indexing: precompute row counts

[nominatim.git] / test / python / api / conftest.py

diff --git a/test/python/api/conftest.py b/test/python/api/conftest.py
index cfe14e1eddc85797cabaf08672e2ccdf1d63c1c5..a902e2640a7996a5cedbbd3765cb25f593e0f3a3 100644 (file)
--- a/test/python/api/conftest.py
+++ b/test/python/api/conftest.py
@@ -1,8 +1,8 @@
-# SPDX-License-Identifier: GPL-2.0-only
+# SPDX-License-Identifier: GPL-3.0-or-later

 #
 # This file is part of Nominatim. (https://nominatim.org)
 #
 #
 # This file is part of Nominatim. (https://nominatim.org)
 #

-# Copyright (C) 2023 by the Nominatim developer community.
+# Copyright (C) 2024 by the Nominatim developer community.

 # For a full list of authors see the git log.
 """
 Helper fixtures for API call tests.
 # For a full list of authors see the git log.
 """
 Helper fixtures for API call tests.


@@ -14,9 +14,11 @@ import datetime as dt
 
 import sqlalchemy as sa
 
 
 import sqlalchemy as sa
 

-import nominatim.api as napi
-from nominatim.db.sql_preprocessor import SQLPreprocessor
-import nominatim.api.logging as loglib
+import nominatim_api as napi
+from nominatim_db.db.sql_preprocessor import SQLPreprocessor
+from nominatim_api.search.query_analyzer_factory import make_query_analyzer
+from nominatim_db.tools import convert_sqlite
+import nominatim_api.logging as loglib

 
 class APITester:
 
 
 class APITester:
 


@@ -66,11 +68,11 @@ class APITester:
                       'rank_search': kw.get('rank_search', 30),
                       'rank_address': kw.get('rank_address', 30),
                       'importance': kw.get('importance'),
                       'rank_search': kw.get('rank_search', 30),
                       'rank_address': kw.get('rank_address', 30),
                       'importance': kw.get('importance'),

-                      'centroid': 'SRID=4326;POINT(%f %f)' % centroid,
+                      'centroid': 'POINT(%f %f)' % centroid,

                       'indexed_status': kw.get('indexed_status', 0),
                       'indexed_date': kw.get('indexed_date',
                                              dt.datetime(2022, 12, 7, 14, 14, 46, 0)),
                       'indexed_status': kw.get('indexed_status', 0),
                       'indexed_date': kw.get('indexed_date',
                                              dt.datetime(2022, 12, 7, 14, 14, 46, 0)),

-                      'geometry': 'SRID=4326;' + geometry})
+                      'geometry': geometry})

 
 
     def add_address_placex(self, object_id, **kw):
 
 
     def add_address_placex(self, object_id, **kw):


@@ -97,7 +99,7 @@ class APITester:
                       'address': kw.get('address'),
                       'postcode': kw.get('postcode'),
                       'country_code': kw.get('country_code'),
                       'address': kw.get('address'),
                       'postcode': kw.get('postcode'),
                       'country_code': kw.get('country_code'),

-                      'linegeo': 'SRID=4326;' + kw.get('geometry', 'LINESTRING(1.1 -0.2, 1.09 -0.22)')})
+                      'linegeo': kw.get('geometry', 'LINESTRING(1.1 -0.2, 1.09 -0.22)')})

 
 
     def add_tiger(self, **kw):
 
 
     def add_tiger(self, **kw):


@@ -108,7 +110,7 @@ class APITester:
                       'endnumber': kw.get('endnumber', 6),
                       'step': kw.get('step', 2),
                       'postcode': kw.get('postcode'),
                       'endnumber': kw.get('endnumber', 6),
                       'step': kw.get('step', 2),
                       'postcode': kw.get('postcode'),

-                      'linegeo': 'SRID=4326;' + kw.get('geometry', 'LINESTRING(1.1 -0.2, 1.09 -0.22)')})
+                      'linegeo': kw.get('geometry', 'LINESTRING(1.1 -0.2, 1.09 -0.22)')})

 
 
     def add_postcode(self, **kw):
 
 
     def add_postcode(self, **kw):


@@ -121,14 +123,14 @@ class APITester:
                       'rank_address': kw.get('rank_address', 22),
                       'indexed_date': kw.get('indexed_date',
                                              dt.datetime(2022, 12, 7, 14, 14, 46, 0)),
                       'rank_address': kw.get('rank_address', 22),
                       'indexed_date': kw.get('indexed_date',
                                              dt.datetime(2022, 12, 7, 14, 14, 46, 0)),

-                      'geometry': 'SRID=4326;' + kw.get('geometry', 'POINT(23 34)')})
+                      'geometry': kw.get('geometry', 'POINT(23 34)')})

 
 
     def add_country(self, country_code, geometry):
         self.add_data('country_grid',
                       {'country_code': country_code,
                        'area': 0.1,
 
 
     def add_country(self, country_code, geometry):
         self.add_data('country_grid',
                       {'country_code': country_code,
                        'area': 0.1,

-                       'geometry': 'SRID=4326;' + geometry})
+                       'geometry': geometry})

 
 
     def add_country_name(self, country_code, names, partition=0):
 
 
     def add_country_name(self, country_code, names, partition=0):


@@ -148,7 +150,7 @@ class APITester:
                        'name_vector': kw.get('names', []),
                        'nameaddress_vector': kw.get('address', []),
                        'country_code': kw.get('country_code', 'xx'),
                        'name_vector': kw.get('names', []),
                        'nameaddress_vector': kw.get('address', []),
                        'country_code': kw.get('country_code', 'xx'),

-                       'centroid': 'SRID=4326;POINT(%f %f)' % centroid})
+                       'centroid': 'POINT(%f %f)' % centroid})

 
 
     def add_class_type_table(self, cls, typ):
 
 
     def add_class_type_table(self, cls, typ):


@@ -159,6 +161,22 @@ class APITester:
                                      """)))
 
 
                                      """)))
 
 

+    def add_word_table(self, content):
+        data = [dict(zip(['word_id', 'word_token', 'type', 'word', 'info'], c))
+                for c in content]
+
+        async def _do_sql():
+            async with self.api._async_api.begin() as conn:
+                if 'word' not in conn.t.meta.tables:
+                    await make_query_analyzer(conn)
+                    word_table = conn.t.meta.tables['word']
+                    await conn.connection.run_sync(word_table.create)
+                if data:
+                    await conn.execute(conn.t.meta.tables['word'].insert(), data)
+
+        self.async_to_sync(_do_sql())
+
+

     async def exec_async(self, sql, *args, **kwargs):
         async with self.api._async_api.begin() as conn:
             return await conn.execute(sql, *args, **kwargs)
     async def exec_async(self, sql, *args, **kwargs):
         async with self.api._async_api.begin() as conn:
             return await conn.execute(sql, *args, **kwargs)


@@ -178,7 +196,6 @@ def apiobj(temp_db_with_extensions, temp_db_conn, monkeypatch):
     testapi.async_to_sync(testapi.create_tables())
 
     proc = SQLPreprocessor(temp_db_conn, testapi.api.config)
     testapi.async_to_sync(testapi.create_tables())
 
     proc = SQLPreprocessor(temp_db_conn, testapi.api.config)

-    proc.run_sql_file(temp_db_conn, 'functions/address_lookup.sql')

     proc.run_sql_file(temp_db_conn, 'functions/ranking.sql')
 
     loglib.set_log_output('text')
     proc.run_sql_file(temp_db_conn, 'functions/ranking.sql')
 
     loglib.set_log_output('text')


@@ -186,3 +203,44 @@ def apiobj(temp_db_with_extensions, temp_db_conn, monkeypatch):
     print(loglib.get_and_disable())
 
     testapi.api.close()
     print(loglib.get_and_disable())
 
     testapi.api.close()

+
+
+@pytest.fixture(params=['postgres_db', 'sqlite_db'])
+def frontend(request, event_loop, tmp_path):
+    testapis = []
+    if request.param == 'sqlite_db':
+        db = str(tmp_path / 'test_nominatim_python_unittest.sqlite')
+
+        def mkapi(apiobj, options={'reverse'}):
+            apiobj.add_data('properties',
+                        [{'property': 'tokenizer', 'value': 'icu'},
+                         {'property': 'tokenizer_import_normalisation', 'value': ':: lower();'},
+                         {'property': 'tokenizer_import_transliteration', 'value': "'1' > '/1/'; 'ä' > 'ä '"},
+                        ])
+
+            async def _do_sql():
+                async with apiobj.api._async_api.begin() as conn:
+                    if 'word' in conn.t.meta.tables:
+                        return
+                    await make_query_analyzer(conn)
+                    word_table = conn.t.meta.tables['word']
+                    await conn.connection.run_sync(word_table.create)
+
+            apiobj.async_to_sync(_do_sql())
+
+            event_loop.run_until_complete(convert_sqlite.convert(Path('/invalid'),
+                                                                 db, options))
+            outapi = napi.NominatimAPI(Path('/invalid'),
+                                       {'NOMINATIM_DATABASE_DSN': f"sqlite:dbname={db}",
+                                        'NOMINATIM_USE_US_TIGER_DATA': 'yes'})
+            testapis.append(outapi)
+
+            return outapi
+    elif request.param == 'postgres_db':
+        def mkapi(apiobj, options=None):
+            return apiobj.api
+
+    yield mkapi
+
+    for api in testapis:
+        api.close()