mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-22 03:49:17 +03:00
db55577c45
* Remove unicode declarations * Remove Python 3.5 and 2.7 from CI * Don't require pathlib * Replace compat helpers * Remove OrderedDict * Use f-strings * Set Cython compiler language level * Fix typo * Re-add OrderedDict for Table * Update setup.cfg * Revert CONTRIBUTING.md * Revert lookups.md * Revert top-level.md * Small adjustments and docs [ci skip]
20 lines
584 B
Python
20 lines
584 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
|
|
assert tokens[0].lemma_ == lemma
|
|
|
|
|
|
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."
|
|
assert tokens[7].lemma_ == "aproximadament"
|