lgcosta/paperless-ngx
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feature: better support for accented characters in date parsing

Browse Source
This commit is contained in:
Fabien Dubuy 2024-06-25 19:21:48 +02:00 committed by GitHub
parent f3b7ae93f0
commit 759bd11fea
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/documents/parsers.py
View File

@ -39,11 +39,11 @@ from documents.utils import run_subprocess
DATE_REGEX = re.compile(
r"(\b|(?!=([_-])))([0-9]{1,2})[\.\/-]([0-9]{1,2})[\.\/-]([0-9]{4}|[0-9]{2})(\b|(?=([_-])))|"
r"(\b|(?!=([_-])))([0-9]{4}|[0-9]{2})[\.\/-]([0-9]{1,2})[\.\/-]([0-9]{1,2})(\b|(?=([_-])))|"
r"(\b|(?!=([_-])))([0-9]{1,2}[\. ]+[a-zA-Z]{3,9} [0-9]{4}|[a-zA-Z]{3,9} [0-9]{1,2}, [0-9]{4})(\b|(?=([_-])))|"
r"(\b|(?!=([_-])))([0-9]{1,2}[\. ]+[a-zA-ZÀ-ÖØ-öø-ÿ]{3,9} [0-9]{4}|[a-zA-ZÀ-ÖØ-öø-ÿ]{3,9} [0-9]{1,2}, [0-9]{4})(\b|(?=([_-])))|"
r"(\b|(?!=([_-])))([^\W\d_]{3,9} [0-9]{1,2}, ([0-9]{4}))(\b|(?=([_-])))|"
r"(\b|(?!=([_-])))([^\W\d_]{3,9} [0-9]{4})(\b|(?=([_-])))|"
r"(\b|(?!=([_-])))([0-9]{1,2}[^ ]{2}[\. ]+[^ ]{3,9}[ \.\/-][0-9]{4})(\b|(?=([_-])))|"
r"(\b|(?!=([_-])))(\b[0-9]{1,2}[ \.\/-][a-zA-Z]{3}[ \.\/-][0-9]{4})(\b|(?=([_-])))",
r"(\b|(?!=([_-])))(\b[0-9]{1,2}[ \.\/-][a-zA-ZÀ-ÖØ-öø-ÿ]{3}[ \.\/-][0-9]{4})(\b|(?=([_-])))",
)