Skip to content

GH-00000: [C++][Compute] Tighten case_when exact dispatch #80

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

Draft
zanmato1984 wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

GH-00000: [C++][Compute] Tighten case_when exact dispatch #80

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
14 changes: 6 additions & 8 deletions cpp/src/arrow/compute/kernels/scalar_if_else.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1494,13 +1494,10 @@ struct CaseWhenFunction : ScalarFunction {
return arrow::compute::detail::NoMatchingKernel(this, *types);
}

static std::shared_ptr<MatchConstraint> DecimalMatchConstraint() {
static std::shared_ptr<MatchConstraint> ValueTypesMatchConstraint() {
static auto constraint =
MatchConstraint::Make([](const std::vector<TypeHolder>& types) -> bool {
DCHECK_GE(types.size(), 2);
DCHECK(std::all_of(types.begin() + 1, types.end(), [](const TypeHolder& type) {
return is_decimal(type.id());
}));
return std::all_of(
types.begin() + 2, types.end(),
[&types](const TypeHolder& type) { return type == types[1]; });
Expand Down Expand Up @@ -2762,6 +2759,9 @@ struct ChooseFunction : ScalarFunction {
void AddCaseWhenKernel(const std::shared_ptr<CaseWhenFunction>& scalar_function,
detail::GetTypeId get_id, ArrayKernelExec exec,
std::shared_ptr<MatchConstraint> constraint = nullptr) {
if (constraint == nullptr) {
constraint = CaseWhenFunction::ValueTypesMatchConstraint();
}
ScalarKernel kernel(
KernelSignature::Make({InputType(Type::STRUCT), InputType(get_id.id)}, LastType,
/*is_varargs=*/true, std::move(constraint)),
Expand Down Expand Up @@ -2939,10 +2939,8 @@ void RegisterScalarIfElse(FunctionRegistry* registry) {
AddPrimitiveCaseWhenKernels(func, {boolean(), null(), float16()});
AddCaseWhenKernel(func, Type::FIXED_SIZE_BINARY,
CaseWhenFunctor<FixedSizeBinaryType>::Exec);
AddCaseWhenKernel(func, Type::DECIMAL128, CaseWhenFunctor<FixedSizeBinaryType>::Exec,
CaseWhenFunction::DecimalMatchConstraint());
AddCaseWhenKernel(func, Type::DECIMAL256, CaseWhenFunctor<FixedSizeBinaryType>::Exec,
CaseWhenFunction::DecimalMatchConstraint());
AddCaseWhenKernel(func, Type::DECIMAL128, CaseWhenFunctor<FixedSizeBinaryType>::Exec);
AddCaseWhenKernel(func, Type::DECIMAL256, CaseWhenFunctor<FixedSizeBinaryType>::Exec);
AddBinaryCaseWhenKernels(func, BaseBinaryTypes());
AddNestedCaseWhenKernels(func);
DCHECK_OK(registry->AddFunction(std::move(func)));
Expand Down
39 changes: 39 additions & 0 deletions cpp/src/arrow/compute/kernels/scalar_if_else_test.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2726,6 +2726,45 @@ TEST(TestCaseWhen, UnionBoolStringRandom) {
}

TEST(TestCaseWhen, DispatchExact) {
// Matching parameterized types should exact-match.
CheckDispatchExact("case_when",
{struct_({field("", boolean())}), fixed_size_binary(4),
fixed_size_binary(4)});
CheckDispatchExact("case_when",
{struct_({field("", boolean())}), list(int32()), list(int32())});
CheckDispatchExact(
"case_when",
{struct_({field("", boolean())}), fixed_size_list(int32(), 2),
fixed_size_list(int32(), 2)});
CheckDispatchExact(
"case_when",
{struct_({field("", boolean())}), dictionary(int8(), utf8()),
dictionary(int8(), utf8())});

// Mismatched parameterized types should not exact-match.
CheckDispatchExactFails("case_when",
{struct_({field("", boolean())}), fixed_size_binary(4),
fixed_size_binary(5)});
CheckDispatchExactFails("case_when",
{struct_({field("", boolean())}), list(int16()),
list(int32())});
CheckDispatchExactFails(
"case_when",
{struct_({field("", boolean())}), fixed_size_list(int32(), 2),
fixed_size_list(int32(), 3)});
CheckDispatchExactFails(
"case_when",
{struct_({field("", boolean())}), struct_({field("a", int32())}),
struct_({field("a", int64())})});
CheckDispatchExactFails(
"case_when",
{struct_({field("", boolean())}), dictionary(int8(), utf8()),
dictionary(int8(), large_utf8())});
CheckDispatchExactFails(
"case_when",
{struct_({field("", boolean())}), dictionary(int8(), utf8()),
dictionary(int16(), utf8())});

// Decimal types with same (p, s)
CheckDispatchExact("case_when", {struct_({field("", boolean())}), decimal128(20, 3),
decimal128(20, 3)});
Expand Down
Loading