1 /* 2 * Copyright (c) 2004 Tim J. Robbins. All rights reserved. 3 * Copyright (c) 2003 David Xu <davidxu@freebsd.org> 4 * All rights reserved. 5 * 6 * Redistribution and use in source and binary forms, with or without 7 * modification, are permitted provided that the following conditions 8 * are met: 9 * 1. Redistributions of source code must retain the above copyright 10 * notice, this list of conditions and the following disclaimer. 11 * 2. Redistributions in binary form must reproduce the above copyright 12 * notice, this list of conditions and the following disclaimer in the 13 * documentation and/or other materials provided with the distribution. 14 * 15 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND 16 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 17 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 18 * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE 19 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 20 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 21 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 22 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 23 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 24 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 25 * SUCH DAMAGE. 26 */ 27 28 /* 29 * Copyright 2010 Nexenta Systems, Inc. All rights reserved. 30 * Use is subject to license terms. 31 */ 32 33 #include "lint.h" 34 #include <sys/types.h> 35 #include <errno.h> 36 #include "runetype.h" 37 #include <stdlib.h> 38 #include <string.h> 39 #include <wchar.h> 40 #include "mblocal.h" 41 42 static size_t _GB2312_mbrtowc(wchar_t *_RESTRICT_KYWD, 43 const char *_RESTRICT_KYWD, 44 size_t, mbstate_t *_RESTRICT_KYWD); 45 static int _GB2312_mbsinit(const mbstate_t *); 46 static size_t _GB2312_wcrtomb(char *_RESTRICT_KYWD, wchar_t, 47 mbstate_t *_RESTRICT_KYWD); 48 49 typedef struct { 50 int count; 51 uchar_t bytes[2]; 52 } _GB2312State; 53 54 int 55 _GB2312_init(_RuneLocale *rl) 56 { 57 58 _CurrentRuneLocale = rl; 59 __mbrtowc = _GB2312_mbrtowc; 60 __wcrtomb = _GB2312_wcrtomb; 61 __mbsinit = _GB2312_mbsinit; 62 __ctype[520] = 2; 63 return (0); 64 } 65 66 static int 67 _GB2312_mbsinit(const mbstate_t *ps) 68 { 69 70 return (ps == NULL || ((const _GB2312State *)ps)->count == 0); 71 } 72 73 static int 74 _GB2312_check(const char *str, size_t n) 75 { 76 const uchar_t *s = (const uchar_t *)str; 77 78 if (n == 0) 79 /* Incomplete multibyte sequence */ 80 return (-2); 81 if (s[0] >= 0xa1 && s[0] <= 0xfe) { 82 if (n < 2) 83 /* Incomplete multibyte sequence */ 84 return (-2); 85 if (s[1] < 0xa1 || s[1] > 0xfe) 86 /* Invalid multibyte sequence */ 87 return (-1); 88 return (2); 89 } else if (s[0] & 0x80) { 90 /* Invalid multibyte sequence */ 91 return (-1); 92 } 93 return (1); 94 } 95 96 static size_t 97 _GB2312_mbrtowc(wchar_t *_RESTRICT_KYWD pwc, const char *_RESTRICT_KYWD s, 98 size_t n, mbstate_t *_RESTRICT_KYWD ps) 99 { 100 _GB2312State *gs; 101 wchar_t wc; 102 int i, len, ocount; 103 size_t ncopy; 104 105 gs = (_GB2312State *)ps; 106 107 if (gs->count < 0 || gs->count > sizeof (gs->bytes)) { 108 errno = EINVAL; 109 return ((size_t)-1); 110 } 111 112 if (s == NULL) { 113 s = ""; 114 n = 1; 115 pwc = NULL; 116 } 117 118 ncopy = MIN(MIN(n, MB_CUR_MAX), sizeof (gs->bytes) - gs->count); 119 (void) memcpy(gs->bytes + gs->count, s, ncopy); 120 ocount = gs->count; 121 gs->count += ncopy; 122 s = (char *)gs->bytes; 123 n = gs->count; 124 125 if ((len = _GB2312_check(s, n)) < 0) 126 return ((size_t)len); 127 wc = 0; 128 i = len; 129 while (i-- > 0) 130 wc = (wc << 8) | (unsigned char)*s++; 131 if (pwc != NULL) 132 *pwc = wc; 133 gs->count = 0; 134 return (wc == L'\0' ? 0 : len - ocount); 135 } 136 137 static size_t 138 _GB2312_wcrtomb(char *_RESTRICT_KYWD s, wchar_t wc, 139 mbstate_t *_RESTRICT_KYWD ps) 140 { 141 _GB2312State *gs; 142 143 gs = (_GB2312State *)ps; 144 145 if (gs->count != 0) { 146 errno = EINVAL; 147 return ((size_t)-1); 148 } 149 150 if (s == NULL) 151 /* Reset to initial shift state (no-op) */ 152 return (1); 153 if (wc & 0x8000) { 154 *s++ = (wc >> 8) & 0xff; 155 *s = wc & 0xff; 156 return (2); 157 } 158 *s = wc & 0xff; 159 return (1); 160 } 161