docbook/dfilter2xml.pl

   1 #!/usr/bin/perl
   2 #
   3 # Reads the display filter keyword dump produced by 'tshark -G' and
   4 # formats it for a pod document. The pod document is then used to
   5 # make a manpage
   6 #
   7 # STDIN is the wireshark glossary
   8 # arg1 is the pod template file. The =insert_dfilter_table token
   9 #      will be replaced by the pod-formatted glossary
  10 # STDOUT is the output
  11 #
  12 # Gilbert Ramirez <gram [AT] alumni.rice.edu>
  13 #
  14 # $Id$
  15 #
  16 # Wireshark - Network traffic analyzer
  17 # By Gerald Combs <gerald@wireshark.org>
  18 # Copyright 1998 Gerald Combs
  19 #
  20 # This program is free software; you can redistribute it and/or
  21 # modify it under the terms of the GNU General Public License
  22 # as published by the Free Software Foundation; either version 2
  23 # of the License, or (at your option) any later version.
  24 #
  25 # This program is distributed in the hope that it will be useful,
  26 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  27 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  28 # GNU General Public License for more details.
  29 #
  30 # You should have received a copy of the GNU General Public License
  31 # along with this program; if not, write to the Free Software
  32 # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
  33
  34 %ftenum_names = (
  35         'FT_NONE',              'No value',
  36         'FT_PROTOCOL',          'Protocol',
  37         'FT_BOOLEAN',           'Boolean',
  38         'FT_UINT8',             'Unsigned 8-bit integer',
  39         'FT_UINT16',            'Unsigned 16-bit integer',
  40         'FT_UINT24',            'Unsigned 24-bit integer',
  41         'FT_UINT32',            'Unsigned 32-bit integer',
  42         'FT_UINT64',            'Unsigned 64-bit integer',
  43         'FT_INT8',              'Signed 8-bit integer',
  44         'FT_INT16',             'Signed 16-bit integer',
  45         'FT_INT24',             'Signed 24-bit integer',
  46         'FT_INT32',             'Signed 32-bit integer',
  47         'FT_INT64',             'Signed 64-bit integer',
  48         'FT_FLOAT',             'Single-precision floating point',
  49         'FT_DOUBLE',            'Double-precision floating point',
  50         'FT_ABSOLUTE_TIME',     'Date/Time stamp',
  51         'FT_RELATIVE_TIME',     'Time duration',
  52         'FT_STRING',            'String',
  53         'FT_STRINGZ',           'NULL terminated string',
  54         'FT_EBCDIC',            'EBCDIC string',
  55         'FT_UINT_STRING',       'Length string pair',
  56         'FT_ETHER',             '6-byte Hardware (MAC) Address',
  57         'FT_BYTES',             'Byte array',
  58         'FT_UINT_BYTES',        'Length byte array pair',
  59         'FT_IPv4',              'IPv4 address',
  60         'FT_IPv6',              'IPv6 address',
  61         'FT_IPXNET',            'IPX network or server name',
  62         'FT_FRAMENUM',          'Frame number',
  63         'FT_PCRE',              'Perl Compatible Regular Expression',
  64         'FT_GUID',              'Globally Unique Identifier',
  65         'FT_OID',               'Object Identifier',
  66         'FT_REL_OID',           'Relative Object Identifier',
  67 );
  68
  69 # Read all the data into memory
  70 while (<STDIN>) {
  71         next unless (/^([PF])/);
  72
  73         $record_type = $1;
  74         # Strip the line from its line-end sequence
  75         # chomp($_) won't work on Win32/CygWin as it leaves the '\r' character.
  76         $_ =~ s/[\r\n]//g;
  77         $_ =~ s/\&/\&amp\;/g;
  78         $_ =~ s/\>/\&gt;/g;
  79         $_ =~ s/\</\&lt\;/g;
  80
  81         # Store protocol information
  82         if ($record_type eq 'P') {
  83                 ($junk, $name, $abbrev) = split(/\t+/, $_);
  84                 $proto_abbrev{$name} = $abbrev;
  85         }
  86         # Store header field information
  87         else {
  88                 ($junk, $name, $abbrev, $type, $parent, $blurb) =
  89                         split(/\t+/, $_);
  90                 push(@{$field_abbrev{$parent}}, $abbrev);
  91                 $field_info{$abbrev} = [ $name, $type, $blurb ];
  92         }
  93 }
  94
  95 # if there was no input on stdin, bail out
  96 if ($record_type ne 'P' and $record_type ne 'F') {
  97         exit;
  98 }
  99
 100 $template = shift(@ARGV);
 101
 102 open(TEMPLATE, $template) || die "Can't open $template for reading: $!\n";
 103
 104 while (<TEMPLATE>) {
 105         if (/=insert_dfilter_table/) {
 106                 &create_dfilter_table;
 107         }
 108         else {
 109                 print;
 110         }
 111 }
 112
 113 close(TEMPLATE) || die "Can't close $template: $!\n";
 114
 115 sub create_dfilter_table {
 116
 117         print "<appendix id=\"AppFiltFields\"><title>Wireshark Display Filter Fields</title>\n";
 118         $pn_counter = 1;
 119
 120         # Print each protocol
 121         for $proto_name (sort keys %proto_abbrev) {
 122
 123                 $ns_proto_name = $proto_name;
 124                 $ns_proto_name =~ s/\s//g;
 125                 $ns_proto_name =~ s/\)//g;
 126                 $ns_proto_name =~ s/\(//g;
 127                 $ns_proto_name =~ s/_//g;
 128                 $ns_proto_name =~ s/\+/plus/g;
 129                 $ns_proto_name =~ s/\//slash/g;
 130                 $ns_proto_name =~ s/,/comma/g;
 131                 $ns_proto_name =~ s/:/colon/g;
 132                 $ns_proto_name =~ s/'/apos/g;
 133
 134                 # The maximum token name length is apparently 44 characters.
 135                 # That's what NAMELEN is defined as in docbook 4.1, at least.
 136
 137                 if (length ($ns_proto_name) > 41) {  # "SID" and "TID" are prepended below
 138                         $ns_proto_name = sprintf ("%s%04d", substr($ns_proto_name, 0,
 139                                 37), $pn_counter);
 140                         $pn_counter++;
 141                 }
 142
 143                 print "<section id=\"SID$ns_proto_name\"><title>$proto_name ($proto_abbrev{$proto_name})</title>\n\n";
 144
 145                 print "<table id=\"TID$ns_proto_name\"><title>$proto_name ($proto_abbrev{$proto_name})</title>\n";
 146                 print "<tgroup cols=\"4\">\n";
 147 #               print "<colspec colnum=\"1\" colwidth=\"80pt\">\n";
 148 #               print "<colspec colnum=\"2\" colwidth=\"80pt\"\n>";
 149                 print "<thead>\n  <row>\n    ";
 150                 print "<entry>Field</>\n    <entry>Field Name</>\n    <entry>Type</>\n    <entry>Description</>\n\n";
 151
 152                 print "  </row>\n</thead>\n<tbody>\n";
 153
 154                 # If this proto has children fields, print those
 155                 if ($field_abbrev{$proto_abbrev{$proto_name}}) {
 156
 157                         for $field_abbrev (sort @{$field_abbrev{$proto_abbrev{$proto_name}}}) {
 158
 159                                 print "  <row>\n";
 160                                 print "    <entry>$field_abbrev</entry>\n";
 161                                 print "    <entry>", $field_info{$field_abbrev}[0], "</entry>\n";
 162                                 print "    <entry>", $ftenum_names{$field_info{$field_abbrev}[1]}, "</entry>\n";
 163                                 print "    <entry>", $field_info{$field_abbrev}[2], "</>\n";
 164                                 print "  </row>\n\n";
 165
 166                         }
 167
 168                 }
 169                 else {
 170
 171                         print "  <row>\n    <entry></entry>\n    <entry></entry>\n    <entry></entry><entry></entry>\n";
 172                         print "  </row>\n";
 173
 174                 }
 175
 176                 print "</tbody></tgroup></table>\n";
 177                 print "</section>\n\n";
 178
 179         }
 180
 181         print "</appendix>\n";
 182
 183 }