1/* Conversion UTF-8 to UCS-4. 2 Copyright (C) 2001-2002, 2006-2007 Free Software Foundation, Inc. 3 Written by Bruno Haible <bruno@clisp.org>, 2001. 4 5 This program is free software: you can redistribute it and/or modify it 6 under the terms of the GNU General Public License as published 7 by the Free Software Foundation; either version 3 of the License, or 8 (at your option) any later version. 9 10 This program is distributed in the hope that it will be useful, 11 but WITHOUT ANY WARRANTY; without even the implied warranty of 12 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU 13 Lesser General Public License for more details. 14 15 You should have received a copy of the GNU General Public License 16 along with this program. If not, see <http://www.gnu.org/licenses/>. */ 17 18#include <config.h> 19 20/* Specification. */ 21#include "unistr.h" 22 23#if HAVE_INLINE 24 25int 26u8_mbtouc_unsafe_aux (ucs4_t *puc, const uint8_t *s, size_t n) 27{ 28 uint8_t c = *s; 29 30 if (c >= 0xc2) 31 { 32 if (c < 0xe0) 33 { 34 if (n >= 2) 35 { 36#if CONFIG_UNICODE_SAFETY 37 if ((s[1] ^ 0x80) < 0x40) 38#endif 39 { 40 *puc = ((unsigned int) (c & 0x1f) << 6) 41 | (unsigned int) (s[1] ^ 0x80); 42 return 2; 43 } 44 /* invalid multibyte character */ 45 } 46 else 47 { 48 /* incomplete multibyte character */ 49 *puc = 0xfffd; 50 return n; 51 } 52 } 53 else if (c < 0xf0) 54 { 55 if (n >= 3) 56 { 57#if CONFIG_UNICODE_SAFETY 58 if ((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40 59 && (c >= 0xe1 || s[1] >= 0xa0) 60 && (c != 0xed || s[1] < 0xa0)) 61#endif 62 { 63 *puc = ((unsigned int) (c & 0x0f) << 12) 64 | ((unsigned int) (s[1] ^ 0x80) << 6) 65 | (unsigned int) (s[2] ^ 0x80); 66 return 3; 67 } 68 /* invalid multibyte character */ 69 } 70 else 71 { 72 /* incomplete multibyte character */ 73 *puc = 0xfffd; 74 return n; 75 } 76 } 77 else if (c < 0xf8) 78 { 79 if (n >= 4) 80 { 81#if CONFIG_UNICODE_SAFETY 82 if ((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40 83 && (s[3] ^ 0x80) < 0x40 84 && (c >= 0xf1 || s[1] >= 0x90) 85#if 1 86 && (c < 0xf4 || (c == 0xf4 && s[1] < 0x90)) 87#endif 88 ) 89#endif 90 { 91 *puc = ((unsigned int) (c & 0x07) << 18) 92 | ((unsigned int) (s[1] ^ 0x80) << 12) 93 | ((unsigned int) (s[2] ^ 0x80) << 6) 94 | (unsigned int) (s[3] ^ 0x80); 95 return 4; 96 } 97 /* invalid multibyte character */ 98 } 99 else 100 { 101 /* incomplete multibyte character */ 102 *puc = 0xfffd; 103 return n; 104 } 105 } 106#if 0 107 else if (c < 0xfc) 108 { 109 if (n >= 5) 110 { 111#if CONFIG_UNICODE_SAFETY 112 if ((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40 113 && (s[3] ^ 0x80) < 0x40 && (s[4] ^ 0x80) < 0x40 114 && (c >= 0xf9 || s[1] >= 0x88)) 115#endif 116 { 117 *puc = ((unsigned int) (c & 0x03) << 24) 118 | ((unsigned int) (s[1] ^ 0x80) << 18) 119 | ((unsigned int) (s[2] ^ 0x80) << 12) 120 | ((unsigned int) (s[3] ^ 0x80) << 6) 121 | (unsigned int) (s[4] ^ 0x80); 122 return 5; 123 } 124 /* invalid multibyte character */ 125 } 126 else 127 { 128 /* incomplete multibyte character */ 129 *puc = 0xfffd; 130 return n; 131 } 132 } 133 else if (c < 0xfe) 134 { 135 if (n >= 6) 136 { 137#if CONFIG_UNICODE_SAFETY 138 if ((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40 139 && (s[3] ^ 0x80) < 0x40 && (s[4] ^ 0x80) < 0x40 140 && (s[5] ^ 0x80) < 0x40 141 && (c >= 0xfd || s[1] >= 0x84)) 142#endif 143 { 144 *puc = ((unsigned int) (c & 0x01) << 30) 145 | ((unsigned int) (s[1] ^ 0x80) << 24) 146 | ((unsigned int) (s[2] ^ 0x80) << 18) 147 | ((unsigned int) (s[3] ^ 0x80) << 12) 148 | ((unsigned int) (s[4] ^ 0x80) << 6) 149 | (unsigned int) (s[5] ^ 0x80); 150 return 6; 151 } 152 /* invalid multibyte character */ 153 } 154 else 155 { 156 /* incomplete multibyte character */ 157 *puc = 0xfffd; 158 return n; 159 } 160 } 161#endif 162 } 163 /* invalid multibyte character */ 164 *puc = 0xfffd; 165 return 1; 166} 167 168#endif 169