spaCy/spacy/tests/lang/uk/test_tokenizer_exc.py
Ines Montani db55577c45
Drop Python 2.7 and 3.5 (#4828)
* Remove unicode declarations

* Remove Python 3.5 and 2.7 from CI

* Don't require pathlib

* Replace compat helpers

* Remove OrderedDict

* Use f-strings

* Set Cython compiler language level

* Fix typo

* Re-add OrderedDict for Table

* Update setup.cfg

* Revert CONTRIBUTING.md

* Revert lookups.md

* Revert top-level.md

* Small adjustments and docs [ci skip]
2019-12-22 01:53:56 +01:00

12 lines
364 B
Python

import pytest
@pytest.mark.parametrize(
"text,norms,lemmas",
[("ім.", ["імені"], ["ім'я"]), ("проф.", ["професор"], ["професор"])],
)
def test_uk_tokenizer_abbrev_exceptions(uk_tokenizer, text, norms, lemmas):
tokens = uk_tokenizer(text)
assert len(tokens) == 1
assert [token.norm_ for token in tokens] == norms