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 * Redistribution and use in source and binary forms, with or without
12 * modification, are permitted provided that the following conditions
13 * are met:
14 * 1. Redistributions of source code must retain the above copyright
15 * notice, this list of conditions and the following disclaimer.
16 * 2. Redistributions in binary form must reproduce the above copyright
17 * notice, this list of conditions and the following disclaimer in the
18 * documentation and/or other materials provided with the distribution.
19 * 4. Neither the name of the University nor the names of its contributors
20 * may be used to endorse or promote products derived from this software
21 * without specific prior written permission.
22 *
23 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
24 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
25 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
26 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
27 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
28 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
29 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
30 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
31 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
32 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
33 * SUCH DAMAGE.
34 */
35
36 #include "lint.h"
37 #include <sys/types.h>
38 #include <errno.h>
39 #include <stdlib.h>
40 #include <string.h>
41 #include <wchar.h>
42 #include "mblocal.h"
43 #include "lctype.h"
44
45 static size_t _GBK_mbrtowc(wchar_t *_RESTRICT_KYWD,
46 const char *_RESTRICT_KYWD,
47 size_t, mbstate_t *_RESTRICT_KYWD, boolean_t);
48 static int _GBK_mbsinit(const mbstate_t *);
49 static size_t _GBK_wcrtomb(char *_RESTRICT_KYWD, wchar_t,
50 mbstate_t *_RESTRICT_KYWD);
51 static size_t _GBK_mbsnrtowcs(wchar_t *_RESTRICT_KYWD,
52 const char **_RESTRICT_KYWD, size_t, size_t,
53 mbstate_t *_RESTRICT_KYWD);
54 static size_t _GBK_wcsnrtombs(char *_RESTRICT_KYWD,
55 const wchar_t **_RESTRICT_KYWD, size_t, size_t,
56 mbstate_t *_RESTRICT_KYWD);
57
58 void
_GBK_init(struct lc_ctype * lct)59 _GBK_init(struct lc_ctype *lct)
60 {
61 lct->lc_mbrtowc = _GBK_mbrtowc;
62 lct->lc_wcrtomb = _GBK_wcrtomb;
63 lct->lc_mbsinit = _GBK_mbsinit;
64 lct->lc_mbsnrtowcs = _GBK_mbsnrtowcs;
65 lct->lc_wcsnrtombs = _GBK_wcsnrtombs;
66 lct->lc_max_mblen = 2;
67 lct->lc_is_ascii = 0;
68 }
69
70 static int
_GBK_mbsinit(const mbstate_t * ps)71 _GBK_mbsinit(const mbstate_t *ps)
72 {
73
74 return (ps == NULL || ((const _GBKState *)ps)->ch == 0);
75 }
76
77 static int
_gbk_check(uint_t c)78 _gbk_check(uint_t c)
79 {
80
81 c &= 0xff;
82 return ((c >= 0x81 && c <= 0xfe) ? 2 : 1);
83 }
84
85 static size_t
_GBK_mbrtowc(wchar_t * _RESTRICT_KYWD pwc,const char * _RESTRICT_KYWD s,size_t n,mbstate_t * _RESTRICT_KYWD ps,boolean_t zero)86 _GBK_mbrtowc(wchar_t *_RESTRICT_KYWD pwc, const char *_RESTRICT_KYWD s,
87 size_t n, mbstate_t *_RESTRICT_KYWD ps, boolean_t zero)
88 {
89 _GBKState *gs;
90 wchar_t wc;
91 size_t len;
92
93 gs = (_GBKState *)ps;
94
95 if ((gs->ch & ~0xFF) != 0) {
96 /* Bad conversion state. */
97 errno = EINVAL;
98 return ((size_t)-1);
99 }
100
101 if (s == NULL) {
102 s = "";
103 n = 1;
104 pwc = NULL;
105 }
106
107 if (n == 0)
108 /* Incomplete multibyte sequence */
109 return ((size_t)-2);
110
111 if (gs->ch != 0) {
112 if (*s == '\0') {
113 errno = EILSEQ;
114 return ((size_t)-1);
115 }
116 wc = (gs->ch << 8) | (*s & 0xFF);
117 if (pwc != NULL)
118 *pwc = wc;
119 gs->ch = 0;
120 return (1);
121 }
122
123 len = (size_t)_gbk_check(*s);
124 wc = *s++ & 0xff;
125 if (len == 2) {
126 if (n < 2) {
127 /* Incomplete multibyte sequence */
128 gs->ch = wc;
129 return ((size_t)-2);
130 }
131 if (*s == '\0') {
132 errno = EILSEQ;
133 return ((size_t)-1);
134 }
135 wc = (wc << 8) | (*s++ & 0xff);
136 if (pwc != NULL)
137 *pwc = wc;
138 return (2);
139 } else {
140 if (pwc != NULL)
141 *pwc = wc;
142 if (zero || wc != L'\0') {
143 return (1);
144 } else {
145 return (0);
146 }
147 }
148 }
149
150 static size_t
_GBK_wcrtomb(char * _RESTRICT_KYWD s,wchar_t wc,mbstate_t * _RESTRICT_KYWD ps)151 _GBK_wcrtomb(char *_RESTRICT_KYWD s, wchar_t wc, mbstate_t *_RESTRICT_KYWD ps)
152 {
153 _GBKState *gs;
154
155 gs = (_GBKState *)ps;
156
157 if (gs->ch != 0) {
158 errno = EINVAL;
159 return ((size_t)-1);
160 }
161
162 if (s == NULL)
163 /* Reset to initial shift state (no-op) */
164 return (1);
165 if (wc & 0x8000) {
166 *s++ = (wc >> 8) & 0xff;
167 *s = wc & 0xff;
168 return (2);
169 }
170 *s = wc & 0xff;
171 return (1);
172 }
173
174 static size_t
_GBK_mbsnrtowcs(wchar_t * _RESTRICT_KYWD dst,const char ** _RESTRICT_KYWD src,size_t nms,size_t len,mbstate_t * _RESTRICT_KYWD ps)175 _GBK_mbsnrtowcs(wchar_t *_RESTRICT_KYWD dst, const char **_RESTRICT_KYWD src,
176 size_t nms, size_t len, mbstate_t *_RESTRICT_KYWD ps)
177 {
178 return (__mbsnrtowcs_std(dst, src, nms, len, ps, _GBK_mbrtowc));
179 }
180
181 static size_t
_GBK_wcsnrtombs(char * _RESTRICT_KYWD dst,const wchar_t ** _RESTRICT_KYWD src,size_t nwc,size_t len,mbstate_t * _RESTRICT_KYWD ps)182 _GBK_wcsnrtombs(char *_RESTRICT_KYWD dst, const wchar_t **_RESTRICT_KYWD src,
183 size_t nwc, size_t len, mbstate_t *_RESTRICT_KYWD ps)
184 {
185 return (__wcsnrtombs_std(dst, src, nwc, len, ps, _GBK_wcrtomb));
186 }
187