Skip to content

Instantly share code, notes, and snippets.

@jbroadway

jbroadway/URLify.php

Created May 2, 2012 22:29
Show Gist options
  • Save jbroadway/2581025 to your computer and use it in GitHub Desktop.
Save jbroadway/2581025 to your computer and use it in GitHub Desktop.
Download ZIP
URLify vs Urlizer
Raw
URLify.php
<?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);
}
}
?>
Raw
urlify_test.php
<?php
$start = microtime (true);
require 'URLify.php';
echo URLify::filter (' J\'étudie le français ') . PHP_EOL;
echo URLify::filter ('Lo siento, no hablo español.') . PHP_EOL;
echo URLify::filter ('ΦΞΠΏΣ') . PHP_EOL;
echo microtime (true) - $start . PHP_EOL;
echo memory_get_peak_usage () . PHP_EOL;
?>
Raw
Urlizer.php
<?php
namespace Gedmo\Sluggable\Util;
/**
* This is the part taken from Doctrine 1.2.3
* Doctrine inflector has static methods for inflecting text
*
* The methods in these classes are from several different sources collected
* across several different php projects and several different authors. The
* original author names and emails are not known
*
* Uses 3rd party libraries and functions:
* http://sourceforge.net/projects/phputf8
*
* @package Gedmo.Sluggable.Util
* @subpackage Urlizer
* @license http://www.opensource.org/licenses/lgpl-license.php LGPL
* @link www.doctrine-project.org
* @since 1.0
* @version $Revision: 3189 $
* @author Konsta Vesterinen <[email protected]>
* @author Jonathan H. Wage <[email protected]>
* @author <[email protected]>
*/
class Urlizer
{
/**
* Check if a string has utf7 characters in it
*
* By bmorel at ssi dot fr
*
* @param string $string
* @return boolean $bool
*/
public static function seemsUtf8($string)
{
for ($i = 0; $i < strlen($string); $i++) {
if (ord($string[$i]) < 0x80) continue; # 0bbbbbbb
elseif ((ord($string[$i]) & 0xE0) == 0xC0) $n=1; # 110bbbbb
elseif ((ord($string[$i]) & 0xF0) == 0xE0) $n=2; # 1110bbbb
elseif ((ord($string[$i]) & 0xF8) == 0xF0) $n=3; # 11110bbb
elseif ((ord($string[$i]) & 0xFC) == 0xF8) $n=4; # 111110bb
elseif ((ord($string[$i]) & 0xFE) == 0xFC) $n=5; # 1111110b
else return false; # Does not match any model
for ($j=0; $j<$n; $j++) { # n bytes matching 10bbbbbb follow ?
if ((++$i == strlen($string)) || ((ord($string[$i]) & 0xC0) != 0x80))
return false;
}
}
return true;
}
/**
* Remove any illegal characters, accents, etc.
*
* @param string $string String to unaccent
* @return string $string Unaccented string
*/
public static function unaccent($string)
{
if (!preg_match('/[\x80-\xff]/', $string)) {
return $string;
}
if (self::seemsUtf8($string)) {
$chars = array(
// Decompositions for Latin-1 Supplement
chr(195).chr(128) => 'A', chr(195).chr(129) => 'A',
chr(195).chr(130) => 'A', chr(195).chr(131) => 'A',
chr(195).chr(132) => 'A', chr(195).chr(133) => 'A',
chr(195).chr(135) => 'C', chr(195).chr(136) => 'E',
chr(195).chr(137) => 'E', chr(195).chr(138) => 'E',
chr(195).chr(139) => 'E', chr(195).chr(140) => 'I',
chr(195).chr(141) => 'I', chr(195).chr(142) => 'I',
chr(195).chr(143) => 'I', chr(195).chr(145) => 'N',
chr(195).chr(146) => 'O', chr(195).chr(147) => 'O',
chr(195).chr(148) => 'O', chr(195).chr(149) => 'O',
chr(195).chr(150) => 'O', chr(195).chr(153) => 'U',
chr(195).chr(154) => 'U', chr(195).chr(155) => 'U',
chr(195).chr(156) => 'U', chr(195).chr(157) => 'Y',
chr(195).chr(159) => 's', chr(195).chr(160) => 'a',
chr(195).chr(161) => 'a', chr(195).chr(162) => 'a',
chr(195).chr(163) => 'a', chr(195).chr(164) => 'a',
chr(195).chr(165) => 'a', chr(195).chr(167) => 'c',
chr(195).chr(168) => 'e', chr(195).chr(169) => 'e',
chr(195).chr(170) => 'e', chr(195).chr(171) => 'e',
chr(195).chr(172) => 'i', chr(195).chr(173) => 'i',
chr(195).chr(174) => 'i', chr(195).chr(175) => 'i',
chr(195).chr(177) => 'n', chr(195).chr(178) => 'o',
chr(195).chr(179) => 'o', chr(195).chr(180) => 'o',
chr(195).chr(181) => 'o', chr(195).chr(182) => 'o',
chr(195).chr(182) => 'o', chr(195).chr(185) => 'u',
chr(195).chr(186) => 'u', chr(195).chr(187) => 'u',
chr(195).chr(188) => 'u', chr(195).chr(189) => 'y',
chr(195).chr(191) => 'y',
// Decompositions for Latin Extended-A
chr(196).chr(128) => 'A', chr(196).chr(129) => 'a',
chr(196).chr(130) => 'A', chr(196).chr(131) => 'a',
chr(196).chr(132) => 'A', chr(196).chr(133) => 'a',
chr(196).chr(134) => 'C', chr(196).chr(135) => 'c',
chr(196).chr(136) => 'C', chr(196).chr(137) => 'c',
chr(196).chr(138) => 'C', chr(196).chr(139) => 'c',
chr(196).chr(140) => 'C', chr(196).chr(141) => 'c',
chr(196).chr(142) => 'D', chr(196).chr(143) => 'd',
chr(196).chr(144) => 'D', chr(196).chr(145) => 'd',
chr(196).chr(146) => 'E', chr(196).chr(147) => 'e',
chr(196).chr(148) => 'E', chr(196).chr(149) => 'e',
chr(196).chr(150) => 'E', chr(196).chr(151) => 'e',
chr(196).chr(152) => 'E', chr(196).chr(153) => 'e',
chr(196).chr(154) => 'E', chr(196).chr(155) => 'e',
chr(196).chr(156) => 'G', chr(196).chr(157) => 'g',
chr(196).chr(158) => 'G', chr(196).chr(159) => 'g',
chr(196).chr(160) => 'G', chr(196).chr(161) => 'g',
chr(196).chr(162) => 'G', chr(196).chr(163) => 'g',
chr(196).chr(164) => 'H', chr(196).chr(165) => 'h',
chr(196).chr(166) => 'H', chr(196).chr(167) => 'h',
chr(196).chr(168) => 'I', chr(196).chr(169) => 'i',
chr(196).chr(170) => 'I', chr(196).chr(171) => 'i',
chr(196).chr(172) => 'I', chr(196).chr(173) => 'i',
chr(196).chr(174) => 'I', chr(196).chr(175) => 'i',
chr(196).chr(176) => 'I', chr(196).chr(177) => 'i',
chr(196).chr(178) => 'IJ',chr(196).chr(179) => 'ij',
chr(196).chr(180) => 'J', chr(196).chr(181) => 'j',
chr(196).chr(182) => 'K', chr(196).chr(183) => 'k',
chr(196).chr(184) => 'k', chr(196).chr(185) => 'L',
chr(196).chr(186) => 'l', chr(196).chr(187) => 'L',
chr(196).chr(188) => 'l', chr(196).chr(189) => 'L',
chr(196).chr(190) => 'l', chr(196).chr(191) => 'L',
chr(197).chr(128) => 'l', chr(197).chr(129) => 'L',
chr(197).chr(130) => 'l', chr(197).chr(131) => 'N',
chr(197).chr(132) => 'n', chr(197).chr(133) => 'N',
chr(197).chr(134) => 'n', chr(197).chr(135) => 'N',
chr(197).chr(136) => 'n', chr(197).chr(137) => 'N',
chr(197).chr(138) => 'n', chr(197).chr(139) => 'N',
chr(197).chr(140) => 'O', chr(197).chr(141) => 'o',
chr(197).chr(142) => 'O', chr(197).chr(143) => 'o',
chr(197).chr(144) => 'O', chr(197).chr(145) => 'o',
chr(197).chr(146) => 'OE',chr(197).chr(147) => 'oe',
chr(197).chr(148) => 'R', chr(197).chr(149) => 'r',
chr(197).chr(150) => 'R', chr(197).chr(151) => 'r',
chr(197).chr(152) => 'R', chr(197).chr(153) => 'r',
chr(197).chr(154) => 'S', chr(197).chr(155) => 's',
chr(197).chr(156) => 'S', chr(197).chr(157) => 's',
chr(197).chr(158) => 'S', chr(197).chr(159) => 's',
chr(197).chr(160) => 'S', chr(197).chr(161) => 's',
chr(197).chr(162) => 'T', chr(197).chr(163) => 't',
chr(197).chr(164) => 'T', chr(197).chr(165) => 't',
chr(197).chr(166) => 'T', chr(197).chr(167) => 't',
chr(197).chr(168) => 'U', chr(197).chr(169) => 'u',
chr(197).chr(170) => 'U', chr(197).chr(171) => 'u',
chr(197).chr(172) => 'U', chr(197).chr(173) => 'u',
chr(197).chr(174) => 'U', chr(197).chr(175) => 'u',
chr(197).chr(176) => 'U', chr(197).chr(177) => 'u',
chr(197).chr(178) => 'U', chr(197).chr(179) => 'u',
chr(197).chr(180) => 'W', chr(197).chr(181) => 'w',
chr(197).chr(182) => 'Y', chr(197).chr(183) => 'y',
chr(197).chr(184) => 'Y', chr(197).chr(185) => 'Z',
chr(197).chr(186) => 'z', chr(197).chr(187) => 'Z',
chr(197).chr(188) => 'z', chr(197).chr(189) => 'Z',
chr(197).chr(190) => 'z', chr(197).chr(191) => 's',
// Euro Sign
chr(226).chr(130).chr(172) => 'E',
// GBP (Pound) Sign
chr(194).chr(163) => '',
'Ä' => 'Ae', 'ä' => 'ae', 'Ü' => 'Ue', 'ü' => 'ue',
'Ö' => 'Oe', 'ö' => 'oe', 'ß' => 'ss',
// Norwegian characters
'Å'=>'Aa','Æ'=>'Ae','Ø'=>'O','æ'=>'a','ø'=>'o','å'=>'aa'
);
$string = strtr($string, $chars);
} else {
// Assume ISO-8859-1 if not UTF-8
$chars['in'] = chr(128).chr(131).chr(138).chr(142).chr(154).chr(158)
.chr(159).chr(162).chr(165).chr(181).chr(192).chr(193).chr(194)
.chr(195).chr(196).chr(197).chr(199).chr(200).chr(201).chr(202)
.chr(203).chr(204).chr(205).chr(206).chr(207).chr(209).chr(210)
.chr(211).chr(212).chr(213).chr(214).chr(216).chr(217).chr(218)
.chr(219).chr(220).chr(221).chr(224).chr(225).chr(226).chr(227)
.chr(228).chr(229).chr(231).chr(232).chr(233).chr(234).chr(235)
.chr(236).chr(237).chr(238).chr(239).chr(241).chr(242).chr(243)
.chr(244).chr(245).chr(246).chr(248).chr(249).chr(250).chr(251)
.chr(252).chr(253).chr(255);
$chars['out'] = "EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYaaaaaaceeeeiiiinoooooouuuuyy";
$string = strtr($string, $chars['in'], $chars['out']);
$doubleChars['in'] = array(chr(140), chr(156), chr(198), chr(208), chr(222), chr(223), chr(230), chr(240), chr(254));
$doubleChars['out'] = array('OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th');
$string = str_replace($doubleChars['in'], $doubleChars['out'], $string);
}
return $string;
}
/**
* US-ASCII transliterations of Unicode text
* Ported Sean M. Burke's Text::Unidecode Perl module (He did all the hard work!)
* Warning: you should only pass this well formed UTF-8!
* Be aware it works by making a copy of the input string which it appends transliterated
* characters to - it uses a PHP output buffer to do this - it means, memory use will increase,
* requiring up to the same amount again as the input string
*
* @see http://search.cpan.org/~sburke/Text-Unidecode-0.04/lib/Text/Unidecode.pm
* @param string UTF-8 string to convert
* @author <[email protected]>
* @param string (default = ?) Character use if character unknown
* @return string US-ASCII string
*/
public static function utf8ToAscii($str, $unknown = '?')
{
static $UTF8_TO_ASCII;
if (strlen($str) == 0) {
return;
}
preg_match_all('/.{1}|[^\x00]{1,1}$/us', $str, $ar);
$chars = $ar[0];
foreach ($chars as $i => $c) {
$ud = 0;
if (ord($c{0})>=0 && ord($c{0})<=127) { continue; } // ASCII - next please
if (ord($c{0})>=192 && ord($c{0})<=223) { $ord = (ord($c{0})-192)*64 + (ord($c{1})-128); }
if (ord($c{0})>=224 && ord($c{0})<=239) { $ord = (ord($c{0})-224)*4096 + (ord($c{1})-128)*64 + (ord($c{2})-128); }
if (ord($c{0})>=240 && ord($c{0})<=247) { $ord = (ord($c{0})-240)*262144 + (ord($c{1})-128)*4096 + (ord($c{2})-128)*64 + (ord($c{3})-128); }
if (ord($c{0})>=248 && ord($c{0})<=251) { $ord = (ord($c{0})-248)*16777216 + (ord($c{1})-128)*262144 + (ord($c{2})-128)*4096 + (ord($c{3})-128)*64 + (ord($c{4})-128); }
if (ord($c{0})>=252 && ord($c{0})<=253) { $ord = (ord($c{0})-252)*1073741824 + (ord($c{1})-128)*16777216 + (ord($c{2})-128)*262144 + (ord($c{3})-128)*4096 + (ord($c{4})-128)*64 + (ord($c{5})-128); }
if (ord($c{0})>=254 && ord($c{0})<=255) { $chars{$i} = $unknown; continue; } //error
$bank = $ord >> 8;
if (!array_key_exists($bank, (array)$UTF8_TO_ASCII)) {
$bankfile = __DIR__. '/data/'. sprintf("x%02x",$bank).'.php';
if (file_exists($bankfile)) {
include $bankfile;
} else {
$UTF8_TO_ASCII[$bank] = array();
}
}
$newchar = $ord & 255;
if (array_key_exists($newchar, $UTF8_TO_ASCII[$bank])) {
$chars{$i} = $UTF8_TO_ASCII[$bank][$newchar];
} else {
$chars{$i} = $unknown;
}
}
return implode('', $chars);
}
/**
* Does not transliterate correctly eastern languages
*
* @param string $text
* @param string $separator
* @return string
*/
public static function urlize($text, $separator = '-')
{
$text = self::unaccent($text);
return self::postProcessText($text, $separator);
}
/**
* Uses transliteration tables to convert any kind of utf8 character
*
* @param string $text
* @param string $separator
* @return string $text
*/
public static function transliterate($text, $separator = '-')
{
if (preg_match('/[\x80-\xff]/', $text) && self::validUtf8($text)) {
$text = self::utf8ToAscii($text);
}
return $text;
}
/**
* Tests a string as to whether it's valid UTF-8 and supported by the
* Unicode standard
* Note: this function has been modified to simple return true or false
* @author <[email protected]>
* @param string UTF-8 encoded string
* @return boolean true if valid
* @see http://hsivonen.iki.fi/php-utf8/
*/
public static function validUtf8($str)
{
$mState = 0; // cached expected number of octets after the current octet
// until the beginning of the next UTF8 character sequence
$mUcs4 = 0; // cached Unicode character
$mBytes = 1; // cached expected number of octets in the current sequence
$len = strlen($str);
for ($i = 0; $i < $len; $i++) {
$in = ord($str{$i});
if ($mState == 0) {
// When mState is zero we expect either a US-ASCII character or a
// multi-octet sequence.
if (0 == (0x80 & ($in))) {
// US-ASCII, pass straight through.
$mBytes = 1;
} elseif (0xC0 == (0xE0 & ($in))) {
// First octet of 2 octet sequence
$mUcs4 = ($in);
$mUcs4 = ($mUcs4 & 0x1F) << 6;
$mState = 1;
$mBytes = 2;
} elseif (0xE0 == (0xF0 & ($in))) {
// First octet of 3 octet sequence
$mUcs4 = ($in);
$mUcs4 = ($mUcs4 & 0x0F) << 12;
$mState = 2;
$mBytes = 3;
} elseif (0xF0 == (0xF8 & ($in))) {
// First octet of 4 octet sequence
$mUcs4 = ($in);
$mUcs4 = ($mUcs4 & 0x07) << 18;
$mState = 3;
$mBytes = 4;
} elseif (0xF8 == (0xFC & ($in))) {
/* First octet of 5 octet sequence.
*
* This is illegal because the encoded codepoint must be either
* (a) not the shortest form or
* (b) outside the Unicode range of 0-0x10FFFF.
* Rather than trying to resynchronize, we will carry on until the end
* of the sequence and let the later error handling code catch it.
*/
$mUcs4 = ($in);
$mUcs4 = ($mUcs4 & 0x03) << 24;
$mState = 4;
$mBytes = 5;
} elseif (0xFC == (0xFE & ($in))) {
// First octet of 6 octet sequence, see comments for 5 octet sequence.
$mUcs4 = ($in);
$mUcs4 = ($mUcs4 & 1) << 30;
$mState = 5;
$mBytes = 6;
} else {
/* Current octet is neither in the US-ASCII range nor a legal first
* octet of a multi-octet sequence.
*/
return false;
}
} else {
// When mState is non-zero, we expect a continuation of the multi-octet
// sequence
if (0x80 == (0xC0 & ($in))) {
// Legal continuation.
$shift = ($mState - 1) * 6;
$tmp = $in;
$tmp = ($tmp & 0x0000003F) << $shift;
$mUcs4 |= $tmp;
/**
* End of the multi-octet sequence. mUcs4 now contains the final
* Unicode codepoint to be output
*/
if (0 == --$mState) {
/*
* Check for illegal sequences and codepoints.
*/
// From Unicode 3.1, non-shortest form is illegal
if (((2 == $mBytes) && ($mUcs4 < 0x0080)) ||
((3 == $mBytes) && ($mUcs4 < 0x0800)) ||
((4 == $mBytes) && ($mUcs4 < 0x10000)) ||
(4 < $mBytes) ||
// From Unicode 3.2, surrogate characters are illegal
(($mUcs4 & 0xFFFFF800) == 0xD800) ||
// Codepoints outside the Unicode range are illegal
($mUcs4 > 0x10FFFF)
) {
return false;
}
//initialize UTF8 cache
$mState = 0;
$mUcs4 = 0;
$mBytes = 1;
}
} else {
/**
*((0xC0 & (*in) != 0x80) && (mState != 0))
* Incomplete multi-octet sequence.
*/
return false;
}
}
}
return true;
}
/**
* Cleans up the text and adds separator
*
* @param string $text
* @param string $separator
* @return string
*/
private static function postProcessText($text, $separator)
{
if (function_exists('mb_strtolower')) {
$text = mb_strtolower($text);
} else {
$text = strtolower($text);
}
// Remove all none word characters
$text = preg_replace('/\W/', ' ', $text);
// More stripping. Replace spaces with dashes
$text = strtolower(preg_replace('/[^A-Z^a-z^0-9^\/]+/', $separator,
preg_replace('/([a-z\d])([A-Z])/', '\1_\2',
preg_replace('/([A-Z]+)([A-Z][a-z])/', '\1_\2',
preg_replace('/::/', '/', $text)))));
return trim($text, $separator);
}
}
Raw
urlizer_test.php
<?php
$start = microtime (true);
require 'Urlizer.php';
use Gedmo\Sluggable\Util\Urlizer;
echo Urlizer::urlize (' J\'étudie le français ') . PHP_EOL;
echo Urlizer::urlize ('Lo siento, no hablo español.') . PHP_EOL;
echo Urlizer::urlize ('ΦΞΠΏΣ') . PHP_EOL;
echo microtime (true) - $start . PHP_EOL;
echo memory_get_peak_usage () . PHP_EOL;
?>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment