amorfo77/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2026-08-01 16:42:18 +00:00
Code Issues Projects Releases Wiki Activity

Fix: don't skip OCR/archive for tagged PDFs with no actual text (#13351)

Browse Source
This commit is contained in:
Trenton H
2026-07-27 16:52:29 -07:00
committed by GitHub
parent 7eee8538ec
commit dcff067dc1
5 changed files with 47 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/documents/consumer.py
+3 -2
View File
@@ -160,13 +160,14 @@ def should_produce_archive(
_log.debug("Archive: yes — image document, ARCHIVE_FILE_GENERATION=auto")
return True
if mime_type == "application/pdf":
if is_tagged_pdf(document_path):
text = extract_pdf_text(document_path)
has_text = text is not None and len(text) > 0
if has_text and is_tagged_pdf(document_path):
_log.debug(
"Archive: no — born-digital PDF (structure tags detected),"
" ARCHIVE_FILE_GENERATION=auto",
)
return False
text = extract_pdf_text(document_path)
if text is None or len(text) <= PDF_TEXT_MIN_LENGTH:
_log.debug(
"Archive: yes — scanned PDF (text_length=%d ≤ %d),"