You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
20 lines
488 B
20 lines
488 B
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
|