mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-22 03:49:17 +03:00
15 lines
531 B
Python
15 lines
531 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
|