mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-29 11:26:28 +03:00
e2b70df012
* Use isort with Black profile * isort all the things * Fix import cycles as a result of import sorting * Add DOCBIN_ALL_ATTRS type definition * Add isort to requirements * Remove isort from build dependencies check * Typo
24 lines
773 B
Python
24 lines
773 B
Python
import pytest
|
|
|
|
from spacy.lang.char_classes import ALPHA
|
|
from spacy.lang.punctuation import TOKENIZER_INFIXES
|
|
from spacy.language import BaseDefaults, Language
|
|
|
|
|
|
@pytest.mark.issue(768)
|
|
@pytest.mark.parametrize(
|
|
"text,expected_tokens", [("l'avion", ["l'", "avion"]), ("j'ai", ["j'", "ai"])]
|
|
)
|
|
def test_issue768(text, expected_tokens):
|
|
"""Allow zero-width 'infix' token during the tokenization process."""
|
|
SPLIT_INFIX = r"(?<=[{a}]\')(?=[{a}])".format(a=ALPHA)
|
|
|
|
class FrenchTest(Language):
|
|
class Defaults(BaseDefaults):
|
|
infixes = TOKENIZER_INFIXES + [SPLIT_INFIX]
|
|
|
|
fr_tokenizer_w_infix = FrenchTest().tokenizer
|
|
tokens = fr_tokenizer_w_infix(text)
|
|
assert len(tokens) == 2
|
|
assert [t.text for t in tokens] == expected_tokens
|