gb2312.c revision 142654
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 142654 2005-02-27 15:11:09Z phantom $");
30
31#include <errno.h>
32#include <runetype.h>
33#include <stdlib.h>
34#include <string.h>
35#include <wchar.h>
36#include "mblocal.h"
37
38static size_t	_GB2312_mbrtowc(wchar_t * __restrict, const char * __restrict,
39		    size_t, mbstate_t * __restrict);
40static int	_GB2312_mbsinit(const mbstate_t *);
41static size_t	_GB2312_wcrtomb(char * __restrict, wchar_t,
42		    mbstate_t * __restrict);
43
44typedef struct {
45	int	count;
46	u_char	bytes[2];
47} _GB2312State;
48
49int
50_GB2312_init(_RuneLocale *rl)
51{
52
53	_CurrentRuneLocale = rl;
54	__mbrtowc = _GB2312_mbrtowc;
55	__wcrtomb = _GB2312_wcrtomb;
56	__mbsinit = _GB2312_mbsinit;
57	__mb_cur_max = 2;
58	return (0);
59}
60
61static int
62_GB2312_mbsinit(const mbstate_t *ps)
63{
64
65	return (ps == NULL || ((const _GB2312State *)ps)->count == 0);
66}
67
68static __inline int
69_GB2312_check(const char *str, size_t n)
70{
71	const u_char *s = (const u_char *)str;
72
73	if (n == 0)
74		/* Incomplete multibyte sequence */
75		return (-2);
76	if (s[0] >= 0xa1 && s[0] <= 0xfe) {
77		if (n < 2)
78			/* Incomplete multibyte sequence */
79			return (-2);
80		if (s[1] < 0xa1 || s[1] > 0xfe)
81			/* Invalid multibyte sequence */
82			return (-1);
83		return (2);
84	} else if (s[0] & 0x80) {
85		/* Invalid multibyte sequence */
86		return (-1);
87	}
88	return (1);
89}
90
91static size_t
92_GB2312_mbrtowc(wchar_t * __restrict pwc, const char * __restrict s, size_t n,
93    mbstate_t * __restrict ps)
94{
95	_GB2312State *gs;
96	wchar_t wc;
97	int i, len, ocount;
98	size_t ncopy;
99
100	gs = (_GB2312State *)ps;
101
102	if (gs->count < 0 || gs->count > sizeof(gs->bytes)) {
103		errno = EINVAL;
104		return ((size_t)-1);
105	}
106
107	if (s == NULL) {
108		s = "";
109		n = 1;
110		pwc = NULL;
111	}
112
113	ncopy = MIN(MIN(n, MB_CUR_MAX), sizeof(gs->bytes) - gs->count);
114	memcpy(gs->bytes + gs->count, s, ncopy);
115	ocount = gs->count;
116	gs->count += ncopy;
117	s = (char *)gs->bytes;
118	n = gs->count;
119
120	if ((len = _GB2312_check(s, n)) < 0)
121		return ((size_t)len);
122	wc = 0;
123	i = len;
124	while (i-- > 0)
125		wc = (wc << 8) | (unsigned char)*s++;
126	if (pwc != NULL)
127		*pwc = wc;
128	gs->count = 0;
129	return (wc == L'\0' ? 0 : len - ocount);
130}
131
132static size_t
133_GB2312_wcrtomb(char * __restrict s, wchar_t wc, mbstate_t * __restrict ps)
134{
135	_GB2312State *gs;
136
137	gs = (_GB2312State *)ps;
138
139	if (gs->count != 0) {
140		errno = EINVAL;
141		return ((size_t)-1);
142	}
143
144	if (s == NULL)
145		/* Reset to initial shift state (no-op) */
146		return (1);
147	if (wc & 0x8000) {
148		*s++ = (wc >> 8) & 0xff;
149		*s = wc & 0xff;
150		return (2);
151	}
152	*s = wc & 0xff;
153	return (1);
154}
155