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, re
  19
  20 infile_name = sys.argv[1]
  21 id_out_name = sys.argv[2]
  22 name_out_name = sys.argv[3]
  23 txt_out_name = sys.argv[4]
  24 instrict_name = sys.argv[5]
  25 strict_out_name = sys.argv[6]
  26
  27 # parse input file
  28
  29 namespaces = {}
  30
  31 with open(infile_name) as infile:
  32     for line in infile:
  33         line = line.strip()
  34         # trim comments
  35         line = line.split('#')[0]
  36         # skip empty lines
  37         if line:
  38             # check for valid characters
  39             m = re.match(r'([a-zA-Z][a-zA-Z0-9]*)\s+([a-zA-Z0-9-.:\/]+)\s*$', line)
  40             if not m:
  41                 sys.exit('Invalid character in input data: ' + line)
  42             namespaces[m.group(1)] = m.group(2)
  43
  44 # OOXML strict namespaces
  45
  46 namespaces_strict = {}
  47 with open(instrict_name) as infile_strict:
  48     for line in infile_strict:
  49         line = line.strip()
  50         # trim comments
  51         line = line.split('#')[0]
  52         # skip empty lines
  53         if line:
  54             # check for valid characters
  55             m = re.match(r'([a-zA-Z][a-zA-Z0-9]*)\s+([a-zA-Z0-9-.:\/]+)\s*$', line)
  56             if not m:
  57                 sys.exit("Error: invalid character in input data: " + line)
  58             namespaces_strict[m.group(1)] = m.group(2)
  59
  60 # generate output files
  61
  62 idfile = open(id_out_name, 'w')
  63 namefile = open(name_out_name, 'w')
  64 txtfile = open(txt_out_name, 'w')
  65 namefile_strict = open(strict_out_name, 'w')
  66
  67 # number of bits to shift the namespace identifier
  68 shift = 16
  69
  70 idfile.write("const size_t NMSP_SHIFT = {};\n".format(shift))
  71
  72 i = 1;
  73 for token in sorted(namespaces.keys()):
  74     idfile.write("const sal_Int32 NMSP_{} = {} << NMSP_SHIFT;\n".format(token, i))
  75     cur_id = i << shift
  76     namefile.write("{{ {}, \"{}\" }},\n".format(cur_id, namespaces[token]))
  77     namefile_strict.write("{{ {}, \"{}\" }},\n".format(cur_id, namespaces_strict[token]))
  78     txtfile.write("{} {} {}\n".format(cur_id, token, namespaces[token]))
  79     txtfile.write("{} {} {}\n".format(cur_id, token, namespaces_strict[token]))
  80     i += 1
  81
  82 idfile.close()
  83 namefile.close()
  84 namefile_strict.close()
  85 txtfile.close()