ai-content-maker/.venv/Lib/site-packages/spacy/tests/lang/sq/test_tokenizer.py

32 lines
817 B
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

import pytest
SQ_BASIC_TOKENIZATION_TESTS = [
(
"Askush nuk mund ti nënshtrohet torturës ose dënimeve ose "
"trajtimeve çnjerëzore ose poshtëruese.",
[
"Askush",
"nuk",
"mund",
"ti",
"nënshtrohet",
"torturës",
"ose",
"dënimeve",
"ose",
"trajtimeve",
"çnjerëzore",
"ose",
"poshtëruese",
".",
],
),
]
@pytest.mark.parametrize("text,expected_tokens", SQ_BASIC_TOKENIZATION_TESTS)
def test_sq_tokenizer_basic(sq_tokenizer, text, expected_tokens):
tokens = sq_tokenizer(text)
token_list = [token.text for token in tokens if not token.is_space]
assert expected_tokens == token_list