smokephil/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-12-06 06:45:05 +01:00
Code Issues Projects Releases Packages Wiki Activity

Updated the docstring to show what's actually happening

Browse source
This commit is contained in:
Daniel Quinn 2016-01-10 15:51:38 +00:00
parent 5b479c5058
commit 10a0556951
1 changed files with 5 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

11
src/documents/management/commands/consume.py
View file

@ -21,12 +21,11 @@ from documents.models import Document
class Command(BaseCommand):
"""
Loop over every file found in CONSUMPTION_DIR and:
1. Convert it to a greyscale tif
2. Convert it to a full-colour jpg
3. Use tesseract on the tif
4. Store the OCR'd text in the database along with the paths to the jpg
and original pdf
5. Delete the pdf and images
1. Convert it to a greyscale png
2. Use tesseract on the png
3. Encrypt and store the PDF in the MEDIA_ROOT
4. Store the OCR'd text in the database
5. Delete the pdf and image(s)
"""
LOOP_TIME = 10 # Seconds