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) 2002-2004 Tim J. Robbins 7 * All rights reserved. 8 * 9 * Copyright (c) 2011 The FreeBSD Foundation 10 * 11 * Portions of this software were developed by David Chisnall 12 * under sponsorship from the FreeBSD Foundation. 13 * 14 * Redistribution and use in source and binary forms, with or without 15 * modification, are permitted provided that the following conditions 16 * are met: 17 * 1. Redistributions of source code must retain the above copyright 18 * notice, this list of conditions and the following disclaimer. 19 * 2. Redistributions in binary form must reproduce the above copyright 20 * notice, this list of conditions and the following disclaimer in the 21 * documentation and/or other materials provided with the distribution. 22 * 23 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND 24 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 25 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 26 * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE 27 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 28 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 29 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 30 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 31 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 32 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 33 * SUCH DAMAGE. 34 */ 35 36 /* 37 * PRC National Standard GB 18030-2000 encoding of Chinese text. 38 * 39 * See gb18030(5) for details. 40 */ 41 42 #include <sys/param.h> 43 __FBSDID("$FreeBSD$"); 44 45 #include <errno.h> 46 #include <runetype.h> 47 #include <stdlib.h> 48 #include <string.h> 49 #include <wchar.h> 50 #include "mblocal.h" 51 52 static size_t _GB18030_mbrtowc(wchar_t * __restrict, const char * __restrict, 53 size_t, mbstate_t * __restrict); 54 static int _GB18030_mbsinit(const mbstate_t *); 55 static size_t _GB18030_wcrtomb(char * __restrict, wchar_t, 56 mbstate_t * __restrict); 57 static size_t _GB18030_mbsnrtowcs(wchar_t * __restrict, 58 const char ** __restrict, size_t, size_t, 59 mbstate_t * __restrict); 60 static size_t _GB18030_wcsnrtombs(char * __restrict, 61 const wchar_t ** __restrict, size_t, size_t, 62 mbstate_t * __restrict); 63 64 65 typedef struct { 66 int count; 67 u_char bytes[4]; 68 } _GB18030State; 69 70 int 71 _GB18030_init(struct xlocale_ctype *l, _RuneLocale *rl) 72 { 73 74 l->__mbrtowc = _GB18030_mbrtowc; 75 l->__wcrtomb = _GB18030_wcrtomb; 76 l->__mbsinit = _GB18030_mbsinit; 77 l->__mbsnrtowcs = _GB18030_mbsnrtowcs; 78 l->__wcsnrtombs = _GB18030_wcsnrtombs; 79 l->runes = rl; 80 l->__mb_cur_max = 4; 81 l->__mb_sb_limit = 128; 82 83 return (0); 84 } 85 86 static int 87 _GB18030_mbsinit(const mbstate_t *ps) 88 { 89 90 return (ps == NULL || ((const _GB18030State *)ps)->count == 0); 91 } 92 93 static size_t 94 _GB18030_mbrtowc(wchar_t * __restrict pwc, const char * __restrict s, 95 size_t n, mbstate_t * __restrict ps) 96 { 97 _GB18030State *gs; 98 wchar_t wch; 99 int ch, len, ocount; 100 size_t ncopy; 101 102 gs = (_GB18030State *)ps; 103 104 if (gs->count < 0 || gs->count > sizeof(gs->bytes)) { 105 errno = EINVAL; 106 return ((size_t)-1); 107 } 108 109 if (s == NULL) { 110 s = ""; 111 n = 1; 112 pwc = NULL; 113 } 114 115 ncopy = MIN(MIN(n, MB_CUR_MAX), sizeof(gs->bytes) - gs->count); 116 memcpy(gs->bytes + gs->count, s, ncopy); 117 ocount = gs->count; 118 gs->count += ncopy; 119 s = (char *)gs->bytes; 120 n = gs->count; 121 122 if (n == 0) 123 /* Incomplete multibyte sequence */ 124 return ((size_t)-2); 125 126 /* 127 * Single byte: [00-7f] 128 * Two byte: [81-fe][40-7e,80-fe] 129 * Four byte: [81-fe][30-39][81-fe][30-39] 130 */ 131 ch = (unsigned char)*s++; 132 if (ch <= 0x7f) { 133 len = 1; 134 wch = ch; 135 } else if (ch >= 0x81 && ch <= 0xfe) { 136 wch = ch; 137 if (n < 2) 138 return ((size_t)-2); 139 ch = (unsigned char)*s++; 140 if ((ch >= 0x40 && ch <= 0x7e) || (ch >= 0x80 && ch <= 0xfe)) { 141 wch = (wch << 8) | ch; 142 len = 2; 143 } else if (ch >= 0x30 && ch <= 0x39) { 144 /* 145 * Strip high bit off the wide character we will 146 * eventually output so that it is positive when 147 * cast to wint_t on 32-bit twos-complement machines. 148 */ 149 wch = ((wch & 0x7f) << 8) | ch; 150 if (n < 3) 151 return ((size_t)-2); 152 ch = (unsigned char)*s++; 153 if (ch < 0x81 || ch > 0xfe) 154 goto ilseq; 155 wch = (wch << 8) | ch; 156 if (n < 4) 157 return ((size_t)-2); 158 ch = (unsigned char)*s++; 159 if (ch < 0x30 || ch > 0x39) 160 goto ilseq; 161 wch = (wch << 8) | ch; 162 len = 4; 163 } else 164 goto ilseq; 165 } else 166 goto ilseq; 167 168 if (pwc != NULL) 169 *pwc = wch; 170 gs->count = 0; 171 return (wch == L'\0' ? 0 : len - ocount); 172 ilseq: 173 errno = EILSEQ; 174 return ((size_t)-1); 175 } 176 177 static size_t 178 _GB18030_wcrtomb(char * __restrict s, wchar_t wc, mbstate_t * __restrict ps) 179 { 180 _GB18030State *gs; 181 size_t len; 182 int c; 183 184 gs = (_GB18030State *)ps; 185 186 if (gs->count != 0) { 187 errno = EINVAL; 188 return ((size_t)-1); 189 } 190 191 if (s == NULL) 192 /* Reset to initial shift state (no-op) */ 193 return (1); 194 if ((wc & ~0x7fffffff) != 0) 195 goto ilseq; 196 if (wc & 0x7f000000) { 197 /* Replace high bit that mbrtowc() removed. */ 198 wc |= 0x80000000; 199 c = (wc >> 24) & 0xff; 200 if (c < 0x81 || c > 0xfe) 201 goto ilseq; 202 *s++ = c; 203 c = (wc >> 16) & 0xff; 204 if (c < 0x30 || c > 0x39) 205 goto ilseq; 206 *s++ = c; 207 c = (wc >> 8) & 0xff; 208 if (c < 0x81 || c > 0xfe) 209 goto ilseq; 210 *s++ = c; 211 c = wc & 0xff; 212 if (c < 0x30 || c > 0x39) 213 goto ilseq; 214 *s++ = c; 215 len = 4; 216 } else if (wc & 0x00ff0000) 217 goto ilseq; 218 else if (wc & 0x0000ff00) { 219 c = (wc >> 8) & 0xff; 220 if (c < 0x81 || c > 0xfe) 221 goto ilseq; 222 *s++ = c; 223 c = wc & 0xff; 224 if (c < 0x40 || c == 0x7f || c == 0xff) 225 goto ilseq; 226 *s++ = c; 227 len = 2; 228 } else if (wc <= 0x7f) { 229 *s++ = wc; 230 len = 1; 231 } else 232 goto ilseq; 233 234 return (len); 235 ilseq: 236 errno = EILSEQ; 237 return ((size_t)-1); 238 } 239 240 static size_t 241 _GB18030_mbsnrtowcs(wchar_t * __restrict dst, 242 const char ** __restrict src, size_t nms, size_t len, 243 mbstate_t * __restrict ps) 244 { 245 return (__mbsnrtowcs_std(dst, src, nms, len, ps, _GB18030_mbrtowc)); 246 } 247 248 static size_t 249 _GB18030_wcsnrtombs(char * __restrict dst, 250 const wchar_t ** __restrict src, size_t nwc, size_t len, 251 mbstate_t * __restrict ps) 252 { 253 return (__wcsnrtombs_std(dst, src, nwc, len, ps, _GB18030_wcrtomb)); 254 } 255