1 /* $NetBSD: unicode.h,v 1.5 2007/02/26 12:33:08 drochner Exp $ */ 2 3 /*- 4 * Copyright (c) 2001, 2004 The NetBSD Foundation, Inc. 5 * All rights reserved. 6 * 7 * Redistribution and use in source and binary forms, with or without 8 * modification, are permitted provided that the following conditions 9 * are met: 10 * 1. Redistributions of source code must retain the above copyright 11 * notice, this list of conditions and the following disclaimer. 12 * 2. Redistributions in binary form must reproduce the above copyright 13 * notice, this list of conditions and the following disclaimer in the 14 * documentation and/or other materials provided with the distribution. 15 * 3. All advertising materials mentioning features or use of this software 16 * must display the following acknowledgement: 17 * This product includes software developed by the NetBSD 18 * Foundation, Inc. and its contributors. 19 * 4. Neither the name of The NetBSD Foundation nor the names of its 20 * contributors may be used to endorse or promote products derived 21 * from this software without specific prior written permission. 22 * 23 * THIS SOFTWARE IS PROVIDED BY THE NETBSD FOUNDATION, INC. AND CONTRIBUTORS 24 * ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED 25 * TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR 26 * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE FOUNDATION OR CONTRIBUTORS 27 * BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR 28 * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF 29 * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS 30 * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN 31 * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) 32 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE 33 * POSSIBILITY OF SUCH DAMAGE. 34 */ 35 36 /*- 37 * Copyright (c) 1993 38 * The Regents of the University of California. All rights reserved. 39 * 40 * This code is derived from software contributed to Berkeley by 41 * Paul Borman at Krystal Technologies. 42 * 43 * Redistribution and use in source and binary forms, with or without 44 * modification, are permitted provided that the following conditions 45 * are met: 46 * 1. Redistributions of source code must retain the above copyright 47 * notice, this list of conditions and the following disclaimer. 48 * 2. Redistributions in binary form must reproduce the above copyright 49 * notice, this list of conditions and the following disclaimer in the 50 * documentation and/or other materials provided with the distribution. 51 * 3. All advertising materials mentioning features or use of this software 52 * must display the following acknowledgement: 53 * This product includes software developed by the University of 54 * California, Berkeley and its contributors. 55 * 4. Neither the name of the University nor the names of its contributors 56 * may be used to endorse or promote products derived from this software 57 * without specific prior written permission. 58 * 59 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 60 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 61 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 62 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 63 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 64 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 65 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 66 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 67 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 68 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 69 * SUCH DAMAGE. 70 */ 71 72 /* 73 * Routines for handling Unicode encoded in UTF-8 form, code derived from 74 * src/lib/libc/locale/utf2.c. 75 */ 76 static u_int16_t wget_utf8(const char **, size_t *) __unused; 77 static int wput_utf8(char *, size_t, u_int16_t) __unused; 78 79 /* 80 * Read one UTF8-encoded character off the string, shift the string pointer 81 * and return the character. 82 */ 83 static u_int16_t 84 wget_utf8(const char **str, size_t *sz) 85 { 86 int c; 87 u_int16_t rune = 0; 88 const char *s = *str; 89 static const int _utf_count[16] = { 90 1, 1, 1, 1, 1, 1, 1, 1, 91 0, 0, 0, 0, 2, 2, 3, 0, 92 }; 93 94 /* must be called with at least one byte remaining */ 95 KASSERT(*sz > 0); 96 97 c = _utf_count[(s[0] & 0xf0) >> 4]; 98 if (c == 0 || c > *sz) { 99 decoding_error: 100 /* 101 * The first character is in range 128-255 and doesn't 102 * mark valid a valid UTF-8 sequence. There is not much 103 * we can do with this, so handle by returning 104 * the first character as if it would be a correctly 105 * encoded ISO-8859-1 character. 106 */ 107 c = 1; 108 } 109 110 switch (c) { 111 case 1: 112 rune = s[0] & 0xff; 113 break; 114 case 2: 115 if ((s[1] & 0xc0) != 0x80) 116 goto decoding_error; 117 rune = ((s[0] & 0x1F) << 6) | (s[1] & 0x3F); 118 break; 119 case 3: 120 if ((s[1] & 0xC0) != 0x80 || (s[2] & 0xC0) != 0x80) 121 goto decoding_error; 122 rune = ((s[0] & 0x0F) << 12) | ((s[1] & 0x3F) << 6) 123 | (s[2] & 0x3F); 124 break; 125 } 126 127 *str += c; 128 *sz -= c; 129 return rune; 130 } 131 132 /* 133 * Encode wide character and write it to the string. 'n' specifies 134 * how much buffer space remains in 's'. Returns number of bytes written 135 * to the target string 's'. 136 */ 137 static int 138 wput_utf8(char *s, size_t n, u_int16_t wc) 139 { 140 if (wc & 0xf800) { 141 if (n < 3) { 142 /* bound check failure */ 143 return 0; 144 } 145 146 s[0] = 0xE0 | (wc >> 12); 147 s[1] = 0x80 | ((wc >> 6) & 0x3F); 148 s[2] = 0x80 | ((wc) & 0x3F); 149 return 3; 150 } else if (wc & 0x0780) { 151 if (n < 2) { 152 /* bound check failure */ 153 return 0; 154 } 155 156 s[0] = 0xC0 | (wc >> 6); 157 s[1] = 0x80 | ((wc) & 0x3F); 158 return 2; 159 } else { 160 if (n < 1) { 161 /* bound check failure */ 162 return 0; 163 } 164 165 s[0] = wc; 166 return 1; 167 } 168 } 169