mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 20:28:20 +03:00
b6e991440c
* Auto-format tests with black * Add flake8 config * Tidy up and remove unused imports * Fix redefinitions of test functions * Replace orths_and_spaces with words and spaces * Fix compatibility with pytest 4.0 * xfail test for now Test was previously overwritten by following test due to naming conflict, so failure wasn't reported * Unfail passing test * Only use fixture via arguments Fixes pytest 4.0 compatibility
28 lines
692 B
Python
28 lines
692 B
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
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"
|