smokephil/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-12-08 07:45:32 +01:00
Code Issues Projects Releases Packages Wiki Activity

fixes #794

Browse source
This commit is contained in:
jonaswinkler 2021-03-22 22:46:35 +01:00
parent 27cb243a2f
commit d26c46e034
1 changed files with 2 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

2
src/paperless_tesseract/parsers.py
View file

@ -119,6 +119,8 @@ class RasterisedDocumentParser(DocumentParser):
try:
text = extract_text(pdf_file)
stripped = strip_excess_whitespace(text)
stripped = stripped.replace("\0", " ")
self.log("debug", f"Extracted text from PDF file {pdf_file}")
return stripped
except PDFException: