mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 10:26:35 +03:00
20 lines
567 B
Python
20 lines
567 B
Python
# coding: utf-8
|
||
from __future__ import unicode_literals
|
||
|
||
import pytest
|
||
|
||
|
||
@pytest.mark.parametrize(
|
||
"text,norms,lemmas",
|
||
[
|
||
("о.г.", ["ове године"], ["ова година"]),
|
||
("чет.", ["четвртак"], ["четвртак"]),
|
||
("гђа", ["госпођа"], ["госпођа"]),
|
||
("ил'", ["или"], ["или"]),
|
||
],
|
||
)
|
||
def test_sr_tokenizer_abbrev_exceptions(sr_tokenizer, text, norms, lemmas):
|
||
tokens = sr_tokenizer(text)
|
||
assert len(tokens) == 1
|
||
assert [token.norm_ for token in tokens] == norms
|