smokephil/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-12-16 03:26:50 +01:00
Code Issues Projects Releases Packages Wiki Activity

Updates to provide the user provided max pixel size to ocrmypdf

Browse source
This commit is contained in:
Trenton Holmes 2022-05-22 16:56:08 -07:00
parent feaf2da834
commit fc26fe0ac0
No known key found for this signature in database
GPG key ID: 4815A6E23A56B8D1
3 changed files with 23 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

20
src/paperless_tesseract/parsers.py
View file

@ -8,8 +8,6 @@ from documents.parsers import make_thumbnail_from_pdf
from documents.parsers import ParseError
from PIL import Image
Image.MAX_IMAGE_PIXELS = settings.OCR_MAX_IMAGE_PIXELS
class NoTextFoundException(Exception):
pass
@ -225,6 +223,24 @@ class RasterisedDocumentParser(DocumentParser):
f"they will not be used. Error: {e}",
)
if settings.OCR_MAX_IMAGE_PIXELS is not None:
# Convert pixels to mega-pixels and provide to ocrmypdf
max_pixels_mpixels = settings.OCR_MAX_IMAGE_PIXELS / 1_000_000.0
if max_pixels_mpixels > 0:
self.log(
"debug",
f"Calculated {max_pixels_mpixels} megapixels for OCR",
)
ocrmypdf_args["max_image_mpixels"] = max_pixels_mpixels
else:
self.log(
"warning",
"There is an issue with PAPERLESS_OCR_MAX_IMAGE_PIXELS, "
"this value must be at least 1 megapixel if set",
)
return ocrmypdf_args
def parse(self, document_path, mime_type, file_name=None):