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 <newlib.h> |
---|
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 <string.h> |
---|
41 | #include <wctype.h> |
---|
42 | #include "local.h" |
---|
43 | #include "jp2uc.h" |
---|
44 | |
---|
45 | /* Japanese encoding types supported */ |
---|
46 | #define JP_JIS 1 |
---|
47 | #define JP_SJIS 2 |
---|
48 | #define JP_EUCJP 3 |
---|
49 | |
---|
50 | static wint_t |
---|
51 | __jp2uc (wint_t c, int type) |
---|
52 | { |
---|
53 | int index, adj; |
---|
54 | unsigned char byte1, byte2; |
---|
55 | wint_t ret; |
---|
56 | |
---|
57 | /* we actually use tables of EUCJP to Unicode. For JIS, we simply |
---|
58 | note that EUCJP is essentially JIS with the top bits on in each |
---|
59 | byte and translate to EUCJP. For SJIS, we do a translation to EUCJP before |
---|
60 | accessing the tables. */ |
---|
61 | switch (type) |
---|
62 | { |
---|
63 | case JP_JIS: |
---|
64 | byte1 = (c >> 8) + 0x80; |
---|
65 | byte2 = (c & 0xff) + 0x80; |
---|
66 | break; |
---|
67 | case JP_EUCJP: |
---|
68 | byte1 = (c >> 8); |
---|
69 | byte2 = (c & 0xff); |
---|
70 | break; |
---|
71 | case JP_SJIS: |
---|
72 | byte1 = c >> 8; |
---|
73 | byte2 = c & 0xff; |
---|
74 | if (byte2 <= 0x9e) |
---|
75 | { |
---|
76 | adj = 0xa1 - 0x22; |
---|
77 | byte2 = (byte2 - 31) + 0xa1; |
---|
78 | } |
---|
79 | else |
---|
80 | { |
---|
81 | adj = 0xa1 - 0x21; |
---|
82 | byte2 = (byte2 - 126) + 0xa1; |
---|
83 | } |
---|
84 | if (byte1 <= 0x9f) |
---|
85 | byte1 = ((byte1 - 112) << 1) + adj; |
---|
86 | else |
---|
87 | byte1 = ((byte1 - 176) << 1) + adj; |
---|
88 | break; |
---|
89 | default: |
---|
90 | return WEOF; |
---|
91 | } |
---|
92 | |
---|
93 | /* find conversion in jp2uc arrays */ |
---|
94 | |
---|
95 | /* handle larger ranges first */ |
---|
96 | if (byte1 >= 0xb0 && byte1 <= 0xcf && c <= 0xcfd3) |
---|
97 | { |
---|
98 | index = (byte1 - 0xb0) * 0xfe + (byte2 - 0xa1); |
---|
99 | return b02cf[index]; |
---|
100 | } |
---|
101 | else if (byte1 >= 0xd0 && byte1 <= 0xf4 && c <= 0xf4a6) |
---|
102 | { |
---|
103 | index = (byte1 - 0xd0) * 0xfe + (byte2 - 0xa1); |
---|
104 | return d02f4[index]; |
---|
105 | } |
---|
106 | |
---|
107 | /* handle smaller ranges here */ |
---|
108 | switch (byte1) |
---|
109 | { |
---|
110 | case 0xA1: |
---|
111 | return (wint_t)a1[byte2 - 0xa1]; |
---|
112 | case 0xA2: |
---|
113 | ret = a2[byte2 - 0xa1]; |
---|
114 | if (ret != 0) |
---|
115 | return (wint_t)ret; |
---|
116 | break; |
---|
117 | case 0xA3: |
---|
118 | if (a3[byte2 - 0xa1]) |
---|
119 | return (wint_t)(0xff00 + (byte2 - 0xa0)); |
---|
120 | break; |
---|
121 | case 0xA4: |
---|
122 | if (byte2 <= 0xf3) |
---|
123 | return (wint_t)(0x3000 + (byte2 - 0x60)); |
---|
124 | break; |
---|
125 | case 0xA5: |
---|
126 | if (byte2 <= 0xf6) |
---|
127 | return (wint_t)(0x3000 + byte2); |
---|
128 | break; |
---|
129 | case 0xA6: |
---|
130 | ret = 0; |
---|
131 | if (byte2 <= 0xd8) |
---|
132 | ret = (wint_t)a6[byte2 - 0xa1]; |
---|
133 | if (ret != 0) |
---|
134 | return ret; |
---|
135 | break; |
---|
136 | case 0xA7: |
---|
137 | ret = 0; |
---|
138 | if (byte2 <= 0xf1) |
---|
139 | ret = (wint_t)a7[byte2 - 0xa1]; |
---|
140 | if (ret != 0) |
---|
141 | return ret; |
---|
142 | break; |
---|
143 | case 0xA8: |
---|
144 | if (byte2 <= 0xc0) |
---|
145 | return (wint_t)a8[byte2 - 0xa1]; |
---|
146 | break; |
---|
147 | default: |
---|
148 | return WEOF; |
---|
149 | } |
---|
150 | |
---|
151 | return WEOF; |
---|
152 | } |
---|
153 | |
---|
154 | wint_t |
---|
155 | _jp2uc (wint_t c) |
---|
156 | { |
---|
157 | if (!strcmp (__current_locale_charset (), "JIS")) |
---|
158 | c = __jp2uc (c, JP_JIS); |
---|
159 | else if (!strcmp (__current_locale_charset (), "SJIS")) |
---|
160 | c = __jp2uc (c, JP_SJIS); |
---|
161 | else if (!strcmp (__current_locale_charset (), "EUCJP")) |
---|
162 | c = __jp2uc (c, JP_EUCJP); |
---|
163 | return c; |
---|
164 | } |
---|
165 | |
---|
166 | #endif /* !__CYGWIN__ */ |
---|
167 | #endif /* _MB_CAPABLE */ |
---|