/* [<][>][^][v][top][bottom][index][help] */
1 /*
2 * char-sjis.h
3 *
4 * Copyright (c) 2000-2004 Shiro Kawai, 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
8 * are met:
9 *
10 * 1. Redistributions of source code must retain the above copyright
11 * notice, this list of conditions and the following disclaimer.
12 *
13 * 2. Redistributions in binary form must reproduce the above copyright
14 * notice, this list of conditions and the following disclaimer in the
15 * documentation and/or other materials provided with the distribution.
16 *
17 * 3. Neither the name of the authors nor the names of its contributors
18 * may be used to endorse or promote products derived from this
19 * software without specific prior written permission.
20 *
21 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
22 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
23 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
24 * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
25 * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
26 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
27 * TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
28 * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
29 * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
30 * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
31 * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
32 *
33 * $Id: char_sjis.h,v 1.6 2004/09/17 03:42:10 shirok Exp $
34 */
35
36 #ifndef SCM_CHAR_ENCODING_BODY
37 /*===============================================================
38 * Header part
39 */
40
41 /* The name of the encoding. Scheme procedure
42 * gauche-character-encoding returns a symbol with this name.
43 */
44 #define SCM_CHAR_ENCODING_NAME "sjis"
45
46 /* Given first byte of the multibyte character, returns # of
47 * bytes that follows, i.e. if the byte consists a single-byte
48 * character, it returns 0; if the byte is the first byte of
49 * two-byte character, it returns 1. It may return -1 if
50 * the given byte can't be a valid first byte of multibyte characters.
51 */
52 #define SCM_CHAR_NFOLLOWS(byte) \
53 (((unsigned char)(byte)) < 0x81? 0 : \
54 (((unsigned char)(byte)) < 0xa0? 1 : \
55 (((unsigned char)(byte)) < 0xe0? 0 : 1)))
56
57 /* Given wide character CH, returns # of bytes used when CH is
58 * encoded in multibyte string.
59 */
60 #define SCM_CHAR_NBYTES(ch) (((ch) > 0x0ff) ? 2 : 1)
61
62 /* Maximun # of multibyte character */
63 #define SCM_CHAR_MAX_BYTES 2
64
65 /* From a multibyte string pointed by const char *cp, extract a character
66 * and store it in ScmChar ch. If cp doesn't point to valid multibyte
67 * character, store SCM_CHAR_INVALID to ch. cp is not modified.
68 */
69 #define SCM_CHAR_GET(cp, ch) \
70 do { \
71 (ch) = (unsigned char)*(cp); \
72 if ((unsigned char)(ch) >= 0x80) { \
73 if ((unsigned char)(ch) < 0xa0 || (unsigned char)(ch) >= 0xe0) { \
74 (ch) = (((unsigned char)(ch)) << 8) + (unsigned char)*(cp+1); \
75 } \
76 } \
77 } while (0)
78
79 /* Convert a character CH to multibyte form and put it to the buffer
80 * starting from char *cp. You can assume the buffer has enough length
81 * to contain the multibyte char. cp is not modified.
82 */
83 #define SCM_CHAR_PUT(cp, ch) \
84 do { \
85 if ((ch) > 0xff) { \
86 (cp)[0] = (ch >> 8) & 0xff; \
87 (cp)[1] = ch & 0xff; \
88 } else { \
89 (cp)[0] = ch & 0xff; \
90 } \
91 } while (0)
92
93 /* const char *cp points to a multibyte string. Set const char *result
94 * to point to the previous character of the one cp points to.
95 * const char *start points to the beginning of the buffer.
96 * result is set to NULL if there's no valid multibyte char found
97 * just before cp. cp and start is not modified.
98 */
99 #define SCM_CHAR_BACKWARD(cp, start, result) \
100 do { \
101 (result) = (cp); \
102 if ((result) == (start)) (result) = NULL; \
103 else if ((result) == (start) + 1) (result) = (start); \
104 else if (SCM_CHAR_NFOLLOWS(*((result)-2)) == 1) { \
105 (result) -= 2; \
106 } else { \
107 (result) -= 1; \
108 } \
109 } while (0)
110
111 #else /* !SCM_CHAR_ENCODING_BODY */
112 /*==================================================================
113 * This part is included in char.c
114 */
115
116 /* Array of character encoding names, recognizable by iconv, that are
117 compatible with this native encoding. */
118 static const char *supportedCharacterEncodings[] = {
119 "SHIFT_JIS",
120 "SHIFT-JIS",
121 "SHIFT_JISX0213",
122 "SHIFT-JISX0213",
123 "SJIS",
124 NULL
125 };
126
127 #endif /* !SCM_CHAR_ENCODING_BODY */