+
+
+def test_update_sql_functions(sql_preprocessor, temp_db_conn,
+ tokenizer_factory, test_config, table_factory,
+ monkeypatch, temp_db_cursor):
+ monkeypatch.setenv('NOMINATIM_MAX_WORD_FREQUENCY', '1133')
+ monkeypatch.setattr(legacy_tokenizer, '_check_module', lambda m, c: None)
+ tok = tokenizer_factory()
+ tok.init_new_db(test_config)
+ monkeypatch.undo()
+
+ assert properties.get_property(temp_db_conn, legacy_tokenizer.DBCFG_MAXWORDFREQ) == '1133'
+
+ table_factory('test', 'txt TEXT')
+
+ func_file = test_config.lib_dir.sql / 'tokenizer' / 'legacy_tokenizer.sql'
+ func_file.write_text("""INSERT INTO test VALUES ('{{max_word_freq}}'),
+ ('{{modulepath}}')""")
+
+ tok.update_sql_functions(test_config)
+
+ test_content = temp_db_cursor.row_set('SELECT * FROM test')
+ assert test_content == set((('1133', ), (str(test_config.project_dir / 'module'), )))
+
+
+def test_migrate_database(tokenizer_factory, test_config, temp_db_conn, monkeypatch):
+ monkeypatch.setattr(legacy_tokenizer, '_check_module', lambda m, c: None)
+ tok = tokenizer_factory()
+ tok.migrate_database(test_config)
+
+ assert properties.get_property(temp_db_conn, legacy_tokenizer.DBCFG_MAXWORDFREQ) is not None
+ assert properties.get_property(temp_db_conn, legacy_tokenizer.DBCFG_NORMALIZATION) is not None
+
+ outfile = test_config.project_dir / 'module' / 'nominatim.so'
+
+ assert outfile.exists()
+ assert outfile.read_text() == 'TEST nomiantim.so'
+ assert outfile.stat().st_mode == 33261
+
+
+def test_normalize(analyzer):
+ assert analyzer.normalize('TEsT') == 'test'
+
+
+def test_update_postcodes_from_db_empty(analyzer, table_factory, word_table,
+ create_postcode_id):
+ table_factory('location_postcode', 'postcode TEXT',
+ content=(('1234',), ('12 34',), ('AB23',), ('1234',)))
+
+ analyzer.update_postcodes_from_db()
+
+ assert word_table.count() == 3
+ assert word_table.get_postcodes() == {'1234', '12 34', 'AB23'}
+
+
+def test_update_postcodes_from_db_add_and_remove(analyzer, table_factory, word_table,
+ create_postcode_id):
+ table_factory('location_postcode', 'postcode TEXT',
+ content=(('1234',), ('45BC', ), ('XX45', )))
+ word_table.add_postcode(' 1234', '1234')
+ word_table.add_postcode(' 5678', '5678')
+
+ analyzer.update_postcodes_from_db()
+
+ assert word_table.count() == 3
+ assert word_table.get_postcodes() == {'1234', '45BC', 'XX45'}
+
+
+def test_update_special_phrase_empty_table(analyzer, word_table, make_standard_name):
+ analyzer.update_special_phrases([
+ ("König bei", "amenity", "royal", "near"),
+ ("Könige", "amenity", "royal", "-"),
+ ("könige", "amenity", "royal", "-"),
+ ("strasse", "highway", "primary", "in")
+ ], True)
+
+ assert word_table.get_special() \
+ == set(((' #könig bei#', 'könig bei', 'amenity', 'royal', 'near'),
+ (' #könige#', 'könige', 'amenity', 'royal', None),
+ (' #strasse#', 'strasse', 'highway', 'primary', 'in')))
+
+
+def test_update_special_phrase_delete_all(analyzer, word_table, make_standard_name):
+ word_table.add_special(' #foo#', 'foo', 'amenity', 'prison', 'in')
+ word_table.add_special(' #bar#', 'bar', 'highway', 'road', None)
+
+ assert word_table.count_special() == 2
+
+ analyzer.update_special_phrases([], True)
+
+ assert word_table.count_special() == 0
+
+
+def test_update_special_phrases_no_replace(analyzer, word_table, make_standard_name):
+ word_table.add_special(' #foo#', 'foo', 'amenity', 'prison', 'in')
+ word_table.add_special(' #bar#', 'bar', 'highway', 'road', None)
+
+ assert word_table.count_special() == 2
+
+ analyzer.update_special_phrases([], False)
+
+ assert word_table.count_special() == 2
+
+
+def test_update_special_phrase_modify(analyzer, word_table, make_standard_name):
+ word_table.add_special(' #foo#', 'foo', 'amenity', 'prison', 'in')
+ word_table.add_special(' #bar#', 'bar', 'highway', 'road', None)
+
+ assert word_table.count_special() == 2
+
+ analyzer.update_special_phrases([
+ ('prison', 'amenity', 'prison', 'in'),
+ ('bar', 'highway', 'road', '-'),
+ ('garden', 'leisure', 'garden', 'near')
+ ], True)
+
+ assert word_table.get_special() \
+ == set(((' #prison#', 'prison', 'amenity', 'prison', 'in'),
+ (' #bar#', 'bar', 'highway', 'road', None),
+ (' #garden#', 'garden', 'leisure', 'garden', 'near')))
+
+
+def test_add_country_names(analyzer, word_table, make_standard_name):
+ analyzer.add_country_names('de', {'name': 'Germany',
+ 'name:de': 'Deutschland',
+ 'short_name': 'germany'})
+
+ assert word_table.get_country() \
+ == {('de', ' #germany#'),
+ ('de', ' #deutschland#')}
+
+
+def test_add_more_country_names(analyzer, word_table, make_standard_name):
+ word_table.add_country('fr', ' #france#')
+ word_table.add_country('it', ' #italy#')
+ word_table.add_country('it', ' #itala#')
+
+ analyzer.add_country_names('it', {'name': 'Italy', 'ref': 'IT'})
+
+ assert word_table.get_country() \
+ == {('fr', ' #france#'),
+ ('it', ' #italy#'),
+ ('it', ' #itala#'),
+ ('it', ' #it#')}
+
+
+def test_process_place_names(analyzer, make_keywords):
+ info = analyzer.process_place(PlaceInfo({'name' : {'name' : 'Soft bAr', 'ref': '34'}}))
+
+ assert info['names'] == '{1,2,3}'
+
+
+@pytest.mark.parametrize('pcode', ['12345', 'AB 123', '34-345'])
+def test_process_place_postcode(analyzer, create_postcode_id, word_table, pcode):
+ analyzer.process_place(PlaceInfo({'address': {'postcode' : pcode}}))
+
+ assert word_table.get_postcodes() == {pcode, }
+
+
+@pytest.mark.parametrize('pcode', ['12:23', 'ab;cd;f', '123;836'])
+def test_process_place_bad_postcode(analyzer, create_postcode_id, word_table, pcode):
+ analyzer.process_place(PlaceInfo({'address': {'postcode' : pcode}}))
+
+ assert not word_table.get_postcodes()
+
+
+class TestHousenumberName:
+
+ @staticmethod
+ @pytest.fixture(autouse=True)
+ def setup_create_housenumbers(temp_db_cursor):
+ temp_db_cursor.execute("""CREATE OR REPLACE FUNCTION create_housenumbers(
+ housenumbers TEXT[],
+ OUT tokens TEXT, OUT normtext TEXT)
+ AS $$
+ SELECT housenumbers::TEXT, array_to_string(housenumbers, ';')
+ $$ LANGUAGE SQL""")
+
+
+ @staticmethod
+ @pytest.mark.parametrize('hnr', ['123a', '1', '101'])
+ def test_process_place_housenumbers_simple(analyzer, hnr):
+ info = analyzer.process_place(PlaceInfo({'address': {'housenumber' : hnr}}))
+
+ assert info['hnr'] == hnr
+ assert info['hnr_tokens'].startswith("{")
+
+
+ @staticmethod
+ def test_process_place_housenumbers_lists(analyzer):
+ info = analyzer.process_place(PlaceInfo({'address': {'conscriptionnumber' : '1; 2;3'}}))
+
+ assert set(info['hnr'].split(';')) == set(('1', '2', '3'))
+
+
+ @staticmethod
+ def test_process_place_housenumbers_duplicates(analyzer):
+ info = analyzer.process_place(PlaceInfo({'address': {'housenumber' : '134',
+ 'conscriptionnumber' : '134',
+ 'streetnumber' : '99a'}}))
+
+ assert set(info['hnr'].split(';')) == set(('134', '99a'))