mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-25 09:26:27 +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
31 lines
916 B
Python
31 lines
916 B
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
|
|
|
|
def test_fr_lemmatizer_verb(fr_tokenizer):
|
|
tokens = fr_tokenizer("Qu'est-ce que tu fais?")
|
|
assert tokens[0].lemma_ == "que"
|
|
assert tokens[1].lemma_ == "être"
|
|
assert tokens[5].lemma_ == "faire"
|
|
|
|
|
|
def test_fr_lemmatizer_noun_verb_2(fr_tokenizer):
|
|
tokens = fr_tokenizer("Les abaissements de température sont gênants.")
|
|
assert tokens[4].lemma_ == "être"
|
|
|
|
|
|
@pytest.mark.xfail(
|
|
reason="Costaricienne TAG is PROPN instead of NOUN and spacy don't lemmatize PROPN"
|
|
)
|
|
def test_fr_lemmatizer_noun(fr_tokenizer):
|
|
tokens = fr_tokenizer("il y a des Costaricienne.")
|
|
assert tokens[4].lemma_ == "Costaricain"
|
|
|
|
|
|
def test_fr_lemmatizer_noun_2(fr_tokenizer):
|
|
tokens = fr_tokenizer("Les abaissements de température sont gênants.")
|
|
assert tokens[1].lemma_ == "abaissement"
|
|
assert tokens[5].lemma_ == "gênant"
|