def test_remove_background(spoof_tesseract_noop, resources, outdir):
from PIL import Image
# Ensure the input image does not contain pure white/black
im = Image.open(resources / 'congress.jpg')
assert im.getextrema() != ((0, 255), (0, 255), (0, 255))
output_pdf = check_ocrmypdf(resources / 'congress.jpg',
outdir / 'test_remove_bg.pdf',
'--remove-background',
'--image-dpi',
'150',
env=spoof_tesseract_noop)
log = logging.getLogger()
output_png = outdir / 'remove_bg.png'
ghostscript.rasterize_pdf(output_pdf,
output_png,
xres=100,
yres=100,
raster_device='png16m',
log=log,
pageno=1)
# The output image should contain pure white and black
im = Image.open(output_png)
assert im.getextrema() == ((0, 255), (0, 255), (0, 255))
def test_deskew(spoof_tesseract_noop, resources, outdir):
# Run with deskew
deskewed_pdf = check_ocrmypdf(resources / 'skew.pdf',
outdir / 'skew.pdf',
'-d',
env=spoof_tesseract_noop)
# Now render as an image again and use Leptonica to find the skew angle
# to confirm that it was deskewed
log = logging.getLogger()
deskewed_png = outdir / 'deskewed.png'
ghostscript.rasterize_pdf(deskewed_pdf,
deskewed_png,
xres=150,
yres=150,
raster_device='pngmono',
log=log,
pageno=1)
from ocrmypdf.leptonica import Pix
pix = Pix.read(str(deskewed_png))
skew_angle, skew_confidence = pix.find_skew()
print(skew_angle)
assert -0.5 < skew_angle < 0.5, "Deskewing failed"
def test_deskew(spoof_tesseract_noop, resources, outdir):
# Run with deskew
deskewed_pdf = check_ocrmypdf(
resources / 'skew.pdf', outdir / 'skew.pdf', '-d',
env=spoof_tesseract_noop)
# Now render as an image again and use Leptonica to find the skew angle
# to confirm that it was deskewed
log = logging.getLogger()
deskewed_png = outdir / 'deskewed.png'
ghostscript.rasterize_pdf(
deskewed_pdf,
deskewed_png,
xres=150,
yres=150,
raster_device='pngmono',
log=log,
pageno=1)
from ocrmypdf.leptonica import Pix
pix = Pix.read(str(deskewed_png))
skew_angle, skew_confidence = pix.find_skew()
print(skew_angle)
assert -0.5 < skew_angle < 0.5, "Deskewing failed"
def rasterize(pdf, pageno, png):
if png.exists():
print(png)
return
ghostscript.rasterize_pdf(
pdf, png, xres=100, yres=100,
raster_device='pngmono', log=gslog, pageno=pageno)
def test_rasterize_rotated(linn, outdir, caplog):
path, pdf = linn
page_size_pts = (pdf.pages[0].MediaBox[2], pdf.pages[0].MediaBox[3])
assert pdf.pages[0].MediaBox[0] == pdf.pages[0].MediaBox[1] == 0
page_size = (page_size_pts[0] / Decimal(72),
page_size_pts[1] / Decimal(72))
target_size = Decimal('200.0'), Decimal('150.0')
target_dpi = 42.0, 4242.0
log = logging.getLogger()
caplog.set_level(logging.DEBUG)
rasterize_pdf(
path,
outdir / 'out.png',
target_size[0] / page_size[0],
target_size[1] / page_size[1],
raster_device='pngmono',
log=log,
page_dpi=target_dpi,
rotation=90,
)
with Image.open(outdir / 'out.png') as im:
assert im.size == (target_size[1], target_size[0])
assert im.info['dpi'] == (target_dpi[1], target_dpi[0])
def rasterize(pdf, pageno, png):
if png.exists():
print(png)
return
ghostscript.rasterize_pdf(
pdf, png, xres=100, yres=100,
raster_device='pngmono', log=gslog, pageno=pageno)
def test_remove_background(spoof_tesseract_noop, resources, outdir):
from PIL import Image
# Ensure the input image does not contain pure white/black
im = Image.open(resources / 'congress.jpg')
assert im.getextrema() != ((0, 255), (0, 255), (0, 255))
output_pdf = check_ocrmypdf(
resources / 'congress.jpg',
outdir / 'test_remove_bg.pdf',
'--remove-background',
'--image-dpi', '150',
env=spoof_tesseract_noop)
log = logging.getLogger()
output_png = outdir / 'remove_bg.png'
ghostscript.rasterize_pdf(
output_pdf,
output_png,
xres=100,
yres=100,
raster_device='png16m',
log=log,
pageno=1)
# The output image should contain pure white and black
im = Image.open(output_png)
assert im.getextrema() == ((0, 255), (0, 255), (0, 255))
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_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_rasterize_size(linn, outdir, caplog):
path, pdf = linn
page_size_pts = (pdf.pages[0].MediaBox[2], pdf.pages[0].MediaBox[3])
assert pdf.pages[0].MediaBox[0] == pdf.pages[0].MediaBox[1] == 0
page_size = (page_size_pts[0] / Decimal(72), page_size_pts[1] / Decimal(72))
target_size = Decimal('200.0'), Decimal('150.0')
target_dpi = 42.0, 4242.0
log = logging.getLogger()
rasterize_pdf(
path,
outdir / 'out.png',
target_size[0] / page_size[0],
target_size[1] / page_size[1],
raster_device='pngmono',
log=log,
page_dpi=target_dpi,
)
with Image.open(outdir / 'out.png') as im:
assert im.size == target_size
assert im.info['dpi'] == target_dpi
def test_rasterize_size(francais, outdir, caplog):
path, pdf = francais
page_size_pts = (pdf.pages[0].MediaBox[2], pdf.pages[0].MediaBox[3])
assert pdf.pages[0].MediaBox[0] == pdf.pages[0].MediaBox[1] == 0
page_size = (page_size_pts[0] / Decimal(72),
page_size_pts[1] / Decimal(72))
target_size = Decimal('50.0'), Decimal('30.0')
forced_dpi = 42.0, 4242.0
log = logging.getLogger()
rasterize_pdf(
path,
outdir / 'out.png',
target_size[0] / page_size[0],
target_size[1] / page_size[1],
raster_device='pngmono',
log=log,
page_dpi=forced_dpi,
)
with Image.open(outdir / 'out.png') as im:
assert im.size == target_size
assert im.info['dpi'] == forced_dpi
