admin/charsets/big5.awk

   1 # Copyright (C) 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011
   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 of the License, or
  10 # (at your option) 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.  If not, see <https://www.gnu.org/licenses/>.
  19
  20 BEGIN {
  21   tohex["A"] = 10;
  22   tohex["B"] = 11;
  23   tohex["C"] = 12;
  24   tohex["D"] = 13;
  25   tohex["E"] = 14;
  26   tohex["F"] = 15;
  27   tohex["a"] = 10;
  28   tohex["b"] = 11;
  29   tohex["c"] = 12;
  30   tohex["d"] = 13;
  31   tohex["e"] = 14;
  32   tohex["f"] = 15;
  33 }
  34
  35 function decode_hex(str) {
  36   n = 0;
  37   len = length(str);
  38   for (i = 1; i <= len; i++)
  39     {
  40       c = substr (str, i, 1);
  41       if (c >= "0" && c <= "9")
  42         n = n * 16 + (c - "0");
  43       else
  44         n = n * 16 + tohex[c];
  45     }
  46   return n;
  47 }
  48
  49 function decode_big5(big5) {
  50   b0 = int(big5 / 256);
  51   b1 = big5 % 256;
  52 # (0xFF - 0xA1 + 0x7F - 0x40) = 157
  53 # (0xA1 - (0x7F - 0x40)) = 98
  54 # (0xC9 - 0xA1) * (0xFF - 0xA1 + 0x7F - 0x40) = 6280
  55   if (b1 < 127)
  56     idx = (b0 - 161) * 157 + (b1 - 64);
  57   else
  58     idx = (b0 - 161) * 157 + (b1 - 98);
  59   if (b0 >= 201)
  60     idx -= 6280;
  61   b0 = int(idx / 94) + 33;
  62   b1 = (idx % 94) + 33;
  63   return (b0 * 256 + b1)
  64 }
  65
  66 {
  67   big5 = decode_hex($1);
  68   code = decode_big5(big5);
  69   printf "0x%04X %s\n", code, $2;
  70 }