spaCy/spacy/tests/fr/test_exceptions.py
Gregory Howard 8ff4682255 correcting tokenizer exception.
Adding tests for lemmatization
2017-04-27 11:52:14 +02:00

65 lines
2.1 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"])
def test_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_tokenizer_handles_abbr(fr_tokenizer, text, lemma):
tokens = fr_tokenizer(text)
assert len(tokens) == 1
assert tokens[0].lemma_ == lemma
def test_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_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_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"
def test_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_tokenizer_handles_title_2(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"