spaCy/spacy/tests/lang/fr/test_exceptions.py
Sofie c6ad557cea French regular expressions instead of extensive exceptions list (on develop) (#3046) (resolves #2679)
* merge changes of PR 3023 into develop branch instead of master

* further deletions from exception list according to PR 3023
2018-12-16 18:04:55 +01:00

83 lines
2.5 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.parametrize(
"text", ["aujourd'hui", "Aujourd'hui", "prud'hommes", "prudhommal",
"audio-numérique", "Audio-numérique",
"entr'amis", "entr'abat", "rentr'ouvertes", "grand'hamien",
"Châteauneuf-la-Forêt", "Château-Guibert",
"11-septembre", "11-Septembre", "refox-trottâmes",
"K-POP", "K-Pop", "K-pop", "z'yeutes",
"black-outeront", "états-unienne",
"courtes-pattes", "court-pattes",
"saut-de-ski", "Écourt-Saint-Quentin", "Bout-de-l'Îlien", "pet-en-l'air"]
)
def test_fr_tokenizer_infix_exceptions(fr_tokenizer, text):
tokens = fr_tokenizer(text)
assert len(tokens) == 1
@pytest.mark.parametrize(
"text,lemma",
[
("janv.", "janvier"),
("juill.", "juillet"),
("Dr.", "docteur"),
("av.", "avant"),
("sept.", "septembre"),
],
)
def test_fr_tokenizer_handles_abbr(fr_tokenizer, text, lemma):
tokens = fr_tokenizer(text)
assert len(tokens) == 1
assert tokens[0].lemma_ == lemma
def test_fr_tokenizer_handles_exc_in_text(fr_tokenizer):
text = "Je suis allé au mois de janv. aux prudhommes."
tokens = fr_tokenizer(text)
assert len(tokens) == 10
assert tokens[6].text == "janv."
assert tokens[6].lemma_ == "janvier"
assert tokens[8].text == "prudhommes"
def test_fr_tokenizer_handles_exc_in_text_2(fr_tokenizer):
text = "Cette après-midi, je suis allé dans un restaurant italo-mexicain."
tokens = fr_tokenizer(text)
assert len(tokens) == 11
assert tokens[1].text == "après-midi"
assert tokens[9].text == "italo-mexicain"
def test_fr_tokenizer_handles_title(fr_tokenizer):
text = "N'est-ce pas génial?"
tokens = fr_tokenizer(text)
assert len(tokens) == 6
assert tokens[0].text == "N'"
assert tokens[0].lemma_ == "ne"
assert tokens[1].text == "est"
assert tokens[1].lemma_ == "être"
assert tokens[2].text == "-ce"
assert tokens[2].lemma_ == "ce"
@pytest.mark.xfail
def test_fr_tokenizer_handles_title_2(fr_tokenizer):
text = "Est-ce pas génial?"
tokens = fr_tokenizer(text)
assert len(tokens) == 6
assert tokens[0].text == "Est"
assert tokens[0].lemma_ == "être"
def test_fr_tokenizer_handles_title_3(fr_tokenizer):
text = "Qu'est-ce que tu fais?"
tokens = fr_tokenizer(text)
assert len(tokens) == 7
assert tokens[0].text == "Qu'"
assert tokens[0].lemma_ == "que"