mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-25 17:36:30 +03:00
17 lines
540 B
Python
17 lines
540 B
Python
|
# coding: utf-8
|
||
|
|
"""Test that tokenizer exceptions are parsed correctly."""
|
||
|
|
|
||
|
|
|
||
|
|
from __future__ import unicode_literals
|
||
|
|
|
||
|
|
import pytest
|
||
|
|
|
||
|
|
|
||
|
|
@pytest.mark.parametrize('text,norms', [("пн.", ["понедельник"]),
|
||
|
|
("пт.", ["пятница"]),
|
||
|
|
("дек.", ["декабрь"])])
|
||
|
|
def test_ru_tokenizer_abbrev_exceptions(ru_tokenizer, text, norms):
|
||
|
|
tokens = ru_tokenizer(text)
|
||
|
|
assert len(tokens) == 1
|
||
|
|
assert [token.norm_ for token in tokens] == norms
|