oox/source/token/namespaces.py

   1 # This file is part of the LibreOffice project.
   2 #
   3 # This Source Code Form is subject to the terms of the Mozilla Public
   4 # License, v. 2.0. If a copy of the MPL was not distributed with this
   5 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
   6 #
   7 # This file incorporates work covered by the following license notice:
   8 #
   9 #   Licensed to the Apache Software Foundation (ASF) under one or more
  10 #   contributor license agreements. See the NOTICE file distributed
  11 #   with this work for additional information regarding copyright
  12 #   ownership. The ASF licenses this file to you under the Apache
  13 #   License, Version 2.0 (the "License"); you may not use this file
  14 #   except in compliance with the License. You may obtain a copy of
  15 #   the License at http://www.apache.org/licenses/LICENSE-2.0 .
  16 #
  17
  18 import sys
  19 import re
  20
  21 infile_name = sys.argv[1]
  22 id_out_name = sys.argv[2]
  23 name_out_name = sys.argv[3]
  24 txt_out_name = sys.argv[4]
  25 instrict_name = sys.argv[5]
  26 strict_out_name = sys.argv[6]
  27
  28 # parse input file
  29
  30 namespaces = {}
  31
  32 with open(infile_name) as infile:
  33     for line in infile:
  34         line = line.strip()
  35         # trim comments
  36         line = line.split('#')[0]
  37         # skip empty lines
  38         if line:
  39             # check for valid characters
  40             m = re.match(r'([a-zA-Z][a-zA-Z0-9]*)\s+([a-zA-Z0-9-.:\/]+)\s*$', line)
  41             if not m:
  42                 sys.exit('Invalid character in input data: ' + line)
  43             namespaces[m.group(1)] = m.group(2)
  44
  45 # OOXML strict namespaces
  46
  47 namespaces_strict = {}
  48 with open(instrict_name) as infile_strict:
  49     for line in infile_strict:
  50         line = line.strip()
  51         # trim comments
  52         line = line.split('#')[0]
  53         # skip empty lines
  54         if line:
  55             # check for valid characters
  56             m = re.match(r'([a-zA-Z][a-zA-Z0-9]*)\s+([a-zA-Z0-9-.:\/]+)\s*$', line)
  57             if not m:
  58                 sys.exit("Error: invalid character in input data: " + line)
  59             namespaces_strict[m.group(1)] = m.group(2)
  60
  61 # generate output files
  62
  63 idfile = open(id_out_name, 'w')
  64 namefile = open(name_out_name, 'w')
  65 txtfile = open(txt_out_name, 'w')
  66 namefile_strict = open(strict_out_name, 'w')
  67
  68 # number of bits to shift the namespace identifier
  69 shift = 16
  70
  71 idfile.write("const size_t NMSP_SHIFT = {};\n".format(shift))
  72
  73 i = 1
  74 for token in sorted(namespaces.keys()):
  75     idfile.write("const sal_Int32 NMSP_{} = {} << NMSP_SHIFT;\n".format(token, i))
  76     cur_id = i << shift
  77     namefile.write("{{ {}, \"{}\" }},\n".format(cur_id, namespaces[token]))
  78     namefile_strict.write("{{ {}, \"{}\" }},\n".format(cur_id, namespaces_strict[token]))
  79     txtfile.write("{} {} {}\n".format(cur_id, token, namespaces[token]))
  80     txtfile.write("{} {} {}\n".format(cur_id, token, namespaces_strict[token]))
  81     i += 1
  82
  83 idfile.close()
  84 namefile.close()
  85 namefile_strict.close()
  86 txtfile.close()