def test_leptonica_compile(tmpdir):
from ocrmypdf.lib.compile_leptonica import ffibuilder
# Compile the library but build it somewhere that won't interfere with
# existing compiled library. Also compile in API mode so that we test
# the interfaces, even though we use it ABI mode.
ffibuilder.compile(tmpdir=fspath(tmpdir),
target=fspath(tmpdir / 'lepttest.*'))
def test_srgb_in_unicode_path(tmpdir):
"""Test that we can produce pdfmark when install path is not ASCII"""
dstdir = Path(fspath(tmpdir)) / b'\xe4\x80\x80'.decode('utf-8')
dstdir.mkdir()
dst = dstdir / 'sRGB.icc'
copyfile(SRGB_ICC_PROFILE, fspath(dst))
with patch('ocrmypdf.pdfa.SRGB_ICC_PROFILE', new=str(dst)):
generate_pdfa_ps(dstdir / 'out.ps', {})
def test_no_languages(ensure_tess4, tmpdir):
env = ensure_tess4
(tmpdir / 'tessdata').mkdir()
env['TESSDATA_PREFIX'] = fspath(tmpdir)
with modified_os_environ(env):
with pytest.raises(MissingDependencyError):
tesseract.languages.cache_clear()
tesseract.languages()
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',
'10',
'--optimize',
'3',
env=spoof_tesseract_noop)
pdf = pikepdf.open(outdir / 'out.pdf')
pim = pikepdf.PdfImage(next(iter(pdf.pages[0].images.values())))
assert pim.filters[0] == '/JBIG2Decode'
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 make_rotate_test(prefix, image_angle, page_angle):
im = Image.open(fspath(resources / 'typewriter.png'))
if image_angle != 0:
ccw_angle = -image_angle % 360
im = im.transpose(getattr(Image, 'ROTATE_{}'.format(ccw_angle)))
memimg = BytesIO()
im.save(memimg, format='PNG')
memimg.seek(0)
mempdf = BytesIO()
img2pdf.convert(memimg.read(),
layout_fun=img2pdf.get_fixed_dpi_layout_fun(
(200, 200)),
outputstream=mempdf)
mempdf.seek(0)
pike = pikepdf.open(mempdf)
pike.pages[0].Rotate = page_angle
target = outdir / '{}_{}_{}.pdf'.format(prefix, image_angle,
page_angle)
pike.save(target)
return target