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
16 行
449 B
Python
16 行
449 B
Python
import pytest
|
|
|
|
LG_BASIC_TOKENIZATION_TESTS = [
|
|
(
|
|
"Abooluganda ab’emmamba ababiri",
|
|
["Abooluganda", "ab’emmamba", "ababiri"],
|
|
),
|
|
]
|
|
|
|
|
|
@pytest.mark.parametrize("text,expected_tokens", LG_BASIC_TOKENIZATION_TESTS)
|
|
def test_lg_tokenizer_basic(lg_tokenizer, text, expected_tokens):
|
|
tokens = lg_tokenizer(text)
|
|
token_list = [token.text for token in tokens if not token.is_space]
|
|
assert expected_tokens == token_list
|