#!/usr/bin/python2
# -*- coding: utf-8 -*-

# Copyright (C) 2015 Michael Weghorn <m.weghorn@posteo.de>
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.

# You should have received a copy of the GNU General Public License
# along with this program.  If not, see <http://www.gnu.org/licenses/>.

import os
import re
import subprocess
import sys

# TODO adjust as necessary
# This must be a directory to which CUPS has the permission to write.
BASEPATH = '/var/spool/cups'

# end of PDF file followed by start of next PDF file
re_eof = re.compile("\n*%%EOF\n*%PDF-")

# args: job-id user title copies options [file]
arg_count = len(sys.argv)

if arg_count == 1:
    # TODO print information as specified, s. 'man backend'
    exit(0)

if arg_count < 6 or arg_count > 7:
    print("Usage: {} job-id user title copies options [file]".format(
        sys.argv[0]))
    exit(1)

if arg_count == 7:
    filename = sys.argv[6]
    with open(filename) as source:
        content = source.read()
else:
    content = sys.stdin.read()

# extract single PDF documents from the input
docs = re_eof.split(content)
if "" in docs:
    docs.remove("")

document_names = []
# write out the single PDF documents
for i in range(0, len(docs)):
    filename = "out{}.pdf".format(i)
    filename = os.path.join(BASEPATH, filename)
    document_names.append(filename)
    with open(filename, "w") as outfile:
        file_content = docs[i] + "\n%%EOF\n"
        # restore PDF "header" for all PDF documents except for the first
        # which still has the original one
        if i != 0:
            file_content = "%PDF-" + file_content
        outfile.write(file_content)

# merge all documents using pdftk
outfile_name = os.path.join(BASEPATH, 'result.pdf')
subprocess.call(["pdftk"] + document_names + ["cat", "output", outfile_name])