annotate admin/charsets/cp932.awk @ 89745:708856d4c65b

New file.
author Kenichi Handa <handa@m17n.org>
date Sun, 25 Jan 2004 23:35:58 +0000
parents
children cce22763e5b1
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
89745
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
1 # cp932.awk -- Add sort key at the tail of each line of CP932-2BYTE.map.
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
2 # Copyright (C) 2004
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
3 # National Institute of Advanced Industrial Science and Technology (AIST)
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
4 # Registration Number H13PRO009
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
5 #
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
6 # This file is part of GNU Emacs.
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
7 #
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
8 # GNU Emacs is free software; you can redistribute it and/or modify
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
9 # it under the terms of the GNU General Public License as published by
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
10 # the Free Software Foundation; either version 2, or (at your option)
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
11 # any later version.
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
12 #
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
13 # GNU Emacs is distributed in the hope that it will be useful,
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
14 # but WITHOUT ANY WARRANTY; without even the implied warranty of
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
15 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
16 # GNU General Public License for more details.
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
17 #
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
18 # You should have received a copy of the GNU General Public License
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
19 # along with GNU Emacs; see the file COPYING. If not, write to the
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
20 # Free Software Foundation, Inc., 59 Temple Place - Suite 330,
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
21 # Boston, MA 02111-1307, USA.
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
22
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
23 # Comment:
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
24 # Add a sort key 0, 1, 2, or 3 at the tail of each line as a comment
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
25 # to realize the round trip mapping to Unicode works as described in
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
26 # this page:
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
27 # http://support.microsoft.com/default.aspx?scid=kb;EN-US;170559
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
28 # Each sort key means as below:
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
29 # 0: JISX0208 characters.
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
30 # 1: NEC special characters.
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
31 # 2: IBM extension characters.
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
32 # 3: NEC selection of IBM extension characters.
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
33
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
34 BEGIN {
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
35 tohex["A"] = 10;
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
36 tohex["B"] = 11;
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
37 tohex["C"] = 12;
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
38 tohex["D"] = 13;
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
39 tohex["E"] = 14;
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
40 tohex["F"] = 15;
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
41 }
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
42
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
43 function decode_hex(str) {
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
44 n = 0;
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
45 len = length(str);
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
46 for (i = 1; i <= len; i++)
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
47 {
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
48 c = substr(str, i, 1);
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
49 if (c >= "0" && c <= "9")
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
50 n = n * 16 + (c - "0");
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
51 else
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
52 n = n * 16 + tohex[c];
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
53 }
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
54 return n;
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
55 }
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
56
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
57 function sjis_to_jis_ku(code)
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
58 {
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
59 s1 = int(code / 256);
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
60 s2 = code % 256;
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
61 if (s2 >= 159) # s2 >= 0x9F
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
62 {
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
63 if (s1 >= 224) # s1 >= 0xE0
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
64 j1 = s1 * 2 - 352; # j1 = s1 * 2 - 0x160
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
65 else
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
66 j1 = s1 * 2 - 224; # j1 = s1 * 2 - 0xE0
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
67 }
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
68 else
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
69 {
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
70 if (s1 >= 224)
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
71 j1 = s1 * 2 - 353; # j1 = s1 * 2 - 0x161
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
72 else
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
73 j1 = s1 * 2 - 225; # j1 = s1 * 2 - 0xE1
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
74 }
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
75 return j1 - 32;
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
76 }
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
77
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
78 /^0x[89E]/ {
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
79 sjis=decode_hex(substr($1, 3, 4))
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
80 ku=sjis_to_jis_ku(sjis);
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
81 if (ku == 13)
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
82 print $0" # 1";
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
83 else if (ku >= 89 && ku <= 92)
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
84 print $0" # 3";
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
85 else
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
86 print $0" # 0";
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
87 next;
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
88 }
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
89
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
90 /^0xF/ {
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
91 print $0" # 2";
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
92 next;
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
93 }
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
94
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
95 {
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
96 print;
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
97 }