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
31 lines
783 B
Python
31 lines
783 B
Python
import pytest
|
|
|
|
IS_BASIC_TOKENIZATION_TESTS = [
|
|
(
|
|
"Enginn maður skal sæta pyndingum eða ómannlegri eða "
|
|
"vanvirðandi meðferð eða refsingu. ",
|
|
[
|
|
"Enginn",
|
|
"maður",
|
|
"skal",
|
|
"sæta",
|
|
"pyndingum",
|
|
"eða",
|
|
"ómannlegri",
|
|
"eða",
|
|
"vanvirðandi",
|
|
"meðferð",
|
|
"eða",
|
|
"refsingu",
|
|
".",
|
|
],
|
|
),
|
|
]
|
|
|
|
|
|
@pytest.mark.parametrize("text,expected_tokens", IS_BASIC_TOKENIZATION_TESTS)
|
|
def test_is_tokenizer_basic(is_tokenizer, text, expected_tokens):
|
|
tokens = is_tokenizer(text)
|
|
token_list = [token.text for token in tokens if not token.is_space]
|
|
assert expected_tokens == token_list
|