if lossy:
args.append('--jbig2-lossy')
check_ocrmypdf(*args, env=spoof_tesseract_noop)
pdf = pikepdf.open(outpdf)
pim = pikepdf.PdfImage(next(iter(pdf.pages[0].images.values())))
assert pim.filters[0] == '/JBIG2Decode'
if lossy:
assert '/JBIG2Globals' in pim.decode_parms[0]
else:
assert len(pim.decode_parms) == 0
@pytest.mark.skipif(not jbig2enc.available() or not pngquant.available(),
reason='need jbig2enc and pngquant')
def test_flate_to_jbig2(resources, outdir, spoof_tesseract_noop):
# This test requires an image that pngquant is capable of converting to
# to 1bpp - so use an existing 1bpp image, convert up, confirm it can
# convert down
im = Image.open(fspath(resources / 'typewriter.png'))
assert im.mode in ('1', 'P')
im = im.convert('L')
im.save(fspath(outdir / 'type8.png'))
check_ocrmypdf(outdir / 'type8.png',
outdir / 'out.pdf',
'--image-dpi',
'100',
'--png-quality',
args.append('--jbig2-lossy')
check_ocrmypdf(*args, env=spoof_tesseract_noop)
pdf = pikepdf.open(outpdf)
pim = pikepdf.PdfImage(next(iter(pdf.pages[0].images.values())))
assert pim.filters[0] == '/JBIG2Decode'
if lossy:
assert '/JBIG2Globals' in pim.decode_parms[0]
else:
assert len(pim.decode_parms) == 0
@pytest.mark.skipif(
not jbig2enc.available() or not pngquant.available(),
reason='need jbig2enc and pngquant',
)
def test_flate_to_jbig2(resources, outdir, spoof_tesseract_noop):
# This test requires an image that pngquant is capable of converting to
# to 1bpp - so use an existing 1bpp image, convert up, confirm it can
# convert down
im = Image.open(fspath(resources / 'typewriter.png'))
assert im.mode in ('1', 'P')
im = im.convert('L')
im.save(fspath(outdir / 'type8.png'))
check_ocrmypdf(
outdir / 'type8.png',
outdir / 'out.pdf',
'--image-dpi',
args.append('--jbig2-lossy')
check_ocrmypdf(*args, env=spoof_tesseract_noop)
pdf = pikepdf.open(outpdf)
pim = pikepdf.PdfImage(next(iter(pdf.pages[0].images.values())))
assert pim.filters[0] == '/JBIG2Decode'
if lossy:
assert '/JBIG2Globals' in pim.decode_parms[0]
else:
assert len(pim.decode_parms) == 0
@pytest.mark.skipif(
not jbig2enc.available() or not pngquant.available(),
reason='need jbig2enc and pngquant',
)
def test_flate_to_jbig2(resources, outdir, spoof_tesseract_noop):
# This test requires an image that pngquant is capable of converting to
# to 1bpp - so use an existing 1bpp image, convert up, confirm it can
# convert down
im = Image.open(fspath(resources / 'typewriter.png'))
assert im.mode in ('1', 'P')
im = im.convert('L')
im.save(fspath(outdir / 'type8.png'))
check_ocrmypdf(
outdir / 'type8.png',
outdir / 'out.pdf',
'--image-dpi',
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_not_inverted'),
)
with Image.open(fspath(outdir / 'im.png')) as im:
assert im.getpixel((0, 0)) == 255, "Expected white background"
@pytest.mark.skipif(not pngquant.available(), reason='need pngquant')
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,
)