spaCy/spacy/tests/lang/sr/test_exceptions.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

17 lines
510 B
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

import pytest
@pytest.mark.parametrize(
"text,norms,lemmas",
[
("о.г.", ["ове године"], ["ова година"]),
("чет.", ["четвртак"], ["четвртак"]),
("гђа", ["госпођа"], ["госпођа"]),
("ил'", ["или"], ["или"]),
],
)
def test_sr_tokenizer_abbrev_exceptions(sr_tokenizer, text, norms, lemmas):
tokens = sr_tokenizer(text)
assert len(tokens) == 1
assert [token.norm_ for token in tokens] == norms