patterns.php
2.81 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
<?php
/**
* PCRE Regular expressions for UTF-8. Note this file is not actually used by
* the rest of the library but these regular expressions can be useful to have
* available.
* @see http://www.w3.org/International/questions/qa-forms-utf-8
* @package utf8
*/
//--------------------------------------------------------------------
/**
* PCRE Pattern to check a UTF-8 string is valid
* Comes from W3 FAQ: Multilingual Forms
* Note: modified to include full ASCII range including control chars
* @see http://www.w3.org/International/questions/qa-forms-utf-8
* @package utf8
*/
$UTF8_VALID = '^('.
'[\x00-\x7F]'. # ASCII (including control chars)
'|[\xC2-\xDF][\x80-\xBF]'. # non-overlong 2-byte
'|\xE0[\xA0-\xBF][\x80-\xBF]'. # excluding overlongs
'|[\xE1-\xEC\xEE\xEF][\x80-\xBF]{2}'. # straight 3-byte
'|\xED[\x80-\x9F][\x80-\xBF]'. # excluding surrogates
'|\xF0[\x90-\xBF][\x80-\xBF]{2}'. # planes 1-3
'|[\xF1-\xF3][\x80-\xBF]{3}'. # planes 4-15
'|\xF4[\x80-\x8F][\x80-\xBF]{2}'. # plane 16
')*$';
//--------------------------------------------------------------------
/**
* PCRE Pattern to match single UTF-8 characters
* Comes from W3 FAQ: Multilingual Forms
* Note: modified to include full ASCII range including control chars
* @see http://www.w3.org/International/questions/qa-forms-utf-8
* @package utf8
*/
$UTF8_MATCH =
'([\x00-\x7F])'. # ASCII (including control chars)
'|([\xC2-\xDF][\x80-\xBF])'. # non-overlong 2-byte
'|(\xE0[\xA0-\xBF][\x80-\xBF])'. # excluding overlongs
'|([\xE1-\xEC\xEE\xEF][\x80-\xBF]{2})'. # straight 3-byte
'|(\xED[\x80-\x9F][\x80-\xBF])'. # excluding surrogates
'|(\xF0[\x90-\xBF][\x80-\xBF]{2})'. # planes 1-3
'|([\xF1-\xF3][\x80-\xBF]{3})'. # planes 4-15
'|(\xF4[\x80-\x8F][\x80-\xBF]{2})'; # plane 16
//--------------------------------------------------------------------
/**
* PCRE Pattern to locate bad bytes in a UTF-8 string
* Comes from W3 FAQ: Multilingual Forms
* Note: modified to include full ASCII range including control chars
* @see http://www.w3.org/International/questions/qa-forms-utf-8
* @package utf8
*/
$UTF8_BAD =
'([\x00-\x7F]'. # ASCII (including control chars)
'|[\xC2-\xDF][\x80-\xBF]'. # non-overlong 2-byte
'|\xE0[\xA0-\xBF][\x80-\xBF]'. # excluding overlongs
'|[\xE1-\xEC\xEE\xEF][\x80-\xBF]{2}'. # straight 3-byte
'|\xED[\x80-\x9F][\x80-\xBF]'. # excluding surrogates
'|\xF0[\x90-\xBF][\x80-\xBF]{2}'. # planes 1-3
'|[\xF1-\xF3][\x80-\xBF]{3}'. # planes 4-15
'|\xF4[\x80-\x8F][\x80-\xBF]{2}'. # plane 16
'|(.{1}))'; # invalid byte