admin/charsets/gb180304.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 gb_to_index(gb) {
  52   b0 = int(gb / 256);
  53   b1 = gb % 256;
  54   idx = (((b0 - 129)) * 191 + b1 - 64);
  55 #  if (b1 >= 127)
  56 #    idx--;
  57   return idx
  58 }
  59
  60 function index_to_gb(idx) {
  61   b3 = (idx % 10) + 48;
  62   idx = int(idx / 10);
  63   b2 = (idx % 126) + 129;
  64   idx = int(idx / 126);
  65   b1 = (idx % 10) + 48;
  66   b0 = int(idx / 10) + 129;
  67   return sprintf("%02X%02X%02X%02X", b0, b1, b2, b3);
  68 }
  69
  70 /^\#/ {
  71   print;
  72   next;
  73 }
  74
  75 /0x....-0x..../ {
  76   gb_from = gb_to_index(decode_hex(substr($1, 3, 4)));
  77   gb_to = gb_to_index(decode_hex(substr($1, 10, 4)));
  78   unicode = decode_hex(substr($2, 3, 4));
  79   while (gb_from <= gb_to)
  80     {
  81       table[unicode++] = 1;
  82       gb_from++;
  83     }
  84   next;
  85 }
  86
  87 {
  88   gb = decode_hex(substr($1, 3, 4));
  89   unicode = decode_hex(substr($2, 3, 4));
  90   table[unicode] = 1;
  91 }
  92
  93 END {
  94   from_gb = -1;
  95   to_gb = 0;
  96   from_i = 0;
  97   table[65536] = 1;
  98   for (i = 128; i <= 65536; i++)
  99     {
 100       if (table[i] == 0)
 101         {
 102           if (i < 55296 || i >= 57344)
 103             {
 104               if (from_gb < 0)
 105                 {
 106                   from_gb = to_gb;
 107                   from_i = i;
 108                 }
 109               to_gb++;
 110             }
 111         }
 112       else if (from_gb >= 0)
 113         {
 114           if (from_gb + 1 == to_gb)
 115             printf "0x%s\t\t0x%04X\n",
 116               index_to_gb(from_gb), from_i;
 117           else
 118             printf "0x%s-0x%s\t0x%04X\n",
 119               index_to_gb(from_gb), index_to_gb(to_gb - 1), from_i;
 120           from_gb = -1;
 121         }
 122     }
 123 }
 124
 125 # arch-tag: 8e5a22ae-610e-411f-ae17-d6e528b30d71