mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 18:36:36 +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]
25 lines
635 B
Python
25 lines
635 B
Python
import pytest
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"text,lemma",
|
|
[
|
|
("aprox.", "aproximadamente"),
|
|
("esq.", "esquina"),
|
|
("pág.", "página"),
|
|
("p.ej.", "por ejemplo"),
|
|
],
|
|
)
|
|
def test_es_tokenizer_handles_abbr(es_tokenizer, text, lemma):
|
|
tokens = es_tokenizer(text)
|
|
assert len(tokens) == 1
|
|
assert tokens[0].lemma_ == lemma
|
|
|
|
|
|
def test_es_tokenizer_handles_exc_in_text(es_tokenizer):
|
|
text = "Mariano Rajoy ha corrido aprox. medio kilómetro"
|
|
tokens = es_tokenizer(text)
|
|
assert len(tokens) == 7
|
|
assert tokens[4].text == "aprox."
|
|
assert tokens[4].lemma_ == "aproximadamente"
|