ARROW-14108: [C++] interval_between(timestamptz, timestamptz) -> struct kernel#12477

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

Closed
rok wants to merge 1 commit into from
Closed

ARROW-14108: [C++] interval_between(timestamptz, timestamptz) -> struct kernel #12477

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
305 changes: 305 additions & 0 deletions cpp/src/arrow/compute/kernels/scalar_temporal_binary.cc
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -61,10 +61,16 @@ using arrow_vendored::date::literals::sun;
using arrow_vendored::date::literals::thu;
using arrow_vendored::date::literals::wed;
using internal::applicator::ScalarBinaryNotNullStatefulEqualTypes;
using internal::applicator::SimpleBinary;

using DayOfWeekState = OptionsWrapper<DayOfWeekOptions>;
using WeekState = OptionsWrapper<WeekOptions>;

const std::shared_ptr<DataType>& DayHoursType() {
static auto type = struct_({field("days", int32()), field("hours", int32())});
return type;
}

Status CheckTimezones(const ExecBatch& batch) {
const auto& timezone = GetInputTimezone(batch.values[0]);
for (int i = 1; i < batch.num_values(); i++) {
Expand DownExpand Up@@ -275,6 +281,272 @@ struct DayTimeBetween {
Localizer localizer_;
};

template <typename Duration, typename Localizer>
std::array<int32_t, 2> GetDayHoursBetween(int64_t arg0, int64_t arg1,
Localizer&& localizer) {
auto from = localizer.template ConvertTimePoint<Duration>(arg0);
auto to = localizer.template ConvertTimePoint<Duration>(arg1);
const int32_t num_days =
static_cast<int32_t>((floor<days>(to) - floor<days>(from)).count());
auto from_time = static_cast<int32_t>(
std::chrono::duration_cast<std::chrono::milliseconds>(from - floor<days>(from))
.count());
auto to_time = static_cast<int32_t>(
std::chrono::duration_cast<std::chrono::milliseconds>(to - floor<days>(to))
.count());
const int32_t num_millis = to_time - from_time;
return {num_days, num_millis / 3600000};
}

template <typename Duration, typename InType>
struct DayHoursBetweenWrapper {
static Result<std::array<int32_t, 2>> Get(const Scalar& arg0, const Scalar& arg1) {
const auto& arg0_val = internal::UnboxScalar<const InType>::Unbox(arg0);
const auto& arg1_val = internal::UnboxScalar<const InType>::Unbox(arg1);
return GetDayHoursBetween<Duration>(arg0_val, arg1_val, NonZonedLocalizer{});
}
};

template <typename Duration>
struct DayHoursBetweenWrapper<Duration, TimestampType> {
static Result<std::array<int32_t, 2>> Get(const Scalar& arg0, const Scalar& arg1) {
const auto& arg0_val = internal::UnboxScalar<const TimestampType>::Unbox(arg0);
const auto& arg1_val = internal::UnboxScalar<const TimestampType>::Unbox(arg1);
const auto& timezone0 = GetInputTimezone(arg0);
const auto& timezone1 = GetInputTimezone(arg1);
if (timezone0 != timezone1) {
return Status::Invalid(timezone0, " != ", timezone1);
}
if (timezone0.empty()) {
return GetDayHoursBetween<Duration>(arg0_val, arg1_val, NonZonedLocalizer{});
} else {
ARROW_ASSIGN_OR_RAISE(auto tz, LocateZone(timezone0));
return GetDayHoursBetween<Duration>(arg0_val, arg1_val, ZonedLocalizer{tz});
}
}
};

template <typename Duration, typename InType, typename BuilderType>
struct DayHoursBetweenVisitValueFunction {
static Result<std::function<void(typename InType::c_type, typename InType::c_type)>>
Get(const std::vector<BuilderType*>& field_builders, const ArrayData&, const ArrayData&,
StructBuilder* struct_builder) {
return [=](typename InType::c_type arg0, typename InType::c_type arg1) {
const auto day_hours_between =
GetDayHoursBetween<Duration>(arg0, arg1, NonZonedLocalizer{});
field_builders[0]->UnsafeAppend(day_hours_between[0]);
field_builders[1]->UnsafeAppend(day_hours_between[1]);
DCHECK_OK(struct_builder->Append());
};
}
};

template <typename Duration, typename BuilderType>
struct DayHoursBetweenVisitValueFunction<Duration, TimestampType, BuilderType> {
static Result<
std::function<void(typename TimestampType::c_type, typename TimestampType::c_type)>>
Get(const std::vector<BuilderType*>& field_builders, const ArrayData& in0,
const ArrayData& in1, StructBuilder* struct_builder) {
const auto& timezone0 = GetInputTimezone(in0);
const auto& timezone1 = GetInputTimezone(in1);
if (timezone0 != timezone1) {
return Status::Invalid(timezone0, " != ", timezone1);
}
if (timezone0.empty()) {
return [=](TimestampType::c_type arg0, TimestampType::c_type arg1) {
const auto day_hours_between =
GetDayHoursBetween<Duration>(arg0, arg1, NonZonedLocalizer{});
field_builders[0]->UnsafeAppend(day_hours_between[0]);
field_builders[1]->UnsafeAppend(day_hours_between[1]);
DCHECK_OK(struct_builder->Append());
};
}
ARROW_ASSIGN_OR_RAISE(auto tz, LocateZone(timezone0));
return [=](TimestampType::c_type arg0, TimestampType::c_type arg1) {
const auto day_hours_between =
GetDayHoursBetween<Duration>(arg0, arg1, ZonedLocalizer{tz});
field_builders[0]->UnsafeAppend(day_hours_between[0]);
field_builders[1]->UnsafeAppend(day_hours_between[1]);
DCHECK_OK(struct_builder->Append());
};
}
};

template <typename Duration, typename InType, typename BuilderType>
struct DayHoursBetweenVisitValueFunction2 {
static Result<std::function<Status(typename InType::c_type)>> Get(
const std::vector<BuilderType*>& field_builders, const Scalar& in0,
const ArrayData&, StructBuilder* struct_builder) {
const auto& in0_val = internal::UnboxScalar<const InType>::Unbox(in0);

return [=](typename InType::c_type arg1) {
const auto day_hours_between =
GetDayHoursBetween<Duration>(in0_val, arg1, NonZonedLocalizer{});
field_builders[0]->UnsafeAppend(day_hours_between[0]);
field_builders[1]->UnsafeAppend(day_hours_between[1]);
return struct_builder->Append();
};
}

static Result<std::function<Status(typename InType::c_type)>> Get(
const std::vector<BuilderType*>& field_builders, const ArrayData&,
const Scalar& in1, StructBuilder* struct_builder) {
const auto& in1_val = internal::UnboxScalar<const InType>::Unbox(in1);

return [=](typename InType::c_type arg0) {
const auto day_hours_between =
GetDayHoursBetween<Duration>(arg0, in1_val, NonZonedLocalizer{});
field_builders[0]->UnsafeAppend(day_hours_between[0]);
field_builders[1]->UnsafeAppend(day_hours_between[1]);
return struct_builder->Append();
};
}
};

template <typename Duration, typename BuilderType>
struct DayHoursBetweenVisitValueFunction2<Duration, TimestampType, BuilderType> {
static Result<std::function<Status(typename TimestampType::c_type)>> Get(
const std::vector<BuilderType*>& field_builders, const Scalar& in0,
const ArrayData&, StructBuilder* struct_builder) {
const auto& in0_val = internal::UnboxScalar<const TimestampType>::Unbox(in0);

return [=](typename TimestampType::c_type arg1) {
const auto day_hours_between =
GetDayHoursBetween<Duration>(in0_val, arg1, NonZonedLocalizer{});
field_builders[0]->UnsafeAppend(day_hours_between[0]);
field_builders[1]->UnsafeAppend(day_hours_between[1]);
return struct_builder->Append();
};
}

static Result<std::function<Status(typename TimestampType::c_type)>> Get(
const std::vector<BuilderType*>& field_builders, const ArrayData&,
const Scalar& in1, StructBuilder* struct_builder) {
const auto& in1_val = internal::UnboxScalar<const TimestampType>::Unbox(in1);

return [=](typename TimestampType::c_type arg0) {
const auto day_hours_between =
GetDayHoursBetween<Duration>(arg0, in1_val, NonZonedLocalizer{});
field_builders[0]->UnsafeAppend(day_hours_between[0]);
field_builders[1]->UnsafeAppend(day_hours_between[1]);
return struct_builder->Append();
};
}
};

template <typename Duration, typename InType>
struct DayHoursBetween {
static Status Call(KernelContext* ctx, const Scalar& arg0, const Scalar& arg1,
Scalar* out) {
if (arg0.is_valid && arg1.is_valid) {
ARROW_ASSIGN_OR_RAISE(auto day_hours_between,
(DayHoursBetweenWrapper<Duration, InType>::Get(arg0, arg1)));
ScalarVector values = {std::make_shared<Int64Scalar>(day_hours_between[0]),
std::make_shared<Int64Scalar>(day_hours_between[1])};
*checked_cast<StructScalar*>(out) = StructScalar(std::move(values), DayHoursType());
} else {
out->is_valid = false;
}
return Status::OK();
}

static Status Call(KernelContext* ctx, const ArrayData& arg0, const ArrayData& arg1,
ArrayData* out) {
using BuilderType = typename TypeTraits<Int64Type>::BuilderType;

std::unique_ptr<ArrayBuilder> array_builder;
RETURN_NOT_OK(MakeBuilder(ctx->memory_pool(), DayHoursType(), &array_builder));
StructBuilder* struct_builder = checked_cast<StructBuilder*>(array_builder.get());

if (arg0.length != arg1.length) {
return Status::Invalid(arg0.length, " != ", arg1.length);
}
RETURN_NOT_OK(struct_builder->Reserve(arg0.length));

std::vector<BuilderType*> field_builders;
field_builders.reserve(2);
for (int i = 0; i < 2; i++) {
field_builders.push_back(
checked_cast<BuilderType*>(struct_builder->field_builder(i)));
RETURN_NOT_OK(field_builders[i]->Reserve(1));
}

auto visit_null = [=]() { DCHECK_OK(struct_builder->AppendNull()); };
std::function<void(typename InType::c_type, typename InType::c_type)> visit_value;
ARROW_ASSIGN_OR_RAISE(
visit_value,
(DayHoursBetweenVisitValueFunction<Duration, InType, BuilderType>::Get(
field_builders, arg0, arg1, struct_builder)));

VisitTwoArrayValuesInline<typename InType::PhysicalType,
typename InType::PhysicalType>(arg0, arg1, visit_value,
visit_null);
std::shared_ptr<Array> out_array;
RETURN_NOT_OK(struct_builder->Finish(&out_array));
*out = *std::move(out_array->data());

return Status::OK();
}

static Status Call(KernelContext* ctx, const ArrayData& arg0, const Scalar& arg1,
ArrayData* out) {
using BuilderType = typename TypeTraits<Int64Type>::BuilderType;
std::unique_ptr<ArrayBuilder> array_builder;
RETURN_NOT_OK(MakeBuilder(ctx->memory_pool(), DayHoursType(), &array_builder));
StructBuilder* struct_builder = checked_cast<StructBuilder*>(array_builder.get());
RETURN_NOT_OK(struct_builder->Reserve(arg0.length));

std::vector<BuilderType*> field_builders;
field_builders.reserve(2);
for (int i = 0; i < 2; i++) {
field_builders.push_back(
checked_cast<BuilderType*>(struct_builder->field_builder(i)));
RETURN_NOT_OK(field_builders[i]->Reserve(1));
}
auto visit_null = [=]() { return struct_builder->AppendNull(); };
std::function<Status(typename InType::c_type arg)> visit_value;
ARROW_ASSIGN_OR_RAISE(
visit_value,
(DayHoursBetweenVisitValueFunction2<Duration, InType, BuilderType>::Get(
field_builders, arg0, arg1, struct_builder)));
RETURN_NOT_OK(VisitArrayDataInline<typename InType::PhysicalType>(arg0, visit_value,
visit_null));
std::shared_ptr<Array> out_array;
RETURN_NOT_OK(struct_builder->Finish(&out_array));
*out = *std::move(out_array->data());
return Status::OK();
}

static Status Call(KernelContext* ctx, const Scalar& arg0, const ArrayData& arg1,
ArrayData* out) {
using BuilderType = typename TypeTraits<Int64Type>::BuilderType;
std::unique_ptr<ArrayBuilder> array_builder;
RETURN_NOT_OK(MakeBuilder(ctx->memory_pool(), DayHoursType(), &array_builder));
StructBuilder* struct_builder = checked_cast<StructBuilder*>(array_builder.get());
RETURN_NOT_OK(struct_builder->Reserve(arg1.length));

std::vector<BuilderType*> field_builders;
field_builders.reserve(2);
for (int i = 0; i < 2; i++) {
field_builders.push_back(
checked_cast<BuilderType*>(struct_builder->field_builder(i)));
RETURN_NOT_OK(field_builders[i]->Reserve(1));
}
auto visit_null = [=]() { return struct_builder->AppendNull(); };
std::function<Status(typename InType::c_type arg)> visit_value;
ARROW_ASSIGN_OR_RAISE(
visit_value,
(DayHoursBetweenVisitValueFunction2<Duration, InType, BuilderType>::Get(
field_builders, arg0, arg1, struct_builder)));
RETURN_NOT_OK(VisitArrayDataInline<typename InType::PhysicalType>(arg1, visit_value,
visit_null));
std::shared_ptr<Array> out_array;
RETURN_NOT_OK(struct_builder->Finish(&out_array));
*out = *std::move(out_array->data());
return Status::OK();
}
};

template <typename Unit, typename Duration, typename Localizer>
struct UnitsBetween {
UnitsBetween(const FunctionOptions* options, Localizer&& localizer)
Expand DownExpand Up@@ -343,6 +615,31 @@ struct BinaryTemporalFactory {
}
};

template <template <typename...> class Op>
struct SimpleBinaryTemporalFactory {
OutputType out_type;
KernelInit init;
std::shared_ptr<ScalarFunction> func;

template <typename... WithTypes>
static std::shared_ptr<ScalarFunction> Make(
std::string name, OutputType out_type, const FunctionDoc* doc,
const FunctionOptions* default_options = NULLPTR, KernelInit init = NULLPTR) {
DCHECK_NE(sizeof...(WithTypes), 0);
SimpleBinaryTemporalFactory self{
out_type, init,
std::make_shared<ScalarFunction>(name, Arity::Binary(), doc, default_options)};
AddTemporalKernels(&self, WithTypes{}...);
return self.func;
}

template <typename Duration, typename InType>
void AddKernel(InputType in_type) {
auto exec = SimpleBinary<Op<Duration, InType>>;
DCHECK_OK(func->AddKernel({in_type, in_type}, out_type, std::move(exec), init));
}
};

const FunctionDoc years_between_doc{
"Compute the number of years between two timestamps",
("Returns the number of year boundaries crossed from `start` to `end`.\n"
Expand DownExpand Up@@ -452,6 +749,8 @@ const FunctionDoc nanoseconds_between_doc{
"Null values emit null."),
{"start", "end"}};

const FunctionDoc dayhours_between_doc{"TODO", ("TODO"), {"start", "end"}};

} // namespace

void RegisterScalarTemporalBinary(FunctionRegistry* registry) {
Expand DownExpand Up@@ -494,6 +793,12 @@ void RegisterScalarTemporalBinary(FunctionRegistry* registry) {
&day_time_interval_between_doc);
DCHECK_OK(registry->AddFunction(std::move(day_time_interval_between)));

auto dayhours_between =
SimpleBinaryTemporalFactory<DayHoursBetween>::Make<WithDates, WithTimes,
WithTimestamps>(
"dayhours_between", DayHoursType(), &dayhours_between_doc);
DCHECK_OK(registry->AddFunction(std::move(dayhours_between)));

auto days_between =
BinaryTemporalFactory<DaysBetween, TemporalBinary, Int64Type>::Make<WithDates,
WithTimestamps>(
Expand Down
Loading
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Add copy buttons to all 
 blocks\n(function() {\n function addCopyButtons() {\n document.querySelectorAll('pre code').forEach(function(codeBlock) {\n if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;\n codeBlock.parentElement.setAttribute('data-copy-added', 'true');\n \n var btn = document.createElement('button');\n btn.textContent = 'Copy';\n btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';\n btn.onmouseover = function() { this.style.opacity = '1'; };\n btn.onmouseout = function() { this.style.opacity = '0.7'; };\n btn.onclick = function() {\n navigator.clipboard.writeText(codeBlock.textContent).then(function() {\n btn.textContent = 'Copied!';\n setTimeout(function() { btn.textContent = 'Copy'; }, 1500);\n });\n };\n codeBlock.parentElement.style.position = 'relative';\n codeBlock.parentElement.appendChild(btn);\n });\n }\n \n addCopyButtons();\n \n // Re-run on dynamic content\n var observer = new MutationObserver(addCopyButtons);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Add Copy Buttons to Code Blocks");
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '

Skip to content
ARROW-14108: [C++] interval_between(timestamptz, timestamptz) -> struct kernel#12477

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

 Closed

rok
wants to merge
1
commit into

from

 Closed


ARROW-14108: [C++] interval_between(timestamptz, timestamptz) -> struct kernel
#12477
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


305 changes: 305 additions & 0 deletions
cpp/src/arrow/compute/kernels/scalar_temporal_binary.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -61,10 +61,16 @@ using arrow_vendored::date::literals::sun;
using arrow_vendored::date::literals::thu;
using arrow_vendored::date::literals::wed;
using internal::applicator::ScalarBinaryNotNullStatefulEqualTypes;
using internal::applicator::SimpleBinary;

using DayOfWeekState = OptionsWrapper<DayOfWeekOptions>;
using WeekState = OptionsWrapper<WeekOptions>;

const std::shared_ptr<DataType>& DayHoursType() {
 static auto type = struct_({field("days", int32()), field("hours", int32())});
 return type;
}

Status CheckTimezones(const ExecBatch& batch) {
 const auto& timezone = GetInputTimezone(batch.values[0]);
 for (int i = 1; i < batch.num_values(); i++) {
Expand DownExpand Up@@ -275,6 +281,272 @@ struct DayTimeBetween {
 Localizer localizer_;
};

template <typename Duration, typename Localizer>
std::array<int32_t, 2> GetDayHoursBetween(int64_t arg0, int64_t arg1,
 Localizer&& localizer) {
 auto from = localizer.template ConvertTimePoint<Duration>(arg0);
 auto to = localizer.template ConvertTimePoint<Duration>(arg1);
 const int32_t num_days =
 static_cast<int32_t>((floor<days>(to) - floor<days>(from)).count());
 auto from_time = static_cast<int32_t>(
 std::chrono::duration_cast<std::chrono::milliseconds>(from - floor<days>(from))
 .count());
 auto to_time = static_cast<int32_t>(
 std::chrono::duration_cast<std::chrono::milliseconds>(to - floor<days>(to))
 .count());
 const int32_t num_millis = to_time - from_time;
 return {num_days, num_millis / 3600000};
}

template <typename Duration, typename InType>
struct DayHoursBetweenWrapper {
 static Result<std::array<int32_t, 2>> Get(const Scalar& arg0, const Scalar& arg1) {
 const auto& arg0_val = internal::UnboxScalar<const InType>::Unbox(arg0);
 const auto& arg1_val = internal::UnboxScalar<const InType>::Unbox(arg1);
 return GetDayHoursBetween<Duration>(arg0_val, arg1_val, NonZonedLocalizer{});
 }
};

template <typename Duration>
struct DayHoursBetweenWrapper<Duration, TimestampType> {
 static Result<std::array<int32_t, 2>> Get(const Scalar& arg0, const Scalar& arg1) {
 const auto& arg0_val = internal::UnboxScalar<const TimestampType>::Unbox(arg0);
 const auto& arg1_val = internal::UnboxScalar<const TimestampType>::Unbox(arg1);
 const auto& timezone0 = GetInputTimezone(arg0);
 const auto& timezone1 = GetInputTimezone(arg1);
 if (timezone0 != timezone1) {
 return Status::Invalid(timezone0, " != ", timezone1);
 }
 if (timezone0.empty()) {
 return GetDayHoursBetween<Duration>(arg0_val, arg1_val, NonZonedLocalizer{});
 } else {
 ARROW_ASSIGN_OR_RAISE(auto tz, LocateZone(timezone0));
 return GetDayHoursBetween<Duration>(arg0_val, arg1_val, ZonedLocalizer{tz});
 }
 }
};

template <typename Duration, typename InType, typename BuilderType>
struct DayHoursBetweenVisitValueFunction {
 static Result<std::function<void(typename InType::c_type, typename InType::c_type)>>
 Get(const std::vector<BuilderType*>& field_builders, const ArrayData&, const ArrayData&,
 StructBuilder* struct_builder) {
 return [=](typename InType::c_type arg0, typename InType::c_type arg1) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(arg0, arg1, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 DCHECK_OK(struct_builder->Append());
 };
 }
};

template <typename Duration, typename BuilderType>
struct DayHoursBetweenVisitValueFunction<Duration, TimestampType, BuilderType> {
 static Result<
 std::function<void(typename TimestampType::c_type, typename TimestampType::c_type)>>
 Get(const std::vector<BuilderType*>& field_builders, const ArrayData& in0,
 const ArrayData& in1, StructBuilder* struct_builder) {
 const auto& timezone0 = GetInputTimezone(in0);
 const auto& timezone1 = GetInputTimezone(in1);
 if (timezone0 != timezone1) {
 return Status::Invalid(timezone0, " != ", timezone1);
 }
 if (timezone0.empty()) {
 return [=](TimestampType::c_type arg0, TimestampType::c_type arg1) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(arg0, arg1, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 DCHECK_OK(struct_builder->Append());
 };
 }
 ARROW_ASSIGN_OR_RAISE(auto tz, LocateZone(timezone0));
 return [=](TimestampType::c_type arg0, TimestampType::c_type arg1) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(arg0, arg1, ZonedLocalizer{tz});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 DCHECK_OK(struct_builder->Append());
 };
 }
};

template <typename Duration, typename InType, typename BuilderType>
struct DayHoursBetweenVisitValueFunction2 {
 static Result<std::function<Status(typename InType::c_type)>> Get(
 const std::vector<BuilderType*>& field_builders, const Scalar& in0,
 const ArrayData&, StructBuilder* struct_builder) {
 const auto& in0_val = internal::UnboxScalar<const InType>::Unbox(in0);

 return [=](typename InType::c_type arg1) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(in0_val, arg1, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 return struct_builder->Append();
 };
 }

 static Result<std::function<Status(typename InType::c_type)>> Get(
 const std::vector<BuilderType*>& field_builders, const ArrayData&,
 const Scalar& in1, StructBuilder* struct_builder) {
 const auto& in1_val = internal::UnboxScalar<const InType>::Unbox(in1);

 return [=](typename InType::c_type arg0) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(arg0, in1_val, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 return struct_builder->Append();
 };
 }
};

template <typename Duration, typename BuilderType>
struct DayHoursBetweenVisitValueFunction2<Duration, TimestampType, BuilderType> {
 static Result<std::function<Status(typename TimestampType::c_type)>> Get(
 const std::vector<BuilderType*>& field_builders, const Scalar& in0,
 const ArrayData&, StructBuilder* struct_builder) {
 const auto& in0_val = internal::UnboxScalar<const TimestampType>::Unbox(in0);

 return [=](typename TimestampType::c_type arg1) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(in0_val, arg1, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 return struct_builder->Append();
 };
 }

 static Result<std::function<Status(typename TimestampType::c_type)>> Get(
 const std::vector<BuilderType*>& field_builders, const ArrayData&,
 const Scalar& in1, StructBuilder* struct_builder) {
 const auto& in1_val = internal::UnboxScalar<const TimestampType>::Unbox(in1);

 return [=](typename TimestampType::c_type arg0) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(arg0, in1_val, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 return struct_builder->Append();
 };
 }
};

template <typename Duration, typename InType>
struct DayHoursBetween {
 static Status Call(KernelContext* ctx, const Scalar& arg0, const Scalar& arg1,
 Scalar* out) {
 if (arg0.is_valid && arg1.is_valid) {
 ARROW_ASSIGN_OR_RAISE(auto day_hours_between,
 (DayHoursBetweenWrapper<Duration, InType>::Get(arg0, arg1)));
 ScalarVector values = {std::make_shared<Int64Scalar>(day_hours_between[0]),
 std::make_shared<Int64Scalar>(day_hours_between[1])};
 *checked_cast<StructScalar*>(out) = StructScalar(std::move(values), DayHoursType());
 } else {
 out->is_valid = false;
 }
 return Status::OK();
 }

 static Status Call(KernelContext* ctx, const ArrayData& arg0, const ArrayData& arg1,
 ArrayData* out) {
 using BuilderType = typename TypeTraits<Int64Type>::BuilderType;

 std::unique_ptr<ArrayBuilder> array_builder;
 RETURN_NOT_OK(MakeBuilder(ctx->memory_pool(), DayHoursType(), &array_builder));
 StructBuilder* struct_builder = checked_cast<StructBuilder*>(array_builder.get());

 if (arg0.length != arg1.length) {
 return Status::Invalid(arg0.length, " != ", arg1.length);
 }
 RETURN_NOT_OK(struct_builder->Reserve(arg0.length));

 std::vector<BuilderType*> field_builders;
 field_builders.reserve(2);
 for (int i = 0; i < 2; i++) {
 field_builders.push_back(
 checked_cast<BuilderType*>(struct_builder->field_builder(i)));
 RETURN_NOT_OK(field_builders[i]->Reserve(1));
 }

 auto visit_null = [=]() { DCHECK_OK(struct_builder->AppendNull()); };
 std::function<void(typename InType::c_type, typename InType::c_type)> visit_value;
 ARROW_ASSIGN_OR_RAISE(
 visit_value,
 (DayHoursBetweenVisitValueFunction<Duration, InType, BuilderType>::Get(
 field_builders, arg0, arg1, struct_builder)));

 VisitTwoArrayValuesInline<typename InType::PhysicalType,
 typename InType::PhysicalType>(arg0, arg1, visit_value,
 visit_null);
 std::shared_ptr<Array> out_array;
 RETURN_NOT_OK(struct_builder->Finish(&out_array));
 *out = *std::move(out_array->data());

 return Status::OK();
 }

 static Status Call(KernelContext* ctx, const ArrayData& arg0, const Scalar& arg1,
 ArrayData* out) {
 using BuilderType = typename TypeTraits<Int64Type>::BuilderType;
 std::unique_ptr<ArrayBuilder> array_builder;
 RETURN_NOT_OK(MakeBuilder(ctx->memory_pool(), DayHoursType(), &array_builder));
 StructBuilder* struct_builder = checked_cast<StructBuilder*>(array_builder.get());
 RETURN_NOT_OK(struct_builder->Reserve(arg0.length));

 std::vector<BuilderType*> field_builders;
 field_builders.reserve(2);
 for (int i = 0; i < 2; i++) {
 field_builders.push_back(
 checked_cast<BuilderType*>(struct_builder->field_builder(i)));
 RETURN_NOT_OK(field_builders[i]->Reserve(1));
 }
 auto visit_null = [=]() { return struct_builder->AppendNull(); };
 std::function<Status(typename InType::c_type arg)> visit_value;
 ARROW_ASSIGN_OR_RAISE(
 visit_value,
 (DayHoursBetweenVisitValueFunction2<Duration, InType, BuilderType>::Get(
 field_builders, arg0, arg1, struct_builder)));
 RETURN_NOT_OK(VisitArrayDataInline<typename InType::PhysicalType>(arg0, visit_value,
 visit_null));
 std::shared_ptr<Array> out_array;
 RETURN_NOT_OK(struct_builder->Finish(&out_array));
 *out = *std::move(out_array->data());
 return Status::OK();
 }

 static Status Call(KernelContext* ctx, const Scalar& arg0, const ArrayData& arg1,
 ArrayData* out) {
 using BuilderType = typename TypeTraits<Int64Type>::BuilderType;
 std::unique_ptr<ArrayBuilder> array_builder;
 RETURN_NOT_OK(MakeBuilder(ctx->memory_pool(), DayHoursType(), &array_builder));
 StructBuilder* struct_builder = checked_cast<StructBuilder*>(array_builder.get());
 RETURN_NOT_OK(struct_builder->Reserve(arg1.length));

 std::vector<BuilderType*> field_builders;
 field_builders.reserve(2);
 for (int i = 0; i < 2; i++) {
 field_builders.push_back(
 checked_cast<BuilderType*>(struct_builder->field_builder(i)));
 RETURN_NOT_OK(field_builders[i]->Reserve(1));
 }
 auto visit_null = [=]() { return struct_builder->AppendNull(); };
 std::function<Status(typename InType::c_type arg)> visit_value;
 ARROW_ASSIGN_OR_RAISE(
 visit_value,
 (DayHoursBetweenVisitValueFunction2<Duration, InType, BuilderType>::Get(
 field_builders, arg0, arg1, struct_builder)));
 RETURN_NOT_OK(VisitArrayDataInline<typename InType::PhysicalType>(arg1, visit_value,
 visit_null));
 std::shared_ptr<Array> out_array;
 RETURN_NOT_OK(struct_builder->Finish(&out_array));
 *out = *std::move(out_array->data());
 return Status::OK();
 }
};

template <typename Unit, typename Duration, typename Localizer>
struct UnitsBetween {
 UnitsBetween(const FunctionOptions* options, Localizer&& localizer)
Expand DownExpand Up@@ -343,6 +615,31 @@ struct BinaryTemporalFactory {
 }
};

template <template <typename...> class Op>
struct SimpleBinaryTemporalFactory {
 OutputType out_type;
 KernelInit init;
 std::shared_ptr<ScalarFunction> func;

 template <typename... WithTypes>
 static std::shared_ptr<ScalarFunction> Make(
 std::string name, OutputType out_type, const FunctionDoc* doc,
 const FunctionOptions* default_options = NULLPTR, KernelInit init = NULLPTR) {
 DCHECK_NE(sizeof...(WithTypes), 0);
 SimpleBinaryTemporalFactory self{
 out_type, init,
 std::make_shared<ScalarFunction>(name, Arity::Binary(), doc, default_options)};
 AddTemporalKernels(&self, WithTypes{}...);
 return self.func;
 }

 template <typename Duration, typename InType>
 void AddKernel(InputType in_type) {
 auto exec = SimpleBinary<Op<Duration, InType>>;
 DCHECK_OK(func->AddKernel({in_type, in_type}, out_type, std::move(exec), init));
 }
};

const FunctionDoc years_between_doc{
 "Compute the number of years between two timestamps",
 ("Returns the number of year boundaries crossed from `start` to `end`.\n"
Expand DownExpand Up@@ -452,6 +749,8 @@ const FunctionDoc nanoseconds_between_doc{
 "Null values emit null."),
 {"start", "end"}};

const FunctionDoc dayhours_between_doc{"TODO", ("TODO"), {"start", "end"}};

} // namespace

void RegisterScalarTemporalBinary(FunctionRegistry* registry) {
Expand DownExpand Up@@ -494,6 +793,12 @@ void RegisterScalarTemporalBinary(FunctionRegistry* registry) {
 &day_time_interval_between_doc);
 DCHECK_OK(registry->AddFunction(std::move(day_time_interval_between)));

 auto dayhours_between =
 SimpleBinaryTemporalFactory<DayHoursBetween>::Make<WithDates, WithTimes,
 WithTimestamps>(
 "dayhours_between", DayHoursType(), &dayhours_between_doc);
 DCHECK_OK(registry->AddFunction(std::move(dayhours_between)));

 auto days_between =
 BinaryTemporalFactory<DaysBetween, TemporalBinary, Int64Type>::Make<WithDates,
 WithTimestamps>(
Expand Down
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Force GitHub README to respect dark mode\n(function() {\n var style = document.createElement('style');\n style.textContent = '\n .markdown-body {\n color-scheme: dark light;\n }\n .markdown-body pre { background: #161b22 !important; }\n .markdown-body code { background: rgba(110, 118, 129, 0.4) !important; }\n .markdown-body table th, .markdown-body table td { border-color: #30363d !important; }\n .markdown-body img { background: #0d1117; }\n .markdown-body blockquote { border-left-color: #8b949e; }\n .markdown-body hr { border-color: #30363d; }\n ';\n document.head.appendChild(style);\n})();", "GitHub Dark Mode README Fix");
}
} catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
ARROW-14108: [C++] interval_between(timestamptz, timestamptz) -> struct kernel#12477

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

 Closed

rok
wants to merge
1
commit into

from

 Closed


ARROW-14108: [C++] interval_between(timestamptz, timestamptz) -> struct kernel
#12477
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


305 changes: 305 additions & 0 deletions
cpp/src/arrow/compute/kernels/scalar_temporal_binary.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -61,10 +61,16 @@ using arrow_vendored::date::literals::sun;
using arrow_vendored::date::literals::thu;
using arrow_vendored::date::literals::wed;
using internal::applicator::ScalarBinaryNotNullStatefulEqualTypes;
using internal::applicator::SimpleBinary;

using DayOfWeekState = OptionsWrapper<DayOfWeekOptions>;
using WeekState = OptionsWrapper<WeekOptions>;

const std::shared_ptr<DataType>& DayHoursType() {
 static auto type = struct_({field("days", int32()), field("hours", int32())});
 return type;
}

Status CheckTimezones(const ExecBatch& batch) {
 const auto& timezone = GetInputTimezone(batch.values[0]);
 for (int i = 1; i < batch.num_values(); i++) {
Expand DownExpand Up@@ -275,6 +281,272 @@ struct DayTimeBetween {
 Localizer localizer_;
};

template <typename Duration, typename Localizer>
std::array<int32_t, 2> GetDayHoursBetween(int64_t arg0, int64_t arg1,
 Localizer&& localizer) {
 auto from = localizer.template ConvertTimePoint<Duration>(arg0);
 auto to = localizer.template ConvertTimePoint<Duration>(arg1);
 const int32_t num_days =
 static_cast<int32_t>((floor<days>(to) - floor<days>(from)).count());
 auto from_time = static_cast<int32_t>(
 std::chrono::duration_cast<std::chrono::milliseconds>(from - floor<days>(from))
 .count());
 auto to_time = static_cast<int32_t>(
 std::chrono::duration_cast<std::chrono::milliseconds>(to - floor<days>(to))
 .count());
 const int32_t num_millis = to_time - from_time;
 return {num_days, num_millis / 3600000};
}

template <typename Duration, typename InType>
struct DayHoursBetweenWrapper {
 static Result<std::array<int32_t, 2>> Get(const Scalar& arg0, const Scalar& arg1) {
 const auto& arg0_val = internal::UnboxScalar<const InType>::Unbox(arg0);
 const auto& arg1_val = internal::UnboxScalar<const InType>::Unbox(arg1);
 return GetDayHoursBetween<Duration>(arg0_val, arg1_val, NonZonedLocalizer{});
 }
};

template <typename Duration>
struct DayHoursBetweenWrapper<Duration, TimestampType> {
 static Result<std::array<int32_t, 2>> Get(const Scalar& arg0, const Scalar& arg1) {
 const auto& arg0_val = internal::UnboxScalar<const TimestampType>::Unbox(arg0);
 const auto& arg1_val = internal::UnboxScalar<const TimestampType>::Unbox(arg1);
 const auto& timezone0 = GetInputTimezone(arg0);
 const auto& timezone1 = GetInputTimezone(arg1);
 if (timezone0 != timezone1) {
 return Status::Invalid(timezone0, " != ", timezone1);
 }
 if (timezone0.empty()) {
 return GetDayHoursBetween<Duration>(arg0_val, arg1_val, NonZonedLocalizer{});
 } else {
 ARROW_ASSIGN_OR_RAISE(auto tz, LocateZone(timezone0));
 return GetDayHoursBetween<Duration>(arg0_val, arg1_val, ZonedLocalizer{tz});
 }
 }
};

template <typename Duration, typename InType, typename BuilderType>
struct DayHoursBetweenVisitValueFunction {
 static Result<std::function<void(typename InType::c_type, typename InType::c_type)>>
 Get(const std::vector<BuilderType*>& field_builders, const ArrayData&, const ArrayData&,
 StructBuilder* struct_builder) {
 return [=](typename InType::c_type arg0, typename InType::c_type arg1) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(arg0, arg1, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 DCHECK_OK(struct_builder->Append());
 };
 }
};

template <typename Duration, typename BuilderType>
struct DayHoursBetweenVisitValueFunction<Duration, TimestampType, BuilderType> {
 static Result<
 std::function<void(typename TimestampType::c_type, typename TimestampType::c_type)>>
 Get(const std::vector<BuilderType*>& field_builders, const ArrayData& in0,
 const ArrayData& in1, StructBuilder* struct_builder) {
 const auto& timezone0 = GetInputTimezone(in0);
 const auto& timezone1 = GetInputTimezone(in1);
 if (timezone0 != timezone1) {
 return Status::Invalid(timezone0, " != ", timezone1);
 }
 if (timezone0.empty()) {
 return [=](TimestampType::c_type arg0, TimestampType::c_type arg1) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(arg0, arg1, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 DCHECK_OK(struct_builder->Append());
 };
 }
 ARROW_ASSIGN_OR_RAISE(auto tz, LocateZone(timezone0));
 return [=](TimestampType::c_type arg0, TimestampType::c_type arg1) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(arg0, arg1, ZonedLocalizer{tz});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 DCHECK_OK(struct_builder->Append());
 };
 }
};

template <typename Duration, typename InType, typename BuilderType>
struct DayHoursBetweenVisitValueFunction2 {
 static Result<std::function<Status(typename InType::c_type)>> Get(
 const std::vector<BuilderType*>& field_builders, const Scalar& in0,
 const ArrayData&, StructBuilder* struct_builder) {
 const auto& in0_val = internal::UnboxScalar<const InType>::Unbox(in0);

 return [=](typename InType::c_type arg1) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(in0_val, arg1, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 return struct_builder->Append();
 };
 }

 static Result<std::function<Status(typename InType::c_type)>> Get(
 const std::vector<BuilderType*>& field_builders, const ArrayData&,
 const Scalar& in1, StructBuilder* struct_builder) {
 const auto& in1_val = internal::UnboxScalar<const InType>::Unbox(in1);

 return [=](typename InType::c_type arg0) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(arg0, in1_val, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 return struct_builder->Append();
 };
 }
};

template <typename Duration, typename BuilderType>
struct DayHoursBetweenVisitValueFunction2<Duration, TimestampType, BuilderType> {
 static Result<std::function<Status(typename TimestampType::c_type)>> Get(
 const std::vector<BuilderType*>& field_builders, const Scalar& in0,
 const ArrayData&, StructBuilder* struct_builder) {
 const auto& in0_val = internal::UnboxScalar<const TimestampType>::Unbox(in0);

 return [=](typename TimestampType::c_type arg1) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(in0_val, arg1, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 return struct_builder->Append();
 };
 }

 static Result<std::function<Status(typename TimestampType::c_type)>> Get(
 const std::vector<BuilderType*>& field_builders, const ArrayData&,
 const Scalar& in1, StructBuilder* struct_builder) {
 const auto& in1_val = internal::UnboxScalar<const TimestampType>::Unbox(in1);

 return [=](typename TimestampType::c_type arg0) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(arg0, in1_val, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 return struct_builder->Append();
 };
 }
};

template <typename Duration, typename InType>
struct DayHoursBetween {
 static Status Call(KernelContext* ctx, const Scalar& arg0, const Scalar& arg1,
 Scalar* out) {
 if (arg0.is_valid && arg1.is_valid) {
 ARROW_ASSIGN_OR_RAISE(auto day_hours_between,
 (DayHoursBetweenWrapper<Duration, InType>::Get(arg0, arg1)));
 ScalarVector values = {std::make_shared<Int64Scalar>(day_hours_between[0]),
 std::make_shared<Int64Scalar>(day_hours_between[1])};
 *checked_cast<StructScalar*>(out) = StructScalar(std::move(values), DayHoursType());
 } else {
 out->is_valid = false;
 }
 return Status::OK();
 }

 static Status Call(KernelContext* ctx, const ArrayData& arg0, const ArrayData& arg1,
 ArrayData* out) {
 using BuilderType = typename TypeTraits<Int64Type>::BuilderType;

 std::unique_ptr<ArrayBuilder> array_builder;
 RETURN_NOT_OK(MakeBuilder(ctx->memory_pool(), DayHoursType(), &array_builder));
 StructBuilder* struct_builder = checked_cast<StructBuilder*>(array_builder.get());

 if (arg0.length != arg1.length) {
 return Status::Invalid(arg0.length, " != ", arg1.length);
 }
 RETURN_NOT_OK(struct_builder->Reserve(arg0.length));

 std::vector<BuilderType*> field_builders;
 field_builders.reserve(2);
 for (int i = 0; i < 2; i++) {
 field_builders.push_back(
 checked_cast<BuilderType*>(struct_builder->field_builder(i)));
 RETURN_NOT_OK(field_builders[i]->Reserve(1));
 }

 auto visit_null = [=]() { DCHECK_OK(struct_builder->AppendNull()); };
 std::function<void(typename InType::c_type, typename InType::c_type)> visit_value;
 ARROW_ASSIGN_OR_RAISE(
 visit_value,
 (DayHoursBetweenVisitValueFunction<Duration, InType, BuilderType>::Get(
 field_builders, arg0, arg1, struct_builder)));

 VisitTwoArrayValuesInline<typename InType::PhysicalType,
 typename InType::PhysicalType>(arg0, arg1, visit_value,
 visit_null);
 std::shared_ptr<Array> out_array;
 RETURN_NOT_OK(struct_builder->Finish(&out_array));
 *out = *std::move(out_array->data());

 return Status::OK();
 }

 static Status Call(KernelContext* ctx, const ArrayData& arg0, const Scalar& arg1,
 ArrayData* out) {
 using BuilderType = typename TypeTraits<Int64Type>::BuilderType;
 std::unique_ptr<ArrayBuilder> array_builder;
 RETURN_NOT_OK(MakeBuilder(ctx->memory_pool(), DayHoursType(), &array_builder));
 StructBuilder* struct_builder = checked_cast<StructBuilder*>(array_builder.get());
 RETURN_NOT_OK(struct_builder->Reserve(arg0.length));

 std::vector<BuilderType*> field_builders;
 field_builders.reserve(2);
 for (int i = 0; i < 2; i++) {
 field_builders.push_back(
 checked_cast<BuilderType*>(struct_builder->field_builder(i)));
 RETURN_NOT_OK(field_builders[i]->Reserve(1));
 }
 auto visit_null = [=]() { return struct_builder->AppendNull(); };
 std::function<Status(typename InType::c_type arg)> visit_value;
 ARROW_ASSIGN_OR_RAISE(
 visit_value,
 (DayHoursBetweenVisitValueFunction2<Duration, InType, BuilderType>::Get(
 field_builders, arg0, arg1, struct_builder)));
 RETURN_NOT_OK(VisitArrayDataInline<typename InType::PhysicalType>(arg0, visit_value,
 visit_null));
 std::shared_ptr<Array> out_array;
 RETURN_NOT_OK(struct_builder->Finish(&out_array));
 *out = *std::move(out_array->data());
 return Status::OK();
 }

 static Status Call(KernelContext* ctx, const Scalar& arg0, const ArrayData& arg1,
 ArrayData* out) {
 using BuilderType = typename TypeTraits<Int64Type>::BuilderType;
 std::unique_ptr<ArrayBuilder> array_builder;
 RETURN_NOT_OK(MakeBuilder(ctx->memory_pool(), DayHoursType(), &array_builder));
 StructBuilder* struct_builder = checked_cast<StructBuilder*>(array_builder.get());
 RETURN_NOT_OK(struct_builder->Reserve(arg1.length));

 std::vector<BuilderType*> field_builders;
 field_builders.reserve(2);
 for (int i = 0; i < 2; i++) {
 field_builders.push_back(
 checked_cast<BuilderType*>(struct_builder->field_builder(i)));
 RETURN_NOT_OK(field_builders[i]->Reserve(1));
 }
 auto visit_null = [=]() { return struct_builder->AppendNull(); };
 std::function<Status(typename InType::c_type arg)> visit_value;
 ARROW_ASSIGN_OR_RAISE(
 visit_value,
 (DayHoursBetweenVisitValueFunction2<Duration, InType, BuilderType>::Get(
 field_builders, arg0, arg1, struct_builder)));
 RETURN_NOT_OK(VisitArrayDataInline<typename InType::PhysicalType>(arg1, visit_value,
 visit_null));
 std::shared_ptr<Array> out_array;
 RETURN_NOT_OK(struct_builder->Finish(&out_array));
 *out = *std::move(out_array->data());
 return Status::OK();
 }
};

template <typename Unit, typename Duration, typename Localizer>
struct UnitsBetween {
 UnitsBetween(const FunctionOptions* options, Localizer&& localizer)
Expand DownExpand Up@@ -343,6 +615,31 @@ struct BinaryTemporalFactory {
 }
};

template <template <typename...> class Op>
struct SimpleBinaryTemporalFactory {
 OutputType out_type;
 KernelInit init;
 std::shared_ptr<ScalarFunction> func;

 template <typename... WithTypes>
 static std::shared_ptr<ScalarFunction> Make(
 std::string name, OutputType out_type, const FunctionDoc* doc,
 const FunctionOptions* default_options = NULLPTR, KernelInit init = NULLPTR) {
 DCHECK_NE(sizeof...(WithTypes), 0);
 SimpleBinaryTemporalFactory self{
 out_type, init,
 std::make_shared<ScalarFunction>(name, Arity::Binary(), doc, default_options)};
 AddTemporalKernels(&self, WithTypes{}...);
 return self.func;
 }

 template <typename Duration, typename InType>
 void AddKernel(InputType in_type) {
 auto exec = SimpleBinary<Op<Duration, InType>>;
 DCHECK_OK(func->AddKernel({in_type, in_type}, out_type, std::move(exec), init));
 }
};

const FunctionDoc years_between_doc{
 "Compute the number of years between two timestamps",
 ("Returns the number of year boundaries crossed from `start` to `end`.\n"
Expand DownExpand Up@@ -452,6 +749,8 @@ const FunctionDoc nanoseconds_between_doc{
 "Null values emit null."),
 {"start", "end"}};

const FunctionDoc dayhours_between_doc{"TODO", ("TODO"), {"start", "end"}};

} // namespace

void RegisterScalarTemporalBinary(FunctionRegistry* registry) {
Expand DownExpand Up@@ -494,6 +793,12 @@ void RegisterScalarTemporalBinary(FunctionRegistry* registry) {
 &day_time_interval_between_doc);
 DCHECK_OK(registry->AddFunction(std::move(day_time_interval_between)));

 auto dayhours_between =
 SimpleBinaryTemporalFactory<DayHoursBetween>::Make<WithDates, WithTimes,
 WithTimestamps>(
 "dayhours_between", DayHoursType(), &dayhours_between_doc);
 DCHECK_OK(registry->AddFunction(std::move(dayhours_between)));

 auto days_between =
 BinaryTemporalFactory<DaysBetween, TemporalBinary, Int64Type>::Make<WithDates,
 WithTimestamps>(
Expand Down
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Highlight search terms from Google/DuckDuckGo/Bing referrer\n(function() {\n var ref = document.referrer;\n var terms = [];\n \n if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) {\n var url = new URL(ref);\n var q = url.searchParams.get('q') || url.searchParams.get('p');\n if (q) {\n terms = q.split(/\\s+/).filter(function(t) { return t.length > 2; });\n }\n }\n \n if (terms.length === 0) return;\n \n var style = document.createElement('style');\n style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }';\n document.head.appendChild(style);\n \n function highlight(node) {\n if (node.nodeType === 3) { // text node\n var text = node.textContent;\n var found = false;\n terms.forEach(function(term) {\n var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\\]\\\\]/g, '\\\\') + ')', 'gi');\n if (regex.test(text)) {\n found = true;\n var frag = document.createDocumentFragment();\n var parts = text.split(regex);\n parts.forEach(function(part, i) {\n if (i % 2 === 0) {\n frag.appendChild(document.createTextNode(part));\n } else {\n var span = document.createElement('span');\n span.className = 'userscript-highlight';\n span.textContent = part;\n frag.appendChild(span);\n }\n });\n node.parentNode.replaceChild(frag, node);\n }\n });\n } else if (node.nodeType === 1 && node.childNodes) { // element\n var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT'];\n if (!skipTags.includes(node.tagName)) {\n Array.from(node.childNodes).forEach(highlight);\n }\n }\n }\n \n highlight(document.body);\n \n // Re-highlight on dynamic content\n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1 || node.nodeType === 3) highlight(node);\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Highlight Search Terms");
}
} catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
ARROW-14108: [C++] interval_between(timestamptz, timestamptz) -> struct kernel#12477

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

 Closed

rok
wants to merge
1
commit into

from

 Closed


ARROW-14108: [C++] interval_between(timestamptz, timestamptz) -> struct kernel
#12477
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


305 changes: 305 additions & 0 deletions
cpp/src/arrow/compute/kernels/scalar_temporal_binary.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -61,10 +61,16 @@ using arrow_vendored::date::literals::sun;
using arrow_vendored::date::literals::thu;
using arrow_vendored::date::literals::wed;
using internal::applicator::ScalarBinaryNotNullStatefulEqualTypes;
using internal::applicator::SimpleBinary;

using DayOfWeekState = OptionsWrapper<DayOfWeekOptions>;
using WeekState = OptionsWrapper<WeekOptions>;

const std::shared_ptr<DataType>& DayHoursType() {
 static auto type = struct_({field("days", int32()), field("hours", int32())});
 return type;
}

Status CheckTimezones(const ExecBatch& batch) {
 const auto& timezone = GetInputTimezone(batch.values[0]);
 for (int i = 1; i < batch.num_values(); i++) {
Expand DownExpand Up@@ -275,6 +281,272 @@ struct DayTimeBetween {
 Localizer localizer_;
};

template <typename Duration, typename Localizer>
std::array<int32_t, 2> GetDayHoursBetween(int64_t arg0, int64_t arg1,
 Localizer&& localizer) {
 auto from = localizer.template ConvertTimePoint<Duration>(arg0);
 auto to = localizer.template ConvertTimePoint<Duration>(arg1);
 const int32_t num_days =
 static_cast<int32_t>((floor<days>(to) - floor<days>(from)).count());
 auto from_time = static_cast<int32_t>(
 std::chrono::duration_cast<std::chrono::milliseconds>(from - floor<days>(from))
 .count());
 auto to_time = static_cast<int32_t>(
 std::chrono::duration_cast<std::chrono::milliseconds>(to - floor<days>(to))
 .count());
 const int32_t num_millis = to_time - from_time;
 return {num_days, num_millis / 3600000};
}

template <typename Duration, typename InType>
struct DayHoursBetweenWrapper {
 static Result<std::array<int32_t, 2>> Get(const Scalar& arg0, const Scalar& arg1) {
 const auto& arg0_val = internal::UnboxScalar<const InType>::Unbox(arg0);
 const auto& arg1_val = internal::UnboxScalar<const InType>::Unbox(arg1);
 return GetDayHoursBetween<Duration>(arg0_val, arg1_val, NonZonedLocalizer{});
 }
};

template <typename Duration>
struct DayHoursBetweenWrapper<Duration, TimestampType> {
 static Result<std::array<int32_t, 2>> Get(const Scalar& arg0, const Scalar& arg1) {
 const auto& arg0_val = internal::UnboxScalar<const TimestampType>::Unbox(arg0);
 const auto& arg1_val = internal::UnboxScalar<const TimestampType>::Unbox(arg1);
 const auto& timezone0 = GetInputTimezone(arg0);
 const auto& timezone1 = GetInputTimezone(arg1);
 if (timezone0 != timezone1) {
 return Status::Invalid(timezone0, " != ", timezone1);
 }
 if (timezone0.empty()) {
 return GetDayHoursBetween<Duration>(arg0_val, arg1_val, NonZonedLocalizer{});
 } else {
 ARROW_ASSIGN_OR_RAISE(auto tz, LocateZone(timezone0));
 return GetDayHoursBetween<Duration>(arg0_val, arg1_val, ZonedLocalizer{tz});
 }
 }
};

template <typename Duration, typename InType, typename BuilderType>
struct DayHoursBetweenVisitValueFunction {
 static Result<std::function<void(typename InType::c_type, typename InType::c_type)>>
 Get(const std::vector<BuilderType*>& field_builders, const ArrayData&, const ArrayData&,
 StructBuilder* struct_builder) {
 return [=](typename InType::c_type arg0, typename InType::c_type arg1) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(arg0, arg1, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 DCHECK_OK(struct_builder->Append());
 };
 }
};

template <typename Duration, typename BuilderType>
struct DayHoursBetweenVisitValueFunction<Duration, TimestampType, BuilderType> {
 static Result<
 std::function<void(typename TimestampType::c_type, typename TimestampType::c_type)>>
 Get(const std::vector<BuilderType*>& field_builders, const ArrayData& in0,
 const ArrayData& in1, StructBuilder* struct_builder) {
 const auto& timezone0 = GetInputTimezone(in0);
 const auto& timezone1 = GetInputTimezone(in1);
 if (timezone0 != timezone1) {
 return Status::Invalid(timezone0, " != ", timezone1);
 }
 if (timezone0.empty()) {
 return [=](TimestampType::c_type arg0, TimestampType::c_type arg1) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(arg0, arg1, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 DCHECK_OK(struct_builder->Append());
 };
 }
 ARROW_ASSIGN_OR_RAISE(auto tz, LocateZone(timezone0));
 return [=](TimestampType::c_type arg0, TimestampType::c_type arg1) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(arg0, arg1, ZonedLocalizer{tz});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 DCHECK_OK(struct_builder->Append());
 };
 }
};

template <typename Duration, typename InType, typename BuilderType>
struct DayHoursBetweenVisitValueFunction2 {
 static Result<std::function<Status(typename InType::c_type)>> Get(
 const std::vector<BuilderType*>& field_builders, const Scalar& in0,
 const ArrayData&, StructBuilder* struct_builder) {
 const auto& in0_val = internal::UnboxScalar<const InType>::Unbox(in0);

 return [=](typename InType::c_type arg1) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(in0_val, arg1, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 return struct_builder->Append();
 };
 }

 static Result<std::function<Status(typename InType::c_type)>> Get(
 const std::vector<BuilderType*>& field_builders, const ArrayData&,
 const Scalar& in1, StructBuilder* struct_builder) {
 const auto& in1_val = internal::UnboxScalar<const InType>::Unbox(in1);

 return [=](typename InType::c_type arg0) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(arg0, in1_val, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 return struct_builder->Append();
 };
 }
};

template <typename Duration, typename BuilderType>
struct DayHoursBetweenVisitValueFunction2<Duration, TimestampType, BuilderType> {
 static Result<std::function<Status(typename TimestampType::c_type)>> Get(
 const std::vector<BuilderType*>& field_builders, const Scalar& in0,
 const ArrayData&, StructBuilder* struct_builder) {
 const auto& in0_val = internal::UnboxScalar<const TimestampType>::Unbox(in0);

 return [=](typename TimestampType::c_type arg1) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(in0_val, arg1, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 return struct_builder->Append();
 };
 }

 static Result<std::function<Status(typename TimestampType::c_type)>> Get(
 const std::vector<BuilderType*>& field_builders, const ArrayData&,
 const Scalar& in1, StructBuilder* struct_builder) {
 const auto& in1_val = internal::UnboxScalar<const TimestampType>::Unbox(in1);

 return [=](typename TimestampType::c_type arg0) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(arg0, in1_val, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 return struct_builder->Append();
 };
 }
};

template <typename Duration, typename InType>
struct DayHoursBetween {
 static Status Call(KernelContext* ctx, const Scalar& arg0, const Scalar& arg1,
 Scalar* out) {
 if (arg0.is_valid && arg1.is_valid) {
 ARROW_ASSIGN_OR_RAISE(auto day_hours_between,
 (DayHoursBetweenWrapper<Duration, InType>::Get(arg0, arg1)));
 ScalarVector values = {std::make_shared<Int64Scalar>(day_hours_between[0]),
 std::make_shared<Int64Scalar>(day_hours_between[1])};
 *checked_cast<StructScalar*>(out) = StructScalar(std::move(values), DayHoursType());
 } else {
 out->is_valid = false;
 }
 return Status::OK();
 }

 static Status Call(KernelContext* ctx, const ArrayData& arg0, const ArrayData& arg1,
 ArrayData* out) {
 using BuilderType = typename TypeTraits<Int64Type>::BuilderType;

 std::unique_ptr<ArrayBuilder> array_builder;
 RETURN_NOT_OK(MakeBuilder(ctx->memory_pool(), DayHoursType(), &array_builder));
 StructBuilder* struct_builder = checked_cast<StructBuilder*>(array_builder.get());

 if (arg0.length != arg1.length) {
 return Status::Invalid(arg0.length, " != ", arg1.length);
 }
 RETURN_NOT_OK(struct_builder->Reserve(arg0.length));

 std::vector<BuilderType*> field_builders;
 field_builders.reserve(2);
 for (int i = 0; i < 2; i++) {
 field_builders.push_back(
 checked_cast<BuilderType*>(struct_builder->field_builder(i)));
 RETURN_NOT_OK(field_builders[i]->Reserve(1));
 }

 auto visit_null = [=]() { DCHECK_OK(struct_builder->AppendNull()); };
 std::function<void(typename InType::c_type, typename InType::c_type)> visit_value;
 ARROW_ASSIGN_OR_RAISE(
 visit_value,
 (DayHoursBetweenVisitValueFunction<Duration, InType, BuilderType>::Get(
 field_builders, arg0, arg1, struct_builder)));

 VisitTwoArrayValuesInline<typename InType::PhysicalType,
 typename InType::PhysicalType>(arg0, arg1, visit_value,
 visit_null);
 std::shared_ptr<Array> out_array;
 RETURN_NOT_OK(struct_builder->Finish(&out_array));
 *out = *std::move(out_array->data());

 return Status::OK();
 }

 static Status Call(KernelContext* ctx, const ArrayData& arg0, const Scalar& arg1,
 ArrayData* out) {
 using BuilderType = typename TypeTraits<Int64Type>::BuilderType;
 std::unique_ptr<ArrayBuilder> array_builder;
 RETURN_NOT_OK(MakeBuilder(ctx->memory_pool(), DayHoursType(), &array_builder));
 StructBuilder* struct_builder = checked_cast<StructBuilder*>(array_builder.get());
 RETURN_NOT_OK(struct_builder->Reserve(arg0.length));

 std::vector<BuilderType*> field_builders;
 field_builders.reserve(2);
 for (int i = 0; i < 2; i++) {
 field_builders.push_back(
 checked_cast<BuilderType*>(struct_builder->field_builder(i)));
 RETURN_NOT_OK(field_builders[i]->Reserve(1));
 }
 auto visit_null = [=]() { return struct_builder->AppendNull(); };
 std::function<Status(typename InType::c_type arg)> visit_value;
 ARROW_ASSIGN_OR_RAISE(
 visit_value,
 (DayHoursBetweenVisitValueFunction2<Duration, InType, BuilderType>::Get(
 field_builders, arg0, arg1, struct_builder)));
 RETURN_NOT_OK(VisitArrayDataInline<typename InType::PhysicalType>(arg0, visit_value,
 visit_null));
 std::shared_ptr<Array> out_array;
 RETURN_NOT_OK(struct_builder->Finish(&out_array));
 *out = *std::move(out_array->data());
 return Status::OK();
 }

 static Status Call(KernelContext* ctx, const Scalar& arg0, const ArrayData& arg1,
 ArrayData* out) {
 using BuilderType = typename TypeTraits<Int64Type>::BuilderType;
 std::unique_ptr<ArrayBuilder> array_builder;
 RETURN_NOT_OK(MakeBuilder(ctx->memory_pool(), DayHoursType(), &array_builder));
 StructBuilder* struct_builder = checked_cast<StructBuilder*>(array_builder.get());
 RETURN_NOT_OK(struct_builder->Reserve(arg1.length));

 std::vector<BuilderType*> field_builders;
 field_builders.reserve(2);
 for (int i = 0; i < 2; i++) {
 field_builders.push_back(
 checked_cast<BuilderType*>(struct_builder->field_builder(i)));
 RETURN_NOT_OK(field_builders[i]->Reserve(1));
 }
 auto visit_null = [=]() { return struct_builder->AppendNull(); };
 std::function<Status(typename InType::c_type arg)> visit_value;
 ARROW_ASSIGN_OR_RAISE(
 visit_value,
 (DayHoursBetweenVisitValueFunction2<Duration, InType, BuilderType>::Get(
 field_builders, arg0, arg1, struct_builder)));
 RETURN_NOT_OK(VisitArrayDataInline<typename InType::PhysicalType>(arg1, visit_value,
 visit_null));
 std::shared_ptr<Array> out_array;
 RETURN_NOT_OK(struct_builder->Finish(&out_array));
 *out = *std::move(out_array->data());
 return Status::OK();
 }
};

template <typename Unit, typename Duration, typename Localizer>
struct UnitsBetween {
 UnitsBetween(const FunctionOptions* options, Localizer&& localizer)
Expand DownExpand Up@@ -343,6 +615,31 @@ struct BinaryTemporalFactory {
 }
};

template <template <typename...> class Op>
struct SimpleBinaryTemporalFactory {
 OutputType out_type;
 KernelInit init;
 std::shared_ptr<ScalarFunction> func;

 template <typename... WithTypes>
 static std::shared_ptr<ScalarFunction> Make(
 std::string name, OutputType out_type, const FunctionDoc* doc,
 const FunctionOptions* default_options = NULLPTR, KernelInit init = NULLPTR) {
 DCHECK_NE(sizeof...(WithTypes), 0);
 SimpleBinaryTemporalFactory self{
 out_type, init,
 std::make_shared<ScalarFunction>(name, Arity::Binary(), doc, default_options)};
 AddTemporalKernels(&self, WithTypes{}...);
 return self.func;
 }

 template <typename Duration, typename InType>
 void AddKernel(InputType in_type) {
 auto exec = SimpleBinary<Op<Duration, InType>>;
 DCHECK_OK(func->AddKernel({in_type, in_type}, out_type, std::move(exec), init));
 }
};

const FunctionDoc years_between_doc{
 "Compute the number of years between two timestamps",
 ("Returns the number of year boundaries crossed from `start` to `end`.\n"
Expand DownExpand Up@@ -452,6 +749,8 @@ const FunctionDoc nanoseconds_between_doc{
 "Null values emit null."),
 {"start", "end"}};

const FunctionDoc dayhours_between_doc{"TODO", ("TODO"), {"start", "end"}};

} // namespace

void RegisterScalarTemporalBinary(FunctionRegistry* registry) {
Expand DownExpand Up@@ -494,6 +793,12 @@ void RegisterScalarTemporalBinary(FunctionRegistry* registry) {
 &day_time_interval_between_doc);
 DCHECK_OK(registry->AddFunction(std::move(day_time_interval_between)));

 auto dayhours_between =
 SimpleBinaryTemporalFactory<DayHoursBetween>::Make<WithDates, WithTimes,
 WithTimestamps>(
 "dayhours_between", DayHoursType(), &dayhours_between_doc);
 DCHECK_OK(registry->AddFunction(std::move(dayhours_between)));

 auto days_between =
 BinaryTemporalFactory<DaysBetween, TemporalBinary, Int64Type>::Make<WithDates,
 WithTimestamps>(
Expand Down
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Strip utm_, fbclid, gclid, etc. from all links on page\n(function() {\n var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content',\n 'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid',\n 'ref', 'ref_src', 'source', 'medium', 'campaign'];\n \n function cleanUrl(url) {\n try {\n var u = new URL(url, window.location.origin);\n var changed = false;\n trackingParams.forEach(function(p) {\n if (u.searchParams.has(p)) {\n u.searchParams.delete(p);\n changed = true;\n }\n });\n return changed ? u.toString() : url;\n } catch (e) {\n return url;\n }\n }\n \n function cleanLinks() {\n document.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n \n cleanLinks();\n \n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1) {\n if (node.tagName === 'A') cleanLinks();\n node.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Remove Tracking Parameters from Links");
}
} catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); }
})();
(function(){
try {
var __m = "youtube.com";
var __re = new RegExp('^' + "youtube\\.com" + '

Skip to content
ARROW-14108: [C++] interval_between(timestamptz, timestamptz) -> struct kernel#12477

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

 Closed

rok
wants to merge
1
commit into

from

 Closed


ARROW-14108: [C++] interval_between(timestamptz, timestamptz) -> struct kernel
#12477
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


305 changes: 305 additions & 0 deletions
cpp/src/arrow/compute/kernels/scalar_temporal_binary.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -61,10 +61,16 @@ using arrow_vendored::date::literals::sun;
using arrow_vendored::date::literals::thu;
using arrow_vendored::date::literals::wed;
using internal::applicator::ScalarBinaryNotNullStatefulEqualTypes;
using internal::applicator::SimpleBinary;

using DayOfWeekState = OptionsWrapper<DayOfWeekOptions>;
using WeekState = OptionsWrapper<WeekOptions>;

const std::shared_ptr<DataType>& DayHoursType() {
 static auto type = struct_({field("days", int32()), field("hours", int32())});
 return type;
}

Status CheckTimezones(const ExecBatch& batch) {
 const auto& timezone = GetInputTimezone(batch.values[0]);
 for (int i = 1; i < batch.num_values(); i++) {
Expand DownExpand Up@@ -275,6 +281,272 @@ struct DayTimeBetween {
 Localizer localizer_;
};

template <typename Duration, typename Localizer>
std::array<int32_t, 2> GetDayHoursBetween(int64_t arg0, int64_t arg1,
 Localizer&& localizer) {
 auto from = localizer.template ConvertTimePoint<Duration>(arg0);
 auto to = localizer.template ConvertTimePoint<Duration>(arg1);
 const int32_t num_days =
 static_cast<int32_t>((floor<days>(to) - floor<days>(from)).count());
 auto from_time = static_cast<int32_t>(
 std::chrono::duration_cast<std::chrono::milliseconds>(from - floor<days>(from))
 .count());
 auto to_time = static_cast<int32_t>(
 std::chrono::duration_cast<std::chrono::milliseconds>(to - floor<days>(to))
 .count());
 const int32_t num_millis = to_time - from_time;
 return {num_days, num_millis / 3600000};
}

template <typename Duration, typename InType>
struct DayHoursBetweenWrapper {
 static Result<std::array<int32_t, 2>> Get(const Scalar& arg0, const Scalar& arg1) {
 const auto& arg0_val = internal::UnboxScalar<const InType>::Unbox(arg0);
 const auto& arg1_val = internal::UnboxScalar<const InType>::Unbox(arg1);
 return GetDayHoursBetween<Duration>(arg0_val, arg1_val, NonZonedLocalizer{});
 }
};

template <typename Duration>
struct DayHoursBetweenWrapper<Duration, TimestampType> {
 static Result<std::array<int32_t, 2>> Get(const Scalar& arg0, const Scalar& arg1) {
 const auto& arg0_val = internal::UnboxScalar<const TimestampType>::Unbox(arg0);
 const auto& arg1_val = internal::UnboxScalar<const TimestampType>::Unbox(arg1);
 const auto& timezone0 = GetInputTimezone(arg0);
 const auto& timezone1 = GetInputTimezone(arg1);
 if (timezone0 != timezone1) {
 return Status::Invalid(timezone0, " != ", timezone1);
 }
 if (timezone0.empty()) {
 return GetDayHoursBetween<Duration>(arg0_val, arg1_val, NonZonedLocalizer{});
 } else {
 ARROW_ASSIGN_OR_RAISE(auto tz, LocateZone(timezone0));
 return GetDayHoursBetween<Duration>(arg0_val, arg1_val, ZonedLocalizer{tz});
 }
 }
};

template <typename Duration, typename InType, typename BuilderType>
struct DayHoursBetweenVisitValueFunction {
 static Result<std::function<void(typename InType::c_type, typename InType::c_type)>>
 Get(const std::vector<BuilderType*>& field_builders, const ArrayData&, const ArrayData&,
 StructBuilder* struct_builder) {
 return [=](typename InType::c_type arg0, typename InType::c_type arg1) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(arg0, arg1, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 DCHECK_OK(struct_builder->Append());
 };
 }
};

template <typename Duration, typename BuilderType>
struct DayHoursBetweenVisitValueFunction<Duration, TimestampType, BuilderType> {
 static Result<
 std::function<void(typename TimestampType::c_type, typename TimestampType::c_type)>>
 Get(const std::vector<BuilderType*>& field_builders, const ArrayData& in0,
 const ArrayData& in1, StructBuilder* struct_builder) {
 const auto& timezone0 = GetInputTimezone(in0);
 const auto& timezone1 = GetInputTimezone(in1);
 if (timezone0 != timezone1) {
 return Status::Invalid(timezone0, " != ", timezone1);
 }
 if (timezone0.empty()) {
 return [=](TimestampType::c_type arg0, TimestampType::c_type arg1) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(arg0, arg1, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 DCHECK_OK(struct_builder->Append());
 };
 }
 ARROW_ASSIGN_OR_RAISE(auto tz, LocateZone(timezone0));
 return [=](TimestampType::c_type arg0, TimestampType::c_type arg1) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(arg0, arg1, ZonedLocalizer{tz});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 DCHECK_OK(struct_builder->Append());
 };
 }
};

template <typename Duration, typename InType, typename BuilderType>
struct DayHoursBetweenVisitValueFunction2 {
 static Result<std::function<Status(typename InType::c_type)>> Get(
 const std::vector<BuilderType*>& field_builders, const Scalar& in0,
 const ArrayData&, StructBuilder* struct_builder) {
 const auto& in0_val = internal::UnboxScalar<const InType>::Unbox(in0);

 return [=](typename InType::c_type arg1) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(in0_val, arg1, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 return struct_builder->Append();
 };
 }

 static Result<std::function<Status(typename InType::c_type)>> Get(
 const std::vector<BuilderType*>& field_builders, const ArrayData&,
 const Scalar& in1, StructBuilder* struct_builder) {
 const auto& in1_val = internal::UnboxScalar<const InType>::Unbox(in1);

 return [=](typename InType::c_type arg0) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(arg0, in1_val, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 return struct_builder->Append();
 };
 }
};

template <typename Duration, typename BuilderType>
struct DayHoursBetweenVisitValueFunction2<Duration, TimestampType, BuilderType> {
 static Result<std::function<Status(typename TimestampType::c_type)>> Get(
 const std::vector<BuilderType*>& field_builders, const Scalar& in0,
 const ArrayData&, StructBuilder* struct_builder) {
 const auto& in0_val = internal::UnboxScalar<const TimestampType>::Unbox(in0);

 return [=](typename TimestampType::c_type arg1) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(in0_val, arg1, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 return struct_builder->Append();
 };
 }

 static Result<std::function<Status(typename TimestampType::c_type)>> Get(
 const std::vector<BuilderType*>& field_builders, const ArrayData&,
 const Scalar& in1, StructBuilder* struct_builder) {
 const auto& in1_val = internal::UnboxScalar<const TimestampType>::Unbox(in1);

 return [=](typename TimestampType::c_type arg0) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(arg0, in1_val, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 return struct_builder->Append();
 };
 }
};

template <typename Duration, typename InType>
struct DayHoursBetween {
 static Status Call(KernelContext* ctx, const Scalar& arg0, const Scalar& arg1,
 Scalar* out) {
 if (arg0.is_valid && arg1.is_valid) {
 ARROW_ASSIGN_OR_RAISE(auto day_hours_between,
 (DayHoursBetweenWrapper<Duration, InType>::Get(arg0, arg1)));
 ScalarVector values = {std::make_shared<Int64Scalar>(day_hours_between[0]),
 std::make_shared<Int64Scalar>(day_hours_between[1])};
 *checked_cast<StructScalar*>(out) = StructScalar(std::move(values), DayHoursType());
 } else {
 out->is_valid = false;
 }
 return Status::OK();
 }

 static Status Call(KernelContext* ctx, const ArrayData& arg0, const ArrayData& arg1,
 ArrayData* out) {
 using BuilderType = typename TypeTraits<Int64Type>::BuilderType;

 std::unique_ptr<ArrayBuilder> array_builder;
 RETURN_NOT_OK(MakeBuilder(ctx->memory_pool(), DayHoursType(), &array_builder));
 StructBuilder* struct_builder = checked_cast<StructBuilder*>(array_builder.get());

 if (arg0.length != arg1.length) {
 return Status::Invalid(arg0.length, " != ", arg1.length);
 }
 RETURN_NOT_OK(struct_builder->Reserve(arg0.length));

 std::vector<BuilderType*> field_builders;
 field_builders.reserve(2);
 for (int i = 0; i < 2; i++) {
 field_builders.push_back(
 checked_cast<BuilderType*>(struct_builder->field_builder(i)));
 RETURN_NOT_OK(field_builders[i]->Reserve(1));
 }

 auto visit_null = [=]() { DCHECK_OK(struct_builder->AppendNull()); };
 std::function<void(typename InType::c_type, typename InType::c_type)> visit_value;
 ARROW_ASSIGN_OR_RAISE(
 visit_value,
 (DayHoursBetweenVisitValueFunction<Duration, InType, BuilderType>::Get(
 field_builders, arg0, arg1, struct_builder)));

 VisitTwoArrayValuesInline<typename InType::PhysicalType,
 typename InType::PhysicalType>(arg0, arg1, visit_value,
 visit_null);
 std::shared_ptr<Array> out_array;
 RETURN_NOT_OK(struct_builder->Finish(&out_array));
 *out = *std::move(out_array->data());

 return Status::OK();
 }

 static Status Call(KernelContext* ctx, const ArrayData& arg0, const Scalar& arg1,
 ArrayData* out) {
 using BuilderType = typename TypeTraits<Int64Type>::BuilderType;
 std::unique_ptr<ArrayBuilder> array_builder;
 RETURN_NOT_OK(MakeBuilder(ctx->memory_pool(), DayHoursType(), &array_builder));
 StructBuilder* struct_builder = checked_cast<StructBuilder*>(array_builder.get());
 RETURN_NOT_OK(struct_builder->Reserve(arg0.length));

 std::vector<BuilderType*> field_builders;
 field_builders.reserve(2);
 for (int i = 0; i < 2; i++) {
 field_builders.push_back(
 checked_cast<BuilderType*>(struct_builder->field_builder(i)));
 RETURN_NOT_OK(field_builders[i]->Reserve(1));
 }
 auto visit_null = [=]() { return struct_builder->AppendNull(); };
 std::function<Status(typename InType::c_type arg)> visit_value;
 ARROW_ASSIGN_OR_RAISE(
 visit_value,
 (DayHoursBetweenVisitValueFunction2<Duration, InType, BuilderType>::Get(
 field_builders, arg0, arg1, struct_builder)));
 RETURN_NOT_OK(VisitArrayDataInline<typename InType::PhysicalType>(arg0, visit_value,
 visit_null));
 std::shared_ptr<Array> out_array;
 RETURN_NOT_OK(struct_builder->Finish(&out_array));
 *out = *std::move(out_array->data());
 return Status::OK();
 }

 static Status Call(KernelContext* ctx, const Scalar& arg0, const ArrayData& arg1,
 ArrayData* out) {
 using BuilderType = typename TypeTraits<Int64Type>::BuilderType;
 std::unique_ptr<ArrayBuilder> array_builder;
 RETURN_NOT_OK(MakeBuilder(ctx->memory_pool(), DayHoursType(), &array_builder));
 StructBuilder* struct_builder = checked_cast<StructBuilder*>(array_builder.get());
 RETURN_NOT_OK(struct_builder->Reserve(arg1.length));

 std::vector<BuilderType*> field_builders;
 field_builders.reserve(2);
 for (int i = 0; i < 2; i++) {
 field_builders.push_back(
 checked_cast<BuilderType*>(struct_builder->field_builder(i)));
 RETURN_NOT_OK(field_builders[i]->Reserve(1));
 }
 auto visit_null = [=]() { return struct_builder->AppendNull(); };
 std::function<Status(typename InType::c_type arg)> visit_value;
 ARROW_ASSIGN_OR_RAISE(
 visit_value,
 (DayHoursBetweenVisitValueFunction2<Duration, InType, BuilderType>::Get(
 field_builders, arg0, arg1, struct_builder)));
 RETURN_NOT_OK(VisitArrayDataInline<typename InType::PhysicalType>(arg1, visit_value,
 visit_null));
 std::shared_ptr<Array> out_array;
 RETURN_NOT_OK(struct_builder->Finish(&out_array));
 *out = *std::move(out_array->data());
 return Status::OK();
 }
};

template <typename Unit, typename Duration, typename Localizer>
struct UnitsBetween {
 UnitsBetween(const FunctionOptions* options, Localizer&& localizer)
Expand DownExpand Up@@ -343,6 +615,31 @@ struct BinaryTemporalFactory {
 }
};

template <template <typename...> class Op>
struct SimpleBinaryTemporalFactory {
 OutputType out_type;
 KernelInit init;
 std::shared_ptr<ScalarFunction> func;

 template <typename... WithTypes>
 static std::shared_ptr<ScalarFunction> Make(
 std::string name, OutputType out_type, const FunctionDoc* doc,
 const FunctionOptions* default_options = NULLPTR, KernelInit init = NULLPTR) {
 DCHECK_NE(sizeof...(WithTypes), 0);
 SimpleBinaryTemporalFactory self{
 out_type, init,
 std::make_shared<ScalarFunction>(name, Arity::Binary(), doc, default_options)};
 AddTemporalKernels(&self, WithTypes{}...);
 return self.func;
 }

 template <typename Duration, typename InType>
 void AddKernel(InputType in_type) {
 auto exec = SimpleBinary<Op<Duration, InType>>;
 DCHECK_OK(func->AddKernel({in_type, in_type}, out_type, std::move(exec), init));
 }
};

const FunctionDoc years_between_doc{
 "Compute the number of years between two timestamps",
 ("Returns the number of year boundaries crossed from `start` to `end`.\n"
Expand DownExpand Up@@ -452,6 +749,8 @@ const FunctionDoc nanoseconds_between_doc{
 "Null values emit null."),
 {"start", "end"}};

const FunctionDoc dayhours_between_doc{"TODO", ("TODO"), {"start", "end"}};

} // namespace

void RegisterScalarTemporalBinary(FunctionRegistry* registry) {
Expand DownExpand Up@@ -494,6 +793,12 @@ void RegisterScalarTemporalBinary(FunctionRegistry* registry) {
 &day_time_interval_between_doc);
 DCHECK_OK(registry->AddFunction(std::move(day_time_interval_between)));

 auto dayhours_between =
 SimpleBinaryTemporalFactory<DayHoursBetween>::Make<WithDates, WithTimes,
 WithTimestamps>(
 "dayhours_between", DayHoursType(), &dayhours_between_doc);
 DCHECK_OK(registry->AddFunction(std::move(dayhours_between)));

 auto days_between =
 BinaryTemporalFactory<DaysBetween, TemporalBinary, Int64Type>::Make<WithDates,
 WithTimestamps>(
Expand Down
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Auto-enable theater mode on YouTube\n(function() {\n function tryTheater() {\n var btn = document.querySelector('button[aria-label=\"Theater mode\"], ytd-player #player button[title=\"Theater mode\"]');\n if (btn && !btn.classList.contains('activated')) {\n btn.click();\n }\n }\n \n // Try immediately\n tryTheater();\n \n // Try after navigation (SPA)\n var lastUrl = location.href;\n setInterval(function() {\n if (location.href !== lastUrl) {\n lastUrl = location.href;\n setTimeout(tryTheater, 500);\n }\n }, 1000);\n \n // Also try on player load\n var observer = new MutationObserver(tryTheater);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "YouTube Theater Mode Default");
}
} catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
ARROW-14108: [C++] interval_between(timestamptz, timestamptz) -> struct kernel#12477

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

 Closed

rok
wants to merge
1
commit into

from

 Closed


ARROW-14108: [C++] interval_between(timestamptz, timestamptz) -> struct kernel
#12477
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


305 changes: 305 additions & 0 deletions
cpp/src/arrow/compute/kernels/scalar_temporal_binary.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -61,10 +61,16 @@ using arrow_vendored::date::literals::sun;
using arrow_vendored::date::literals::thu;
using arrow_vendored::date::literals::wed;
using internal::applicator::ScalarBinaryNotNullStatefulEqualTypes;
using internal::applicator::SimpleBinary;

using DayOfWeekState = OptionsWrapper<DayOfWeekOptions>;
using WeekState = OptionsWrapper<WeekOptions>;

const std::shared_ptr<DataType>& DayHoursType() {
 static auto type = struct_({field("days", int32()), field("hours", int32())});
 return type;
}

Status CheckTimezones(const ExecBatch& batch) {
 const auto& timezone = GetInputTimezone(batch.values[0]);
 for (int i = 1; i < batch.num_values(); i++) {
Expand DownExpand Up@@ -275,6 +281,272 @@ struct DayTimeBetween {
 Localizer localizer_;
};

template <typename Duration, typename Localizer>
std::array<int32_t, 2> GetDayHoursBetween(int64_t arg0, int64_t arg1,
 Localizer&& localizer) {
 auto from = localizer.template ConvertTimePoint<Duration>(arg0);
 auto to = localizer.template ConvertTimePoint<Duration>(arg1);
 const int32_t num_days =
 static_cast<int32_t>((floor<days>(to) - floor<days>(from)).count());
 auto from_time = static_cast<int32_t>(
 std::chrono::duration_cast<std::chrono::milliseconds>(from - floor<days>(from))
 .count());
 auto to_time = static_cast<int32_t>(
 std::chrono::duration_cast<std::chrono::milliseconds>(to - floor<days>(to))
 .count());
 const int32_t num_millis = to_time - from_time;
 return {num_days, num_millis / 3600000};
}

template <typename Duration, typename InType>
struct DayHoursBetweenWrapper {
 static Result<std::array<int32_t, 2>> Get(const Scalar& arg0, const Scalar& arg1) {
 const auto& arg0_val = internal::UnboxScalar<const InType>::Unbox(arg0);
 const auto& arg1_val = internal::UnboxScalar<const InType>::Unbox(arg1);
 return GetDayHoursBetween<Duration>(arg0_val, arg1_val, NonZonedLocalizer{});
 }
};

template <typename Duration>
struct DayHoursBetweenWrapper<Duration, TimestampType> {
 static Result<std::array<int32_t, 2>> Get(const Scalar& arg0, const Scalar& arg1) {
 const auto& arg0_val = internal::UnboxScalar<const TimestampType>::Unbox(arg0);
 const auto& arg1_val = internal::UnboxScalar<const TimestampType>::Unbox(arg1);
 const auto& timezone0 = GetInputTimezone(arg0);
 const auto& timezone1 = GetInputTimezone(arg1);
 if (timezone0 != timezone1) {
 return Status::Invalid(timezone0, " != ", timezone1);
 }
 if (timezone0.empty()) {
 return GetDayHoursBetween<Duration>(arg0_val, arg1_val, NonZonedLocalizer{});
 } else {
 ARROW_ASSIGN_OR_RAISE(auto tz, LocateZone(timezone0));
 return GetDayHoursBetween<Duration>(arg0_val, arg1_val, ZonedLocalizer{tz});
 }
 }
};

template <typename Duration, typename InType, typename BuilderType>
struct DayHoursBetweenVisitValueFunction {
 static Result<std::function<void(typename InType::c_type, typename InType::c_type)>>
 Get(const std::vector<BuilderType*>& field_builders, const ArrayData&, const ArrayData&,
 StructBuilder* struct_builder) {
 return [=](typename InType::c_type arg0, typename InType::c_type arg1) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(arg0, arg1, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 DCHECK_OK(struct_builder->Append());
 };
 }
};

template <typename Duration, typename BuilderType>
struct DayHoursBetweenVisitValueFunction<Duration, TimestampType, BuilderType> {
 static Result<
 std::function<void(typename TimestampType::c_type, typename TimestampType::c_type)>>
 Get(const std::vector<BuilderType*>& field_builders, const ArrayData& in0,
 const ArrayData& in1, StructBuilder* struct_builder) {
 const auto& timezone0 = GetInputTimezone(in0);
 const auto& timezone1 = GetInputTimezone(in1);
 if (timezone0 != timezone1) {
 return Status::Invalid(timezone0, " != ", timezone1);
 }
 if (timezone0.empty()) {
 return [=](TimestampType::c_type arg0, TimestampType::c_type arg1) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(arg0, arg1, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 DCHECK_OK(struct_builder->Append());
 };
 }
 ARROW_ASSIGN_OR_RAISE(auto tz, LocateZone(timezone0));
 return [=](TimestampType::c_type arg0, TimestampType::c_type arg1) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(arg0, arg1, ZonedLocalizer{tz});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 DCHECK_OK(struct_builder->Append());
 };
 }
};

template <typename Duration, typename InType, typename BuilderType>
struct DayHoursBetweenVisitValueFunction2 {
 static Result<std::function<Status(typename InType::c_type)>> Get(
 const std::vector<BuilderType*>& field_builders, const Scalar& in0,
 const ArrayData&, StructBuilder* struct_builder) {
 const auto& in0_val = internal::UnboxScalar<const InType>::Unbox(in0);

 return [=](typename InType::c_type arg1) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(in0_val, arg1, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 return struct_builder->Append();
 };
 }

 static Result<std::function<Status(typename InType::c_type)>> Get(
 const std::vector<BuilderType*>& field_builders, const ArrayData&,
 const Scalar& in1, StructBuilder* struct_builder) {
 const auto& in1_val = internal::UnboxScalar<const InType>::Unbox(in1);

 return [=](typename InType::c_type arg0) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(arg0, in1_val, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 return struct_builder->Append();
 };
 }
};

template <typename Duration, typename BuilderType>
struct DayHoursBetweenVisitValueFunction2<Duration, TimestampType, BuilderType> {
 static Result<std::function<Status(typename TimestampType::c_type)>> Get(
 const std::vector<BuilderType*>& field_builders, const Scalar& in0,
 const ArrayData&, StructBuilder* struct_builder) {
 const auto& in0_val = internal::UnboxScalar<const TimestampType>::Unbox(in0);

 return [=](typename TimestampType::c_type arg1) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(in0_val, arg1, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 return struct_builder->Append();
 };
 }

 static Result<std::function<Status(typename TimestampType::c_type)>> Get(
 const std::vector<BuilderType*>& field_builders, const ArrayData&,
 const Scalar& in1, StructBuilder* struct_builder) {
 const auto& in1_val = internal::UnboxScalar<const TimestampType>::Unbox(in1);

 return [=](typename TimestampType::c_type arg0) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(arg0, in1_val, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 return struct_builder->Append();
 };
 }
};

template <typename Duration, typename InType>
struct DayHoursBetween {
 static Status Call(KernelContext* ctx, const Scalar& arg0, const Scalar& arg1,
 Scalar* out) {
 if (arg0.is_valid && arg1.is_valid) {
 ARROW_ASSIGN_OR_RAISE(auto day_hours_between,
 (DayHoursBetweenWrapper<Duration, InType>::Get(arg0, arg1)));
 ScalarVector values = {std::make_shared<Int64Scalar>(day_hours_between[0]),
 std::make_shared<Int64Scalar>(day_hours_between[1])};
 *checked_cast<StructScalar*>(out) = StructScalar(std::move(values), DayHoursType());
 } else {
 out->is_valid = false;
 }
 return Status::OK();
 }

 static Status Call(KernelContext* ctx, const ArrayData& arg0, const ArrayData& arg1,
 ArrayData* out) {
 using BuilderType = typename TypeTraits<Int64Type>::BuilderType;

 std::unique_ptr<ArrayBuilder> array_builder;
 RETURN_NOT_OK(MakeBuilder(ctx->memory_pool(), DayHoursType(), &array_builder));
 StructBuilder* struct_builder = checked_cast<StructBuilder*>(array_builder.get());

 if (arg0.length != arg1.length) {
 return Status::Invalid(arg0.length, " != ", arg1.length);
 }
 RETURN_NOT_OK(struct_builder->Reserve(arg0.length));

 std::vector<BuilderType*> field_builders;
 field_builders.reserve(2);
 for (int i = 0; i < 2; i++) {
 field_builders.push_back(
 checked_cast<BuilderType*>(struct_builder->field_builder(i)));
 RETURN_NOT_OK(field_builders[i]->Reserve(1));
 }

 auto visit_null = [=]() { DCHECK_OK(struct_builder->AppendNull()); };
 std::function<void(typename InType::c_type, typename InType::c_type)> visit_value;
 ARROW_ASSIGN_OR_RAISE(
 visit_value,
 (DayHoursBetweenVisitValueFunction<Duration, InType, BuilderType>::Get(
 field_builders, arg0, arg1, struct_builder)));

 VisitTwoArrayValuesInline<typename InType::PhysicalType,
 typename InType::PhysicalType>(arg0, arg1, visit_value,
 visit_null);
 std::shared_ptr<Array> out_array;
 RETURN_NOT_OK(struct_builder->Finish(&out_array));
 *out = *std::move(out_array->data());

 return Status::OK();
 }

 static Status Call(KernelContext* ctx, const ArrayData& arg0, const Scalar& arg1,
 ArrayData* out) {
 using BuilderType = typename TypeTraits<Int64Type>::BuilderType;
 std::unique_ptr<ArrayBuilder> array_builder;
 RETURN_NOT_OK(MakeBuilder(ctx->memory_pool(), DayHoursType(), &array_builder));
 StructBuilder* struct_builder = checked_cast<StructBuilder*>(array_builder.get());
 RETURN_NOT_OK(struct_builder->Reserve(arg0.length));

 std::vector<BuilderType*> field_builders;
 field_builders.reserve(2);
 for (int i = 0; i < 2; i++) {
 field_builders.push_back(
 checked_cast<BuilderType*>(struct_builder->field_builder(i)));
 RETURN_NOT_OK(field_builders[i]->Reserve(1));
 }
 auto visit_null = [=]() { return struct_builder->AppendNull(); };
 std::function<Status(typename InType::c_type arg)> visit_value;
 ARROW_ASSIGN_OR_RAISE(
 visit_value,
 (DayHoursBetweenVisitValueFunction2<Duration, InType, BuilderType>::Get(
 field_builders, arg0, arg1, struct_builder)));
 RETURN_NOT_OK(VisitArrayDataInline<typename InType::PhysicalType>(arg0, visit_value,
 visit_null));
 std::shared_ptr<Array> out_array;
 RETURN_NOT_OK(struct_builder->Finish(&out_array));
 *out = *std::move(out_array->data());
 return Status::OK();
 }

 static Status Call(KernelContext* ctx, const Scalar& arg0, const ArrayData& arg1,
 ArrayData* out) {
 using BuilderType = typename TypeTraits<Int64Type>::BuilderType;
 std::unique_ptr<ArrayBuilder> array_builder;
 RETURN_NOT_OK(MakeBuilder(ctx->memory_pool(), DayHoursType(), &array_builder));
 StructBuilder* struct_builder = checked_cast<StructBuilder*>(array_builder.get());
 RETURN_NOT_OK(struct_builder->Reserve(arg1.length));

 std::vector<BuilderType*> field_builders;
 field_builders.reserve(2);
 for (int i = 0; i < 2; i++) {
 field_builders.push_back(
 checked_cast<BuilderType*>(struct_builder->field_builder(i)));
 RETURN_NOT_OK(field_builders[i]->Reserve(1));
 }
 auto visit_null = [=]() { return struct_builder->AppendNull(); };
 std::function<Status(typename InType::c_type arg)> visit_value;
 ARROW_ASSIGN_OR_RAISE(
 visit_value,
 (DayHoursBetweenVisitValueFunction2<Duration, InType, BuilderType>::Get(
 field_builders, arg0, arg1, struct_builder)));
 RETURN_NOT_OK(VisitArrayDataInline<typename InType::PhysicalType>(arg1, visit_value,
 visit_null));
 std::shared_ptr<Array> out_array;
 RETURN_NOT_OK(struct_builder->Finish(&out_array));
 *out = *std::move(out_array->data());
 return Status::OK();
 }
};

template <typename Unit, typename Duration, typename Localizer>
struct UnitsBetween {
 UnitsBetween(const FunctionOptions* options, Localizer&& localizer)
Expand DownExpand Up@@ -343,6 +615,31 @@ struct BinaryTemporalFactory {
 }
};

template <template <typename...> class Op>
struct SimpleBinaryTemporalFactory {
 OutputType out_type;
 KernelInit init;
 std::shared_ptr<ScalarFunction> func;

 template <typename... WithTypes>
 static std::shared_ptr<ScalarFunction> Make(
 std::string name, OutputType out_type, const FunctionDoc* doc,
 const FunctionOptions* default_options = NULLPTR, KernelInit init = NULLPTR) {
 DCHECK_NE(sizeof...(WithTypes), 0);
 SimpleBinaryTemporalFactory self{
 out_type, init,
 std::make_shared<ScalarFunction>(name, Arity::Binary(), doc, default_options)};
 AddTemporalKernels(&self, WithTypes{}...);
 return self.func;
 }

 template <typename Duration, typename InType>
 void AddKernel(InputType in_type) {
 auto exec = SimpleBinary<Op<Duration, InType>>;
 DCHECK_OK(func->AddKernel({in_type, in_type}, out_type, std::move(exec), init));
 }
};

const FunctionDoc years_between_doc{
 "Compute the number of years between two timestamps",
 ("Returns the number of year boundaries crossed from `start` to `end`.\n"
Expand DownExpand Up@@ -452,6 +749,8 @@ const FunctionDoc nanoseconds_between_doc{
 "Null values emit null."),
 {"start", "end"}};

const FunctionDoc dayhours_between_doc{"TODO", ("TODO"), {"start", "end"}};

} // namespace

void RegisterScalarTemporalBinary(FunctionRegistry* registry) {
Expand DownExpand Up@@ -494,6 +793,12 @@ void RegisterScalarTemporalBinary(FunctionRegistry* registry) {
 &day_time_interval_between_doc);
 DCHECK_OK(registry->AddFunction(std::move(day_time_interval_between)));

 auto dayhours_between =
 SimpleBinaryTemporalFactory<DayHoursBetween>::Make<WithDates, WithTimes,
 WithTimestamps>(
 "dayhours_between", DayHoursType(), &dayhours_between_doc);
 DCHECK_OK(registry->AddFunction(std::move(dayhours_between)));

 auto days_between =
 BinaryTemporalFactory<DaysBetween, TemporalBinary, Int64Type>::Make<WithDates,
 WithTimestamps>(
Expand Down
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Remove or un-stick sticky/fixed headers that block content\n(function() {\n function unstick() {\n document.querySelectorAll('header, nav, [role=\"banner\"], .header, .navbar, .sticky, .fixed-top, [style*=\"position: fixed\"], [style*=\"position:sticky\"]').forEach(function(el) {\n if (el.style.position === 'fixed' || el.style.position === 'sticky' || \n getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') {\n el.style.position = 'static';\n el.style.top = 'auto';\n el.style.zIndex = 'auto';\n }\n });\n }\n \n unstick();\n \n var observer = new MutationObserver(unstick);\n observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] });\n})();", "Kill Sticky Headers");
}
} catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
ARROW-14108: [C++] interval_between(timestamptz, timestamptz) -> struct kernel#12477

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

 Closed

rok
wants to merge
1
commit into

from

 Closed


ARROW-14108: [C++] interval_between(timestamptz, timestamptz) -> struct kernel
#12477
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


305 changes: 305 additions & 0 deletions
cpp/src/arrow/compute/kernels/scalar_temporal_binary.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -61,10 +61,16 @@ using arrow_vendored::date::literals::sun;
using arrow_vendored::date::literals::thu;
using arrow_vendored::date::literals::wed;
using internal::applicator::ScalarBinaryNotNullStatefulEqualTypes;
using internal::applicator::SimpleBinary;

using DayOfWeekState = OptionsWrapper<DayOfWeekOptions>;
using WeekState = OptionsWrapper<WeekOptions>;

const std::shared_ptr<DataType>& DayHoursType() {
 static auto type = struct_({field("days", int32()), field("hours", int32())});
 return type;
}

Status CheckTimezones(const ExecBatch& batch) {
 const auto& timezone = GetInputTimezone(batch.values[0]);
 for (int i = 1; i < batch.num_values(); i++) {
Expand DownExpand Up@@ -275,6 +281,272 @@ struct DayTimeBetween {
 Localizer localizer_;
};

template <typename Duration, typename Localizer>
std::array<int32_t, 2> GetDayHoursBetween(int64_t arg0, int64_t arg1,
 Localizer&& localizer) {
 auto from = localizer.template ConvertTimePoint<Duration>(arg0);
 auto to = localizer.template ConvertTimePoint<Duration>(arg1);
 const int32_t num_days =
 static_cast<int32_t>((floor<days>(to) - floor<days>(from)).count());
 auto from_time = static_cast<int32_t>(
 std::chrono::duration_cast<std::chrono::milliseconds>(from - floor<days>(from))
 .count());
 auto to_time = static_cast<int32_t>(
 std::chrono::duration_cast<std::chrono::milliseconds>(to - floor<days>(to))
 .count());
 const int32_t num_millis = to_time - from_time;
 return {num_days, num_millis / 3600000};
}

template <typename Duration, typename InType>
struct DayHoursBetweenWrapper {
 static Result<std::array<int32_t, 2>> Get(const Scalar& arg0, const Scalar& arg1) {
 const auto& arg0_val = internal::UnboxScalar<const InType>::Unbox(arg0);
 const auto& arg1_val = internal::UnboxScalar<const InType>::Unbox(arg1);
 return GetDayHoursBetween<Duration>(arg0_val, arg1_val, NonZonedLocalizer{});
 }
};

template <typename Duration>
struct DayHoursBetweenWrapper<Duration, TimestampType> {
 static Result<std::array<int32_t, 2>> Get(const Scalar& arg0, const Scalar& arg1) {
 const auto& arg0_val = internal::UnboxScalar<const TimestampType>::Unbox(arg0);
 const auto& arg1_val = internal::UnboxScalar<const TimestampType>::Unbox(arg1);
 const auto& timezone0 = GetInputTimezone(arg0);
 const auto& timezone1 = GetInputTimezone(arg1);
 if (timezone0 != timezone1) {
 return Status::Invalid(timezone0, " != ", timezone1);
 }
 if (timezone0.empty()) {
 return GetDayHoursBetween<Duration>(arg0_val, arg1_val, NonZonedLocalizer{});
 } else {
 ARROW_ASSIGN_OR_RAISE(auto tz, LocateZone(timezone0));
 return GetDayHoursBetween<Duration>(arg0_val, arg1_val, ZonedLocalizer{tz});
 }
 }
};

template <typename Duration, typename InType, typename BuilderType>
struct DayHoursBetweenVisitValueFunction {
 static Result<std::function<void(typename InType::c_type, typename InType::c_type)>>
 Get(const std::vector<BuilderType*>& field_builders, const ArrayData&, const ArrayData&,
 StructBuilder* struct_builder) {
 return [=](typename InType::c_type arg0, typename InType::c_type arg1) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(arg0, arg1, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 DCHECK_OK(struct_builder->Append());
 };
 }
};

template <typename Duration, typename BuilderType>
struct DayHoursBetweenVisitValueFunction<Duration, TimestampType, BuilderType> {
 static Result<
 std::function<void(typename TimestampType::c_type, typename TimestampType::c_type)>>
 Get(const std::vector<BuilderType*>& field_builders, const ArrayData& in0,
 const ArrayData& in1, StructBuilder* struct_builder) {
 const auto& timezone0 = GetInputTimezone(in0);
 const auto& timezone1 = GetInputTimezone(in1);
 if (timezone0 != timezone1) {
 return Status::Invalid(timezone0, " != ", timezone1);
 }
 if (timezone0.empty()) {
 return [=](TimestampType::c_type arg0, TimestampType::c_type arg1) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(arg0, arg1, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 DCHECK_OK(struct_builder->Append());
 };
 }
 ARROW_ASSIGN_OR_RAISE(auto tz, LocateZone(timezone0));
 return [=](TimestampType::c_type arg0, TimestampType::c_type arg1) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(arg0, arg1, ZonedLocalizer{tz});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 DCHECK_OK(struct_builder->Append());
 };
 }
};

template <typename Duration, typename InType, typename BuilderType>
struct DayHoursBetweenVisitValueFunction2 {
 static Result<std::function<Status(typename InType::c_type)>> Get(
 const std::vector<BuilderType*>& field_builders, const Scalar& in0,
 const ArrayData&, StructBuilder* struct_builder) {
 const auto& in0_val = internal::UnboxScalar<const InType>::Unbox(in0);

 return [=](typename InType::c_type arg1) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(in0_val, arg1, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 return struct_builder->Append();
 };
 }

 static Result<std::function<Status(typename InType::c_type)>> Get(
 const std::vector<BuilderType*>& field_builders, const ArrayData&,
 const Scalar& in1, StructBuilder* struct_builder) {
 const auto& in1_val = internal::UnboxScalar<const InType>::Unbox(in1);

 return [=](typename InType::c_type arg0) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(arg0, in1_val, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 return struct_builder->Append();
 };
 }
};

template <typename Duration, typename BuilderType>
struct DayHoursBetweenVisitValueFunction2<Duration, TimestampType, BuilderType> {
 static Result<std::function<Status(typename TimestampType::c_type)>> Get(
 const std::vector<BuilderType*>& field_builders, const Scalar& in0,
 const ArrayData&, StructBuilder* struct_builder) {
 const auto& in0_val = internal::UnboxScalar<const TimestampType>::Unbox(in0);

 return [=](typename TimestampType::c_type arg1) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(in0_val, arg1, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 return struct_builder->Append();
 };
 }

 static Result<std::function<Status(typename TimestampType::c_type)>> Get(
 const std::vector<BuilderType*>& field_builders, const ArrayData&,
 const Scalar& in1, StructBuilder* struct_builder) {
 const auto& in1_val = internal::UnboxScalar<const TimestampType>::Unbox(in1);

 return [=](typename TimestampType::c_type arg0) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(arg0, in1_val, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 return struct_builder->Append();
 };
 }
};

template <typename Duration, typename InType>
struct DayHoursBetween {
 static Status Call(KernelContext* ctx, const Scalar& arg0, const Scalar& arg1,
 Scalar* out) {
 if (arg0.is_valid && arg1.is_valid) {
 ARROW_ASSIGN_OR_RAISE(auto day_hours_between,
 (DayHoursBetweenWrapper<Duration, InType>::Get(arg0, arg1)));
 ScalarVector values = {std::make_shared<Int64Scalar>(day_hours_between[0]),
 std::make_shared<Int64Scalar>(day_hours_between[1])};
 *checked_cast<StructScalar*>(out) = StructScalar(std::move(values), DayHoursType());
 } else {
 out->is_valid = false;
 }
 return Status::OK();
 }

 static Status Call(KernelContext* ctx, const ArrayData& arg0, const ArrayData& arg1,
 ArrayData* out) {
 using BuilderType = typename TypeTraits<Int64Type>::BuilderType;

 std::unique_ptr<ArrayBuilder> array_builder;
 RETURN_NOT_OK(MakeBuilder(ctx->memory_pool(), DayHoursType(), &array_builder));
 StructBuilder* struct_builder = checked_cast<StructBuilder*>(array_builder.get());

 if (arg0.length != arg1.length) {
 return Status::Invalid(arg0.length, " != ", arg1.length);
 }
 RETURN_NOT_OK(struct_builder->Reserve(arg0.length));

 std::vector<BuilderType*> field_builders;
 field_builders.reserve(2);
 for (int i = 0; i < 2; i++) {
 field_builders.push_back(
 checked_cast<BuilderType*>(struct_builder->field_builder(i)));
 RETURN_NOT_OK(field_builders[i]->Reserve(1));
 }

 auto visit_null = [=]() { DCHECK_OK(struct_builder->AppendNull()); };
 std::function<void(typename InType::c_type, typename InType::c_type)> visit_value;
 ARROW_ASSIGN_OR_RAISE(
 visit_value,
 (DayHoursBetweenVisitValueFunction<Duration, InType, BuilderType>::Get(
 field_builders, arg0, arg1, struct_builder)));

 VisitTwoArrayValuesInline<typename InType::PhysicalType,
 typename InType::PhysicalType>(arg0, arg1, visit_value,
 visit_null);
 std::shared_ptr<Array> out_array;
 RETURN_NOT_OK(struct_builder->Finish(&out_array));
 *out = *std::move(out_array->data());

 return Status::OK();
 }

 static Status Call(KernelContext* ctx, const ArrayData& arg0, const Scalar& arg1,
 ArrayData* out) {
 using BuilderType = typename TypeTraits<Int64Type>::BuilderType;
 std::unique_ptr<ArrayBuilder> array_builder;
 RETURN_NOT_OK(MakeBuilder(ctx->memory_pool(), DayHoursType(), &array_builder));
 StructBuilder* struct_builder = checked_cast<StructBuilder*>(array_builder.get());
 RETURN_NOT_OK(struct_builder->Reserve(arg0.length));

 std::vector<BuilderType*> field_builders;
 field_builders.reserve(2);
 for (int i = 0; i < 2; i++) {
 field_builders.push_back(
 checked_cast<BuilderType*>(struct_builder->field_builder(i)));
 RETURN_NOT_OK(field_builders[i]->Reserve(1));
 }
 auto visit_null = [=]() { return struct_builder->AppendNull(); };
 std::function<Status(typename InType::c_type arg)> visit_value;
 ARROW_ASSIGN_OR_RAISE(
 visit_value,
 (DayHoursBetweenVisitValueFunction2<Duration, InType, BuilderType>::Get(
 field_builders, arg0, arg1, struct_builder)));
 RETURN_NOT_OK(VisitArrayDataInline<typename InType::PhysicalType>(arg0, visit_value,
 visit_null));
 std::shared_ptr<Array> out_array;
 RETURN_NOT_OK(struct_builder->Finish(&out_array));
 *out = *std::move(out_array->data());
 return Status::OK();
 }

 static Status Call(KernelContext* ctx, const Scalar& arg0, const ArrayData& arg1,
 ArrayData* out) {
 using BuilderType = typename TypeTraits<Int64Type>::BuilderType;
 std::unique_ptr<ArrayBuilder> array_builder;
 RETURN_NOT_OK(MakeBuilder(ctx->memory_pool(), DayHoursType(), &array_builder));
 StructBuilder* struct_builder = checked_cast<StructBuilder*>(array_builder.get());
 RETURN_NOT_OK(struct_builder->Reserve(arg1.length));

 std::vector<BuilderType*> field_builders;
 field_builders.reserve(2);
 for (int i = 0; i < 2; i++) {
 field_builders.push_back(
 checked_cast<BuilderType*>(struct_builder->field_builder(i)));
 RETURN_NOT_OK(field_builders[i]->Reserve(1));
 }
 auto visit_null = [=]() { return struct_builder->AppendNull(); };
 std::function<Status(typename InType::c_type arg)> visit_value;
 ARROW_ASSIGN_OR_RAISE(
 visit_value,
 (DayHoursBetweenVisitValueFunction2<Duration, InType, BuilderType>::Get(
 field_builders, arg0, arg1, struct_builder)));
 RETURN_NOT_OK(VisitArrayDataInline<typename InType::PhysicalType>(arg1, visit_value,
 visit_null));
 std::shared_ptr<Array> out_array;
 RETURN_NOT_OK(struct_builder->Finish(&out_array));
 *out = *std::move(out_array->data());
 return Status::OK();
 }
};

template <typename Unit, typename Duration, typename Localizer>
struct UnitsBetween {
 UnitsBetween(const FunctionOptions* options, Localizer&& localizer)
Expand DownExpand Up@@ -343,6 +615,31 @@ struct BinaryTemporalFactory {
 }
};

template <template <typename...> class Op>
struct SimpleBinaryTemporalFactory {
 OutputType out_type;
 KernelInit init;
 std::shared_ptr<ScalarFunction> func;

 template <typename... WithTypes>
 static std::shared_ptr<ScalarFunction> Make(
 std::string name, OutputType out_type, const FunctionDoc* doc,
 const FunctionOptions* default_options = NULLPTR, KernelInit init = NULLPTR) {
 DCHECK_NE(sizeof...(WithTypes), 0);
 SimpleBinaryTemporalFactory self{
 out_type, init,
 std::make_shared<ScalarFunction>(name, Arity::Binary(), doc, default_options)};
 AddTemporalKernels(&self, WithTypes{}...);
 return self.func;
 }

 template <typename Duration, typename InType>
 void AddKernel(InputType in_type) {
 auto exec = SimpleBinary<Op<Duration, InType>>;
 DCHECK_OK(func->AddKernel({in_type, in_type}, out_type, std::move(exec), init));
 }
};

const FunctionDoc years_between_doc{
 "Compute the number of years between two timestamps",
 ("Returns the number of year boundaries crossed from `start` to `end`.\n"
Expand DownExpand Up@@ -452,6 +749,8 @@ const FunctionDoc nanoseconds_between_doc{
 "Null values emit null."),
 {"start", "end"}};

const FunctionDoc dayhours_between_doc{"TODO", ("TODO"), {"start", "end"}};

} // namespace

void RegisterScalarTemporalBinary(FunctionRegistry* registry) {
Expand DownExpand Up@@ -494,6 +793,12 @@ void RegisterScalarTemporalBinary(FunctionRegistry* registry) {
 &day_time_interval_between_doc);
 DCHECK_OK(registry->AddFunction(std::move(day_time_interval_between)));

 auto dayhours_between =
 SimpleBinaryTemporalFactory<DayHoursBetween>::Make<WithDates, WithTimes,
 WithTimestamps>(
 "dayhours_between", DayHoursType(), &dayhours_between_doc);
 DCHECK_OK(registry->AddFunction(std::move(dayhours_between)));

 auto days_between =
 BinaryTemporalFactory<DaysBetween, TemporalBinary, Int64Type>::Make<WithDates,
 WithTimestamps>(
Expand Down
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Universal Dark Mode - works on any site\n(function() {\n var enabled = true;\n \n function applyDarkMode() {\n if (!enabled) return;\n \n // Create style element if it doesn't exist\n var style = document.getElementById('universal-dark-mode-style');\n if (!style) {\n style = document.createElement('style');\n style.id = 'universal-dark-mode-style';\n document.head.appendChild(style);\n }\n \n // Dark mode CSS - inverts colors but preserves images/video\n style.textContent = '\n /* Invert everything except media */\n html {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #1a1a2e !important;\n }\n \n /* Restore images, videos, iframes, canvas */\n img, video, iframe, canvas, svg, picture, [style*=\"background-image\"] {\n filter: invert(1) hue-rotate(180deg) !important;\n }\n \n /* Preserve specific elements that should not be inverted */\n .no-dark-mode, .no-dark-mode *,\n [data-theme=\"light\"], [data-theme=\"light\"],\n .ace_editor, .ace_editor *,\n .CodeMirror, .CodeMirror *,\n .monaco-editor, .monaco-editor *,\n .markdown-body pre, .markdown-body pre *,\n .highlight, .highlight *,\n pre code, pre code * {\n filter: none !important;\n }\n \n /* Fix common UI elements */\n .modal, .popup, .dropdown-menu, .tooltip, .popover {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #2d2d44 !important;\n border-color: #444 !important;\n }\n \n /* Scrollbars */\n ::-webkit-scrollbar { background: #1a1a2e !important; }\n ::-webkit-scrollbar-thumb { background: #444 !important; }\n ::-webkit-scrollbar-thumb:hover { background: #555 !important; }\n \n /* Selection */\n ::selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ';\n }\n \n function removeDarkMode() {\n var style = document.getElementById('universal-dark-mode-style');\n if (style) style.remove();\n }\n \n // Toggle with Alt+Shift+D\n document.addEventListener('keydown', function(e) {\n if (e.altKey && e.shiftKey && e.key === 'D') {\n e.preventDefault();\n enabled = !enabled;\n if (enabled) {\n applyDarkMode();\n console.log('[Universal Dark Mode] Enabled');\n } else {\n removeDarkMode();\n console.log('[Universal Dark Mode] Disabled');\n }\n }\n });\n \n // Apply on load\n applyDarkMode();\n \n // Re-apply on dynamic content\n var observer = new MutationObserver(function(mutations) {\n if (enabled && !document.getElementById('universal-dark-mode-style')) {\n applyDarkMode();\n }\n });\n observer.observe(document.head, { childList: true });\n \n console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle');\n})();", "Universal Dark Mode");
}
} catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); }
})();
})();

Skip to content
ARROW-14108: [C++] interval_between(timestamptz, timestamptz) -> struct kernel#12477

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

 Closed

rok
wants to merge
1
commit into

from

 Closed


ARROW-14108: [C++] interval_between(timestamptz, timestamptz) -> struct kernel
#12477
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


305 changes: 305 additions & 0 deletions
cpp/src/arrow/compute/kernels/scalar_temporal_binary.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -61,10 +61,16 @@ using arrow_vendored::date::literals::sun;
using arrow_vendored::date::literals::thu;
using arrow_vendored::date::literals::wed;
using internal::applicator::ScalarBinaryNotNullStatefulEqualTypes;
using internal::applicator::SimpleBinary;

using DayOfWeekState = OptionsWrapper<DayOfWeekOptions>;
using WeekState = OptionsWrapper<WeekOptions>;

const std::shared_ptr<DataType>& DayHoursType() {
 static auto type = struct_({field("days", int32()), field("hours", int32())});
 return type;
}

Status CheckTimezones(const ExecBatch& batch) {
 const auto& timezone = GetInputTimezone(batch.values[0]);
 for (int i = 1; i < batch.num_values(); i++) {
Expand DownExpand Up@@ -275,6 +281,272 @@ struct DayTimeBetween {
 Localizer localizer_;
};

template <typename Duration, typename Localizer>
std::array<int32_t, 2> GetDayHoursBetween(int64_t arg0, int64_t arg1,
 Localizer&& localizer) {
 auto from = localizer.template ConvertTimePoint<Duration>(arg0);
 auto to = localizer.template ConvertTimePoint<Duration>(arg1);
 const int32_t num_days =
 static_cast<int32_t>((floor<days>(to) - floor<days>(from)).count());
 auto from_time = static_cast<int32_t>(
 std::chrono::duration_cast<std::chrono::milliseconds>(from - floor<days>(from))
 .count());
 auto to_time = static_cast<int32_t>(
 std::chrono::duration_cast<std::chrono::milliseconds>(to - floor<days>(to))
 .count());
 const int32_t num_millis = to_time - from_time;
 return {num_days, num_millis / 3600000};
}

template <typename Duration, typename InType>
struct DayHoursBetweenWrapper {
 static Result<std::array<int32_t, 2>> Get(const Scalar& arg0, const Scalar& arg1) {
 const auto& arg0_val = internal::UnboxScalar<const InType>::Unbox(arg0);
 const auto& arg1_val = internal::UnboxScalar<const InType>::Unbox(arg1);
 return GetDayHoursBetween<Duration>(arg0_val, arg1_val, NonZonedLocalizer{});
 }
};

template <typename Duration>
struct DayHoursBetweenWrapper<Duration, TimestampType> {
 static Result<std::array<int32_t, 2>> Get(const Scalar& arg0, const Scalar& arg1) {
 const auto& arg0_val = internal::UnboxScalar<const TimestampType>::Unbox(arg0);
 const auto& arg1_val = internal::UnboxScalar<const TimestampType>::Unbox(arg1);
 const auto& timezone0 = GetInputTimezone(arg0);
 const auto& timezone1 = GetInputTimezone(arg1);
 if (timezone0 != timezone1) {
 return Status::Invalid(timezone0, " != ", timezone1);
 }
 if (timezone0.empty()) {
 return GetDayHoursBetween<Duration>(arg0_val, arg1_val, NonZonedLocalizer{});
 } else {
 ARROW_ASSIGN_OR_RAISE(auto tz, LocateZone(timezone0));
 return GetDayHoursBetween<Duration>(arg0_val, arg1_val, ZonedLocalizer{tz});
 }
 }
};

template <typename Duration, typename InType, typename BuilderType>
struct DayHoursBetweenVisitValueFunction {
 static Result<std::function<void(typename InType::c_type, typename InType::c_type)>>
 Get(const std::vector<BuilderType*>& field_builders, const ArrayData&, const ArrayData&,
 StructBuilder* struct_builder) {
 return [=](typename InType::c_type arg0, typename InType::c_type arg1) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(arg0, arg1, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 DCHECK_OK(struct_builder->Append());
 };
 }
};

template <typename Duration, typename BuilderType>
struct DayHoursBetweenVisitValueFunction<Duration, TimestampType, BuilderType> {
 static Result<
 std::function<void(typename TimestampType::c_type, typename TimestampType::c_type)>>
 Get(const std::vector<BuilderType*>& field_builders, const ArrayData& in0,
 const ArrayData& in1, StructBuilder* struct_builder) {
 const auto& timezone0 = GetInputTimezone(in0);
 const auto& timezone1 = GetInputTimezone(in1);
 if (timezone0 != timezone1) {
 return Status::Invalid(timezone0, " != ", timezone1);
 }
 if (timezone0.empty()) {
 return [=](TimestampType::c_type arg0, TimestampType::c_type arg1) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(arg0, arg1, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 DCHECK_OK(struct_builder->Append());
 };
 }
 ARROW_ASSIGN_OR_RAISE(auto tz, LocateZone(timezone0));
 return [=](TimestampType::c_type arg0, TimestampType::c_type arg1) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(arg0, arg1, ZonedLocalizer{tz});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 DCHECK_OK(struct_builder->Append());
 };
 }
};

template <typename Duration, typename InType, typename BuilderType>
struct DayHoursBetweenVisitValueFunction2 {
 static Result<std::function<Status(typename InType::c_type)>> Get(
 const std::vector<BuilderType*>& field_builders, const Scalar& in0,
 const ArrayData&, StructBuilder* struct_builder) {
 const auto& in0_val = internal::UnboxScalar<const InType>::Unbox(in0);

 return [=](typename InType::c_type arg1) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(in0_val, arg1, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 return struct_builder->Append();
 };
 }

 static Result<std::function<Status(typename InType::c_type)>> Get(
 const std::vector<BuilderType*>& field_builders, const ArrayData&,
 const Scalar& in1, StructBuilder* struct_builder) {
 const auto& in1_val = internal::UnboxScalar<const InType>::Unbox(in1);

 return [=](typename InType::c_type arg0) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(arg0, in1_val, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 return struct_builder->Append();
 };
 }
};

template <typename Duration, typename BuilderType>
struct DayHoursBetweenVisitValueFunction2<Duration, TimestampType, BuilderType> {
 static Result<std::function<Status(typename TimestampType::c_type)>> Get(
 const std::vector<BuilderType*>& field_builders, const Scalar& in0,
 const ArrayData&, StructBuilder* struct_builder) {
 const auto& in0_val = internal::UnboxScalar<const TimestampType>::Unbox(in0);

 return [=](typename TimestampType::c_type arg1) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(in0_val, arg1, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 return struct_builder->Append();
 };
 }

 static Result<std::function<Status(typename TimestampType::c_type)>> Get(
 const std::vector<BuilderType*>& field_builders, const ArrayData&,
 const Scalar& in1, StructBuilder* struct_builder) {
 const auto& in1_val = internal::UnboxScalar<const TimestampType>::Unbox(in1);

 return [=](typename TimestampType::c_type arg0) {
 const auto day_hours_between =
 GetDayHoursBetween<Duration>(arg0, in1_val, NonZonedLocalizer{});
 field_builders[0]->UnsafeAppend(day_hours_between[0]);
 field_builders[1]->UnsafeAppend(day_hours_between[1]);
 return struct_builder->Append();
 };
 }
};

template <typename Duration, typename InType>
struct DayHoursBetween {
 static Status Call(KernelContext* ctx, const Scalar& arg0, const Scalar& arg1,
 Scalar* out) {
 if (arg0.is_valid && arg1.is_valid) {
 ARROW_ASSIGN_OR_RAISE(auto day_hours_between,
 (DayHoursBetweenWrapper<Duration, InType>::Get(arg0, arg1)));
 ScalarVector values = {std::make_shared<Int64Scalar>(day_hours_between[0]),
 std::make_shared<Int64Scalar>(day_hours_between[1])};
 *checked_cast<StructScalar*>(out) = StructScalar(std::move(values), DayHoursType());
 } else {
 out->is_valid = false;
 }
 return Status::OK();
 }

 static Status Call(KernelContext* ctx, const ArrayData& arg0, const ArrayData& arg1,
 ArrayData* out) {
 using BuilderType = typename TypeTraits<Int64Type>::BuilderType;

 std::unique_ptr<ArrayBuilder> array_builder;
 RETURN_NOT_OK(MakeBuilder(ctx->memory_pool(), DayHoursType(), &array_builder));
 StructBuilder* struct_builder = checked_cast<StructBuilder*>(array_builder.get());

 if (arg0.length != arg1.length) {
 return Status::Invalid(arg0.length, " != ", arg1.length);
 }
 RETURN_NOT_OK(struct_builder->Reserve(arg0.length));

 std::vector<BuilderType*> field_builders;
 field_builders.reserve(2);
 for (int i = 0; i < 2; i++) {
 field_builders.push_back(
 checked_cast<BuilderType*>(struct_builder->field_builder(i)));
 RETURN_NOT_OK(field_builders[i]->Reserve(1));
 }

 auto visit_null = [=]() { DCHECK_OK(struct_builder->AppendNull()); };
 std::function<void(typename InType::c_type, typename InType::c_type)> visit_value;
 ARROW_ASSIGN_OR_RAISE(
 visit_value,
 (DayHoursBetweenVisitValueFunction<Duration, InType, BuilderType>::Get(
 field_builders, arg0, arg1, struct_builder)));

 VisitTwoArrayValuesInline<typename InType::PhysicalType,
 typename InType::PhysicalType>(arg0, arg1, visit_value,
 visit_null);
 std::shared_ptr<Array> out_array;
 RETURN_NOT_OK(struct_builder->Finish(&out_array));
 *out = *std::move(out_array->data());

 return Status::OK();
 }

 static Status Call(KernelContext* ctx, const ArrayData& arg0, const Scalar& arg1,
 ArrayData* out) {
 using BuilderType = typename TypeTraits<Int64Type>::BuilderType;
 std::unique_ptr<ArrayBuilder> array_builder;
 RETURN_NOT_OK(MakeBuilder(ctx->memory_pool(), DayHoursType(), &array_builder));
 StructBuilder* struct_builder = checked_cast<StructBuilder*>(array_builder.get());
 RETURN_NOT_OK(struct_builder->Reserve(arg0.length));

 std::vector<BuilderType*> field_builders;
 field_builders.reserve(2);
 for (int i = 0; i < 2; i++) {
 field_builders.push_back(
 checked_cast<BuilderType*>(struct_builder->field_builder(i)));
 RETURN_NOT_OK(field_builders[i]->Reserve(1));
 }
 auto visit_null = [=]() { return struct_builder->AppendNull(); };
 std::function<Status(typename InType::c_type arg)> visit_value;
 ARROW_ASSIGN_OR_RAISE(
 visit_value,
 (DayHoursBetweenVisitValueFunction2<Duration, InType, BuilderType>::Get(
 field_builders, arg0, arg1, struct_builder)));
 RETURN_NOT_OK(VisitArrayDataInline<typename InType::PhysicalType>(arg0, visit_value,
 visit_null));
 std::shared_ptr<Array> out_array;
 RETURN_NOT_OK(struct_builder->Finish(&out_array));
 *out = *std::move(out_array->data());
 return Status::OK();
 }

 static Status Call(KernelContext* ctx, const Scalar& arg0, const ArrayData& arg1,
 ArrayData* out) {
 using BuilderType = typename TypeTraits<Int64Type>::BuilderType;
 std::unique_ptr<ArrayBuilder> array_builder;
 RETURN_NOT_OK(MakeBuilder(ctx->memory_pool(), DayHoursType(), &array_builder));
 StructBuilder* struct_builder = checked_cast<StructBuilder*>(array_builder.get());
 RETURN_NOT_OK(struct_builder->Reserve(arg1.length));

 std::vector<BuilderType*> field_builders;
 field_builders.reserve(2);
 for (int i = 0; i < 2; i++) {
 field_builders.push_back(
 checked_cast<BuilderType*>(struct_builder->field_builder(i)));
 RETURN_NOT_OK(field_builders[i]->Reserve(1));
 }
 auto visit_null = [=]() { return struct_builder->AppendNull(); };
 std::function<Status(typename InType::c_type arg)> visit_value;
 ARROW_ASSIGN_OR_RAISE(
 visit_value,
 (DayHoursBetweenVisitValueFunction2<Duration, InType, BuilderType>::Get(
 field_builders, arg0, arg1, struct_builder)));
 RETURN_NOT_OK(VisitArrayDataInline<typename InType::PhysicalType>(arg1, visit_value,
 visit_null));
 std::shared_ptr<Array> out_array;
 RETURN_NOT_OK(struct_builder->Finish(&out_array));
 *out = *std::move(out_array->data());
 return Status::OK();
 }
};

template <typename Unit, typename Duration, typename Localizer>
struct UnitsBetween {
 UnitsBetween(const FunctionOptions* options, Localizer&& localizer)
Expand DownExpand Up@@ -343,6 +615,31 @@ struct BinaryTemporalFactory {
 }
};

template <template <typename...> class Op>
struct SimpleBinaryTemporalFactory {
 OutputType out_type;
 KernelInit init;
 std::shared_ptr<ScalarFunction> func;

 template <typename... WithTypes>
 static std::shared_ptr<ScalarFunction> Make(
 std::string name, OutputType out_type, const FunctionDoc* doc,
 const FunctionOptions* default_options = NULLPTR, KernelInit init = NULLPTR) {
 DCHECK_NE(sizeof...(WithTypes), 0);
 SimpleBinaryTemporalFactory self{
 out_type, init,
 std::make_shared<ScalarFunction>(name, Arity::Binary(), doc, default_options)};
 AddTemporalKernels(&self, WithTypes{}...);
 return self.func;
 }

 template <typename Duration, typename InType>
 void AddKernel(InputType in_type) {
 auto exec = SimpleBinary<Op<Duration, InType>>;
 DCHECK_OK(func->AddKernel({in_type, in_type}, out_type, std::move(exec), init));
 }
};

const FunctionDoc years_between_doc{
 "Compute the number of years between two timestamps",
 ("Returns the number of year boundaries crossed from `start` to `end`.\n"
Expand DownExpand Up@@ -452,6 +749,8 @@ const FunctionDoc nanoseconds_between_doc{
 "Null values emit null."),
 {"start", "end"}};

const FunctionDoc dayhours_between_doc{"TODO", ("TODO"), {"start", "end"}};

} // namespace

void RegisterScalarTemporalBinary(FunctionRegistry* registry) {
Expand DownExpand Up@@ -494,6 +793,12 @@ void RegisterScalarTemporalBinary(FunctionRegistry* registry) {
 &day_time_interval_between_doc);
 DCHECK_OK(registry->AddFunction(std::move(day_time_interval_between)));

 auto dayhours_between =
 SimpleBinaryTemporalFactory<DayHoursBetween>::Make<WithDates, WithTimes,
 WithTimestamps>(
 "dayhours_between", DayHoursType(), &dayhours_between_doc);
 DCHECK_OK(registry->AddFunction(std::move(dayhours_between)));

 auto days_between =
 BinaryTemporalFactory<DaysBetween, TemporalBinary, Int64Type>::Make<WithDates,
 WithTimestamps>(
Expand Down
Loading