/* [<][>][^][v][top][bottom][index][help] */
DEFINITIONS
This source file includes following definitions.
- Scm_CharUtf8Getc
- Scm_CharUtf8Putc
1 /*
2 * char_utf8.h - UTF8 encoding interface
3 *
4 * Copyright (c) 2000-2003 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_utf_8.h,v 1.10 2005/08/05 11:38:26 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 "utf-8"
45
46 SCM_EXTERN char Scm_CharSizeTable[];
47 SCM_EXTERN ScmChar Scm_CharUtf8Getc(const unsigned char *);
48 SCM_EXTERN void Scm_CharUtf8Putc(unsigned char *, ScmChar);
49
50 /* Given first byte of the multibyte character, returns # of
51 * bytes that follows, i.e. if the byte consists a single-byte
52 * character, it returns 0; if the byte is the first byte of
53 * two-byte character, it returns 1. It may return -1 if
54 * the given byte can't be a valid first byte of multibyte characters.
55 */
56 #define SCM_CHAR_NFOLLOWS(ch) ((int)Scm_CharSizeTable[(unsigned char)(ch)])
57
58 /* Given wide character CH, returns # of bytes used when CH is
59 * encoded in multibyte string.
60 */
61 #define SCM_CHAR_NBYTES(ch) \
62 (((ch) < 0x80) ? 1 : \
63 (((ch) < 0x800) ? 2 : \
64 (((ch) < 0x10000) ? 3 : \
65 (((ch) < 0x200000) ? 4 : \
66 (((ch) < 0x4000000) ? 5 : 6)))))
67
68 /* Maximun # of multibyte character */
69 #define SCM_CHAR_MAX_BYTES 6
70
71 /* From a multibyte string pointed by const char *cp, extract a character
72 * and store it in ScmChar ch. If cp doesn't point to valid multibyte
73 * character, store SCM_CHAR_INVALID to ch. cp is not modified.
74 */
75 #define SCM_CHAR_GET(cp, ch) \
76 do { \
77 if (((ch) = (unsigned char)*(cp)) >= 0x80) { \
78 (ch) = Scm_CharUtf8Getc((unsigned char*)cp); \
79 } \
80 } while (0)
81
82 /* Convert a character CH to multibyte form and put it to the buffer
83 * starting from char *cp. You can assume the buffer has enough length
84 * to contain the multibyte char. cp is not modified.
85 */
86 #define SCM_CHAR_PUT(cp, ch) \
87 do { \
88 if (ch >= 0x80) { \
89 Scm_CharUtf8Putc((unsigned char*)cp, ch); \
90 } else { \
91 *(cp) = (ch); \
92 } \
93 } while (0)
94
95 /* const char *cp points to a multibyte string. Set const char *result
96 * to point to the previous character of the one cp points to.
97 * const char *start points to the beginning of the buffer.
98 * result is set to NULL if there's no valid multibyte char found
99 * just before cp. cp and start is not modified.
100 */
101 #define SCM_CHAR_BACKWARD(cp, start, result) \
102 do { \
103 switch ((cp) - (start)) { \
104 default: \
105 (result) = (cp) - 6; \
106 if (SCM_CHAR_NFOLLOWS(*(result)) == 5) break; \
107 /* FALLTHROUGH */ \
108 case 5: \
109 (result) = (cp) - 5; \
110 if (SCM_CHAR_NFOLLOWS(*(result)) == 4) break; \
111 /* FALLTHROUGH */ \
112 case 4: \
113 (result) = (cp) - 4; \
114 if (SCM_CHAR_NFOLLOWS(*(result)) == 3) break; \
115 /* FALLTHROUGH */ \
116 case 3: \
117 (result) = (cp) - 3; \
118 if (SCM_CHAR_NFOLLOWS(*(result)) == 2) break; \
119 /* FALLTHROUGH */ \
120 case 2: \
121 (result) = (cp) - 2; \
122 if (SCM_CHAR_NFOLLOWS(*(result)) == 1) break; \
123 /* FALLTHROUGH */ \
124 case 1: \
125 (result) = (cp) - 1; \
126 if (SCM_CHAR_NFOLLOWS(*(result)) == 0) break; \
127 (result) = NULL; \
128 } \
129 } while (0)
130
131 #else /* !SCM_CHAR_ENCODING_BODY */
132 /*==================================================================
133 * This part is included in char.c
134 */
135
136 /* Array of character encoding names, recognizable by iconv, that are
137 compatible with this native encoding. */
138 static const char *supportedCharacterEncodings[] = {
139 "UTF-8",
140 "ISO-10646/UTF-8",
141 "UTF8",
142 NULL
143 };
144
145 char Scm_CharSizeTable[256] = {
146 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 0x */
147 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 1x */
148 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 2x */
149 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 3x */
150 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 4x */
151 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 5x */
152 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 6x */
153 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 7x */
154 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 8x */
155 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 9x */
156 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* ax */
157 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* bx */
158 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, /* cx */
159 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, /* dx */
160 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, /* ex */
161 3, 3, 3, 3, 3, 3, 3, 3, 4, 4, 4, 4, 5, 5, 0, 0 /* fx */
162 };
163
164 ScmChar Scm_CharUtf8Getc(const unsigned char *cp)
165 {
166 ScmChar ch;
167 unsigned char *ucp = (unsigned char *)cp;
168 unsigned char first = *ucp++;
169 if (first < 0x80) { ch = first; }
170 else if (first < 0xc0) { ch = SCM_CHAR_INVALID; }
171 else if (first < 0xe0) {
172 ch = first&0x1f;
173 ch = (ch<<6) | (*ucp++&0x3f);
174 if (ch < 0x80) ch = SCM_CHAR_INVALID;
175 }
176 else if (first < 0xf0) {
177 ch = first&0x0f;
178 ch = (ch<<6) | (*ucp++&0x3f);
179 ch = (ch<<6) | (*ucp++&0x3f);
180 if (ch < 0x800) ch = SCM_CHAR_INVALID;
181 }
182 else if (first < 0xf8) {
183 ch = first&0x07;
184 ch = (ch<<6) | (*ucp++&0x3f);
185 ch = (ch<<6) | (*ucp++&0x3f);
186 ch = (ch<<6) | (*ucp++&0x3f);
187 if (ch < 0x10000) ch = SCM_CHAR_INVALID;
188 }
189 else if (first < 0xfc) {
190 ch = first&0x03;
191 ch = (ch<<6) | (*ucp++&0x3f);
192 ch = (ch<<6) | (*ucp++&0x3f);
193 ch = (ch<<6) | (*ucp++&0x3f);
194 ch = (ch<<6) | (*ucp++&0x3f);
195 if (ch < 0x200000) ch = SCM_CHAR_INVALID;
196 }
197 else if (first < 0xfe) {
198 ch = first&0x01;
199 ch = (ch<<6) | (*ucp++&0x3f);
200 ch = (ch<<6) | (*ucp++&0x3f);
201 ch = (ch<<6) | (*ucp++&0x3f);
202 ch = (ch<<6) | (*ucp++&0x3f);
203 ch = (ch<<6) | (*ucp++&0x3f);
204 if (ch < 0x4000000) ch = SCM_CHAR_INVALID;
205 }
206 else {
207 ch = SCM_CHAR_INVALID;
208 }
209 return ch;
210 }
211
212 void Scm_CharUtf8Putc(unsigned char *cp, ScmChar ch)
213 {
214 if (ch < 0x80) {
215 *cp = ch;
216 }
217 else if (ch < 0x800) {
218 *cp++ = ((ch>>6)&0x1f) | 0xc0;
219 *cp = (ch&0x3f) | 0x80;
220 }
221 else if (ch < 0x10000) {
222 *cp++ = ((ch>>12)&0x0f) | 0xe0;
223 *cp++ = ((ch>>6)&0x3f) | 0x80;
224 *cp = (ch&0x3f) | 0x80;
225 }
226 else if (ch < 0x200000) {
227 *cp++ = ((ch>>18)&0x07) | 0xf0;
228 *cp++ = ((ch>>12)&0x3f) | 0x80;
229 *cp++ = ((ch>>6)&0x3f) | 0x80;
230 *cp = (ch&0x3f) | 0x80;
231 }
232 else if (ch < 0x4000000) {
233 *cp++ = ((ch>>24)&0x03) | 0xf8;
234 *cp++ = ((ch>>18)&0x3f) | 0x80;
235 *cp++ = ((ch>>12)&0x3f) | 0x80;
236 *cp++ = ((ch>>6)&0x3f) | 0x80;
237 *cp = (ch&0x3f) | 0x80;
238 } else {
239 *cp++ = ((ch>>30)&0x1) | 0xfc;
240 *cp++ = ((ch>>24)&0x3f) | 0x80;
241 *cp++ = ((ch>>18)&0x3f) | 0x80;
242 *cp++ = ((ch>>12)&0x3f) | 0x80;
243 *cp++ = ((ch>>6)&0x3f) | 0x80;
244 *cp++ = (ch&0x3f) | 0x80;
245 }
246 }
247
248 #endif /* !SCM_CHAR_ENCODING_BODY */