mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-14 13:47:13 +03:00
14 lines
292 B
Python
14 lines
292 B
Python
|
# coding: utf-8
|
||
|
|
from __future__ import unicode_literals
|
||
|
|
|
||
|
|
import pytest
|
||
|
|
|
||
|
|
|
||
|
|
@pytest.mark.parametrize(
|
||
|
|
"text", ['ہےں۔', 'کیا۔']
|
||
|
|
)
|
||
|
|
def test_contractions(ur_tokenizer, text):
|
||
|
|
"""Test specific Urdu punctuation character"""
|
||
|
|
tokens = ur_tokenizer(text)
|
||
|
|
assert len(tokens) == 2
|