mirror of
https://github.com/explosion/spaCy.git
synced 2025-11-04 09:57:26 +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
22 lines
641 B
Python
22 lines
641 B
Python
from ..char_classes import ALPHA, ALPHA_LOWER, ALPHA_UPPER, LIST_ELLIPSES, LIST_ICONS
|
||
|
||
ELISION = " ' ’ ".strip().replace(" ", "")
|
||
|
||
abbrev = ("d", "D")
|
||
|
||
_infixes = (
|
||
LIST_ELLIPSES
|
||
+ LIST_ICONS
|
||
+ [
|
||
r"(?<=^[{ab}][{el}])(?=[{a}])".format(ab=abbrev, a=ALPHA, el=ELISION),
|
||
r"(?<=[{al}])\.(?=[{au}])".format(al=ALPHA_LOWER, au=ALPHA_UPPER),
|
||
r"(?<=[{a}])[,!?](?=[{a}])".format(a=ALPHA),
|
||
r"(?<=[{a}])[:<>=](?=[{a}])".format(a=ALPHA),
|
||
r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA),
|
||
r"(?<=[{a}])--(?=[{a}])".format(a=ALPHA),
|
||
r"(?<=[0-9])-(?=[0-9])",
|
||
]
|
||
)
|
||
|
||
TOKENIZER_INFIXES = _infixes
|