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) 1997-2008 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_config.h" |
---|
46 | #include "pcre_internal.h" |
---|
47 | |
---|
48 | |
---|
49 | /************************************************* |
---|
50 | * Validate a UTF-8 string * |
---|
51 | *************************************************/ |
---|
52 | |
---|
53 | /* This function is called (optionally) at the start of compile or match, to |
---|
54 | validate that a supposed UTF-8 string is actually valid. The early check means |
---|
55 | that subsequent code can assume it is dealing with a valid string. The check |
---|
56 | can be turned off for maximum performance, but the consequences of supplying |
---|
57 | an invalid string are then undefined. |
---|
58 | |
---|
59 | Originally, this function checked according to RFC 2279, allowing for values in |
---|
60 | the range 0 to 0x7fffffff, up to 6 bytes long, but ensuring that they were in |
---|
61 | the canonical format. Once somebody had pointed out RFC 3629 to me (it |
---|
62 | obsoletes 2279), additional restrictions were applied. The values are now |
---|
63 | limited to be between 0 and 0x0010ffff, no more than 4 bytes long, and the |
---|
64 | subrange 0xd000 to 0xdfff is excluded. |
---|
65 | |
---|
66 | Arguments: |
---|
67 | string points to the string |
---|
68 | length length of string, or -1 if the string is zero-terminated |
---|
69 | |
---|
70 | Returns: < 0 if the string is a valid UTF-8 string |
---|
71 | >= 0 otherwise; the value is the offset of the bad byte |
---|
72 | */ |
---|
73 | |
---|
74 | int |
---|
75 | _pcre_valid_utf8(const uschar *string, int length) |
---|
76 | { |
---|
77 | #ifdef SUPPORT_UTF8 |
---|
78 | register const uschar *p; |
---|
79 | |
---|
80 | if (length < 0) |
---|
81 | { |
---|
82 | for (p = string; *p != 0; p++); |
---|
83 | length = p - string; |
---|
84 | } |
---|
85 | |
---|
86 | for (p = string; length-- > 0; p++) |
---|
87 | { |
---|
88 | register int ab; |
---|
89 | register int c = *p; |
---|
90 | if (c < 128) continue; |
---|
91 | if (c < 0xc0) return p - string; |
---|
92 | ab = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ |
---|
93 | if (length < ab || ab > 3) return p - string; |
---|
94 | length -= ab; |
---|
95 | |
---|
96 | /* Check top bits in the second byte */ |
---|
97 | if ((*(++p) & 0xc0) != 0x80) return p - string; |
---|
98 | |
---|
99 | /* Check for overlong sequences for each different length, and for the |
---|
100 | excluded range 0xd000 to 0xdfff. */ |
---|
101 | |
---|
102 | switch (ab) |
---|
103 | { |
---|
104 | /* Check for xx00 000x (overlong sequence) */ |
---|
105 | |
---|
106 | case 1: |
---|
107 | if ((c & 0x3e) == 0) return p - string; |
---|
108 | continue; /* We know there aren't any more bytes to check */ |
---|
109 | |
---|
110 | /* Check for 1110 0000, xx0x xxxx (overlong sequence) or |
---|
111 | 1110 1101, 1010 xxxx (0xd000 - 0xdfff) */ |
---|
112 | |
---|
113 | case 2: |
---|
114 | if ((c == 0xe0 && (*p & 0x20) == 0) || |
---|
115 | (c == 0xed && *p >= 0xa0)) |
---|
116 | return p - string; |
---|
117 | break; |
---|
118 | |
---|
119 | /* Check for 1111 0000, xx00 xxxx (overlong sequence) or |
---|
120 | greater than 0x0010ffff (f4 8f bf bf) */ |
---|
121 | |
---|
122 | case 3: |
---|
123 | if ((c == 0xf0 && (*p & 0x30) == 0) || |
---|
124 | (c > 0xf4 ) || |
---|
125 | (c == 0xf4 && *p > 0x8f)) |
---|
126 | return p - string; |
---|
127 | break; |
---|
128 | |
---|
129 | #if 0 |
---|
130 | /* These cases can no longer occur, as we restrict to a maximum of four |
---|
131 | bytes nowadays. Leave the code here in case we ever want to add an option |
---|
132 | for longer sequences. */ |
---|
133 | |
---|
134 | /* Check for 1111 1000, xx00 0xxx */ |
---|
135 | case 4: |
---|
136 | if (c == 0xf8 && (*p & 0x38) == 0) return p - string; |
---|
137 | break; |
---|
138 | |
---|
139 | /* Check for leading 0xfe or 0xff, and then for 1111 1100, xx00 00xx */ |
---|
140 | case 5: |
---|
141 | if (c == 0xfe || c == 0xff || |
---|
142 | (c == 0xfc && (*p & 0x3c) == 0)) return p - string; |
---|
143 | break; |
---|
144 | #endif |
---|
145 | |
---|
146 | } |
---|
147 | |
---|
148 | /* Check for valid bytes after the 2nd, if any; all must start 10 */ |
---|
149 | while (--ab > 0) |
---|
150 | { |
---|
151 | if ((*(++p) & 0xc0) != 0x80) return p - string; |
---|
152 | } |
---|
153 | } |
---|
154 | #else |
---|
155 | (void)(string); /* Keep picky compilers happy */ |
---|
156 | (void)(length); |
---|
157 | #endif |
---|
158 | |
---|
159 | return -1; |
---|
160 | } |
---|
161 | |
---|
162 | /* End of pcre_valid_utf8.c */ |
---|