|
88123
|
1 # compact.awk -- Make charset map compact.
|
|
|
2 # Copyright (C) 2003
|
|
|
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 2, or (at your option)
|
|
|
11 # 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; see the file COPYING. If not, write to the
|
|
|
20 # Free Software Foundation, Inc., 59 Temple Place - Suite 330,
|
|
|
21 # Boston, MA 02111-1307, USA.
|
|
|
22
|
|
|
23 # Comment:
|
|
|
24 # Make a charset map compact by changing this kind of line sequence:
|
|
|
25 # 0x00 0x0000
|
|
|
26 # 0x01 0x0001
|
|
|
27 # ...
|
|
|
28 # 0x7F 0x007F
|
|
|
29 # to one line of this format:
|
|
|
30 # 0x00-0x7F 0x0000
|
|
|
31
|
|
|
32 BEGIN {
|
|
|
33 tohex["0"] = 1;
|
|
|
34 tohex["1"] = 2;
|
|
|
35 tohex["2"] = 3;
|
|
|
36 tohex["3"] = 4;
|
|
|
37 tohex["4"] = 5;
|
|
|
38 tohex["5"] = 6;
|
|
|
39 tohex["6"] = 7;
|
|
|
40 tohex["7"] = 8;
|
|
|
41 tohex["8"] = 9;
|
|
|
42 tohex["9"] = 10;
|
|
|
43 tohex["A"] = 11;
|
|
|
44 tohex["B"] = 12;
|
|
|
45 tohex["C"] = 13;
|
|
|
46 tohex["D"] = 14;
|
|
|
47 tohex["E"] = 15;
|
|
|
48 tohex["F"] = 16;
|
|
|
49 tohex["a"] = 11;
|
|
|
50 tohex["b"] = 12;
|
|
|
51 tohex["c"] = 13;
|
|
|
52 tohex["d"] = 14;
|
|
|
53 tohex["e"] = 15;
|
|
|
54 tohex["f"] = 16;
|
|
|
55 from_code = 0;
|
|
|
56 to_code = -1;
|
|
|
57 to_unicode = 0;
|
|
|
58 from_unicode = 0;
|
|
|
59 }
|
|
|
60
|
|
|
61 function decode_hex(str, idx) {
|
|
|
62 n = 0;
|
|
|
63 len = length(str);
|
|
|
64 for (i = idx; i <= len; i++)
|
|
|
65 {
|
|
|
66 c = tohex[substr (str, i, 1)];
|
|
|
67 if (c == 0)
|
|
|
68 break;
|
|
|
69 n = n * 16 + c - 1;
|
|
|
70 }
|
|
|
71 return n;
|
|
|
72 }
|
|
|
73
|
|
|
74 /^\#/ {
|
|
|
75 print;
|
|
|
76 next;
|
|
|
77 }
|
|
|
78
|
|
|
79 {
|
|
|
80 code = decode_hex($1, 3);
|
|
|
81 unicode = decode_hex($2, 3);
|
|
|
82 if ((code == to_code + 1) && (unicode == to_unicode + 1))
|
|
|
83 {
|
|
|
84 to_code++;
|
|
|
85 to_unicode++;
|
|
|
86 }
|
|
|
87 else
|
|
|
88 {
|
|
|
89 if (to_code < 256)
|
|
|
90 {
|
|
|
91 if (from_code == to_code)
|
|
|
92 printf "0x%02X 0x%04X\n", from_code, from_unicode;
|
|
|
93 else if (from_code < to_code)
|
|
|
94 printf "0x%02X-0x%02X 0x%04X\n", from_code, to_code, from_unicode;
|
|
|
95 }
|
|
|
96 else
|
|
|
97 {
|
|
|
98 if (from_code == to_code)
|
|
|
99 printf "0x%04X 0x%04X\n", from_code, from_unicode;
|
|
|
100 else if (from_code < to_code)
|
|
|
101 printf "0x%04X-0x%04X 0x%04X\n", from_code, to_code, from_unicode;
|
|
|
102 }
|
|
|
103 from_code = to_code = code;
|
|
|
104 from_unicode = to_unicode = unicode;
|
|
|
105 }
|
|
|
106 }
|
|
|
107
|
|
|
108 END {
|
|
|
109 if (to_code < 256)
|
|
|
110 {
|
|
|
111 if (from_code == to_code)
|
|
|
112 printf "0x%02X 0x%04X\n", from_code, from_unicode;
|
|
|
113 else
|
|
|
114 printf "0x%02X-0x%02X 0x%04X\n", from_code, to_code, from_unicode;
|
|
|
115 }
|
|
|
116 else
|
|
|
117 {
|
|
|
118 if (from_code == to_code)
|
|
|
119 printf "0x%04X 0x%04X\n", from_code, from_unicode;
|
|
|
120 else
|
|
|
121 printf "0x%04X-0x%04X 0x%04X\n", from_code, to_code, from_unicode;
|
|
|
122 }
|
|
|
123 }
|
