Upgrade GEOS, Improve documentation, Add/Rename ST_Extent_Agg

deps/CMakeLists.txt

@@ -177,7 +177,7 @@ set(GDAL_DEPENDENCIES ${GDAL_DEPENDENCIES} EXPAT)
 # GEOS
 ExternalProject_Add(
     GEOS
-    URL ${CMAKE_CURRENT_SOURCE_DIR}/vendor/geos-3.12.1.tar.bz2
+    URL ${CMAKE_CURRENT_SOURCE_DIR}/vendor/geos-3.13.0.tar.bz2
     CONFIGURE_HANDLED_BY_BUILD TRUE
     CMAKE_ARGS 
     # CMake options

docs/functions.md

@@ -113,7 +113,8 @@
 
 | Function | Summary |
 | --- | --- |
-| [`ST_Envelope_Agg`](#st_envelope_agg) | Computes a minimal-bounding-box polygon 'enveloping' the set of input geometries |
+| [`ST_Envelope_Agg`](#st_envelope_agg) | Alias for [ST_Extent_Agg](#st_extent_agg). |
+| [`ST_Extent_Agg`](#st_extent_agg) | Computes the minimal-bounding-box polygon containing the set of input geometries |
 | [`ST_Intersection_Agg`](#st_intersection_agg) | Computes the intersection of a set of geometries |
 | [`ST_Union_Agg`](#st_union_agg) | Computes the union of a set of input geometries |
 
@@ -124,7 +125,7 @@
 | [`ST_Drivers`](#st_drivers) | Returns the list of supported GDAL drivers and file formats |
 | [`ST_Read`](#st_read) | Read and import a variety of geospatial file formats using the GDAL library. |
 | [`ST_ReadOSM`](#st_readosm) | The `ST_ReadOsm()` table function enables reading compressed OpenStreetMap data directly from a `.osm.pbf file.` |
-| [`ST_Read_Meta`](#st_read_meta) | Read and the metadata from a variety of geospatial file formats using the GDAL library. |
+| [`ST_Read_Meta`](#st_read_meta) | Read the metadata from a variety of geospatial file formats using the GDAL library. |
 
 ----
 
@@ -342,9 +343,9 @@ Returns the "boundary" of a geometry
 #### Signatures
 
 ```sql
-GEOMETRY ST_Buffer (col0 GEOMETRY, col1 DOUBLE)
-GEOMETRY ST_Buffer (col0 GEOMETRY, col1 DOUBLE, col2 INTEGER)
-GEOMETRY ST_Buffer (col0 GEOMETRY, col1 DOUBLE, col2 INTEGER, col3 VARCHAR, col4 VARCHAR, col5 DOUBLE)
+GEOMETRY ST_Buffer (geom GEOMETRY, distance DOUBLE)
+GEOMETRY ST_Buffer (geom GEOMETRY, distance DOUBLE, num_triangles INTEGER)
+GEOMETRY ST_Buffer (geom GEOMETRY, distance DOUBLE, num_triangles INTEGER, join_style VARCHAR, cap_style VARCHAR, mitre_limit DOUBLE)
 ```
 
 #### Description
@@ -716,7 +717,7 @@ DOUBLE ST_Distance_Spheroid (col0 POINT_2D, col1 POINT_2D)
 
 Returns the distance between two geometries in meters using a ellipsoidal model of the earths surface
 
-The input geometry is assumed to be in the [EPSG:4326](https://en.wikipedia.org/wiki/World_Geodetic_System) coordinate system (WGS84), with [latitude, longitude] axis order and the distance is returned in meters. This function uses the [GeographicLib](https://geographiclib.sourceforge.io/) library to solve the [inverse geodesic problem](https://en.wikipedia.org/wiki/Geodesics_on_an_ellipsoid#Solution_of_the_direct_and_inverse_problems), calculating the distance between two points using an ellipsoidal model of the earth. This is a highly accurate method for calculating the distance between two arbitrary points taking the curvature of the earths surface into account, but is also the slowest.
+The input geometry is assumed to be in the [EPSG:4326](https://en.wikipedia.org/wiki/World_Geodetic_System) coordinate system (WGS84), with [latitude, longitude] axis order and the distance limit is expected to be in meters. This function uses the [GeographicLib](https://geographiclib.sourceforge.io/) library to solve the [inverse geodesic problem](https://en.wikipedia.org/wiki/Geodesics_on_an_ellipsoid#Solution_of_the_direct_and_inverse_problems), calculating the distance between two points using an ellipsoidal model of the earth. This is a highly accurate method for calculating the distance between two arbitrary points taking the curvature of the earths surface into account, but is also the slowest.
 
 #### Example
 
@@ -1885,12 +1886,12 @@ Returns true if geom1 "touches" geom2
 #### Signatures
 
 ```sql
-BOX_2D ST_Transform (col0 BOX_2D, col1 VARCHAR, col2 VARCHAR)
-BOX_2D ST_Transform (col0 BOX_2D, col1 VARCHAR, col2 VARCHAR, col3 BOOLEAN)
-POINT_2D ST_Transform (col0 POINT_2D, col1 VARCHAR, col2 VARCHAR)
-POINT_2D ST_Transform (col0 POINT_2D, col1 VARCHAR, col2 VARCHAR, col3 BOOLEAN)
-GEOMETRY ST_Transform (col0 GEOMETRY, col1 VARCHAR, col2 VARCHAR)
-GEOMETRY ST_Transform (col0 GEOMETRY, col1 VARCHAR, col2 VARCHAR, col3 BOOLEAN)
+BOX_2D ST_Transform (geom BOX_2D, source_crs VARCHAR, target_crs VARCHAR)
+BOX_2D ST_Transform (geom BOX_2D, source_crs VARCHAR, target_crs VARCHAR, always_xy BOOLEAN)
+POINT_2D ST_Transform (geom POINT_2D, source_crs VARCHAR, target_crs VARCHAR)
+POINT_2D ST_Transform (geom POINT_2D, source_crs VARCHAR, target_crs VARCHAR, always_xy BOOLEAN)
+GEOMETRY ST_Transform (geom GEOMETRY, source_crs VARCHAR, target_crs VARCHAR)
+GEOMETRY ST_Transform (geom GEOMETRY, source_crs VARCHAR, target_crs VARCHAR, always_xy BOOLEAN)
 ```
 
 #### Description
@@ -2201,7 +2202,38 @@ GEOMETRY ST_Envelope_Agg (col0 GEOMETRY)
 
 #### Description
 
-Computes a minimal-bounding-box polygon 'enveloping' the set of input geometries
+Alias for [ST_Extent_Agg](#st_extent_agg).
+
+Computes the minimal-bounding-box polygon containing the set of input geometries.
+
+#### Example
+
+```sql
+SELECT ST_Extent_Agg(geom) FROM UNNEST([ST_Point(1,1), ST_Point(5,5)]) AS _(geom);
+-- POLYGON ((1 1, 1 5, 5 5, 5 1, 1 1))
+```
+
+----
+
+### ST_Extent_Agg
+
+
+#### Signature
+
+```sql
+GEOMETRY ST_Extent_Agg (col0 GEOMETRY)
+```
+
+#### Description
+
+Computes the minimal-bounding-box polygon containing the set of input geometries
+
+#### Example
+
+```sql
+SELECT ST_Extent_Agg(geom) FROM UNNEST([ST_Point(1,1), ST_Point(5,5)]) AS _(geom);
+-- POLYGON ((1 1, 1 5, 5 5, 5 1, 1 1))
+```
 
 ----
 
@@ -2371,7 +2403,7 @@ ST_Read_Meta (col0 VARCHAR[])
 
 #### Description
 
-Read and the metadata from a variety of geospatial file formats using the GDAL library.
+Read the metadata from a variety of geospatial file formats using the GDAL library.
 
 The `ST_Read_Meta` table function accompanies the `ST_Read` table function, but instead of reading the contents of a file, this function scans the metadata instead.
 Since the data model of the underlying GDAL library is quite flexible, most of the interesting metadata is within the returned `layers` column, which is a somewhat complex nested structure of DuckDB `STRUCT` and `LIST` types.

spatial/include/spatial/core/functions/aggregate.hpp

@@ -8,11 +8,11 @@ namespace core {
 struct CoreAggregateFunctions {
 public:
 	static void Register(DatabaseInstance &db) {
-		RegisterStEnvelopeAgg(db);
+		RegisterStExtentAgg(db);
 	}
 
 private:
-	static void RegisterStEnvelopeAgg(DatabaseInstance &db);
+	static void RegisterStExtentAgg(DatabaseInstance &db);
 };
 
 } // namespace core

spatial/include/spatial/core/index/rtree/rtree_node.hpp

@@ -184,7 +184,9 @@ struct alignas(RTreeEntry) RTreeNode {
 private:
 	uint32_t count;
 
+public:
 	// We got 20 bytes for the future
+	// make this public so compiler stops warning about unused fields
 	uint8_t _unused[20] = {};
 };
 

spatial/include/spatial/doc_util.hpp

@@ -24,6 +24,8 @@ struct DocUtil {
 		}
 		AddDocumentation(db, function_name, description, example, tag_map);
 	}
+
+	static void AddFunctionParameterNames(duckdb::DatabaseInstance &db, const char *function_name, duckdb::vector<duckdb::string> names);
 };
 
 } // namespace spatial

spatial/src/spatial/core/functions/aggregate/CMakeLists.txt

@@ -1,5 +1,5 @@
 set(EXTENSION_SOURCES
     ${EXTENSION_SOURCES}
-    ${CMAKE_CURRENT_SOURCE_DIR}/st_envelope_agg.cpp
+    ${CMAKE_CURRENT_SOURCE_DIR}/st_extent_agg.cpp
     PARENT_SCOPE
 )

spatial/src/spatial/core/functions/aggregate/st_envelope_agg.cpp → spatial/src/spatial/core/functions/aggregate/st_extent_agg.cpp

@@ -11,7 +11,7 @@ namespace spatial {
 
 namespace core {
 
-struct EnvelopeAggState {
+struct ExtentAggState {
 	bool is_set;
 	double xmin;
 	double xmax;
@@ -22,7 +22,7 @@ struct EnvelopeAggState {
 //------------------------------------------------------------------------
 // ENVELOPE AGG
 //------------------------------------------------------------------------
-struct EnvelopeAggFunction {
+struct ExtentAggFunction {
 	template <class STATE>
 	static void Initialize(STATE &state) {
 		state.is_set = false;
@@ -90,24 +90,37 @@ struct EnvelopeAggFunction {
 //------------------------------------------------------------------------------
 static constexpr DocTag DOC_TAGS[] = {{"ext", "spatial"}, {"category", "construction"}};
 static constexpr const char *DOC_DESCRIPTION = R"(
-    Computes a minimal-bounding-box polygon 'enveloping' the set of input geometries
+    Computes the minimal-bounding-box polygon containing the set of input geometries
 )";
 static constexpr const char *DOC_EXAMPLE = R"(
+	SELECT ST_Extent_Agg(geom) FROM UNNEST([ST_Point(1,1), ST_Point(5,5)]) AS _(geom);
+	-- POLYGON ((1 1, 1 5, 5 5, 5 1, 1 1))
+)";
+
+static constexpr const char* DOC_ALIAS_DESCRIPTION = R"(
+	Alias for [ST_Extent_Agg](#st_extent_agg).
 
+	Computes the minimal-bounding-box polygon containing the set of input geometries.
 )";
 
 //------------------------------------------------------------------------
 // Register
 //------------------------------------------------------------------------
-void CoreAggregateFunctions::RegisterStEnvelopeAgg(DatabaseInstance &db) {
+void CoreAggregateFunctions::RegisterStExtentAgg(DatabaseInstance &db) {
+
+	auto function = AggregateFunction::UnaryAggregate<ExtentAggState, geometry_t, geometry_t, ExtentAggFunction>(
+			GeoTypes::GEOMETRY(), GeoTypes::GEOMETRY());
+
+	// Register the function
+	function.name = "ST_Extent_Agg";
+	ExtensionUtil::RegisterFunction(db, function);
+	DocUtil::AddDocumentation(db, "ST_Extent_Agg", DOC_DESCRIPTION, DOC_EXAMPLE, DOC_TAGS);
 
-	AggregateFunctionSet st_envelope_agg("ST_Envelope_Agg");
-	st_envelope_agg.AddFunction(
-	    AggregateFunction::UnaryAggregate<EnvelopeAggState, geometry_t, geometry_t, EnvelopeAggFunction>(
-	        GeoTypes::GEOMETRY(), GeoTypes::GEOMETRY()));
+	// Also add an alias with the name ST_Envelope_Agg
+	function.name = "ST_Envelope_Agg";
+	ExtensionUtil::RegisterFunction(db, function);
+	DocUtil::AddDocumentation(db, "ST_Envelope_Agg", DOC_ALIAS_DESCRIPTION, DOC_EXAMPLE, DOC_TAGS);
 
-	ExtensionUtil::RegisterFunction(db, st_envelope_agg);
-	DocUtil::AddDocumentation(db, "ST_Envelope_Agg", DOC_DESCRIPTION, DOC_EXAMPLE, DOC_TAGS);
 }
 
 } // namespace core

spatial/src/spatial/gdal/functions/st_read_meta.cpp

@@ -211,7 +211,7 @@ static void Scan(ClientContext &context, TableFunctionInput &input, DataChunk &o
 static constexpr DocTag DOC_TAGS[] = {{"ext", "spatial"}};
 
 static constexpr const char *DOC_DESCRIPTION = R"(
-    Read and the metadata from a variety of geospatial file formats using the GDAL library.
+    Read the metadata from a variety of geospatial file formats using the GDAL library.
 
     The `ST_Read_Meta` table function accompanies the `ST_Read` table function, but instead of reading the contents of a file, this function scans the metadata instead.
     Since the data model of the underlying GDAL library is quite flexible, most of the interesting metadata is within the returned `layers` column, which is a somewhat complex nested structure of DuckDB `STRUCT` and `LIST` types.

spatial/src/spatial/geographiclib/functions/st_distance_spheroid.cpp

@@ -38,7 +38,7 @@ static void GeodesicPoint2DFunction(DataChunk &args, ExpressionState &state, Vec
 static constexpr const char *DOC_DESCRIPTION = R"(
 Returns the distance between two geometries in meters using a ellipsoidal model of the earths surface
 
-The input geometry is assumed to be in the [EPSG:4326](https://en.wikipedia.org/wiki/World_Geodetic_System) coordinate system (WGS84), with [latitude, longitude] axis order and the distance is returned in meters. This function uses the [GeographicLib](https://geographiclib.sourceforge.io/) library to solve the [inverse geodesic problem](https://en.wikipedia.org/wiki/Geodesics_on_an_ellipsoid#Solution_of_the_direct_and_inverse_problems), calculating the distance between two points using an ellipsoidal model of the earth. This is a highly accurate method for calculating the distance between two arbitrary points taking the curvature of the earths surface into account, but is also the slowest.
+The input geometry is assumed to be in the [EPSG:4326](https://en.wikipedia.org/wiki/World_Geodetic_System) coordinate system (WGS84), with [latitude, longitude] axis order and the distance limit is expected to be in meters. This function uses the [GeographicLib](https://geographiclib.sourceforge.io/) library to solve the [inverse geodesic problem](https://en.wikipedia.org/wiki/Geodesics_on_an_ellipsoid#Solution_of_the_direct_and_inverse_problems), calculating the distance between two points using an ellipsoidal model of the earth. This is a highly accurate method for calculating the distance between two arbitrary points taking the curvature of the earths surface into account, but is also the slowest.
 )";
 
 static constexpr const char *DOC_EXAMPLE = R"(

spatial/src/spatial/geos/functions/scalar/st_buffer.cpp

@@ -131,6 +131,8 @@ void GEOSScalarFunctions::RegisterStBuffer(DatabaseInstance &db) {
 
 	ExtensionUtil::RegisterFunction(db, set);
 	DocUtil::AddDocumentation(db, "ST_Buffer", DOC_DESCRIPTION, DOC_EXAMPLE, DOC_TAGS);
+	DocUtil::AddFunctionParameterNames(db, "ST_Buffer", {"geom", "distance", "num_triangles", "join_style", "cap_style",
+	                                                     "mitre_limit"});
 }
 
 } // namespace geos

spatial/src/spatial/proj/functions.cpp

@@ -511,6 +511,7 @@ void ProjFunctions::Register(DatabaseInstance &db) {
 
 	ExtensionUtil::RegisterFunction(db, set);
 	DocUtil::AddDocumentation(db, "ST_Transform", DOC_DESCRIPTION, DOC_EXAMPLE, DOC_TAGS);
+	DocUtil::AddFunctionParameterNames(db, "ST_Transform", {"geom", "source_crs", "target_crs", "always_xy"});
 
 	GenerateSpatialRefSysTable::Register(db);
 }

spatial/src/spatial_extension.cpp

@@ -84,6 +84,30 @@ void spatial::DocUtil::AddDocumentation(duckdb::DatabaseInstance &db, const char
 	}
 }
 
+void spatial::DocUtil::AddFunctionParameterNames(duckdb::DatabaseInstance &db, const char *function_name,
+                                                 duckdb::vector<duckdb::string> names) {
+	auto &system_catalog = Catalog::GetSystemCatalog(db);
+	auto data = CatalogTransaction::GetSystemTransaction(db);
+	auto &schema = system_catalog.GetSchema(data, DEFAULT_SCHEMA);
+	auto catalog_entry = schema.GetEntry(data, CatalogType::SCALAR_FUNCTION_ENTRY, function_name);
+	if (!catalog_entry) {
+		// Try get a aggregate function
+		catalog_entry = schema.GetEntry(data, CatalogType::AGGREGATE_FUNCTION_ENTRY, function_name);
+		if (!catalog_entry) {
+			// Try get a table function
+			catalog_entry = schema.GetEntry(data, CatalogType::TABLE_FUNCTION_ENTRY, function_name);
+			if (!catalog_entry) {
+				throw duckdb::InvalidInputException("Function with name \"%s\" not found in DocUtil::AddDocumentation",
+													function_name);
+			}
+		}
+	}
+
+	auto &func_entry = catalog_entry->Cast<FunctionEntry>();
+	func_entry.parameter_names = std::move(names);
+}
+
+
 namespace duckdb {
 
 static void LoadInternal(DatabaseInstance &instance) {