1 # cp932.awk -- Add sort keys and append user defined area to CP932-2BYTE.map.
2 # Copyright (C) 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011
3 # National Institute of Advanced Industrial Science and Technology (AIST)
4 # Registration Number H13PRO009
6 # This file is part of GNU Emacs.
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.
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.
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/>.
23 # Add a sort key 0, 1, 2, or 3 at the tail of each line as a comment
24 # to realize the round trip mapping to Unicode works as described in
25 # https://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP932.TXT
26 # Each sort key means as below:
27 # 0: JISX0208 characters.
28 # 1: NEC special characters.
29 # 2: IBM extension characters.
30 # 3: NEC selection of IBM extension characters.
31 # 4: user defined area
42 function decode_hex
(str
) {
45 for (i =
1; i
<= len
; i
++)
47 c =
substr(str
, i
, 1);
48 if (c
>=
"0" && c
<=
"9")
49 n = n
* 16 + (c
- "0");
51 n = n
* 16 + tohex
[c
];
56 function sjis_to_jis_ku
(code
)
60 if (s2
>=
159) # s2 >= 0x9F
62 if (s1
>=
224) # s1 >= 0xE0
63 j1 = s1
* 2 - 352; # j1 = s1 * 2 - 0x160
65 j1 = s1
* 2 - 224; # j1 = s1 * 2 - 0xE0
66 j2 = s2
- 126 # j2 = s2 - #x7E
71 j1 = s1
* 2 - 353; # j1 = s1 * 2 - 0x161
73 j1 = s1
* 2 - 225; # j1 = s1 * 2 - 0xE1
74 if (s2
>=
127) # s2 >= #x7F
83 sjis=decode_hex
(substr($
1, 3, 4))
84 ku=sjis_to_jis_ku
(sjis
);
86 printf "%s # 1 %02X%02X\n", $
0, j1
, j2
;
87 else if (ku
>=
89 && ku
<=
92)
88 printf "%s # 3 %02X%02X\n", $
0, j1
, j2
;
90 printf "%s # 0 %02X%02X\n", $
0, j1
, j2
;
95 printf "%s # 2\n", $
0;
104 code =
57344; # 0xE000
105 for (i =
240; i
< 250; i
++)
107 for (j =
64; j
<=
126; j
++)
108 printf "0x%02X%02X 0x%04X # 4\n", i
, j
, code
++;
109 for (j =
128; j
<=
158; j
++)
110 printf "0x%02X%02X 0x%04X # 4\n", i
, j
, code
++;
111 for (; j
<=
252; j
++)
112 printf "0x%02X%02X 0x%04X # 4\n", i
, j
, code
++;