Merge pull request #3273 from lonvia/search-with-sqlite

[nominatim.git] / nominatim / db / sqlalchemy_functions.py

diff --git a/nominatim/db/sqlalchemy_functions.py b/nominatim/db/sqlalchemy_functions.py
index 6eed880367dfd9947b9e87ef17c646ab869f6955..e2437dd2e34c4ad4b5080558f8b4dee28ceb4cb1 100644 (file)
--- a/nominatim/db/sqlalchemy_functions.py
+++ b/nominatim/db/sqlalchemy_functions.py
@@ -15,42 +15,146 @@ from sqlalchemy.ext.compiler import compiles
 
 from nominatim.typing import SaColumn
 
 
 from nominatim.typing import SaColumn
 

-# pylint: disable=abstract-method,missing-function-docstring,consider-using-f-string
+# pylint: disable=all

 
 

-def select_index_placex_geometry_reverse_lookuppolygon(table: str) -> 'sa.TextClause':
-    """ Create an expression with the necessary conditions over a placex
-        table that the index 'idx_placex_geometry_reverse_lookupPolygon'
-        can be used.
-    """
-    return sa.text(f"ST_GeometryType({table}.geometry) in ('ST_Polygon', 'ST_MultiPolygon')"
-                   f" AND {table}.rank_address between 4 and 25"
-                   f" AND {table}.type != 'postcode'"
-                   f" AND {table}.name is not null"
-                   f" AND {table}.indexed_status = 0"
-                   f" AND {table}.linked_place_id is null")
-
-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.
+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.

     """
     """

-    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'")
+    name = 'PlacexGeometryReverseLookuppolygon'
+    inherit_cache = True
+
+
+@compiles(PlacexGeometryReverseLookuppolygon) # type: ignore[no-untyped-call, misc]
+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"
+            " AND placex.type != 'postcode'"
+            " AND placex.name is not null"
+            " AND placex.indexed_status = 0"
+            " AND placex.linked_place_id is null)")
+
+
+@compiles(PlacexGeometryReverseLookuppolygon, 'sqlite') # type: ignore[no-untyped-call, misc]
+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"
+            " AND placex.type != 'postcode'"
+            " AND placex.name is not null"
+            " AND placex.indexed_status = 0"
+            " AND placex.linked_place_id is null)")
+
+
+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]
+                         table.c.rank_search, geom)
+        self.tablename = table.name
+
+
+@compiles(IntersectsReverseDistance) # type: ignore[no-untyped-call, misc]
+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"\
+           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)" % \
+               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: 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"\
+            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 MbrIntersects(%s, ST_Expand(%s, 14.0 * exp(-0.2 * %s) - 0.03))"\
+            f" AND {table}.place_id IN"\
+             " (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)))") % (
+                compiler.process(geom1, **kw),
+                compiler.process(geom2, **kw),
+                compiler.process(rank, **kw),
+                compiler.process(geom2, **kw))
+
+
+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: IsBelowReverseDistance,
+                                      compiler: 'sa.Compiled', **kw: Any) -> str:
+    dist, rank = list(element.clauses)
+    return "%s < reverse_place_diameter(%s)" % (compiler.process(dist, **kw),
+                                                compiler.process(rank, **kw))
+
+
+@compiles(IsBelowReverseDistance, 'sqlite') # type: ignore[no-untyped-call, misc]
+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))
+
+
+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]
+                         table.c.housenumber, table.c.name)

 
 

-class CrosscheckNames(sa.sql.functions.GenericFunction[bool]):
+
+@compiles(IsAddressPoint) # type: ignore[no-untyped-call, misc]
+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'))" % (
+                compiler.process(rank, **kw),
+                compiler.process(hnr, **kw),
+                compiler.process(name, **kw))
+
+
+@compiles(IsAddressPoint, 'sqlite') # type: ignore[no-untyped-call, misc]
+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)" % (
+                compiler.process(rank, **kw),
+                compiler.process(hnr, **kw),
+                compiler.process(name, **kw))
+
+
+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.
     """
     """ 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]
     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)" % (
                              compiler: 'sa.Compiled', **kw: Any) -> str:
     arg1, arg2 = list(element.clauses)
     return "coalesce(avals(%s) && ARRAY(SELECT * FROM json_array_elements_text(%s)), false)" % (


@@ -58,7 +162,7 @@ def compile_crosscheck_names(element: SaColumn,
 
 
 @compiles(CrosscheckNames, 'sqlite') # type: ignore[no-untyped-call, misc]
 
 
 @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 *"\
                                     compiler: 'sa.Compiled', **kw: Any) -> str:
     arg1, arg2 = list(element.clauses)
     return "EXISTS(SELECT *"\


@@ -75,15 +179,16 @@ class JsonArrayEach(sa.sql.functions.GenericFunction[Any]):
 
 
 @compiles(JsonArrayEach) # type: ignore[no-untyped-call, misc]
 
 
 @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]
     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)
 
 
     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.
     """
 class Greatest(sa.sql.functions.GenericFunction[Any]):
     """ Function to compute maximum of all its input parameters.
     """


@@ -92,5 +197,25 @@ class Greatest(sa.sql.functions.GenericFunction[Any]):
 
 
 @compiles(Greatest, 'sqlite') # type: ignore[no-untyped-call, misc]
 
 
 @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)
     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))