1 /* 2 * Copyright (c) 2002-2004 Tim J. Robbins 3 * All rights reserved. 4 * 5 * Redistribution and use in source and binary forms, with or without 6 * modification, are permitted provided that the following conditions 7 * are met: 8 * 1. Redistributions of source code must retain the above copyright 9 * notice, this list of conditions and the following disclaimer. 10 * 2. Redistributions in binary form must reproduce the above copyright 11 * notice, this list of conditions and the following disclaimer in the 12 * documentation and/or other materials provided with the distribution. 13 * 14 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND 15 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 16 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 17 * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE 18 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 19 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 20 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 21 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 22 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 23 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 24 * SUCH DAMAGE. 25 */ 26 27 /* 28 * Copyright 2010 Nexenta Systems, Inc. All rights reserved. 29 * Use is subject to license terms. 30 */ 31 32 /* 33 * PRC National Standard GB 18030-2000 encoding of Chinese text. 34 * 35 * See gb18030(5) for details. 36 */ 37 38 #include "lint.h" 39 #include <sys/types.h> 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 48 static size_t _GB18030_mbrtowc(wchar_t *_RESTRICT_KYWD, 49 const char *_RESTRICT_KYWD, 50 size_t, mbstate_t *_RESTRICT_KYWD); 51 static int _GB18030_mbsinit(const mbstate_t *); 52 static size_t _GB18030_wcrtomb(char *_RESTRICT_KYWD, wchar_t, 53 mbstate_t *_RESTRICT_KYWD); 54 55 typedef struct { 56 int count; 57 uchar_t bytes[4]; 58 } _GB18030State; 59 60 int 61 _GB18030_init(_RuneLocale *rl) 62 { 63 64 __mbrtowc = _GB18030_mbrtowc; 65 __wcrtomb = _GB18030_wcrtomb; 66 __mbsinit = _GB18030_mbsinit; 67 _CurrentRuneLocale = rl; 68 __ctype[520] = 4; 69 70 return (0); 71 } 72 73 static int 74 _GB18030_mbsinit(const mbstate_t *ps) 75 { 76 77 return (ps == NULL || ((const _GB18030State *)ps)->count == 0); 78 } 79 80 static size_t 81 _GB18030_mbrtowc(wchar_t *_RESTRICT_KYWD pwc, const char *_RESTRICT_KYWD s, 82 size_t n, mbstate_t *_RESTRICT_KYWD ps) 83 { 84 _GB18030State *gs; 85 wchar_t wch; 86 int ch, len, ocount; 87 size_t ncopy; 88 89 gs = (_GB18030State *)ps; 90 91 if (gs->count < 0 || gs->count > sizeof (gs->bytes)) { 92 errno = EINVAL; 93 return ((size_t)-1); 94 } 95 96 if (s == NULL) { 97 s = ""; 98 n = 1; 99 pwc = NULL; 100 } 101 102 ncopy = MIN(MIN(n, MB_CUR_MAX), sizeof (gs->bytes) - gs->count); 103 (void) memcpy(gs->bytes + gs->count, s, ncopy); 104 ocount = gs->count; 105 gs->count += ncopy; 106 s = (char *)gs->bytes; 107 n = gs->count; 108 109 if (n == 0) 110 /* Incomplete multibyte sequence */ 111 return ((size_t)-2); 112 113 /* 114 * Single byte: [00-7f] 115 * Two byte: [81-fe][40-7e,80-fe] 116 * Four byte: [81-fe][30-39][81-fe][30-39] 117 */ 118 ch = (unsigned char)*s++; 119 if (ch <= 0x7f) { 120 len = 1; 121 wch = ch; 122 } else if (ch >= 0x81 && ch <= 0xfe) { 123 wch = ch; 124 if (n < 2) 125 return ((size_t)-2); 126 ch = (unsigned char)*s++; 127 if ((ch >= 0x40 && ch <= 0x7e) || (ch >= 0x80 && ch <= 0xfe)) { 128 wch = (wch << 8) | ch; 129 len = 2; 130 } else if (ch >= 0x30 && ch <= 0x39) { 131 /* 132 * Strip high bit off the wide character we will 133 * eventually output so that it is positive when 134 * cast to wint_t on 32-bit twos-complement machines. 135 */ 136 wch = ((wch & 0x7f) << 8) | ch; 137 if (n < 3) 138 return ((size_t)-2); 139 ch = (unsigned char)*s++; 140 if (ch < 0x81 || ch > 0xfe) 141 goto ilseq; 142 wch = (wch << 8) | ch; 143 if (n < 4) 144 return ((size_t)-2); 145 ch = (unsigned char)*s++; 146 if (ch < 0x30 || ch > 0x39) 147 goto ilseq; 148 wch = (wch << 8) | ch; 149 len = 4; 150 } else 151 goto ilseq; 152 } else 153 goto ilseq; 154 155 if (pwc != NULL) 156 *pwc = wch; 157 gs->count = 0; 158 return (wch == L'\0' ? 0 : len - ocount); 159 ilseq: 160 errno = EILSEQ; 161 return ((size_t)-1); 162 } 163 164 static size_t 165 _GB18030_wcrtomb(char *_RESTRICT_KYWD s, wchar_t wc, 166 mbstate_t *_RESTRICT_KYWD ps) 167 { 168 _GB18030State *gs; 169 size_t len; 170 int c; 171 172 gs = (_GB18030State *)ps; 173 174 if (gs->count != 0) { 175 errno = EINVAL; 176 return ((size_t)-1); 177 } 178 179 if (s == NULL) 180 /* Reset to initial shift state (no-op) */ 181 return (1); 182 if ((wc & ~0x7fffffff) != 0) 183 goto ilseq; 184 if (wc & 0x7f000000) { 185 /* Replace high bit that mbrtowc() removed. */ 186 wc |= 0x80000000; 187 c = (wc >> 24) & 0xff; 188 if (c < 0x81 || c > 0xfe) 189 goto ilseq; 190 *s++ = c; 191 c = (wc >> 16) & 0xff; 192 if (c < 0x30 || c > 0x39) 193 goto ilseq; 194 *s++ = c; 195 c = (wc >> 8) & 0xff; 196 if (c < 0x81 || c > 0xfe) 197 goto ilseq; 198 *s++ = c; 199 c = wc & 0xff; 200 if (c < 0x30 || c > 0x39) 201 goto ilseq; 202 *s++ = c; 203 len = 4; 204 } else if (wc & 0x00ff0000) 205 goto ilseq; 206 else if (wc & 0x0000ff00) { 207 c = (wc >> 8) & 0xff; 208 if (c < 0x81 || c > 0xfe) 209 goto ilseq; 210 *s++ = c; 211 c = wc & 0xff; 212 if (c < 0x40 || c == 0x7f || c == 0xff) 213 goto ilseq; 214 *s++ = c; 215 len = 2; 216 } else if (wc <= 0x7f) { 217 *s++ = wc; 218 len = 1; 219 } else 220 goto ilseq; 221 222 return (len); 223 ilseq: 224 errno = EILSEQ; 225 return ((size_t)-1); 226 } 227