X-Git-Url: https://git.openstreetmap.org./nominatim.git/blobdiff_plain/899a04ad264c45197ec7509b164c934a05392f30..3fb739de9275680d4f482d363f22c535442f0017:/nominatim/db/sqlalchemy_functions.py diff --git a/nominatim/db/sqlalchemy_functions.py b/nominatim/db/sqlalchemy_functions.py index 65b813cb..f576d32f 100644 --- a/nominatim/db/sqlalchemy_functions.py +++ b/nominatim/db/sqlalchemy_functions.py @@ -17,20 +17,19 @@ from nominatim.typing import SaColumn # pylint: disable=all -class PlacexGeometryReverseLookuppolygon(sa.sql.functions.GenericFunction[bool]): +class PlacexGeometryReverseLookuppolygon(sa.sql.functions.GenericFunction[Any]): """ Check for conditions that allow partial index use on 'idx_placex_geometry_reverse_lookupPolygon'. Needs to be constant, so that the query planner picks them up correctly in prepared statements. """ - type = sa.Boolean() name = 'PlacexGeometryReverseLookuppolygon' inherit_cache = True @compiles(PlacexGeometryReverseLookuppolygon) # type: ignore[no-untyped-call, misc] -def _default_intersects(element: SaColumn, +def _default_intersects(element: PlacexGeometryReverseLookuppolygon, compiler: 'sa.Compiled', **kw: Any) -> str: return ("(ST_GeometryType(placex.geometry) in ('ST_Polygon', 'ST_MultiPolygon')" " AND placex.rank_address between 4 and 25" @@ -41,7 +40,7 @@ def _default_intersects(element: SaColumn, @compiles(PlacexGeometryReverseLookuppolygon, 'sqlite') # type: ignore[no-untyped-call, misc] -def _sqlite_intersects(element: SaColumn, +def _sqlite_intersects(element: PlacexGeometryReverseLookuppolygon, compiler: 'sa.Compiled', **kw: Any) -> str: return ("(ST_GeometryType(placex.geometry) in ('POLYGON', 'MULTIPOLYGON')" " AND placex.rank_address between 4 and 25" @@ -51,37 +50,36 @@ def _sqlite_intersects(element: SaColumn, " AND placex.linked_place_id is null)") -class IntersectsReverseDistance(sa.sql.functions.GenericFunction[bool]): - type = sa.Boolean() +class IntersectsReverseDistance(sa.sql.functions.GenericFunction[Any]): name = 'IntersectsReverseDistance' inherit_cache = True def __init__(self, table: sa.Table, geom: SaColumn) -> None: - super().__init__(table.c.geometry, # type: ignore[no-untyped-call] + super().__init__(table.c.geometry, table.c.rank_search, geom) self.tablename = table.name @compiles(IntersectsReverseDistance) # type: ignore[no-untyped-call, misc] -def default_reverse_place_diameter(element: SaColumn, +def default_reverse_place_diameter(element: IntersectsReverseDistance, compiler: 'sa.Compiled', **kw: Any) -> str: table = element.tablename - return f"{table}.rank_address between 4 and 25"\ + return f"({table}.rank_address between 4 and 25"\ f" AND {table}.type != 'postcode'"\ f" AND {table}.name is not null"\ f" AND {table}.linked_place_id is null"\ f" AND {table}.osm_type = 'N'" + \ - " AND ST_Buffer(%s, reverse_place_diameter(%s)) && %s" % \ + " AND ST_Buffer(%s, reverse_place_diameter(%s)) && %s)" % \ tuple(map(lambda c: compiler.process(c, **kw), element.clauses)) @compiles(IntersectsReverseDistance, 'sqlite') # type: ignore[no-untyped-call, misc] -def sqlite_reverse_place_diameter(element: SaColumn, +def sqlite_reverse_place_diameter(element: IntersectsReverseDistance, compiler: 'sa.Compiled', **kw: Any) -> str: geom1, rank, geom2 = list(element.clauses) table = element.tablename - return (f"{table}.rank_address between 4 and 25"\ + return (f"({table}.rank_address between 4 and 25"\ f" AND {table}.type != 'postcode'"\ f" AND {table}.name is not null"\ f" AND {table}.linked_place_id is null"\ @@ -91,21 +89,20 @@ def sqlite_reverse_place_diameter(element: SaColumn, " (SELECT place_id FROM placex_place_node_areas"\ " WHERE ROWID IN (SELECT ROWID FROM SpatialIndex"\ " WHERE f_table_name = 'placex_place_node_areas'"\ - " AND search_frame = %s))") % ( + " AND search_frame = %s)))") % ( compiler.process(geom1, **kw), compiler.process(geom2, **kw), compiler.process(rank, **kw), compiler.process(geom2, **kw)) -class IsBelowReverseDistance(sa.sql.functions.GenericFunction[bool]): - type = sa.Boolean() +class IsBelowReverseDistance(sa.sql.functions.GenericFunction[Any]): name = 'IsBelowReverseDistance' inherit_cache = True @compiles(IsBelowReverseDistance) # type: ignore[no-untyped-call, misc] -def default_is_below_reverse_distance(element: SaColumn, +def default_is_below_reverse_distance(element: IsBelowReverseDistance, compiler: 'sa.Compiled', **kw: Any) -> str: dist, rank = list(element.clauses) return "%s < reverse_place_diameter(%s)" % (compiler.process(dist, **kw), @@ -113,37 +110,24 @@ def default_is_below_reverse_distance(element: SaColumn, @compiles(IsBelowReverseDistance, 'sqlite') # type: ignore[no-untyped-call, misc] -def sqlite_is_below_reverse_distance(element: SaColumn, +def sqlite_is_below_reverse_distance(element: IsBelowReverseDistance, compiler: 'sa.Compiled', **kw: Any) -> str: dist, rank = list(element.clauses) return "%s < 14.0 * exp(-0.2 * %s) - 0.03" % (compiler.process(dist, **kw), compiler.process(rank, **kw)) -def select_index_placex_geometry_reverse_lookupplacenode(table: str) -> 'sa.TextClause': - """ Create an expression with the necessary conditions over a placex - table that the index 'idx_placex_geometry_reverse_lookupPlaceNode' - can be used. - """ - return sa.text(f"{table}.rank_address between 4 and 25" - f" AND {table}.type != 'postcode'" - f" AND {table}.name is not null" - f" AND {table}.linked_place_id is null" - f" AND {table}.osm_type = 'N'") - - -class IsAddressPoint(sa.sql.functions.GenericFunction[bool]): - type = sa.Boolean() +class IsAddressPoint(sa.sql.functions.GenericFunction[Any]): name = 'IsAddressPoint' inherit_cache = True def __init__(self, table: sa.Table) -> None: - super().__init__(table.c.rank_address, # type: ignore[no-untyped-call] + super().__init__(table.c.rank_address, table.c.housenumber, table.c.name) @compiles(IsAddressPoint) # type: ignore[no-untyped-call, misc] -def default_is_address_point(element: SaColumn, +def default_is_address_point(element: IsAddressPoint, compiler: 'sa.Compiled', **kw: Any) -> str: rank, hnr, name = list(element.clauses) return "(%s = 30 AND (%s IS NOT NULL OR %s ? 'addr:housename'))" % ( @@ -153,7 +137,7 @@ def default_is_address_point(element: SaColumn, @compiles(IsAddressPoint, 'sqlite') # type: ignore[no-untyped-call, misc] -def sqlite_is_address_point(element: SaColumn, +def sqlite_is_address_point(element: IsAddressPoint, compiler: 'sa.Compiled', **kw: Any) -> str: rank, hnr, name = list(element.clauses) return "(%s = 30 AND coalesce(%s, json_extract(%s, '$.addr:housename')) IS NOT NULL)" % ( @@ -162,16 +146,15 @@ def sqlite_is_address_point(element: SaColumn, compiler.process(name, **kw)) -class CrosscheckNames(sa.sql.functions.GenericFunction[bool]): +class CrosscheckNames(sa.sql.functions.GenericFunction[Any]): """ Check if in the given list of names in parameters 1 any of the names from the JSON array in parameter 2 are contained. """ - type = sa.Boolean() name = 'CrosscheckNames' inherit_cache = True @compiles(CrosscheckNames) # type: ignore[no-untyped-call, misc] -def compile_crosscheck_names(element: SaColumn, +def compile_crosscheck_names(element: CrosscheckNames, compiler: 'sa.Compiled', **kw: Any) -> str: arg1, arg2 = list(element.clauses) return "coalesce(avals(%s) && ARRAY(SELECT * FROM json_array_elements_text(%s)), false)" % ( @@ -179,7 +162,7 @@ def compile_crosscheck_names(element: SaColumn, @compiles(CrosscheckNames, 'sqlite') # type: ignore[no-untyped-call, misc] -def compile_sqlite_crosscheck_names(element: SaColumn, +def compile_sqlite_crosscheck_names(element: CrosscheckNames, compiler: 'sa.Compiled', **kw: Any) -> str: arg1, arg2 = list(element.clauses) return "EXISTS(SELECT *"\ @@ -196,15 +179,16 @@ class JsonArrayEach(sa.sql.functions.GenericFunction[Any]): @compiles(JsonArrayEach) # type: ignore[no-untyped-call, misc] -def default_json_array_each(element: SaColumn, compiler: 'sa.Compiled', **kw: Any) -> str: +def default_json_array_each(element: JsonArrayEach, compiler: 'sa.Compiled', **kw: Any) -> str: return "json_array_elements(%s)" % compiler.process(element.clauses, **kw) @compiles(JsonArrayEach, 'sqlite') # type: ignore[no-untyped-call, misc] -def sqlite_json_array_each(element: SaColumn, compiler: 'sa.Compiled', **kw: Any) -> str: +def sqlite_json_array_each(element: JsonArrayEach, compiler: 'sa.Compiled', **kw: Any) -> str: return "json_each(%s)" % compiler.process(element.clauses, **kw) + class Greatest(sa.sql.functions.GenericFunction[Any]): """ Function to compute maximum of all its input parameters. """ @@ -213,5 +197,25 @@ class Greatest(sa.sql.functions.GenericFunction[Any]): @compiles(Greatest, 'sqlite') # type: ignore[no-untyped-call, misc] -def sqlite_greatest(element: SaColumn, compiler: 'sa.Compiled', **kw: Any) -> str: +def sqlite_greatest(element: Greatest, compiler: 'sa.Compiled', **kw: Any) -> str: return "max(%s)" % compiler.process(element.clauses, **kw) + + + +class RegexpWord(sa.sql.functions.GenericFunction[Any]): + """ Check if a full word is in a given string. + """ + name = 'RegexpWord' + inherit_cache = True + + +@compiles(RegexpWord, 'postgresql') # type: ignore[no-untyped-call, misc] +def postgres_regexp_nocase(element: RegexpWord, compiler: 'sa.Compiled', **kw: Any) -> str: + arg1, arg2 = list(element.clauses) + return "%s ~* ('\\m(' || %s || ')\\M')::text" % (compiler.process(arg2, **kw), compiler.process(arg1, **kw)) + + +@compiles(RegexpWord, 'sqlite') # type: ignore[no-untyped-call, misc] +def sqlite_regexp_nocase(element: RegexpWord, compiler: 'sa.Compiled', **kw: Any) -> str: + arg1, arg2 = list(element.clauses) + return "regexp('\\b(' || %s || ')\\b', %s)" % (compiler.process(arg1, **kw), compiler.process(arg2, **kw))