explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 09:26:27 +03:00
Code Issues Packages Projects Releases Wiki Activity

Add punctuation

Browse Source
This commit is contained in:
muratjumashev 2021-01-23 21:31:31 +06:00
parent 101d265778
commit 4418ec2eee
1 changed files with 23 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
spacy/lang/ky/punctuation.py Normal file
View File

@ -0,0 +1,23 @@
# coding: utf8
from __future__ import unicode_literals
from ..char_classes import ALPHA, ALPHA_LOWER, ALPHA_UPPER, CONCAT_QUOTES, HYPHENS
from ..char_classes import LIST_ELLIPSES, LIST_ICONS
_hyphens_no_dash = HYPHENS.replace("-", "").strip("|").replace("||", "")
_infixes = (
LIST_ELLIPSES
+ LIST_ICONS
+ [
r"(?<=[{al}])\.(?=[{au}])".format(al=ALPHA_LOWER, au=ALPHA_UPPER),
r"(?<=[{a}])[,!?/()]+(?=[{a}])".format(a=ALPHA),
r"(?<=[{a}{q}])[:<>=](?=[{a}])".format(a=ALPHA, q=CONCAT_QUOTES),
r"(?<=[{a}])--(?=[{a}])".format(a=ALPHA),
r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA),
r"(?<=[{a}])([{q}\)\]\(\[])(?=[\-{a}])".format(a=ALPHA, q=CONCAT_QUOTES),
r"(?<=[{a}])(?:{h})(?=[{a}])".format(a=ALPHA, h=_hyphens_no_dash),
r"(?<=[0-9])-(?=[0-9])",
]
)
TOKENIZER_INFIXES = _infixes