smokephil/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-12-10 08:37:19 +01:00
Code Issues Projects Releases Packages Wiki Activity

Runs the pre-commit hooks over all the Python files

Browse source
This commit is contained in:
Trenton Holmes 2022-03-11 10:55:51 -08:00
parent d3e9799279
commit 1771d18a21
94 changed files with 1638 additions and 991 deletions
Download patch file Download diff file Expand all files Collapse all files

12
src/documents/parsers.py
View file

@ -9,6 +9,8 @@ import tempfile
import magic
from django.conf import settings
from django.utils import timezone
from documents.loggers import LoggingMixin
from documents.signals import document_consumer_declaration
# This regular expression will try to find dates in the document at
# hand and will match the following formats:
@ -21,17 +23,15 @@ from django.utils import timezone
# - XX. MONTH ZZZZ with XX being 1 or 2 and ZZZZ being 2 or 4 digits
# - MONTH ZZZZ, with ZZZZ being 4 digits
# - MONTH XX, ZZZZ with XX being 1 or 2 and ZZZZ being 4 digits
from documents.loggers import LoggingMixin
from documents.signals import document_consumer_declaration
# TODO: isnt there a date parsing library for this?
DATE_REGEX = re.compile(
r"(\b|(?!=([_-])))([0-9]{1,2})[\.\/-]([0-9]{1,2})[\.\/-]([0-9]{4}|[0-9]{2})(\b|(?=([_-])))|" # NOQA: E501
r"(\b|(?!=([_-])))([0-9]{4}|[0-9]{2})[\.\/-]([0-9]{1,2})[\.\/-]([0-9]{1,2})(\b|(?=([_-])))|" # NOQA: E501
r"(\b|(?!=([_-])))([0-9]{1,2}[\. ]+[^ ]{3,9} ([0-9]{4}|[0-9]{2}))(\b|(?=([_-])))|" # NOQA: E501
r"(\b|(?!=([_-])))([0-9]{1,2})[\.\/-]([0-9]{1,2})[\.\/-]([0-9]{4}|[0-9]{2})(\b|(?=([_-])))|" # noqa: E501
r"(\b|(?!=([_-])))([0-9]{4}|[0-9]{2})[\.\/-]([0-9]{1,2})[\.\/-]([0-9]{1,2})(\b|(?=([_-])))|" # noqa: E501
r"(\b|(?!=([_-])))([0-9]{1,2}[\. ]+[^ ]{3,9} ([0-9]{4}|[0-9]{2}))(\b|(?=([_-])))|" # noqa: E501
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|(?!=([_-])))([^\W\d_]{3,9} [0-9]{4})(\b|(?=([_-])))",
)