explosion--spacy
wehub-resource-sync
f877c37fc6
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 (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 (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
26 行
669 B
Python
26 行
669 B
Python
import pytest
|
||
|
||
XX_BASIC_TOKENIZATION_TESTS = [
|
||
(
|
||
"Lääʹddjânnmest lie nuʹtt 10 000 säʹmmliʹžžed. Seeʹst pâʹjjel",
|
||
[
|
||
"Lääʹddjânnmest",
|
||
"lie",
|
||
"nuʹtt",
|
||
"10",
|
||
"000",
|
||
"säʹmmliʹžžed",
|
||
".",
|
||
"Seeʹst",
|
||
"pâʹjjel",
|
||
],
|
||
),
|
||
]
|
||
|
||
|
||
@pytest.mark.parametrize("text,expected_tokens", XX_BASIC_TOKENIZATION_TESTS)
|
||
def test_xx_tokenizer_basic(xx_tokenizer, text, expected_tokens):
|
||
tokens = xx_tokenizer(text)
|
||
token_list = [token.text for token in tokens if not token.is_space]
|
||
assert expected_tokens == token_list
|