mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 02:16:32 +03:00
18 lines
499 B
Python
18 lines
499 B
Python
import pytest
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"text,lemma",
|
|
[("aprox.", "aproximadament"), ("pàg.", "pàgina"), ("p.ex.", "per exemple")],
|
|
)
|
|
def test_ca_tokenizer_handles_abbr(ca_tokenizer, text, lemma):
|
|
tokens = ca_tokenizer(text)
|
|
assert len(tokens) == 1
|
|
|
|
|
|
def test_ca_tokenizer_handles_exc_in_text(ca_tokenizer):
|
|
text = "La Núria i el Pere han vingut aprox. a les 7 de la tarda."
|
|
tokens = ca_tokenizer(text)
|
|
assert len(tokens) == 15
|
|
assert tokens[7].text == "aprox."
|