1 /*-
2 * SPDX-License-Identifier: BSD-2-Clause
3 *
4 * Copyright 2013 Garrett D'Amore <garrett@damore.org>
5 * Copyright 2010 Nexenta Systems, Inc. All rights reserved.
6 * Copyright (c) 2002-2004 Tim J. Robbins
7 * All rights reserved.
8 *
9 * Copyright (c) 2011 The FreeBSD Foundation
10 *
11 * Portions of this software were developed by David Chisnall
12 * under sponsorship from the FreeBSD Foundation.
13 *
14 * Redistribution and use in source and binary forms, with or without
15 * modification, are permitted provided that the following conditions
16 * are met:
17 * 1. Redistributions of source code must retain the above copyright
18 * notice, this list of conditions and the following disclaimer.
19 * 2. Redistributions in binary form must reproduce the above copyright
20 * notice, this list of conditions and the following disclaimer in the
21 * documentation and/or other materials provided with the distribution.
22 *
23 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR 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 AUTHOR 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 /*
37 * PRC National Standard GB 18030-2000 encoding of Chinese text.
38 *
39 * See gb18030(5) for details.
40 */
41
42 #include <sys/param.h>
43 #include <errno.h>
44 #include <runetype.h>
45 #include <stdlib.h>
46 #include <string.h>
47 #include <wchar.h>
48 #include "mblocal.h"
49
50 static size_t _GB18030_mbrtowc(wchar_t * __restrict, const char * __restrict,
51 size_t, mbstate_t * __restrict);
52 static int _GB18030_mbsinit(const mbstate_t *);
53 static size_t _GB18030_wcrtomb(char * __restrict, wchar_t,
54 mbstate_t * __restrict);
55 static size_t _GB18030_mbsnrtowcs(wchar_t * __restrict,
56 const char ** __restrict, size_t, size_t,
57 mbstate_t * __restrict);
58 static size_t _GB18030_wcsnrtombs(char * __restrict,
59 const wchar_t ** __restrict, size_t, size_t,
60 mbstate_t * __restrict);
61
62
63 typedef struct {
64 int count;
65 u_char bytes[4];
66 } _GB18030State;
67
68 int
_GB18030_init(struct xlocale_ctype * l,_RuneLocale * rl)69 _GB18030_init(struct xlocale_ctype *l, _RuneLocale *rl)
70 {
71
72 l->__mbrtowc = _GB18030_mbrtowc;
73 l->__wcrtomb = _GB18030_wcrtomb;
74 l->__mbsinit = _GB18030_mbsinit;
75 l->__mbsnrtowcs = _GB18030_mbsnrtowcs;
76 l->__wcsnrtombs = _GB18030_wcsnrtombs;
77 l->runes = rl;
78 l->__mb_cur_max = 4;
79 l->__mb_sb_limit = 128;
80
81 return (0);
82 }
83
84 static int
_GB18030_mbsinit(const mbstate_t * ps)85 _GB18030_mbsinit(const mbstate_t *ps)
86 {
87
88 return (ps == NULL || ((const _GB18030State *)ps)->count == 0);
89 }
90
91 static size_t
_GB18030_mbrtowc(wchar_t * __restrict pwc,const char * __restrict s,size_t n,mbstate_t * __restrict ps)92 _GB18030_mbrtowc(wchar_t * __restrict pwc, const char * __restrict s,
93 size_t n, mbstate_t * __restrict ps)
94 {
95 _GB18030State *gs;
96 wchar_t wch;
97 int ch, len, ocount;
98 size_t ncopy;
99
100 gs = (_GB18030State *)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 (n == 0)
121 /* Incomplete multibyte sequence */
122 return ((size_t)-2);
123
124 /*
125 * Single byte: [00-7f]
126 * Two byte: [81-fe][40-7e,80-fe]
127 * Four byte: [81-fe][30-39][81-fe][30-39]
128 */
129 ch = (unsigned char)*s++;
130 if (ch <= 0x7f) {
131 len = 1;
132 wch = ch;
133 } else if (ch >= 0x81 && ch <= 0xfe) {
134 wch = ch;
135 if (n < 2)
136 return ((size_t)-2);
137 ch = (unsigned char)*s++;
138 if ((ch >= 0x40 && ch <= 0x7e) || (ch >= 0x80 && ch <= 0xfe)) {
139 wch = (wch << 8) | ch;
140 len = 2;
141 } else if (ch >= 0x30 && ch <= 0x39) {
142 /*
143 * Strip high bit off the wide character we will
144 * eventually output so that it is positive when
145 * cast to wint_t on 32-bit twos-complement machines.
146 */
147 wch = ((wch & 0x7f) << 8) | ch;
148 if (n < 3)
149 return ((size_t)-2);
150 ch = (unsigned char)*s++;
151 if (ch < 0x81 || ch > 0xfe)
152 goto ilseq;
153 wch = (wch << 8) | ch;
154 if (n < 4)
155 return ((size_t)-2);
156 ch = (unsigned char)*s++;
157 if (ch < 0x30 || ch > 0x39)
158 goto ilseq;
159 wch = (wch << 8) | ch;
160 len = 4;
161 } else
162 goto ilseq;
163 } else
164 goto ilseq;
165
166 if (pwc != NULL)
167 *pwc = wch;
168 gs->count = 0;
169 return (wch == L'\0' ? 0 : len - ocount);
170 ilseq:
171 errno = EILSEQ;
172 return ((size_t)-1);
173 }
174
175 static size_t
_GB18030_wcrtomb(char * __restrict s,wchar_t wc,mbstate_t * __restrict ps)176 _GB18030_wcrtomb(char * __restrict s, wchar_t wc, mbstate_t * __restrict ps)
177 {
178 _GB18030State *gs;
179 size_t len;
180 int c;
181
182 gs = (_GB18030State *)ps;
183
184 if (gs->count != 0) {
185 errno = EINVAL;
186 return ((size_t)-1);
187 }
188
189 if (s == NULL)
190 /* Reset to initial shift state (no-op) */
191 return (1);
192 if ((wc & ~0x7fffffff) != 0)
193 goto ilseq;
194 if (wc & 0x7f000000) {
195 /* Replace high bit that mbrtowc() removed. */
196 wc |= 0x80000000;
197 c = (wc >> 24) & 0xff;
198 if (c < 0x81 || c > 0xfe)
199 goto ilseq;
200 *s++ = c;
201 c = (wc >> 16) & 0xff;
202 if (c < 0x30 || c > 0x39)
203 goto ilseq;
204 *s++ = c;
205 c = (wc >> 8) & 0xff;
206 if (c < 0x81 || c > 0xfe)
207 goto ilseq;
208 *s++ = c;
209 c = wc & 0xff;
210 if (c < 0x30 || c > 0x39)
211 goto ilseq;
212 *s++ = c;
213 len = 4;
214 } else if (wc & 0x00ff0000)
215 goto ilseq;
216 else if (wc & 0x0000ff00) {
217 c = (wc >> 8) & 0xff;
218 if (c < 0x81 || c > 0xfe)
219 goto ilseq;
220 *s++ = c;
221 c = wc & 0xff;
222 if (c < 0x40 || c == 0x7f || c == 0xff)
223 goto ilseq;
224 *s++ = c;
225 len = 2;
226 } else if (wc <= 0x7f) {
227 *s++ = wc;
228 len = 1;
229 } else
230 goto ilseq;
231
232 return (len);
233 ilseq:
234 errno = EILSEQ;
235 return ((size_t)-1);
236 }
237
238 static size_t
_GB18030_mbsnrtowcs(wchar_t * __restrict dst,const char ** __restrict src,size_t nms,size_t len,mbstate_t * __restrict ps)239 _GB18030_mbsnrtowcs(wchar_t * __restrict dst,
240 const char ** __restrict src, size_t nms, size_t len,
241 mbstate_t * __restrict ps)
242 {
243 return (__mbsnrtowcs_std(dst, src, nms, len, ps, _GB18030_mbrtowc));
244 }
245
246 static size_t
_GB18030_wcsnrtombs(char * __restrict dst,const wchar_t ** __restrict src,size_t nwc,size_t len,mbstate_t * __restrict ps)247 _GB18030_wcsnrtombs(char * __restrict dst,
248 const wchar_t ** __restrict src, size_t nwc, size_t len,
249 mbstate_t * __restrict ps)
250 {
251 return (__wcsnrtombs_std(dst, src, nwc, len, ps, _GB18030_wcrtomb));
252 }
253