cf/w32-hh-toc-from-info.pl

   1 ########################################################################
   2 #
   3 # Copyright (c) 2010, Secure Endpoints Inc.
   4 # All rights reserved.
   5 #
   6 # Redistribution and use in source and binary forms, with or without
   7 # modification, are permitted provided that the following conditions
   8 # are met:
   9 #
  10 # - Redistributions of source code must retain the above copyright
  11 #   notice, this list of conditions and the following disclaimer.
  12 #
  13 # - Redistributions in binary form must reproduce the above copyright
  14 #   notice, this list of conditions and the following disclaimer in
  15 #   the documentation and/or other materials provided with the
  16 #   distribution.
  17 #
  18 # THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
  19 # "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
  20 # LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
  21 # FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
  22 # COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
  23 # INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
  24 # BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
  25 # LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
  26 # CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  27 # LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
  28 # ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
  29 # POSSIBILITY OF SUCH DAMAGE.
  30 #
  31
  32 use HTML::TreeBuilder;
  33
  34
  35 my $input_file = "index.html";
  36 my $toc_file = "toc.hhc";
  37
  38 for (@ARGV) {
  39   ARG: {
  40       /-o(.*)/ && do {
  41           $toc_file = $1;
  42           last ARG;
  43       };
  44
  45       $input_file = $_;
  46     }
  47 }
  48
  49 print "Processing TOC in $input_file\n";
  50 print "Writing to $toc_file\n";
  51
  52 open(TOC, '>', $toc_file) or die "Can't open $toc_file\n";
  53
  54 my $tree = HTML::TreeBuilder->new();
  55
  56 $tree->parse_file($input_file);
  57
  58 my $contents = $tree->look_down('class', 'contents');
  59 if (defined($contents)) {
  60   my $clist = $contents->find_by_tag_name('ul');
  61 }
  62
  63 print TOC '<!DOCTYPE HTML PUBLIC "-//IETF//DTD HTML//EN">
  64 <html>
  65 <head>
  66 <meta name="GENERATOR" content="Heimdal">
  67 </head>
  68 <body>
  69 ';
  70
  71 process_ul_element($clist, 0);
  72
  73 print TOC '
  74 </body>
  75 </html>
  76 ';
  77
  78
  79 sub process_ul_element
  80 {
  81     my $e = shift;
  82     my $level = shift;
  83
  84     return unless defined($e);
  85
  86     if ($e->tag() eq "ul") {
  87
  88         print TOC '  'x$level;
  89         print TOC "<ul>\n";
  90
  91         my @items = $e->content_list();
  92
  93         for (@items) {
  94             process_li_element($_, $level + 1);
  95         }
  96
  97         print TOC '  'x$level;
  98         print TOC "</ul>\n";
  99     }
 100 }
 101
 102 sub process_li_element
 103 {
 104     my $e = shift;
 105     my $level = shift;
 106
 107     if ($e->tag() eq "li") {
 108         my $a = $e->find_by_tag_name('a');
 109
 110         my $href = $a->attr('href');
 111         my @ac = $a->content_list();
 112         my $title = $ac[0];
 113
 114         print TOC "  "x$level;
 115         print TOC "<li><object type=\"text/sitemap\"><param name=\"Name\" value=\"$title\"><param name=\"Local\" value=\"$href\"></object>\n";
 116
 117         my @items = $e->content_list();
 118
 119         for (@items) {
 120             process_ul_element($_, $level + 1);
 121         }
 122     }
 123 }
 124