lift restrictions on search with frequent terms slightly

[nominatim.git] / test / python / tokenizer / test_legacy.py

diff --git a/test/python/tokenizer/test_legacy.py b/test/python/tokenizer/test_legacy.py
index 8f79e2422b74c46f7634462e797092dd40a1bfac..bf208c92dc8684eb346f8b1f129614978494f1a3 100644 (file)
--- a/test/python/tokenizer/test_legacy.py
+++ b/test/python/tokenizer/test_legacy.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) 2022 by the Nominatim developer community.
+# Copyright (C) 2024 by the Nominatim developer community.

 # For a full list of authors see the git log.
 """
 Test for legacy tokenizer.
 # For a full list of authors see the git log.
 """
 Test for legacy tokenizer.


@@ -12,10 +12,10 @@ import re
 
 import pytest
 
 
 import pytest
 

-from nominatim.indexer.place_info import PlaceInfo
-from nominatim.tokenizer import legacy_tokenizer
-from nominatim.db import properties
-from nominatim.errors import UsageError
+from nominatim_db.data.place_info import PlaceInfo
+from nominatim_db.tokenizer import legacy_tokenizer
+from nominatim_db.db import properties
+from nominatim_db.errors import UsageError

 
 from mock_legacy_word_table import MockLegacyWordTable
 
 
 from mock_legacy_word_table import MockLegacyWordTable
 


@@ -238,19 +238,19 @@ def test_check_database_bad_setup(test_config, tokenizer_factory, monkeypatch,
     assert tok.check_database(False) is not None
 
 
     assert tok.check_database(False) is not None
 
 

-def test_update_statistics_reverse_only(word_table, tokenizer_factory):
+def test_update_statistics_reverse_only(word_table, tokenizer_factory, test_config):

     tok = tokenizer_factory()
     tok = tokenizer_factory()

-    tok.update_statistics()
+    tok.update_statistics(test_config)

 
 
 
 

-def test_update_statistics(word_table, table_factory, temp_db_cursor, tokenizer_factory):
+def test_update_statistics(word_table, table_factory, temp_db_cursor, tokenizer_factory, test_config):

     word_table.add_full_word(1000, 'hello')
     table_factory('search_name',
                   'place_id BIGINT, name_vector INT[]',
                   [(12, [1000])])
     tok = tokenizer_factory()
 
     word_table.add_full_word(1000, 'hello')
     table_factory('search_name',
                   'place_id BIGINT, name_vector INT[]',
                   [(12, [1000])])
     tok = tokenizer_factory()
 

-    tok.update_statistics()
+    tok.update_statistics(test_config)

 
     assert temp_db_cursor.scalar("""SELECT count(*) FROM word
                                     WHERE word_token like ' %' and
 
     assert temp_db_cursor.scalar("""SELECT count(*) FROM word
                                     WHERE word_token like ' %' and


@@ -549,7 +549,7 @@ class TestPlaceAddress:
     def test_process_place_street_empty(self):
         info = self.process_address(street='🜵')
 
     def test_process_place_street_empty(self):
         info = self.process_address(street='🜵')
 

-        assert 'street' not in info
+        assert info['street'] == '{}'

 
 
     def test_process_place_place(self):
 
 
     def test_process_place_place(self):