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

Reverts the change around skip_noarchive to align with how it is documented to work

Browse Source
This commit is contained in:
Trenton Holmes
2022-10-19 11:37:47 -07:00
committed by Trenton H
parent 53e8d84af2
commit d1aa08850d
2 changed files with 44 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
src/paperless_tesseract/parsers.py
View File

@@ -249,16 +249,22 @@ class RasterisedDocumentParser(DocumentParser):
if mime_type == "application/pdf":
text_original = self.extract_text(None, document_path)
original_has_text = text_original and len(text_original) > 50
original_has_text = text_original is not None and len(text_original) > 50
else:
text_original = None
original_has_text = False
# If the original has text, and the user doesn't want an archive,
# we're done here
if settings.OCR_MODE == "skip_noarchive" and original_has_text:
self.log("debug", "Document has text, skipping OCRmyPDF entirely.")
self.text = text_original
return
# Either no text was in the original or there should be an archive
# file created, so OCR the file and create an archive with any
# test located via OCR
import ocrmypdf
from ocrmypdf import InputFileError, EncryptedPdfError
@@ -276,9 +282,7 @@ class RasterisedDocumentParser(DocumentParser):
self.log("debug", f"Calling OCRmyPDF with args: {args}")
ocrmypdf.ocr(**args)
# Only create archive file if archiving isn't being skipped
if settings.OCR_MODE != "skip_noarchive":
self.archive_path = archive_path
self.archive_path = archive_path
self.text = self.extract_text(sidecar_file, archive_path)