westonpace commented on a change in pull request #8984:
URL: https://github.com/apache/arrow/pull/8984#discussion_r554220685
##########
File path: cpp/src/arrow/array/array_dict.cc
##########
@@ -44,6 +44,29 @@ namespace arrow {
using internal::checked_cast;
using internal::CopyBitmap;
+struct MaxIndexAccessor {
+ MaxIndexAccessor() {}
+
+ template <typename T>
+ enable_if_t<!is_integer_type<T>::value, Status> Visit(const T&) {
+ return Status::Invalid("Dictionary index types must be integer types");
+ }
+
+ template <typename T>
+ enable_if_integer<T, Status> Visit(const T&) {
+ max_index_value_ = std::numeric_limits<typename T::c_type>::max();
+ return Status::OK();
+ }
+
+ int64_t max_index_value_ = 0;
+};
+
+Result<int64_t> DictionaryIndexMaxValue(std::shared_ptr<DataType> index_type) {
Review comment:
Good catch. N/A anymore since using int_util.
##########
File path: cpp/src/arrow/array/concatenate.cc
##########
@@ -163,6 +163,46 @@ static Status PutOffsets(const std::shared_ptr<Buffer>&
src, Offset first_offset
return Status::OK();
}
+struct DictionaryConcatenate {
+ DictionaryConcatenate(BufferVector& index_buffers,
+ std::vector<std::shared_ptr<Buffer>>& index_lookup,
+ MemoryPool* pool)
+ : out_(nullptr),
+ index_buffers_(index_buffers),
+ index_lookup_(index_lookup),
+ pool_(pool) {}
+
+ template <typename T>
+ enable_if_t<!is_integer_type<T>::value, Status> Visit(const T& t) {
+ return Status::Invalid("Dictionary indices must be integral types");
+ }
+
+ template <typename T, typename CType = typename T::c_type>
+ enable_if_integer<T, Status> Visit(const T& index_type) {
+ int64_t out_length = 0;
+ for (const auto& buffer : index_buffers_) {
+ out_length += buffer->size();
+ }
+ ARROW_ASSIGN_OR_RAISE(out_, AllocateBuffer(out_length, pool_));
+ auto out_data = out_->mutable_data();
+ for (size_t i = 0; i < index_buffers_.size(); i++) {
+ auto buffer = index_buffers_[i];
+ auto old_indices = reinterpret_cast<const CType*>(buffer->data());
+ auto indices_map =
reinterpret_cast<int32_t*>(index_lookup_[i]->mutable_data());
Review comment:
Fixed.
##########
File path: cpp/src/arrow/array/concatenate.cc
##########
@@ -274,7 +329,12 @@ class ConcatenateImpl {
ARROW_ASSIGN_OR_RAISE(auto index_buffers, Buffers(1, *fixed));
return ConcatenateBuffers(index_buffers, pool_).Value(&out_->buffers[1]);
} else {
- return Status::NotImplemented("Concat with dictionary unification NYI");
+ ARROW_ASSIGN_OR_RAISE(auto index_buffers, Buffers(1, *fixed));
Review comment:
Fixed.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
