spaCy/spacy/tests/lang/ur/test_prefix_suffix_infix.py
2019-09-29 17:32:12 +02:00

12 lines
286 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