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
7 * Copyright (c) 2011 The FreeBSD Foundation
9 * Portions of this software were developed by David Chisnall
10 * under sponsorship from the FreeBSD Foundation.
12 * Redistribution and use in source and binary forms, with or without
13 * modification, are permitted provided that the following conditions
15 * 1. Redistributions of source code must retain the above copyright
16 * notice, this list of conditions and the following disclaimer.
17 * 2. Redistributions in binary form must reproduce the above copyright
18 * notice, this list of conditions and the following disclaimer in the
19 * documentation and/or other materials provided with the distribution.
21 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
22 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
23 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
24 * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
25 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
26 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
27 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
28 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
29 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
30 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
35 * PRC National Standard GB 18030-2000 encoding of Chinese text.
37 * See gb18030(5) for details.
40 #include <sys/param.h>
41 __FBSDID("$FreeBSD$");
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);
69 _GB18030_init(struct xlocale_ctype *l, _RuneLocale *rl)
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;
79 l->__mb_sb_limit = 128;
85 _GB18030_mbsinit(const mbstate_t *ps)
88 return (ps == NULL || ((const _GB18030State *)ps)->count == 0);
92 _GB18030_mbrtowc(wchar_t * __restrict pwc, const char * __restrict s,
93 size_t n, mbstate_t * __restrict ps)
100 gs = (_GB18030State *)ps;
102 if (gs->count < 0 || gs->count > sizeof(gs->bytes)) {
113 ncopy = MIN(MIN(n, MB_CUR_MAX), sizeof(gs->bytes) - gs->count);
114 memcpy(gs->bytes + gs->count, s, ncopy);
117 s = (char *)gs->bytes;
121 /* Incomplete multibyte sequence */
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]
129 ch = (unsigned char)*s++;
133 } else if (ch >= 0x81 && ch <= 0xfe) {
137 ch = (unsigned char)*s++;
138 if ((ch >= 0x40 && ch <= 0x7e) || (ch >= 0x80 && ch <= 0xfe)) {
139 wch = (wch << 8) | ch;
141 } else if (ch >= 0x30 && ch <= 0x39) {
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.
147 wch = ((wch & 0x7f) << 8) | ch;
150 ch = (unsigned char)*s++;
151 if (ch < 0x81 || ch > 0xfe)
153 wch = (wch << 8) | ch;
156 ch = (unsigned char)*s++;
157 if (ch < 0x30 || ch > 0x39)
159 wch = (wch << 8) | ch;
169 return (wch == L'\0' ? 0 : len - ocount);
176 _GB18030_wcrtomb(char * __restrict s, wchar_t wc, mbstate_t * __restrict ps)
182 gs = (_GB18030State *)ps;
184 if (gs->count != 0) {
190 /* Reset to initial shift state (no-op) */
192 if ((wc & ~0x7fffffff) != 0)
194 if (wc & 0x7f000000) {
195 /* Replace high bit that mbrtowc() removed. */
197 c = (wc >> 24) & 0xff;
198 if (c < 0x81 || c > 0xfe)
201 c = (wc >> 16) & 0xff;
202 if (c < 0x30 || c > 0x39)
205 c = (wc >> 8) & 0xff;
206 if (c < 0x81 || c > 0xfe)
210 if (c < 0x30 || c > 0x39)
214 } else if (wc & 0x00ff0000)
216 else if (wc & 0x0000ff00) {
217 c = (wc >> 8) & 0xff;
218 if (c < 0x81 || c > 0xfe)
222 if (c < 0x40 || c == 0x7f || c == 0xff)
226 } else if (wc <= 0x7f) {
239 _GB18030_mbsnrtowcs(wchar_t * __restrict dst,
240 const char ** __restrict src, size_t nms, size_t len,
241 mbstate_t * __restrict ps)
243 return (__mbsnrtowcs_std(dst, src, nms, len, ps, _GB18030_mbrtowc));
247 _GB18030_wcsnrtombs(char * __restrict dst,
248 const wchar_t ** __restrict src, size_t nwc, size_t len,
249 mbstate_t * __restrict ps)
251 return (__wcsnrtombs_std(dst, src, nwc, len, ps, _GB18030_wcrtomb));