mirror of
https://github.com/ocrmypdf/OCRmyPDF.git
synced 2025-06-26 23:49:59 +00:00
83 lines
2.6 KiB
Python
83 lines
2.6 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 pathlib import Path
|
|
|
|
import pytest
|
|
import logging
|
|
|
|
from PIL import Image
|
|
|
|
import pikepdf
|
|
|
|
from ocrmypdf import optimize as opt
|
|
from ocrmypdf.exec.ghostscript import rasterize_pdf
|
|
from ocrmypdf.exec import jbig2enc
|
|
from ocrmypdf.helpers import fspath
|
|
|
|
|
|
check_ocrmypdf = pytest.helpers.check_ocrmypdf
|
|
|
|
|
|
@pytest.mark.parametrize('pdf', ['multipage.pdf', 'palette.pdf'])
|
|
def test_basic(resources, pdf, outpdf):
|
|
infile = resources / pdf
|
|
opt.main(infile, outpdf, level=3)
|
|
|
|
assert Path(outpdf).stat().st_size <= Path(infile).stat().st_size
|
|
|
|
|
|
def test_mono_not_inverted(resources, outdir):
|
|
infile = resources / '2400dpi.pdf'
|
|
opt.main(infile, outdir / 'out.pdf', level=3)
|
|
|
|
rasterize_pdf(
|
|
outdir / 'out.pdf', outdir / 'im.png',
|
|
xres=10, yres=10, raster_device='pnggray',
|
|
log=logging.getLogger(name='test_mono_flip')
|
|
)
|
|
|
|
im = Image.open(fspath(outdir / 'im.png'))
|
|
assert im.getpixel((0, 0)) == 255, "Expected white background"
|
|
|
|
|
|
def test_jpg_png_params(resources, outpdf, spoof_tesseract_noop):
|
|
check_ocrmypdf(
|
|
resources / 'crom.png', outpdf, '--image-dpi', '200',
|
|
'--optimize', '3', '--jpg-quality', '50', '--png-quality', '20',
|
|
env=spoof_tesseract_noop
|
|
)
|
|
|
|
|
|
@pytest.mark.skipif(not jbig2enc.available(), reason='need jbig2enc')
|
|
@pytest.mark.parametrize('optimize', ['2', '3'])
|
|
def test_jbig2(optimize, resources, outpdf, spoof_tesseract_noop):
|
|
check_ocrmypdf(
|
|
resources / 'ccitt.pdf', outpdf, '--image-dpi', '200',
|
|
'--optimize', optimize, '--jpg-quality', '50', '--png-quality', '20',
|
|
env=spoof_tesseract_noop
|
|
)
|
|
|
|
pdf = pikepdf.open(outpdf)
|
|
pim = pikepdf.PdfImage(next(iter(pdf.pages[0].images.values())))
|
|
assert pim.filters[0] == '/JBIG2Decode'
|
|
|
|
if optimize == '3':
|
|
assert '/JBIG2Globals' in pim.decode_parms[0]
|
|
else:
|
|
assert len(pim.decode_parms) == 0
|