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

31 lines
778 B
Python

import pytest
LV_BASIC_TOKENIZATION_TESTS = [
(
"Nevienu nedrīkst spīdzināt vai cietsirdīgi vai pazemojoši ar viņu "
"apieties vai sodīt.",
[
"Nevienu",
"nedrīkst",
"spīdzināt",
"vai",
"cietsirdīgi",
"vai",
"pazemojoši",
"ar",
"viņu",
"apieties",
"vai",
"sodīt",
".",
],
),
]
@pytest.mark.parametrize("text,expected_tokens", LV_BASIC_TOKENIZATION_TESTS)
def test_lv_tokenizer_basic(lv_tokenizer, text, expected_tokens):
tokens = lv_tokenizer(text)
token_list = [token.text for token in tokens if not token.is_space]
assert expected_tokens == token_list