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 * 4. 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
41 #include <sys/cdefs.h>
42 __FBSDID("$FreeBSD$");
43
44 #include <sys/types.h>
45 #include <errno.h>
46 #include <runetype.h>
47 #include <stdlib.h>
48 #include <string.h>
49 #include <wchar.h>
50 #include "mblocal.h"
51
52 extern int __mb_sb_limit;
53
54 static size_t _GBK_mbrtowc(wchar_t * __restrict, const char * __restrict,
55 size_t, mbstate_t * __restrict);
56 static int _GBK_mbsinit(const mbstate_t *);
57 static size_t _GBK_wcrtomb(char * __restrict, wchar_t,
58 mbstate_t * __restrict);
59 static size_t _GBK_mbsnrtowcs(wchar_t * __restrict,
60 const char ** __restrict, size_t, size_t,
61 mbstate_t * __restrict);
62 static size_t _GBK_wcsnrtombs(char * __restrict,
63 const wchar_t ** __restrict, size_t, size_t,
64 mbstate_t * __restrict);
65
66 typedef struct {
67 wchar_t ch;
68 } _GBKState;
69
70 int
_GBK_init(struct xlocale_ctype * l,_RuneLocale * rl)71 _GBK_init(struct xlocale_ctype *l, _RuneLocale *rl)
72 {
73
74 l->__mbrtowc = _GBK_mbrtowc;
75 l->__wcrtomb = _GBK_wcrtomb;
76 l->__mbsinit = _GBK_mbsinit;
77 l->__mbsnrtowcs = _GBK_mbsnrtowcs;
78 l->__wcsnrtombs = _GBK_wcsnrtombs;
79 l->runes = rl;
80 l->__mb_cur_max = 2;
81 l->__mb_sb_limit = 128;
82 return (0);
83 }
84
85 static int
_GBK_mbsinit(const mbstate_t * ps)86 _GBK_mbsinit(const mbstate_t *ps)
87 {
88
89 return (ps == NULL || ((const _GBKState *)ps)->ch == 0);
90 }
91
92 static int
_gbk_check(u_int c)93 _gbk_check(u_int c)
94 {
95
96 c &= 0xff;
97 return ((c >= 0x81 && c <= 0xfe) ? 2 : 1);
98 }
99
100 static size_t
_GBK_mbrtowc(wchar_t * __restrict pwc,const char * __restrict s,size_t n,mbstate_t * __restrict ps)101 _GBK_mbrtowc(wchar_t * __restrict pwc, const char * __restrict s, size_t n,
102 mbstate_t * __restrict ps)
103 {
104 _GBKState *gs;
105 wchar_t wc;
106 size_t len;
107
108 gs = (_GBKState *)ps;
109
110 if ((gs->ch & ~0xFF) != 0) {
111 /* Bad conversion state. */
112 errno = EINVAL;
113 return ((size_t)-1);
114 }
115
116 if (s == NULL) {
117 s = "";
118 n = 1;
119 pwc = NULL;
120 }
121
122 if (n == 0)
123 /* Incomplete multibyte sequence */
124 return ((size_t)-2);
125
126 if (gs->ch != 0) {
127 if (*s == '\0') {
128 errno = EILSEQ;
129 return ((size_t)-1);
130 }
131 wc = (gs->ch << 8) | (*s & 0xFF);
132 if (pwc != NULL)
133 *pwc = wc;
134 gs->ch = 0;
135 return (1);
136 }
137
138 len = (size_t)_gbk_check(*s);
139 wc = *s++ & 0xff;
140 if (len == 2) {
141 if (n < 2) {
142 /* Incomplete multibyte sequence */
143 gs->ch = wc;
144 return ((size_t)-2);
145 }
146 if (*s == '\0') {
147 errno = EILSEQ;
148 return ((size_t)-1);
149 }
150 wc = (wc << 8) | (*s++ & 0xff);
151 if (pwc != NULL)
152 *pwc = wc;
153 return (2);
154 } else {
155 if (pwc != NULL)
156 *pwc = wc;
157 return (wc == L'\0' ? 0 : 1);
158 }
159 }
160
161 static size_t
_GBK_wcrtomb(char * __restrict s,wchar_t wc,mbstate_t * __restrict ps)162 _GBK_wcrtomb(char * __restrict s, wchar_t wc, mbstate_t * __restrict ps)
163 {
164 _GBKState *gs;
165
166 gs = (_GBKState *)ps;
167
168 if (gs->ch != 0) {
169 errno = EINVAL;
170 return ((size_t)-1);
171 }
172
173 if (s == NULL)
174 /* Reset to initial shift state (no-op) */
175 return (1);
176 if (wc & 0x8000) {
177 *s++ = (wc >> 8) & 0xff;
178 *s = wc & 0xff;
179 return (2);
180 }
181 *s = wc & 0xff;
182 return (1);
183 }
184
185 static size_t
_GBK_mbsnrtowcs(wchar_t * __restrict dst,const char ** __restrict src,size_t nms,size_t len,mbstate_t * __restrict ps)186 _GBK_mbsnrtowcs(wchar_t * __restrict dst, const char ** __restrict src,
187 size_t nms, size_t len, mbstate_t * __restrict ps)
188 {
189 return (__mbsnrtowcs_std(dst, src, nms, len, ps, _GBK_mbrtowc));
190 }
191
192 static size_t
_GBK_wcsnrtombs(char * __restrict dst,const wchar_t ** __restrict src,size_t nwc,size_t len,mbstate_t * __restrict ps)193 _GBK_wcsnrtombs(char * __restrict dst, const wchar_t ** __restrict src,
194 size_t nwc, size_t len, mbstate_t * __restrict ps)
195 {
196 return (__wcsnrtombs_std(dst, src, nwc, len, ps, _GBK_wcrtomb));
197 }
198