Skip to content

GH-54924: [C++] HasVariadicBuffers should respect extension types #54925

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
taepper wants to merge 1 commit into
base: main
Choose a base branch
from
+27 −2
Open

GH-54924: [C++] HasVariadicBuffers should respect extension types #54925

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
20 changes: 20 additions & 0 deletions cpp/src/arrow/array/array_test.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1139,6 +1139,26 @@ TEST_F(TestArray, TestBinaryViewAppendArraySlice) {
AssertArraysEqual(*src, *dst);
}

// GH-54924: ArraySpan::HasVariadicBuffers must look through extension types.
TEST_F(TestArray, TestBinaryViewExtensionArraySpanRoundtrip) {
auto storage = ArrayFromJSON(
binary_view(),
R"([null, "short", "long string that is not inlined", "another somewhat long string"])");
auto extension_type = binary_view_extension_type();
auto extension_array = ExtensionType::WrapArray(extension_type, storage);
ASSERT_OK(extension_array->ValidateFull());

ArraySpan span(*extension_array->data());
ASSERT_TRUE(span.HasVariadicBuffers());
ASSERT_EQ(span.GetVariadicBuffers().size(), storage->data()->buffers.size() - 2);

auto roundtripped = span.ToArray();
ASSERT_OK(roundtripped->ValidateFull());
AssertArraysEqual(*extension_array, *roundtripped);
ASSERT_EQ(roundtripped->data()->buffers.size(),
extension_array->data()->buffers.size());
}

TEST_F(TestArray, ValidateBuffersPrimitive) {
auto empty_buffer = std::make_shared<Buffer>("");
auto null_buffer = Buffer::FromString("\xff");
Expand Down
9 changes: 7 additions & 2 deletions cpp/src/arrow/array/data.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -321,7 +321,7 @@ void ArraySpan::SetMembers(const ArrayData& data) {
this->buffers[i] = {};
}

if (type_id == Type::STRING_VIEW || type_id == Type::BINARY_VIEW) {
if (HasVariadicBuffers()) {
// store the span of data buffers in the third buffer
this->buffers[2] = internal::PackVariadicBuffers(std::span(data.buffers).subspan(2));
}
Expand Down Expand Up @@ -687,7 +687,12 @@ std::span<const std::shared_ptr<Buffer>> ArraySpan::GetVariadicBuffers() const {
}

bool ArraySpan::HasVariadicBuffers() const {
return type->id() == Type::BINARY_VIEW || type->id() == Type::STRING_VIEW;
Type::type type_id = type->id();
if (type_id == Type::EXTENSION) {
const auto* ext_type = checked_cast<const ExtensionType*>(type);
type_id = ext_type->storage_type()->id();
}
return type_id == Type::BINARY_VIEW || type_id == Type::STRING_VIEW;
}

std::shared_ptr<Array> ArraySpan::ToArray() const {
Expand Down
Loading