def extract_image_jbig2(*, pike: pikepdf.Pdf, root: Path, image: Object,
xref: Xref, options) -> Optional[XrefExt]:
result = extract_image_filter(pike, root, image, xref)
if result is None:
return None
pim, filtdp = result
if (pim.bits_per_component == 1 and filtdp[0] != Name.JBIG2Decode
and jbig2enc.available()):
# Save any colorspace associated with the image, so that we
# will export a pure 1-bit PNG with no palette or ICC profile.
# Showing the palette or ICC to jbig2enc will cause it to perform
# colorspace transform to 1bpp, which will conflict the palette or
# ICC if it exists.
colorspace = pim.obj.get(pikepdf.Name.ColorSpace, None)
if colorspace is not None or pim.image_mask:
try:
# Set to DeviceGray temporarily; we already in 1 bpc.
pim.obj.ColorSpace = pikepdf.Name.DeviceGray
imgname = root / f'{xref:08d}'
with imgname.open('wb') as f:
ext = pim.extract_to(stream=f)
imgname.rename(imgname.with_suffix(ext))
except pikepdf.UnsupportedImageTypeError:
return None
finally:
# Restore image colorspace after temporarily setting it to DeviceGray
if colorspace is not None:
pim.obj.ColorSpace = colorspace
else:
del pim.obj.ColorSpace
return XrefExt(xref, ext)
return None
def report_output_file_size(options, input_file, output_file):
try:
output_size = Path(output_file).stat().st_size
input_size = Path(input_file).stat().st_size
except FileNotFoundError:
return # Outputting to stream or something
with pikepdf.open(output_file) as p:
# Overhead constants obtained by estimating amount of data added by OCR
# PDF/A conversion, and possible XMP metadata addition, with compression
FILE_OVERHEAD = 4000
OCR_PER_PAGE_OVERHEAD = 3000
reasonable_overhead = FILE_OVERHEAD + OCR_PER_PAGE_OVERHEAD * len(
p.pages)
ratio = output_size / input_size
reasonable_ratio = output_size / (input_size + reasonable_overhead)
if reasonable_ratio < 1.35 or input_size < 25000:
return # Seems fine
reasons = []
image_preproc = {
'deskew',
'clean_final',
'remove_background',
'oversample',
'force_ocr',
}
for arg in image_preproc:
if getattr(options, arg, False):
reasons.append(
f"The argument --{arg.replace('_', '-')} was issued, causing transcoding."
)
if options.optimize == 0:
reasons.append("Optimization was disabled.")
else:
image_optimizers = {
'jbig2': jbig2enc.available(),
'pngquant': pngquant.available(),
}
for name, available in image_optimizers.items():
if not available:
reasons.append(
f"The optional dependency '{name}' was not found, so some image "
f"optimizations could not be attempted.")
if options.output_type.startswith('pdfa'):
reasons.append(
"PDF/A conversion was enabled. (Try `--output-type pdf`.)")
if options.plugins:
reasons.append("Plugins were used.")
if reasons:
explanation = "Possible reasons for this include:\n" + '\n'.join(
reasons) + "\n"
else:
explanation = "No reason for this increase is known. Please report this issue."
log.warning(
f"The output file size is {ratio:.2f}× larger than the input file.\n"
f"{explanation}")
def extract_image_jbig2(*, pike: pikepdf.Pdf, root: Path, image: Object,
xref: Xref, options) -> Optional[XrefExt]:
result = extract_image_filter(pike, root, image, xref)
if result is None:
return None
pim, filtdp = result
if (pim.bits_per_component == 1 and filtdp[0] != Name.JBIG2Decode
and jbig2enc.available()):
try:
imgname = root / f'{xref:08d}'
with imgname.open('wb') as f:
ext = pim.extract_to(stream=f)
imgname.rename(imgname.with_suffix(ext))
except pikepdf.UnsupportedImageTypeError:
return None
return XrefExt(xref, ext)
return None
resources / 'crom.png',
outpdf,
'--image-dpi',
'200',
'--optimize',
'3',
'--jpg-quality',
'50',
'--png-quality',
'20',
'--plugin',
'tests/plugins/tesseract_noop.py',
)
@pytest.mark.skipif(not jbig2enc.available(), reason='need jbig2enc')
@pytest.mark.parametrize('lossy', [False, True])
def test_jbig2_lossy(lossy, resources, outpdf):
args = [
resources / 'ccitt.pdf',
outpdf,
'--image-dpi',
'200',
'--optimize',
3,
'--jpg-quality',
'50',
'--png-quality',
'20',
'--plugin',
'tests/plugins/tesseract_noop.py',
import img2pdf
import pikepdf
import pytest
from PIL import Image, ImageDraw
from ocrmypdf import optimize as opt
from ocrmypdf._exec import jbig2enc, pngquant
from ocrmypdf._exec.ghostscript import rasterize_pdf
from ocrmypdf.helpers import Resolution
from .conftest import check_ocrmypdf
needs_pngquant = pytest.mark.skipif(not pngquant.available(),
reason="pngquant not installed")
needs_jbig2enc = pytest.mark.skipif(not jbig2enc.available(),
reason="jbig2enc not installed")
@needs_pngquant
@pytest.mark.parametrize('pdf', ['multipage.pdf', 'palette.pdf'])
def test_basic(resources, pdf, outpdf):
infile = resources / pdf
opt.main(infile, outpdf, level=3)
assert 0.98 * Path(outpdf).stat().st_size <= Path(infile).stat().st_size
@needs_pngquant
def test_mono_not_inverted(resources, outdir):
infile = resources / '2400dpi.pdf'
