X-Git-Url: https://git.openstreetmap.org./nominatim.git/blobdiff_plain/16daa57e4757e4daeffec1e61630f989727dc563..7cfcbacfc75ab2e39ee7eab6a5cf40e8cbd152f5:/test/python/test_tokenizer_icu.py diff --git a/test/python/test_tokenizer_icu.py b/test/python/test_tokenizer_icu.py index 4b7c56d5..52cca6a7 100644 --- a/test/python/test_tokenizer_icu.py +++ b/test/python/test_tokenizer_icu.py @@ -67,10 +67,13 @@ def analyzer(tokenizer_factory, test_config, monkeypatch, monkeypatch.undo() def _mk_analyser(norm=("[[:Punctuation:][:Space:]]+ > ' '",), trans=(':: upper()',), - variants=('~gasse -> gasse', 'street => st', )): - cfgstr = {'normalization' : list(norm), - 'transliteration' : list(trans), - 'variants' : [ {'words': list(variants)}]} + variants=('~gasse -> gasse', 'street => st', ), + sanitizers=[]): + cfgstr = {'normalization': list(norm), + 'sanitizers': sanitizers, + 'transliteration': list(trans), + 'token-analysis': [{'analyzer': 'generic', + 'variants': [{'words': list(variants)}]}]} (test_config.project_dir / 'icu_tokenizer.yaml').write_text(yaml.dump(cfgstr)) tok.loader = ICURuleLoader(test_config) @@ -309,14 +312,15 @@ class TestPlaceNames: @pytest.fixture(autouse=True) def setup(self, analyzer, sql_functions): - with analyzer() as anl: + sanitizers = [{'step': 'split-name-list'}, + {'step': 'strip-brace-terms'}] + with analyzer(sanitizers=sanitizers) as anl: self.analyzer = anl yield anl def expect_name_terms(self, info, *expected_terms): tokens = self.analyzer.get_word_token_info(expected_terms) - print (tokens) for token in tokens: assert token[2] is not None, "No token for {0}".format(token) @@ -324,9 +328,7 @@ class TestPlaceNames: def process_named_place(self, names): - place = {'name': names} - - return self.analyzer.process_place(PlaceInfo(place)) + return self.analyzer.process_place(PlaceInfo({'name': names})) def test_simple_names(self):