mirror of
https://github.com/explosion/spaCy.git
synced 2025-11-04 01:48:04 +03:00
7ed7908716
* Add support basic support for upper sorbian. * Add tokenizer exceptions and tests. * Update spacy/lang/hsb/examples.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
33 lines
866 B
Python
33 lines
866 B
Python
import pytest
|
|
|
|
HSB_BASIC_TOKENIZATION_TESTS = [
|
|
(
|
|
"Hornjoserbšćina wobsteji resp. wobsteješe z wjacorych dialektow, kotrež so zdźěla chětro wot so rozeznawachu.",
|
|
[
|
|
"Hornjoserbšćina",
|
|
"wobsteji",
|
|
"resp.",
|
|
"wobsteješe",
|
|
"z",
|
|
"wjacorych",
|
|
"dialektow",
|
|
",",
|
|
"kotrež",
|
|
"so",
|
|
"zdźěla",
|
|
"chětro",
|
|
"wot",
|
|
"so",
|
|
"rozeznawachu",
|
|
".",
|
|
],
|
|
),
|
|
]
|
|
|
|
|
|
@pytest.mark.parametrize("text,expected_tokens", HSB_BASIC_TOKENIZATION_TESTS)
|
|
def test_hsb_tokenizer_basic(hsb_tokenizer, text, expected_tokens):
|
|
tokens = hsb_tokenizer(text)
|
|
token_list = [token.text for token in tokens if not token.is_space]
|
|
assert expected_tokens == token_list
|