gb2312.c revision 128155 
1/*-
2 * Copyright (c) 2004 Tim J. Robbins. All rights reserved.
3 * Copyright (c) 2003 David Xu <davidxu@freebsd.org>
4 * 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 * 1. Redistributions of source code must retain the above copyright
10 *    notice, this list of conditions and the following disclaimer.
11 * 2. Redistributions in binary form must reproduce the above copyright
12 *    notice, this list of conditions and the following disclaimer in the
13 *    documentation and/or other materials provided with the distribution.
14 *
15 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
16 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
17 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
18 * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
19 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
20 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
21 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
22 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
23 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
24 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
25 * SUCH DAMAGE.
26 */
27
28#include <sys/param.h>
29__FBSDID("$FreeBSD: head/lib/libc/locale/gb2312.c 128155 2004-04-12 13:09:18Z tjr $");
30
31#include <errno.h>
32#include <runetype.h>
33#include <stdlib.h>
34#include <string.h>
35#include <wchar.h>
36
37extern size_t (*__mbrtowc)(wchar_t * __restrict, const char * __restrict,
38    size_t, mbstate_t * __restrict);
39extern int (*__mbsinit)(const mbstate_t *);
40extern size_t (*__wcrtomb)(char * __restrict, wchar_t, mbstate_t * __restrict);
41
42int	_GB2312_init(_RuneLocale *);
43size_t	_GB2312_mbrtowc(wchar_t * __restrict, const char * __restrict, size_t,
44	    mbstate_t * __restrict);
45int	_GB2312_mbsinit(const mbstate_t *);
46size_t	_GB2312_wcrtomb(char * __restrict, wchar_t, mbstate_t * __restrict);
47
48typedef struct {
49	int	count;
50	u_char	bytes[2];
51} _GB2312State;
52
53int
54_GB2312_init(_RuneLocale *rl)
55{
56
57	_CurrentRuneLocale = rl;
58	__mbrtowc = _GB2312_mbrtowc;
59	__wcrtomb = _GB2312_wcrtomb;
60	__mbsinit = _GB2312_mbsinit;
61	__mb_cur_max = 2;
62	return (0);
63}
64
65int
66_GB2312_mbsinit(const mbstate_t *ps)
67{
68
69	return (ps == NULL || ((const _GB2312State *)ps)->count == 0);
70}
71
72static __inline int
73_GB2312_check(const char *str, size_t n)
74{
75	const u_char *s = (const u_char *)str;
76
77	if (n == 0)
78		/* Incomplete multibyte sequence */
79		return (-2);
80	if (s[0] >= 0xa1 && s[0] <= 0xfe) {
81		if (n < 2)
82			/* Incomplete multibyte sequence */
83			return (-2);
84		if (s[1] < 0xa1 || s[1] > 0xfe)
85			/* Invalid multibyte sequence */
86			return (-1);
87		return (2);
88	} else if (s[0] & 0x80) {
89		/* Invalid multibyte sequence */
90		return (-1);
91	}
92	return (1);
93}
94
95size_t
96_GB2312_mbrtowc(wchar_t * __restrict pwc, const char * __restrict s, size_t n,
97    mbstate_t * __restrict ps)
98{
99	_GB2312State *gs;
100	wchar_t wc;
101	int i, len, ocount;
102	size_t ncopy;
103
104	gs = (_GB2312State *)ps;
105
106	if (gs->count < 0 || gs->count > sizeof(gs->bytes)) {
107		errno = EINVAL;
108		return ((size_t)-1);
109	}
110
111	if (s == NULL) {
112		s = "";
113		n = 1;
114		pwc = NULL;
115	}
116
117	ncopy = MIN(MIN(n, MB_CUR_MAX), sizeof(gs->bytes) - gs->count);
118	memcpy(gs->bytes + gs->count, s, ncopy);
119	ocount = gs->count;
120	gs->count += ncopy;
121	s = (char *)gs->bytes;
122	n = gs->count;
123
124	if ((len = _GB2312_check(s, n)) < 0)
125		return ((size_t)len);
126	wc = 0;
127	i = len;
128	while (i-- > 0)
129		wc = (wc << 8) | (unsigned char)*s++;
130	if (pwc != NULL)
131		*pwc = wc;
132	gs->count = 0;
133	return (wc == L'\0' ? 0 : len - ocount);
134}
135
136size_t
137_GB2312_wcrtomb(char * __restrict s, wchar_t wc, mbstate_t * __restrict ps)
138{
139	_GB2312State *gs;
140
141	gs = (_GB2312State *)ps;
142
143	if (gs->count != 0) {
144		errno = EINVAL;
145		return ((size_t)-1);
146	}
147
148	if (s == NULL)
149		/* Reset to initial shift state (no-op) */
150		return (1);
151	if (wc & 0x8000) {
152		*s++ = (wc >> 8) & 0xff;
153		*s = wc & 0xff;
154		return (2);
155	}
156	*s = wc & 0xff;
157	return (1);
158}
159