mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-22 03:49:17 +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]
101 lines
2.6 KiB
Python
101 lines
2.6 KiB
Python
import pytest
|
||
|
||
|
||
@pytest.mark.parametrize(
|
||
"text",
|
||
[
|
||
"aujourd'hui",
|
||
"Aujourd'hui",
|
||
"prud'hommes",
|
||
"prud’hommal",
|
||
"audio-numérique",
|
||
"Audio-numérique",
|
||
"entr'amis",
|
||
"entr'abat",
|
||
"rentr'ouvertes",
|
||
"grand'hamien",
|
||
"Châteauneuf-la-Forêt",
|
||
"Château-Guibert",
|
||
"11-septembre",
|
||
"11-Septembre",
|
||
"refox-trottâmes",
|
||
# u"K-POP",
|
||
# u"K-Pop",
|
||
# u"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 prud’hommes."
|
||
tokens = fr_tokenizer(text)
|
||
assert len(tokens) == 10
|
||
assert tokens[6].text == "janv."
|
||
assert tokens[6].lemma_ == "janvier"
|
||
assert tokens[8].text == "prud’hommes"
|
||
|
||
|
||
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"
|