Skip to content

GH-50624: [C++][Compute] Tighten case_when exact dispatch for parameterized types #50625

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
zanmato1984 wants to merge 1 commit into
base: main
Choose a base branch
from
+88 −32
Open

GH-50624: [C++][Compute] Tighten case_when exact dispatch for parameterized types #50625

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
68 changes: 36 additions & 32 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 @@ -1495,13 +1495,11 @@ struct CaseWhenFunction : ScalarFunction {
return arrow::compute::detail::NoMatchingKernel(this, *types);
}

static std::shared_ptr<MatchConstraint> DecimalMatchConstraint() {
// For case_when exact dispatch, all value arguments must have identical DataType.
static std::shared_ptr<MatchConstraint> AllValueTypesMatchConstraint() {
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 @@ -2738,7 +2736,7 @@ struct ChooseFunction : ScalarFunction {

void AddCaseWhenKernel(const std::shared_ptr<CaseWhenFunction>& scalar_function,
detail::GetTypeId get_id, ArrayKernelExec exec,
std::shared_ptr<MatchConstraint> constraint = nullptr) {
std::shared_ptr<MatchConstraint> constraint) {
ScalarKernel kernel(
KernelSignature::Make({InputType(Type::STRUCT), InputType(get_id.id)}, LastType,
/*is_varargs=*/true, std::move(constraint)),
Expand All @@ -2756,38 +2754,42 @@ void AddCaseWhenKernel(const std::shared_ptr<CaseWhenFunction>& scalar_function,
}

void AddPrimitiveCaseWhenKernels(const std::shared_ptr<CaseWhenFunction>& scalar_function,
const std::vector<std::shared_ptr<DataType>>& types) {
const std::vector<std::shared_ptr<DataType>>& types,
std::shared_ptr<MatchConstraint> constraint) {
for (auto&& type : types) {
auto exec = GenerateTypeAgnosticPrimitive<CaseWhenFunctor>(*type);
AddCaseWhenKernel(scalar_function, type, std::move(exec));
AddCaseWhenKernel(scalar_function, type, std::move(exec), constraint);
}
}

void AddBinaryCaseWhenKernels(const std::shared_ptr<CaseWhenFunction>& scalar_function,
const std::vector<std::shared_ptr<DataType>>& types) {
const std::vector<std::shared_ptr<DataType>>& types,
std::shared_ptr<MatchConstraint> constraint) {
for (auto&& type : types) {
auto exec = GenerateTypeAgnosticVarBinaryBase<CaseWhenFunctor>(*type);
AddCaseWhenKernel(scalar_function, type, std::move(exec));
AddCaseWhenKernel(scalar_function, type, std::move(exec), constraint);
}
}

template <typename ArrowNestedType>
void AddNestedCaseWhenKernel(const std::shared_ptr<CaseWhenFunction>& scalar_function) {
void AddNestedCaseWhenKernel(const std::shared_ptr<CaseWhenFunction>& scalar_function,
std::shared_ptr<MatchConstraint> constraint) {
AddCaseWhenKernel(scalar_function, ArrowNestedType::type_id,
CaseWhenFunctor<ArrowNestedType>::Exec);
CaseWhenFunctor<ArrowNestedType>::Exec, constraint);
}

void AddNestedCaseWhenKernels(const std::shared_ptr<CaseWhenFunction>& scalar_function) {
AddNestedCaseWhenKernel<FixedSizeListType>(scalar_function);
AddNestedCaseWhenKernel<ListType>(scalar_function);
AddNestedCaseWhenKernel<LargeListType>(scalar_function);
AddNestedCaseWhenKernel<ListViewType>(scalar_function);
AddNestedCaseWhenKernel<LargeListViewType>(scalar_function);
AddNestedCaseWhenKernel<MapType>(scalar_function);
AddNestedCaseWhenKernel<StructType>(scalar_function);
AddNestedCaseWhenKernel<DenseUnionType>(scalar_function);
AddNestedCaseWhenKernel<SparseUnionType>(scalar_function);
AddNestedCaseWhenKernel<DictionaryType>(scalar_function);
void AddNestedCaseWhenKernels(const std::shared_ptr<CaseWhenFunction>& scalar_function,
std::shared_ptr<MatchConstraint> constraint) {
AddNestedCaseWhenKernel<FixedSizeListType>(scalar_function, constraint);
AddNestedCaseWhenKernel<ListType>(scalar_function, constraint);
AddNestedCaseWhenKernel<LargeListType>(scalar_function, constraint);
AddNestedCaseWhenKernel<ListViewType>(scalar_function, constraint);
AddNestedCaseWhenKernel<LargeListViewType>(scalar_function, constraint);
AddNestedCaseWhenKernel<MapType>(scalar_function, constraint);
AddNestedCaseWhenKernel<StructType>(scalar_function, constraint);
AddNestedCaseWhenKernel<DenseUnionType>(scalar_function, constraint);
AddNestedCaseWhenKernel<SparseUnionType>(scalar_function, constraint);
AddNestedCaseWhenKernel<DictionaryType>(scalar_function, constraint);
}

void AddCoalesceKernel(const std::shared_ptr<ScalarFunction>& scalar_function,
Expand Down Expand Up @@ -2909,19 +2911,21 @@ void RegisterScalarIfElse(FunctionRegistry* registry) {
{
auto func = std::make_shared<CaseWhenFunction>(
"case_when", Arity::VarArgs(/*min_args=*/2), case_when_doc);
AddPrimitiveCaseWhenKernels(func, NumericTypes());
AddPrimitiveCaseWhenKernels(func, TemporalTypes());
AddPrimitiveCaseWhenKernels(func, IntervalTypes());
AddPrimitiveCaseWhenKernels(func, DurationTypes());
AddPrimitiveCaseWhenKernels(func, {boolean(), null(), float16()});
auto all_value_types_match = CaseWhenFunction::AllValueTypesMatchConstraint();
AddPrimitiveCaseWhenKernels(func, NumericTypes(), all_value_types_match);
AddPrimitiveCaseWhenKernels(func, TemporalTypes(), all_value_types_match);
AddPrimitiveCaseWhenKernels(func, IntervalTypes(), all_value_types_match);
AddPrimitiveCaseWhenKernels(func, DurationTypes(), all_value_types_match);
AddPrimitiveCaseWhenKernels(func, {boolean(), null(), float16()},
all_value_types_match);
AddCaseWhenKernel(func, Type::FIXED_SIZE_BINARY,
CaseWhenFunctor<FixedSizeBinaryType>::Exec);
CaseWhenFunctor<FixedSizeBinaryType>::Exec, all_value_types_match);
AddCaseWhenKernel(func, Type::DECIMAL128, CaseWhenFunctor<FixedSizeBinaryType>::Exec,
CaseWhenFunction::DecimalMatchConstraint());
all_value_types_match);
AddCaseWhenKernel(func, Type::DECIMAL256, CaseWhenFunctor<FixedSizeBinaryType>::Exec,
CaseWhenFunction::DecimalMatchConstraint());
AddBinaryCaseWhenKernels(func, BaseBinaryTypes());
AddNestedCaseWhenKernels(func);
all_value_types_match);
AddBinaryCaseWhenKernels(func, BaseBinaryTypes(), all_value_types_match);
AddNestedCaseWhenKernels(func, all_value_types_match);
DCHECK_OK(registry->AddFunction(std::move(func)));
}
{
Expand Down
52 changes: 52 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 +2726,36 @@ 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 Expand Up @@ -2825,6 +2855,28 @@ TEST(TestCaseWhen, DispatchBest) {
{struct_({field("", boolean())}), decimal256(23, 3), decimal256(23, 3)});
}

TEST(TestCaseWhen, ParameterizedValueTypeMismatch) {
auto cond = MakeStruct({ArrayFromJSON(boolean(), "[true]")});

ASSERT_RAISES(
NotImplemented,
CallFunction("case_when", {cond, ArrayFromJSON(fixed_size_binary(4), R"(["abcd"])"),
ArrayFromJSON(fixed_size_binary(5), R"(["efghi"])")}));
ASSERT_RAISES(NotImplemented,
CallFunction("case_when", {cond, ArrayFromJSON(list(int16()), "[[1, 2]]"),
ArrayFromJSON(list(int32()), "[[3, 4]]")}));
ASSERT_RAISES(
NotImplemented,
CallFunction("case_when",
{cond, ArrayFromJSON(fixed_size_list(int32(), 2), "[[1, 2]]"),
ArrayFromJSON(fixed_size_list(int32(), 3), "[[3, 4, 5]]")}));
ASSERT_RAISES(
NotImplemented,
CallFunction("case_when",
{cond, ArrayFromJSON(struct_({field("a", int32())}), R"([{"a": 1}])"),
ArrayFromJSON(struct_({field("a", int64())}), R"([{"a": 2}])")}));
}

template <typename Type>
class TestCoalesceNumeric : public ::testing::Test {};
template <typename Type>
Expand Down
Loading