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) 2004 Tim J. Robbins. All rights reserved. 7 * Copyright (c) 2003 David Xu <davidxu@freebsd.org> 8 * All rights reserved. 9 * 10 * Copyright (c) 2011 The FreeBSD Foundation 11 * 12 * Portions of this software were developed by David Chisnall 13 * under sponsorship from the FreeBSD Foundation. 14 * 15 * Redistribution and use in source and binary forms, with or without 16 * modification, are permitted provided that the following conditions 17 * are met: 18 * 1. Redistributions of source code must retain the above copyright 19 * notice, this list of conditions and the following disclaimer. 20 * 2. Redistributions in binary form must reproduce the above copyright 21 * notice, this list of conditions and the following disclaimer in the 22 * documentation and/or other materials provided with the distribution. 23 * 24 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND 25 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 26 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 27 * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE 28 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 29 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 30 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 31 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 32 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 33 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 34 * SUCH DAMAGE. 35 */ 36 37 #include <sys/param.h> 38 __FBSDID("$FreeBSD$"); 39 40 #include <errno.h> 41 #include <runetype.h> 42 #include <stdlib.h> 43 #include <string.h> 44 #include <wchar.h> 45 #include "mblocal.h" 46 47 static size_t _GB2312_mbrtowc(wchar_t * __restrict, const char * __restrict, 48 size_t, mbstate_t * __restrict); 49 static int _GB2312_mbsinit(const mbstate_t *); 50 static size_t _GB2312_wcrtomb(char * __restrict, wchar_t, 51 mbstate_t * __restrict); 52 static size_t _GB2312_mbsnrtowcs(wchar_t * __restrict, 53 const char ** __restrict, size_t, size_t, 54 mbstate_t * __restrict); 55 static size_t _GB2312_wcsnrtombs(char * __restrict, 56 const wchar_t ** __restrict, size_t, size_t, 57 mbstate_t * __restrict); 58 59 60 typedef struct { 61 int count; 62 u_char bytes[2]; 63 } _GB2312State; 64 65 int 66 _GB2312_init(struct xlocale_ctype *l, _RuneLocale *rl) 67 { 68 69 l->runes = rl; 70 l->__mbrtowc = _GB2312_mbrtowc; 71 l->__wcrtomb = _GB2312_wcrtomb; 72 l->__mbsinit = _GB2312_mbsinit; 73 l->__mbsnrtowcs = _GB2312_mbsnrtowcs; 74 l->__wcsnrtombs = _GB2312_wcsnrtombs; 75 l->__mb_cur_max = 2; 76 l->__mb_sb_limit = 128; 77 return (0); 78 } 79 80 static int 81 _GB2312_mbsinit(const mbstate_t *ps) 82 { 83 84 return (ps == NULL || ((const _GB2312State *)ps)->count == 0); 85 } 86 87 static int 88 _GB2312_check(const char *str, size_t n) 89 { 90 const u_char *s = (const u_char *)str; 91 92 if (n == 0) 93 /* Incomplete multibyte sequence */ 94 return (-2); 95 if (s[0] >= 0xa1 && s[0] <= 0xfe) { 96 if (n < 2) 97 /* Incomplete multibyte sequence */ 98 return (-2); 99 if (s[1] < 0xa1 || s[1] > 0xfe) 100 /* Invalid multibyte sequence */ 101 return (-1); 102 return (2); 103 } else if (s[0] & 0x80) { 104 /* Invalid multibyte sequence */ 105 return (-1); 106 } 107 return (1); 108 } 109 110 static size_t 111 _GB2312_mbrtowc(wchar_t * __restrict pwc, const char * __restrict s, size_t n, 112 mbstate_t * __restrict ps) 113 { 114 _GB2312State *gs; 115 wchar_t wc; 116 int i, len, ocount; 117 size_t ncopy; 118 119 gs = (_GB2312State *)ps; 120 121 if (gs->count < 0 || gs->count > sizeof(gs->bytes)) { 122 errno = EINVAL; 123 return ((size_t)-1); 124 } 125 126 if (s == NULL) { 127 s = ""; 128 n = 1; 129 pwc = NULL; 130 } 131 132 ncopy = MIN(MIN(n, MB_CUR_MAX), sizeof(gs->bytes) - gs->count); 133 memcpy(gs->bytes + gs->count, s, ncopy); 134 ocount = gs->count; 135 gs->count += ncopy; 136 s = (char *)gs->bytes; 137 n = gs->count; 138 139 if ((len = _GB2312_check(s, n)) < 0) 140 return ((size_t)len); 141 wc = 0; 142 i = len; 143 while (i-- > 0) 144 wc = (wc << 8) | (unsigned char)*s++; 145 if (pwc != NULL) 146 *pwc = wc; 147 gs->count = 0; 148 return (wc == L'\0' ? 0 : len - ocount); 149 } 150 151 static size_t 152 _GB2312_wcrtomb(char * __restrict s, wchar_t wc, mbstate_t * __restrict ps) 153 { 154 _GB2312State *gs; 155 156 gs = (_GB2312State *)ps; 157 158 if (gs->count != 0) { 159 errno = EINVAL; 160 return ((size_t)-1); 161 } 162 163 if (s == NULL) 164 /* Reset to initial shift state (no-op) */ 165 return (1); 166 if (wc & 0x8000) { 167 *s++ = (wc >> 8) & 0xff; 168 *s = wc & 0xff; 169 return (2); 170 } 171 *s = wc & 0xff; 172 return (1); 173 } 174 175 static size_t 176 _GB2312_mbsnrtowcs(wchar_t * __restrict dst, 177 const char ** __restrict src, size_t nms, size_t len, 178 mbstate_t * __restrict ps) 179 { 180 return (__mbsnrtowcs_std(dst, src, nms, len, ps, _GB2312_mbrtowc)); 181 } 182 183 static size_t 184 _GB2312_wcsnrtombs(char * __restrict dst, 185 const wchar_t ** __restrict src, size_t nwc, size_t len, 186 mbstate_t * __restrict ps) 187 { 188 return (__wcsnrtombs_std(dst, src, nwc, len, ps, _GB2312_wcrtomb)); 189 } 190