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>
49 static size_t _GB18030_mbrtowc(wchar_t * __restrict, const char * __restrict,
50 size_t, mbstate_t * __restrict);
51 static int _GB18030_mbsinit(const mbstate_t *);
52 static size_t _GB18030_wcrtomb(char * __restrict, wchar_t,
53 mbstate_t * __restrict);
54 static size_t _GB18030_mbsnrtowcs(wchar_t * __restrict,
55 const char ** __restrict, size_t, size_t,
56 mbstate_t * __restrict);
57 static size_t _GB18030_wcsnrtombs(char * __restrict,
58 const wchar_t ** __restrict, size_t, size_t,
59 mbstate_t * __restrict);
68 _GB18030_init(struct xlocale_ctype *l, _RuneLocale *rl)
71 l->__mbrtowc = _GB18030_mbrtowc;
72 l->__wcrtomb = _GB18030_wcrtomb;
73 l->__mbsinit = _GB18030_mbsinit;
74 l->__mbsnrtowcs = _GB18030_mbsnrtowcs;
75 l->__wcsnrtombs = _GB18030_wcsnrtombs;
78 l->__mb_sb_limit = 128;
84 _GB18030_mbsinit(const mbstate_t *ps)
87 return (ps == NULL || ((const _GB18030State *)ps)->count == 0);
91 _GB18030_mbrtowc(wchar_t * __restrict pwc, const char * __restrict s,
92 size_t n, mbstate_t * __restrict ps)
99 gs = (_GB18030State *)ps;
101 if (gs->count < 0 || gs->count > sizeof(gs->bytes)) {
112 ncopy = MIN(MIN(n, MB_CUR_MAX), sizeof(gs->bytes) - gs->count);
113 (void) memcpy(gs->bytes + gs->count, s, ncopy);
116 s = (char *)gs->bytes;
120 /* Incomplete multibyte sequence */
124 * Single byte: [00-7f]
125 * Two byte: [81-fe][40-7e,80-fe]
126 * Four byte: [81-fe][30-39][81-fe][30-39]
128 ch = (unsigned char)*s++;
132 } else if (ch >= 0x81 && ch <= 0xfe) {
136 ch = (unsigned char)*s++;
137 if ((ch >= 0x40 && ch <= 0x7e) || (ch >= 0x80 && ch <= 0xfe)) {
138 wch = (wch << 8) | ch;
140 } else if (ch >= 0x30 && ch <= 0x39) {
142 * Strip high bit off the wide character we will
143 * eventually output so that it is positive when
144 * cast to wint_t on 32-bit twos-complement machines.
146 wch = ((wch & 0x7f) << 8) | ch;
149 ch = (unsigned char)*s++;
150 if (ch < 0x81 || ch > 0xfe)
152 wch = (wch << 8) | ch;
155 ch = (unsigned char)*s++;
156 if (ch < 0x30 || ch > 0x39)
158 wch = (wch << 8) | ch;
168 return (wch == L'\0' ? 0 : len - ocount);
175 _GB18030_wcrtomb(char * __restrict s, wchar_t wc, mbstate_t * __restrict ps)
181 gs = (_GB18030State *)ps;
183 if (gs->count != 0) {
189 /* Reset to initial shift state (no-op) */
191 if ((wc & ~0x7fffffff) != 0)
193 if (wc & 0x7f000000) {
194 /* Replace high bit that mbrtowc() removed. */
196 c = (wc >> 24) & 0xff;
197 if (c < 0x81 || c > 0xfe)
200 c = (wc >> 16) & 0xff;
201 if (c < 0x30 || c > 0x39)
204 c = (wc >> 8) & 0xff;
205 if (c < 0x81 || c > 0xfe)
209 if (c < 0x30 || c > 0x39)
213 } else if (wc & 0x00ff0000)
215 else if (wc & 0x0000ff00) {
216 c = (wc >> 8) & 0xff;
217 if (c < 0x81 || c > 0xfe)
221 if (c < 0x40 || c == 0x7f || c == 0xff)
225 } else if (wc <= 0x7f) {
238 _GB18030_mbsnrtowcs(wchar_t * __restrict dst,
239 const char ** __restrict src, size_t nms, size_t len,
240 mbstate_t * __restrict ps)
242 return (__mbsnrtowcs_std(dst, src, nms, len, ps, _GB18030_mbrtowc));
246 _GB18030_wcsnrtombs(char * __restrict dst,
247 const wchar_t ** __restrict src, size_t nwc, size_t len,
248 mbstate_t * __restrict ps)
250 return (__wcsnrtombs_std(dst, src, nwc, len, ps, _GB18030_wcrtomb));