Skip to content

[feature](function) Add ST_NumGeometries, ST_NumPoints, ST_Geometries functions #63049

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
acarofpigs wants to merge 4 commits into
base: master
Choose a base branch
from
Open

[feature](function) Add ST_NumGeometries, ST_NumPoints, ST_Geometries functions #63049

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
8feb287
[feature](function) Add ST_NumGeometries, ST_NumPoints, ST_Geometries…
May 19, 2026
fb632cd
[fix](function) Fix ArrayType.of parameter error in StGeometries
May 20, 2026
37dabf7
[test](function) Add BE unit tests for ST_NumGeometries, ST_NumPoints…
May 22, 2026
29bda20
[fix](function) Return null for unsupported ST_NumPoints geometry
acarofpigs May 23, 2026
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
173 changes: 173 additions & 0 deletions be/src/exprs/function/geo/functions_geo.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,8 +28,10 @@
#include "core/block/block.h"
#include "core/block/column_with_type_and_name.h"
#include "core/column/column.h"
#include "core/column/column_array.h"
#include "core/column/column_execute_util.h"
#include "core/column/column_nullable.h"
#include "core/data_type/data_type_array.h"
#include "core/data_type/data_type_nullable.h"
#include "core/data_type/data_type_number.h"
#include "core/data_type/data_type_string.h"
Expand Down Expand Up @@ -917,6 +919,174 @@ struct StDistance {
}
};

struct StNumGeometries {
static constexpr auto NAME = "st_numgeometries";
static const size_t NUM_ARGS = 1;
using Type = DataTypeInt64;

static Status execute(Block& block, const ColumnNumbers& arguments, size_t result) {
DCHECK_EQ(arguments.size(), 1);

auto col = block.get_by_position(arguments[0]).column->convert_to_full_column_if_const();
const auto size = col->size();

auto res = ColumnInt64::create();
res->reserve(size);

auto null_map = ColumnUInt8::create(size, 0);
auto& null_map_data = null_map->get_data();

for (int row = 0; row < size; ++row) {
auto value = col->get_data_at(row);
auto shape = GeoShape::from_encoded(value.data, value.size);
if (!shape) {
null_map_data[row] = 1;
res->insert_default();
continue;
}

res->insert_value(shape->num_geometries());
}

block.replace_by_position(result,
ColumnNullable::create(std::move(res), std::move(null_map)));
return Status::OK();
}
};

struct StGeometries {
static constexpr auto NAME = "st_geometries";
static const size_t NUM_ARGS = 1;

static Status execute(Block& block, const ColumnNumbers& arguments, size_t result) {
DCHECK_EQ(arguments.size(), 1);

auto col = block.get_by_position(arguments[0]).column->convert_to_full_column_if_const();
const auto size = col->size();

auto nested_data = ColumnString::create();
auto offsets_col = ColumnArray::ColumnOffsets::create();
auto& offsets = offsets_col->get_data();
offsets.reserve(size);

auto null_map = ColumnUInt8::create(size, 0);
auto& null_map_data = null_map->get_data();

size_t current_offset = 0;
std::string buf;

for (size_t row = 0; row < size; ++row) {
auto shape_value = col->get_data_at(row);
auto shape = GeoShape::from_encoded(shape_value.data, shape_value.size);

if (!shape) {
null_map_data[row] = 1;
offsets.push_back(current_offset);
continue;
}

if (shape->type() == GEO_SHAPE_MULTI_POLYGON) {
auto* multi_polygon = static_cast<GeoMultiPolygon*>(shape.get());
const auto& polygons = multi_polygon->polygons();

if (polygons.empty()) {
null_map_data[row] = 1;
offsets.push_back(current_offset);
continue;
}

for (const auto& polygon : polygons) {
DCHECK(polygon != nullptr);
buf.clear();
polygon->encode_to(&buf);
nested_data->insert_data(buf.data(), buf.size());
++current_offset;
}
} else {
nested_data->insert_data(shape_value.data, shape_value.size);
++current_offset;
}

offsets.push_back(current_offset);
}

auto nested_null_map = ColumnUInt8::create(nested_data->size(), 0);
auto nested_nullable =
ColumnNullable::create(std::move(nested_data), std::move(nested_null_map));
auto array_col = ColumnArray::create(std::move(nested_nullable), std::move(offsets_col));

block.replace_by_position(
result, ColumnNullable::create(std::move(array_col), std::move(null_map)));

return Status::OK();
}
};

class FunctionStGeometries final : public IFunction {
public:
static constexpr auto name = StGeometries::NAME;

static FunctionPtr create() { return std::make_shared<FunctionStGeometries>(); }

String get_name() const override { return name; }

size_t get_number_of_arguments() const override { return StGeometries::NUM_ARGS; }

bool is_variadic() const override { return false; }

DataTypePtr get_return_type_impl(const DataTypes& arguments) const override {
return make_nullable(
std::make_shared<DataTypeArray>(make_nullable(std::make_shared<DataTypeString>())));
}

Status execute_impl(FunctionContext* context, Block& block, const ColumnNumbers& arguments,
uint32_t result, size_t input_rows_count) const override {
return StGeometries::execute(block, arguments, result);
}
};

struct StNumPoints {
static constexpr auto NAME = "st_numpoints";
static const size_t NUM_ARGS = 1;
using Type = DataTypeInt64;

static Status execute(Block& block, const ColumnNumbers& arguments, size_t result) {
DCHECK_EQ(arguments.size(), 1);

auto col = block.get_by_position(arguments[0]).column->convert_to_full_column_if_const();
const auto size = col->size();

auto res = ColumnInt64::create();
res->reserve(size);

auto null_map = ColumnUInt8::create(size, 0);
auto& null_map_data = null_map->get_data();

for (int row = 0; row < size; ++row) {
auto value = col->get_data_at(row);
auto shape = GeoShape::from_encoded(value.data, value.size);
if (!shape) {
null_map_data[row] = 1;
res->insert_default();
continue;
}

auto num_points = shape->num_points();
if (num_points < 0) {
null_map_data[row] = 1;
res->insert_default();
continue;
}

res->insert_value(num_points);
}
Copy link
Copy Markdown
Contributor

@github-actions github-actions Bot May 23, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

GeoShape::num_points() uses -1 as the base-class sentinel for shapes that do not implement a point count, and GeoCircle does not override it. This line therefore returns -1 for ST_NumPoints(ST_Circle(...)) (the new regression output also locks that in), which exposes an internal sentinel as a user-visible count. A point-count function should not return a negative count for a valid geometry; please convert negative num_points() results to NULL (or define a real non-negative count for circles) before inserting the value.


block.replace_by_position(result,
ColumnNullable::create(std::move(res), std::move(null_map)));
return Status::OK();
}
};

void register_function_geo(SimpleFunctionFactory& factory) {
factory.register_function<GeoFunction<StPoint>>();
factory.register_function<GeoFunction<StAsText<StAsWktName>>>();
Expand Down Expand Up @@ -947,6 +1117,9 @@ void register_function_geo(SimpleFunctionFactory& factory) {
factory.register_function<GeoFunction<StLength>>();
factory.register_function<GeoFunction<StGeometryType>>();
factory.register_function<GeoFunction<StDistance>>();
factory.register_function<GeoFunction<StNumGeometries>>();
factory.register_function<GeoFunction<StNumPoints>>();
factory.register_function<FunctionStGeometries>();
}

} // namespace doris
21 changes: 21 additions & 0 deletions be/src/exprs/function/geo/geo_types.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1929,6 +1929,27 @@ double GeoMultiPolygon::Distance(const GeoShape* rhs) const {
return (min_distance == std::numeric_limits<double>::max()) ? -1.0 : min_distance;
}

int GeoPolygon::num_points() const {
int total = 0;
for (int i = 0; i < numLoops(); ++i) {
auto* loop = getLoop(i);
DCHECK(loop != nullptr);
total += loop->num_vertices() + 1;
}
return total;
}

int GeoMultiPolygon::num_points() const {
int total = 0;
for (const auto& polygon : _polygons) {
DCHECK(polygon != nullptr);
int point_count = polygon->num_points();
DCHECK_GE(point_count, 0);
total += point_count;
}
return total;
}

double GeoCircle::Distance(const GeoShape* rhs) const {
// Both rhs and self are guaranteed to be valid by StDistance (functions_geo.cpp)
double circle_radius = S2Earth::ToMeters(_cap->radius());
Expand Down
15 changes: 15 additions & 0 deletions be/src/exprs/function/geo/geo_types.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,6 +81,9 @@ class GeoShape {

static bool ComputeArea(GeoShape* rhs, double* angle, std::string square_unit);

virtual int num_geometries() const { return 1; }
virtual int num_points() const { return -1; }

protected:
virtual void encode(std::string* buf) = 0;
virtual bool decode(const void* data, size_t size) = 0;
Expand Down Expand Up @@ -125,6 +128,9 @@ class GeoPoint : public GeoShape {
double x() const;
double y() const;

int num_geometries() const override { return 1; }
int num_points() const override { return 1; }

protected:
void encode(std::string* buf) override;
bool decode(const void* data, size_t size) override;
Expand Down Expand Up @@ -161,6 +167,9 @@ class GeoLine : public GeoShape {
int numPoint() const;
const S2Point* getPoint(int i) const;

int num_geometries() const override { return 1; }
int num_points() const override { return numPoint(); }

protected:
void encode(std::string* buf) override;
bool decode(const void* data, size_t size) override;
Expand Down Expand Up @@ -199,6 +208,9 @@ class GeoPolygon : public GeoShape {
double Distance(const GeoShape* rhs) const override;
S2Loop* getLoop(int i) const;

int num_geometries() const override { return 1; }
int num_points() const override;

protected:
void encode(std::string* buf) override;
bool decode(const void* data, size_t size) override;
Expand Down Expand Up @@ -232,6 +244,9 @@ class GeoMultiPolygon : public GeoShape {
double Length() const override;
double Distance(const GeoShape* rhs) const override;

int num_geometries() const override { return static_cast<int>(_polygons.size()); }
int num_points() const override;

protected:
void encode(std::string* buf) override;
bool decode(const void* data, size_t size) override;
Expand Down
Loading
Loading