Merge pull request #3665 from lonvia/pattern-matching-postcodes

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

diff --git a/test/python/tokenizer/test_icu.py b/test/python/tokenizer/test_icu.py
index 2a4865db2acb95e4e177c5732441ef1f7dc610a0..06a3cd6ce7b81a3697c3d2006089e0f79126ae35 100644 (file)
--- a/test/python/tokenizer/test_icu.py
+++ b/test/python/tokenizer/test_icu.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)
 #
-# 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.
 """
 Tests for ICU tokenizer.
@@ -12,11 +12,11 @@ import itertools
 
 import pytest
 
-from nominatim.tokenizer import icu_tokenizer
-import nominatim.tokenizer.icu_rule_loader
-from nominatim.db import properties
-from nominatim.db.sql_preprocessor import SQLPreprocessor
-from nominatim.data.place_info import PlaceInfo
+from nominatim_db.tokenizer import icu_tokenizer
+import nominatim_db.tokenizer.icu_rule_loader
+from nominatim_db.db import properties
+from nominatim_db.db.sql_preprocessor import SQLPreprocessor
+from nominatim_db.data.place_info import PlaceInfo
 
 from mock_icu_word_table import MockIcuWordTable
 
@@ -83,7 +83,7 @@ def analyzer(tokenizer_factory, test_config, monkeypatch,
             cfgstr['token-analysis'].append({'id': '@postcode',
                                              'analyzer': 'postcodes'})
         (test_config.project_dir / 'icu_tokenizer.yaml').write_text(yaml.dump(cfgstr))
-        tok.loader = nominatim.tokenizer.icu_rule_loader.ICURuleLoader(test_config)
+        tok.loader = nominatim_db.tokenizer.icu_rule_loader.ICURuleLoader(test_config)
 
         return tok.name_analyzer()
 
@@ -157,7 +157,7 @@ def test_init_new(tokenizer_factory, test_config, db_prop):
     tok = tokenizer_factory()
     tok.init_new_db(test_config)
 
-    assert db_prop(nominatim.tokenizer.icu_rule_loader.DBCFG_IMPORT_NORM_RULES) \
+    assert db_prop(nominatim_db.tokenizer.icu_rule_loader.DBCFG_IMPORT_NORM_RULES) \
             .startswith(':: lower ();')
 
 
@@ -199,16 +199,16 @@ def test_update_sql_functions(db_prop, temp_db_cursor,
     assert test_content == set((('1133', ), ))
 
 
-def test_finalize_import(tokenizer_factory, temp_db_conn,
-                         temp_db_cursor, test_config, sql_preprocessor_cfg):
+def test_finalize_import(tokenizer_factory, temp_db_cursor,
+                         test_config, sql_preprocessor_cfg):
     tok = tokenizer_factory()
     tok.init_new_db(test_config)
 
-    assert not temp_db_conn.index_exists('idx_word_word_id')
+    assert not temp_db_cursor.index_exists('word', 'idx_word_word_id')
 
     tok.finalize_import(test_config)
 
-    assert temp_db_conn.index_exists('idx_word_word_id')
+    assert temp_db_cursor.index_exists('word', 'idx_word_word_id')
 
 
 def test_check_database(test_config, tokenizer_factory,
@@ -265,37 +265,13 @@ class TestPostcodes:
                                                       'address': {'postcode': postcode}}))
 
 
-    def test_update_postcodes_from_db_empty(self, table_factory, word_table):
-        table_factory('location_postcode', 'country_code TEXT, postcode TEXT',
-                      content=(('de', '12345'), ('se', '132 34'),
-                               ('bm', 'AB23'), ('fr', '12345')))
-
-        self.analyzer.update_postcodes_from_db()
-
-        assert word_table.count() == 5
-        assert word_table.get_postcodes() == {'12345', '132 34@132 34', 'AB 23@AB 23'}
-
-
-    def test_update_postcodes_from_db_ambigious(self, table_factory, word_table):
-        table_factory('location_postcode', 'country_code TEXT, postcode TEXT',
-                      content=(('in', '123456'), ('sg', '123456')))
-
-        self.analyzer.update_postcodes_from_db()
-
-        assert word_table.count() == 3
-        assert word_table.get_postcodes() == {'123456', '123456@123 456'}
-
-
-    def test_update_postcodes_from_db_add_and_remove(self, table_factory, word_table):
-        table_factory('location_postcode', 'country_code TEXT, postcode TEXT',
-                      content=(('ch', '1234'), ('bm', 'BC 45'), ('bm', 'XX45')))
+    def test_update_postcodes_deleted(self, word_table):
         word_table.add_postcode(' 1234', '1234')
         word_table.add_postcode(' 5678', '5678')
 
         self.analyzer.update_postcodes_from_db()
 
-        assert word_table.count() == 5
-        assert word_table.get_postcodes() == {'1234', 'BC 45@BC 45', 'XX 45@XX 45'}
+        assert word_table.count() == 0
 
 
     def test_process_place_postcode_simple(self, word_table):
@@ -303,16 +279,12 @@ class TestPostcodes:
 
         assert info['postcode'] == '12345'
 
-        assert word_table.get_postcodes() == {'12345', }
-
 
     def test_process_place_postcode_with_space(self, word_table):
         info = self.process_postcode('in', '123 567')
 
         assert info['postcode'] == '123567'
 
-        assert word_table.get_postcodes() == {'123567@123 567', }
-
 
 
 def test_update_special_phrase_empty_table(analyzer, word_table):
@@ -477,9 +449,9 @@ class TestPlaceAddress:
 
     @pytest.mark.parametrize('pcode', ['12345', 'AB 123', '34-345'])
     def test_process_place_postcode(self, word_table, pcode):
-        self.process_address(postcode=pcode)
+        info = self.process_address(postcode=pcode)
 
-        assert word_table.get_postcodes() == {pcode, }
+        assert info['postcode'] == pcode
 
 
     @pytest.mark.parametrize('hnr', ['123a', '1', '101'])