compact.awk 2.82 KB
Newer Older
Kenichi Handa's avatar
Kenichi Handa committed
1
# compact.awk -- Make charset map compact.
2
# Copyright (C) 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011
Kenichi Handa's avatar
Kenichi Handa committed
3 4
#   National Institute of Advanced Industrial Science and Technology (AIST)
#   Registration Number H13PRO009
5

Kenichi Handa's avatar
Kenichi Handa committed
6
# This file is part of GNU Emacs.
7 8

# GNU Emacs is free software: you can redistribute it and/or modify
Kenichi Handa's avatar
Kenichi Handa committed
9
# it under the terms of the GNU General Public License as published by
10 11 12
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.

Kenichi Handa's avatar
Kenichi Handa committed
13 14 15 16
# GNU Emacs is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
17

Kenichi Handa's avatar
Kenichi Handa committed
18
# You should have received a copy of the GNU General Public License
19
# along with GNU Emacs.  If not, see <http://www.gnu.org/licenses/>.
Kenichi Handa's avatar
Kenichi Handa committed
20

21
# Commentary:
Kenichi Handa's avatar
Kenichi Handa committed
22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71
# Make a charset map compact by changing this kind of line sequence:
#   0x00 0x0000
#   0x01 0x0001
#   ...
#   0x7F 0x007F
# to one line of this format:
#   0x00-0x7F 0x0000

BEGIN {
  tohex["0"] = 1;
  tohex["1"] = 2;
  tohex["2"] = 3;
  tohex["3"] = 4;
  tohex["4"] = 5;
  tohex["5"] = 6;
  tohex["6"] = 7;
  tohex["7"] = 8;
  tohex["8"] = 9;
  tohex["9"] = 10;
  tohex["A"] = 11;
  tohex["B"] = 12;
  tohex["C"] = 13;
  tohex["D"] = 14;
  tohex["E"] = 15;
  tohex["F"] = 16;
  tohex["a"] = 11;
  tohex["b"] = 12;
  tohex["c"] = 13;
  tohex["d"] = 14;
  tohex["e"] = 15;
  tohex["f"] = 16;
  from_code = 0;
  to_code = -1;
  to_unicode = 0;
  from_unicode = 0;
}

function decode_hex(str, idx) {
  n = 0;
  len = length(str);
  for (i = idx; i <= len; i++)
    {
      c = tohex[substr (str, i, 1)];
      if (c == 0)
	break;
      n = n * 16 + c - 1;
    }
  return n;
}

72
/^#/ {
Kenichi Handa's avatar
Kenichi Handa committed
73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121
  print;
  next;
}

{
  code = decode_hex($1, 3);
  unicode = decode_hex($2, 3);
  if ((code == to_code + 1) && (unicode == to_unicode + 1))
    {
      to_code++;
      to_unicode++;
    }
  else
    {
      if (to_code < 256)
	{
	  if (from_code == to_code)
	    printf "0x%02X 0x%04X\n", from_code, from_unicode;
	  else if (from_code < to_code)
	    printf "0x%02X-0x%02X 0x%04X\n", from_code, to_code, from_unicode;
	}
      else
	{
	  if (from_code == to_code)
	    printf "0x%04X 0x%04X\n", from_code, from_unicode;
	  else if (from_code < to_code)
	    printf "0x%04X-0x%04X 0x%04X\n", from_code, to_code, from_unicode;
	}
      from_code = to_code = code;
      from_unicode = to_unicode = unicode;
    }
}

END {
  if (to_code < 256)
    {
      if (from_code == to_code)
	printf "0x%02X 0x%04X\n", from_code, from_unicode;
      else
	printf "0x%02X-0x%02X 0x%04X\n", from_code, to_code, from_unicode;
    }
  else
    {
      if (from_code == to_code)
	printf "0x%04X 0x%04X\n", from_code, from_unicode;
      else
	printf "0x%04X-0x%04X 0x%04X\n", from_code, to_code, from_unicode;
    }
}