paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-04-09 09:58:20 -05:00
Code Issues Packages Projects Releases Wiki Activity

Let convert handle the removal of the alpha channel

Browse Source
This commit is contained in:
Trenton H 2023-01-02 14:20:46 -08:00
parent 24ce1830eb
commit 59e0c1fe4e
1 changed files with 13 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
src/paperless_tesseract/parsers.py
View File

@ -1,6 +1,7 @@
import json import json
import os import os
import re import re
import subprocess
from pathlib import Path from pathlib import Path
from typing import Optional from typing import Optional
@ -79,6 +80,17 @@ class RasterisedDocumentParser(DocumentParser):
with Image.open(image) as im: with Image.open(image) as im:
return im.mode in ("RGBA", "LA") return im.mode in ("RGBA", "LA")
def remove_alpha(self, image_path: str):
subprocess.run(
[
settings.CONVERT_BINARY,
"-alpha",
"off",
image_path,
image_path,
],
)
def get_dpi(self, image): def get_dpi(self, image):
try: try:
with Image.open(image) as im: with Image.open(image) as im:
@ -230,11 +242,7 @@ class RasterisedDocumentParser(DocumentParser):
f"Removing alpha layer from {input_file} " f"Removing alpha layer from {input_file} "
"for compatibility with img2pdf", "for compatibility with img2pdf",
) )
with Image.open(input_file) as im: self.remove_alpha(input_file)
background = Image.new("RGBA", im.size, (255, 255, 255))
background.alpha_composite(im)
background = background.convert("RGB")
background.save(input_file, format=im.format)
if dpi: if dpi:
self.log("debug", f"Detected DPI for image {input_file}: {dpi}") self.log("debug", f"Detected DPI for image {input_file}: {dpi}")