explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-24 00:46:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix regex invalid escape sequences (#11276)

Browse Source
This commit is contained in:
Adriane Boyd 2022-08-09 10:59:36 +02:00 committed by GitHub
parent 23749cfc91
commit fc4246558b
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
spacy/lang/ko/punctuation.py
View File

@ -3,7 +3,7 @@ from ..punctuation import TOKENIZER_INFIXES as BASE_TOKENIZER_INFIXES
_infixes = (
["·", "ㆍ", "\(", "\)"]
["·", "ㆍ", r"\(", r"\)"]
+ [r"(?<=[0-9])~(?=[0-9-])"]
+ LIST_QUOTES
+ BASE_TOKENIZER_INFIXES

2
spacy/schemas.py
View File

@ -207,7 +207,7 @@ class TokenPatternOperatorSimple(str, Enum):
class TokenPatternOperatorMinMax(ConstrainedStr):
regex = re.compile("^({\d+}|{\d+,\d*}|{\d*,\d+})$")
regex = re.compile(r"^({\d+}|{\d+,\d*}|{\d*,\d+})$")
TokenPatternOperator = Union[TokenPatternOperatorSimple, TokenPatternOperatorMinMax]