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

26 lines
669 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
XX_BASIC_TOKENIZATION_TESTS = [
(
"Lääʹddjânnmest lie nuʹtt 10 000 säʹmmliʹžžed. Seeʹst pâʹjjel",
[
"Lääʹddjânnmest",
"lie",
"nuʹtt",
"10",
"000",
"ʹmmliʹžžed",
".",
"Seeʹst",
"ʹjjel",
],
),
]
@pytest.mark.parametrize("text,expected_tokens", XX_BASIC_TOKENIZATION_TESTS)
def test_xx_tokenizer_basic(xx_tokenizer, text, expected_tokens):
tokens = xx_tokenizer(text)
token_list = [token.text for token in tokens if not token.is_space]
assert expected_tokens == token_list