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
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
|
/* $OpenBSD: citrus_utf8.c,v 1.10 2015/09/05 15:22:04 semarie Exp $ */
/*-
* Copyright (c) 2002-2004 Tim J. Robbins
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*/
#include <sys/errno.h>
#include <sys/types.h>
#include <sys/limits.h>
#include <errno.h>
#include <stdio.h>
#include <stdlib.h>
#include <stddef.h>
#include <string.h>
#include <wchar.h>
#include "citrus_ctype.h"
#include "citrus_utf8.h"
#define MINIMUM(a, b) (((a) < (b)) ? (a) : (b))
_CITRUS_CTYPE_DEF_OPS(utf8);
struct _utf8_state {
wchar_t ch;
int want;
wchar_t lbound;
};
size_t
/*ARGSUSED*/
_citrus_utf8_ctype_mbrtowc(wchar_t * __restrict pwc,
const char * __restrict s, size_t n,
void * __restrict pspriv)
{
struct _utf8_state *us;
int ch, i, mask, want;
wchar_t lbound, wch;
us = (struct _utf8_state *)pspriv;
if (us->want < 0 || us->want > _CITRUS_UTF8_MB_CUR_MAX) {
errno = EINVAL;
return ((size_t)-1);
}
if (s == NULL) {
s = "";
n = 1;
pwc = NULL;
}
if (n == 0) {
/* Incomplete multibyte sequence */
return ((size_t)-2);
}
if (us->want == 0 && ((ch = (unsigned char)*s) & ~0x7f) == 0) {
/* Fast path for plain ASCII characters. */
if (pwc != NULL)
*pwc = ch;
return (ch != '\0' ? 1 : 0);
}
if (us->want == 0) {
/*
* Determine the number of octets that make up this character
* from the first octet, and a mask that extracts the
* interesting bits of the first octet. We already know
* the character is at least two bytes long.
*
* We also specify a lower bound for the character code to
* detect redundant, non-"shortest form" encodings. For
* example, the sequence C0 80 is _not_ a legal representation
* of the null character. This enforces a 1-to-1 mapping
* between character codes and their multibyte representations.
*/
ch = (unsigned char)*s;
if ((ch & 0x80) == 0) {
mask = 0x7f;
want = 1;
lbound = 0;
} else if ((ch & 0xe0) == 0xc0) {
mask = 0x1f;
want = 2;
lbound = 0x80;
} else if ((ch & 0xf0) == 0xe0) {
mask = 0x0f;
want = 3;
lbound = 0x800;
} else if ((ch & 0xf8) == 0xf0) {
mask = 0x07;
want = 4;
lbound = 0x10000;
} else {
/*
* Malformed input; input is not UTF-8.
* See RFC 3629.
*/
errno = EILSEQ;
return ((size_t)-1);
}
} else {
want = us->want;
lbound = us->lbound;
}
/*
* Decode the octet sequence representing the character in chunks
* of 6 bits, most significant first.
*/
if (us->want == 0)
wch = (unsigned char)*s++ & mask;
else
wch = us->ch;
for (i = (us->want == 0) ? 1 : 0; i < MINIMUM(want, n); i++) {
if ((*s & 0xc0) != 0x80) {
/*
* Malformed input; bad characters in the middle
* of a character.
*/
errno = EILSEQ;
return ((size_t)-1);
}
wch <<= 6;
wch |= *s++ & 0x3f;
}
if (i < want) {
/* Incomplete multibyte sequence. */
us->want = want - i;
us->lbound = lbound;
us->ch = wch;
return ((size_t)-2);
}
if (wch < lbound) {
/*
* Malformed input; redundant encoding.
*/
errno = EILSEQ;
return ((size_t)-1);
}
if (wch >= 0xd800 && wch <= 0xdfff) {
/*
* Malformed input; invalid code points.
*/
errno = EILSEQ;
return ((size_t)-1);
}
if (wch > 0x10ffff) {
/*
* Malformed input; invalid code points.
*/
errno = EILSEQ;
return ((size_t)-1);
}
if (pwc != NULL)
*pwc = wch;
us->want = 0;
return (wch == L'\0' ? 0 : want);
}
int
/*ARGSUSED*/
_citrus_utf8_ctype_mbsinit(const void * __restrict pspriv)
{
return (pspriv == NULL ||
((const struct _utf8_state *)pspriv)->want == 0);
}
size_t
/*ARGSUSED*/
_citrus_utf8_ctype_mbsnrtowcs(wchar_t * __restrict dst,
const char ** __restrict src,
size_t nmc, size_t len,
void * __restrict pspriv)
{
struct _utf8_state *us;
size_t i, o, r;
us = (struct _utf8_state *)pspriv;
if (dst == NULL) {
/*
* The fast path in the loop below is not safe if an ASCII
* character appears as anything but the first byte of a
* multibyte sequence. Check now to avoid doing it in the loop.
*/
if (nmc > 0 && us->want > 0 && (unsigned char)(*src)[0] < 0x80) {
errno = EILSEQ;
return ((size_t)-1);
}
for (i = o = 0; i < nmc; i += r, o++) {
if ((unsigned char)(*src)[i] < 0x80) {
/* Fast path for plain ASCII characters. */
if ((*src)[i] == '\0')
return (o);
r = 1;
} else {
r = _citrus_utf8_ctype_mbrtowc(NULL, *src + i,
nmc - i, us);
if (r == (size_t)-1)
return (r);
if (r == (size_t)-2)
return (o);
if (r == 0)
return (o);
}
}
return (o);
}
/*
* The fast path in the loop below is not safe if an ASCII
* character appears as anything but the first byte of a
* multibyte sequence. Check now to avoid doing it in the loop.
*/
if (len > 0 && nmc > 0 && us->want > 0 && (unsigned char)(*src)[0] < 0x80) {
errno = EILSEQ;
return ((size_t)-1);
}
for (i = o = 0; i < nmc && o < len; i += r, o++) {
if ((unsigned char)(*src)[i] < 0x80) {
/* Fast path for plain ASCII characters. */
dst[o] = (wchar_t)(unsigned char)(*src)[i];
if ((*src)[i] == '\0') {
*src = NULL;
return (o);
}
r = 1;
} else {
r = _citrus_utf8_ctype_mbrtowc(dst + o, *src + i,
nmc - i, us);
if (r == (size_t)-1) {
*src += i;
return (r);
}
if (r == (size_t)-2) {
*src += nmc;
return (o);
}
if (r == 0) {
*src = NULL;
return (o);
}
}
}
*src += i;
return (o);
}
size_t
/*ARGSUSED*/
_citrus_utf8_ctype_wcrtomb(char * __restrict s,
wchar_t wc, void * __restrict pspriv)
{
struct _utf8_state *us;
unsigned char lead;
int i, len;
us = (struct _utf8_state *)pspriv;
if (us->want != 0) {
errno = EINVAL;
return ((size_t)-1);
}
if (s == NULL) {
/* Reset to initial shift state (no-op) */
return (1);
}
if ((wc & ~0x7f) == 0) {
/* Fast path for plain ASCII characters. */
*s = (char)wc;
return (1);
}
/*
* Determine the number of octets needed to represent this character.
* We always output the shortest sequence possible. Also specify the
* first few bits of the first octet, which contains the information
* about the sequence length.
*/
if ((wc & ~0x7f) == 0) {
lead = 0;
len = 1;
} else if ((wc & ~0x7ff) == 0) {
lead = 0xc0;
len = 2;
} else if ((wc & ~0xffff) == 0) {
lead = 0xe0;
len = 3;
} else if ((wc & ~0x1fffff) == 0) {
lead = 0xf0;
len = 4;
} else {
errno = EILSEQ;
return ((size_t)-1);
}
/*
* Output the octets representing the character in chunks
* of 6 bits, least significant last. The first octet is
* a special case because it contains the sequence length
* information.
*/
for (i = len - 1; i > 0; i--) {
s[i] = (wc & 0x3f) | 0x80;
wc >>= 6;
}
*s = (wc & 0xff) | lead;
return (len);
}
size_t
/*ARGSUSED*/
_citrus_utf8_ctype_wcsnrtombs(char * __restrict dst,
const wchar_t ** __restrict src,
size_t nwc, size_t len,
void * __restrict pspriv)
{
struct _utf8_state *us;
char buf[_CITRUS_UTF8_MB_CUR_MAX];
size_t i, o, r;
us = (struct _utf8_state *)pspriv;
if (us->want != 0) {
errno = EINVAL;
return ((size_t)-1);
}
if (dst == NULL) {
for (i = o = 0; i < nwc; i++, o += r) {
wchar_t wc = (*src)[i];
if (wc >= 0 && wc < 0x80) {
/* Fast path for plain ASCII characters. */
if (wc == 0)
return (o);
r = 1;
} else {
r = _citrus_utf8_ctype_wcrtomb(buf, wc, us);
if (r == (size_t)-1)
return (r);
}
}
return (o);
}
for (i = o = 0; i < nwc && o < len; i++, o += r) {
wchar_t wc = (*src)[i];
if (wc >= 0 && wc < 0x80) {
/* Fast path for plain ASCII characters. */
dst[o] = (wchar_t)wc;
if (wc == 0) {
*src = NULL;
return (o);
}
r = 1;
} else if (len - o >= _CITRUS_UTF8_MB_CUR_MAX) {
/* Enough space to translate in-place. */
r = _citrus_utf8_ctype_wcrtomb(dst + o, wc, us);
if (r == (size_t)-1) {
*src += i;
return (r);
}
} else {
/* May not be enough space; use temp buffer. */
r = _citrus_utf8_ctype_wcrtomb(buf, wc, us);
if (r == (size_t)-1) {
*src += i;
return (r);
}
if (r > len - o)
break;
memcpy(dst + o, buf, r);
}
}
*src += i;
return (o);
}
|