James R. Barlow
b27b92fbf3
If the color count of an image is low such as when black and white documents are scanned in color, PNG with lossy quantization may produce a superior encoding to JPEG. This is expensive to test however.
71 lines
1.9 KiB
Python
71 lines
1.9 KiB
Python
# © 2018 James R. Barlow: github.com/jbarlow83
|
|
#
|
|
# This file is part of OCRmyPDF.
|
|
#
|
|
# OCRmyPDF is free software: you can redistribute it and/or modify
|
|
# it under the terms of the GNU General Public License as published by
|
|
# the Free Software Foundation, either version 3 of the License, or
|
|
# (at your option) any later version.
|
|
#
|
|
# OCRmyPDF is distributed in the hope that it will be useful,
|
|
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
# GNU General Public License for more details.
|
|
#
|
|
# You should have received a copy of the GNU General Public License
|
|
# along with OCRmyPDF. If not, see <http://www.gnu.org/licenses/>.
|
|
|
|
from functools import lru_cache
|
|
from subprocess import run
|
|
from tempfile import NamedTemporaryFile
|
|
|
|
from PIL import Image
|
|
|
|
from . import get_version
|
|
from ..exceptions import MissingDependencyError
|
|
|
|
|
|
@lru_cache(maxsize=1)
|
|
def version():
|
|
return get_version('pngquant', regex=r'(\d+(\.\d+)*).*')
|
|
|
|
|
|
def available():
|
|
try:
|
|
version()
|
|
except MissingDependencyError:
|
|
return False
|
|
return True
|
|
|
|
|
|
def quantize(input_file, output_file, quality_min, quality_max):
|
|
if input_file.endswith('.jpg'):
|
|
im = Image.open(input_file)
|
|
with NamedTemporaryFile(suffix='.png') as tmp:
|
|
im.save(tmp)
|
|
args = [
|
|
'pngquant',
|
|
'--force',
|
|
'--skip-if-larger',
|
|
'--output',
|
|
output_file,
|
|
'--quality',
|
|
f'{quality_min}-{quality_max}',
|
|
'--',
|
|
tmp.name,
|
|
]
|
|
run(args)
|
|
else:
|
|
args = [
|
|
'pngquant',
|
|
'--force',
|
|
'--skip-if-larger',
|
|
'--output',
|
|
output_file,
|
|
'--quality',
|
|
f'{quality_min}-{quality_max}',
|
|
'--',
|
|
input_file,
|
|
]
|
|
run(args)
|