1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
|
/*
* utf8.c - Handle UTF-8 sequence.
*
* Copyright (C) 2012 by Hatuka*nezumi - IKEDA Soji.
*
* This file is part of the Sombok Package. This program is free
* software; you can redistribute it and/or modify it under the terms of
* either the GNU General Public License or the Artistic License, as
* specified in the README file.
*
*/
#include "sombok.h"
/** @defgroup utf8 utf8
* @brief Handle UTF-8 sequence.
*
* @note This module was introduced by release 2.1.0.
*
*@{*/
/** Decode UTF-8 string to Unicode string
*
* @param[out] unistr Unicode string, must not be NULL.
* @param[in] maxchars maximum number of characters to be decoded.
* 0 means infinite
* @param[in] utf8 source UTF-8 string
* @param[in] utf8len length of string
* @param[in] check 0: no check; 1: check malformed sequence; 2: check
* surrogate too; 3: check codes beyond Unicode too
*
* @returns Unicode string.
* If unistr->str was NULL or maxchars was 0 (infinite), required buffer will
* be (re-)allocated.
* If error occurred, NULL is returned and errno is set.
*
* @note unistr->str must not point to static memory.
*/
unistr_t *sombok_decode_utf8(unistr_t *unistr, size_t maxchars,
const char *utf8, size_t utf8len, int check)
{
size_t i, unilen;
unichar_t unichar, *uni;
int pass;
if (unistr == NULL) {
errno = EINVAL;
return NULL;
}
uni = unistr->str;
if (utf8 == NULL)
utf8len = 0;
for (pass = 1; pass <= 2; pass++) {
for (i = 0, unilen = 0; i < utf8len; unilen++) {
if (maxchars != 0 && maxchars < unilen + 1)
break;
if ((utf8[i] & 0x80) == 0) {
if (pass == 2)
uni[unilen] = utf8[i];
i++;
} else if (i + 1 < utf8len &&
(utf8[i] & 0xE0) == 0xC0 &&
(utf8[i + 1] & 0xC0) == 0x80) {
if (pass == 2) {
unichar = utf8[i] & 0x1F;
unichar <<= 6;
unichar |= utf8[i + 1] & 0x3F;
uni[unilen] = unichar;
}
i += 2;
} else if (i + 2 < utf8len &&
(utf8[i] & 0xF0) == 0xE0 &&
(utf8[i + 1] & 0xC0) == 0x80 &&
(utf8[i + 2] & 0xC0) == 0x80) {
if (SOMBOK_UTF8_CHECK_SURROGATE <= check &&
(utf8[i] & 0x0F) == 0x0D && (utf8[i + 1] & 0x20) == 0x20) {
errno = EPERM;
return NULL;
}
if (pass == 2) {
unichar = utf8[i] & 0x0F;
unichar <<= 6;
unichar |= utf8[i + 1] & 0x3F;
unichar <<= 6;
unichar |= utf8[i + 2] & 0x3F;
uni[unilen] = unichar;
}
i += 3;
} else if (i + 3 < utf8len &&
(utf8[i] & 0xF8) == 0xF0 &&
(utf8[i + 1] & 0xC0) == 0x80 &&
(utf8[i + 2] & 0xC0) == 0x80 &&
(utf8[i + 3] & 0xC0) == 0x80) {
if (SOMBOK_UTF8_CHECK_NONUNICODE <= check &&
0x10 <
(((utf8[i] & 0x07) << 2) | ((utf8[i + 1] & 0x30) >> 4))) {
errno = EPERM;
return NULL;
}
if (pass == 2) {
unichar = utf8[i] & 0x07;
unichar <<= 6;
unichar |= utf8[i + 1] & 0x3F;
unichar <<= 6;
unichar |= utf8[i + 2] & 0x3F;
unichar <<= 6;
unichar |= utf8[i + 3] & 0x3F;
uni[unilen] = unichar;
}
i += 4;
} else if (SOMBOK_UTF8_CHECK_NONUNICODE <= check) {
errno = EPERM;
return NULL;
} else if (i + 4 < utf8len &&
(utf8[i] & 0xFC) == 0xF8 &&
(utf8[i + 1] & 0xC0) == 0x80 &&
(utf8[i + 2] & 0xC0) == 0x80 &&
(utf8[i + 3] & 0xC0) == 0x80 &&
(utf8[i + 4] & 0xC0) == 0x80) {
if (pass == 2) {
unichar = utf8[i] & 0x03;
unichar <<= 6;
unichar |= utf8[i + 1] & 0x3F;
unichar <<= 6;
unichar |= utf8[i + 2] & 0x3F;
unichar <<= 6;
unichar |= utf8[i + 3] & 0x3F;
unichar <<= 6;
unichar |= utf8[i + 4] & 0x3F;
uni[unilen] = unichar;
}
i += 5;
} else if (i + 5 < utf8len &&
(utf8[i] & 0xFE) == 0xFC &&
(utf8[i + 1] & 0xC0) == 0x80 &&
(utf8[i + 2] & 0xC0) == 0x80 &&
(utf8[i + 3] & 0xC0) == 0x80 &&
(utf8[i + 4] & 0xC0) == 0x80 &&
(utf8[i + 5] & 0xC0) == 0x80) {
if (pass == 2) {
unichar = utf8[i] & 0x01;
unichar <<= 6;
unichar |= utf8[i + 1] & 0x3F;
unichar <<= 6;
unichar |= utf8[i + 2] & 0x3F;
unichar <<= 6;
unichar |= utf8[i + 3] & 0x3F;
unichar <<= 6;
unichar |= utf8[i + 4] & 0x3F;
unichar <<= 6;
unichar |= utf8[i + 5] & 0x3F;
uni[unilen] = unichar;
}
i += 6;
} else {
if (SOMBOK_UTF8_CHECK_MALFORMED <= check) {
errno = EPERM;
return NULL;
}
if (pass == 2)
uni[unilen] = utf8[i];
i++;
}
}
if (pass == 1) {
if (uni == NULL) {
if ((uni = malloc(sizeof(unichar_t) * (unilen + 1))) == NULL)
return NULL;
uni[unilen] = 0;
} else if (maxchars == 0) {
if ((uni = realloc(uni,
sizeof(unichar_t) * (unilen + 1))) == NULL)
return NULL;
uni[unilen] = 0;
} else if (unilen < maxchars)
uni[unilen] = 0;
unistr->str = uni;
unistr->len = unilen;
}
}
return unistr;
}
/** Encode Unicode string to UTF-8 string
*
* @param[out] utf8 string buffer, may be NULL.
* @param[out] utf8lenp pointer to length of buffer, may be NULL.
* @param[in] maxbytes maximum number of bytes to be encoded. 0 means infinite
* @param[in] unistr source Unicode string, must not be NULL.
*
* @returns string buffer.
* If utf8 was NULL or maxbytes was 0 (infinite), required buffer will be
* (re-)allocated.
* If error occurred, NULL is returned and errno is set.
*
* @note utf8 must not point to static memory.
*/
char *sombok_encode_utf8(char *utf8, size_t *utf8lenp, size_t maxbytes,
unistr_t *unistr)
{
size_t i, utf8len, unilen;
unichar_t unichar;
int pass;
if (unistr == NULL) {
errno = EINVAL;
return NULL;
}
if (unistr->str == NULL)
unilen = 0;
else
unilen = unistr->len;
for (pass = 1; pass <= 2; pass++) {
for (i = 0, utf8len = 0; i < unilen; i++) {
unichar = unistr->str[i];
if (unichar == (unichar & 0x007F)) {
if (maxbytes != 0 && maxbytes < utf8len + 1)
break;
if (pass == 2)
utf8[utf8len] = (char) unichar;
utf8len++;
} else if (unichar == (unichar & 0x07FF)) {
if (maxbytes != 0 && maxbytes < utf8len + 2)
break;
if (pass == 2) {
utf8[utf8len + 1] = (char) (unichar & 0x3F) | 0x80;
unichar >>= 6;
utf8[utf8len] = (char) (unichar & 0x1F) | 0xC0;
}
utf8len += 2;
} else if (unichar == (unichar & 0x00FFFF)) {
if (maxbytes != 0 && maxbytes < utf8len + 3)
break;
if (pass == 2) {
utf8[utf8len + 2] = (char) (unichar & 0x3F) | 0x80;
unichar >>= 6;
utf8[utf8len + 1] = (char) (unichar & 0x3F) | 0x80;
unichar >>= 6;
utf8[utf8len] = (char) (unichar & 0x0F) | 0xE0;
}
utf8len += 3;
} else if (unichar == (unichar & 0x001FFFFF)) {
if (maxbytes != 0 && maxbytes < utf8len + 4)
break;
if (pass == 2) {
utf8[utf8len + 3] = (char) (unichar & 0x3F) | 0x80;
unichar >>= 6;
utf8[utf8len + 2] = (char) (unichar & 0x3F) | 0x80;
unichar >>= 6;
utf8[utf8len + 1] = (char) (unichar & 0x3F) | 0x80;
unichar >>= 6;
utf8[utf8len] = (char) (unichar & 0x07) | 0xF0;
}
utf8len += 4;
} else if (unichar == (unichar & 0x03FFFFFF)) {
if (maxbytes != 0 && maxbytes < utf8len + 5)
break;
if (pass == 2) {
utf8[utf8len + 4] = (char) (unichar & 0x3F) | 0x80;
unichar >>= 6;
utf8[utf8len + 3] = (char) (unichar & 0x3F) | 0x80;
unichar >>= 6;
utf8[utf8len + 2] = (char) (unichar & 0x3F) | 0x80;
unichar >>= 6;
utf8[utf8len + 1] = (char) (unichar & 0x3F) | 0x80;
unichar >>= 6;
utf8[utf8len] = (char) (unichar & 0x03) | 0xF8;
}
utf8len += 5;
} else if (unichar == (unichar & 0x7FFFFFFF)) {
if (maxbytes != 0 && maxbytes < utf8len + 6)
break;
if (pass == 2) {
utf8[utf8len + 5] = (char) (unichar & 0x3F) | 0x80;
unichar >>= 6;
utf8[utf8len + 4] = (char) (unichar & 0x3F) | 0x80;
unichar >>= 6;
utf8[utf8len + 3] = (char) (unichar & 0x3F) | 0x80;
unichar >>= 6;
utf8[utf8len + 2] = (char) (unichar & 0x3F) | 0x80;
unichar >>= 6;
utf8[utf8len + 1] = (char) (unichar & 0x3F) | 0x80;
unichar >>= 6;
utf8[utf8len] = (char) (unichar & 0x01) | 0xFC;
}
utf8len += 6;
} else {
errno = EPERM;
return NULL;
}
}
if (pass == 1) {
if (utf8 == NULL) {
if ((utf8 = malloc(sizeof(char) * (utf8len + 1))) == NULL)
return NULL;
utf8[utf8len] = '\0';
} else if (maxbytes == 0) {
if ((utf8 = realloc(utf8,
sizeof(char) * (utf8len + 1))) == NULL)
return NULL;
utf8[utf8len] = '\0';
} else if (utf8len < maxbytes)
utf8[utf8len] = '\0';
if (utf8lenp != NULL)
*utf8lenp = utf8len;
}
}
return utf8;
}
|
