mirror of
https://github.com/danpros/htmly.git
synced 2026-04-22 05:26:22 +05:30
Composer Update
This commit is contained in:
danpros
parent
71418faf1b
commit
6163b18bf5
404 changed files with 35954 additions and 1177 deletions
829
system/vendor/jbroadway/urlify/URLify.php
vendored
829
system/vendor/jbroadway/urlify/URLify.php
vendored
|
|
@ -1,300 +1,591 @@
|
|||
<?php
|
||||
|
||||
/**
|
||||
* A PHP port of URLify.js from the Django project
|
||||
* (https://github.com/django/django/blob/master/django/contrib/admin/static/admin/js/urlify.js).
|
||||
* Handles symbols from Latin languages, Greek, Turkish, Bulgarian, Russian,
|
||||
* Ukrainian, Czech, Polish, Romanian, Latvian, Lithuanian, Vietnamese, Arabic,
|
||||
* Serbian, Azerbaijani, Kazakh and Slovak. Symbols it cannot transliterate
|
||||
* it will simply omit.
|
||||
* A fast PHP slug generator and transliteration library, started as a PHP port of URLify.js
|
||||
* from the Django project + fallback via "Portable ASCII".
|
||||
*
|
||||
* Usage:
|
||||
* - https://github.com/django/django/blob/master/django/contrib/admin/static/admin/js/urlify.js
|
||||
* - https://github.com/voku/portable-ascii
|
||||
*
|
||||
* echo URLify::filter (' J\'étudie le français ');
|
||||
* // "jetudie-le-francais"
|
||||
*
|
||||
* echo URLify::filter ('Lo siento, no hablo español.');
|
||||
* // "lo-siento-no-hablo-espanol"
|
||||
* Handles symbols from latin languages, Arabic, Azerbaijani, Bulgarian, Burmese, Croatian, Czech, Danish, Esperanto,
|
||||
* Estonian, Finnish, French, Switzerland (French), Austrian (French), Georgian, German, Switzerland (German),
|
||||
* Austrian (German), Greek, Hindi, Kazakh, Latvian, Lithuanian, Norwegian, Persian, Polish, Romanian, Russian, Swedish,
|
||||
* Serbian, Slovak, Turkish, Ukrainian and Vietnamese ... and many other via "ASCII::to_transliterate()".
|
||||
*/
|
||||
class URLify
|
||||
{
|
||||
public static $maps = array (
|
||||
'de' => array ( /* German */
|
||||
'Ä' => 'Ae', 'Ö' => 'Oe', 'Ü' => 'Ue', 'ä' => 'ae', 'ö' => 'oe', 'ü' => 'ue', 'ß' => 'ss',
|
||||
'ẞ' => 'SS'
|
||||
),
|
||||
'latin' => array (
|
||||
'À' => 'A', 'Á' => 'A', 'Â' => 'A', 'Ã' => 'A', 'Ä' => 'A', 'Å' => 'A','Ă' => 'A', 'Æ' => 'AE', 'Ç' =>
|
||||
'C', 'È' => 'E', 'É' => 'E', 'Ê' => 'E', 'Ë' => 'E', 'Ì' => 'I', 'Í' => 'I', 'Î' => 'I',
|
||||
'Ï' => 'I', 'Ð' => 'D', 'Ñ' => 'N', 'Ò' => 'O', 'Ó' => 'O', 'Ô' => 'O', 'Õ' => 'O', 'Ö' =>
|
||||
'O', 'Ő' => 'O', 'Ø' => 'O', 'Œ' => 'OE' ,'Ș' => 'S','Ț' => 'T', 'Ù' => 'U', 'Ú' => 'U', 'Û' => 'U', 'Ü' => 'U', 'Ű' => 'U',
|
||||
'Ý' => 'Y', 'Þ' => 'TH', 'ß' => 'ss', 'à' => 'a', 'á' => 'a', 'â' => 'a', 'ã' => 'a', 'ä' =>
|
||||
'a', 'å' => 'a', 'ă' => 'a', 'æ' => 'ae', 'ç' => 'c', 'è' => 'e', 'é' => 'e', 'ê' => 'e', 'ë' => 'e',
|
||||
'ì' => 'i', 'í' => 'i', 'î' => 'i', 'ï' => 'i', 'ð' => 'd', 'ñ' => 'n', 'ò' => 'o', 'ó' =>
|
||||
'o', 'ô' => 'o', 'õ' => 'o', 'ö' => 'o', 'ő' => 'o', 'ø' => 'o', 'œ' => 'oe', 'ș' => 's', 'ț' => 't', 'ù' => 'u', 'ú' => 'u',
|
||||
'û' => 'u', 'ü' => 'u', 'ű' => 'u', 'ý' => 'y', 'þ' => 'th', 'ÿ' => 'y'
|
||||
),
|
||||
'latin_symbols' => array (
|
||||
'©' => '(c)'
|
||||
),
|
||||
'el' => array ( /* Greek */
|
||||
'α' => 'a', 'β' => 'b', 'γ' => 'g', 'δ' => 'd', 'ε' => 'e', 'ζ' => 'z', 'η' => 'h', 'θ' => '8',
|
||||
'ι' => 'i', 'κ' => 'k', 'λ' => 'l', 'μ' => 'm', 'ν' => 'n', 'ξ' => '3', 'ο' => 'o', 'π' => 'p',
|
||||
'ρ' => 'r', 'σ' => 's', 'τ' => 't', 'υ' => 'y', 'φ' => 'f', 'χ' => 'x', 'ψ' => 'ps', 'ω' => 'w',
|
||||
'ά' => 'a', 'έ' => 'e', 'ί' => 'i', 'ό' => 'o', 'ύ' => 'y', 'ή' => 'h', 'ώ' => 'w', 'ς' => 's',
|
||||
'ϊ' => 'i', 'ΰ' => 'y', 'ϋ' => 'y', 'ΐ' => 'i',
|
||||
'Α' => 'A', 'Β' => 'B', 'Γ' => 'G', 'Δ' => 'D', 'Ε' => 'E', 'Ζ' => 'Z', 'Η' => 'H', 'Θ' => '8',
|
||||
'Ι' => 'I', 'Κ' => 'K', 'Λ' => 'L', 'Μ' => 'M', 'Ν' => 'N', 'Ξ' => '3', 'Ο' => 'O', 'Π' => 'P',
|
||||
'Ρ' => 'R', 'Σ' => 'S', 'Τ' => 'T', 'Υ' => 'Y', 'Φ' => 'F', 'Χ' => 'X', 'Ψ' => 'PS', 'Ω' => 'W',
|
||||
'Ά' => 'A', 'Έ' => 'E', 'Ί' => 'I', 'Ό' => 'O', 'Ύ' => 'Y', 'Ή' => 'H', 'Ώ' => 'W', 'Ϊ' => 'I',
|
||||
'Ϋ' => 'Y'
|
||||
),
|
||||
'tr' => array ( /* Turkish */
|
||||
'ş' => 's', 'Ş' => 'S', 'ı' => 'i', 'İ' => 'I', 'ç' => 'c', 'Ç' => 'C', 'ü' => 'u', 'Ü' => 'U',
|
||||
'ö' => 'o', 'Ö' => 'O', 'ğ' => 'g', 'Ğ' => 'G'
|
||||
),
|
||||
'bg' => array( /* Bulgarian */
|
||||
'Щ' => 'Sht', 'Ш' => 'Sh', 'Ч' => 'Ch', 'Ц' => 'C', 'Ю' => 'Yu', 'Я' => 'Ya',
|
||||
'Ж' => 'J', 'А' => 'A', 'Б' => 'B', 'В' => 'V', 'Г' => 'G', 'Д' => 'D',
|
||||
'Е' => 'E', 'З' => 'Z', 'И' => 'I', 'Й' => 'Y', 'К' => 'K', 'Л' => 'L',
|
||||
'М' => 'M', 'Н' => 'N', 'О' => 'O', 'П' => 'P', 'Р' => 'R', 'С' => 'S',
|
||||
'Т' => 'T', 'У' => 'U', 'Ф' => 'F', 'Х' => 'H', 'Ь' => '', 'Ъ' => 'A',
|
||||
'щ' => 'sht', 'ш' => 'sh', 'ч' => 'ch', 'ц' => 'c', 'ю' => 'yu', 'я' => 'ya',
|
||||
'ж' => 'j', 'а' => 'a', 'б' => 'b', 'в' => 'v', 'г' => 'g', 'д' => 'd',
|
||||
'е' => 'e', 'з' => 'z', 'и' => 'i', 'й' => 'y', 'к' => 'k', 'л' => 'l',
|
||||
'м' => 'm', 'н' => 'n', 'о' => 'o', 'п' => 'p', 'р' => 'r', 'с' => 's',
|
||||
'т' => 't', 'у' => 'u', 'ф' => 'f', 'х' => 'h', 'ь' => '', 'ъ' => 'a'
|
||||
),
|
||||
'ru' => array ( /* Russian */
|
||||
'а' => 'a', 'б' => 'b', 'в' => 'v', 'г' => 'g', 'д' => 'd', 'е' => 'e', 'ё' => 'yo', 'ж' => 'zh',
|
||||
'з' => 'z', 'и' => 'i', 'й' => 'i', 'к' => 'k', 'л' => 'l', 'м' => 'm', 'н' => 'n', 'о' => 'o',
|
||||
'п' => 'p', 'р' => 'r', 'с' => 's', 'т' => 't', 'у' => 'u', 'ф' => 'f', 'х' => 'h', 'ц' => 'c',
|
||||
'ч' => 'ch', 'ш' => 'sh', 'щ' => 'sh', 'ъ' => '', 'ы' => 'y', 'ь' => '', 'э' => 'e', 'ю' => 'yu',
|
||||
'я' => 'ya',
|
||||
'А' => 'A', 'Б' => 'B', 'В' => 'V', 'Г' => 'G', 'Д' => 'D', 'Е' => 'E', 'Ё' => 'Yo', 'Ж' => 'Zh',
|
||||
'З' => 'Z', 'И' => 'I', 'Й' => 'I', 'К' => 'K', 'Л' => 'L', 'М' => 'M', 'Н' => 'N', 'О' => 'O',
|
||||
'П' => 'P', 'Р' => 'R', 'С' => 'S', 'Т' => 'T', 'У' => 'U', 'Ф' => 'F', 'Х' => 'H', 'Ц' => 'C',
|
||||
'Ч' => 'Ch', 'Ш' => 'Sh', 'Щ' => 'Sh', 'Ъ' => '', 'Ы' => 'Y', 'Ь' => '', 'Э' => 'E', 'Ю' => 'Yu',
|
||||
'Я' => 'Ya',
|
||||
'№' => ''
|
||||
),
|
||||
'uk' => array ( /* Ukrainian */
|
||||
'Є' => 'Ye', 'І' => 'I', 'Ї' => 'Yi', 'Ґ' => 'G', 'є' => 'ye', 'і' => 'i', 'ї' => 'yi', 'ґ' => 'g'
|
||||
),
|
||||
'kk' => array ( /* Kazakh */
|
||||
'Ә' => 'A', 'Ғ' => 'G', 'Қ' => 'Q', 'Ң' => 'N', 'Ө' => 'O', 'Ұ' => 'U', 'Ү' => 'U', 'Һ' => 'H',
|
||||
'ә' => 'a', 'ғ' => 'g', 'қ' => 'q', 'ң' => 'n', 'ө' => 'o', 'ұ' => 'u', 'ү' => 'u', 'һ' => 'h',
|
||||
),
|
||||
'cs' => array ( /* Czech */
|
||||
'č' => 'c', 'ď' => 'd', 'ě' => 'e', 'ň' => 'n', 'ř' => 'r', 'š' => 's', 'ť' => 't', 'ů' => 'u',
|
||||
'ž' => 'z', 'Č' => 'C', 'Ď' => 'D', 'Ě' => 'E', 'Ň' => 'N', 'Ř' => 'R', 'Š' => 'S', 'Ť' => 'T',
|
||||
'Ů' => 'U', 'Ž' => 'Z'
|
||||
),
|
||||
'pl' => array ( /* Polish */
|
||||
'ą' => 'a', 'ć' => 'c', 'ę' => 'e', 'ł' => 'l', 'ń' => 'n', 'ó' => 'o', 'ś' => 's', 'ź' => 'z',
|
||||
'ż' => 'z', 'Ą' => 'A', 'Ć' => 'C', 'Ę' => 'e', 'Ł' => 'L', 'Ń' => 'N', 'Ó' => 'O', 'Ś' => 'S',
|
||||
'Ź' => 'Z', 'Ż' => 'Z'
|
||||
),
|
||||
'ro' => array ( /* Romanian */
|
||||
'ă' => 'a', 'â' => 'a', 'î' => 'i', 'ș' => 's', 'ț' => 't', 'Ţ' => 'T', 'ţ' => 't'
|
||||
),
|
||||
'lv' => array ( /* Latvian */
|
||||
'ā' => 'a', 'č' => 'c', 'ē' => 'e', 'ģ' => 'g', 'ī' => 'i', 'ķ' => 'k', 'ļ' => 'l', 'ņ' => 'n',
|
||||
'š' => 's', 'ū' => 'u', 'ž' => 'z', 'Ā' => 'A', 'Č' => 'C', 'Ē' => 'E', 'Ģ' => 'G', 'Ī' => 'i',
|
||||
'Ķ' => 'k', 'Ļ' => 'L', 'Ņ' => 'N', 'Š' => 'S', 'Ū' => 'u', 'Ž' => 'Z'
|
||||
),
|
||||
'lt' => array ( /* Lithuanian */
|
||||
'ą' => 'a', 'č' => 'c', 'ę' => 'e', 'ė' => 'e', 'į' => 'i', 'š' => 's', 'ų' => 'u', 'ū' => 'u', 'ž' => 'z',
|
||||
'Ą' => 'A', 'Č' => 'C', 'Ę' => 'E', 'Ė' => 'E', 'Į' => 'I', 'Š' => 'S', 'Ų' => 'U', 'Ū' => 'U', 'Ž' => 'Z'
|
||||
),
|
||||
'vi' => array ( /* Vietnamese */
|
||||
'Á' => 'A', 'À' => 'A', 'Ả' => 'A', 'Ã' => 'A', 'Ạ' => 'A', 'Ă' => 'A', 'Ắ' => 'A', 'Ằ' => 'A', 'Ẳ' => 'A', 'Ẵ' => 'A', 'Ặ' => 'A', 'Â' => 'A', 'Ấ' => 'A', 'Ầ' => 'A', 'Ẩ' => 'A', 'Ẫ' => 'A', 'Ậ' => 'A',
|
||||
'á' => 'a', 'à' => 'a', 'ả' => 'a', 'ã' => 'a', 'ạ' => 'a', 'ă' => 'a', 'ắ' => 'a', 'ằ' => 'a', 'ẳ' => 'a', 'ẵ' => 'a', 'ặ' => 'a', 'â' => 'a', 'ấ' => 'a', 'ầ' => 'a', 'ẩ' => 'a', 'ẫ' => 'a', 'ậ' => 'a',
|
||||
'É' => 'E', 'È' => 'E', 'Ẻ' => 'E', 'Ẽ' => 'E', 'Ẹ' => 'E', 'Ê' => 'E', 'Ế' => 'E', 'Ề' => 'E', 'Ể' => 'E', 'Ễ' => 'E', 'Ệ' => 'E',
|
||||
'é' => 'e', 'è' => 'e', 'ẻ' => 'e', 'ẽ' => 'e', 'ẹ' => 'e', 'ê' => 'e', 'ế' => 'e', 'ề' => 'e', 'ể' => 'e', 'ễ' => 'e', 'ệ' => 'e',
|
||||
'Í' => 'I', 'Ì' => 'I', 'Ỉ' => 'I', 'Ĩ' => 'I', 'Ị' => 'I', 'í' => 'i', 'ì' => 'i', 'ỉ' => 'i', 'ĩ' => 'i', 'ị' => 'i',
|
||||
'Ó' => 'O', 'Ò' => 'O', 'Ỏ' => 'O', 'Õ' => 'O', 'Ọ' => 'O', 'Ô' => 'O', 'Ố' => 'O', 'Ồ' => 'O', 'Ổ' => 'O', 'Ỗ' => 'O', 'Ộ' => 'O', 'Ơ' => 'O', 'Ớ' => 'O', 'Ờ' => 'O', 'Ở' => 'O', 'Ỡ' => 'O', 'Ợ' => 'O',
|
||||
'ó' => 'o', 'ò' => 'o', 'ỏ' => 'o', 'õ' => 'o', 'ọ' => 'o', 'ô' => 'o', 'ố' => 'o', 'ồ' => 'o', 'ổ' => 'o', 'ỗ' => 'o', 'ộ' => 'o', 'ơ' => 'o', 'ớ' => 'o', 'ờ' => 'o', 'ở' => 'o', 'ỡ' => 'o', 'ợ' => 'o',
|
||||
'Ú' => 'U', 'Ù' => 'U', 'Ủ' => 'U', 'Ũ' => 'U', 'Ụ' => 'U', 'Ư' => 'U', 'Ứ' => 'U', 'Ừ' => 'U', 'Ử' => 'U', 'Ữ' => 'U', 'Ự' => 'U',
|
||||
'ú' => 'u', 'ù' => 'u', 'ủ' => 'u', 'ũ' => 'u', 'ụ' => 'u', 'ư' => 'u', 'ứ' => 'u', 'ừ' => 'u', 'ử' => 'u', 'ữ' => 'u', 'ự' => 'u',
|
||||
'Ý' => 'Y', 'Ỳ' => 'Y', 'Ỷ' => 'Y', 'Ỹ' => 'Y', 'Ỵ' => 'Y', 'ý' => 'y', 'ỳ' => 'y', 'ỷ' => 'y', 'ỹ' => 'y', 'ỵ' => 'y',
|
||||
'Đ' => 'D', 'đ' => 'd'
|
||||
),
|
||||
'ar' => array ( /* Arabic */
|
||||
'أ' => 'a', 'ب' => 'b', 'ت' => 't', 'ث' => 'th', 'ج' => 'g', 'ح' => 'h', 'خ' => 'kh', 'د' => 'd',
|
||||
'ذ' => 'th', 'ر' => 'r', 'ز' => 'z', 'س' => 's', 'ش' => 'sh', 'ص' => 's', 'ض' => 'd', 'ط' => 't',
|
||||
'ظ' => 'th', 'ع' => 'aa', 'غ' => 'gh', 'ف' => 'f', 'ق' => 'k', 'ك' => 'k', 'ل' => 'l', 'م' => 'm',
|
||||
'ن' => 'n', 'ه' => 'h', 'و' => 'o', 'ي' => 'y',
|
||||
'ا' => 'a', 'إ' => 'a', 'آ' => 'a', 'ؤ' => 'o', 'ئ' => 'y', 'ء' => 'aa',
|
||||
'٠' => '0', '١' => '1', '٢' => '2', '٣' => '3', '٤' => '4', '٥' => '5', '٦' => '6', '٧' => '7', '٨' => '8', '٩' => '9',
|
||||
),
|
||||
'fa' => array ( /* Persian */
|
||||
'گ' => 'g', 'ژ' => 'j', 'پ' => 'p', 'چ' => 'ch', 'ی' => 'y', 'ک' => 'k',
|
||||
'۰' => '0', '۱' => '1', '۲' => '2', '۳' => '3', '۴' => '4', '۵' => '5', '۶' => '6', '۷' => '7', '۸' => '8', '۹' => '9',
|
||||
),
|
||||
'sr' => array ( /* Serbian */
|
||||
'ђ' => 'dj', 'ј' => 'j', 'љ' => 'lj', 'њ' => 'nj', 'ћ' => 'c', 'џ' => 'dz', 'đ' => 'dj',
|
||||
'Ђ' => 'Dj', 'Ј' => 'j', 'Љ' => 'Lj', 'Њ' => 'Nj', 'Ћ' => 'C', 'Џ' => 'Dz', 'Đ' => 'Dj'
|
||||
),
|
||||
'az' => array ( /* Azerbaijani */
|
||||
'ç' => 'c', 'ə' => 'e', 'ğ' => 'g', 'ı' => 'i', 'ö' => 'o', 'ş' => 's', 'ü' => 'u',
|
||||
'Ç' => 'C', 'Ə' => 'E', 'Ğ' => 'G', 'İ' => 'I', 'Ö' => 'O', 'Ş' => 'S', 'Ü' => 'U'
|
||||
),
|
||||
'sk' => array ( /* Slovak */
|
||||
'ĺ' => 'l', 'ľ' => 'l', 'ŕ' => 'r'
|
||||
)
|
||||
);
|
||||
/**
|
||||
* The language-mapping array.
|
||||
*
|
||||
* ISO 639-1 codes: https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes
|
||||
*
|
||||
* @var array[]
|
||||
*/
|
||||
public static $maps = [];
|
||||
|
||||
/**
|
||||
* List of words to remove from URLs.
|
||||
*/
|
||||
public static $remove_list = array (
|
||||
'a', 'an', 'as', 'at', 'before', 'but', 'by', 'for', 'from',
|
||||
'is', 'in', 'into', 'like', 'of', 'off', 'on', 'onto', 'per',
|
||||
'since', 'than', 'the', 'this', 'that', 'to', 'up', 'via',
|
||||
'with'
|
||||
);
|
||||
/**
|
||||
* List of words to remove from URLs.
|
||||
*
|
||||
* @var array[]
|
||||
*/
|
||||
public static $remove_list = [];
|
||||
|
||||
/**
|
||||
* The character map.
|
||||
*/
|
||||
private static $map = array ();
|
||||
/**
|
||||
* An array of strings that will convert into the separator-char - used by "URLify::filter()".
|
||||
*
|
||||
* @var string[]
|
||||
*/
|
||||
private static $arrayToSeparator = [];
|
||||
|
||||
/**
|
||||
* The character list as a string.
|
||||
*/
|
||||
private static $chars = '';
|
||||
|
||||
/**
|
||||
* The character list as a regular expression.
|
||||
*/
|
||||
private static $regex = '';
|
||||
|
||||
/**
|
||||
* The current language
|
||||
*/
|
||||
private static $language = '';
|
||||
|
||||
/**
|
||||
* Initializes the character map.
|
||||
* @param string $language
|
||||
*/
|
||||
private static function init ($language = "")
|
||||
/**
|
||||
* Add new strings the will be replaced with the separator.
|
||||
*
|
||||
* @param array $array <p>An array of things that should replaced by the separator.</p>
|
||||
* @param bool $merge <p>Keep the previous (default) array-to-separator array.</p>
|
||||
*
|
||||
* @return void
|
||||
*
|
||||
* @psalm-param string[] $array
|
||||
*/
|
||||
public static function add_array_to_separator(array $array, bool $merge = true)
|
||||
{
|
||||
if (count (self::$map) > 0 && (($language == "") || ($language == self::$language))) {
|
||||
return;
|
||||
}
|
||||
if ($merge === true) {
|
||||
self::$arrayToSeparator = \array_unique(
|
||||
\array_merge(
|
||||
self::$arrayToSeparator,
|
||||
$array
|
||||
)
|
||||
);
|
||||
} else {
|
||||
self::$arrayToSeparator = $array;
|
||||
}
|
||||
}
|
||||
|
||||
/* Is a specific map associated with $language ? */
|
||||
if (isset(self::$maps[$language]) && is_array(self::$maps[$language])) {
|
||||
/* Move this map to end. This means it will have priority over others */
|
||||
$m = self::$maps[$language];
|
||||
unset(self::$maps[$language]);
|
||||
self::$maps[$language] = $m;
|
||||
}
|
||||
/* Reset static vars */
|
||||
self::$language = $language;
|
||||
self::$map = array();
|
||||
self::$chars = '';
|
||||
|
||||
foreach (self::$maps as $map) {
|
||||
foreach ($map as $orig => $conv) {
|
||||
self::$map[$orig] = $conv;
|
||||
self::$chars .= $orig;
|
||||
}
|
||||
}
|
||||
|
||||
self::$regex = '/[' . preg_quote(self::$chars, '/') . ']/u';
|
||||
}
|
||||
|
||||
/**
|
||||
* Add new characters to the list. `$map` should be a hash.
|
||||
* @param array $map
|
||||
*/
|
||||
public static function add_chars ($map)
|
||||
/**
|
||||
* Add new characters to the list. `$map` should be a hash.
|
||||
*
|
||||
* @param array $map
|
||||
* @param string|null $language
|
||||
*
|
||||
* @return void
|
||||
*
|
||||
* @psalm-param array<string, string> $map
|
||||
*/
|
||||
public static function add_chars(array $map, string $language = null)
|
||||
{
|
||||
if (! is_array ($map)) {
|
||||
throw new LogicException ('$map must be an associative array.');
|
||||
}
|
||||
self::$maps[] = $map;
|
||||
self::$map = array ();
|
||||
self::$chars = '';
|
||||
}
|
||||
$language_key = $language ?? \uniqid('urlify', true);
|
||||
|
||||
/**
|
||||
* Append words to the remove list. Accepts either single words
|
||||
* or an array of words.
|
||||
* @param mixed $words
|
||||
*/
|
||||
public static function remove_words ($words)
|
||||
if (isset(self::$maps[$language_key])) {
|
||||
self::$maps[$language_key] = \array_merge($map, self::$maps[$language_key]);
|
||||
} else {
|
||||
self::$maps[$language_key] = $map;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* @return void
|
||||
*/
|
||||
public static function reset_chars()
|
||||
{
|
||||
$words = is_array ($words) ? $words : array ($words);
|
||||
self::$remove_list = array_unique (array_merge (self::$remove_list, $words));
|
||||
}
|
||||
self::$maps = [];
|
||||
}
|
||||
|
||||
/**
|
||||
* Transliterates characters to their ASCII equivalents.
|
||||
/**
|
||||
* Transliterates characters to their ASCII equivalents.
|
||||
* $language specifies a priority for a specific language.
|
||||
* The latter is useful if languages have different rules for the same character.
|
||||
* @param string $text
|
||||
*
|
||||
* @param string $string <p>The input string.</p>
|
||||
* @param string $language <p>Your primary language.</p>
|
||||
* @param string $unknown <p>Character use if character unknown. (default is ?).</p>
|
||||
*
|
||||
* @return string
|
||||
*/
|
||||
public static function downcode(
|
||||
string $string,
|
||||
string $language = 'en',
|
||||
string $unknown = ''
|
||||
): string {
|
||||
$string = self::expandString($string, $language);
|
||||
|
||||
foreach (self::$maps as $mapsInner) {
|
||||
foreach ($mapsInner as $orig => $replace) {
|
||||
$string = \str_replace($orig, $replace, $string);
|
||||
}
|
||||
}
|
||||
|
||||
$string = \voku\helper\ASCII::to_ascii(
|
||||
$string,
|
||||
$language,
|
||||
false,
|
||||
true
|
||||
);
|
||||
|
||||
return \voku\helper\ASCII::to_transliterate(
|
||||
$string,
|
||||
$unknown,
|
||||
false
|
||||
);
|
||||
}
|
||||
|
||||
/**
|
||||
* Convert a String to URL slug. Wraps <strong>filter()</strong> with a simpler
|
||||
* set of defaults for typical usage in generating blog post slugs.
|
||||
*
|
||||
* @param string $string <p>The text you want to convert.</p>
|
||||
* @param int $maxLength <p>Max. length of the output string, set to "0" (zero) to
|
||||
* disable it</p>
|
||||
* @param string $separator <p>Define a new separator for the words.</p>
|
||||
* @param string $language <p>The language you want to convert to.</p>
|
||||
*/
|
||||
public static function slug(
|
||||
string $string,
|
||||
int $maxLength = 200,
|
||||
string $separator = '-',
|
||||
string $language = 'en'
|
||||
): string {
|
||||
return self::filter ($string, $maxLength, $language, false, false, true, $separator);
|
||||
}
|
||||
|
||||
/**
|
||||
* Convert a String to URL.
|
||||
*
|
||||
* e.g.: "Petty<br>theft" to "Petty-theft"
|
||||
*
|
||||
* @param string $string <p>The text you want to convert.</p>
|
||||
* @param int $maxLength <p>Max. length of the output string, set to "0" (zero) to
|
||||
* disable it</p>
|
||||
* @param string $language <p>The language you want to convert to.</p>
|
||||
* @param bool $fileName <p>
|
||||
* Keep the "." from the extension e.g.: "imaäe.jpg" =>
|
||||
* "image.jpg"
|
||||
* </p>
|
||||
* @param bool $removeWords <p>
|
||||
* Remove some "words" from the string.<br />
|
||||
* Info: Set extra words via <strong>remove_words()</strong>.
|
||||
* </p>
|
||||
* @param bool $strToLower <p>Use <strong>strtolower()</strong> at the end.</p>
|
||||
* @param bool|string $separator <p>Define a new separator for the words.</p>
|
||||
*
|
||||
* @return string
|
||||
*/
|
||||
public static function filter(
|
||||
string $string,
|
||||
int $maxLength = 200,
|
||||
string $language = 'en',
|
||||
bool $fileName = false,
|
||||
bool $removeWords = false,
|
||||
bool $strToLower = true,
|
||||
$separator = '-'
|
||||
): string {
|
||||
if ($string === '') {
|
||||
return '';
|
||||
}
|
||||
|
||||
// fallback
|
||||
if ($language === '') {
|
||||
$language = 'en';
|
||||
}
|
||||
|
||||
// separator-fallback
|
||||
if ($separator === false) {
|
||||
$separator = '_';
|
||||
}
|
||||
if ($separator === true || $separator === '') {
|
||||
$separator = '-';
|
||||
}
|
||||
|
||||
// escaped separator
|
||||
$separatorEscaped = \preg_quote($separator, '/');
|
||||
|
||||
// use defaults, if there are no values
|
||||
if (self::$arrayToSeparator === []) {
|
||||
self::reset_array_to_separator();
|
||||
}
|
||||
|
||||
// remove apostrophes which are not used as quotes around a string
|
||||
if (\strpos($string, "'") !== false) {
|
||||
$stringTmp = \preg_replace("/(\w)'(\w)/u", '${1}${2}', $string);
|
||||
if ($stringTmp !== null) {
|
||||
$string = (string) $stringTmp;
|
||||
}
|
||||
}
|
||||
|
||||
// replace with $separator
|
||||
$string = (string) \preg_replace(
|
||||
self::$arrayToSeparator,
|
||||
$separator,
|
||||
$string
|
||||
);
|
||||
|
||||
// remove all other html-tags
|
||||
if (
|
||||
\strpos($string, '<') !== false
|
||||
||
|
||||
\strpos($string, '>') !== false
|
||||
) {
|
||||
$string = \strip_tags($string);
|
||||
}
|
||||
|
||||
// use special language replacer
|
||||
$string = self::downcode($string, $language);
|
||||
|
||||
// replace with $separator, again
|
||||
$string = (string) \preg_replace(
|
||||
self::$arrayToSeparator,
|
||||
$separator,
|
||||
$string
|
||||
);
|
||||
|
||||
// remove all these words from the string before urlifying
|
||||
$removeWordsSearch = '//';
|
||||
if ($removeWords === true) {
|
||||
$removeList = self::get_remove_list($language);
|
||||
if ($removeList !== []) {
|
||||
$removeWordsSearch = '/\b(?:' . \implode('|', $removeList) . ')\b/ui';
|
||||
}
|
||||
}
|
||||
|
||||
// keep the "." from e.g.: a file-extension?
|
||||
if ($fileName) {
|
||||
$removePatternAddOn = '.';
|
||||
} else {
|
||||
$removePatternAddOn = '';
|
||||
}
|
||||
|
||||
$string = (string) \preg_replace(
|
||||
[
|
||||
// 1) remove un-needed chars
|
||||
'/[^' . $separatorEscaped . $removePatternAddOn . '\-a-zA-Z0-9\s]/u',
|
||||
// 2) convert spaces to $separator
|
||||
'/[\s]+/u',
|
||||
// 3) remove some extras words
|
||||
$removeWordsSearch,
|
||||
// 4) remove double $separator's
|
||||
'/[' . ($separatorEscaped ?: ' ') . ']+/u',
|
||||
// 5) remove $separator at the end
|
||||
'/[' . ($separatorEscaped ?: ' ') . ']+$/u',
|
||||
],
|
||||
[
|
||||
'',
|
||||
$separator,
|
||||
'',
|
||||
$separator,
|
||||
'',
|
||||
],
|
||||
$string
|
||||
);
|
||||
|
||||
// "substr" only if "$length" is set
|
||||
if (
|
||||
$maxLength
|
||||
&&
|
||||
$maxLength > 0
|
||||
&&
|
||||
\strlen($string) > $maxLength
|
||||
) {
|
||||
$string = (string) \substr(\trim($string, $separator), 0, $maxLength);
|
||||
}
|
||||
|
||||
// convert to lowercase
|
||||
if ($strToLower === true) {
|
||||
$string = \strtolower($string);
|
||||
}
|
||||
|
||||
// trim "$separator" from beginning and end of the string
|
||||
return \trim($string, $separator);
|
||||
}
|
||||
|
||||
/**
|
||||
* Append words to the remove list. Accepts either single words or an array of words.
|
||||
*
|
||||
* @param string|string[] $words
|
||||
* @param string $language
|
||||
* @param bool $merge <p>Keep the previous (default) remove-words array.</p>
|
||||
*
|
||||
* @return void
|
||||
*/
|
||||
public static function remove_words($words, string $language = 'en', bool $merge = true)
|
||||
{
|
||||
if (\is_array($words) === false) {
|
||||
$words = [$words];
|
||||
}
|
||||
|
||||
foreach ($words as $removeWordKey => $removeWord) {
|
||||
$words[$removeWordKey] = \preg_quote($removeWord, '/');
|
||||
}
|
||||
|
||||
if ($merge === true) {
|
||||
self::$remove_list[$language] = \array_unique(
|
||||
\array_merge(
|
||||
self::get_remove_list($language),
|
||||
$words
|
||||
)
|
||||
);
|
||||
} else {
|
||||
self::$remove_list[$language] = $words;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Reset the internal "self::$arrayToSeparator" to the default values.
|
||||
*
|
||||
* @return void
|
||||
*/
|
||||
public static function reset_array_to_separator()
|
||||
{
|
||||
self::$arrayToSeparator = [
|
||||
'/"|&|<|>|–|—/i', // ", &, <, >, –, —
|
||||
'/⁻|-|—|_|"|`|´|\'/',
|
||||
"#/\r\n|\r|\n|<br.*/?>#isU",
|
||||
];
|
||||
}
|
||||
|
||||
/**
|
||||
* reset the word-remove-array
|
||||
*
|
||||
* @param string $language
|
||||
*
|
||||
* @return void
|
||||
*/
|
||||
public static function reset_remove_list(string $language = 'en')
|
||||
{
|
||||
if ($language === '') {
|
||||
return;
|
||||
}
|
||||
|
||||
$language_orig = $language;
|
||||
$language = self::get_language_for_reset_remove_list($language);
|
||||
if ($language === '') {
|
||||
return;
|
||||
}
|
||||
|
||||
$stopWords = new \voku\helper\StopWords();
|
||||
|
||||
try {
|
||||
self::$remove_list[$language_orig] = $stopWords->getStopWordsFromLanguage($language);
|
||||
} catch (\voku\helper\StopWordsLanguageNotExists $e) {
|
||||
self::$remove_list[$language_orig] = [];
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Alias of `URLify::downcode()`.
|
||||
*
|
||||
* @param string $string
|
||||
* @param string $language
|
||||
*
|
||||
* @return string
|
||||
*/
|
||||
public static function downcode ($text, $language = "")
|
||||
*/
|
||||
public static function transliterate(string $string, string $language = 'en'): string
|
||||
{
|
||||
self::init ($language);
|
||||
return self::downcode($string, $language);
|
||||
}
|
||||
|
||||
if (preg_match_all (self::$regex, $text, $matches)) {
|
||||
for ($i = 0; $i < count ($matches[0]); $i++) {
|
||||
$char = $matches[0][$i];
|
||||
if (isset (self::$map[$char])) {
|
||||
$text = str_replace ($char, self::$map[$char], $text);
|
||||
}
|
||||
}
|
||||
}
|
||||
return $text;
|
||||
}
|
||||
/**
|
||||
* Expands the given string replacing some special parts for words.
|
||||
* e.g. "lorem@ipsum.com" is replaced by "lorem at ipsum dot com".
|
||||
*
|
||||
* Most of these transformations have been inspired by the pelle/slugger
|
||||
* project, distributed under the Eclipse Public License.
|
||||
* Copyright 2012 Pelle Braendgaard
|
||||
*
|
||||
* @param string $string The string to expand
|
||||
* @param string $language
|
||||
*
|
||||
* @return string The result of expanding the string
|
||||
*/
|
||||
protected static function expandString(string $string, string $language = 'en'): string
|
||||
{
|
||||
$string = self::expandCurrencies($string, $language);
|
||||
|
||||
/**
|
||||
* Filters a string, e.g., "Petty theft" to "petty-theft"
|
||||
* @param string $text The text to return filtered
|
||||
* @param int $length The length (after filtering) of the string to be returned
|
||||
* @param string $language The transliteration language, passed down to downcode()
|
||||
* @param bool $file_name Whether there should be and additional filter considering this is a filename
|
||||
* @param bool $use_remove_list Whether you want to remove specific elements previously set in self::$remove_list
|
||||
* @param bool $lower_case Whether you want the filter to maintain casing or lowercase everything (default)
|
||||
* @param bool $treat_underscore_as_space Treat underscore as space, so it will replaced with "-"
|
||||
return self::expandSymbols($string, $language);
|
||||
}
|
||||
|
||||
/**
|
||||
* @param string $language
|
||||
*
|
||||
* @return string
|
||||
*/
|
||||
public static function filter ($text, $length = 60, $language = "", $file_name = false, $use_remove_list = true, $lower_case = true, $treat_underscore_as_space = true)
|
||||
*/
|
||||
private static function get_language_for_reset_remove_list(string $language)
|
||||
{
|
||||
$text = self::downcode ($text,$language);
|
||||
if ($language === '') {
|
||||
return '';
|
||||
}
|
||||
|
||||
if ($use_remove_list) {
|
||||
// remove all these words from the string before urlifying
|
||||
$text = preg_replace ('/\b(' . join ('|', self::$remove_list) . ')\b/i', '', $text);
|
||||
}
|
||||
if (
|
||||
\strpos($language, '_') === false
|
||||
&&
|
||||
\strpos($language, '-') === false
|
||||
) {
|
||||
$language = \strtolower($language);
|
||||
} else {
|
||||
$regex = '/(?<first>[a-z]{2}).*/i';
|
||||
$language = \strtolower((string) \preg_replace($regex, '$1', $language));
|
||||
}
|
||||
|
||||
// if downcode doesn't hit, the char will be stripped here
|
||||
$remove_pattern = ($file_name) ? '/[^_\-.\-a-zA-Z0-9\s]/u' : '/[^\s_\-a-zA-Z0-9]/u';
|
||||
$text = preg_replace ($remove_pattern, '', $text); // remove unneeded chars
|
||||
if ($treat_underscore_as_space) {
|
||||
$text = str_replace ('_', ' ', $text); // treat underscores as spaces
|
||||
}
|
||||
$text = preg_replace ('/^\s+|\s+$/u', '', $text); // trim leading/trailing spaces
|
||||
$text = preg_replace ('/[-\s]+/u', '-', $text); // convert spaces to hyphens
|
||||
if ($lower_case) {
|
||||
$text = strtolower ($text); // convert to lowercase
|
||||
}
|
||||
return $language;
|
||||
}
|
||||
|
||||
return trim (substr ($text, 0, $length), '-'); // trim to first $length chars
|
||||
}
|
||||
|
||||
/**
|
||||
* Alias of `URLify::downcode()`.
|
||||
*/
|
||||
public static function transliterate ($text)
|
||||
/**
|
||||
* Expands the numeric currencies in euros, dollars, pounds
|
||||
* and yens that the given string may include.
|
||||
*
|
||||
* @param string $string
|
||||
* @param string $language
|
||||
*
|
||||
* @return string
|
||||
*/
|
||||
private static function expandCurrencies(string $string, string $language = 'en')
|
||||
{
|
||||
return self::downcode ($text);
|
||||
}
|
||||
if (
|
||||
\strpos($string, '€') === false
|
||||
&&
|
||||
\strpos($string, '$') === false
|
||||
&&
|
||||
\strpos($string, '£') === false
|
||||
&&
|
||||
\strpos($string, '¥') === false
|
||||
) {
|
||||
return $string;
|
||||
}
|
||||
|
||||
if ($language === 'de') {
|
||||
return (string) \preg_replace(
|
||||
[
|
||||
'/(?:\s|^)(\d+)(?: )*€(?:\s|$)/',
|
||||
'/(?:\s|^)\$(?: )*(\d+)(?:\s|$)/',
|
||||
'/(?:\s|^)£(?: )*(\d+)(?:\s|$)/',
|
||||
'/(?:\s|^)¥(?: )*(\d+)(?:\s|$)/',
|
||||
'/(?:\s|^)(\d+)[.|,](\d+)(?: )*€(?:\s|$)/',
|
||||
'/(?:\s|^)\$(?: )*(\d+)[.|,](\d+)(?:\s|$)/',
|
||||
'/(?:\s|^)£(?: )*(\d+)[.|,](\d+)(?:\s|$)/',
|
||||
],
|
||||
[
|
||||
' \1 Euro ',
|
||||
' \1 Dollar ',
|
||||
' \1 Pound ',
|
||||
' \1 Yen ',
|
||||
' \1 Euro \2 Cent ',
|
||||
' \1 Dollar \2 Cent ',
|
||||
' \1 Pound \2 Pence ',
|
||||
],
|
||||
$string
|
||||
);
|
||||
}
|
||||
|
||||
return (string) \preg_replace(
|
||||
[
|
||||
'/(?:\s|^)1(?: )*€(?:\s|$)/',
|
||||
'/(?:\s|^)(\d+)(?: )*€(?:\s|$)/',
|
||||
'/(?:\s|^)\$(?: )*1(?:\s|$)/',
|
||||
'/(?:\s|^)\$(?: )*(\d+)(?:\s|$)/',
|
||||
'/(?:\s|^)£(?: )*1(?:\s|$)/',
|
||||
'/(?:\s|^)£(?: )*(\d+)(?:\s|$)/',
|
||||
'/(?:\s|^)¥(?: )*(\d+)(?:\s|$)/',
|
||||
'/(?:\s|^)1[.|,](\d+)(?: )*€(?:\s|$)/',
|
||||
'/(?:\s|^)(\d+)[.|,](\d+)(?: )*€(?:\s|$)/',
|
||||
'/(?:\s|^)1[.|,](\d+)(?: )*$(?:\s|$)/',
|
||||
'/(?:\s|^)\$(?: )*(\d+)[.|,](\d+)(?:\s|$)/',
|
||||
'/(?:\s|^)1[.|,](\d+)(?: )*£(?:\s|$)/',
|
||||
'/(?:\s|^)£(?: )*(\d+)[.|,](\d+)(?:\s|$)/',
|
||||
],
|
||||
[
|
||||
' 1 Euro ',
|
||||
' \1 Euros ',
|
||||
' 1 Dollar ',
|
||||
' \1 Dollars ',
|
||||
' 1 Pound ',
|
||||
' \1 Pounds ',
|
||||
' \1 Yen ',
|
||||
' 1 Euros \1 Cents ',
|
||||
' \1 Euros \2 Cents ',
|
||||
' 1 Dollars \1 Cents ',
|
||||
' \1 Dollars \2 Cents ',
|
||||
' 1 Pounds \1 Pence ',
|
||||
' \1 Pounds \2 Pence ',
|
||||
],
|
||||
$string
|
||||
);
|
||||
}
|
||||
|
||||
/**
|
||||
* Expands the special symbols that the given string may include, such as '@', '.', '#' and '%'.
|
||||
*
|
||||
* @param string $string
|
||||
* @param string $language
|
||||
*
|
||||
* @return string
|
||||
*/
|
||||
private static function expandSymbols(string $string, string $language = 'en')
|
||||
{
|
||||
if (
|
||||
\strpos($string, '©') === false
|
||||
&&
|
||||
\strpos($string, '®') === false
|
||||
&&
|
||||
\strpos($string, '@') === false
|
||||
&&
|
||||
\strpos($string, '&') === false
|
||||
&&
|
||||
\strpos($string, '%') === false
|
||||
&&
|
||||
\strpos($string, '=') === false
|
||||
) {
|
||||
return $string;
|
||||
}
|
||||
|
||||
$maps = \voku\helper\ASCII::charsArray(true);
|
||||
|
||||
return (string) \preg_replace(
|
||||
[
|
||||
'/\s*©\s*/',
|
||||
'/\s*®\s*/',
|
||||
'/\s*@\s*/',
|
||||
'/\s*&\s*/',
|
||||
'/\s*%\s*/',
|
||||
'/(\s*=\s*)/',
|
||||
],
|
||||
[
|
||||
$maps['latin_symbols']['©'],
|
||||
$maps['latin_symbols']['®'],
|
||||
$maps['latin_symbols']['@'],
|
||||
$maps[$language]['&'] ?? '&',
|
||||
$maps[$language]['%'] ?? '%',
|
||||
$maps[$language]['='] ?? '=',
|
||||
],
|
||||
$string
|
||||
);
|
||||
}
|
||||
|
||||
/**
|
||||
* return the "self::$remove_list[$language]" array
|
||||
*
|
||||
* @param string $language
|
||||
*
|
||||
* @return array<mixed>
|
||||
*/
|
||||
private static function get_remove_list(string $language = 'en')
|
||||
{
|
||||
// check for language
|
||||
if ($language === '') {
|
||||
return [];
|
||||
}
|
||||
|
||||
// set remove-array
|
||||
if (!isset(self::$remove_list[$language])) {
|
||||
self::reset_remove_list($language);
|
||||
}
|
||||
|
||||
// check for array
|
||||
if (
|
||||
!isset(self::$remove_list[$language])
|
||||
||
|
||||
empty(self::$remove_list[$language])
|
||||
) {
|
||||
return [];
|
||||
}
|
||||
|
||||
return self::$remove_list[$language];
|
||||
}
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue