spaCy/spacy/tests/lang/bg/test_tokenizer.py

9 lines
252 B
Python
Raw Normal View History

import pytest
def test_bg_tokenizer_handles_final_diacritics(bg_tokenizer):
text = "Ня̀маше яйца̀. Ня̀маше яйца̀."
tokens = bg_tokenizer(text)
assert tokens[1].text == "яйца̀"
assert tokens[2].text == "."