1 /* $NetBSD: unicode.h,v 1.4 2006/05/20 08:28:27 yamt 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 77 /* 78 * Read one UTF8-encoded character off the string, shift the string pointer 79 * and return the character. 80 */ 81 static u_int16_t 82 wget_utf8(const char **str, size_t *sz) 83 { 84 int c; 85 u_int16_t rune = 0; 86 const char *s = *str; 87 static const int _utf_count[16] = { 88 1, 1, 1, 1, 1, 1, 1, 1, 89 0, 0, 0, 0, 2, 2, 3, 0, 90 }; 91 92 /* must be called with at least one byte remaining */ 93 KASSERT(*sz > 0); 94 95 c = _utf_count[(s[0] & 0xf0) >> 4]; 96 if (c == 0 || c > *sz) { 97 decoding_error: 98 /* 99 * The first character is in range 128-255 and doesn't 100 * mark valid a valid UTF-8 sequence. There is not much 101 * we can do with this, so handle by returning 102 * the first character as if it would be a correctly 103 * encoded ISO-8859-1 character. 104 */ 105 c = 1; 106 } 107 108 switch (c) { 109 case 1: 110 rune = s[0] & 0xff; 111 break; 112 case 2: 113 if ((s[1] & 0xc0) != 0x80) 114 goto decoding_error; 115 rune = ((s[0] & 0x1F) << 6) | (s[1] & 0x3F); 116 break; 117 case 3: 118 if ((s[1] & 0xC0) != 0x80 || (s[2] & 0xC0) != 0x80) 119 goto decoding_error; 120 rune = ((s[0] & 0x1F) << 12) | ((s[1] & 0x3F) << 6) 121 | (s[2] & 0x3F); 122 break; 123 } 124 125 *str += c; 126 *sz -= c; 127 return rune; 128 } 129 130 /* 131 * Encode wide character and write it to the string. 'n' specifies 132 * how much buffer space remains in 's'. Returns number of bytes written 133 * to the target string 's'. 134 */ 135 static int 136 wput_utf8(char *s, size_t n, u_int16_t wc) 137 { 138 if (wc & 0xf800) { 139 if (n < 3) { 140 /* bound check failure */ 141 return 0; 142 } 143 144 s[0] = 0xE0 | ((wc >> 12) & 0x0F); 145 s[1] = 0x80 | ((wc >> 6) & 0x3F); 146 s[2] = 0x80 | ((wc) & 0x3F); 147 return 3; 148 } else if (wc & 0x0780) { 149 if (n < 2) { 150 /* bound check failure */ 151 return 0; 152 } 153 154 s[0] = 0xC0 | ((wc >> 6) & 0x1F); 155 s[1] = 0x80 | ((wc) & 0x3F); 156 return 2; 157 } else { 158 if (n < 1) { 159 /* bound check failure */ 160 return 0; 161 } 162 163 s[0] = wc; 164 return 1; 165 } 166 } 167