Files
wehub-resource-sync f877c37fc6
tests / Test (macos-latest, 3.14) (push) Has been cancelled
tests / Test (ubuntu-latest, 3.10) (push) Has been cancelled
tests / Test (ubuntu-latest, 3.11) (push) Has been cancelled
tests / Test (windows-latest, 3.13) (push) Has been cancelled
tests / Test (windows-latest, 3.14) (push) Has been cancelled
tests / Validate (push) Has been cancelled
tests / Test (macos-latest, 3.10) (push) Has been cancelled
tests / Test (macos-latest, 3.11) (push) Has been cancelled
tests / Test (macos-latest, 3.12) (push) Has been cancelled
tests / Test (macos-latest, 3.13) (push) Has been cancelled
tests / Test (ubuntu-latest, 3.12) (push) Has been cancelled
tests / Test (ubuntu-latest, 3.13) (push) Has been cancelled
tests / Test (ubuntu-latest, 3.14) (push) Has been cancelled
tests / Test (windows-latest, 3.10) (push) Has been cancelled
tests / Test (windows-latest, 3.11) (push) Has been cancelled
tests / Test (windows-latest, 3.12) (push) Has been cancelled
universe validation / Validate (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 12:37:51 +08:00

16 lines
684 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