paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-04-09 09:58:20 -05:00
Code Issues Packages Projects Releases Wiki Activity

respect settings.skip_archive_file before OCR fails

Browse Source
This commit is contained in:
Ben Greiner 2025-02-14 18:34:56 +01:00 committed by GitHub
parent a9ef7ff58e
commit 71d7a8ab0c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
src/paperless_tesseract/parsers.py
View File

@ -378,13 +378,13 @@ class RasterisedDocumentParser(DocumentParser):
sidecar_file, sidecar_file,
) )
if self.settings.skip_archive_file != ArchiveFileChoices.ALWAYS:
self.archive_path = archive_path
try: try:
self.log.debug(f"Calling OCRmyPDF with args: {args}") self.log.debug(f"Calling OCRmyPDF with args: {args}")
ocrmypdf.ocr(**args) ocrmypdf.ocr(**args)
if self.settings.skip_archive_file != ArchiveFileChoices.ALWAYS:
self.archive_path = archive_path
self.text = self.extract_text(sidecar_file, archive_path) self.text = self.extract_text(sidecar_file, archive_path)
if not self.text: if not self.text: