spaCy/spacy/tests/lang/ga/test_tokenizer.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
685 B
Python

import pytest
# fmt: off
GA_TOKEN_EXCEPTION_TESTS = [
("Niall Ó Domhnaill, Rialtas na hÉireann 1977 (lch. 600).", ["Niall", "Ó", "Domhnaill", ",", "Rialtas", "na", "hÉireann", "1977", "(", "lch.", "600", ")", "."]),
("Daoine a bhfuil Gaeilge acu, m.sh. tusa agus mise", ["Daoine", "a", "bhfuil", "Gaeilge", "acu", ",", "m.sh.", "tusa", "agus", "mise"])
]
# fmt: on
@pytest.mark.parametrize("text,expected_tokens", GA_TOKEN_EXCEPTION_TESTS)
def test_ga_tokenizer_handles_exception_cases(ga_tokenizer, text, expected_tokens):
tokens = ga_tokenizer(text)
token_list = [token.text for token in tokens if not token.is_space]
assert expected_tokens == token_list