mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-29 11:26:28 +03:00
7b134b8fbd
* Added Slovak * Added Slovenian tests * Added Estonian tests * Added Croatian tests * Added Latvian tests * Added Icelandic tests * Added Afrikaans tests * Added language-independent tests * Added Kannada tests * Tidied up * Added Albanian tests * Formatted with black * Added failing tests for anomalies * Update spacy/tests/lang/af/test_text.py Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Added context to failing Estonian tokenizer test Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Added context to failing Croatian tokenizer test Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Added context to failing Icelandic tokenizer test Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Added context to failing Latvian tokenizer test Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Added context to failing Slovak tokenizer test Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Added context to failing Slovenian tokenizer test Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
26 lines
669 B
Python
26 lines
669 B
Python
import pytest
|
||
|
||
XX_BASIC_TOKENIZATION_TESTS = [
|
||
(
|
||
"Lääʹddjânnmest lie nuʹtt 10 000 säʹmmliʹžžed. Seeʹst pâʹjjel",
|
||
[
|
||
"Lääʹddjânnmest",
|
||
"lie",
|
||
"nuʹtt",
|
||
"10",
|
||
"000",
|
||
"säʹmmliʹžžed",
|
||
".",
|
||
"Seeʹst",
|
||
"pâʹjjel",
|
||
],
|
||
),
|
||
]
|
||
|
||
|
||
@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
|