Jim Barlow
d7a9f3a2ab
What a pain getting Unicode right, but there it is. I cannot find anything to confirm that it is acceptable to put the PDF/A definition file at the end of the Ghostscript inputs. I did this because Ghostscript seems to copy document info from the last document on the list so reportlab's information "wins" in normal order, so it fixes that issue, and reportlab 'helpfully' fills in all of those fields even if it does not have information. It could also work to pass document information along to reportlab, and set it in each output PDF: .debug.pdf, .rendered.pdf, and .page.pdf to ensure that whatever page is last in the pipeline has the right information. Or perhaps it's possible to write a Postscript trailer that overwrites any previous docinfo with no side effects, but I can't find any information on how to do that. I don't think it's worth pursuing unless this arrangement causes some problem with PDF/A generation. On a minor note, Jhove misreads the way I have encoded the strings in producing its validation log. It reads them as UTF-16 little endian, so will tend to produce a string of Asian characters in place of the real data.
133 lines
4.4 KiB
Python
133 lines
4.4 KiB
Python
#!/usr/bin/env python3
|
|
# -*- coding: utf-8 -*-
|
|
#
|
|
# © 2015: jbarlow83 (https://github.com/jbarlow83)
|
|
#
|
|
# Generate a PDFA_def.ps file for Ghostscript >= 9.14
|
|
|
|
from __future__ import print_function, absolute_import, division
|
|
from string import Template
|
|
from subprocess import Popen, PIPE
|
|
import os
|
|
import codecs
|
|
|
|
|
|
# This is a template written in PostScript which is needed to create PDF/A
|
|
# files, from the Ghostscript documentation. Lines beginning with % are
|
|
# comments. Python substitution variables have a '$' prefix.
|
|
pdfa_def_template = u"""%!
|
|
% This is a sample prefix file for creating a PDF/A document.
|
|
% Feel free to modify entries marked with "Customize".
|
|
% This assumes an ICC profile to reside in the file (ISO Coated sb.icc),
|
|
% unless the user modifies the corresponding line below.
|
|
|
|
% Define entries in the document Info dictionary :
|
|
/ICCProfile ($icc_profile)
|
|
def
|
|
|
|
[ /Title <$title>
|
|
/Author <$author>
|
|
/Subject <$subject>
|
|
/Keywords <$keywords>
|
|
/DOCINFO pdfmark
|
|
|
|
% Define an ICC profile :
|
|
|
|
[/_objdef {icc_PDFA} /type /stream /OBJ pdfmark
|
|
[{icc_PDFA}
|
|
<<
|
|
/N currentpagedevice /ProcessColorModel known {
|
|
currentpagedevice /ProcessColorModel get dup /DeviceGray eq
|
|
{pop 1} {
|
|
/DeviceRGB eq
|
|
{3}{4} ifelse
|
|
} ifelse
|
|
} {
|
|
(ERROR, unable to determine ProcessColorModel) == flush
|
|
} ifelse
|
|
>> /PUT pdfmark
|
|
[{icc_PDFA} ICCProfile (r) file /PUT pdfmark
|
|
|
|
% Define the output intent dictionary :
|
|
|
|
[/_objdef {OutputIntent_PDFA} /type /dict /OBJ pdfmark
|
|
[{OutputIntent_PDFA} <<
|
|
/Type /OutputIntent % Must be so (the standard requires).
|
|
/S /GTS_PDFA1 % Must be so (the standard requires).
|
|
/DestOutputProfile {icc_PDFA} % Must be so (see above).
|
|
/OutputConditionIdentifier ($icc_identifier)
|
|
>> /PUT pdfmark
|
|
[{Catalog} <</OutputIntents [ {OutputIntent_PDFA} ]>> /PUT pdfmark
|
|
"""
|
|
|
|
|
|
def encode_text_string(s: str) -> str:
|
|
'''Encode text string to hex string for use in a PDF
|
|
|
|
From PDF 32000-1:2008 a string object may be included in hexademical form
|
|
if it is enclosed in angle brackets. For general Unicode the string should
|
|
be UTF-16 (big endian) with byte order marks. A non-hexademical
|
|
presentation is possible but this is preferable since it allows the output
|
|
Postscript file to be completely ASCII.
|
|
'''
|
|
if s == '':
|
|
return ''
|
|
utf16_bytes = s.encode('utf-16be')
|
|
ascii_hex_bytes = codecs.encode(b'\xfe\xff' + utf16_bytes, 'hex')
|
|
ascii_hex_str = ascii_hex_bytes.decode('ascii').lower()
|
|
return ascii_hex_str
|
|
|
|
|
|
def _get_pdfa_def(icc_profile, icc_identifier, pdfmark):
|
|
pdfmark_utf16 = {k: encode_text_string(v) for k, v in pdfmark.items()}
|
|
|
|
t = Template(pdfa_def_template)
|
|
result = t.substitute(icc_profile=icc_profile,
|
|
icc_identifier=icc_identifier,
|
|
title=pdfmark_utf16.get('title', ''),
|
|
author=pdfmark_utf16.get('author', ''),
|
|
subject=pdfmark_utf16.get('subject', ''),
|
|
keywords=pdfmark_utf16.get('keywords', ''))
|
|
print(result)
|
|
return result
|
|
|
|
|
|
def _get_postscript_icc_path():
|
|
"Parse Ghostscript's help message to find where iccprofiles are stored"
|
|
|
|
p_gs = Popen(['gs', '--help'], close_fds=True, universal_newlines=True,
|
|
stdout=PIPE, stderr=PIPE)
|
|
out, _ = p_gs.communicate()
|
|
lines = out.splitlines()
|
|
|
|
def search_paths(lines):
|
|
seeking = True
|
|
for line in lines:
|
|
if seeking:
|
|
if line.startswith('Search path'):
|
|
seeking = False
|
|
continue
|
|
else:
|
|
if line.strip().startswith('/'):
|
|
yield from (
|
|
path.strip() for path in line.split(':')
|
|
if path.strip() != '')
|
|
for root in search_paths(lines):
|
|
path = os.path.realpath(os.path.join(root, '../iccprofiles'))
|
|
if os.path.exists(path):
|
|
return path
|
|
|
|
|
|
def generate_pdfa_def(target_filename, pdfmark, icc='sRGB'):
|
|
if icc == 'sRGB':
|
|
icc_profile = os.path.join(_get_postscript_icc_path(), 'srgb.icc')
|
|
else:
|
|
raise NotImplementedError("Only supporting sRGB")
|
|
|
|
ps = _get_pdfa_def(icc_profile, icc, pdfmark)
|
|
|
|
# Since PostScript might not handle UTF-8 (it's hard to get a clear
|
|
# answer), insist on ascii
|
|
with open(target_filename, 'w', encoding='ascii') as f:
|
|
f.write(ps)
|