1 /* 2 * Copyright 2013 Garrett D'Amore <garrett@damore.org> 3 * Copyright 2010 Nexenta Systems, Inc. All rights reserved. 4 * Copyright (c) 2004 Tim J. Robbins. All rights reserved. 5 * Copyright (c) 2003 David Xu <davidxu@freebsd.org> 6 * All rights reserved. 7 * 8 * Copyright (c) 2011 The FreeBSD Foundation 9 * All rights reserved. 10 * Portions of this software were developed by David Chisnall 11 * under sponsorship from the FreeBSD Foundation. 12 * 13 * Redistribution and use in source and binary forms, with or without 14 * modification, are permitted provided that the following conditions 15 * are met: 16 * 1. Redistributions of source code must retain the above copyright 17 * notice, this list of conditions and the following disclaimer. 18 * 2. Redistributions in binary form must reproduce the above copyright 19 * notice, this list of conditions and the following disclaimer in the 20 * documentation and/or other materials provided with the distribution. 21 * 22 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND 23 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 24 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 25 * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE 26 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 27 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 28 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 29 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 30 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 31 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 32 * SUCH DAMAGE. 33 */ 34 35 #include <sys/param.h> 36 37 #include <errno.h> 38 #include <runetype.h> 39 #include <stdlib.h> 40 #include <string.h> 41 #include <wchar.h> 42 #include "mblocal.h" 43 44 static size_t _GB2312_mbrtowc(wchar_t * __restrict, const char * __restrict, 45 size_t, mbstate_t * __restrict); 46 static int _GB2312_mbsinit(const mbstate_t *); 47 static size_t _GB2312_wcrtomb(char * __restrict, wchar_t, 48 mbstate_t * __restrict); 49 static size_t _GB2312_mbsnrtowcs(wchar_t * __restrict, 50 const char ** __restrict, size_t, size_t, 51 mbstate_t * __restrict); 52 static size_t _GB2312_wcsnrtombs(char * __restrict, 53 const wchar_t ** __restrict, size_t, size_t, 54 mbstate_t * __restrict); 55 56 57 typedef struct { 58 int count; 59 u_char bytes[2]; 60 } _GB2312State; 61 62 int 63 _GB2312_init(struct xlocale_ctype *l, _RuneLocale *rl) 64 { 65 66 l->runes = rl; 67 l->__mbrtowc = _GB2312_mbrtowc; 68 l->__wcrtomb = _GB2312_wcrtomb; 69 l->__mbsinit = _GB2312_mbsinit; 70 l->__mbsnrtowcs = _GB2312_mbsnrtowcs; 71 l->__wcsnrtombs = _GB2312_wcsnrtombs; 72 l->__mb_cur_max = 2; 73 l->__mb_sb_limit = 128; 74 return (0); 75 } 76 77 static int 78 _GB2312_mbsinit(const mbstate_t *ps) 79 { 80 81 return (ps == NULL || ((const _GB2312State *)ps)->count == 0); 82 } 83 84 static int 85 _GB2312_check(const char *str, size_t n) 86 { 87 const u_char *s = (const u_char *)str; 88 89 if (n == 0) 90 /* Incomplete multibyte sequence */ 91 return (-2); 92 if (s[0] >= 0xa1 && s[0] <= 0xfe) { 93 if (n < 2) 94 /* Incomplete multibyte sequence */ 95 return (-2); 96 if (s[1] < 0xa1 || s[1] > 0xfe) 97 /* Invalid multibyte sequence */ 98 return (-1); 99 return (2); 100 } else if (s[0] & 0x80) { 101 /* Invalid multibyte sequence */ 102 return (-1); 103 } 104 return (1); 105 } 106 107 static size_t 108 _GB2312_mbrtowc(wchar_t * __restrict pwc, const char * __restrict s, size_t n, 109 mbstate_t * __restrict ps) 110 { 111 _GB2312State *gs; 112 wchar_t wc; 113 int i, len, ocount; 114 size_t ncopy; 115 116 gs = (_GB2312State *)ps; 117 118 if (gs->count < 0 || gs->count > sizeof(gs->bytes)) { 119 errno = EINVAL; 120 return ((size_t)-1); 121 } 122 123 if (s == NULL) { 124 s = ""; 125 n = 1; 126 pwc = NULL; 127 } 128 129 ncopy = MIN(MIN(n, MB_CUR_MAX), sizeof(gs->bytes) - gs->count); 130 (void) memcpy(gs->bytes + gs->count, s, ncopy); 131 ocount = gs->count; 132 gs->count += ncopy; 133 s = (char *)gs->bytes; 134 n = gs->count; 135 136 if ((len = _GB2312_check(s, n)) < 0) 137 return ((size_t)len); 138 wc = 0; 139 i = len; 140 while (i-- > 0) 141 wc = (wc << 8) | (unsigned char)*s++; 142 if (pwc != NULL) 143 *pwc = wc; 144 gs->count = 0; 145 return (wc == L'\0' ? 0 : len - ocount); 146 } 147 148 static size_t 149 _GB2312_wcrtomb(char * __restrict s, wchar_t wc, mbstate_t * __restrict ps) 150 { 151 _GB2312State *gs; 152 153 gs = (_GB2312State *)ps; 154 155 if (gs->count != 0) { 156 errno = EINVAL; 157 return ((size_t)-1); 158 } 159 160 if (s == NULL) 161 /* Reset to initial shift state (no-op) */ 162 return (1); 163 if (wc & 0x8000) { 164 *s++ = (wc >> 8) & 0xff; 165 *s = wc & 0xff; 166 return (2); 167 } 168 *s = wc & 0xff; 169 return (1); 170 } 171 172 static size_t 173 _GB2312_mbsnrtowcs(wchar_t * __restrict dst, 174 const char ** __restrict src, size_t nms, size_t len, 175 mbstate_t * __restrict ps) 176 { 177 return (__mbsnrtowcs_std(dst, src, nms, len, ps, _GB2312_mbrtowc)); 178 } 179 180 static size_t 181 _GB2312_wcsnrtombs(char * __restrict dst, 182 const wchar_t ** __restrict src, size_t nwc, size_t len, 183 mbstate_t * __restrict ps) 184 { 185 return (__wcsnrtombs_std(dst, src, nwc, len, ps, _GB2312_wcrtomb)); 186 } 187