aboutsummaryrefslogblamecommitdiffstats
path: root/library/urlify/URLify.php
blob: 1337f9a918e54d367bb910b0b98fea17a215ea1b (plain) (tree)



























































































































































































                                                                                                                                                                
<?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, Russian, Ukrainian,
 * Czech, Polish, and Latvian. Symbols it cannot transliterate
 * it will simply omit.
 *
 * Usage:
 *
 *     echo URLify::filter (' J\'étudie le français ');
 *     // "jetudie-le-francais"
 *     
 *     echo URLify::filter ('Lo siento, no hablo español.');
 *     // "lo-siento-no-hablo-espanol"
 */
class URLify {
	public static $maps = array (
		'latin_map' => array (
			'À' => 'A', 'Á' => 'A', 'Â' => 'A', 'Ã' => 'A', 'Ä' => 'A', 'Å' => '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', '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', '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', 'ù' => 'u', 'ú' => 'u',
			'û' => 'u', 'ü' => 'u', 'ű' => 'u', 'ý' => 'y', 'þ' => 'th', 'ÿ' => 'y'
		),
		'latin_symbols_map' => array (
			'©' => '(c)'
		),
		'greek_map' => array (
			'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'
		),
		'turkish_map' => array (
			'ş' => 's', 'Ş' => 'S', 'ı' => 'i', 'İ' => 'I', 'ç' => 'c', 'Ç' => 'C', 'ü' => 'u', 'Ü' => 'U',
			'ö' => 'o', 'Ö' => 'O', 'ğ' => 'g', 'Ğ' => 'G'
		),
		'russian_map' => array (
			'а' => 'a', 'б' => 'b', 'в' => 'v', 'г' => 'g', 'д' => 'd', 'е' => 'e', 'ё' => 'yo', 'ж' => 'zh',
			'з' => 'z', 'и' => 'i', 'й' => 'j', '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' => 'J', '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'
		),
		'ukrainian_map' => array (
			'Є' => 'Ye', 'І' => 'I', 'Ї' => 'Yi', 'Ґ' => 'G', 'є' => 'ye', 'і' => 'i', 'ї' => 'yi', 'ґ' => 'g'
		),
		'czech_map' => array (
			'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'
		),
		'polish_map' => array (
			'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'
		),
		'latvian_map' => array (
			'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'
		)
	);

	/**
	 * 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'
	);

	/**
	 * The character map.
	 */
	private static $map = array ();

	/**
	 * The character list as a string.
	 */
	private static $chars = '';

	/**
	 * The character list as a regular expression.
	 */
	private static $regex = '';

	/**
	 * Initializes the character map.
	 */
	private static function init () {
		if (count (self::$map) > 0) {
			return;
		}

		foreach (self::$maps as $map) {
			foreach ($map as $orig => $conv) {
				self::$map[$orig] = $conv;
				self::$chars .= $orig;
			}
		}

		self::$regex = '/[' . self::$chars . ']/u';
	}

	/**
	 * Add new characters to the list. `$map` should be a hash.
	 */
	public static function add_chars ($map) {
		if (! is_array ($map)) {
			throw new LogicException ('$map must be an associative array.');
		}
		self::$maps[] = $map;
		self::$map = array ();
		self::$chars = '';
	}

	/**
	 * Append words to the remove list. Accepts either single words
	 * or an array of words.
	 */
	public static function remove_words ($words) {
		$words = is_array ($words) ? $words : array ($words);
		self::$remove_list = array_merge (self::$remove_list, $words);
	}

	/**
	 * Transliterates characters to their ASCII equivalents.
	 */
	public static function downcode ($text) {
		self::init ();

		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;
	}

	/**
	 * Filters a string, e.g., "Petty theft" to "petty-theft"
	 */
	public static function filter ($text, $length = 60) {
		$text = self::downcode ($text);

		// remove all these words from the string before urlifying
		$text = preg_replace ('/\b(' . join ('|', self::$remove_list) . ')\b/i', '', $text);

		// if downcode doesn't hit, the char will be stripped here
		$text = preg_replace ('/[^-\w\s]/', '', $text);		// remove unneeded chars
		$text = preg_replace ('/^\s+|\s+$/', '', $text);	// trim leading/trailing spaces
		$text = preg_replace ('/[-\s]+/', '-', $text);		// convert spaces to hyphens
		$text = strtolower ($text);							// convert to lowercase						
		return trim (substr ($text, 0, $length), '-');	// trim to first $length chars
	}

	/**
	 * Alias of `URLify::downcode()`.
	 */
	public static function transliterate ($text) {
		return self::downcode ($text);
	}
}

?>