mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-13 05:07:03 +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
12 lines
267 B
Python
12 lines
267 B
Python
from ..char_classes import LIST_QUOTES
|
|
from ..punctuation import TOKENIZER_INFIXES as BASE_TOKENIZER_INFIXES
|
|
|
|
_infixes = (
|
|
["·", "ㆍ", r"\(", r"\)"]
|
|
+ [r"(?<=[0-9])~(?=[0-9-])"]
|
|
+ LIST_QUOTES
|
|
+ BASE_TOKENIZER_INFIXES
|
|
)
|
|
|
|
TOKENIZER_INFIXES = _infixes
|