mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-25 09:26:27 +03:00
Update punctuation.py
This commit is contained in:
parent
99a543367d
commit
d1f0b397b5
|
@ -5,11 +5,13 @@ from ..char_classes import LIST_ELLIPSES, LIST_ICONS, ALPHA, ALPHA_LOWER, ALPHA_
|
|||
|
||||
ELISION = " ' ’ ".strip().replace(" ", "")
|
||||
|
||||
abbrev = ("d", "D")
|
||||
|
||||
_infixes = (
|
||||
LIST_ELLIPSES
|
||||
+ LIST_ICONS
|
||||
+ [
|
||||
r"(?<=[{a}][{el}])(?=[{a}])".format(a=ALPHA, el=ELISION),
|
||||
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),
|
||||
|
|
Loading…
Reference in New Issue
Block a user