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