paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-09-16 21:55:37 -05:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #302 from BastianPoe/bugfix/extend_regex_to_find_more_dates

Browse Source 
Extends the regex to find dates in documents as reported by @isaacsando
This commit is contained in:
Daniel Quinn
2018-02-18 17:23:49 +01:00
committed by GitHub
parent 9a47dba494 96c7222269
commit 5d01410dc0
4 changed files with 153 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

47
src/paperless_tesseract/parsers.py
View File

@@ -202,7 +202,13 @@ class RasterisedDocumentParser(DocumentParser):
return text
def get_date(self):
text = self.get_text()
date = None
datestring = None
try:
text = self.get_text()
except ParseError as e:
return None
# This regular expression will try to find dates in the document at
# hand and will match the following formats:
@@ -210,19 +216,38 @@ class RasterisedDocumentParser(DocumentParser):
# - XX/YY/ZZZZ with XX + YY being 1 or 2 and ZZZZ being 2 or 4 digits
# - XX-YY-ZZZZ with XX + YY being 1 or 2 and ZZZZ being 2 or 4 digits
# - XX. MONTH ZZZZ with XX being 1 or 2 and ZZZZ being 2 or 4 digits
# - MONTH ZZZZ
m = re.search(
# - MONTH ZZZZ, with ZZZZ being 4 digits
# - MONTH XX, ZZZZ with XX being 1 or 2 and ZZZZ being 4 digits
pattern = re.compile(
r'\b([0-9]{1,2})[\.\/-]([0-9]{1,2})[\.\/-]([0-9]{4}|[0-9]{2})\b|' +
r'\b([0-9]{1,2}\. [^ ]{3,9} ([0-9]{4}|[0-9]{2}))\b|' +
r'\b([^ ]{3,9} [0-9]{4})\b', text)
r'\b([0-9]{1,2}[\. ]+[^ ]{3,9} ([0-9]{4}|[0-9]{2}))\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')
if m is None:
return None
# Iterate through all regex matches and try to parse the date
for m in re.finditer(pattern, text):
datestring = m.group(0)
return dateparser.parse(m.group(0),
settings={'DATE_ORDER': self.DATE_ORDER,
'PREFER_DAY_OF_MONTH': 'first',
'RETURN_AS_TIMEZONE_AWARE': True})
try:
date = dateparser.parse(
datestring,
settings={'DATE_ORDER': self.DATE_ORDER,
'PREFER_DAY_OF_MONTH': 'first',
'RETURN_AS_TIMEZONE_AWARE': True})
except TypeError:
# Skip all matches that do not parse to a proper date
continue
if date is not None:
break
if date is not None:
self.log("info", "Detected document date " + date.strftime("%x") +
" based on string " + datestring)
else:
self.log("info", "Unable to detect date for document")
return date
def run_convert(*args):