1
<?php
2
/**
3
* Provides string functions for UTF-8 strings
4
* use Iñtërnâtiônàlizætiøn for testing (it contains 20 characters)
5
*
6
* This class is implemented to provide a UTF-8 version of almost every built-in
7
* PHP string function. For more information about UTF-8, please visit
8
* http://flourishlib.com/docs/UTF-8.
9
*
10
* @author Zhou Yuan <yuanzhou19@gmail.com>
11
* @link http://www.infopotato.com/
12
* @copyright Copyright © 2009-2011 Zhou Yuan
13
* @license http://www.opensource.org/licenses/mit-license.php MIT Licence
14
* @link based on http://flourishlib.com/fUTF8
15
*/
16
class UTF8 {
17
/**
18
* Depending how things are compiled, NetBSD and Solaris don't support //IGNORE in iconv()
19
*
20
* If //IGNORE support is not provided strings with invalid characters will be truncated
21
*
22
* @var boolean
23
*/
24
private static $_can_ignore_invalid = NULL;
25
26
/**
27
* All lowercase UTF-8 characters mapped to uppercase characters
28
*
29
* @var array
30
*/
31
private static $_lower_to_upper = array(
32
'a' => 'A', 'b' => 'B', 'c' => 'C', 'd' => 'D', 'e' => 'E', 'f' => 'F',
33
'g' => 'G', 'h' => 'H', 'i' => 'I', 'j' => 'J', 'k' => 'K', 'l' => 'L',
34
'm' => 'M', 'n' => 'N', 'o' => 'O', 'p' => 'P', 'q' => 'Q', 'r' => 'R',
35
's' => 'S', 't' => 'T', 'u' => 'U', 'v' => 'V', 'w' => 'W', 'x' => 'X',
36
'y' => 'Y', 'z' => 'Z', 'à' => 'À', 'á' => 'Á', 'â' => 'Â', 'ã' => 'Ã',
37
'ä' => 'Ä', 'å' => 'Å', 'æ' => 'Æ', 'ç' => 'Ç', 'è' => 'È', 'é' => 'É',
38
'ê' => 'Ê', 'ë' => 'Ë', 'ì' => 'Ì', 'í' => 'Í', 'î' => 'Î', 'ï' => 'Ï',
39
'ð' => 'Ð', 'ñ' => 'Ñ', 'ò' => 'Ò', 'ó' => 'Ó', 'ô' => 'Ô', 'õ' => 'Õ',
40
'ö' => 'Ö', 'ø' => 'Ø', 'ù' => 'Ù', 'ú' => 'Ú', 'û' => 'Û', 'ü' => 'Ü',
41
'ý' => 'Ý', 'þ' => 'Þ', 'ā' => 'Ā', 'ă' => 'Ă', 'ą' => 'Ą', 'ć' => 'Ć',
42
'ĉ' => 'Ĉ', 'ċ' => 'Ċ', 'č' => 'Č', 'ď' => 'Ď', 'đ' => 'Đ', 'ē' => 'Ē',
43
'ĕ' => 'Ĕ', 'ė' => 'Ė', 'ę' => 'Ę', 'ě' => 'Ě', 'ĝ' => 'Ĝ', 'ğ' => 'Ğ',
44
'ġ' => 'Ġ', 'ģ' => 'Ģ', 'ĥ' => 'Ĥ', 'ħ' => 'Ħ', 'ĩ' => 'Ĩ', 'ī' => 'Ī',
45
'ĭ' => 'Ĭ', 'į' => 'Į', 'ij' => 'IJ', 'ĵ' => 'Ĵ', 'ķ' => 'Ķ', 'ĺ' => 'Ĺ',
46
'ļ' => 'Ļ', 'ľ' => 'Ľ', 'ŀ' => 'Ŀ', 'ł' => 'Ł', 'ń' => 'Ń', 'ņ' => 'Ņ',
47
'ň' => 'Ň', 'ŋ' => 'Ŋ', 'ō' => 'Ō', 'ŏ' => 'Ŏ', 'ő' => 'Ő', 'œ' => 'Œ',
48
'ŕ' => 'Ŕ', 'ŗ' => 'Ŗ', 'ř' => 'Ř', 'ś' => 'Ś', 'ŝ' => 'Ŝ', 'ş' => 'Ş',
49
'š' => 'Š', 'ţ' => 'Ţ', 'ť' => 'Ť', 'ŧ' => 'Ŧ', 'ũ' => 'Ũ', 'ū' => 'Ū',
50
'ŭ' => 'Ŭ', 'ů' => 'Ů', 'ű' => 'Ű', 'ų' => 'Ų', 'ŵ' => 'Ŵ', 'ŷ' => 'Ŷ',
51
'ÿ' => 'Ÿ', 'ź' => 'Ź', 'ż' => 'Ż', 'ž' => 'Ž', 'ɓ' => 'Ɓ', 'ƃ' => 'Ƃ',
52
'ƅ' => 'Ƅ', 'ɔ' => 'Ɔ', 'ƈ' => 'Ƈ', 'ɗ' => 'Ɗ', 'ƌ' => 'Ƌ', 'ɘ' => 'Ǝ',
53
'ə' => 'Ə', 'ɛ' => 'Ɛ', 'ƒ' => 'Ƒ', 'ɠ' => 'Ɠ', 'ɣ' => 'Ɣ', 'ɩ' => 'Ɩ',
54
'ɨ' => 'Ɨ', 'ƙ' => 'Ƙ', 'ɯ' => 'Ɯ', 'ɲ' => 'Ɲ', 'ɵ' => 'Ɵ', 'ơ' => 'Ơ',
55
'ƣ' => 'Ƣ', 'ƥ' => 'Ƥ', 'ƨ' => 'Ƨ', 'ʃ' => 'Ʃ', 'ƭ' => 'Ƭ', 'ʈ' => 'Ʈ',
56
'ư' => 'Ư', 'ʊ' => 'Ʊ', 'ʋ' => 'Ʋ', 'ƴ' => 'Ƴ', 'ƶ' => 'Ƶ', 'ʒ' => 'Ʒ',
57
'ƹ' => 'Ƹ', 'ƽ' => 'Ƽ', 'dž' => 'DŽ', 'dž' => 'Dž', 'lj' => 'LJ', 'lj' => 'Lj',
58
'nj' => 'NJ', 'nj' => 'Nj', 'ǎ' => 'Ǎ', 'ǐ' => 'Ǐ', 'ǒ' => 'Ǒ', 'ǔ' => 'Ǔ',
59
'ǖ' => 'Ǖ', 'ǘ' => 'Ǘ', 'ǚ' => 'Ǚ', 'ǜ' => 'Ǜ', 'ǟ' => 'Ǟ', 'ǡ' => 'Ǡ',
60
'ǣ' => 'Ǣ', 'ǥ' => 'Ǥ', 'ǧ' => 'Ǧ', 'ǩ' => 'Ǩ', 'ǫ' => 'Ǫ', 'ǭ' => 'Ǭ',
61
'ǯ' => 'Ǯ', 'dz' => 'DZ', 'ǵ' => 'Ǵ', 'ǻ' => 'Ǻ', 'ǽ' => 'Ǽ', 'ǿ' => 'Ǿ',
62
'ȁ' => 'Ȁ', 'ȃ' => 'Ȃ', 'ȅ' => 'Ȅ', 'ȇ' => 'Ȇ', 'ȉ' => 'Ȉ', 'ȋ' => 'Ȋ',
63
'ȍ' => 'Ȍ', 'ȏ' => 'Ȏ', 'ȑ' => 'Ȑ', 'ȓ' => 'Ȓ', 'ȕ' => 'Ȕ', 'ȗ' => 'Ȗ',
64
'ά' => 'Ά', 'έ' => 'Έ', 'ή' => 'Ή', 'ί' => 'Ί', 'ό' => 'Ό', 'ύ' => 'Ύ',
65
'ώ' => 'Ώ', 'α' => 'Α', 'β' => 'Β', 'γ' => 'Γ', 'δ' => 'Δ', 'ε' => 'Ε',
66
'ζ' => 'Ζ', 'η' => 'Η', 'θ' => 'Θ', 'ι' => 'Ι', 'κ' => 'Κ', 'λ' => 'Λ',
67
'μ' => 'Μ', 'ν' => 'Ν', 'ξ' => 'Ξ', 'ο' => 'Ο', 'π' => 'Π', 'ρ' => 'Ρ',
68
'σ' => 'Σ', 'τ' => 'Τ', 'υ' => 'Υ', 'φ' => 'Φ', 'χ' => 'Χ', 'ψ' => 'Ψ',
69
'ω' => 'Ω', 'ϊ' => 'Ϊ', 'ϋ' => 'Ϋ', 'ϣ' => 'Ϣ', 'ϥ' => 'Ϥ', 'ϧ' => 'Ϧ',
70
'ϩ' => 'Ϩ', 'ϫ' => 'Ϫ', 'ϭ' => 'Ϭ', 'ϯ' => 'Ϯ', 'ё' => 'Ё', 'ђ' => 'Ђ',
71
'ѓ' => 'Ѓ', 'є' => 'Є', 'ѕ' => 'Ѕ', 'і' => 'І', 'ї' => 'Ї', 'ј' => 'Ј',
72
'љ' => 'Љ', 'њ' => 'Њ', 'ћ' => 'Ћ', 'ќ' => 'Ќ', 'ў' => 'Ў', 'џ' => 'Џ',
73
'а' => 'А', 'б' => 'Б', 'в' => 'В', 'г' => 'Г', 'д' => 'Д', 'е' => 'Е',
74
'ж' => 'Ж', 'з' => 'З', 'и' => 'И', 'й' => 'Й', 'к' => 'К', 'л' => 'Л',
75
'м' => 'М', 'н' => 'Н', 'о' => 'О', 'п' => 'П', 'р' => 'Р', 'с' => 'С',
76
'т' => 'Т', 'у' => 'У', 'ф' => 'Ф', 'х' => 'Х', 'ц' => 'Ц', 'ч' => 'Ч',
77
'ш' => 'Ш', 'щ' => 'Щ', 'ъ' => 'Ъ', 'ы' => 'Ы', 'ь' => 'Ь', 'э' => 'Э',
78
'ю' => 'Ю', 'я' => 'Я', 'ѡ' => 'Ѡ', 'ѣ' => 'Ѣ', 'ѥ' => 'Ѥ', 'ѧ' => 'Ѧ',
79
'ѩ' => 'Ѩ', 'ѫ' => 'Ѫ', 'ѭ' => 'Ѭ', 'ѯ' => 'Ѯ', 'ѱ' => 'Ѱ', 'ѳ' => 'Ѳ',
80
'ѵ' => 'Ѵ', 'ѷ' => 'Ѷ', 'ѹ' => 'Ѹ', 'ѻ' => 'Ѻ', 'ѽ' => 'Ѽ', 'ѿ' => 'Ѿ',
81
'ҁ' => 'Ҁ', 'ґ' => 'Ґ', 'ғ' => 'Ғ', 'ҕ' => 'Ҕ', 'җ' => 'Җ', 'ҙ' => 'Ҙ',
82
'қ' => 'Қ', 'ҝ' => 'Ҝ', 'ҟ' => 'Ҟ', 'ҡ' => 'Ҡ', 'ң' => 'Ң', 'ҥ' => 'Ҥ',
83
'ҧ' => 'Ҧ', 'ҩ' => 'Ҩ', 'ҫ' => 'Ҫ', 'ҭ' => 'Ҭ', 'ү' => 'Ү', 'ұ' => 'Ұ',
84
'ҳ' => 'Ҳ', 'ҵ' => 'Ҵ', 'ҷ' => 'Ҷ', 'ҹ' => 'Ҹ', 'һ' => 'Һ', 'ҽ' => 'Ҽ',
85
'ҿ' => 'Ҿ', 'ӂ' => 'Ӂ', 'ӄ' => 'Ӄ', 'ӈ' => 'Ӈ', 'ӌ' => 'Ӌ', 'ӑ' => 'Ӑ',
86
'ӓ' => 'Ӓ', 'ӕ' => 'Ӕ', 'ӗ' => 'Ӗ', 'ә' => 'Ә', 'ӛ' => 'Ӛ', 'ӝ' => 'Ӝ',
87
'ӟ' => 'Ӟ', 'ӡ' => 'Ӡ', 'ӣ' => 'Ӣ', 'ӥ' => 'Ӥ', 'ӧ' => 'Ӧ', 'ө' => 'Ө',
88
'ӫ' => 'Ӫ', 'ӯ' => 'Ӯ', 'ӱ' => 'Ӱ', 'ӳ' => 'Ӳ', 'ӵ' => 'Ӵ', 'ӹ' => 'Ӹ',
89
'ա' => 'Ա', 'բ' => 'Բ', 'գ' => 'Գ', 'դ' => 'Դ', 'ե' => 'Ե', 'զ' => 'Զ',
90
'է' => 'Է', 'ը' => 'Ը', 'թ' => 'Թ', 'ժ' => 'Ժ', 'ի' => 'Ի', 'լ' => 'Լ',
91
'խ' => 'Խ', 'ծ' => 'Ծ', 'կ' => 'Կ', 'հ' => 'Հ', 'ձ' => 'Ձ', 'ղ' => 'Ղ',
92
'ճ' => 'Ճ', 'մ' => 'Մ', 'յ' => 'Յ', 'ն' => 'Ն', 'շ' => 'Շ', 'ո' => 'Ո',
93
'չ' => 'Չ', 'պ' => 'Պ', 'ջ' => 'Ջ', 'ռ' => 'Ռ', 'ս' => 'Ս', 'վ' => 'Վ',
94
'տ' => 'Տ', 'ր' => 'Ր', 'ց' => 'Ց', 'ւ' => 'Ւ', 'փ' => 'Փ', 'ք' => 'Ք',
95
'օ' => 'Օ', 'ֆ' => 'Ֆ', 'ა' => 'Ⴀ', 'ბ' => 'Ⴁ', 'გ' => 'Ⴂ', 'დ' => 'Ⴃ',
96
'ე' => 'Ⴄ', 'ვ' => 'Ⴅ', 'ზ' => 'Ⴆ', 'თ' => 'Ⴇ', 'ი' => 'Ⴈ', 'კ' => 'Ⴉ',
97
'ლ' => 'Ⴊ', 'მ' => 'Ⴋ', 'ნ' => 'Ⴌ', 'ო' => 'Ⴍ', 'პ' => 'Ⴎ', 'ჟ' => 'Ⴏ',
98
'რ' => 'Ⴐ', 'ს' => 'Ⴑ', 'ტ' => 'Ⴒ', 'უ' => 'Ⴓ', 'ფ' => 'Ⴔ', 'ქ' => 'Ⴕ',
99
'ღ' => 'Ⴖ', 'ყ' => 'Ⴗ', 'შ' => 'Ⴘ', 'ჩ' => 'Ⴙ', 'ც' => 'Ⴚ', 'ძ' => 'Ⴛ',
100
'წ' => 'Ⴜ', 'ჭ' => 'Ⴝ', 'ხ' => 'Ⴞ', 'ჯ' => 'Ⴟ', 'ჰ' => 'Ⴠ', 'ჱ' => 'Ⴡ',
101
'ჲ' => 'Ⴢ', 'ჳ' => 'Ⴣ', 'ჴ' => 'Ⴤ', 'ჵ' => 'Ⴥ', 'ḁ' => 'Ḁ', 'ḃ' => 'Ḃ',
102
'ḅ' => 'Ḅ', 'ḇ' => 'Ḇ', 'ḉ' => 'Ḉ', 'ḋ' => 'Ḋ', 'ḍ' => 'Ḍ', 'ḏ' => 'Ḏ',
103
'ḑ' => 'Ḑ', 'ḓ' => 'Ḓ', 'ḕ' => 'Ḕ', 'ḗ' => 'Ḗ', 'ḙ' => 'Ḙ', 'ḛ' => 'Ḛ',
104
'ḝ' => 'Ḝ', 'ḟ' => 'Ḟ', 'ḡ' => 'Ḡ', 'ḣ' => 'Ḣ', 'ḥ' => 'Ḥ', 'ḧ' => 'Ḧ',
105
'ḩ' => 'Ḩ', 'ḫ' => 'Ḫ', 'ḭ' => 'Ḭ', 'ḯ' => 'Ḯ', 'ḱ' => 'Ḱ', 'ḳ' => 'Ḳ',
106
'ḵ' => 'Ḵ', 'ḷ' => 'Ḷ', 'ḹ' => 'Ḹ', 'ḻ' => 'Ḻ', 'ḽ' => 'Ḽ', 'ḿ' => 'Ḿ',
107
'ṁ' => 'Ṁ', 'ṃ' => 'Ṃ', 'ṅ' => 'Ṅ', 'ṇ' => 'Ṇ', 'ṉ' => 'Ṉ', 'ṋ' => 'Ṋ',
108
'ṍ' => 'Ṍ', 'ṏ' => 'Ṏ', 'ṑ' => 'Ṑ', 'ṓ' => 'Ṓ', 'ṕ' => 'Ṕ', 'ṗ' => 'Ṗ',
109
'ṙ' => 'Ṙ', 'ṛ' => 'Ṛ', 'ṝ' => 'Ṝ', 'ṟ' => 'Ṟ', 'ṡ' => 'Ṡ', 'ṣ' => 'Ṣ',
110
'ṥ' => 'Ṥ', 'ṧ' => 'Ṧ', 'ṩ' => 'Ṩ', 'ṫ' => 'Ṫ', 'ṭ' => 'Ṭ', 'ṯ' => 'Ṯ',
111
'ṱ' => 'Ṱ', 'ṳ' => 'Ṳ', 'ṵ' => 'Ṵ', 'ṷ' => 'Ṷ', 'ṹ' => 'Ṹ', 'ṻ' => 'Ṻ',
112
'ṽ' => 'Ṽ', 'ṿ' => 'Ṿ', 'ẁ' => 'Ẁ', 'ẃ' => 'Ẃ', 'ẅ' => 'Ẅ', 'ẇ' => 'Ẇ',
113
'ẉ' => 'Ẉ', 'ẋ' => 'Ẋ', 'ẍ' => 'Ẍ', 'ẏ' => 'Ẏ', 'ẑ' => 'Ẑ', 'ẓ' => 'Ẓ',
114
'ẕ' => 'Ẕ', 'ạ' => 'Ạ', 'ả' => 'Ả', 'ấ' => 'Ấ', 'ầ' => 'Ầ', 'ẩ' => 'Ẩ',
115
'ẫ' => 'Ẫ', 'ậ' => 'Ậ', 'ắ' => 'Ắ', 'ằ' => 'Ằ', 'ẳ' => 'Ẳ', 'ẵ' => 'Ẵ',
116
'ặ' => 'Ặ', 'ẹ' => 'Ẹ', 'ẻ' => 'Ẻ', 'ẽ' => 'Ẽ', 'ế' => 'Ế', 'ề' => 'Ề',
117
'ể' => 'Ể', 'ễ' => 'Ễ', 'ệ' => 'Ệ', 'ỉ' => 'Ỉ', 'ị' => 'Ị', 'ọ' => 'Ọ',
118
'ỏ' => 'Ỏ', 'ố' => 'Ố', 'ồ' => 'Ồ', 'ổ' => 'Ổ', 'ỗ' => 'Ỗ', 'ộ' => 'Ộ',
119
'ớ' => 'Ớ', 'ờ' => 'Ờ', 'ở' => 'Ở', 'ỡ' => 'Ỡ', 'ợ' => 'Ợ', 'ụ' => 'Ụ',
120
'ủ' => 'Ủ', 'ứ' => 'Ứ', 'ừ' => 'Ừ', 'ử' => 'Ử', 'ữ' => 'Ữ', 'ự' => 'Ự',
121
'ỳ' => 'Ỳ', 'ỵ' => 'Ỵ', 'ỷ' => 'Ỷ', 'ỹ' => 'Ỹ', 'ἀ' => 'Ἀ', 'ἁ' => 'Ἁ',
122
'ἂ' => 'Ἂ', 'ἃ' => 'Ἃ', 'ἄ' => 'Ἄ', 'ἅ' => 'Ἅ', 'ἆ' => 'Ἆ', 'ἇ' => 'Ἇ',
123
'ἐ' => 'Ἐ', 'ἑ' => 'Ἑ', 'ἒ' => 'Ἒ', 'ἓ' => 'Ἓ', 'ἔ' => 'Ἔ', 'ἕ' => 'Ἕ',
124
'ἠ' => 'Ἠ', 'ἡ' => 'Ἡ', 'ἢ' => 'Ἢ', 'ἣ' => 'Ἣ', 'ἤ' => 'Ἤ', 'ἥ' => 'Ἥ',
125
'ἦ' => 'Ἦ', 'ἧ' => 'Ἧ', 'ἰ' => 'Ἰ', 'ἱ' => 'Ἱ', 'ἲ' => 'Ἲ', 'ἳ' => 'Ἳ',
126
'ἴ' => 'Ἴ', 'ἵ' => 'Ἵ', 'ἶ' => 'Ἶ', 'ἷ' => 'Ἷ', 'ὀ' => 'Ὀ', 'ὁ' => 'Ὁ',
127
'ὂ' => 'Ὂ', 'ὃ' => 'Ὃ', 'ὄ' => 'Ὄ', 'ὅ' => 'Ὅ', 'ὑ' => 'Ὑ', 'ὓ' => 'Ὓ',
128
'ὕ' => 'Ὕ', 'ὗ' => 'Ὗ', 'ὠ' => 'Ὠ', 'ὡ' => 'Ὡ', 'ὢ' => 'Ὢ', 'ὣ' => 'Ὣ',
129
'ὤ' => 'Ὤ', 'ὥ' => 'Ὥ', 'ὦ' => 'Ὦ', 'ὧ' => 'Ὧ', 'ᾀ' => 'ᾈ', 'ᾁ' => 'ᾉ',
130
'ᾂ' => 'ᾊ', 'ᾃ' => 'ᾋ', 'ᾄ' => 'ᾌ', 'ᾅ' => 'ᾍ', 'ᾆ' => 'ᾎ', 'ᾇ' => 'ᾏ',
131
'ᾐ' => 'ᾘ', 'ᾑ' => 'ᾙ', 'ᾒ' => 'ᾚ', 'ᾓ' => 'ᾛ', 'ᾔ' => 'ᾜ', 'ᾕ' => 'ᾝ',
132
'ᾖ' => 'ᾞ', 'ᾗ' => 'ᾟ', 'ᾠ' => 'ᾨ', 'ᾡ' => 'ᾩ', 'ᾢ' => 'ᾪ', 'ᾣ' => 'ᾫ',
133
'ᾤ' => 'ᾬ', 'ᾥ' => 'ᾭ', 'ᾦ' => 'ᾮ', 'ᾧ' => 'ᾯ', 'ᾰ' => 'Ᾰ', 'ᾱ' => 'Ᾱ',
134
'ῐ' => 'Ῐ', 'ῑ' => 'Ῑ', 'ῠ' => 'Ῠ', 'ῡ' => 'Ῡ', 'ⓐ' => 'Ⓐ', 'ⓑ' => 'Ⓑ',
135
'ⓒ' => 'Ⓒ', 'ⓓ' => 'Ⓓ', 'ⓔ' => 'Ⓔ', 'ⓕ' => 'Ⓕ', 'ⓖ' => 'Ⓖ', 'ⓗ' => 'Ⓗ',
136
'ⓘ' => 'Ⓘ', 'ⓙ' => 'Ⓙ', 'ⓚ' => 'Ⓚ', 'ⓛ' => 'Ⓛ', 'ⓜ' => 'Ⓜ', 'ⓝ' => 'Ⓝ',
137
'ⓞ' => 'Ⓞ', 'ⓟ' => 'Ⓟ', 'ⓠ' => 'Ⓠ', 'ⓡ' => 'Ⓡ', 'ⓢ' => 'Ⓢ', 'ⓣ' => 'Ⓣ',
138
'ⓤ' => 'Ⓤ', 'ⓥ' => 'Ⓥ', 'ⓦ' => 'Ⓦ', 'ⓧ' => 'Ⓧ', 'ⓨ' => 'Ⓨ', 'ⓩ' => 'Ⓩ',
139
'ａ' => 'Ａ', 'ｂ' => 'Ｂ', 'ｃ' => 'Ｃ', 'ｄ' => 'Ｄ', 'ｅ' => 'Ｅ', 'ｆ' => 'Ｆ',
140
'ｇ' => 'Ｇ', 'ｈ' => 'Ｈ', 'ｉ' => 'Ｉ', 'ｊ' => 'Ｊ', 'ｋ' => 'Ｋ', 'ｌ' => 'Ｌ',
141
'ｍ' => 'Ｍ', 'ｎ' => 'Ｎ', 'ｏ' => 'Ｏ', 'ｐ' => 'Ｐ', 'ｑ' => 'Ｑ', 'ｒ' => 'Ｒ',
142
'ｓ' => 'Ｓ', 'ｔ' => 'Ｔ', 'ｕ' => 'Ｕ', 'ｖ' => 'Ｖ', 'ｗ' => 'Ｗ', 'ｘ' => 'Ｘ',
143
'ｙ' => 'Ｙ', 'ｚ' => 'Ｚ'
144
);
145
146
/**
147
* All lowercase UTF-8 characters not properly handled by [http://php.net/mb_strtoupper mb_strtoupper()] mapped to uppercase characters
148
*
149
* @var array
150
*/
151
private static $_mb_lower_to_upper_fix = array(
152
'ɘ' => 'Ǝ', 'Dz' => 'DZ', 'ა' => 'Ⴀ', 'ბ' => 'Ⴁ', 'გ' => 'Ⴂ', 'დ' => 'Ⴃ',
153
'ე' => 'Ⴄ', 'ვ' => 'Ⴅ', 'ზ' => 'Ⴆ', 'თ' => 'Ⴇ', 'ი' => 'Ⴈ', 'კ' => 'Ⴉ',
154
'ლ' => 'Ⴊ', 'მ' => 'Ⴋ', 'ნ' => 'Ⴌ', 'ო' => 'Ⴍ', 'პ' => 'Ⴎ', 'ჟ' => 'Ⴏ',
155
'რ' => 'Ⴐ', 'ს' => 'Ⴑ', 'ტ' => 'Ⴒ', 'უ' => 'Ⴓ', 'ფ' => 'Ⴔ', 'ქ' => 'Ⴕ',
156
'ღ' => 'Ⴖ', 'ყ' => 'Ⴗ', 'შ' => 'Ⴘ', 'ჩ' => 'Ⴙ', 'ც' => 'Ⴚ', 'ძ' => 'Ⴛ',
157
'წ' => 'Ⴜ', 'ჭ' => 'Ⴝ', 'ხ' => 'Ⴞ', 'ჯ' => 'Ⴟ', 'ჰ' => 'Ⴠ', 'ჱ' => 'Ⴡ',
158
'ჲ' => 'Ⴢ', 'ჳ' => 'Ⴣ', 'ჴ' => 'Ⴤ', 'ჵ' => 'Ⴥ', 'ⓐ' => 'Ⓐ', 'ⓑ' => 'Ⓑ',
159
'ⓒ' => 'Ⓒ', 'ⓓ' => 'Ⓓ', 'ⓔ' => 'Ⓔ', 'ⓕ' => 'Ⓕ', 'ⓖ' => 'Ⓖ', 'ⓗ' => 'Ⓗ',
160
'ⓘ' => 'Ⓘ', 'ⓙ' => 'Ⓙ', 'ⓚ' => 'Ⓚ', 'ⓛ' => 'Ⓛ', 'ⓜ' => 'Ⓜ', 'ⓝ' => 'Ⓝ',
161
'ⓞ' => 'Ⓞ', 'ⓟ' => 'Ⓟ', 'ⓠ' => 'Ⓠ', 'ⓡ' => 'Ⓡ', 'ⓢ' => 'Ⓢ', 'ⓣ' => 'Ⓣ',
162
'ⓤ' => 'Ⓤ', 'ⓥ' => 'Ⓥ', 'ⓦ' => 'Ⓦ', 'ⓧ' => 'Ⓧ', 'ⓨ' => 'Ⓨ', 'ⓩ' => 'Ⓩ'
163
);
164
165
/**
166
* All uppercase UTF-8 characters not properly handled by [http://php.net/mb_strtolower mb_strtolower()] mapped to lowercase characters
167
*
168
* @var array
169
*/
170
private static $_mb_upper_to_lower_fix = array(
171
'ǝ' => 'ɘ', 'Dž' => 'dž', 'Lj' => 'lj', 'Nj' => 'nj', 'Ⴀ' => 'ა', 'Ⴁ' => 'ბ',
172
'Ⴂ' => 'გ', 'Ⴃ' => 'დ', 'Ⴄ' => 'ე', 'Ⴅ' => 'ვ', 'Ⴆ' => 'ზ', 'Ⴇ' => 'თ',
173
'Ⴈ' => 'ი', 'Ⴉ' => 'კ', 'Ⴊ' => 'ლ', 'Ⴋ' => 'მ', 'Ⴌ' => 'ნ', 'Ⴍ' => 'ო',
174
'Ⴎ' => 'პ', 'Ⴏ' => 'ჟ', 'Ⴐ' => 'რ', 'Ⴑ' => 'ს', 'Ⴒ' => 'ტ', 'Ⴓ' => 'უ',
175
'Ⴔ' => 'ფ', 'Ⴕ' => 'ქ', 'Ⴖ' => 'ღ', 'Ⴗ' => 'ყ', 'Ⴘ' => 'შ', 'Ⴙ' => 'ჩ',
176
'Ⴚ' => 'ც', 'Ⴛ' => 'ძ', 'Ⴜ' => 'წ', 'Ⴝ' => 'ჭ', 'Ⴞ' => 'ხ', 'Ⴟ' => 'ჯ',
177
'Ⴠ' => 'ჰ', 'Ⴡ' => 'ჱ', 'Ⴢ' => 'ჲ', 'Ⴣ' => 'ჳ', 'Ⴤ' => 'ჴ', 'Ⴥ' => 'ჵ',
178
'ᾈ' => 'ᾀ', 'ᾉ' => 'ᾁ', 'ᾊ' => 'ᾂ', 'ᾋ' => 'ᾃ', 'ᾌ' => 'ᾄ', 'ᾍ' => 'ᾅ',
179
'ᾎ' => 'ᾆ', 'ᾏ' => 'ᾇ', 'ᾘ' => 'ᾐ', 'ᾙ' => 'ᾑ', 'ᾚ' => 'ᾒ', 'ᾛ' => 'ᾓ',
180
'ᾜ' => 'ᾔ', 'ᾝ' => 'ᾕ', 'ᾞ' => 'ᾖ', 'ᾟ' => 'ᾗ', 'ᾨ' => 'ᾠ', 'ᾩ' => 'ᾡ',
181
'ᾪ' => 'ᾢ', 'ᾫ' => 'ᾣ', 'ᾬ' => 'ᾤ', 'ᾭ' => 'ᾥ', 'ᾮ' => 'ᾦ', 'ᾯ' => 'ᾧ',
182
'Ⓐ' => 'ⓐ', 'Ⓑ' => 'ⓑ', 'Ⓒ' => 'ⓒ', 'Ⓓ' => 'ⓓ', 'Ⓔ' => 'ⓔ', 'Ⓕ' => 'ⓕ',
183
'Ⓖ' => 'ⓖ', 'Ⓗ' => 'ⓗ', 'Ⓘ' => 'ⓘ', 'Ⓙ' => 'ⓙ', 'Ⓚ' => 'ⓚ', 'Ⓛ' => 'ⓛ',
184
'Ⓜ' => 'ⓜ', 'Ⓝ' => 'ⓝ', 'Ⓞ' => 'ⓞ', 'Ⓟ' => 'ⓟ', 'Ⓠ' => 'ⓠ', 'Ⓡ' => 'ⓡ',
185
'Ⓢ' => 'ⓢ', 'Ⓣ' => 'ⓣ', 'Ⓤ' => 'ⓤ', 'Ⓥ' => 'ⓥ', 'Ⓦ' => 'ⓦ', 'Ⓧ' => 'ⓧ',
186
'Ⓨ' => 'ⓨ', 'Ⓩ' => 'ⓩ'
187
);
188
189
/**
190
* All uppercase UTF-8 characters mapped to lowercase characters
191
*
192
* @var array
193
*/
194
private static $_upper_to_lower = array(
195
'A' => 'a', 'B' => 'b', 'C' => 'c', 'D' => 'd', 'E' => 'e', 'F' => 'f',
196
'G' => 'g', 'H' => 'h', 'I' => 'i', 'J' => 'j', 'K' => 'k', 'L' => 'l',
197
'M' => 'm', 'N' => 'n', 'O' => 'o', 'P' => 'p', 'Q' => 'q', 'R' => 'r',
198
'S' => 's', 'T' => 't', 'U' => 'u', 'V' => 'v', 'W' => 'w', 'X' => 'x',
199
'Y' => 'y', 'Z' => 'z', 'À' => 'à', 'Á' => 'á', 'Â' => 'â', 'Ã' => 'ã',
200
'Ä' => 'ä', 'Å' => 'å', 'Æ' => 'æ', 'Ç' => 'ç', 'È' => 'è', 'É' => 'é',
201
'Ê' => 'ê', 'Ë' => 'ë', 'Ì' => 'ì', 'Í' => 'í', 'Î' => 'î', 'Ï' => 'ï',
202
'Ð' => 'ð', 'Ñ' => 'ñ', 'Ò' => 'ò', 'Ó' => 'ó', 'Ô' => 'ô', 'Õ' => 'õ',
203
'Ö' => 'ö', 'Ø' => 'ø', 'Ù' => 'ù', 'Ú' => 'ú', 'Û' => 'û', 'Ü' => 'ü',
204
'Ý' => 'ý', 'Þ' => 'þ', 'Ā' => 'ā', 'Ă' => 'ă', 'Ą' => 'ą', 'Ć' => 'ć',
205
'Ĉ' => 'ĉ', 'Ċ' => 'ċ', 'Č' => 'č', 'Ď' => 'ď', 'Đ' => 'đ', 'Ē' => 'ē',
206
'Ĕ' => 'ĕ', 'Ė' => 'ė', 'Ę' => 'ę', 'Ě' => 'ě', 'Ĝ' => 'ĝ', 'Ğ' => 'ğ',
207
'Ġ' => 'ġ', 'Ģ' => 'ģ', 'Ĥ' => 'ĥ', 'Ħ' => 'ħ', 'Ĩ' => 'ĩ', 'Ī' => 'ī',
208
'Ĭ' => 'ĭ', 'Į' => 'į', 'İ' => 'i', 'IJ' => 'ij', 'Ĵ' => 'ĵ', 'Ķ' => 'ķ',
209
'Ĺ' => 'ĺ', 'Ļ' => 'ļ', 'Ľ' => 'ľ', 'Ŀ' => 'ŀ', 'Ł' => 'ł', 'Ń' => 'ń',
210
'Ņ' => 'ņ', 'Ň' => 'ň', 'Ŋ' => 'ŋ', 'Ō' => 'ō', 'Ŏ' => 'ŏ', 'Ő' => 'ő',
211
'Œ' => 'œ', 'Ŕ' => 'ŕ', 'Ŗ' => 'ŗ', 'Ř' => 'ř', 'Ś' => 'ś', 'Ŝ' => 'ŝ',
212
'Ş' => 'ş', 'Š' => 'š', 'Ţ' => 'ţ', 'Ť' => 'ť', 'Ŧ' => 'ŧ', 'Ũ' => 'ũ',
213
'Ū' => 'ū', 'Ŭ' => 'ŭ', 'Ů' => 'ů', 'Ű' => 'ű', 'Ų' => 'ų', 'Ŵ' => 'ŵ',
214
'Ŷ' => 'ŷ', 'Ÿ' => 'ÿ', 'Ź' => 'ź', 'Ż' => 'ż', 'Ž' => 'ž', 'Ɓ' => 'ɓ',
215
'Ƃ' => 'ƃ', 'Ƅ' => 'ƅ', 'Ɔ' => 'ɔ', 'Ƈ' => 'ƈ', 'Ɗ' => 'ɗ', 'Ƌ' => 'ƌ',
216
'Ǝ' => 'ɘ', 'Ə' => 'ə', 'Ɛ' => 'ɛ', 'Ƒ' => 'ƒ', 'Ɠ' => 'ɠ', 'Ɣ' => 'ɣ',
217
'Ɩ' => 'ɩ', 'Ɨ' => 'ɨ', 'Ƙ' => 'ƙ', 'Ɯ' => 'ɯ', 'Ɲ' => 'ɲ', 'Ɵ' => 'ɵ',
218
'Ơ' => 'ơ', 'Ƣ' => 'ƣ', 'Ƥ' => 'ƥ', 'Ƨ' => 'ƨ', 'Ʃ' => 'ʃ', 'Ƭ' => 'ƭ',
219
'Ʈ' => 'ʈ', 'Ư' => 'ư', 'Ʊ' => 'ʊ', 'Ʋ' => 'ʋ', 'Ƴ' => 'ƴ', 'Ƶ' => 'ƶ',
220
'Ʒ' => 'ʒ', 'Ƹ' => 'ƹ', 'Ƽ' => 'ƽ', 'DŽ' => 'dž', 'Dž' => 'dž', 'LJ' => 'lj',
221
'Lj' => 'lj', 'NJ' => 'nj', 'Nj' => 'nj', 'Ǎ' => 'ǎ', 'Ǐ' => 'ǐ', 'Ǒ' => 'ǒ',
222
'Ǔ' => 'ǔ', 'Ǖ' => 'ǖ', 'Ǘ' => 'ǘ', 'Ǚ' => 'ǚ', 'Ǜ' => 'ǜ', 'Ǟ' => 'ǟ',
223
'Ǡ' => 'ǡ', 'Ǣ' => 'ǣ', 'Ǥ' => 'ǥ', 'Ǧ' => 'ǧ', 'Ǩ' => 'ǩ', 'Ǫ' => 'ǫ',
224
'Ǭ' => 'ǭ', 'Ǯ' => 'ǯ', 'DZ' => 'dz', 'Ǵ' => 'ǵ', 'Ǻ' => 'ǻ', 'Ǽ' => 'ǽ',
225
'Ǿ' => 'ǿ', 'Ȁ' => 'ȁ', 'Ȃ' => 'ȃ', 'Ȅ' => 'ȅ', 'Ȇ' => 'ȇ', 'Ȉ' => 'ȉ',
226
'Ȋ' => 'ȋ', 'Ȍ' => 'ȍ', 'Ȏ' => 'ȏ', 'Ȑ' => 'ȑ', 'Ȓ' => 'ȓ', 'Ȕ' => 'ȕ',
227
'Ȗ' => 'ȗ', 'Ά' => 'ά', 'Έ' => 'έ', 'Ή' => 'ή', 'Ί' => 'ί', 'Ό' => 'ό',
228
'Ύ' => 'ύ', 'Ώ' => 'ώ', 'Α' => 'α', 'Β' => 'β', 'Γ' => 'γ', 'Δ' => 'δ',
229
'Ε' => 'ε', 'Ζ' => 'ζ', 'Η' => 'η', 'Θ' => 'θ', 'Ι' => 'ι', 'Κ' => 'κ',
230
'Λ' => 'λ', 'Μ' => 'μ', 'Ν' => 'ν', 'Ξ' => 'ξ', 'Ο' => 'ο', 'Π' => 'π',
231
'Ρ' => 'ρ', 'Σ' => 'σ', 'Τ' => 'τ', 'Υ' => 'υ', 'Φ' => 'φ', 'Χ' => 'χ',
232
'Ψ' => 'ψ', 'Ω' => 'ω', 'Ϊ' => 'ϊ', 'Ϋ' => 'ϋ', 'Ϣ' => 'ϣ', 'Ϥ' => 'ϥ',
233
'Ϧ' => 'ϧ', 'Ϩ' => 'ϩ', 'Ϫ' => 'ϫ', 'Ϭ' => 'ϭ', 'Ϯ' => 'ϯ', 'Ё' => 'ё',
234
'Ђ' => 'ђ', 'Ѓ' => 'ѓ', 'Є' => 'є', 'Ѕ' => 'ѕ', 'І' => 'і', 'Ї' => 'ї',
235
'Ј' => 'ј', 'Љ' => 'љ', 'Њ' => 'њ', 'Ћ' => 'ћ', 'Ќ' => 'ќ', 'Ў' => 'ў',
236
'Џ' => 'џ', 'А' => 'а', 'Б' => 'б', 'В' => 'в', 'Г' => 'г', 'Д' => 'д',
237
'Е' => 'е', 'Ж' => 'ж', 'З' => 'з', 'И' => 'и', 'Й' => 'й', 'К' => 'к',
238
'Л' => 'л', 'М' => 'м', 'Н' => 'н', 'О' => 'о', 'П' => 'п', 'Р' => 'р',
239
'С' => 'с', 'Т' => 'т', 'У' => 'у', 'Ф' => 'ф', 'Х' => 'х', 'Ц' => 'ц',
240
'Ч' => 'ч', 'Ш' => 'ш', 'Щ' => 'щ', 'Ъ' => 'ъ', 'Ы' => 'ы', 'Ь' => 'ь',
241
'Э' => 'э', 'Ю' => 'ю', 'Я' => 'я', 'Ѡ' => 'ѡ', 'Ѣ' => 'ѣ', 'Ѥ' => 'ѥ',
242
'Ѧ' => 'ѧ', 'Ѩ' => 'ѩ', 'Ѫ' => 'ѫ', 'Ѭ' => 'ѭ', 'Ѯ' => 'ѯ', 'Ѱ' => 'ѱ',
243
'Ѳ' => 'ѳ', 'Ѵ' => 'ѵ', 'Ѷ' => 'ѷ', 'Ѹ' => 'ѹ', 'Ѻ' => 'ѻ', 'Ѽ' => 'ѽ',
244
'Ѿ' => 'ѿ', 'Ҁ' => 'ҁ', 'Ґ' => 'ґ', 'Ғ' => 'ғ', 'Ҕ' => 'ҕ', 'Җ' => 'җ',
245
'Ҙ' => 'ҙ', 'Қ' => 'қ', 'Ҝ' => 'ҝ', 'Ҟ' => 'ҟ', 'Ҡ' => 'ҡ', 'Ң' => 'ң',
246
'Ҥ' => 'ҥ', 'Ҧ' => 'ҧ', 'Ҩ' => 'ҩ', 'Ҫ' => 'ҫ', 'Ҭ' => 'ҭ', 'Ү' => 'ү',
247
'Ұ' => 'ұ', 'Ҳ' => 'ҳ', 'Ҵ' => 'ҵ', 'Ҷ' => 'ҷ', 'Ҹ' => 'ҹ', 'Һ' => 'һ',
248
'Ҽ' => 'ҽ', 'Ҿ' => 'ҿ', 'Ӂ' => 'ӂ', 'Ӄ' => 'ӄ', 'Ӈ' => 'ӈ', 'Ӌ' => 'ӌ',
249
'Ӑ' => 'ӑ', 'Ӓ' => 'ӓ', 'Ӕ' => 'ӕ', 'Ӗ' => 'ӗ', 'Ә' => 'ә', 'Ӛ' => 'ӛ',
250
'Ӝ' => 'ӝ', 'Ӟ' => 'ӟ', 'Ӡ' => 'ӡ', 'Ӣ' => 'ӣ', 'Ӥ' => 'ӥ', 'Ӧ' => 'ӧ',
251
'Ө' => 'ө', 'Ӫ' => 'ӫ', 'Ӯ' => 'ӯ', 'Ӱ' => 'ӱ', 'Ӳ' => 'ӳ', 'Ӵ' => 'ӵ',
252
'Ӹ' => 'ӹ', 'Ա' => 'ա', 'Բ' => 'բ', 'Գ' => 'գ', 'Դ' => 'դ', 'Ե' => 'ե',
253
'Զ' => 'զ', 'Է' => 'է', 'Ը' => 'ը', 'Թ' => 'թ', 'Ժ' => 'ժ', 'Ի' => 'ի',
254
'Լ' => 'լ', 'Խ' => 'խ', 'Ծ' => 'ծ', 'Կ' => 'կ', 'Հ' => 'հ', 'Ձ' => 'ձ',
255
'Ղ' => 'ղ', 'Ճ' => 'ճ', 'Մ' => 'մ', 'Յ' => 'յ', 'Ն' => 'ն', 'Շ' => 'շ',
256
'Ո' => 'ո', 'Չ' => 'չ', 'Պ' => 'պ', 'Ջ' => 'ջ', 'Ռ' => 'ռ', 'Ս' => 'ս',
257
'Վ' => 'վ', 'Տ' => 'տ', 'Ր' => 'ր', 'Ց' => 'ց', 'Ւ' => 'ւ', 'Փ' => 'փ',
258
'Ք' => 'ք', 'Օ' => 'օ', 'Ֆ' => 'ֆ', 'Ⴀ' => 'ა', 'Ⴁ' => 'ბ', 'Ⴂ' => 'გ',
259
'Ⴃ' => 'დ', 'Ⴄ' => 'ე', 'Ⴅ' => 'ვ', 'Ⴆ' => 'ზ', 'Ⴇ' => 'თ', 'Ⴈ' => 'ი',
260
'Ⴉ' => 'კ', 'Ⴊ' => 'ლ', 'Ⴋ' => 'მ', 'Ⴌ' => 'ნ', 'Ⴍ' => 'ო', 'Ⴎ' => 'პ',
261
'Ⴏ' => 'ჟ', 'Ⴐ' => 'რ', 'Ⴑ' => 'ს', 'Ⴒ' => 'ტ', 'Ⴓ' => 'უ', 'Ⴔ' => 'ფ',
262
'Ⴕ' => 'ქ', 'Ⴖ' => 'ღ', 'Ⴗ' => 'ყ', 'Ⴘ' => 'შ', 'Ⴙ' => 'ჩ', 'Ⴚ' => 'ც',
263
'Ⴛ' => 'ძ', 'Ⴜ' => 'წ', 'Ⴝ' => 'ჭ', 'Ⴞ' => 'ხ', 'Ⴟ' => 'ჯ', 'Ⴠ' => 'ჰ',
264
'Ⴡ' => 'ჱ', 'Ⴢ' => 'ჲ', 'Ⴣ' => 'ჳ', 'Ⴤ' => 'ჴ', 'Ⴥ' => 'ჵ', 'Ḁ' => 'ḁ',
265
'Ḃ' => 'ḃ', 'Ḅ' => 'ḅ', 'Ḇ' => 'ḇ', 'Ḉ' => 'ḉ', 'Ḋ' => 'ḋ', 'Ḍ' => 'ḍ',
266
'Ḏ' => 'ḏ', 'Ḑ' => 'ḑ', 'Ḓ' => 'ḓ', 'Ḕ' => 'ḕ', 'Ḗ' => 'ḗ', 'Ḙ' => 'ḙ',
267
'Ḛ' => 'ḛ', 'Ḝ' => 'ḝ', 'Ḟ' => 'ḟ', 'Ḡ' => 'ḡ', 'Ḣ' => 'ḣ', 'Ḥ' => 'ḥ',
268
'Ḧ' => 'ḧ', 'Ḩ' => 'ḩ', 'Ḫ' => 'ḫ', 'Ḭ' => 'ḭ', 'Ḯ' => 'ḯ', 'Ḱ' => 'ḱ',
269
'Ḳ' => 'ḳ', 'Ḵ' => 'ḵ', 'Ḷ' => 'ḷ', 'Ḹ' => 'ḹ', 'Ḻ' => 'ḻ', 'Ḽ' => 'ḽ',
270
'Ḿ' => 'ḿ', 'Ṁ' => 'ṁ', 'Ṃ' => 'ṃ', 'Ṅ' => 'ṅ', 'Ṇ' => 'ṇ', 'Ṉ' => 'ṉ',
271
'Ṋ' => 'ṋ', 'Ṍ' => 'ṍ', 'Ṏ' => 'ṏ', 'Ṑ' => 'ṑ', 'Ṓ' => 'ṓ', 'Ṕ' => 'ṕ',
272
'Ṗ' => 'ṗ', 'Ṙ' => 'ṙ', 'Ṛ' => 'ṛ', 'Ṝ' => 'ṝ', 'Ṟ' => 'ṟ', 'Ṡ' => 'ṡ',
273
'Ṣ' => 'ṣ', 'Ṥ' => 'ṥ', 'Ṧ' => 'ṧ', 'Ṩ' => 'ṩ', 'Ṫ' => 'ṫ', 'Ṭ' => 'ṭ',
274
'Ṯ' => 'ṯ', 'Ṱ' => 'ṱ', 'Ṳ' => 'ṳ', 'Ṵ' => 'ṵ', 'Ṷ' => 'ṷ', 'Ṹ' => 'ṹ',
275
'Ṻ' => 'ṻ', 'Ṽ' => 'ṽ', 'Ṿ' => 'ṿ', 'Ẁ' => 'ẁ', 'Ẃ' => 'ẃ', 'Ẅ' => 'ẅ',
276
'Ẇ' => 'ẇ', 'Ẉ' => 'ẉ', 'Ẋ' => 'ẋ', 'Ẍ' => 'ẍ', 'Ẏ' => 'ẏ', 'Ẑ' => 'ẑ',
277
'Ẓ' => 'ẓ', 'Ẕ' => 'ẕ', 'Ạ' => 'ạ', 'Ả' => 'ả', 'Ấ' => 'ấ', 'Ầ' => 'ầ',
278
'Ẩ' => 'ẩ', 'Ẫ' => 'ẫ', 'Ậ' => 'ậ', 'Ắ' => 'ắ', 'Ằ' => 'ằ', 'Ẳ' => 'ẳ',
279
'Ẵ' => 'ẵ', 'Ặ' => 'ặ', 'Ẹ' => 'ẹ', 'Ẻ' => 'ẻ', 'Ẽ' => 'ẽ', 'Ế' => 'ế',
280
'Ề' => 'ề', 'Ể' => 'ể', 'Ễ' => 'ễ', 'Ệ' => 'ệ', 'Ỉ' => 'ỉ', 'Ị' => 'ị',
281
'Ọ' => 'ọ', 'Ỏ' => 'ỏ', 'Ố' => 'ố', 'Ồ' => 'ồ', 'Ổ' => 'ổ', 'Ỗ' => 'ỗ',
282
'Ộ' => 'ộ', 'Ớ' => 'ớ', 'Ờ' => 'ờ', 'Ở' => 'ở', 'Ỡ' => 'ỡ', 'Ợ' => 'ợ',
283
'Ụ' => 'ụ', 'Ủ' => 'ủ', 'Ứ' => 'ứ', 'Ừ' => 'ừ', 'Ử' => 'ử', 'Ữ' => 'ữ',
284
'Ự' => 'ự', 'Ỳ' => 'ỳ', 'Ỵ' => 'ỵ', 'Ỷ' => 'ỷ', 'Ỹ' => 'ỹ', 'Ἀ' => 'ἀ',
285
'Ἁ' => 'ἁ', 'Ἂ' => 'ἂ', 'Ἃ' => 'ἃ', 'Ἄ' => 'ἄ', 'Ἅ' => 'ἅ', 'Ἆ' => 'ἆ',
286
'Ἇ' => 'ἇ', 'Ἐ' => 'ἐ', 'Ἑ' => 'ἑ', 'Ἒ' => 'ἒ', 'Ἓ' => 'ἓ', 'Ἔ' => 'ἔ',
287
'Ἕ' => 'ἕ', 'Ἠ' => 'ἠ', 'Ἡ' => 'ἡ', 'Ἢ' => 'ἢ', 'Ἣ' => 'ἣ', 'Ἤ' => 'ἤ',
288
'Ἥ' => 'ἥ', 'Ἦ' => 'ἦ', 'Ἧ' => 'ἧ', 'Ἰ' => 'ἰ', 'Ἱ' => 'ἱ', 'Ἲ' => 'ἲ',
289
'Ἳ' => 'ἳ', 'Ἴ' => 'ἴ', 'Ἵ' => 'ἵ', 'Ἶ' => 'ἶ', 'Ἷ' => 'ἷ', 'Ὀ' => 'ὀ',
290
'Ὁ' => 'ὁ', 'Ὂ' => 'ὂ', 'Ὃ' => 'ὃ', 'Ὄ' => 'ὄ', 'Ὅ' => 'ὅ', 'Ὑ' => 'ὑ',
291
'Ὓ' => 'ὓ', 'Ὕ' => 'ὕ', 'Ὗ' => 'ὗ', 'Ὠ' => 'ὠ', 'Ὡ' => 'ὡ', 'Ὢ' => 'ὢ',
292
'Ὣ' => 'ὣ', 'Ὤ' => 'ὤ', 'Ὥ' => 'ὥ', 'Ὦ' => 'ὦ', 'Ὧ' => 'ὧ', 'ᾈ' => 'ᾀ',
293
'ᾉ' => 'ᾁ', 'ᾊ' => 'ᾂ', 'ᾋ' => 'ᾃ', 'ᾌ' => 'ᾄ', 'ᾍ' => 'ᾅ', 'ᾎ' => 'ᾆ',
294
'ᾏ' => 'ᾇ', 'ᾘ' => 'ᾐ', 'ᾙ' => 'ᾑ', 'ᾚ' => 'ᾒ', 'ᾛ' => 'ᾓ', 'ᾜ' => 'ᾔ',
295
'ᾝ' => 'ᾕ', 'ᾞ' => 'ᾖ', 'ᾟ' => 'ᾗ', 'ᾨ' => 'ᾠ', 'ᾩ' => 'ᾡ', 'ᾪ' => 'ᾢ',
296
'ᾫ' => 'ᾣ', 'ᾬ' => 'ᾤ', 'ᾭ' => 'ᾥ', 'ᾮ' => 'ᾦ', 'ᾯ' => 'ᾧ', 'Ᾰ' => 'ᾰ',
297
'Ᾱ' => 'ᾱ', 'Ῐ' => 'ῐ', 'Ῑ' => 'ῑ', 'Ῠ' => 'ῠ', 'Ῡ' => 'ῡ', 'Ⓐ' => 'ⓐ',
298
'Ⓑ' => 'ⓑ', 'Ⓒ' => 'ⓒ', 'Ⓓ' => 'ⓓ', 'Ⓔ' => 'ⓔ', 'Ⓕ' => 'ⓕ', 'Ⓖ' => 'ⓖ',
299
'Ⓗ' => 'ⓗ', 'Ⓘ' => 'ⓘ', 'Ⓙ' => 'ⓙ', 'Ⓚ' => 'ⓚ', 'Ⓛ' => 'ⓛ', 'Ⓜ' => 'ⓜ',
300
'Ⓝ' => 'ⓝ', 'Ⓞ' => 'ⓞ', 'Ⓟ' => 'ⓟ', 'Ⓠ' => 'ⓠ', 'Ⓡ' => 'ⓡ', 'Ⓢ' => 'ⓢ',
301
'Ⓣ' => 'ⓣ', 'Ⓤ' => 'ⓤ', 'Ⓥ' => 'ⓥ', 'Ⓦ' => 'ⓦ', 'Ⓧ' => 'ⓧ', 'Ⓨ' => 'ⓨ',
302
'Ⓩ' => 'ⓩ', 'Ａ' => 'ａ', 'Ｂ' => 'ｂ', 'Ｃ' => 'ｃ', 'Ｄ' => 'ｄ', 'Ｅ' => 'ｅ',
303
'Ｆ' => 'ｆ', 'Ｇ' => 'ｇ', 'Ｈ' => 'ｈ', 'Ｉ' => 'ｉ', 'Ｊ' => 'ｊ', 'Ｋ' => 'ｋ',
304
'Ｌ' => 'ｌ', 'Ｍ' => 'ｍ', 'Ｎ' => 'ｎ', 'Ｏ' => 'ｏ', 'Ｐ' => 'ｐ', 'Ｑ' => 'ｑ',
305
'Ｒ' => 'ｒ', 'Ｓ' => 'ｓ', 'Ｔ' => 'ｔ', 'Ｕ' => 'ｕ', 'Ｖ' => 'ｖ', 'Ｗ' => 'ｗ',
306
'Ｘ' => 'ｘ', 'Ｙ' => 'ｙ', 'Ｚ' => 'ｚ'
307
);
308
309
/**
310
* A mapping of all ASCII-based latin characters, puntuation, symbols and number forms to ASCII.
311
*
312
* Includes elements form the following unicode blocks:
313
*
314
* - Latin-1 Supplement
315
* - Latin Extended-A
316
* - Latin Extended-B
317
* - IPA Extensions
318
* - Latin Extended Additional
319
* - General Punctuation
320
* - Letterlike symbols
321
* - Number Forms
322
*
323
* @var array
324
*/
325
private static $_utf8_to_ascii = array(
326
// Latin-1 Supplement
327
'©' => '(c)', '«' => '<<', '®' => '(R)', '»' => '>>', '¼' => '1/4',
328
'½' => '1/2', '¾' => '3/4', 'À' => 'A', 'Á' => 'A', 'Â' => 'A',
329
'Ã' => 'A', 'Ä' => 'A', 'Å' => 'A', 'Æ' => 'AE', 'Ç' => 'C',
330
'È' => 'E', 'É' => 'E', 'Ê' => 'E', 'Ë' => 'E', 'Ì' => 'I',
331
'Í' => 'I', 'Î' => 'I', 'Ï' => 'I', 'Ñ' => 'N', 'Ò' => 'O',
332
'Ó' => 'O', 'Ô' => 'O', 'Õ' => 'O', 'Ö' => 'O', 'Ø' => 'O',
333
'Ù' => 'U', 'Ú' => 'U', 'Û' => 'U', 'Ü' => 'U', 'Ý' => 'Y',
334
'à' => 'a', 'á' => 'a', 'â' => 'a', 'ã' => 'a', 'ä' => 'a',
335
'å' => 'a', 'æ' => 'ae', 'ç' => 'c', 'è' => 'e', 'é' => 'e',
336
'ê' => 'e', 'ë' => 'e', 'ì' => 'i', 'í' => 'i', 'î' => 'i',
337
'ï' => 'i', 'ñ' => 'n', 'ò' => 'o', 'ó' => 'o', 'ô' => 'o',
338
'õ' => 'o', 'ö' => 'o', 'ø' => 'o', 'ù' => 'u', 'ú' => 'u',
339
'û' => 'u', 'ü' => 'u', 'ý' => 'y', 'ÿ' => 'y',
340
// Latin Extended-A
341
'Ā' => 'A', 'ā' => 'a', 'Ă' => 'A', 'ă' => 'a', 'Ą' => 'A',
342
'ą' => 'a', 'Ć' => 'C', 'ć' => 'c', 'Ĉ' => 'C', 'ĉ' => 'c',
343
'Ċ' => 'C', 'ċ' => 'c', 'Č' => 'C', 'č' => 'c', 'Ď' => 'D',
344
'ď' => 'd', 'Đ' => 'D', 'đ' => 'd', 'Ē' => 'E', 'ē' => 'e',
345
'Ĕ' => 'E', 'ĕ' => 'e', 'Ė' => 'E', 'ė' => 'e', 'Ę' => 'E',
346
'ę' => 'e', 'Ě' => 'E', 'ě' => 'e', 'Ĝ' => 'G', 'ĝ' => 'g',
347
'Ğ' => 'G', 'ğ' => 'g', 'Ġ' => 'G', 'ġ' => 'g', 'Ģ' => 'G',
348
'ģ' => 'g', 'Ĥ' => 'H', 'ĥ' => 'h', 'Ħ' => 'H', 'ħ' => 'h',
349
'Ĩ' => 'I', 'ĩ' => 'i', 'Ī' => 'I', 'ī' => 'i', 'Ĭ' => 'I',
350
'ĭ' => 'i', 'Į' => 'I', 'į' => 'i', 'İ' => 'I', 'ı' => 'i',
351
'IJ' => 'IJ', 'ij' => 'ij', 'Ĵ' => 'J', 'ĵ' => 'j', 'Ķ' => 'K',
352
'ķ' => 'k', 'Ĺ' => 'L', 'ĺ' => 'l', 'Ļ' => 'L', 'ļ' => 'l',
353
'Ľ' => 'L', 'ľ' => 'l', 'Ŀ' => 'L', 'ŀ' => 'l', 'Ł' => 'L',
354
'ł' => 'l', 'Ń' => 'N', 'ń' => 'n', 'Ņ' => 'N', 'ņ' => 'n',
355
'Ň' => 'N', 'ň' => 'n', 'ʼn' => "'n", 'Ŋ' => 'N', 'ŋ' => 'n',
356
'Ō' => 'O', 'ō' => 'o', 'Ŏ' => 'O', 'ŏ' => 'o', 'Ő' => 'O',
357
'ő' => 'o', 'Œ' => 'OE', 'œ' => 'oe', 'Ŕ' => 'R', 'ŕ' => 'r',
358
'Ŗ' => 'R', 'ŗ' => 'r', 'Ř' => 'R', 'ř' => 'r', 'Ś' => 'S',
359
'ś' => 's', 'Ŝ' => 'S', 'ŝ' => 's', 'Ş' => 'S', 'ş' => 's',
360
'Š' => 'S', 'š' => 's', 'Ţ' => 'T', 'ţ' => 't', 'Ť' => 'T',
361
'ť' => 't', 'Ŧ' => 'T', 'ŧ' => 't', 'Ũ' => 'U', 'ũ' => 'u',
362
'Ū' => 'U', 'ū' => 'u', 'Ŭ' => 'U', 'ŭ' => 'u', 'Ů' => 'U',
363
'ů' => 'u', 'Ű' => 'U', 'ű' => 'u', 'Ų' => 'U', 'ų' => 'u',
364
'Ŵ' => 'W', 'ŵ' => 'w', 'Ŷ' => 'Y', 'ŷ' => 'y', 'Ÿ' => 'Y',
365
'Ź' => 'Z', 'ź' => 'z', 'Ż' => 'Z', 'ż' => 'z', 'Ž' => 'Z',
366
'ž' => 'z',
367
// Latin Extended-B
368
'ƀ' => 'b', 'Ɓ' => 'B', 'Ƃ' => 'B', 'ƃ' => 'b', 'Ɔ' => 'O',
369
'Ƈ' => 'C', 'ƈ' => 'c', 'Ɖ' => 'D', 'Ɗ' => 'D', 'Ƌ' => 'D',
370
'ƌ' => 'd', 'Ǝ' => 'E', 'Ɛ' => 'E', 'Ƒ' => 'F', 'ƒ' => 'f',
371
'Ɠ' => 'G', 'Ɨ' => 'I', 'Ƙ' => 'K', 'ƙ' => 'k', 'ƚ' => 'l',
372
'Ɯ' => 'M', 'Ɲ' => 'N', 'ƞ' => 'n', 'Ɵ' => 'O', 'Ơ' => 'O',
373
'ơ' => 'o', 'Ƣ' => 'OI', 'ƣ' => 'oi', 'Ƥ' => 'P', 'ƥ' => 'p',
374
'ƫ' => 't', 'Ƭ' => 'T', 'ƭ' => 't', 'Ʈ' => 'T', 'Ư' => 'U',
375
'ư' => 'u', 'Ʋ' => 'V', 'Ƴ' => 'Y', 'ƴ' => 'y', 'Ƶ' => 'Z',
376
'ƶ' => 'z', 'ƻ' => '2', 'DŽ' => 'DZ', 'Dž' => 'Dz', 'dž' => 'dz',
377
'LJ' => 'LJ', 'Lj' => 'Lj', 'lj' => 'lj', 'NJ' => 'Nj', 'Nj' => 'Nj',
378
'nj' => 'nj', 'Ǎ' => 'A', 'ǎ' => 'a', 'Ǐ' => 'I', 'ǐ' => 'i',
379
'Ǒ' => 'O', 'ǒ' => 'o', 'Ǔ' => 'U', 'ǔ' => 'u', 'Ǖ' => 'U',
380
'ǖ' => 'u', 'Ǘ' => 'U', 'ǘ' => 'u', 'Ǚ' => 'U', 'ǚ' => 'u',
381
'Ǜ' => 'U', 'ǜ' => 'u', 'ǝ' => 'e', 'Ǟ' => 'A', 'ǟ' => 'a',
382
'Ǡ' => 'A', 'ǡ' => 'a', 'Ǣ' => 'AE', 'ǣ' => 'ae', 'Ǥ' => 'G',
383
'ǥ' => 'g', 'Ǧ' => 'G', 'ǧ' => 'g', 'Ǩ' => 'K', 'ǩ' => 'k',
384
'Ǫ' => 'O', 'ǫ' => 'o', 'Ǭ' => 'O', 'ǭ' => 'o', 'ǰ' => 'j',
385
'DZ' => 'DZ', 'Dz' => 'Dz', 'dz' => 'dz', 'Ǵ' => 'G', 'ǵ' => 'g',
386
'Ǹ' => 'N', 'ǹ' => 'n', 'Ǻ' => 'A', 'ǻ' => 'a', 'Ǽ' => 'AE',
387
'ǽ' => 'ae', 'Ǿ' => 'O', 'ǿ' => 'o', 'Ȁ' => 'A', 'ȁ' => 'a',
388
'Ȃ' => 'A', 'ȃ' => 'a', 'Ȅ' => 'E', 'ȅ' => 'e', 'Ȇ' => 'E',
389
'ȇ' => 'e', 'Ȉ' => 'I', 'ȉ' => 'i', 'Ȋ' => 'I', 'ȋ' => 'i',
390
'Ȍ' => 'O', 'ȍ' => 'o', 'Ȏ' => 'O', 'ȏ' => 'o', 'Ȑ' => 'R',
391
'ȑ' => 'r', 'Ȓ' => 'R', 'ȓ' => 'r', 'Ȕ' => 'U', 'ȕ' => 'u',
392
'Ȗ' => 'U', 'ȗ' => 'u', 'Ș' => 'S', 'ș' => 's', 'Ț' => 'T',
393
'ț' => 't', 'Ȟ' => 'H', 'ȟ' => 'h', 'Ƞ' => 'N', 'ȡ' => 'd',
394
'Ȥ' => 'Z', 'ȥ' => 'z', 'Ȧ' => 'A', 'ȧ' => 'a', 'Ȩ' => 'E',
395
'ȩ' => 'e', 'Ȫ' => 'O', 'ȫ' => 'o', 'Ȭ' => 'O', 'ȭ' => 'o',
396
'Ȯ' => 'O', 'ȯ' => 'o', 'Ȱ' => 'O', 'ȱ' => 'o', 'Ȳ' => 'Y',
397
'ȳ' => 'y', 'ȴ' => 'l', 'ȵ' => 'n', 'ȶ' => 't', 'ȷ' => 'j',
398
'ȸ' => 'db', 'ȹ' => 'qp', 'Ⱥ' => 'A', 'Ȼ' => 'C', 'ȼ' => 'c',
399
'Ƚ' => 'L', 'Ⱦ' => 'T', 'ȿ' => 's', 'ɀ' => 'z', 'Ƀ' => 'B',
400
'Ʉ' => 'U', 'Ʌ' => 'V', 'Ɇ' => 'E', 'ɇ' => 'e', 'Ɉ' => 'J',
401
'ɉ' => 'j', 'Ɋ' => 'Q', 'ɋ' => 'q', 'Ɍ' => 'R', 'ɍ' => 'r',
402
'Ɏ' => 'Y', 'ɏ' => 'y',
403
// IPA Extensions
404
'ɐ' => 'a', 'ɓ' => 'b', 'ɔ' => 'o', 'ɕ' => 'c', 'ɖ' => 'd',
405
'ɗ' => 'd', 'ɘ' => 'e', 'ɛ' => 'e', 'ɜ' => 'e', 'ɝ' => 'e',
406
'ɞ' => 'e', 'ɟ' => 'j', 'ɠ' => 'g', 'ɡ' => 'g', 'ɢ' => 'G',
407
'ɥ' => 'h', 'ɦ' => 'h', 'ɨ' => 'i', 'ɪ' => 'I', 'ɫ' => 'l',
408
'ɬ' => 'l', 'ɭ' => 'l', 'ɯ' => 'm', 'ɰ' => 'm', 'ɱ' => 'm',
409
'ɲ' => 'n', 'ɳ' => 'n', 'ɴ' => 'N', 'ɵ' => 'o', 'ɶ' => 'OE',
410
'ɹ' => 'r', 'ɺ' => 'r', 'ɻ' => 'r', 'ɼ' => 'r', 'ɽ' => 'r',
411
'ɾ' => 'r', 'ɿ' => 'r', 'ʀ' => 'R', 'ʁ' => 'R', 'ʂ' => 's',
412
'ʇ' => 't', 'ʈ' => 't', 'ʉ' => 'u', 'ʋ' => 'v', 'ʌ' => 'v',
413
'ʍ' => 'w', 'ʎ' => 'y', 'ʏ' => 'Y', 'ʐ' => 'z', 'ʑ' => 'z',
414
'ʗ' => 'C', 'ʙ' => 'B', 'ʚ' => 'e', 'ʛ' => 'G', 'ʜ' => 'H',
415
'ʝ' => 'j', 'ʞ' => 'k', 'ʟ' => 'L', 'ʠ' => 'q', 'ʣ' => 'dz',
416
'ʥ' => 'dz', 'ʦ' => 'ts', 'ʨ' => 'tc', 'ʪ' => 'ls', 'ʫ' => 'lz',
417
'ʮ' => 'h', 'ʯ' => 'h',
418
// Latin Extended Additional
419
'Ḁ' => 'A', 'ḁ' => 'a', 'Ḃ' => 'B', 'ḃ' => 'b', 'Ḅ' => 'B',
420
'ḅ' => 'b', 'Ḇ' => 'B', 'ḇ' => 'b', 'Ḉ' => 'C', 'ḉ' => 'c',
421
'Ḋ' => 'D', 'ḋ' => 'd', 'Ḍ' => 'D', 'ḍ' => 'd', 'Ḏ' => 'D',
422
'ḏ' => 'd', 'Ḑ' => 'D', 'ḑ' => 'd', 'Ḓ' => 'D', 'ḓ' => 'd',
423
'Ḕ' => 'E', 'ḕ' => 'e', 'Ḗ' => 'E', 'ḗ' => 'e', 'Ḙ' => 'E',
424
'ḙ' => 'e', 'Ḛ' => 'E', 'ḛ' => 'e', 'Ḝ' => 'E', 'ḝ' => 'e',
425
'Ḟ' => 'F', 'ḟ' => 'f', 'Ḡ' => 'G', 'ḡ' => 'g', 'Ḣ' => 'H',
426
'ḣ' => 'h', 'Ḥ' => 'H', 'ḥ' => 'h', 'Ḧ' => 'H', 'ḧ' => 'h',
427
'Ḩ' => 'H', 'ḩ' => 'h', 'Ḫ' => 'H', 'ḫ' => 'h', 'Ḭ' => 'I',
428
'ḭ' => 'i', 'Ḯ' => 'I', 'ḯ' => 'i', 'Ḱ' => 'K', 'ḱ' => 'k',
429
'Ḳ' => 'K', 'ḳ' => 'k', 'Ḵ' => 'K', 'ḵ' => 'k', 'Ḷ' => 'L',
430
'ḷ' => 'l', 'Ḹ' => 'L', 'ḹ' => 'l', 'Ḻ' => 'L', 'ḻ' => 'l',
431
'Ḽ' => 'L', 'ḽ' => 'l', 'Ḿ' => 'M', 'ḿ' => 'm', 'Ṁ' => 'M',
432
'ṁ' => 'm', 'Ṃ' => 'M', 'ṃ' => 'm', 'Ṅ' => 'N', 'ṅ' => 'n',
433
'Ṇ' => 'N', 'ṇ' => 'n', 'Ṉ' => 'N', 'ṉ' => 'n', 'Ṋ' => 'N',
434
'ṋ' => 'n', 'Ṍ' => 'O', 'ṍ' => 'o', 'Ṏ' => 'O', 'ṏ' => 'o',
435
'Ṑ' => 'O', 'ṑ' => 'o', 'Ṓ' => 'O', 'ṓ' => 'o', 'Ṕ' => 'P',
436
'ṕ' => 'p', 'Ṗ' => 'P', 'ṗ' => 'p', 'Ṙ' => 'R', 'ṙ' => 'r',
437
'Ṛ' => 'R', 'ṛ' => 'r', 'Ṝ' => 'R', 'ṝ' => 'r', 'Ṟ' => 'R',
438
'ṟ' => 'r', 'Ṡ' => 'S', 'ṡ' => 's', 'Ṣ' => 'S', 'ṣ' => 's',
439
'Ṥ' => 'S', 'ṥ' => 's', 'Ṧ' => 'S', 'ṧ' => 's', 'Ṩ' => 'S',
440
'ṩ' => 's', 'Ṫ' => 'T', 'ṫ' => 't', 'Ṭ' => 'T', 'ṭ' => 't',
441
'Ṯ' => 'T', 'ṯ' => 't', 'Ṱ' => 'T', 'ṱ' => 't', 'Ṳ' => 'U',
442
'ṳ' => 'u', 'Ṵ' => 'U', 'ṵ' => 'u', 'Ṷ' => 'U', 'ṷ' => 'u',
443
'Ṹ' => 'U', 'ṹ' => 'u', 'Ṻ' => 'U', 'ṻ' => 'u', 'Ṽ' => 'V',
444
'ṽ' => 'v', 'Ṿ' => 'V', 'ṿ' => 'v', 'Ẁ' => 'W', 'ẁ' => 'w',
445
'Ẃ' => 'W', 'ẃ' => 'w', 'Ẅ' => 'W', 'ẅ' => 'w', 'Ẇ' => 'W',
446
'ẇ' => 'w', 'Ẉ' => 'W', 'ẉ' => 'w', 'Ẋ' => 'X', 'ẋ' => 'x',
447
'Ẍ' => 'X', 'ẍ' => 'x', 'Ẏ' => 'Y', 'ẏ' => 'y', 'Ẑ' => 'Z',
448
'ẑ' => 'z', 'Ẓ' => 'Z', 'ẓ' => 'z', 'Ẕ' => 'Z', 'ẕ' => 'z',
449
'ẖ' => 'h', 'ẗ' => 't', 'ẘ' => 'w', 'ẙ' => 'y', 'ẚ' => 'a',
450
'Ạ' => 'A', 'ạ' => 'a', 'Ả' => 'A', 'ả' => 'a', 'Ấ' => 'A',
451
'ấ' => 'a', 'Ầ' => 'A', 'ầ' => 'a', 'Ẩ' => 'A', 'ẩ' => 'a',
452
'Ẫ' => 'A', 'ẫ' => 'a', 'Ậ' => 'A', 'ậ' => 'a', 'Ắ' => 'A',
453
'ắ' => 'a', 'Ằ' => 'A', 'ằ' => 'a', 'Ẳ' => 'A', 'ẳ' => 'a',
454
'Ẵ' => 'A', 'ẵ' => 'a', 'Ặ' => 'A', 'ặ' => 'a', 'Ẹ' => 'E',
455
'ẹ' => 'e', 'Ẻ' => 'E', 'ẻ' => 'e', 'Ẽ' => 'E', 'ẽ' => 'e',
456
'Ế' => 'E', 'ế' => 'e', 'Ề' => 'E', 'ề' => 'e', 'Ể' => 'E',
457
'ể' => 'e', 'Ễ' => 'E', 'ễ' => 'e', 'Ệ' => 'E', 'ệ' => 'e',
458
'Ỉ' => 'I', 'ỉ' => 'i', 'Ị' => 'I', 'ị' => 'i', 'Ọ' => 'O',
459
'ọ' => 'o', 'Ỏ' => 'O', 'ỏ' => 'o', 'Ố' => 'O', 'ố' => 'o',
460
'Ồ' => 'O', 'ồ' => 'o', 'Ổ' => 'O', 'ổ' => 'o', 'Ỗ' => 'O',
461
'ỗ' => 'o', 'Ộ' => 'O', 'ộ' => 'o', 'Ớ' => 'O', 'ớ' => 'o',
462
'Ờ' => 'O', 'ờ' => 'o', 'Ở' => 'O', 'ở' => 'o', 'Ỡ' => 'O',
463
'ỡ' => 'o', 'Ợ' => 'O', 'ợ' => 'o', 'Ụ' => 'U', 'ụ' => 'u',
464
'Ủ' => 'U', 'ủ' => 'u', 'Ứ' => 'U', 'ứ' => 'u', 'Ừ' => 'U',
465
'ừ' => 'u', 'Ử' => 'U', 'ử' => 'u', 'Ữ' => 'U', 'ữ' => 'u',
466
'Ự' => 'U', 'ự' => 'u', 'Ỳ' => 'Y', 'ỳ' => 'y', 'Ỵ' => 'Y',
467
'ỵ' => 'y', 'Ỷ' => 'Y', 'ỷ' => 'y', 'Ỹ' => 'Y', 'ỹ' => 'y',
468
// General Punctuation
469
' ' => ' ', ' ' => ' ', ' ' => ' ', ' ' => ' ', ' ' => ' ',
470
' ' => ' ', ' ' => ' ', ' ' => ' ', ' ' => ' ', ' ' => ' ',
471
' ' => ' ', '' => '', '' => '', '' => '', '‐' => '-',
472
'‑' => '-', '‒' => '-', '–' => '-', '—' => '-', '―' => '-',
473
'‖' => '||', '‘' => "'", '’' => "'", '‚' => ',', '‛' => "'",
474
'“' => '"', '”' => '"', '‟' => '"', '․' => '.', '‥' => '..',
475
'…' => '...', ' ' => ' ', '′' => "'", '″' => '"', '‴' => '\'"',
476
'‵' => "'", '‶' => '"', '‷' => '"\'', '‹' => '<', '›' => '>',
477
'‼' => '!!', '‽' => '?!', '⁄' => '/', '⁇' => '?/', '⁈' => '?!',
478
'⁉' => '!?',
479
// Letterlike Symbols
480
'℠' => 'SM', '™' => 'TM',
481
// Number Forms
482
'⅓' => '1/3', '⅔' => '2/3', '⅕' => '1/5', '⅖' => '2/5', '⅗' => '3/5',
483
'⅘' => '4/5', '⅙' => '1/6', '⅚' => '5/6', '⅛' => '1/8', '⅜' => '3/8',
484
'⅝' => '5/8', '⅞' => '7/8', 'Ⅰ' => 'I', 'Ⅱ' => 'II', 'Ⅲ' => 'III',
485
'Ⅳ' => 'IV', 'Ⅴ' => 'V', 'Ⅵ' => 'Vi', 'Ⅶ' => 'VII', 'Ⅷ' => 'VIII',
486
'Ⅸ' => 'IX', 'Ⅹ' => 'X', 'Ⅺ' => 'XI', 'Ⅻ' => 'XII', 'Ⅼ' => 'L',
487
'Ⅽ' => 'C', 'Ⅾ' => 'D', 'Ⅿ' => 'M', 'ⅰ' => 'i', 'ⅱ' => 'ii',
488
'ⅲ' => 'iii', 'ⅳ' => 'iv', 'ⅴ' => 'v', 'ⅵ' => 'vi', 'ⅶ' => 'vii',
489
'ⅷ' => 'viii','ⅸ' => 'ix', 'ⅹ' => 'x', 'ⅺ' => 'xi', 'ⅻ' => 'xii',
490
'ⅼ' => 'l', 'ⅽ' => 'c', 'ⅾ' => 'd', 'ⅿ' => 'm'
491
);
492
493
/**
494
* If the [http://php.net/mbstring mbstring] extension is available
495
*
496
* @var boolean
497
*/
498
private static $_mbstring_available = NULL;
499
500
/**
501
* Forces use as a static class
502
*
503
* @return UTF8
504
*/
505
private function __construct() { }
506
507
/**
508
* Maps UTF-8 ASCII-based latin characters, puntuation, symbols and number forms to ASCII
509
*
510
* Any characters or symbols that can not be translated will be removed.
511
*
512
* This function is most useful for situation that only allows ASCII, such
513
* as in URLs.
514
*
515
* Translates elements form the following unicode blocks:
516
*
517
* - Latin-1 Supplement
518
* - Latin Extended-A
519
* - Latin Extended-B
520
* - IPA Extensions
521
* - Latin Extended Additional
522
* - General Punctuation
523
* - Letterlike symbols
524
* - Number Forms
525
*
526
* @internal
527
*
528
* @param string $str The string to convert
529
* @return string The input string in pure ASCII
530
*/
531
public static function ascii($str) {
532
if ( ! self::detect($str)) {
533
return $str;
534
}
535
536
$str = strtr($str, self::$_utf8_to_ascii);
537
return preg_replace('#[^\x00-\x7F]#', '', $str);
538
}
539
540
541
/**
542
* Checks to see if the [http://php.net/mbstring mbstring] extension is available
543
*
544
* @return void
545
*/
546
private static function _check_mb_string() {
547
self::$_mbstring_available = extension_loaded('mbstring');
548
}
549
550
551
/**
552
* Converts a unicode value into a UTF-8 character
553
*
554
* @param mixed $unicode_code_point The character to create, either the `U+hex` or decimal code point
555
* @return string The UTF-8 character
556
*/
557
public static function chr($unicode_code_point) {
558
if (is_string($unicode_code_point) && substr($unicode_code_point, 0, 2) == 'U+') {
559
$unicode_code_point = substr($unicode_code_point, 2);
560
$unicode_code_point = hexdec($unicode_code_point);
561
}
562
563
$bin = decbin($unicode_code_point);
564
$digits = strlen($bin);
565
566
$first = $second = $third = $fourth = NULL;
567
568
// One byte characters
569
if ($digits <= 7) {
570
$first = chr(bindec($bin));
571
572
// Two byte characters
573
} elseif ($digits <= 11) {
574
$first = chr(bindec('110' . str_pad(substr($bin, 0, -6), 5, '0', STR_PAD_LEFT)));
575
$second = chr(bindec('10' . substr($bin, -6)));
576
577
// Three byte characters
578
} elseif ($digits <= 16) {
579
$first = chr(bindec('1110' . str_pad(substr($bin, 0, -12), 4, '0', STR_PAD_LEFT)));
580
$second = chr(bindec('10' . substr($bin, -12, -6)));
581
$third = chr(bindec('10' . substr($bin, -6)));
582
583
// Four byte characters
584
} elseif ($digits <= 21) {
585
$first = chr(bindec('11110' . str_pad(substr($bin, 0, -18), 3, '0', STR_PAD_LEFT)));
586
$second = chr(bindec('10' . substr($bin, -18, -12)));
587
$third = chr(bindec('10' . substr($bin, -12, -6)));
588
$fourth = chr(bindec('10' . substr($bin, -6)));
589
}
590
591
$ord = ord($first);
592
if ($digits > 21 || $ord == 0xC0 || $ord == 0xC1 || $ord > 0xF4) {
593
halt('A System Error Was Encountered', "The code point specified {$unicode_code_point} is invalid", 'sys_error');
594
}
595
596
return $first . $second . $third . $fourth;
597
}
598
599
600
/**
601
* Removes any invalid UTF-8 characters from a string or array of strings
602
*
603
* @param array|string $value The string or array of strings to clean
604
* @return string The cleaned string
605
*/
606
public static function clean($value) {
607
if ( ! is_array($value)) {
608
if (self::$_can_ignore_invalid === NULL) {
609
self::$_can_ignore_invalid = strtolower(ICONV_IMPL) != 'unknown';
610
}
611
// The iconv PHP extension provides functionality to convert text stored in another encoding to UTF-8 using a simple function call
612
return iconv('UTF-8', 'UTF-8' . (self::$_can_ignore_invalid ? '//IGNORE' : ''), (string) $value);
613
}
614
615
$keys = array_keys($value);
616
$num_keys = sizeof($keys);
617
for ($i=0; $i < $num_keys; $i++) {
618
$value[$keys[$i]] = self::clean($value[$keys[$i]]);
619
}
620
621
return $value;
622
}
623
624
625
/**
626
* Compares strings, with the resulting order having latin characters that are based on ASCII letters placed after the relative ASCII characters
627
*
628
* Please note that this function sorts based on English language sorting
629
* rules only. Locale-sepcific sorting is done by
630
* [http://php.net/strcoll strcoll()], however there are technical
631
* limitations.
632
*
633
* @param string $str1 The first string to compare
634
* @param string $str2 The second string to compare
635
* @return integer < 0 if $str1 < $str2, 0 if they are equal, > 0 if $str1 > $str2
636
*/
637
public static function cmp($str1, $str2) {
638
$ascii_str1 = strtr($str1, self::$_utf8_to_ascii);
639
$ascii_str2 = strtr($str2, self::$_utf8_to_ascii);
640
641
$res = strcmp($ascii_str1, $ascii_str2);
642
643
// If the ASCII representations are the same, sort by the UTF-8 representations
644
if ($res === 0) {
645
$res = strcmp($str1, $str2);
646
}
647
648
return $res;
649
}
650
651
652
/**
653
* Converts an offset in characters to an offset in bytes to that we can use the built-in functions for some operations
654
*
655
* @param string $str The string to base the offset on
656
* @param integer $offset The character offset to conver to bytes
657
* @return integer The converted offset
658
*/
659
private static function _convert_offset_to_bytes($str, $offset) {
660
if ($offset == 0) {
661
return 0;
662
}
663
664
$len = strlen($str);
665
666
$byte_offset = 0;
667
$measured_offset = 0;
668
$sign = 1;
669
670
// Negative offsets require us to reverse some stuff
671
if ($offset < 0) {
672
$str = strrev($str);
673
$sign = -1;
674
$offset = abs($offset);
675
}
676
677
for ($i = 0; $i < $len && $measured_offset < $offset; $i++) {
678
$char = $str[$i];
679
++$byte_offset;
680
if (ord($char) < 0x80) {
681
++$measured_offset;
682
} else {
683
switch (ord($char) & 0xF0) {
684
case 0xF0:
685
case 0xE0:
686
case 0xD0:
687
case 0xC0:
688
++$measured_offset;
689
break;
690
}
691
}
692
}
693
694
return $byte_offset * $sign;
695
}
696
697
698
/**
699
* Detects if a UTF-8 string contains any non-ASCII characters
700
*
701
* @param string $str The string to check
702
* @return boolean If the string contains any non-ASCII characters
703
*/
704
private static function detect($str) {
705
return (boolean) preg_match('#[^\x00-\x7F]#', $str);
706
}
707
708
709
/**
710
* Explodes a string on a delimiter
711
*
712
* If no delimiter is provided, the string will be exploded with each
713
* characters being an element in the array.
714
*
715
* @param string $str The string to explode
716
* @param string $delimiter The string to explode on. If `NULL` or `''` this method will return one character per array index.
717
* @return array The exploded string
718
*/
719
public static function explode($str, $delimiter = NULL) {
720
// If a delimiter was passed, we just do an explode
721
if ($delimiter || ( ! $delimiter && is_numeric($delimiter))) {
722
return explode($delimiter, $str);
723
}
724
725
// If no delimiter was passed, we explode the characters into an array
726
preg_match_all('#.|^\z#us', $str, $matches);
727
return $matches[0];
728
}
729
730
731
/**
732
* Compares strings in a case-insensitive manner, with the resulting order having characters that are based on ASCII letters placed after the relative ASCII characters
733
*
734
* Please note that this function sorts based on English language sorting
735
* rules only. Locale-sepcific sorting is done by
736
* [http://php.net/strcoll strcoll()], however there are technical
737
* limitations.
738
*
739
* @param string $str1 The first string to compare
740
* @param string $str2 The second string to compare
741
* @return integer < 0 if $str1 < $str2, 0 if they are equal, > 0 if $str1 > $str2
742
*/
743
public static function icmp($str1, $str2) {
744
$str1 = self::lower($str1);
745
$str2 = self::lower($str2);
746
747
return self::cmp($str1, $str2);
748
}
749
750
751
/**
752
* Compares strings using a natural order algorithm in a case-insensitive manner, with the resulting order having latin characters that are based on ASCII letters placed after the relative ASCII characters
753
*
754
* Please note that this function sorts based on English language sorting
755
* rules only. Locale-sepcific sorting is done by
756
* [http://php.net/strcoll strcoll()], however there are technical
757
* limitations.
758
*
759
* @param string $str1 The first string to compare
760
* @param string $str2 The second string to compare
761
* @return integer `< 0` if `$str1 < $str2`, `0` if they are equal, `> 0` if `$str1 > $str2`
762
*/
763
public static function inatcmp($str1, $str2) {
764
$str1 = self::lower($str1);
765
$str2 = self::lower($str2);
766
767
return self::natcmp($str1, $str2);
768
}
769
770
771
/**
772
* Finds the first position (in characters) of the search value in the string - case is ignored when doing performing a match
773
*
774
* @param string $haystack The string to search in
775
* @param string $needle The string to search for. This match will be done in a case-insensitive manner.
776
* @param integer $offset The character position to start searching from
777
* @return mixed The integer character position of the first occurence of the needle or `FALSE` if no match
778
*/
779
public static function ipos($haystack, $needle, $offset = 0) {
780
// We get better performance falling back for ASCII strings
781
if ( ! self::detect($haystack)) {
782
return stripos($haystack, $needle, $offset);
783
}
784
785
if (self::$_mbstring_available === NULL) {
786
self::_check_mb_string();
787
}
788
789
if (self::$_mbstring_available && function_exists('mb_stripos')) {
790
return mb_stripos($haystack, $needle, $offset, 'UTF-8');
791
}
792
793
$haystack = self::lower($haystack);
794
$needle = self::lower($needle);
795
796
return self::pos($haystack, $needle, $offset);
797
}
798
799
800
/**
801
* Replaces matching parts of the string, with matches being done in a a case-insensitive manner
802
*
803
* If `$search` and `$replace` are both arrays and `$replace` is shorter,
804
* the extra `$search` string will be replaced with an empty string. If
805
* `$search` is an array and `$replace` is a string, all `$search` values
806
* will be replaced with the string specified.
807
*
808
* @param string $str The string to perform the replacements on
809
* @param mixed $search The string (or array of strings) to search for - see method description for details
810
* @param mixed $replace The string (or array of strings) to replace with - see method description for details
811
* @return string The input string with the specified replacements
812
*/
813
public static function ireplace($str, $search, $replace) {
814
if (is_array($search)) {
815
foreach ($search as &$needle) {
816
$needle = '#' . preg_quote($needle, '#') . '#ui';
817
}
818
} else {
819
$search = '#' . preg_quote($search, '#') . '#ui';
820
}
821
return preg_replace(
822
$search,
823
strtr($replace, array('\\' => '\\\\', '$' => '\\$')),
824
$str
825
);
826
}
827
828
829
/**
830
* Finds the last position (in characters) of the search value in the string - case is ignored when doing performing a match
831
*
832
* @param string $haystack The string to search in
833
* @param string $needle The string to search for. This match will be done in a case-insensitive manner.
834
* @param integer $offset The character position to start searching from. A negative value will stop looking that many characters from the end of the string
835
* @return mixed The integer character position of the last occurence of the needle or `FALSE` if no match
836
*/
837
public static function irpos($haystack, $needle, $offset = 0) {
838
// We get better performance falling back for ASCII strings
839
if ( ! self::detect($haystack)) {
840
return strripos($haystack, $needle, $offset);
841
}
842
843
if (self::$_mbstring_available === NULL) {
844
self::_check_mb_string();
845
}
846
847
if (self::$_mbstring_available && function_exists('mb_strripos')) {
848
return mb_strripos($haystack, $needle, $offset, 'UTF-8');
849
}
850
851
$haystack = self::lower($haystack);
852
$needle = self::lower($needle);
853
854
return self::rpos($haystack, $needle, $offset);
855
}
856
857
858
/**
859
* Matches a string needle in the string haystack, returning a substring from the beginning of the needle to the end of the haystack
860
*
861
* Can optionally return the part of the haystack before the needle. Matching
862
* is done in a case-insensitive manner.
863
*
864
* @param string $haystack The string to search in
865
* @param string $needle The string to search for. This match will be done in a case-insensitive manner.
866
* @param boolean $before_needle If a substring of the haystack before the needle should be returned instead of the substring from the needle to the end of the haystack
867
* @return mixed The specified part of the haystack, or `FALSE` if the needle was not found
868
*/
869
public static function istr($haystack, $needle, $before_needle = FALSE) {
870
// We get better performance falling back for ASCII strings
871
if ($before_needle == FALSE && ! self::detect($haystack)) {
872
return stristr($haystack, $needle);
873
}
874
875
if (self::$_mbstring_available === NULL) {
876
self::_check_mb_string();
877
}
878
879
if (self::$_mbstring_available && function_exists('mb_stristr')) {
880
return mb_stristr($haystack, $needle, $before_needle, 'UTF-8');
881
}
882
883
$lower_haystack = self::lower($haystack);
884
$lower_needle = self::lower($needle);
885
886
$pos = strpos($lower_haystack, $lower_needle);
887
888
if ($before_needle) {
889
return substr($haystack, 0, $pos);
890
}
891
892
return substr($haystack, $pos);
893
}
894
895
896
/**
897
* Determines the length (in actual characters) of a string
898
*
899
* @param string $str The string to measure
900
* @return integer The number of characters/bytes in the string
901
*/
902
public static function len($str) {
903
if (self::$_mbstring_available === NULL) {
904
self::_check_mb_string();
905
}
906
907
if (self::$_mbstring_available) {
908
return mb_strlen($str, 'UTF-8');
909
}
910
911
return strlen(utf8_decode($str));
912
}
913
914
915
/**
916
* Converts all uppercase characters to lowercase
917
*
918
* @param string $str The string to convert
919
* @return string The input string with all uppercase characters in lowercase
920
*/
921
public static function lower($str) {
922
// We get better performance falling back for ASCII strings
923
if ( ! self::detect($str)) {
924
return strtolower($str);
925
}
926
927
if (self::$_mbstring_available === NULL) {
928
self::_check_mb_string();
929
}
930
931
if (self::$_mbstring_available) {
932
$string = mb_strtolower($string, 'utf-8');
933
// For some reason mb_strtolower misses some character
934
return strtr($str, self::$_mb_upper_to_lower_fix);
935
}
936
937
return strtr($str, self::$_upper_to_lower);
938
}
939
940
941
/**
942
* Trims whitespace, or any specified characters, from the beginning of a string
943
*
944
* @param string $str The string to trim
945
* @param string $charlist The characters to trim
946
* @return string The trimmed string
947
*/
948
public static function ltrim($str, $charlist = NULL) {
949
if (strlen($charlist) === 0) {
950
return ltrim($str);
951
}
952
953
$search = preg_quote($charlist, '#');
954
$search = str_replace('-', '\-', $search);
955
$search = str_replace('\.\.', '-', $search);
956
return preg_replace('#^[' . $search . ']+#Du', '', $str);
957
}
958
959
960
/**
961
* Compares strings using a natural order algorithm, with the resulting order having latin characters that are based on ASCII letters placed after the relative ASCII characters
962
*
963
* Please note that this function sorts based on English language sorting
964
* rules only. Locale-sepcific sorting is done by
965
* [http://php.net/strcoll strcoll()], however there are technical
966
* limitations.
967
*
968
* @param string $str1 The first string to compare
969
* @param string $str2 The second string to compare
970
* @return integer `< 0` if `$str1 < $str2`, `0` if they are equal, `> 0` if `$str1 > $str2`
971
*/
972
public static function natcmp($str1, $str2) {
973
$ascii_str1 = strtr($str1, self::$_utf8_to_ascii);
974
$ascii_str2 = strtr($str2, self::$_utf8_to_ascii);
975
976
$res = strnatcmp($ascii_str1, $ascii_str2);
977
978
// If the ASCII representations are the same, sort by the UTF-8 representations
979
if ($res === 0) {
980
$res = strnatcmp($str1, $str2);
981
}
982
983
return $res;
984
}
985
986
987
/**
988
* Converts a UTF-8 character to a unicode code point
989
*
990
* @param string $character The character to decode
991
* @return string The U+hex unicode code point for the character
992
*/
993
public static function ord($character) {
994
$b = array_map('ord', str_split($character));
995
$invalid = FALSE;
996
997
switch (strlen($character)) {
998
case 1:
999
if ($b[0] > 0x7F) {
1000
$invalid = TRUE;
1001
break;
1002
}
1003
$bin = decbin($b[0]);
1004
break;
1005
1006
case 2:
1007
if ($b[0] < 0xC2 || $b[0] > 0xDF ||
1008
$b[1] < 0x80 || $b[1] > 0xBF) {
1009
$invalid = TRUE;
1010
break;
1011
}
1012
$bin = substr(decbin($b[0]), 3) .
1013
substr(decbin($b[1]), 2);
1014
break;
1015
1016
case 3:
1017
if ($b[0] < 0xE0 || $b[0] > 0xEF ||
1018
$b[1] < 0x80 || $b[1] > 0xBF ||
1019
$b[2] < 0x80 || $b[2] > 0xBF) {
1020
$invalid = TRUE;
1021
break;
1022
}
1023
$bin = substr(decbin($b[0]), 4) .
1024
substr(decbin($b[1]), 2) .
1025
substr(decbin($b[2]), 2);
1026
break;
1027
1028
case 4:
1029
if ($b[0] < 0xF0 || $b[0] > 0xF4 ||
1030
$b[1] < 0x80 || $b[1] > 0xBF ||
1031
$b[2] < 0x80 || $b[2] > 0xBF ||
1032
$b[3] < 0x80 || $b[3] > 0xBF) {
1033
$invalid = TRUE;
1034
break;
1035
}
1036
$bin = substr(decbin($b[0]), 5) .
1037
substr(decbin($b[1]), 2) .
1038
substr(decbin($b[2]), 2) .
1039
substr(decbin($b[3]), 2);
1040
break;
1041
1042
default:
1043
$invalid = TRUE;
1044
break;
1045
}
1046
1047
if ($invalid) {
1048
halt('A System Error Was Encountered', 'The UTF-8 character specified is invalid', 'sys_error');
1049
}
1050
1051
$hex = strtoupper(dechex(bindec($bin)));
1052
return 'U+' . str_pad($hex, 4, '0', STR_PAD_LEFT);
1053
}
1054
1055
1056
/**
1057
* Pads a string to the number of characters specified
1058
*
1059
* @param string $str The string to pad
1060
* @param integer $pad_length The character length to pad the string to
1061
* @param string $pad_string The string to pad the source string with
1062
* @param string $pad_type The type of padding to do: `'left'`, `'right'`, `'both'`
1063
* @return string The input string padded to the specified character width
1064
*/
1065
public static function pad($str, $pad_length, $pad_string = ' ', $pad_type = 'right') {
1066
$valid_pad_types = array('right', 'left', 'both');
1067
if ( ! in_array($pad_type, $valid_pad_types)) {
1068
halt('A System Error Was Encountered', "The pad type specified, {$pad_type}, is not valid. Must be one of: ".implode(', ', $valid_pad_types), 'sys_error');
1069
}
1070
1071
// We get better performance falling back for ASCII strings
1072
if ( ! self::detect($str) && ! self::detect($pad_string)) {
1073
static $type_map = array(
1074
'left' => STR_PAD_LEFT,
1075
'right' => STR_PAD_RIGHT,
1076
'both' => STR_PAD_BOTH
1077
);
1078
return str_pad($str, $pad_length, $pad_string, $type_map[$pad_type]);
1079
}
1080
1081
1082
$string_length = self::len($str);
1083
$pad_string_length = self::len($pad_string);
1084
1085
$pad_to_length = $pad_length - $string_length;
1086
1087
if ($pad_to_length < 1) {
1088
return $str;
1089
}
1090
1091
$padded = 0;
1092
$next_side = 'left';
1093
$left_pad_string = '';
1094
$right_pad_string = '';
1095
1096
while ($padded < $pad_to_length) {
1097
1098
// For pad strings over 1 characters long, they may be too long to fit
1099
if ($pad_to_length - $padded < $pad_string_length) {
1100
$pad_string = self::sub($pad_string, 0, $pad_to_length - $padded);
1101
}
1102
1103
switch (($pad_type !== 'both') ? $pad_type : $next_side) {
1104
case 'right':
1105
$right_pad_string .= $pad_string;
1106
$next_side = 'left';
1107
break;
1108
1109
case 'left':
1110
$left_pad_string .= $pad_string;
1111
$next_side = 'right';
1112
break;
1113
}
1114
1115
$padded += $pad_string_length;
1116
}
1117
1118
return $left_pad_string . $str . $right_pad_string;
1119
}
1120
1121
1122
/**
1123
* Finds the first position (in characters) of the search value in the string
1124
*
1125
* @param string $haystack The string to search in
1126
* @param string $needle The string to search for
1127
* @param integer $offset The character position to start searching from
1128
* @return mixed The integer character position of the first occurence of the needle or `FALSE` if no match
1129
*/
1130
public static function pos($haystack, $needle, $offset = 0) {
1131
if (self::$_mbstring_available === NULL) {
1132
self::_check_mb_string();
1133
}
1134
1135
if (self::$_mbstring_available) {
1136
return mb_strpos($haystack, $needle, $offset, 'UTF-8');
1137
}
1138
1139
$offset = self::_convert_offset_to_bytes($haystack, $offset);
1140
1141
$position = strpos($haystack, $needle, $offset);
1142
1143
if ($position === FALSE) {
1144
return FALSE;
1145
}
1146
1147
return strlen(utf8_decode(substr($haystack, 0, $position)));
1148
}
1149
1150
1151
/**
1152
* Replaces matching parts of the string
1153
*
1154
* If `$search` and `$replace` are both arrays and `$replace` is shorter,
1155
* the extra `$search` string will be replaced with an empty string. If
1156
* `$search` is an array and `$replace` is a string, all `$search` values
1157
* will be replaced with the string specified.
1158
*
1159
* @param string $str The string to perform the replacements on
1160
* @param mixed $search The string (or array of strings) to search for - see method description for details
1161
* @param mixed $replace The string (or array of strings) to replace with - see method description for details
1162
* @return string The input string with the specified replacements
1163
*/
1164
public static function replace($str, $search, $replace) {
1165
return str_replace($search, $replace, $str);
1166
}
1167
1168
1169
/**
1170
* Resets the configuration of the class
1171
*
1172
* @internal
1173
*
1174
* @return void
1175
*/
1176
public static function reset() {
1177
self::$_mbstring_available = NULL;
1178
}
1179
1180
1181
/**
1182
* Reverses a string
1183
*
1184
* @param string $str The string to reverse
1185
* @return string The reversed string
1186
*/
1187
public static function rev($str) {
1188
$output = '';
1189
$len = strlen($str);
1190
1191
static $char_lens = array(
1192
0xF0 => 4,
1193
0xE0 => 3,
1194
0xD0 => 2,
1195
0xC0 => 2
1196
);
1197
1198
$mb_char = '';
1199
for ($i = 0; $i < $len; $i++) {
1200
$char = $str[$i];
1201
if (ord($char) < 128) {
1202
$output = $char . $output;
1203
} else {
1204
switch (ord($char) & 0xF0) {
1205
case 0xF0:
1206
$output = $str[$i] . $str[$i+1] . $str[$i+2] . $str[$i+3] . $output;
1207
$i += 3;
1208
break;
1209
1210
case 0xE0:
1211
$output = $str[$i] . $str[$i+1] . $str[$i+2] . $output;
1212
$i += 2;
1213
break;
1214
1215
case 0xD0:
1216
case 0xC0:
1217
$output = $str[$i] . $str[$i+1] . $output;
1218
$i += 1;
1219
break;
1220
}
1221
}
1222
}
1223
1224
return $output;
1225
}
1226
1227
1228
/**
1229
* Finds the last position (in characters) of the search value in the string
1230
*
1231
* @param string $haystack The string to search in
1232
* @param string $needle The string to search for.
1233
* @param integer $offset The character position to start searching from. A negative value will stop looking that many characters from the end of the string
1234
* @return mixed The integer character position of the last occurence of the needle or `FALSE` if no match
1235
*/
1236
public static function rpos($haystack, $needle, $offset = 0) {
1237
// We get better performance falling back for ASCII strings
1238
if ( ! self::detect($haystack)) {
1239
return strrpos($haystack, $needle, $offset);
1240
}
1241
1242
// We don't even both trying mb_strrpos since this method is faster
1243
1244
$offset = self::_convert_offset_to_bytes($haystack, $offset);
1245
1246
$position = strrpos($haystack, $needle, $offset);
1247
1248
if ($position === FALSE) {
1249
return FALSE;
1250
}
1251
1252
return strlen(utf8_decode(substr($haystack, 0, $position)));
1253
}
1254
1255
1256
/**
1257
* Trims whitespace, or any specified characters, from the end of a string
1258
*
1259
* @param string $str The string to trim
1260
* @param string $charlist The characters to trim
1261
* @return string The trimmed string
1262
*/
1263
public static function rtrim($str, $charlist = NULL) {
1264
if (strlen($charlist) === 0) {
1265
return rtrim($str);
1266
}
1267
1268
$search = preg_quote($charlist, '#');
1269
$search = str_replace('-', '\-', $search);
1270
$search = str_replace('\.\.', '-', $search);
1271
return preg_replace('#[' . $search . ']+$#Du', '', $str);
1272
}
1273
1274
1275
/**
1276
* Matches a string needle in the string haystack, returning a substring from the beginning of the needle to the end of the haystack
1277
*
1278
* Can optionally return the part of the haystack before the needle.
1279
*
1280
* @param string $haystack The string to search in
1281
* @param string $needle The string to search for
1282
* @param boolean $before_needle If a substring of the haystack before the needle should be returned instead of the substring from the needle to the end of the haystack
1283
* @return mixed The specified part of the haystack, or `FALSE` if the needle was not found
1284
*/
1285
public static function str($haystack, $needle, $before_needle = FALSE) {
1286
if (self::$_mbstring_available === NULL) {
1287
self::_check_mb_string();
1288
}
1289
1290
if (self::$_mbstring_available && function_exists('mb_strstr')) {
1291
return mb_strstr($haystack, $needle, $before_needle, 'UTF-8');
1292
}
1293
1294
$pos = strpos($haystack, $needle);
1295
1296
if ($pos === FALSE) {
1297
return $pos;
1298
}
1299
1300
if ($before_needle) {
1301
return substr($haystack, 0, $pos);
1302
}
1303
1304
return substr($haystack, $pos);
1305
}
1306
1307
1308
/**
1309
* Extracts part of a string
1310
*
1311
* @param string $str The string to extract from
1312
* @param integer $start The zero-based starting index to extract from. Negative values will start the extraction that many characters from the end of the string.
1313
* @param integer $length The length of the string to extract. If an empty value is provided, the remainder of the string will be returned.
1314
* @return mixed The extracted subtring or `FALSE` if the start is out of bounds
1315
*/
1316
public static function sub($str, $start, $length = NULL) {
1317
if (self::$_mbstring_available === NULL) {
1318
self::_check_mb_string();
1319
}
1320
1321
if (self::$_mbstring_available) {
1322
$str_len = mb_strlen($str, 'UTF-8');
1323
if (abs($start) > $str_len) {
1324
return FALSE;
1325
}
1326
if ($length === NULL) {
1327
if ($start >= 0) {
1328
$length = $str_len-$start;
1329
} else {
1330
$length = abs($start);
1331
}
1332
}
1333
return mb_substr($str, $start, $length, 'UTF-8');
1334
}
1335
1336
// We get better performance falling back for ASCII strings
1337
if ( ! self::detect($str)) {
1338
if ($length === NULL) {
1339
if ($start >= 0) {
1340
$length = strlen($str)-$start;
1341
} else {
1342
$length = abs($start);
1343
}
1344
}
1345
return substr($str, $start, $length);
1346
}
1347
1348
1349
// This is the slowest version
1350
$str_len = strlen(utf8_decode($str));
1351
1352
if (abs($start) > $str_len) {
1353
return FALSE;
1354
}
1355
1356
// Optimize looking by changing to negative start positions if the
1357
// start is in the second half of the string
1358
if ($start > $str_len/2) {
1359
$start = 0-($str_len-$start);
1360
}
1361
1362
// Substrings to the end of the string are pretty simple
1363
$start = self::_convert_offset_to_bytes($str, $start);
1364
$str = substr($str, $start);
1365
1366
if ($length === NULL) {
1367
return $str;
1368
}
1369
1370
$length = self::_convert_offset_to_bytes($str, $length);
1371
return substr($str, 0, $length);
1372
}
1373
1374
1375
/**
1376
* Trims whitespace, or any specified characters, from the beginning and end of a string
1377
*
1378
* @param string $str The string to trim
1379
* @param string $charlist The characters to trim, .. indicates a range
1380
* @return string The trimmed string
1381
*/
1382
public static function trim($str, $charlist = NULL) {
1383
if (strlen($charlist) === 0) {
1384
return trim($str);
1385
}
1386
1387
$search = preg_quote($charlist, '#');
1388
$search = str_replace('-', '\-', $search);
1389
$search = str_replace('\.\.', '-', $search);
1390
return preg_replace('#^[' . $search . ']+|[' . $search . ']+$#Du', '', $str);
1391
}
1392
1393
1394
/**
1395
* Converts the first character of the string to uppercase.
1396
*
1397
* @param string $str The string to process
1398
* @return string The processed string
1399
*/
1400
public static function ucfirst($str) {
1401
return self::upper(self::sub($str, 0, 1)) . self::sub($str, 1);
1402
}
1403
1404
1405
/**
1406
* Converts the first character of every word to uppercase
1407
*
1408
* Words are considered to start at the beginning of the string, or after any
1409
* whitespace character.
1410
*
1411
* @param string $string The string to process
1412
* @return string The processed string
1413
*/
1414
public static function ucwords($string) {
1415
return preg_replace_callback(
1416
'#(?<=^|\s|[\x{2000}-\x{200A}]|/|-|\(|\[|\{|\||"|^\'|\s\'|‘|“)(.)#u',
1417
array('self', '_ucwords_callback'),
1418
$string
1419
);
1420
}
1421
1422
1423
/**
1424
* Handles converting a character to uppercase for ::ucwords()
1425
*
1426
* @param array $match The regex match from ::ucwords()
1427
* @return string The uppercase character
1428
*/
1429
private static function _ucwords_callback($match) {
1430
return self::upper($match[1]);
1431
}
1432
1433
1434
/**
1435
* Converts all lowercase characters to uppercase
1436
*
1437
* @param string $str The string to convert
1438
* @return string The input string with all lowercase characters in uppercase
1439
*/
1440
public static function upper($str) {
1441
// We get better performance falling back for ASCII strings
1442
if ( ! self::detect($str)) {
1443
return strtoupper($str);
1444
}
1445
1446
if (self::$_mbstring_available === NULL) {
1447
self::_check_mb_string();
1448
}
1449
1450
if (self::$_mbstring_available) {
1451
$str = mb_strtoupper($str, 'utf-8');
1452
// For some reason mb_strtoupper misses some character
1453
return strtr($str, self::$_mb_lower_to_upper_fix);
1454
}
1455
1456
return strtr($str, self::$_lower_to_upper);
1457
}
1458
1459
1460
/**
1461
* Wraps a string to a specific character width
1462
*
1463
* @param string $str The string to wrap
1464
* @param integer $width The character width to wrap to
1465
* @param string $break The string to insert as a break
1466
* @param boolean $cut If words longer than the character width should be split to fit
1467
* @return string The input string with all lowercase characters in uppercase
1468
*/
1469
public static function wordwrap($str, $width = 75, $break = "\n", $cut = FALSE) {
1470
// We get better performance falling back for ASCII strings
1471
if ( ! self::detect($str)) {
1472
return wordwrap($str, $width, $break, $cut);
1473
}
1474
1475
$words = preg_split('#(?<=\s|[\x{2000}-\x{200A}])#ue', $str);
1476
1477
$output = '';
1478
1479
$line_len = 0;
1480
foreach ($words as $word) {
1481
$word_len = self::len($word);
1482
1483
// Shorten up words that are too long
1484
while ($cut && $word_len > $width) {
1485
$output .= $break;
1486
$output .= self::sub($word, 0, $width);
1487
$line_len = $width;
1488
$word = self::sub($word, $width);
1489
$word_len = self::len($word);
1490
}
1491
1492
if ($line_len && $line_len + $word_len > $width) {
1493
$output .= $break;
1494
$line_len = 0;
1495
}
1496
$output .= $word;
1497
$line_len += $word_len;
1498
}
1499
1500
return $output;
1501
}
1502
1503
}
1504
1505
// End of file: ./system/core/utf8.php
Page URI: http://www.infopotato.com/index.php/code/core/utf8/