annotate admin/charsets/cp932.awk @ 89916:e0e4e6a0599f

Changes from arch/CVS synchronization
author Miles Bader <miles@gnu.org>
date Mon, 19 Apr 2004 20:08:38 +0000
parents cce22763e5b1
children 9a10da450c13
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
89786
cce22763e5b1 Append user defined area of CP932.
Kenichi Handa <handa@m17n.org>
parents: 89745
diff changeset
1 # cp932.awk -- Add sort keys and append user defined area to CP932-2BYTE.map.
89745
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.
89786
cce22763e5b1 Append user defined area of CP932.
Kenichi Handa <handa@m17n.org>
parents: 89745
diff changeset
33 # 4: user defined area
89745
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
34
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
35 BEGIN {
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
36 tohex["A"] = 10;
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
37 tohex["B"] = 11;
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
38 tohex["C"] = 12;
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
39 tohex["D"] = 13;
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
40 tohex["E"] = 14;
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
41 tohex["F"] = 15;
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
42 }
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
43
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
44 function decode_hex(str) {
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
45 n = 0;
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
46 len = length(str);
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
47 for (i = 1; i <= len; i++)
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
48 {
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
49 c = substr(str, i, 1);
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
50 if (c >= "0" && c <= "9")
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
51 n = n * 16 + (c - "0");
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
52 else
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
53 n = n * 16 + tohex[c];
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
54 }
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
55 return n;
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
56 }
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
57
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
58 function sjis_to_jis_ku(code)
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
59 {
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
60 s1 = int(code / 256);
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
61 s2 = code % 256;
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
62 if (s2 >= 159) # s2 >= 0x9F
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
63 {
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
64 if (s1 >= 224) # s1 >= 0xE0
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
65 j1 = s1 * 2 - 352; # j1 = s1 * 2 - 0x160
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
66 else
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
67 j1 = s1 * 2 - 224; # j1 = s1 * 2 - 0xE0
89786
cce22763e5b1 Append user defined area of CP932.
Kenichi Handa <handa@m17n.org>
parents: 89745
diff changeset
68 j2 = s2 - 126 # j2 = s2 - #x7E
89745
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
69 }
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
70 else
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
71 {
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
72 if (s1 >= 224)
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
73 j1 = s1 * 2 - 353; # j1 = s1 * 2 - 0x161
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
74 else
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
75 j1 = s1 * 2 - 225; # j1 = s1 * 2 - 0xE1
89786
cce22763e5b1 Append user defined area of CP932.
Kenichi Handa <handa@m17n.org>
parents: 89745
diff changeset
76 if (s2 >= 127) # s2 >= #x7F
cce22763e5b1 Append user defined area of CP932.
Kenichi Handa <handa@m17n.org>
parents: 89745
diff changeset
77 j2 = s2 - 32;
cce22763e5b1 Append user defined area of CP932.
Kenichi Handa <handa@m17n.org>
parents: 89745
diff changeset
78 else
cce22763e5b1 Append user defined area of CP932.
Kenichi Handa <handa@m17n.org>
parents: 89745
diff changeset
79 j2 = s2 - 31;
89745
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
80 }
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
81 return j1 - 32;
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
82 }
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
83
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
84 /^0x[89E]/ {
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
85 sjis=decode_hex(substr($1, 3, 4))
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
86 ku=sjis_to_jis_ku(sjis);
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
87 if (ku == 13)
89786
cce22763e5b1 Append user defined area of CP932.
Kenichi Handa <handa@m17n.org>
parents: 89745
diff changeset
88 printf "%s # 1 %02X%02X\n", $0, j1, j2;
89745
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
89 else if (ku >= 89 && ku <= 92)
89786
cce22763e5b1 Append user defined area of CP932.
Kenichi Handa <handa@m17n.org>
parents: 89745
diff changeset
90 printf "%s # 3 %02X%02X\n", $0, j1, j2;
89745
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
91 else
89786
cce22763e5b1 Append user defined area of CP932.
Kenichi Handa <handa@m17n.org>
parents: 89745
diff changeset
92 printf "%s # 0 %02X%02X\n", $0, j1, j2;
89745
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
93 next;
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 /^0xF/ {
89786
cce22763e5b1 Append user defined area of CP932.
Kenichi Handa <handa@m17n.org>
parents: 89745
diff changeset
97 printf "%s # 2\n", $0;
89745
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
98 next;
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
99 }
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
100
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
101 {
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
102 print;
708856d4c65b New file.
Kenichi Handa <handa@m17n.org>
parents:
diff changeset
103 }
89786
cce22763e5b1 Append user defined area of CP932.
Kenichi Handa <handa@m17n.org>
parents: 89745
diff changeset
104
cce22763e5b1 Append user defined area of CP932.
Kenichi Handa <handa@m17n.org>
parents: 89745
diff changeset
105 END {
cce22763e5b1 Append user defined area of CP932.
Kenichi Handa <handa@m17n.org>
parents: 89745
diff changeset
106 code = 57344; # 0xE000
cce22763e5b1 Append user defined area of CP932.
Kenichi Handa <handa@m17n.org>
parents: 89745
diff changeset
107 for (i = 240; i < 250; i++)
cce22763e5b1 Append user defined area of CP932.
Kenichi Handa <handa@m17n.org>
parents: 89745
diff changeset
108 {
cce22763e5b1 Append user defined area of CP932.
Kenichi Handa <handa@m17n.org>
parents: 89745
diff changeset
109 for (j = 64; j <= 126; j++)
cce22763e5b1 Append user defined area of CP932.
Kenichi Handa <handa@m17n.org>
parents: 89745
diff changeset
110 printf "0x%02X%02X 0x%04X # 4\n", i, j, code++;
cce22763e5b1 Append user defined area of CP932.
Kenichi Handa <handa@m17n.org>
parents: 89745
diff changeset
111 for (j = 128; j <= 158; j++)
cce22763e5b1 Append user defined area of CP932.
Kenichi Handa <handa@m17n.org>
parents: 89745
diff changeset
112 printf "0x%02X%02X 0x%04X # 4\n", i, j, code++;
cce22763e5b1 Append user defined area of CP932.
Kenichi Handa <handa@m17n.org>
parents: 89745
diff changeset
113 for (; j <= 252; j++)
cce22763e5b1 Append user defined area of CP932.
Kenichi Handa <handa@m17n.org>
parents: 89745
diff changeset
114 printf "0x%02X%02X 0x%04X # 4\n", i, j, code++;
cce22763e5b1 Append user defined area of CP932.
Kenichi Handa <handa@m17n.org>
parents: 89745
diff changeset
115 }
cce22763e5b1 Append user defined area of CP932.
Kenichi Handa <handa@m17n.org>
parents: 89745
diff changeset
116 }
89916
e0e4e6a0599f Changes from arch/CVS synchronization
Miles Bader <miles@gnu.org>
parents: 89786
diff changeset
117
e0e4e6a0599f Changes from arch/CVS synchronization
Miles Bader <miles@gnu.org>
parents: 89786
diff changeset
118 # arch-tag: 998dc444-759d-43ef-87e3-2ab205011394