Go to most recent revision | Details | Last modification | View Log | RSS feed
Rev | Author | Line No. | Line |
---|---|---|---|
4921 | Serge | 1 | /* Routine to translate from Japanese characters to Unicode */ |
2 | |||
3 | /* Copyright (c) 2002 Red Hat Incorporated. |
||
4 | All rights reserved. |
||
5 | |||
6 | Redistribution and use in source and binary forms, with or without |
||
7 | modification, are permitted provided that the following conditions are met: |
||
8 | |||
9 | Redistributions of source code must retain the above copyright |
||
10 | notice, this list of conditions and the following disclaimer. |
||
11 | |||
12 | Redistributions in binary form must reproduce the above copyright |
||
13 | notice, this list of conditions and the following disclaimer in the |
||
14 | documentation and/or other materials provided with the distribution. |
||
15 | |||
16 | The name of Red Hat Incorporated may not be used to endorse |
||
17 | or promote products derived from this software without specific |
||
18 | prior written permission. |
||
19 | |||
20 | THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" |
||
21 | AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE |
||
22 | IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE |
||
23 | ARE DISCLAIMED. IN NO EVENT SHALL RED HAT INCORPORATED BE LIABLE FOR ANY |
||
24 | DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES |
||
25 | (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; |
||
26 | LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND |
||
27 | ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT |
||
28 | (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS |
||
29 | SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
||
30 | */ |
||
31 | |||
32 | #include |
||
33 | |||
34 | #ifdef _MB_CAPABLE |
||
35 | /* Under Cygwin, the incoming wide character is already given in UTF due |
||
36 | to the requirements of the underlying OS. */ |
||
37 | #ifndef __CYGWIN__ |
||
38 | |||
39 | #include <_ansi.h> |
||
40 | #include |
||
41 | #include "local.h" |
||
42 | #include "jp2uc.h" |
||
43 | |||
44 | /* Japanese encoding types supported */ |
||
45 | #define JP_JIS 1 |
||
46 | #define JP_SJIS 2 |
||
47 | #define JP_EUCJP 3 |
||
48 | |||
49 | static wint_t |
||
50 | _DEFUN (__jp2uc, (c, type), wint_t c _AND int type) |
||
51 | { |
||
52 | int index, adj; |
||
53 | unsigned char byte1, byte2; |
||
54 | wint_t ret; |
||
55 | |||
56 | /* we actually use tables of EUCJP to Unicode. For JIS, we simply |
||
57 | note that EUCJP is essentially JIS with the top bits on in each |
||
58 | byte and translate to EUCJP. For SJIS, we do a translation to EUCJP before |
||
59 | accessing the tables. */ |
||
60 | switch (type) |
||
61 | { |
||
62 | case JP_JIS: |
||
63 | byte1 = (c >> 8) + 0x80; |
||
64 | byte2 = (c & 0xff) + 0x80; |
||
65 | break; |
||
66 | case JP_EUCJP: |
||
67 | byte1 = (c >> 8); |
||
68 | byte2 = (c & 0xff); |
||
69 | break; |
||
70 | case JP_SJIS: |
||
71 | byte1 = c >> 8; |
||
72 | byte2 = c & 0xff; |
||
73 | if (byte2 <= 0x9e) |
||
74 | { |
||
75 | adj = 0xa1 - 0x22; |
||
76 | byte2 = (byte2 - 31) + 0xa1; |
||
77 | } |
||
78 | else |
||
79 | { |
||
80 | adj = 0xa1 - 0x21; |
||
81 | byte2 = (byte2 - 126) + 0xa1; |
||
82 | } |
||
83 | if (byte1 <= 0x9f) |
||
84 | byte1 = ((byte1 - 112) << 1) + adj; |
||
85 | else |
||
86 | byte1 = ((byte1 - 176) << 1) + adj; |
||
87 | break; |
||
88 | default: |
||
89 | return WEOF; |
||
90 | } |
||
91 | |||
92 | /* find conversion in jp2uc arrays */ |
||
93 | |||
94 | /* handle larger ranges first */ |
||
95 | if (byte1 >= 0xb0 && byte1 <= 0xcf && c <= 0xcfd3) |
||
96 | { |
||
97 | index = (byte1 - 0xb0) * 0xfe + (byte2 - 0xa1); |
||
98 | return b02cf[index]; |
||
99 | } |
||
100 | else if (byte1 >= 0xd0 && byte1 <= 0xf4 && c <= 0xf4a6) |
||
101 | { |
||
102 | index = (byte1 - 0xd0) * 0xfe + (byte2 - 0xa1); |
||
103 | return d02f4[index]; |
||
104 | } |
||
105 | |||
106 | /* handle smaller ranges here */ |
||
107 | switch (byte1) |
||
108 | { |
||
109 | case 0xA1: |
||
110 | return (wint_t)a1[byte2 - 0xa1]; |
||
111 | case 0xA2: |
||
112 | ret = a2[byte2 - 0xa1]; |
||
113 | if (ret != 0) |
||
114 | return (wint_t)ret; |
||
115 | break; |
||
116 | case 0xA3: |
||
117 | if (a3[byte2 - 0xa1]) |
||
118 | return (wint_t)(0xff00 + (byte2 - 0xa0)); |
||
119 | break; |
||
120 | case 0xA4: |
||
121 | if (byte2 <= 0xf3) |
||
122 | return (wint_t)(0x3000 + (byte2 - 0x60)); |
||
123 | break; |
||
124 | case 0xA5: |
||
125 | if (byte2 <= 0xf6) |
||
126 | return (wint_t)(0x3000 + byte2); |
||
127 | break; |
||
128 | case 0xA6: |
||
129 | ret = 0; |
||
130 | if (byte2 <= 0xd8) |
||
131 | ret = (wint_t)a6[byte2 - 0xa1]; |
||
132 | if (ret != 0) |
||
133 | return ret; |
||
134 | break; |
||
135 | case 0xA7: |
||
136 | ret = 0; |
||
137 | if (byte2 <= 0xf1) |
||
138 | ret = (wint_t)a7[byte2 - 0xa1]; |
||
139 | if (ret != 0) |
||
140 | return ret; |
||
141 | break; |
||
142 | case 0xA8: |
||
143 | if (byte2 <= 0xc0) |
||
144 | return (wint_t)a8[byte2 - 0xa1]; |
||
145 | break; |
||
146 | default: |
||
147 | return WEOF; |
||
148 | } |
||
149 | |||
150 | return WEOF; |
||
151 | } |
||
152 | |||
153 | wint_t |
||
154 | _DEFUN (_jp2uc, (c), wint_t c) |
||
155 | { |
||
156 | if (!strcmp (__locale_charset (), "JIS")) |
||
157 | c = __jp2uc (c, JP_JIS); |
||
158 | else if (!strcmp (__locale_charset (), "SJIS")) |
||
159 | c = __jp2uc (c, JP_SJIS); |
||
160 | else if (!strcmp (__locale_charset (), "EUCJP")) |
||
161 | c = __jp2uc (c, JP_EUCJP); |
||
162 | return c; |
||
163 | } |
||
164 | |||
165 | #endif /* !__CYGWIN__ */ |
||
166 | #endif /* _MB_CAPABLE */=>=>=>=>=>=>=>=>=>><>><>=>=> |