admin/charsets/gb180302.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   from_gb = 0;
  36   to_gb = -1;
  37   to_unicode = 0;
  38   from_unicode = 0;
  39 }
  40
  41 function decode_hex(str) {
  42   n = 0;
  43   len = length(str);
  44   for (i = 1; i <= len; i++)
  45     {
  46       c = substr (str, i, 1);
  47       if (c >= "0" && c <= "9")
  48         n = n * 16 + (c - "0");
  49       else
  50         n = n * 16 + tohex[c];
  51     }
  52   return n;
  53 }
  54
  55 function gb_to_index(gb) {
  56   b0 = int(gb / 256);
  57   b1 = gb % 256;
  58   idx = (((b0 - 129)) * 191 + b1 - 64);
  59 #  if (b1 >= 128)
  60 #    idx--;
  61   return idx
  62 }
  63
  64 function index_to_gb(idx) {
  65   b0 = int(idx / 191) + 129;
  66   b1 = (idx % 191) + 64;
  67 #  if (b1 >= 127)
  68 #    b1++;
  69   return (b0 * 256 + b1);
  70 }
  71
  72 /^\#/ {
  73   print;
  74   next;
  75 }
  76
  77 {
  78   gb = gb_to_index(decode_hex(substr($1, 3, 4)));
  79   unicode = decode_hex(substr($2, 3, 4));
  80   if ((gb == to_gb + 1) && (unicode == to_unicode + 1))
  81     {
  82       to_gb++;
  83       to_unicode++;
  84     }
  85   else
  86     {
  87       if (from_gb == to_gb)
  88         printf "0x%04X 0x%04X\n", index_to_gb(from_gb), from_unicode;
  89       else if (from_gb < to_gb)
  90         printf "0x%04X-0x%04X 0x%04X\n",
  91           index_to_gb(from_gb), index_to_gb(to_gb), from_unicode;
  92       from_gb = to_gb = gb;
  93       from_unicode = to_unicode = unicode;
  94     }
  95 }
  96
  97 END {
  98   if (from_gb <= to_gb)
  99     printf "0x%04X-0x%04X 0x%04X\n",
 100       index_to_gb(from_gb), index_to_gb(to_gb), from_unicode;
 101 }
 102
 103 # arch-tag: d7dbad89-a512-41a4-8ee0-ba1a4505b8c1