paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-04-02 13:45:10 -05:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #133 from muellermartin/fix-png-alpha

Browse Source 
Remove alpha layer from PNG files for img2pdf
This commit is contained in:
Alexander Bauer 2022-02-22 20:02:18 -05:00 committed by GitHub
commit dbdd9b93f8
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 22 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
src/paperless_tesseract/parsers.py
View File

@ -66,6 +66,10 @@ class RasterisedDocumentParser(DocumentParser):
"image/gif",
]
def has_alpha(self, image):
with Image.open(image) as im:
return im.mode in ('RGBA', 'LA')
def get_dpi(self, image):
try:
with Image.open(image) as im:
@ -182,6 +186,19 @@ class RasterisedDocumentParser(DocumentParser):
if self.is_image(mime_type):
dpi = self.get_dpi(input_file)
a4_dpi = self.calculate_a4_dpi(input_file)
if self.has_alpha(input_file):
self.log(
"info",
f"Removing alpha layer from {input_file} "
"for compatibility with img2pdf"
)
with Image.open(input_file) as im:
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:
self.log(
"debug",

9
src/paperless_tesseract/tests/test_parser.py
View File

@ -181,13 +181,14 @@ class TestParser(DirectoriesMixin, TestCase):
self.assertContainsStrings(parser.get_text(), ["This is a test document."])
def test_image_simple_alpha_fail(self):
def test_image_simple_alpha(self):
parser = RasterisedDocumentParser(None)
def f():
parser.parse(os.path.join(self.SAMPLE_FILES, "simple-alpha.png"), "image/png")
parser.parse(os.path.join(self.SAMPLE_FILES, "simple-alpha.png"), "image/png")
self.assertRaises(ParseError, f)
self.assertTrue(os.path.isfile(parser.archive_path))
self.assertContainsStrings(parser.get_text(), ["This is a test document."])
def test_image_calc_a4_dpi(self):
parser = RasterisedDocumentParser(None)