1 /*
2 * Copyright 2013 Garrett D'Amore <garrett@damore.org>
3 * Copyright 2010 Nexenta Systems, Inc. All rights reserved.
4 * Copyright (c) 2002-2004 Tim J. Robbins. All rights reserved.
5 * Copyright (c) 1993
6 * The Regents of the University of California. All rights reserved.
7 *
8 * This code is derived from software contributed to Berkeley by
9 * Paul Borman at Krystal Technologies.
10 *
11 * Copyright (c) 2011 The FreeBSD Foundation
12 * All rights reserved.
13 * Portions of this software were developed by David Chisnall
14 * under sponsorship from the FreeBSD Foundation.
15 *
16 * Redistribution and use in source and binary forms, with or without
17 * modification, are permitted provided that the following conditions
18 * are met:
19 * 1. Redistributions of source code must retain the above copyright
20 * notice, this list of conditions and the following disclaimer.
21 * 2. Redistributions in binary form must reproduce the above copyright
22 * notice, this list of conditions and the following disclaimer in the
23 * documentation and/or other materials provided with the distribution.
24 * 3. Neither the name of the University nor the names of its contributors
25 * may be used to endorse or promote products derived from this software
26 * without specific prior written permission.
27 *
28 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
29 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
30 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
31 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
32 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
33 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
34 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
35 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
36 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
37 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
38 * SUCH DAMAGE.
39 *
40 * @(#)none.c 8.1 (Berkeley) 6/4/93
41 */
42
43 #include <errno.h>
44 #include <limits.h>
45 #include <runetype.h>
46 #include <stddef.h>
47 #include <stdio.h>
48 #include <stdlib.h>
49 #include <string.h>
50 #include <wchar.h>
51 #include "mblocal.h"
52
53 static size_t _none_mbrtowc(wchar_t * __restrict, const char * __restrict,
54 size_t, mbstate_t * __restrict);
55 static int _none_mbsinit(const mbstate_t *);
56 static size_t _none_mbsnrtowcs(wchar_t * __restrict dst,
57 const char ** __restrict src, size_t nms, size_t len,
58 mbstate_t * __restrict ps __unused);
59 static size_t _none_wcrtomb(char * __restrict, wchar_t,
60 mbstate_t * __restrict);
61 static size_t _none_wcsnrtombs(char * __restrict, const wchar_t ** __restrict,
62 size_t, size_t, mbstate_t * __restrict);
63
64 /* setup defaults */
65
66 int __mb_cur_max = 1;
67 int __mb_sb_limit = 256; /* Expected to be <= _CACHED_RUNES */
68
69 int
_none_init(struct xlocale_ctype * l,_RuneLocale * rl)70 _none_init(struct xlocale_ctype *l, _RuneLocale *rl)
71 {
72
73 l->__mbrtowc = _none_mbrtowc;
74 l->__mbsinit = _none_mbsinit;
75 l->__mbsnrtowcs = _none_mbsnrtowcs;
76 l->__wcrtomb = _none_wcrtomb;
77 l->__wcsnrtombs = _none_wcsnrtombs;
78 l->runes = rl;
79 l->__mb_cur_max = 1;
80 l->__mb_sb_limit = 256;
81 return(0);
82 }
83
84 static int
_none_mbsinit(const mbstate_t * ps __unused)85 _none_mbsinit(const mbstate_t *ps __unused)
86 {
87
88 /*
89 * Encoding is not state dependent - we are always in the
90 * initial state.
91 */
92 return (1);
93 }
94
95 static size_t
_none_mbrtowc(wchar_t * __restrict pwc,const char * __restrict s,size_t n,mbstate_t * __restrict ps __unused)96 _none_mbrtowc(wchar_t * __restrict pwc, const char * __restrict s, size_t n,
97 mbstate_t * __restrict ps __unused)
98 {
99
100 if (s == NULL)
101 /* Reset to initial shift state (no-op) */
102 return (0);
103 if (n == 0)
104 /* Incomplete multibyte sequence */
105 return ((size_t)-2);
106 if (pwc != NULL)
107 *pwc = (unsigned char)*s;
108 return (*s == '\0' ? 0 : 1);
109 }
110
111 static size_t
_none_wcrtomb(char * __restrict s,wchar_t wc,mbstate_t * __restrict ps __unused)112 _none_wcrtomb(char * __restrict s, wchar_t wc,
113 mbstate_t * __restrict ps __unused)
114 {
115
116 if (s == NULL)
117 /* Reset to initial shift state (no-op) */
118 return (1);
119 if (wc < 0 || wc > UCHAR_MAX) {
120 errno = EILSEQ;
121 return ((size_t)-1);
122 }
123 *s = (unsigned char)wc;
124 return (1);
125 }
126
127 static size_t
_none_mbsnrtowcs(wchar_t * __restrict dst,const char ** __restrict src,size_t nms,size_t len,mbstate_t * __restrict ps __unused)128 _none_mbsnrtowcs(wchar_t * __restrict dst, const char ** __restrict src,
129 size_t nms, size_t len, mbstate_t * __restrict ps __unused)
130 {
131 const char *s;
132 size_t nchr;
133
134 if (dst == NULL) {
135 s = memchr(*src, '\0', nms);
136 return (s != NULL ? s - *src : nms);
137 }
138
139 s = *src;
140 nchr = 0;
141 while (len-- > 0 && nms-- > 0) {
142 if ((*dst++ = (unsigned char)*s++) == L'\0') {
143 *src = NULL;
144 return (nchr);
145 }
146 nchr++;
147 }
148 *src = s;
149 return (nchr);
150 }
151
152 static size_t
_none_wcsnrtombs(char * __restrict dst,const wchar_t ** __restrict src,size_t nwc,size_t len,mbstate_t * __restrict ps __unused)153 _none_wcsnrtombs(char * __restrict dst, const wchar_t ** __restrict src,
154 size_t nwc, size_t len, mbstate_t * __restrict ps __unused)
155 {
156 const wchar_t *s;
157 size_t nchr;
158
159 if (dst == NULL) {
160 for (s = *src; nwc > 0 && *s != L'\0'; s++, nwc--) {
161 if (*s < 0 || *s > UCHAR_MAX) {
162 errno = EILSEQ;
163 return ((size_t)-1);
164 }
165 }
166 return (s - *src);
167 }
168
169 s = *src;
170 nchr = 0;
171 while (len-- > 0 && nwc-- > 0) {
172 if (*s < 0 || *s > UCHAR_MAX) {
173 *src = s;
174 errno = EILSEQ;
175 return ((size_t)-1);
176 }
177 if ((*dst++ = *s++) == '\0') {
178 *src = NULL;
179 return (nchr);
180 }
181 nchr++;
182 }
183 *src = s;
184 return (nchr);
185 }
186
187 /*
188 * Multibyte binary data to escaped wchar.
189 * Round-trip match guaranteed, including 0x00 bytes.
190 *
191 * Cannot return an error. *slen bytes is converted to the destination
192 * buffer until one or the other is exhausted. Destination elements returned
193 * and *slen modified with source elements processed.
194 *
195 * Incomplete sequences or partial re-encodings that would overflow the
196 * destination buffer are not processed and will also leave excess *slen.
197 *
198 * Never returns an error. Instead, incomplete sequences are not processed
199 * and *slen will index to the beginning of the incomplete sequence. It is
200 * possible for 0 to be returned and for *slen to be set to 0 due to an
201 * incomplete whole-buffer sequence, unless termination is specified.
202 *
203 * If termination is specified any trailing incomplete sequences are escaped
204 * and *slen will index to the end of the source buffer, unless insufficient
205 * room exists in the destination. If there is insufficient room, *slen may
206 * not be able to index to the end of the source buffer.
207 *
208 * Does not support a NULL dst on purpose - caller is expected to loop
209 * in parts.
210 */
211 static size_t
_none_mbintowcr(wchar_t * __restrict dst,const char * __restrict src,size_t dlen,size_t * slen,int flags __unused)212 _none_mbintowcr(wchar_t * __restrict dst, const char * __restrict src,
213 size_t dlen, size_t *slen, int flags __unused)
214 {
215 size_t i;
216 size_t j;
217 size_t n = *slen;
218
219 for (i = j = 0; i < n; ++i) {
220 if (j == dlen)
221 break;
222 if (dst)
223 dst[j] = (unsigned char)src[i];
224 ++j;
225 }
226 /* no partial sequences so we can ignore flags */
227 *slen = i;
228
229 return j;
230 }
231
232 /*
233 * Escaped wchar to multibyte binary data.
234 * Round-trip match guaranteed, including 0x00 bytes.
235 *
236 * *slen bytes is converted to the destination buffer until one or the other
237 * is exhausted. Destination elements returned and *slen modified with
238 * source elements processed.
239 *
240 * Can return an error only if the first wchar src[] element is illegal,
241 * otherwise will process up to the illegal wchar and return an error on
242 * the next call (if called with the remainder).
243 *
244 * Never returns -2. Instead, incomplete sequences are not processed and
245 * *slen will index to the beginning of the incomplete sequence. If
246 * termination is specified, incomplete sequences are discarded and *slen
247 * indexes to the end of the input array.
248 *
249 * Does not support a NULL dst on purpose - caller is expected to loop
250 * in parts.
251 */
252 static size_t
_none_wcrtombin(char * __restrict dst,const wchar_t * __restrict src,size_t dlen,size_t * slen,int flags __unused)253 _none_wcrtombin(char * __restrict dst, const wchar_t * __restrict src,
254 size_t dlen, size_t *slen, int flags __unused)
255 {
256 size_t i;
257 size_t j;
258 size_t n = *slen;
259
260 for (i = j = 0; i < n; ++i) {
261 if (j == dlen)
262 break;
263 if (src[i] >= 0x100) {
264 if (i == 0) {
265 errno = EILSEQ;
266 return(-1);
267 }
268 break;
269 }
270 if (dst)
271 dst[j] = (unsigned char)src[i];
272 ++j;
273 }
274 /* no partial sequences so we can ignore flags */
275 *slen = i;
276
277 return j;
278 }
279
280 /* setup defaults */
281
282 struct xlocale_ctype __xlocale_global_ctype = {
283 {{0}, "C"},
284 (_RuneLocale*)&_DefaultRuneLocale,
285 _none_mbrtowc,
286 _none_mbsinit,
287 _none_mbsnrtowcs,
288 _none_wcrtomb,
289 _none_wcsnrtombs,
290 _none_mbintowcr,
291 _none_wcrtombin,
292 1, /* __mb_cur_max, */
293 256 /* __mb_sb_limit */
294 };
295
296 struct xlocale_ctype __xlocale_C_ctype = {
297 {{0}, "C"},
298 (_RuneLocale*)&_DefaultRuneLocale,
299 _none_mbrtowc,
300 _none_mbsinit,
301 _none_mbsnrtowcs,
302 _none_wcrtomb,
303 _none_wcsnrtombs,
304 _none_mbintowcr,
305 _none_wcrtombin,
306 1, /* __mb_cur_max, */
307 256 /* __mb_sb_limit */
308 };
309