smokephil/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-12-07 07:15:07 +01:00
Code Issues Projects Releases Packages Wiki Activity

Collapsing excess whitespace after OCR

Browse source
This commit is contained in:
Aleksandr Bogdanov 2016-10-12 01:46:34 +02:00
parent 14811a4a49
commit 63de2ca1b0
2 changed files with 22 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

9
src/documents/consumer.py
View file

@ -283,7 +283,7 @@ class Consumer(object):
r = " ".join(r)
# Strip out excess white space to allow matching to go smoother
return re.sub(r"\s+", " ", r)
return strip_excess_whitespace(r)
def _store(self, text, doc, thumbnail):
@ -360,6 +360,13 @@ class Consumer(object):
return Document.objects.filter(checksum=checksum).exists()
def strip_excess_whitespace(text):
collapsed_spaces = re.sub(r"([^\S\r\n]+)", " ", text)
no_leading_whitespace = re.sub("([\n\r]+)([^\S\n\r]+)", '\\1', collapsed_spaces)
no_trailing_whitespace = re.sub("([^\S\n\r]+)$", '', no_leading_whitespace)
return no_trailing_whitespace
def image_to_string(args):
img, lang = args
ocr = pyocr.get_available_tools()[0]