit(const UnionType& type) {
if (data.length > 0) {
if (!IsBufferValid(1)) {
return Status::Invalid("Non-empty union array but type ids are null");
}
if (type.mode() == UnionMode::DENSE && !IsBufferValid(2)) {
return Status::Invalid("Non-empty dense union array but offsets are null");
}
}

for (int i = 0; i < type.num_fields(); ++i) {
const auto& field_data = *data.child_data[i];

Expand Down
Loading