Skip to content

GH-33206: [C++] Add support for StructArray sorting and nested sort keys #35727

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
pitrou merged 8 commits into from
Jun 20, 2023
Merged

GH-33206: [C++] Add support for StructArray sorting and nested sort keys #35727

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
d49de5c
Initial sorting implementations
benibus May 23, 2023
29ebb40
Tweak tests
benibus May 30, 2023
f062177
Add note regarding column flattening
benibus May 30, 2023
8ec3693
Implement sorting full struct fields
benibus Jun 7, 2023
afb0234
Address review points
benibus Jun 19, 2023
6dbeee8
Avoid repeated DataType lookups
benibus Jun 19, 2023
d9ace64
Test deeper nesting levels
benibus Jun 19, 2023
c5e1c31
Encapsulate state in FindSortKeys
benibus Jun 19, 2023
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
23 changes: 22 additions & 1 deletion cpp/src/arrow/compute/kernels/vector_array_sort.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -262,6 +262,19 @@ class ArrayCompareSorter<DictionaryType> {
}
};

template <>
class ArrayCompareSorter<StructType> {
public:
Result<NullPartitionResult> operator()(uint64_t* indices_begin, uint64_t* indices_end,
const Array& array, int64_t offset,
const ArraySortOptions& options,
ExecContext* ctx) {
const auto& struct_array = checked_cast<const StructArray&>(array);
return SortStructArray(ctx, indices_begin, indices_end, struct_array, options.order,
options.null_placement);
}
};

template <typename ArrowType>
class ArrayCountSorter {
using ArrayType = typename TypeTraits<ArrowType>::ArrayType;
Expand Down Expand Up @@ -497,7 +510,7 @@ template <typename Type>
struct ArraySorter<
Type, enable_if_t<is_floating_type<Type>::value || is_base_binary_type<Type>::value ||
is_fixed_size_binary_type<Type>::value ||
is_dictionary_type<Type>::value>> {
is_dictionary_type<Type>::value || is_struct_type<Type>::value>> {
ArrayCompareSorter<Type> impl;
};

Expand Down Expand Up @@ -606,6 +619,13 @@ void AddDictArraySortingKernels(VectorKernel base, VectorFunction* func) {
DCHECK_OK(func->AddKernel(base));
}

template <template <typename...> class ExecTemplate>
void AddStructArraySortingKernels(VectorKernel base, VectorFunction* func) {
base.signature = KernelSignature::Make({Type::STRUCT}, uint64());
base.exec = ExecTemplate<UInt64Type, StructType>::Exec;
DCHECK_OK(func->AddKernel(base));
}

const ArraySortOptions* GetDefaultArraySortOptions() {
static const auto kDefaultArraySortOptions = ArraySortOptions::Defaults();
return &kDefaultArraySortOptions;
Expand Down Expand Up @@ -661,6 +681,7 @@ void RegisterVectorArraySort(FunctionRegistry* registry) {
base.exec_chunked = ArraySortIndicesChunked;
AddArraySortingKernels<ArraySortIndices>(base, array_sort_indices.get());
AddDictArraySortingKernels<ArraySortIndices>(base, array_sort_indices.get());
AddStructArraySortingKernels<ArraySortIndices>(base, array_sort_indices.get());
DCHECK_OK(registry->AddFunction(std::move(array_sort_indices)));

// partition_nth_indices has a parameter so needs its init function
Expand Down
Loading