1
|
|
|
<?php |
2
|
|
|
|
3
|
|
|
declare(strict_types = 1); |
4
|
|
|
|
5
|
|
|
namespace DummyGenerator\Core\Transliterator; |
6
|
|
|
|
7
|
|
|
use DummyGenerator\Definitions\Transliterator\TransliteratorInterface; |
8
|
|
|
|
9
|
|
|
class SimpleTransliterator implements TransliteratorInterface |
10
|
|
|
{ |
11
|
|
|
/** @var array<string, string> */ |
12
|
|
|
protected array $transliterationTable = [ |
13
|
|
|
'IJ' => 'I', 'Ö' => 'O', 'Œ' => 'O', 'Ü' => 'U', 'ä' => 'a', 'æ' => 'a', |
14
|
|
|
'ij' => 'i', 'ö' => 'o', 'œ' => 'o', 'ü' => 'u', 'ß' => 's', 'ſ' => 's', |
15
|
|
|
'À' => 'A', 'Á' => 'A', 'Â' => 'A', 'Ã' => 'A', 'Ä' => 'A', 'Å' => 'A', |
16
|
|
|
'Æ' => 'A', 'Ā' => 'A', 'Ą' => 'A', 'Ă' => 'A', 'Ç' => 'C', 'Ć' => 'C', |
17
|
|
|
'Č' => 'C', 'Ĉ' => 'C', 'Ċ' => 'C', 'Ď' => 'D', 'Đ' => 'D', 'È' => 'E', |
18
|
|
|
'É' => 'E', 'Ê' => 'E', 'Ë' => 'E', 'Ē' => 'E', 'Ę' => 'E', 'Ě' => 'E', |
19
|
|
|
'Ĕ' => 'E', 'Ė' => 'E', 'Ĝ' => 'G', 'Ğ' => 'G', 'Ġ' => 'G', 'Ģ' => 'G', |
20
|
|
|
'Ĥ' => 'H', 'Ħ' => 'H', 'Ì' => 'I', 'Í' => 'I', 'Î' => 'I', 'Ï' => 'I', |
21
|
|
|
'Ī' => 'I', 'Ĩ' => 'I', 'Ĭ' => 'I', 'Į' => 'I', 'İ' => 'I', 'Ĵ' => 'J', |
22
|
|
|
'Ķ' => 'K', 'Ľ' => 'K', 'Ĺ' => 'K', 'Ļ' => 'K', 'Ŀ' => 'K', 'Ł' => 'L', |
23
|
|
|
'Ñ' => 'N', 'Ń' => 'N', 'Ň' => 'N', 'Ņ' => 'N', 'Ŋ' => 'N', 'Ò' => 'O', |
24
|
|
|
'Ó' => 'O', 'Ô' => 'O', 'Õ' => 'O', 'Ø' => 'O', 'Ō' => 'O', 'Ő' => 'O', |
25
|
|
|
'Ŏ' => 'O', 'Ŕ' => 'R', 'Ř' => 'R', 'Ŗ' => 'R', 'Ś' => 'S', 'Ş' => 'S', |
26
|
|
|
'Ŝ' => 'S', 'Ș' => 'S', 'Š' => 'S', 'Ť' => 'T', 'Ţ' => 'T', 'Ŧ' => 'T', |
27
|
|
|
'Ț' => 'T', 'Ù' => 'U', 'Ú' => 'U', 'Û' => 'U', 'Ū' => 'U', 'Ů' => 'U', |
28
|
|
|
'Ű' => 'U', 'Ŭ' => 'U', 'Ũ' => 'U', 'Ų' => 'U', 'Ŵ' => 'W', 'Ŷ' => 'Y', |
29
|
|
|
'Ÿ' => 'Y', 'Ý' => 'Y', 'Ź' => 'Z', 'Ż' => 'Z', 'Ž' => 'Z', 'à' => 'a', |
30
|
|
|
'á' => 'a', 'â' => 'a', 'ã' => 'a', 'ā' => 'a', 'ą' => 'a', 'ă' => 'a', |
31
|
|
|
'å' => 'a', 'ç' => 'c', 'ć' => 'c', 'č' => 'c', 'ĉ' => 'c', 'ċ' => 'c', |
32
|
|
|
'ď' => 'd', 'đ' => 'd', 'è' => 'e', 'é' => 'e', 'ê' => 'e', 'ë' => 'e', |
33
|
|
|
'ē' => 'e', 'ę' => 'e', 'ě' => 'e', 'ĕ' => 'e', 'ė' => 'e', 'ƒ' => 'f', |
34
|
|
|
'ĝ' => 'g', 'ğ' => 'g', 'ġ' => 'g', 'ģ' => 'g', 'ĥ' => 'h', 'ħ' => 'h', |
35
|
|
|
'ì' => 'i', 'í' => 'i', 'î' => 'i', 'ï' => 'i', 'ī' => 'i', 'ĩ' => 'i', |
36
|
|
|
'ĭ' => 'i', 'į' => 'i', 'ı' => 'i', 'ĵ' => 'j', 'ķ' => 'k', 'ĸ' => 'k', |
37
|
|
|
'ł' => 'l', 'ľ' => 'l', 'ĺ' => 'l', 'ļ' => 'l', 'ŀ' => 'l', 'ñ' => 'n', |
38
|
|
|
'ń' => 'n', 'ň' => 'n', 'ņ' => 'n', 'ʼn' => 'n', 'ŋ' => 'n', 'ò' => 'o', |
39
|
|
|
'ó' => 'o', 'ô' => 'o', 'õ' => 'o', 'ø' => 'o', 'ō' => 'o', 'ő' => 'o', |
40
|
|
|
'ŏ' => 'o', 'ŕ' => 'r', 'ř' => 'r', 'ŗ' => 'r', 'ś' => 's', 'š' => 's', |
41
|
|
|
'ť' => 't', 'ù' => 'u', 'ú' => 'u', 'û' => 'u', 'ū' => 'u', 'ů' => 'u', |
42
|
|
|
'ű' => 'u', 'ŭ' => 'u', 'ũ' => 'u', 'ų' => 'u', 'ŵ' => 'w', 'ÿ' => 'y', |
43
|
|
|
'ý' => 'y', 'ŷ' => 'y', 'ż' => 'z', 'ź' => 'z', 'ž' => 'z', 'Α' => 'A', |
44
|
|
|
'Ά' => 'A', 'Ἀ' => 'A', 'Ἁ' => 'A', 'Ἂ' => 'A', 'Ἃ' => 'A', 'Ἄ' => 'A', |
45
|
|
|
'Ἅ' => 'A', 'Ἆ' => 'A', 'Ἇ' => 'A', 'ᾈ' => 'A', 'ᾉ' => 'A', 'ᾊ' => 'A', |
46
|
|
|
'ᾋ' => 'A', 'ᾌ' => 'A', 'ᾍ' => 'A', 'ᾎ' => 'A', 'ᾏ' => 'A', 'Ᾰ' => 'A', |
47
|
|
|
'Ᾱ' => 'A', 'Ὰ' => 'A', 'ᾼ' => 'A', 'Β' => 'B', 'Γ' => 'G', 'Δ' => 'D', |
48
|
|
|
'Ε' => 'E', 'Έ' => 'E', 'Ἐ' => 'E', 'Ἑ' => 'E', 'Ἒ' => 'E', 'Ἓ' => 'E', |
49
|
|
|
'Ἔ' => 'E', 'Ἕ' => 'E', 'Ὲ' => 'E', 'Ζ' => 'Z', 'Η' => 'I', 'Ή' => 'I', |
50
|
|
|
'Ἠ' => 'I', 'Ἡ' => 'I', 'Ἢ' => 'I', 'Ἣ' => 'I', 'Ἤ' => 'I', 'Ἥ' => 'I', |
51
|
|
|
'Ἦ' => 'I', 'Ἧ' => 'I', 'ᾘ' => 'I', 'ᾙ' => 'I', 'ᾚ' => 'I', 'ᾛ' => 'I', |
52
|
|
|
'ᾜ' => 'I', 'ᾝ' => 'I', 'ᾞ' => 'I', 'ᾟ' => 'I', 'Ὴ' => 'I', 'ῌ' => 'I', |
53
|
|
|
'Θ' => 'T', 'Ι' => 'I', 'Ί' => 'I', 'Ϊ' => 'I', 'Ἰ' => 'I', 'Ἱ' => 'I', |
54
|
|
|
'Ἲ' => 'I', 'Ἳ' => 'I', 'Ἴ' => 'I', 'Ἵ' => 'I', 'Ἶ' => 'I', 'Ἷ' => 'I', |
55
|
|
|
'Ῐ' => 'I', 'Ῑ' => 'I', 'Ὶ' => 'I', 'Κ' => 'K', 'Λ' => 'L', 'Μ' => 'M', |
56
|
|
|
'Ν' => 'N', 'Ξ' => 'K', 'Ο' => 'O', 'Ό' => 'O', 'Ὀ' => 'O', 'Ὁ' => 'O', |
57
|
|
|
'Ὂ' => 'O', 'Ὃ' => 'O', 'Ὄ' => 'O', 'Ὅ' => 'O', 'Ὸ' => 'O', 'Π' => 'P', |
58
|
|
|
'Ρ' => 'R', 'Ῥ' => 'R', 'Σ' => 'S', 'Τ' => 'T', 'Υ' => 'Y', 'Ύ' => 'Y', |
59
|
|
|
'Ϋ' => 'Y', 'Ὑ' => 'Y', 'Ὓ' => 'Y', 'Ὕ' => 'Y', 'Ὗ' => 'Y', 'Ῠ' => 'Y', |
60
|
|
|
'Ῡ' => 'Y', 'Ὺ' => 'Y', 'Φ' => 'F', 'Χ' => 'X', 'Ψ' => 'P', 'Ω' => 'O', |
61
|
|
|
'Ώ' => 'O', 'Ὠ' => 'O', 'Ὡ' => 'O', 'Ὢ' => 'O', 'Ὣ' => 'O', 'Ὤ' => 'O', |
62
|
|
|
'Ὥ' => 'O', 'Ὦ' => 'O', 'Ὧ' => 'O', 'ᾨ' => 'O', 'ᾩ' => 'O', 'ᾪ' => 'O', |
63
|
|
|
'ᾫ' => 'O', 'ᾬ' => 'O', 'ᾭ' => 'O', 'ᾮ' => 'O', 'ᾯ' => 'O', 'Ὼ' => 'O', |
64
|
|
|
'ῼ' => 'O', 'α' => 'a', 'ά' => 'a', 'ἀ' => 'a', 'ἁ' => 'a', 'ἂ' => 'a', |
65
|
|
|
'ἃ' => 'a', 'ἄ' => 'a', 'ἅ' => 'a', 'ἆ' => 'a', 'ἇ' => 'a', 'ᾀ' => 'a', |
66
|
|
|
'ᾁ' => 'a', 'ᾂ' => 'a', 'ᾃ' => 'a', 'ᾄ' => 'a', 'ᾅ' => 'a', 'ᾆ' => 'a', |
67
|
|
|
'ᾇ' => 'a', 'ὰ' => 'a', 'ᾰ' => 'a', 'ᾱ' => 'a', 'ᾲ' => 'a', 'ᾳ' => 'a', |
68
|
|
|
'ᾴ' => 'a', 'ᾶ' => 'a', 'ᾷ' => 'a', 'β' => 'b', 'γ' => 'g', 'δ' => 'd', |
69
|
|
|
'ε' => 'e', 'έ' => 'e', 'ἐ' => 'e', 'ἑ' => 'e', 'ἒ' => 'e', 'ἓ' => 'e', |
70
|
|
|
'ἔ' => 'e', 'ἕ' => 'e', 'ὲ' => 'e', 'ζ' => 'z', 'η' => 'i', 'ή' => 'i', |
71
|
|
|
'ἠ' => 'i', 'ἡ' => 'i', 'ἢ' => 'i', 'ἣ' => 'i', 'ἤ' => 'i', 'ἥ' => 'i', |
72
|
|
|
'ἦ' => 'i', 'ἧ' => 'i', 'ᾐ' => 'i', 'ᾑ' => 'i', 'ᾒ' => 'i', 'ᾓ' => 'i', |
73
|
|
|
'ᾔ' => 'i', 'ᾕ' => 'i', 'ᾖ' => 'i', 'ᾗ' => 'i', 'ὴ' => 'i', 'ῂ' => 'i', |
74
|
|
|
'ῃ' => 'i', 'ῄ' => 'i', 'ῆ' => 'i', 'ῇ' => 'i', 'θ' => 't', 'ι' => 'i', |
75
|
|
|
'ί' => 'i', 'ϊ' => 'i', 'ΐ' => 'i', 'ἰ' => 'i', 'ἱ' => 'i', 'ἲ' => 'i', |
76
|
|
|
'ἳ' => 'i', 'ἴ' => 'i', 'ἵ' => 'i', 'ἶ' => 'i', 'ἷ' => 'i', 'ὶ' => 'i', |
77
|
|
|
'ῐ' => 'i', 'ῑ' => 'i', 'ῒ' => 'i', 'ῖ' => 'i', 'ῗ' => 'i', 'κ' => 'k', |
78
|
|
|
'λ' => 'l', 'μ' => 'm', 'ν' => 'n', 'ξ' => 'k', 'ο' => 'o', 'ό' => 'o', |
79
|
|
|
'ὀ' => 'o', 'ὁ' => 'o', 'ὂ' => 'o', 'ὃ' => 'o', 'ὄ' => 'o', 'ὅ' => 'o', |
80
|
|
|
'ὸ' => 'o', 'π' => 'p', 'ρ' => 'r', 'ῤ' => 'r', 'ῥ' => 'r', 'σ' => 's', |
81
|
|
|
'ς' => 's', 'τ' => 't', 'υ' => 'y', 'ύ' => 'y', 'ϋ' => 'y', 'ΰ' => 'y', |
82
|
|
|
'ὐ' => 'y', 'ὑ' => 'y', 'ὒ' => 'y', 'ὓ' => 'y', 'ὔ' => 'y', 'ὕ' => 'y', |
83
|
|
|
'ὖ' => 'y', 'ὗ' => 'y', 'ὺ' => 'y', 'ῠ' => 'y', 'ῡ' => 'y', 'ῢ' => 'y', |
84
|
|
|
'ῦ' => 'y', 'ῧ' => 'y', 'φ' => 'f', 'χ' => 'x', 'ψ' => 'p', 'ω' => 'o', |
85
|
|
|
'ώ' => 'o', 'ὠ' => 'o', 'ὡ' => 'o', 'ὢ' => 'o', 'ὣ' => 'o', 'ὤ' => 'o', |
86
|
|
|
'ὥ' => 'o', 'ὦ' => 'o', 'ὧ' => 'o', 'ᾠ' => 'o', 'ᾡ' => 'o', 'ᾢ' => 'o', |
87
|
|
|
'ᾣ' => 'o', 'ᾤ' => 'o', 'ᾥ' => 'o', 'ᾦ' => 'o', 'ᾧ' => 'o', 'ὼ' => 'o', |
88
|
|
|
'ῲ' => 'o', 'ῳ' => 'o', 'ῴ' => 'o', 'ῶ' => 'o', 'ῷ' => 'o', 'А' => 'A', |
89
|
|
|
'Б' => 'B', 'В' => 'V', 'Г' => 'G', 'Д' => 'D', 'Е' => 'E', 'Ё' => 'E', |
90
|
|
|
'Ж' => 'Z', 'З' => 'Z', 'И' => 'I', 'Й' => 'I', 'К' => 'K', 'Л' => 'L', |
91
|
|
|
'М' => 'M', 'Н' => 'N', 'О' => 'O', 'П' => 'P', 'Р' => 'R', 'С' => 'S', |
92
|
|
|
'Т' => 'T', 'У' => 'U', 'Ф' => 'F', 'Х' => 'K', 'Ц' => 'T', 'Ч' => 'C', |
93
|
|
|
'Ш' => 'S', 'Щ' => 'S', 'Ы' => 'Y', 'Э' => 'E', 'Ю' => 'Y', 'Я' => 'Y', |
94
|
|
|
'а' => 'A', 'б' => 'B', 'в' => 'V', 'г' => 'G', 'д' => 'D', 'е' => 'E', |
95
|
|
|
'ё' => 'E', 'ж' => 'Z', 'з' => 'Z', 'и' => 'I', 'й' => 'I', 'к' => 'K', |
96
|
|
|
'л' => 'L', 'м' => 'M', 'н' => 'N', 'о' => 'O', 'п' => 'P', 'р' => 'R', |
97
|
|
|
'с' => 'S', 'т' => 'T', 'у' => 'U', 'ф' => 'F', 'х' => 'K', 'ц' => 'T', |
98
|
|
|
'ч' => 'C', 'ш' => 'S', 'щ' => 'S', 'ы' => 'Y', 'э' => 'E', 'ю' => 'Y', |
99
|
|
|
'я' => 'Y', 'ð' => 'd', 'Ð' => 'D', 'þ' => 't', 'Þ' => 'T', 'ა' => 'a', |
100
|
|
|
'ბ' => 'b', 'გ' => 'g', 'დ' => 'd', 'ე' => 'e', 'ვ' => 'v', 'ზ' => 'z', |
101
|
|
|
'თ' => 't', 'ი' => 'i', 'კ' => 'k', 'ლ' => 'l', 'მ' => 'm', 'ნ' => 'n', |
102
|
|
|
'ო' => 'o', 'პ' => 'p', 'ჟ' => 'z', 'რ' => 'r', 'ს' => 's', 'ტ' => 't', |
103
|
|
|
'უ' => 'u', 'ფ' => 'p', 'ქ' => 'k', 'ღ' => 'g', 'ყ' => 'q', 'შ' => 's', |
104
|
|
|
'ჩ' => 'c', 'ც' => 't', 'ძ' => 'd', 'წ' => 't', 'ჭ' => 'c', 'ხ' => 'k', |
105
|
|
|
'ჯ' => 'j', 'ჰ' => 'h', 'ţ' => 't', 'ʼ' => "'", '̧' => '', 'ḩ' => 'h', |
106
|
|
|
'‘' => "'", '’' => "'", 'ừ' => 'u', '/' => '', 'ế' => 'e', 'ả' => 'a', |
107
|
|
|
'ị' => 'i', 'ậ' => 'a', 'ệ' => 'e', 'ỉ' => 'i', 'ồ' => 'o', 'ề' => 'e', |
108
|
|
|
'ơ' => 'o', 'ạ' => 'a', 'ẵ' => 'a', 'ư' => 'u', 'ằ' => 'a', 'ầ' => 'a', |
109
|
|
|
'ḑ' => 'd', 'Ḩ' => 'H', 'Ḑ' => 'D', 'ș' => 's', 'ț' => 't', 'ộ' => 'o', |
110
|
|
|
'ắ' => 'a', 'ş' => 's', "'" => '', 'ու' => 'u', 'ա' => 'a', 'բ' => 'b', |
111
|
|
|
'գ' => 'g', 'դ' => 'd', 'ե' => 'e', 'զ' => 'z', 'է' => 'e', 'ը' => 'y', |
112
|
|
|
'թ' => 't', 'ժ' => 'zh', 'ի' => 'i', 'լ' => 'l', 'խ' => 'kh', 'ծ' => 'ts', |
113
|
|
|
'կ' => 'k', 'հ' => 'h', 'ձ' => 'dz', 'ղ' => 'gh', 'ճ' => 'ch', 'մ' => 'm', |
114
|
|
|
'յ' => 'y', 'ն' => 'n', 'շ' => 'sh', 'ո' => 'o', 'չ' => 'ch', 'պ' => 'p', |
115
|
|
|
'ջ' => 'j', 'ռ' => 'r', 'ս' => 's', 'վ' => 'v', 'տ' => 't', 'ր' => 'r', |
116
|
|
|
'ց' => 'ts', 'փ' => 'p', 'ք' => 'q', 'և' => 'ev', 'օ' => 'o', 'ֆ' => 'f', |
117
|
|
|
]; |
118
|
|
|
|
119
|
1 |
|
public function transliterate(string $string): string |
120
|
|
|
{ |
121
|
1 |
|
if (0 === preg_match('/[^A-Za-z0-9_.]/', $string)) { |
122
|
|
|
return $string; |
123
|
|
|
} |
124
|
|
|
|
125
|
1 |
|
$transString = $this->toAscii($string); |
126
|
|
|
|
127
|
1 |
|
$transliterated = preg_replace('/[^A-Za-z0-9_.]/u', '', $transString); |
128
|
|
|
|
129
|
1 |
|
return (!empty($transliterated)) ? $transliterated : ''; |
130
|
|
|
} |
131
|
|
|
|
132
|
1 |
|
protected function toAscii(string $string): string |
133
|
|
|
{ |
134
|
1 |
|
$arrayFrom = array_keys($this->transliterationTable); |
135
|
1 |
|
$arrayTo = array_values($this->transliterationTable); |
136
|
|
|
|
137
|
1 |
|
return str_replace($arrayFrom, $arrayTo, $string); |
138
|
|
|
} |
139
|
|
|
} |
140
|
|
|
|