python/samba/ms_markdown.py

   1 # Create schema.ldif from Github markdown
   2 #
   3 # Each LDF section in the markdown file then gets written to a corresponding
   4 # .LDF output file.
   5 #
   6 # Copyright (C) Andrew Bartlett 2017
   7 #
   8 # This program is free software; you can redistribute it and/or modify
   9 # it under the terms of the GNU General Public License as published by
  10 # the Free Software Foundation; either version 3 of the License, or
  11 # (at your option) any later version.
  12 #
  13 # This program is distributed in the hope that it will be useful,
  14 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  15 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  16 # GNU General Public License for more details.
  17 #
  18 # You should have received a copy of the GNU General Public License
  19 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
  20
  21 """Generate LDIF from Github documentation."""
  22
  23 import re
  24 import os
  25 import markdown
  26 import xml.etree.ElementTree as ET
  27
  28 def innertext(tag):
  29     return (tag.text or '') + \
  30             ''.join(innertext(e) for e in tag) + \
  31             (tag.tail or '')
  32
  33 def read_ms_markdown(in_file, out_folder):
  34     """Read Github documentation-derived schema files."""
  35
  36     with open(in_file) as update_file:
  37         # Remove any comments from the raw LDF files
  38         html = markdown.markdown(re.sub(r'(?m)^# .*\n?', '', update_file.read()),
  39                                  output_format='xhtml')
  40
  41     tree = ET.fromstring('<root>' + html + '</root>')
  42
  43     ldf = None
  44     try:
  45         for node in tree:
  46             if node.tag == 'h3':
  47                 if ldf is not None:
  48                     ldf.close()
  49
  50                 out_path = os.path.join(out_folder, innertext(node).strip())
  51                 ldf = open(out_path, 'w')
  52             elif node.tag == 'p' and ldf is not None:
  53                 ldf.write(innertext(node).replace('```', '') + '\n')
  54     finally:
  55         if ldf is not None:
  56             ldf.close()
  57
  58 if __name__ == '__main__':
  59     import sys
  60
  61     out_folder = ''
  62
  63     if len(sys.argv) == 0:
  64         print >>sys.stderr, "Usage: %s <Schema-Update.md> [<output folder>]" % (sys.argv[0])
  65         sys.exit(1)
  66
  67     in_file = sys.argv[1]
  68     if len(sys.argv) > 2:
  69         out_folder = sys.argv[2]
  70
  71     read_ms_markdown(in_file, out_folder)