mirror of
https://github.com/ocrmypdf/OCRmyPDF.git
synced 2026-05-05 05:05:44 -04:00
6ff6c8614f
This currently distorts the output size because Tesseract assumes it knows the DPI better than we do. Does not work for Ghostscript, because it emerges that Ghostscript honors /UserUnit for rasterizing but not in pdfwrite (resolve/wontfix). https://bugs.ghostscript.com/show_bug.cgi?id=690781 Ghostscript’s output would need to be patched in a PDF/A safe way for this to work. Temporary route may be to block Ghostscript if /UserUnit.
131 lines
4.1 KiB
Python
131 lines
4.1 KiB
Python
#!/usr/bin/env python3
|
|
# © 2015 James R. Barlow: github.com/jbarlow83
|
|
|
|
from tempfile import NamedTemporaryFile
|
|
from subprocess import run, PIPE, STDOUT, CalledProcessError
|
|
from shutil import copy
|
|
from functools import lru_cache
|
|
import re
|
|
import sys
|
|
from . import get_program
|
|
from ..exceptions import SubprocessOutputError
|
|
|
|
|
|
@lru_cache(maxsize=1)
|
|
def version():
|
|
args_gs = [
|
|
get_program('gs'),
|
|
'--version'
|
|
]
|
|
try:
|
|
version = check_output(
|
|
args_gs, close_fds=True, universal_newlines=True,
|
|
stderr=STDOUT)
|
|
except CalledProcessError as e:
|
|
print("Could not find Ghostscript executable on system PATH.",
|
|
file=sys.stderr)
|
|
raise MissingDependencyError from e
|
|
|
|
return version.strip()
|
|
|
|
|
|
def _gs_error_reported(stream):
|
|
return re.search(r'error', stream, flags=re.IGNORECASE)
|
|
|
|
|
|
def rasterize_pdf(input_file, output_file, xres, yres, raster_device, log,
|
|
pageno=1):
|
|
with NamedTemporaryFile(delete=True) as tmp:
|
|
args_gs = [
|
|
get_program('gs'),
|
|
'-dQUIET',
|
|
'-dSAFER',
|
|
'-dBATCH',
|
|
'-dNOPAUSE',
|
|
'-sDEVICE=%s' % raster_device,
|
|
'-dFirstPage=%i' % pageno,
|
|
'-dLastPage=%i' % pageno,
|
|
'-o', tmp.name,
|
|
'-r{0}x{1}'.format(str(round(xres)), str(round(yres))),
|
|
input_file
|
|
]
|
|
|
|
p = run(args_gs, stdout=PIPE, stderr=STDOUT,
|
|
universal_newlines=True)
|
|
if _gs_error_reported(p.stdout):
|
|
log.error(p.stdout)
|
|
else:
|
|
log.debug(p.stdout)
|
|
|
|
if p.returncode == 0:
|
|
copy(tmp.name, output_file)
|
|
else:
|
|
log.error('Ghostscript rasterizing failed')
|
|
raise SubprocessOutputError()
|
|
|
|
|
|
def generate_pdfa(*, pdf_version, pdf_pages, output_file, compression, log,
|
|
threads=1):
|
|
compression_args = []
|
|
if compression == 'jpeg':
|
|
compression_args = [
|
|
"-dAutoFilterColorImages=false",
|
|
"-dColorImageFilter=/DCTEncode",
|
|
"-dAutoFilterGrayImages=false",
|
|
"-dGrayImageFilter=/DCTEncode",
|
|
]
|
|
elif compression == 'lossless':
|
|
compression_args = [
|
|
"-dAutoFilterColorImages=false",
|
|
"-dColorImageFilter=/FlateEncode",
|
|
"-dAutoFilterGrayImages=false",
|
|
"-dGrayImageFilter=/FlateEncode",
|
|
]
|
|
else:
|
|
compression_args = [
|
|
"-dAutoFilterColorImages=true",
|
|
"-dAutoFilterGrayImages=true",
|
|
]
|
|
|
|
with NamedTemporaryFile(delete=True) as gs_pdf:
|
|
args_gs = [
|
|
get_program("gs"),
|
|
"-dQUIET",
|
|
"-dBATCH",
|
|
"-dNOPAUSE",
|
|
'-dCompatibilityLevel=' + str(pdf_version),
|
|
'-dNumRenderingThreads=' + str(threads),
|
|
"-sDEVICE=pdfwrite",
|
|
"-dAutoRotatePages=/None",
|
|
"-sColorConversionStrategy=/RGB",
|
|
"-sProcessColorModel=DeviceRGB"
|
|
] + compression_args + [
|
|
"-dJPEGQ=95",
|
|
"-dPDFA=2",
|
|
"-dPDFACompatibilityPolicy=1",
|
|
"-sOutputFile=" + gs_pdf.name,
|
|
]
|
|
args_gs.extend(pdf_pages)
|
|
p = run(args_gs, stdout=PIPE, stderr=STDOUT,
|
|
universal_newlines=True)
|
|
|
|
if _gs_error_reported(p.stdout):
|
|
log.error(p.stdout)
|
|
elif 'overprint mode not set' in p.stdout:
|
|
# Unless someone is going to print PDF/A documents on a
|
|
# magical sRGB printer I can't see the removal of overprinting
|
|
# being a problem....
|
|
log.debug(
|
|
"Ghostscript had to remove PDF 'overprinting' from the "
|
|
"input file to complete PDF/A conversion. "
|
|
)
|
|
else:
|
|
log.debug(p.stdout)
|
|
|
|
if p.returncode == 0:
|
|
# Ghostscript does not change return code when it fails to create
|
|
# PDF/A - check PDF/A status elsewhere
|
|
copy(gs_pdf.name, output_file)
|
|
else:
|
|
log.error('Ghostscript PDF/A rendering failed')
|
|
raise SubprocessOutputError() |