tools/extract-words-tok.pl

   1 #!perl
   2 #
   3 # ScummVM - Scumm Interpreter
   4 # Copyright (C) 2006 The ScummVM project
   5 #
   6 # This program is free software; you can redistribute it and/or
   7 # modify it under the terms of the GNU General Public License
   8 # as published by the Free Software Foundation; either version 2
   9 # of the License, or (at your option) any later version.
  10 #
  11 # This program is distributed in the hope that it will be useful,
  12 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  13 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  14 # GNU General Public License for more details.
  15 #
  16 # You should have received a copy of the GNU General Public License
  17 # along with this program; if not, write to the Free Software
  18 # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  19 #
  20 # $URL$
  21 # $Id$
  22 #
  23
  24 # This script extracts AGI words.tok file
  25 #
  26 # It produces one word per line. Multiword verbs get splitted
  27 #
  28 # Typical usage:
  29 #
  30 # for i in agigames/*/words.tok
  31 # do
  32 #   tools/extract-words-tok.pl "$i"
  33 # done | tools/construct-pred-dict.pl
  34 #
  35
  36 local $/;
  37 local $file = <>;
  38
  39 #$off = ord(substr($file, $i * 2, 1)) * 256 + ord(substr($file, $i * 2 + 1, 1));
  40 #$offn = ord(substr($file, ($i + 1) * 2, 1)) * 256 + ord(substr($file, ($i + 1) * 2 + 1, 1));
  41
  42 $off = 52;
  43
  44 $word = "";
  45 $mode = 0;
  46
  47 while ($off < length $file) {
  48   $c = (ord(substr($file, $off, 1)));
  49   if ($mode == 0) {
  50     $word = substr $word, 0, $c;
  51     $mode = 1;
  52     $off++;
  53     next;
  54   }
  55
  56   $r = ($c & 0x7f) ^ 0x7f;
  57   $word .= chr($r);
  58
  59   if ($c & 0x80) {
  60     for $w (split ' ', $word) {
  61       print "$w\n";
  62     }
  63     $off += 3;
  64     $mode = 0;
  65     next;
  66   }
  67
  68   $off++;
  69 }
  70
  71 for $w (split ' ', $word) {
  72   print "$w\n";
  73 }