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

Merge branch 'ENH_text_consumer' of git://github.com/jat255/paperless into jat255-ENH_text_consumer

Browse Source
This commit is contained in:
Daniel Quinn
2018-09-09 20:52:59 +01:00
parent 058a88f102 5326895334
commit a3158eedf9
9 changed files with 203 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
src/paperless_tesseract/parsers.py
View File

@@ -14,7 +14,7 @@ from pyocr.libtesseract.tesseract_raw import \
from pyocr.tesseract import TesseractError
import pdftotext
from documents.parsers import DocumentParser, ParseError
from documents.parsers import DocumentParser, ParseError, pattern
from .languages import ISO639
@@ -210,20 +210,6 @@ class RasterisedDocumentParser(DocumentParser):
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:
# - 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-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, 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([^\W\d_]{3,9} [0-9]{1,2}, ([0-9]{4}))\b|' +
r'\b([^\W\d_]{3,9} [0-9]{4})\b')
# Iterate through all regex matches and try to parse the date
for m in re.finditer(pattern, text):
datestring = m.group(0)