jvanstraten commented on a change in pull request #12116:
URL: https://github.com/apache/arrow/pull/12116#discussion_r805894197
##########
File path: cpp/src/arrow/array/util.cc
##########
@@ -534,6 +533,152 @@ class NullArrayFactory {
std::shared_ptr<Buffer> buffer_;
};
+// mutable version of NullArrayFactory, i.e. one that doesn't reuse a single
buffer
+class MutableNullArrayFactory {
+ private:
+ Result<std::shared_ptr<Buffer>> CreateZeroByteBuffer(size_t
scalar_size_bytes) const {
+ ARROW_ASSIGN_OR_RAISE(auto buffer,
+ AllocateBuffer(length_ * scalar_size_bytes, pool_));
+ std::memset(buffer->mutable_data(), 0, buffer->size());
+ return std::shared_ptr<Buffer>(std::move(buffer));
+ }
+
+ Result<std::shared_ptr<Buffer>> CreateZeroOffsetBuffer(size_t
index_size_bytes) const {
+ ARROW_ASSIGN_OR_RAISE(auto buffer,
+ AllocateBuffer((length_ + 1) * index_size_bytes,
pool_));
+ std::memset(buffer->mutable_data(), 0, buffer->size());
+ return std::shared_ptr<Buffer>(std::move(buffer));
+ }
+
+ Result<std::shared_ptr<Buffer>> CreateZeroBitBuffer(size_t scalar_size_bits)
const {
+ ARROW_ASSIGN_OR_RAISE(
+ auto buffer,
+ AllocateBuffer(bit_util::BytesForBits(length_ * scalar_size_bits),
pool_));
+ std::memset(buffer->mutable_data(), 0, buffer->size());
+ return std::shared_ptr<Buffer>(std::move(buffer));
+ }
+
+ static Result<std::shared_ptr<Buffer>> CreateEmptyBuffer() { return
AllocateBuffer(0); }
+
+ public:
+ MutableNullArrayFactory(MemoryPool* pool, const std::shared_ptr<DataType>&
type,
+ int64_t length)
+ : pool_(pool), type_(type), length_(length) {}
+
+ Result<std::shared_ptr<ArrayData>> Create() {
+ std::vector<std::shared_ptr<ArrayData>> child_data(type_->num_fields());
+ ARROW_ASSIGN_OR_RAISE(auto validity, CreateZeroBitBuffer(1));
+ out_ = ArrayData::Make(type_, length_, {validity}, child_data, length_, 0);
+ RETURN_NOT_OK(VisitTypeInline(*type_, this));
+ return out_;
+ }
+
+ Status Visit(const NullType&) {
+ out_->buffers.resize(1, nullptr);
Review comment:
I just copied this from the original `NullArrayFactory`, and don't ask
me why, but at least the `ValidateLayout()` fails when `buffers` is empty. I'm
assuming there is code in Arrow that assumes that the `buffers[0]` entry always
exists and points to the values buffer, even if a type doesn't actually have a
values buffer, as this also explains the `nullptr` entry before the actual
buffer pointers for `UnionType`.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
