Merge pull request #3292 from lonvia/faster-country-search

[nominatim.git] / nominatim / api / core.py

diff --git a/nominatim/api/core.py b/nominatim/api/core.py
index fb03d2df6ddd00bdb8ece0b24328a22c348ab2d5..3481e647399b31cdd6c72201d34970b7a558fe17 100644 (file)
--- a/nominatim/api/core.py
+++ b/nominatim/api/core.py
@@ -19,6 +19,7 @@ import sqlalchemy.ext.asyncio as sa_asyncio
 from nominatim.errors import UsageError
 from nominatim.db.sqlalchemy_schema import SearchTables
 from nominatim.db.async_core_library import PGCORE_LIB, PGCORE_ERROR
 from nominatim.errors import UsageError
 from nominatim.db.sqlalchemy_schema import SearchTables
 from nominatim.db.async_core_library import PGCORE_LIB, PGCORE_ERROR

+import nominatim.db.sqlite_functions

 from nominatim.config import Configuration
 from nominatim.api.connection import SearchConnection
 from nominatim.api.status import get_status, StatusResult
 from nominatim.config import Configuration
 from nominatim.api.connection import SearchConnection
 from nominatim.api.status import get_status, StatusResult


@@ -29,7 +30,7 @@ import nominatim.api.types as ntyp
 from nominatim.api.results import DetailedResult, ReverseResult, SearchResults
 
 
 from nominatim.api.results import DetailedResult, ReverseResult, SearchResults
 
 

-class NominatimAPIAsync:
+class NominatimAPIAsync: #pylint: disable=too-many-instance-attributes

     """ The main frontend to the Nominatim database implements the
         functions for lookup, forward and reverse geocoding using
         asynchronous functions.
     """ The main frontend to the Nominatim database implements the
         functions for lookup, forward and reverse geocoding using
         asynchronous functions.


@@ -58,6 +59,7 @@ class NominatimAPIAsync:
         self.config = Configuration(project_dir, environ)
         self.query_timeout = self.config.get_int('QUERY_TIMEOUT') \
                              if self.config.QUERY_TIMEOUT else None
         self.config = Configuration(project_dir, environ)
         self.query_timeout = self.config.get_int('QUERY_TIMEOUT') \
                              if self.config.QUERY_TIMEOUT else None

+        self.reverse_restrict_to_country_area = self.config.get_bool('SEARCH_WITHIN_COUNTRIES')

         self.server_version = 0
 
         if sys.version_info >= (3, 10):
         self.server_version = 0
 
         if sys.version_info >= (3, 10):


@@ -80,41 +82,78 @@ class NominatimAPIAsync:
             if self._engine:
                 return
 
             if self._engine:
                 return
 

-            dsn = self.config.get_database_params()
-            pool_size = self.config.get_int('API_POOL_SIZE')
-
-            query = {k: v for k, v in dsn.items()
-                      if k not in ('user', 'password', 'dbname', 'host', 'port')}
-
-            dburl = sa.engine.URL.create(
-                       f'postgresql+{PGCORE_LIB}',
-                       database=dsn.get('dbname'),
-                       username=dsn.get('user'), password=dsn.get('password'),
-                       host=dsn.get('host'), port=int(dsn['port']) if 'port' in dsn else None,
-                       query=query)
-            engine = sa_asyncio.create_async_engine(dburl, future=True,
-                                                    max_overflow=0, pool_size=pool_size,
-                                                    echo=self.config.get_bool('DEBUG_SQL'))
-
-            try:
-                async with engine.begin() as conn:
-                    result = await conn.scalar(sa.text('SHOW server_version_num'))
-                    server_version = int(result)
-            except (PGCORE_ERROR, sa.exc.OperationalError):
+            extra_args: Dict[str, Any] = {'future': True,
+                                          'echo': self.config.get_bool('DEBUG_SQL')}
+
+            if self.config.get_int('API_POOL_SIZE') == 0:
+                extra_args['poolclass'] = sa.pool.NullPool
+            else:
+                extra_args['poolclass'] = sa.pool.AsyncAdaptedQueuePool
+                extra_args['max_overflow'] = 0
+                extra_args['pool_size'] = self.config.get_int('API_POOL_SIZE')
+
+
+            is_sqlite = self.config.DATABASE_DSN.startswith('sqlite:')
+
+            if is_sqlite:
+                params = dict((p.split('=', 1)
+                              for p in self.config.DATABASE_DSN[7:].split(';')))
+                dburl = sa.engine.URL.create('sqlite+aiosqlite',
+                                             database=params.get('dbname'))
+
+                if not ('NOMINATIM_DATABASE_RW' in self.config.environ
+                        and self.config.get_bool('DATABASE_RW')) \
+                   and not Path(params.get('dbname', '')).is_file():
+                    raise UsageError(f"SQlite database '{params.get('dbname')}' does not exist.")
+            else:
+                dsn = self.config.get_database_params()
+                query = {k: v for k, v in dsn.items()
+                         if k not in ('user', 'password', 'dbname', 'host', 'port')}
+
+                dburl = sa.engine.URL.create(
+                           f'postgresql+{PGCORE_LIB}',
+                           database=dsn.get('dbname'),
+                           username=dsn.get('user'),
+                           password=dsn.get('password'),
+                           host=dsn.get('host'),
+                           port=int(dsn['port']) if 'port' in dsn else None,
+                           query=query)
+
+            engine = sa_asyncio.create_async_engine(dburl, **extra_args)
+
+            if is_sqlite:

                 server_version = 0
 
                 server_version = 0
 

-            if server_version >= 110000:

                 @sa.event.listens_for(engine.sync_engine, "connect")
                 @sa.event.listens_for(engine.sync_engine, "connect")

-                def _on_connect(dbapi_con: Any, _: Any) -> None:
+                def _on_sqlite_connect(dbapi_con: Any, _: Any) -> None:
+                    dbapi_con.run_async(lambda conn: conn.enable_load_extension(True))
+                    nominatim.db.sqlite_functions.install_custom_functions(dbapi_con)

                     cursor = dbapi_con.cursor()
                     cursor = dbapi_con.cursor()

-                    cursor.execute("SET jit_above_cost TO '-1'")
-                    cursor.execute("SET max_parallel_workers_per_gather TO '0'")
-                # Make sure that all connections get the new settings
-                await self.close()
+                    cursor.execute("SELECT load_extension('mod_spatialite')")
+                    cursor.execute('SELECT SetDecimalPrecision(7)')
+                    dbapi_con.run_async(lambda conn: conn.enable_load_extension(False))
+            else:
+                try:
+                    async with engine.begin() as conn:
+                        result = await conn.scalar(sa.text('SHOW server_version_num'))
+                        server_version = int(result)
+                        if server_version >= 110000:
+                            await conn.execute(sa.text("SET jit_above_cost TO '-1'"))
+                            await conn.execute(sa.text(
+                                    "SET max_parallel_workers_per_gather TO '0'"))
+                except (PGCORE_ERROR, sa.exc.OperationalError):
+                    server_version = 0
+
+                if server_version >= 110000:
+                    @sa.event.listens_for(engine.sync_engine, "connect")
+                    def _on_connect(dbapi_con: Any, _: Any) -> None:
+                        cursor = dbapi_con.cursor()
+                        cursor.execute("SET jit_above_cost TO '-1'")
+                        cursor.execute("SET max_parallel_workers_per_gather TO '0'")

 
             self._property_cache['DB:server_version'] = server_version
 
 
             self._property_cache['DB:server_version'] = server_version
 

-            self._tables = SearchTables(sa.MetaData(), engine.name) # pylint: disable=no-member
+            self._tables = SearchTables(sa.MetaData()) # pylint: disable=no-member

             self._engine = engine
 
 
             self._engine = engine
 
 


@@ -201,7 +240,8 @@ class NominatimAPIAsync:
             conn.set_query_timeout(self.query_timeout)
             if details.keywords:
                 await make_query_analyzer(conn)
             conn.set_query_timeout(self.query_timeout)
             if details.keywords:
                 await make_query_analyzer(conn)

-            geocoder = ReverseGeocoder(conn, details)
+            geocoder = ReverseGeocoder(conn, details,
+                                       self.reverse_restrict_to_country_area)

             return await geocoder.lookup(coord)
 
 
             return await geocoder.lookup(coord)
 
 


@@ -373,7 +413,8 @@ class NominatimAPI:
             or `None` if the place could not be found in the database.
 
             Parameters:
             or `None` if the place could not be found in the database.
 
             Parameters:

-              place: Description of the place to look up. See PlaceRef below
+              place: Description of the place to look up. See
+                     [Place identification](Input-Parameter-Types.md#place-identification)

                      for the various ways to reference a place.
 
             Other parameters:
                      for the various ways to reference a place.
 
             Other parameters:


@@ -455,7 +496,8 @@ class NominatimAPI:
             Each result is a dataclass with the fields detailed below.
 
             Parameters:
             Each result is a dataclass with the fields detailed below.
 
             Parameters:

-              places: List of descriptions of the place to look up. See PlaceRef below
+              places: List of descriptions of the place to look up. See
+                      [Place identification](Input-Parameter-Types.md#place-identification)

                       for the various ways to reference a place.
 
             Other parameters:
                       for the various ways to reference a place.
 
             Other parameters:


@@ -615,10 +657,15 @@ class NominatimAPI:
             Other parameters:
               max_results (int): Maximum number of results to return. The
                 actual number of results may be less. (Default: 10)
             Other parameters:
               max_results (int): Maximum number of results to return. The
                 actual number of results may be less. (Default: 10)

-              min_rank (int): Lowest [address rank](../customize/Ranking.md#address-rank) to return.
-              max_rank (int): Highest address rank to return.
+              min_rank (int): Lowest permissible rank for the result.
+                For addressable places this is the minimum
+                [address rank](../customize/Ranking.md#address-rank). For all
+                other places the [search rank](../customize/Ranking.md#search-rank)
+                is used.
+              max_rank (int): Highest permissible rank for the result. See min_rank above.

               layers (enum): Defines the kind of data to take into account.
               layers (enum): Defines the kind of data to take into account.

-                See description of layers below. (Default: addresses and POIs)
+                See [layers section](Input-Parameter-Types.md#layers) for details.
+                (Default: addresses and POIs)

               countries (list[str]): Restrict search to countries with the given
                 ISO 3166-1 alpha-2 country code. An empty list (the default)
                 disables this filter.
               countries (list[str]): Restrict search to countries with the given
                 ISO 3166-1 alpha-2 country code. An empty list (the default)
                 disables this filter.


@@ -727,10 +774,15 @@ class NominatimAPI:
             Other parameters:
               max_results (int): Maximum number of results to return. The
                 actual number of results may be less. (Default: 10)
             Other parameters:
               max_results (int): Maximum number of results to return. The
                 actual number of results may be less. (Default: 10)

-              min_rank (int): Lowest [address rank](../customize/Ranking.md#address-rank) to return.
-              max_rank (int): Highest address rank to return.
+              min_rank (int): Lowest permissible rank for the result.
+                For addressable places this is the minimum
+                [address rank](../customize/Ranking.md#address-rank). For all
+                other places the [search rank](../customize/Ranking.md#search-rank)
+                is used.
+              max_rank (int): Highest permissible rank for the result. See min_rank above.

               layers (enum): Defines the kind of data to take into account.
               layers (enum): Defines the kind of data to take into account.

-                See description of layers below. (Default: addresses and POIs)
+                See [layers section](Input-Parameter-Types.md#layers) for details.
+                (Default: addresses and POIs)

               countries (list[str]): Restrict search to countries with the given
                 ISO 3166-1 alpha-2 country code. An empty list (the default)
                 disables this filter. Do not use, when the country parameter
               countries (list[str]): Restrict search to countries with the given
                 ISO 3166-1 alpha-2 country code. An empty list (the default)
                 disables this filter. Do not use, when the country parameter


@@ -834,10 +886,15 @@ class NominatimAPI:
             Other parameters:
               max_results (int): Maximum number of results to return. The
                 actual number of results may be less. (Default: 10)
             Other parameters:
               max_results (int): Maximum number of results to return. The
                 actual number of results may be less. (Default: 10)

-              min_rank (int): Lowest [address rank](../customize/Ranking.md#address-rank) to return.
-              max_rank (int): Highest address rank to return.
+              min_rank (int): Lowest permissible rank for the result.
+                For addressable places this is the minimum
+                [address rank](../customize/Ranking.md#address-rank). For all
+                other places the [search rank](../customize/Ranking.md#search-rank)
+                is used.
+              max_rank (int): Highest permissible rank for the result. See min_rank above.

               layers (enum): Defines the kind of data to take into account.
               layers (enum): Defines the kind of data to take into account.

-                See description of layers below. (Default: addresses and POIs)
+                See [layers section](Input-Parameter-Types.md#layers) for details.
+                (Default: addresses and POIs)

               countries (list[str]): Restrict search to countries with the given
                 ISO 3166-1 alpha-2 country code. An empty list (the default)
                 disables this filter.
               countries (list[str]): Restrict search to countries with the given
                 ISO 3166-1 alpha-2 country code. An empty list (the default)
                 disables this filter.