1/* $Id */ 2 3/* This file is based on the GLIB utf8 validation functions. The 4 * original license text follows. */ 5 6/* gutf8.c - Operations on UTF-8 strings. 7 * 8 * Copyright (C) 1999 Tom Tromey 9 * Copyright (C) 2000 Red Hat, Inc. 10 * 11 * This library is free software; you can redistribute it and/or 12 * modify it under the terms of the GNU Lesser General Public 13 * License as published by the Free Software Foundation; either 14 * version 2 of the License, or (at your option) any later version. 15 * 16 * This library is distributed in the hope that it will be useful, 17 * but WITHOUT ANY WARRANTY; without even the implied warranty of 18 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU 19 * Lesser General Public License for more details. 20 * 21 * You should have received a copy of the GNU Lesser General Public 22 * License along with this library; if not, write to the 23 * Free Software Foundation, Inc., 59 Temple Place - Suite 330, 24 * Boston, MA 02111-1307, USA. 25 */ 26 27#ifdef HAVE_CONFIG_H 28#include <config.h> 29#endif 30 31#include <stdlib.h> 32 33#include "utf8.h" 34 35#define UNICODE_VALID(Char) \ 36 ((Char) < 0x110000 && \ 37 (((Char) & 0xFFFFF800) != 0xD800) && \ 38 ((Char) < 0xFDD0 || (Char) > 0xFDEF) && \ 39 ((Char) & 0xFFFE) != 0xFFFE) 40 41 42#define CONTINUATION_CHAR \ 43 do { \ 44 if ((*(const unsigned char *)p & 0xc0) != 0x80) /* 10xxxxxx */ \ 45 goto error; \ 46 val <<= 6; \ 47 val |= (*(const unsigned char *)p) & 0x3f; \ 48 } while(0) 49 50 51const char * 52avahi_utf8_valid (const char *str) 53 54{ 55 unsigned val = 0; 56 unsigned min = 0; 57 const char *p; 58 59 for (p = str; *p; p++) 60 { 61 if (*(const unsigned char *)p < 128) 62 /* done */; 63 else 64 { 65 const char *last; 66 67 last = p; 68 if ((*(const unsigned char *)p & 0xe0) == 0xc0) /* 110xxxxx */ 69 { 70 if ( ((*(const unsigned char *)p & 0x1e) == 0)) 71 goto error; 72 p++; 73 if ( ((*(const unsigned char *)p & 0xc0) != 0x80)) /* 10xxxxxx */ 74 goto error; 75 } 76 else 77 { 78 if ((*(const unsigned char *)p & 0xf0) == 0xe0) /* 1110xxxx */ 79 { 80 min = (1 << 11); 81 val = *(const unsigned char *)p & 0x0f; 82 goto TWO_REMAINING; 83 } 84 else if ((*(const unsigned char *)p & 0xf8) == 0xf0) /* 11110xxx */ 85 { 86 min = (1 << 16); 87 val = *(const unsigned char *)p & 0x07; 88 } 89 else 90 goto error; 91 92 p++; 93 CONTINUATION_CHAR; 94 TWO_REMAINING: 95 p++; 96 CONTINUATION_CHAR; 97 p++; 98 CONTINUATION_CHAR; 99 100 if ( (val < min)) 101 goto error; 102 103 if ( (!UNICODE_VALID(val))) 104 goto error; 105 } 106 107 continue; 108 109 error: 110 return NULL; 111 } 112 } 113 114 return str; 115} 116