mbrtowc.c revision 102050 
1/*-
2 * Copyright (c) 2002 Tim J. Robbins.
3 * All rights reserved.
4 *
5 * Redistribution and use in source and binary forms, with or without
6 * modification, are permitted provided that the following conditions
7 * are met:
8 * 1. Redistributions of source code must retain the above copyright
9 *    notice, this list of conditions and the following disclaimer.
10 * 2. Redistributions in binary form must reproduce the above copyright
11 *    notice, this list of conditions and the following disclaimer in the
12 *    documentation and/or other materials provided with the distribution.
13 *
14 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
15 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
16 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
17 * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
18 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
19 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
20 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
21 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
22 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
23 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
24 * SUCH DAMAGE.
25 */
26
27#include <sys/cdefs.h>
28__FBSDID("$FreeBSD: head/lib/libc/locale/mbrtowc.c 102050 2002-08-18 06:30:10Z tjr $");
29
30#include <errno.h>
31#include <rune.h>
32#include <stdlib.h>
33#include <wchar.h>
34
35size_t
36mbrtowc(wchar_t *__restrict pwc, const char *__restrict s, size_t n,
37    mbstate_t *__restrict ps __unused)
38{
39        const char *e;
40        rune_t r;
41
42	if (s == NULL) {
43		pwc = NULL;
44		s = "";
45		n = 1;
46	}
47
48	if (*s == '\0') {
49		if (pwc != NULL)
50			*pwc = L'\0';
51		return (0);
52	}
53
54	if ((r = sgetrune(s, n, &e)) == _INVALID_RUNE) {
55		/*
56		 * The design of sgetrune() doesn't give us any way to tell
57		 * between incomplete and invalid multibyte sequences.
58		 */
59
60		if (n >= (size_t)MB_CUR_MAX) {
61			/*
62			 * If we have been supplied with at least MB_CUR_MAX
63			 * bytes and still cannot find a valid character, the
64			 * data must be invalid.
65			 */
66			errno = EILSEQ;
67			return ((size_t)-1);
68		}
69
70		/*
71		 * .. otherwise, it's an incomplete character or an invalid
72		 * character we cannot detect yet.
73		 */
74		return ((size_t)-2);
75	}
76
77	if (pwc != NULL)
78		*pwc = (wchar_t)r;
79
80	return ((size_t)(e - s));
81}
82