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 #include <errno.h> 39 #include <runetype.h> 40 #include <stdlib.h> 41 #include <string.h> 42 #include <wchar.h> 43 #include "mblocal.h" 44 45 static size_t _GB2312_mbrtowc(wchar_t * __restrict, const char * __restrict, 46 size_t, mbstate_t * __restrict); 47 static int _GB2312_mbsinit(const mbstate_t *); 48 static size_t _GB2312_wcrtomb(char * __restrict, wchar_t, 49 mbstate_t * __restrict); 50 static size_t _GB2312_mbsnrtowcs(wchar_t * __restrict, 51 const char ** __restrict, size_t, size_t, 52 mbstate_t * __restrict); 53 static size_t _GB2312_wcsnrtombs(char * __restrict, 54 const wchar_t ** __restrict, size_t, size_t, 55 mbstate_t * __restrict); 56 57 58 typedef struct { 59 int count; 60 u_char bytes[2]; 61 } _GB2312State; 62 63 int 64 _GB2312_init(struct xlocale_ctype *l, _RuneLocale *rl) 65 { 66 67 l->runes = rl; 68 l->__mbrtowc = _GB2312_mbrtowc; 69 l->__wcrtomb = _GB2312_wcrtomb; 70 l->__mbsinit = _GB2312_mbsinit; 71 l->__mbsnrtowcs = _GB2312_mbsnrtowcs; 72 l->__wcsnrtombs = _GB2312_wcsnrtombs; 73 l->__mb_cur_max = 2; 74 l->__mb_sb_limit = 128; 75 return (0); 76 } 77 78 static int 79 _GB2312_mbsinit(const mbstate_t *ps) 80 { 81 82 return (ps == NULL || ((const _GB2312State *)ps)->count == 0); 83 } 84 85 static int 86 _GB2312_check(const char *str, size_t n) 87 { 88 const u_char *s = (const u_char *)str; 89 90 if (n == 0) 91 /* Incomplete multibyte sequence */ 92 return (-2); 93 if (s[0] >= 0xa1 && s[0] <= 0xfe) { 94 if (n < 2) 95 /* Incomplete multibyte sequence */ 96 return (-2); 97 if (s[1] < 0xa1 || s[1] > 0xfe) 98 /* Invalid multibyte sequence */ 99 return (-1); 100 return (2); 101 } else if (s[0] & 0x80) { 102 /* Invalid multibyte sequence */ 103 return (-1); 104 } 105 return (1); 106 } 107 108 static size_t 109 _GB2312_mbrtowc(wchar_t * __restrict pwc, const char * __restrict s, size_t n, 110 mbstate_t * __restrict ps) 111 { 112 _GB2312State *gs; 113 wchar_t wc; 114 int i, len, ocount; 115 size_t ncopy; 116 117 gs = (_GB2312State *)ps; 118 119 if (gs->count < 0 || gs->count > sizeof(gs->bytes)) { 120 errno = EINVAL; 121 return ((size_t)-1); 122 } 123 124 if (s == NULL) { 125 s = ""; 126 n = 1; 127 pwc = NULL; 128 } 129 130 ncopy = MIN(MIN(n, MB_CUR_MAX), sizeof(gs->bytes) - gs->count); 131 memcpy(gs->bytes + gs->count, s, ncopy); 132 ocount = gs->count; 133 gs->count += ncopy; 134 s = (char *)gs->bytes; 135 n = gs->count; 136 137 if ((len = _GB2312_check(s, n)) < 0) 138 return ((size_t)len); 139 wc = 0; 140 i = len; 141 while (i-- > 0) 142 wc = (wc << 8) | (unsigned char)*s++; 143 if (pwc != NULL) 144 *pwc = wc; 145 gs->count = 0; 146 return (wc == L'\0' ? 0 : len - ocount); 147 } 148 149 static size_t 150 _GB2312_wcrtomb(char * __restrict s, wchar_t wc, mbstate_t * __restrict ps) 151 { 152 _GB2312State *gs; 153 154 gs = (_GB2312State *)ps; 155 156 if (gs->count != 0) { 157 errno = EINVAL; 158 return ((size_t)-1); 159 } 160 161 if (s == NULL) 162 /* Reset to initial shift state (no-op) */ 163 return (1); 164 if (wc & 0x8000) { 165 *s++ = (wc >> 8) & 0xff; 166 *s = wc & 0xff; 167 return (2); 168 } 169 *s = wc & 0xff; 170 return (1); 171 } 172 173 static size_t 174 _GB2312_mbsnrtowcs(wchar_t * __restrict dst, 175 const char ** __restrict src, size_t nms, size_t len, 176 mbstate_t * __restrict ps) 177 { 178 return (__mbsnrtowcs_std(dst, src, nms, len, ps, _GB2312_mbrtowc)); 179 } 180 181 static size_t 182 _GB2312_wcsnrtombs(char * __restrict dst, 183 const wchar_t ** __restrict src, size_t nwc, size_t len, 184 mbstate_t * __restrict ps) 185 { 186 return (__wcsnrtombs_std(dst, src, nwc, len, ps, _GB2312_wcrtomb)); 187 } 188