def test_get_search_rules(cfgrules):
loader = ICURuleLoader(cfgrules())
rules = loader.get_search_rules()
trans = Transliterator.createFromRules("test", rules)
assert trans.transliterate(" Baum straße ") == " baum straße "
assert trans.transliterate(" Baumstraße ") == " baumstraße "
assert trans.transliterate(" Baumstrasse ") == " baumstrasse "
assert trans.transliterate(" Baumstr ") == " baumstr "
assert trans.transliterate(" Baumwegstr ") == " baumwegstr "
assert trans.transliterate(" Αθήνα ") == " athēna "
assert trans.transliterate(" проспект ") == " prospekt "
def test_empty_rule_set(self):
self.write_config("""\
normalization:
transliteration:
token-analysis:
- analyzer: generic
variants:
""")
rules = ICURuleLoader(self.project_env)
assert rules.get_search_rules() == ''
assert rules.get_normalization_rules() == ''
assert rules.get_transliteration_rules() == ''
def test_empty_rule_set(test_config):
(test_config.project_dir / 'icu_tokenizer.yaml').write_text(
dedent("""\
normalization:
transliteration:
token-analysis:
- analyzer: generic
variants:
"""))
rules = ICURuleLoader(test_config)
assert rules.get_search_rules() == ''
assert rules.get_normalization_rules() == ''
assert rules.get_transliteration_rules() == ''
def test_get_search_rules(self):
self.config_rules()
loader = ICURuleLoader(self.project_env)
rules = loader.get_search_rules()
trans = Transliterator.createFromRules("test", rules)
assert trans.transliterate(" Baum straße ") == " baum straße "
assert trans.transliterate(" Baumstraße ") == " baumstraße "
assert trans.transliterate(" Baumstrasse ") == " baumstrasse "
assert trans.transliterate(" Baumstr ") == " baumstr "
assert trans.transliterate(" Baumwegstr ") == " baumwegstr "
assert trans.transliterate(" Αθήνα ") == " athēna "
assert trans.transliterate(" проспект ") == " prospekt "
