admin/charsets/big5.awk

   1 # Copyright (C) 2003, 2004, 2005, 2006, 2007, 2008
   2 #   National Institute of Advanced Industrial Science and Technology (AIST)
   3 #   Registration Number H13PRO009
   4 #
   5 # This file is part of GNU Emacs.
   6 #
   7 # GNU Emacs is free software; you can redistribute it and/or modify
   8 # it under the terms of the GNU General Public License as published by
   9 # the Free Software Foundation; either version 3, or (at your option)
  10 # any later version.
  11 #
  12 # GNU Emacs is distributed in the hope that it will be useful,
  13 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  14 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  15 # GNU General Public License for more details.
  16 #
  17 # You should have received a copy of the GNU General Public License
  18 # along with GNU Emacs; see the file COPYING.  If not, write to the
  19 # Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
  20 # Boston, MA 02110-1301, USA.
  21
  22 BEGIN {
  23   tohex["A"] = 10;
  24   tohex["B"] = 11;
  25   tohex["C"] = 12;
  26   tohex["D"] = 13;
  27   tohex["E"] = 14;
  28   tohex["F"] = 15;
  29   tohex["a"] = 10;
  30   tohex["b"] = 11;
  31   tohex["c"] = 12;
  32   tohex["d"] = 13;
  33   tohex["e"] = 14;
  34   tohex["f"] = 15;
  35 }
  36
  37 function decode_hex(str) {
  38   n = 0;
  39   len = length(str);
  40   for (i = 1; i <= len; i++)
  41     {
  42       c = substr (str, i, 1);
  43       if (c >= "0" && c <= "9")
  44         n = n * 16 + (c - "0");
  45       else
  46         n = n * 16 + tohex[c];
  47     }
  48   return n;
  49 }
  50
  51 function decode_big5(big5) {
  52   b0 = int(big5 / 256);
  53   b1 = big5 % 256;
  54 # (0xFF - 0xA1 + 0x7F - 0x40) = 157
  55 # (0xA1 - (0x7F - 0x40)) = 98
  56 # (0xC9 - 0xA1) * (0xFF - 0xA1 + 0x7F - 0x40) = 6280
  57   if (b1 < 127)
  58     idx = (b0 - 161) * 157 + (b1 - 64);
  59   else
  60     idx = (b0 - 161) * 157 + (b1 - 98);
  61   if (b0 >= 201)
  62     idx -= 6280;
  63   b0 = int(idx / 94) + 33;
  64   b1 = (idx % 94) + 33;
  65   return (b0 * 256 + b1)
  66 }
  67
  68 {
  69   big5 = decode_hex($1);
  70   code = decode_big5(big5);
  71   printf "0x%04X %s\n", code, $2;
  72 }
  73
  74
  75 # arch-tag: 36f08d21-0d24-4b67-852d-a9a51299586d