paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-12-14 01:21:14 -06:00
Code Issues Packages Projects Releases Wiki Activity

Fixes for a change in what OCRMyPDF reports when a signed and encrypted document is encountered

Browse Source
This commit is contained in:
Trenton H
2024-11-04 09:09:51 -08:00
committed by Trenton Holmes
parent 24d394ffcc
commit e77774234c
1 changed files with 3 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
src/paperless_tesseract/parsers.py
View File

@@ -365,6 +365,7 @@ class RasterisedDocumentParser(DocumentParser):
from ocrmypdf import EncryptedPdfError from ocrmypdf import EncryptedPdfError
from ocrmypdf import InputFileError from ocrmypdf import InputFileError
from ocrmypdf import SubprocessOutputError from ocrmypdf import SubprocessOutputError
from ocrmypdf.exceptions import DigitalSignatureError
archive_path = Path(os.path.join(self.tempdir, "archive.pdf")) archive_path = Path(os.path.join(self.tempdir, "archive.pdf"))
sidecar_file = Path(os.path.join(self.tempdir, "sidecar.txt")) sidecar_file = Path(os.path.join(self.tempdir, "sidecar.txt"))
@@ -387,9 +388,9 @@ class RasterisedDocumentParser(DocumentParser):
if not self.text: if not self.text:
raise NoTextFoundException("No text was found in the original document") raise NoTextFoundException("No text was found in the original document")
except EncryptedPdfError: except (DigitalSignatureError, EncryptedPdfError):
self.log.warning( self.log.warning(
"This file is encrypted, OCR is impossible. Using " "This file is encrypted and/or signed, OCR is impossible. Using "
"any text present in the original file.", "any text present in the original file.",
) )
if original_has_text: if original_has_text: