Created
January 15, 2014 10:39
-
-
Save mac2000/8434152 to your computer and use it in GitHub Desktop.
Speed tests for different slugify methods
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<?php | |
class PregReplaceSlugify | |
{ | |
public $rules = array( | |
'/º|°/' => 0, | |
'/¹/' => 1, | |
'/²/' => 2, | |
'/³/' => 3, | |
'/æ|ǽ|ä/' => 'ae', | |
'/œ|ö/' => 'oe', | |
'/À|Á|Â|Ã|Å|Ǻ|Ā|Ă|Ą|Ǎ|А/' => 'A', | |
'/à|á|â|ã|å|ǻ|ā|ă|ą|ǎ|ª|а/' => 'a', | |
'/@/' => 'at', | |
'/Б/' => 'B', | |
'/б/' => 'b', | |
'/Ç|Ć|Ĉ|Ċ|Č|Ц/' => 'C', | |
'/ç|ć|ĉ|ċ|č|ц/' => 'c', | |
'/Ð|Ď|Đ|Д/' => 'Dj', | |
'/ð|ď|đ|д/' => 'dj', | |
'/È|É|Ê|Ë|Ē|Ĕ|Ė|Ę|Ě|Е|Ё|Э/' => 'E', | |
'/è|é|ê|ë|ē|ĕ|ė|ę|ě|е|ё|э/' => 'e', | |
'/Ф/' => 'F', | |
'/ƒ|ф/' => 'f', | |
'/Ĝ|Ğ|Ġ|Ģ|Г|Ґ/' => 'G', | |
'/ĝ|ğ|ġ|ģ|г|ґ/' => 'g', | |
'/Ĥ|Ħ|Х/' => 'H', | |
'/ĥ|ħ|х/' => 'h', | |
'/Ì|Í|Î|Ï|Ĩ|Ī|Ĭ|Ǐ|Į|İ|И|І/' => 'I', | |
'/ì|í|î|ï|ĩ|ī|ĭ|ǐ|į|ı|и|і/' => 'i', | |
'/Ĵ|Й/' => 'J', | |
'/ĵ|й/' => 'j', | |
'/Ķ|К/' => 'K', | |
'/ķ|к/' => 'k', | |
'/Ĺ|Ļ|Ľ|Ŀ|Ł|Л/' => 'L', | |
'/ĺ|ļ|ľ|ŀ|ł|л/' => 'l', | |
'/М/' => 'M', | |
'/м/' => 'm', | |
'/Ñ|Ń|Ņ|Ň|Н/' => 'N', | |
'/ñ|ń|ņ|ň|ʼn|н/' => 'n', | |
'/Ò|Ó|Ô|Õ|Ō|Ŏ|Ǒ|Ő|Ơ|Ø|Ǿ|О/' => 'O', | |
'/ò|ó|ô|õ|ō|ŏ|ǒ|ő|ơ|ø|ǿ|º|о/' => 'o', | |
'/П/' => 'P', | |
'/п/' => 'p', | |
'/Ŕ|Ŗ|Ř|Р/' => 'R', | |
'/ŕ|ŗ|ř|р/' => 'r', | |
'/Ś|Ŝ|Ş|Ș|Š|С/' => 'S', | |
'/ś|ŝ|ş|ș|š|ſ|с/' => 's', | |
'/Ţ|Ț|Ť|Ŧ|Т/' => 'T', | |
'/ţ|ț|ť|ŧ|т/' => 't', | |
'/Ù|Ú|Û|Ũ|Ū|Ŭ|Ů|Ű|Ų|Ư|Ǔ|Ǖ|Ǘ|Ǚ|Ǜ|У/' => 'U', | |
'/ù|ú|û|ũ|ū|ŭ|ů|ű|ų|ư|ǔ|ǖ|ǘ|ǚ|ǜ|у/' => 'u', | |
'/ü/' => 'ue', | |
'/Ü/' => 'UE', | |
'/В/' => 'V', | |
'/в/' => 'v', | |
'/Ý|Ÿ|Ŷ|Ы/' => 'Y', | |
'/ý|ÿ|ŷ|ы/' => 'y', | |
'/Ŵ/' => 'W', | |
'/ŵ/' => 'w', | |
'/Ź|Ż|Ž|З/' => 'Z', | |
'/ź|ż|ž|з/' => 'z', | |
'/Æ|Ǽ|Ä/' => 'AE', | |
'/ß/' => 'ss', | |
'/IJ/' => 'IJ', | |
'/ij/' => 'ij', | |
'/Œ|Ö/' => 'OE', | |
'/Ч/' => 'Ch', | |
'/ч/' => 'ch', | |
'/Ю/' => 'Ju', | |
'/ю/' => 'ju', | |
'/Я/' => 'Ja', | |
'/я/' => 'ja', | |
'/Ш/' => 'Sh', | |
'/ш/' => 'sh', | |
'/Щ/' => 'Shch', | |
'/щ/' => 'shch', | |
'/Ж/' => 'Zh', | |
'/ж/' => 'zh', | |
'/ї/' => 'ji', | |
'/Ї/' => 'Ji', | |
); | |
public function replace($string, $separator = '-') | |
{ | |
$string = preg_replace(array_keys($this->rules), array_values($this->rules), $string); | |
$string = preg_replace('/([^a-z0-9]|-)+/usi', $separator, $string); | |
$string = strtolower($string); | |
return trim($string, $separator); | |
} | |
} | |
class StrTrSlugify | |
{ | |
public $rules = array( | |
'º'=>0, | |
'°'=>0, | |
'¹'=>1, | |
'²'=>2, | |
'³'=>3, | |
'æ'=>'ae', | |
'ǽ'=>'ae', | |
'ä'=>'ae', | |
'œ'=>'oe', | |
'ö'=>'oe', | |
'À'=>'A', | |
'Á'=>'A', | |
'Â'=>'A', | |
'Ã'=>'A', | |
'Å'=>'A', | |
'Ǻ'=>'A', | |
'Ā'=>'A', | |
'Ă'=>'A', | |
'Ą'=>'A', | |
'Ǎ'=>'A', | |
'А'=>'A', | |
'à'=>'a', | |
'á'=>'a', | |
'â'=>'a', | |
'ã'=>'a', | |
'å'=>'a', | |
'ǻ'=>'a', | |
'ā'=>'a', | |
'ă'=>'a', | |
'ą'=>'a', | |
'ǎ'=>'a', | |
'ª'=>'a', | |
'а'=>'a', | |
'@'=>'at', | |
'Б'=>'B', | |
'б'=>'b', | |
'Ç'=>'C', | |
'Ć'=>'C', | |
'Ĉ'=>'C', | |
'Ċ'=>'C', | |
'Č'=>'C', | |
'Ц'=>'C', | |
'ç'=>'c', | |
'ć'=>'c', | |
'ĉ'=>'c', | |
'ċ'=>'c', | |
'č'=>'c', | |
'ц'=>'c', | |
'Ð'=>'Dj', | |
'Ď'=>'Dj', | |
'Đ'=>'Dj', | |
'Д'=>'Dj', | |
'ð'=>'dj', | |
'ď'=>'dj', | |
'đ'=>'dj', | |
'д'=>'dj', | |
'È'=>'E', | |
'É'=>'E', | |
'Ê'=>'E', | |
'Ë'=>'E', | |
'Ē'=>'E', | |
'Ĕ'=>'E', | |
'Ė'=>'E', | |
'Ę'=>'E', | |
'Ě'=>'E', | |
'Е'=>'E', | |
'Ё'=>'E', | |
'Э'=>'E', | |
'è'=>'e', | |
'é'=>'e', | |
'ê'=>'e', | |
'ë'=>'e', | |
'ē'=>'e', | |
'ĕ'=>'e', | |
'ė'=>'e', | |
'ę'=>'e', | |
'ě'=>'e', | |
'е'=>'e', | |
'ё'=>'e', | |
'э'=>'e', | |
'Ф'=>'F', | |
'ƒ'=>'f', | |
'ф'=>'f', | |
'Ĝ'=>'G', | |
'Ğ'=>'G', | |
'Ġ'=>'G', | |
'Ģ'=>'G', | |
'Г'=>'G', | |
'Ґ'=>'G', | |
'ĝ'=>'g', | |
'ğ'=>'g', | |
'ġ'=>'g', | |
'ģ'=>'g', | |
'г'=>'g', | |
'ґ'=>'g', | |
'Ĥ'=>'H', | |
'Ħ'=>'H', | |
'Х'=>'H', | |
'ĥ'=>'h', | |
'ħ'=>'h', | |
'х'=>'h', | |
'Ì'=>'I', | |
'Í'=>'I', | |
'Î'=>'I', | |
'Ï'=>'I', | |
'Ĩ'=>'I', | |
'Ī'=>'I', | |
'Ĭ'=>'I', | |
'Ǐ'=>'I', | |
'Į'=>'I', | |
'İ'=>'I', | |
'И'=>'I', | |
'І'=>'I', | |
'ì'=>'i', | |
'í'=>'i', | |
'î'=>'i', | |
'ï'=>'i', | |
'ĩ'=>'i', | |
'ī'=>'i', | |
'ĭ'=>'i', | |
'ǐ'=>'i', | |
'į'=>'i', | |
'ı'=>'i', | |
'и'=>'i', | |
'і'=>'i', | |
'Ĵ'=>'J', | |
'Й'=>'J', | |
'ĵ'=>'j', | |
'й'=>'j', | |
'Ķ'=>'K', | |
'К'=>'K', | |
'ķ'=>'k', | |
'к'=>'k', | |
'Ĺ'=>'L', | |
'Ļ'=>'L', | |
'Ľ'=>'L', | |
'Ŀ'=>'L', | |
'Ł'=>'L', | |
'Л'=>'L', | |
'ĺ'=>'l', | |
'ļ'=>'l', | |
'ľ'=>'l', | |
'ŀ'=>'l', | |
'ł'=>'l', | |
'л'=>'l', | |
'М'=>'M', | |
'м'=>'m', | |
'Ñ'=>'N', | |
'Ń'=>'N', | |
'Ņ'=>'N', | |
'Ň'=>'N', | |
'Н'=>'N', | |
'ñ'=>'n', | |
'ń'=>'n', | |
'ņ'=>'n', | |
'ň'=>'n', | |
'ʼn'=>'n', | |
'н'=>'n', | |
'Ò'=>'O', | |
'Ó'=>'O', | |
'Ô'=>'O', | |
'Õ'=>'O', | |
'Ō'=>'O', | |
'Ŏ'=>'O', | |
'Ǒ'=>'O', | |
'Ő'=>'O', | |
'Ơ'=>'O', | |
'Ø'=>'O', | |
'Ǿ'=>'O', | |
'О'=>'O', | |
'ò'=>'o', | |
'ó'=>'o', | |
'ô'=>'o', | |
'õ'=>'o', | |
'ō'=>'o', | |
'ŏ'=>'o', | |
'ǒ'=>'o', | |
'ő'=>'o', | |
'ơ'=>'o', | |
'ø'=>'o', | |
'ǿ'=>'o', | |
'º'=>'o', | |
'о'=>'o', | |
'П'=>'P', | |
'п'=>'p', | |
'Ŕ'=>'R', | |
'Ŗ'=>'R', | |
'Ř'=>'R', | |
'Р'=>'R', | |
'ŕ'=>'r', | |
'ŗ'=>'r', | |
'ř'=>'r', | |
'р'=>'r', | |
'Ś'=>'S', | |
'Ŝ'=>'S', | |
'Ş'=>'S', | |
'Ș'=>'S', | |
'Š'=>'S', | |
'С'=>'S', | |
'ś'=>'s', | |
'ŝ'=>'s', | |
'ş'=>'s', | |
'ș'=>'s', | |
'š'=>'s', | |
'ſ'=>'s', | |
'с'=>'s', | |
'Ţ'=>'T', | |
'Ț'=>'T', | |
'Ť'=>'T', | |
'Ŧ'=>'T', | |
'Т'=>'T', | |
'ţ'=>'t', | |
'ț'=>'t', | |
'ť'=>'t', | |
'ŧ'=>'t', | |
'т'=>'t', | |
'Ù'=>'U', | |
'Ú'=>'U', | |
'Û'=>'U', | |
'Ũ'=>'U', | |
'Ū'=>'U', | |
'Ŭ'=>'U', | |
'Ů'=>'U', | |
'Ű'=>'U', | |
'Ų'=>'U', | |
'Ư'=>'U', | |
'Ǔ'=>'U', | |
'Ǖ'=>'U', | |
'Ǘ'=>'U', | |
'Ǚ'=>'U', | |
'Ǜ'=>'U', | |
'У'=>'U', | |
'ù'=>'u', | |
'ú'=>'u', | |
'û'=>'u', | |
'ũ'=>'u', | |
'ū'=>'u', | |
'ŭ'=>'u', | |
'ů'=>'u', | |
'ű'=>'u', | |
'ų'=>'u', | |
'ư'=>'u', | |
'ǔ'=>'u', | |
'ǖ'=>'u', | |
'ǘ'=>'u', | |
'ǚ'=>'u', | |
'ǜ'=>'u', | |
'у'=>'u', | |
'ü'=>'ue', | |
'Ü'=>'UE', | |
'В'=>'V', | |
'в'=>'v', | |
'Ý'=>'Y', | |
'Ÿ'=>'Y', | |
'Ŷ'=>'Y', | |
'Ы'=>'Y', | |
'ý'=>'y', | |
'ÿ'=>'y', | |
'ŷ'=>'y', | |
'ы'=>'y', | |
'Ŵ'=>'W', | |
'ŵ'=>'w', | |
'Ź'=>'Z', | |
'Ż'=>'Z', | |
'Ž'=>'Z', | |
'З'=>'Z', | |
'ź'=>'z', | |
'ż'=>'z', | |
'ž'=>'z', | |
'з'=>'z', | |
'Æ'=>'AE', | |
'Ǽ'=>'AE', | |
'Ä'=>'AE', | |
'ß'=>'ss', | |
'IJ'=>'IJ', | |
'ij'=>'ij', | |
'Œ'=>'OE', | |
'Ö'=>'OE', | |
'Ч'=>'Ch', | |
'ч'=>'ch', | |
'Ю'=>'Ju', | |
'ю'=>'ju', | |
'Я'=>'Ja', | |
'я'=>'ja', | |
'Ш'=>'Sh', | |
'ш'=>'sh', | |
'Щ'=>'Shch', | |
'щ'=>'shch', | |
'Ж'=>'Zh', | |
'ж'=>'zh', | |
'ї'=>'ji', | |
'Ї'=>'Ji', | |
); | |
public function replace($string, $separator = '-') | |
{ | |
$string = strtolower(strtr($string, $this->rules)); | |
$string = preg_replace('/([^a-z0-9]|-)+/usi', $separator, $string); | |
$string = strtolower($string); | |
return trim($string, $separator); | |
} | |
} | |
class TransliterateSlugify { | |
public $rules = 'Any-Latin; Latin-ASCII; NFD; NFC; Lower();'; | |
public function replace($string, $separator = '-') | |
{ | |
$string = transliterator_transliterate($this->rules, $string); | |
$string = preg_replace('/([^a-z0-9]|-)+/usi', $separator, $string); | |
return trim($string, $separator); | |
} | |
} | |
function test($o) { | |
$data = array( | |
array('Hello', 'hello'), | |
array('Hello World', 'hello-world'), | |
array('Привет мир', 'privet-mir'), | |
array('Привіт світ', 'privit-svit'), | |
array('Hello: World', 'hello-world'), | |
array('H+e#l1l--o/W§o r.l:d)', 'h-e-l1l-o-w-o-r-l-d'), | |
array(': World', 'world'), | |
array('Hello World!', 'hello-world'), | |
array('Ä ä Ö ö Ü ü ß', 'ae-ae-oe-oe-ue-ue-ss'), | |
array('Á À á à É È é è Ó Ò ó ò Ñ ñ Ú Ù ú ù', 'a-a-a-a-e-e-e-e-o-o-o-o-n-n-u-u-u-u'), | |
array('Â â Ê ê Ô ô Û û', 'a-a-e-e-o-o-u-u'), | |
array('Â â Ê ê Ô ô Û 1', 'a-a-e-e-o-o-u-1'), | |
array('°¹²³@','0123at'), | |
array('Mórë thån wørds', 'more-than-words'), | |
array('Блоґ їжачка', 'blog-izacka'), | |
array('Lorem ipsum dolor sit amet, consectetur adipisicing elit. Officia magni distinctio quasi doloribus mollitia aut atque pariatur nobis. Quos, eveniet a harum sit ipsam quibusdam iusto sapiente at quia maxime.', 'Lorem ipsum dolor sit amet, consectetur adipisicing elit. Officia magni distinctio quasi doloribus mollitia aut atque pariatur nobis. Quos, eveniet a harum sit ipsam quibusdam iusto sapiente at quia maxime.') | |
); | |
$before = microtime(true); | |
for($i=0; $i<1000;$i++) { | |
foreach($data as $item) { | |
$o->replace($item[0]); | |
} | |
} | |
$after = microtime(true); | |
echo sprintf( | |
'%20s: %.4f sec' . PHP_EOL, | |
get_class($o), | |
($after-$before)/$i | |
); | |
} | |
test(new PregReplaceSlugify()); | |
test(new StrTrSlugify()); | |
test(new TransliterateSlugify()); | |
// PregReplaceSlugify: 0.0052 sec | |
// StrTrSlugify: 0.0021 sec | |
//TransliterateSlugify: 0.0031 sec |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment