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