admin/charsets/compact.awk

   1 # compact.awk -- Make charset map compact.
   2 # Copyright (C) 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011
   3 #   National Institute of Advanced Industrial Science and Technology (AIST)
   4 #   Registration Number H13PRO009
   5
   6 # This file is part of GNU Emacs.
   7
   8 # GNU Emacs is free software: you can redistribute it and/or modify
   9 # it under the terms of the GNU General Public License as published by
  10 # the Free Software Foundation, either version 3 of the License, or
  11 # (at your option) any later version.
  12
  13 # GNU Emacs is distributed in the hope that it will be useful,
  14 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  15 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  16 # GNU General Public License for more details.
  17
  18 # You should have received a copy of the GNU General Public License
  19 # along with GNU Emacs.  If not, see <https://www.gnu.org/licenses/>.
  20
  21 # Commentary:
  22 # Make a charset map compact by changing this kind of line sequence:
  23 #   0x00 0x0000
  24 #   0x01 0x0001
  25 #   ...
  26 #   0x7F 0x007F
  27 # to one line of this format:
  28 #   0x00-0x7F 0x0000
  29
  30 BEGIN {
  31   tohex["0"] = 1;
  32   tohex["1"] = 2;
  33   tohex["2"] = 3;
  34   tohex["3"] = 4;
  35   tohex["4"] = 5;
  36   tohex["5"] = 6;
  37   tohex["6"] = 7;
  38   tohex["7"] = 8;
  39   tohex["8"] = 9;
  40   tohex["9"] = 10;
  41   tohex["A"] = 11;
  42   tohex["B"] = 12;
  43   tohex["C"] = 13;
  44   tohex["D"] = 14;
  45   tohex["E"] = 15;
  46   tohex["F"] = 16;
  47   tohex["a"] = 11;
  48   tohex["b"] = 12;
  49   tohex["c"] = 13;
  50   tohex["d"] = 14;
  51   tohex["e"] = 15;
  52   tohex["f"] = 16;
  53   from_code = 0;
  54   to_code = -1;
  55   to_unicode = 0;
  56   from_unicode = 0;
  57 }
  58
  59 function decode_hex(str, idx) {
  60   n = 0;
  61   len = length(str);
  62   for (i = idx; i <= len; i++)
  63     {
  64       c = tohex[substr (str, i, 1)];
  65       if (c == 0)
  66         break;
  67       n = n * 16 + c - 1;
  68     }
  69   return n;
  70 }
  71
  72 /^#/ {
  73   print;
  74   next;
  75 }
  76
  77 {
  78   code = decode_hex($1, 3);
  79   unicode = decode_hex($2, 3);
  80   if ((code == to_code + 1) && (unicode == to_unicode + 1))
  81     {
  82       to_code++;
  83       to_unicode++;
  84     }
  85   else
  86     {
  87       if (to_code < 256)
  88         {
  89           if (from_code == to_code)
  90             printf "0x%02X 0x%04X\n", from_code, from_unicode;
  91           else if (from_code < to_code)
  92             printf "0x%02X-0x%02X 0x%04X\n", from_code, to_code, from_unicode;
  93         }
  94       else
  95         {
  96           if (from_code == to_code)
  97             printf "0x%04X 0x%04X\n", from_code, from_unicode;
  98           else if (from_code < to_code)
  99             printf "0x%04X-0x%04X 0x%04X\n", from_code, to_code, from_unicode;
 100         }
 101       from_code = to_code = code;
 102       from_unicode = to_unicode = unicode;
 103     }
 104 }
 105
 106 END {
 107   if (to_code < 256)
 108     {
 109       if (from_code == to_code)
 110         printf "0x%02X 0x%04X\n", from_code, from_unicode;
 111       else
 112         printf "0x%02X-0x%02X 0x%04X\n", from_code, to_code, from_unicode;
 113     }
 114   else
 115     {
 116       if (from_code == to_code)
 117         printf "0x%04X 0x%04X\n", from_code, from_unicode;
 118       else
 119         printf "0x%04X-0x%04X 0x%04X\n", from_code, to_code, from_unicode;
 120     }
 121 }