spaCy/spacy/tests/fr/test_lemmatization.py

36 lines
1.0 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# coding: utf-8
from __future__ import unicode_literals
import pytest
@pytest.mark.xfail
def test_lemmatizer_(fr_tokenizer):
text = "Je suis allé au mois de janv. aux prudhommes."
tokens = fr_tokenizer(text)
assert len(tokens) == 10
assert tokens[2].lemma_ == "aller"
@pytest.mark.xfail
def test_tokenizer_handles_exc_in_text_2(fr_tokenizer):
text = "Je dois manger ce soir"
tokens = fr_tokenizer(text)
assert len(tokens) == 11
assert tokens[1].lemma_ == "devoir"
@pytest.mark.xfail
def test_tokenizer_handles_exc_in_text_2(fr_tokenizer):
text = "Je dois manger ce soir"
tokens = fr_tokenizer(text)
assert len(tokens) == 11
assert tokens[1].lemma_ == "devoir"
@pytest.mark.xfail
def test_tokenizer_handles_exc_in_text_2(fr_tokenizer):
# This one is tricky because notes is a NOUN and can be a VERB
text = "Nous validerons vos notes plus tard"
tokens = fr_tokenizer(text)
assert len(tokens) == 11
assert tokens[1].lemma_ == "valider"
assert tokens[3].lemma_ == "notes"