paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-07-28 18:24:38 -05:00
Code Issues Packages Projects Releases Wiki Activity

Updates the ignore date parsing to utilize the settings defined date order, instead of guessing a bit

Browse Source
This commit is contained in:
Trenton Holmes
2022-04-13 08:04:15 -07:00
committed by Trenton Holmes
parent a944ef1ca6
commit 304d5b0d5a
3 changed files with 48 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
src/documents/parsers.py
View File

@@ -247,10 +247,8 @@ def parse_date(filename, text) -> Optional[datetime.datetime]:
# if filename date parsing is enabled, search there first:
if settings.FILENAME_DATE_ORDER:
logger.info("Attempting parsing from filename")
for m in re.finditer(DATE_REGEX, filename):
date_string = m.group(0)
logger.info(f"Found potential date: {date_string}")
try:
date = __parser(date_string, settings.FILENAME_DATE_ORDER)
@@ -260,16 +258,11 @@ def parse_date(filename, text) -> Optional[datetime.datetime]:
date = __filter(date)
if date is not None:
logger.info(f"Found date: {date}")
return date
else:
logger.info("Filtered date out")
logger.info("Attempting parsing from content")
# Iterate through all regex matches in text and try to parse the date
for m in re.finditer(DATE_REGEX, text):
date_string = m.group(0)
logger.info(f"Found potential date: {date_string}")
try:
date = __parser(date_string, settings.DATE_ORDER)
@@ -279,10 +272,7 @@ def parse_date(filename, text) -> Optional[datetime.datetime]:
date = __filter(date)
if date is not None:
logger.info(f"Found date: {date}")
return date
else:
logger.info("Filtered date out")
return date