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
20 lines
488 B
Python
20 lines
488 B
Python
import pytest
|
|
|
|
|
|
def test_eu_tokenizer_handles_long_text(eu_tokenizer):
|
|
text = """ta nere guitarra estrenatu ondoren"""
|
|
tokens = eu_tokenizer(text)
|
|
assert len(tokens) == 5
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"text,length",
|
|
[
|
|
("milesker ederra joan zen hitzaldia plazer hutsa", 7),
|
|
("astelehen guztia sofan pasau biot", 5),
|
|
],
|
|
)
|
|
def test_eu_tokenizer_handles_cnts(eu_tokenizer, text, length):
|
|
tokens = eu_tokenizer(text)
|
|
assert len(tokens) == length
|