smokephil/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-12-10 08:37:19 +01:00
Code Issues Projects Releases Packages Wiki Activity

Adds new setting to control color conversions (#4709)

Browse source
This commit is contained in:
Trenton H 2023-11-29 12:18:44 -08:00 • committed by GitHub
parent e1b573adeb
commit e3f4e0b775
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
3 changed files with 24 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

5
src/paperless/settings.py
View file

@ -864,6 +864,11 @@ OCR_MAX_IMAGE_PIXELS: Optional[int] = None
if os.environ.get("PAPERLESS_OCR_MAX_IMAGE_PIXELS") is not None:
OCR_MAX_IMAGE_PIXELS: int = int(os.environ.get("PAPERLESS_OCR_MAX_IMAGE_PIXELS"))
OCR_COLOR_CONVERSION_STRATEGY = os.getenv(
"PAPERLESS_OCR_COLOR_CONVERSION_STRATEGY",
"RGB",
)
OCR_USER_ARGS = os.getenv("PAPERLESS_OCR_USER_ARGS", "{}")
# GNUPG needs a home directory for some reason

5
src/paperless_tesseract/parsers.py
View file

@ -186,6 +186,11 @@ class RasterisedDocumentParser(DocumentParser):
"progress_bar": False,
}
if "pdfa" in ocrmypdf_args["output_type"]:
ocrmypdf_args[
"color_conversion_strategy"
] = settings.OCR_COLOR_CONVERSION_STRATEGY
if settings.OCR_MODE == "force" or safe_fallback:
ocrmypdf_args["force_ocr"] = True
elif settings.OCR_MODE in ["skip", "skip_noarchive"]: