paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-04-29 11:09:27 -05:00
Code Issues Packages Projects Releases Wiki Activity

fix logging getting spammed with pdfminer warnings on JPG files

Browse Source
This commit is contained in:
jonaswinkler 2021-06-13 12:09:16 +02:00
parent a3dae02cfb
commit 1f707e86cc
1 changed files with 6 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
src/paperless_tesseract/parsers.py
View File

@ -214,8 +214,12 @@ class RasterisedDocumentParser(DocumentParser):
# This forces tesseract to use one core per page. # This forces tesseract to use one core per page.
os.environ['OMP_THREAD_LIMIT'] = "1" os.environ['OMP_THREAD_LIMIT'] = "1"
text_original = self.extract_text(None, document_path) if mime_type == "application/pdf":
original_has_text = text_original and len(text_original) > 50 text_original = self.extract_text(None, document_path)
original_has_text = text_original and len(text_original) > 50
else:
text_original = None
original_has_text = False
if settings.OCR_MODE == "skip_noarchive" and original_has_text: if settings.OCR_MODE == "skip_noarchive" and original_has_text:
self.log("debug", self.log("debug",