reintroduce cutoffs when searching for very frequent words

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

diff --git a/nominatim/db/sqlalchemy_schema.py b/nominatim/db/sqlalchemy_schema.py
index 7dd1e0ce0b046182b6224eab7b5ec16769719b96..0ec22b7e1fa322469a2ea75d38642c3b75f02aa8 100644 (file)
--- a/nominatim/db/sqlalchemy_schema.py
+++ b/nominatim/db/sqlalchemy_schema.py
@@ -7,37 +7,10 @@
 """
 SQLAlchemy definitions for all tables used by the frontend.
 """
-from typing import Any
-
 import sqlalchemy as sa
-from sqlalchemy.dialects.postgresql import HSTORE, ARRAY, JSONB, array
-from sqlalchemy.dialects.sqlite import JSON as sqlite_json
 
 import nominatim.db.sqlalchemy_functions #pylint: disable=unused-import
-from nominatim.db.sqlalchemy_types import Geometry
-
-class PostgresTypes:
-    """ Type definitions for complex types as used in Postgres variants.
-    """
-    Composite = HSTORE
-    Json = JSONB
-    IntArray = ARRAY(sa.Integer()) #pylint: disable=invalid-name
-    to_array = array
-
-
-class SqliteTypes:
-    """ Type definitions for complex types as used in Postgres variants.
-    """
-    Composite = sqlite_json
-    Json = sqlite_json
-    IntArray = sqlite_json
-
-    @staticmethod
-    def to_array(arr: Any) -> Any:
-        """ Sqlite has no special conversion for arrays.
-        """
-        return arr
-
+from nominatim.db.sqlalchemy_types import Geometry, KeyValueStore, IntArray
 
 #pylint: disable=too-many-instance-attributes
 class SearchTables:
@@ -47,14 +20,7 @@ class SearchTables:
         Any data used for updates only will not be visible.
     """
 
-    def __init__(self, meta: sa.MetaData, engine_name: str) -> None:
-        if engine_name == 'postgresql':
-            self.types: Any = PostgresTypes
-        elif engine_name == 'sqlite':
-            self.types = SqliteTypes
-        else:
-            raise ValueError("Only 'postgresql' and 'sqlite' engines are supported.")
-
+    def __init__(self, meta: sa.MetaData) -> None:
         self.meta = meta
 
         self.import_status = sa.Table('import_status', meta,
@@ -80,9 +46,9 @@ class SearchTables:
             sa.Column('class', sa.Text, nullable=False, key='class_'),
             sa.Column('type', sa.Text, nullable=False),
             sa.Column('admin_level', sa.SmallInteger),
-            sa.Column('name', self.types.Composite),
-            sa.Column('address', self.types.Composite),
-            sa.Column('extratags', self.types.Composite),
+            sa.Column('name', KeyValueStore),
+            sa.Column('address', KeyValueStore),
+            sa.Column('extratags', KeyValueStore),
             sa.Column('geometry', Geometry, nullable=False),
             sa.Column('wikipedia', sa.Text),
             sa.Column('country_code', sa.String(2)),
@@ -118,14 +84,14 @@ class SearchTables:
             sa.Column('step', sa.SmallInteger),
             sa.Column('indexed_status', sa.SmallInteger),
             sa.Column('linegeo', Geometry),
-            sa.Column('address', self.types.Composite),
+            sa.Column('address', KeyValueStore),
             sa.Column('postcode', sa.Text),
             sa.Column('country_code', sa.String(2)))
 
         self.country_name = sa.Table('country_name', meta,
             sa.Column('country_code', sa.String(2)),
-            sa.Column('name', self.types.Composite),
-            sa.Column('derived_name', self.types.Composite),
+            sa.Column('name', KeyValueStore),
+            sa.Column('derived_name', KeyValueStore),
             sa.Column('partition', sa.Integer))
 
         self.country_grid = sa.Table('country_osm_grid', meta,
@@ -139,8 +105,8 @@ class SearchTables:
             sa.Column('importance', sa.Float),
             sa.Column('search_rank', sa.SmallInteger),
             sa.Column('address_rank', sa.SmallInteger),
-            sa.Column('name_vector', self.types.IntArray),
-            sa.Column('nameaddress_vector', self.types.IntArray),
+            sa.Column('name_vector', IntArray),
+            sa.Column('nameaddress_vector', IntArray),
             sa.Column('country_code', sa.String(2)),
             sa.Column('centroid', Geometry))