1 : /*************************************************
2 : * Perl-Compatible Regular Expressions *
3 : *************************************************/
4 :
5 : /* PCRE is a library of functions to support regular expressions whose syntax
6 : and semantics are as close as possible to those of the Perl 5 language.
7 :
8 : Written by Philip Hazel
9 : Copyright (c) 1997-2006 University of Cambridge
10 :
11 : -----------------------------------------------------------------------------
12 : Redistribution and use in source and binary forms, with or without
13 : modification, are permitted provided that the following conditions are met:
14 :
15 : * Redistributions of source code must retain the above copyright notice,
16 : this list of conditions and the following disclaimer.
17 :
18 : * Redistributions in binary form must reproduce the above copyright
19 : notice, this list of conditions and the following disclaimer in the
20 : documentation and/or other materials provided with the distribution.
21 :
22 : * Neither the name of the University of Cambridge nor the names of its
23 : contributors may be used to endorse or promote products derived from
24 : this software without specific prior written permission.
25 :
26 : THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
27 : AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
28 : IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
29 : ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
30 : LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
31 : CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
32 : SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
33 : INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
34 : CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
35 : ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
36 : POSSIBILITY OF SUCH DAMAGE.
37 : -----------------------------------------------------------------------------
38 : */
39 :
40 :
41 : /* This module contains an internal function for validating UTF-8 character
42 : strings. */
43 :
44 :
45 : #include "pcre_internal.h"
46 :
47 :
48 : /*************************************************
49 : * Validate a UTF-8 string *
50 : *************************************************/
51 :
52 : /* This function is called (optionally) at the start of compile or match, to
53 : validate that a supposed UTF-8 string is actually valid. The early check means
54 : that subsequent code can assume it is dealing with a valid string. The check
55 : can be turned off for maximum performance, but the consequences of supplying
56 : an invalid string are then undefined.
57 :
58 : Arguments:
59 : string points to the string
60 : length length of string, or -1 if the string is zero-terminated
61 :
62 : Returns: < 0 if the string is a valid UTF-8 string
63 : >= 0 otherwise; the value is the offset of the bad byte
64 : */
65 :
66 : int
67 : _pcre_valid_utf8(const uschar *string, int length)
68 0 : {
69 : register const uschar *p;
70 :
71 0 : if (length < 0)
72 : {
73 0 : for (p = string; *p != 0; p++);
74 0 : length = p - string;
75 : }
76 :
77 0 : for (p = string; length-- > 0; p++)
78 : {
79 : register int ab;
80 0 : register int c = *p;
81 0 : if (c < 128) continue;
82 0 : if (c < 0xc0) return p - string;
83 0 : ab = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */
84 0 : if (length < ab) return p - string;
85 0 : length -= ab;
86 :
87 : /* Check top bits in the second byte */
88 0 : if ((*(++p) & 0xc0) != 0x80) return p - string;
89 :
90 : /* Check for overlong sequences for each different length */
91 0 : switch (ab)
92 : {
93 : /* Check for xx00 000x */
94 : case 1:
95 0 : if ((c & 0x3e) == 0) return p - string;
96 0 : continue; /* We know there aren't any more bytes to check */
97 :
98 : /* Check for 1110 0000, xx0x xxxx */
99 : case 2:
100 0 : if (c == 0xe0 && (*p & 0x20) == 0) return p - string;
101 0 : break;
102 :
103 : /* Check for 1111 0000, xx00 xxxx */
104 : case 3:
105 0 : if (c == 0xf0 && (*p & 0x30) == 0) return p - string;
106 0 : break;
107 :
108 : /* Check for 1111 1000, xx00 0xxx */
109 : case 4:
110 0 : if (c == 0xf8 && (*p & 0x38) == 0) return p - string;
111 0 : break;
112 :
113 : /* Check for leading 0xfe or 0xff, and then for 1111 1100, xx00 00xx */
114 : case 5:
115 0 : if (c == 0xfe || c == 0xff ||
116 0 : (c == 0xfc && (*p & 0x3c) == 0)) return p - string;
117 : break;
118 : }
119 :
120 : /* Check for valid bytes after the 2nd, if any; all must start 10 */
121 0 : while (--ab > 0)
122 : {
123 0 : if ((*(++p) & 0xc0) != 0x80) return p - string;
124 : }
125 : }
126 :
127 0 : return -1;
128 : }
129 :
130 : /* End of pcre_valid_utf8.c */
|
