/**
* Changes a string into a URL-friendly string
*
* @param string $string The string to convert
* @param integer $max_length The maximum length of the friendly URL
* @param string $delimiter The delimiter to use between words, defaults to `_`
* @param string |$string
* @param string |$delimiter
* @return string The URL-friendly version of the string
*/
public static function makeFriendly($string, $max_length = NULL, $delimiter = NULL)
{
// This allows omitting the max length, but including a delimiter
if ($max_length && !is_numeric($max_length)) {
$delimiter = $max_length;
$max_length = NULL;
}
$string = fHTML::decode(fUTF8::ascii($string));
$string = strtolower(trim($string));
$string = str_replace("'", '', $string);
if (!strlen($delimiter)) {
$delimiter = '_';
}
$delimiter_replacement = strtr($delimiter, array('\\' => '\\\\', '$' => '\\$'));
$delimiter_regex = preg_quote($delimiter, '#');
$string = preg_replace('#[^a-z0-9\\-_]+#', $delimiter_replacement, $string);
$string = preg_replace('#' . $delimiter_regex . '{2,}#', $delimiter_replacement, $string);
$string = preg_replace('#_-_#', '-', $string);
$string = preg_replace('#(^' . $delimiter_regex . '+|' . $delimiter_regex . '+$)#D', '', $string);
$length = strlen($string);
if ($max_length && $length > $max_length) {
$last_pos = strrpos($string, $delimiter, ($length - $max_length - 1) * -1);
if ($last_pos < ceil($max_length / 2)) {
$last_pos = $max_length;
}
$string = substr($string, 0, $last_pos);
}
return $string;
}
/**
* Changes a string into a URL-friendly string
*
* @param string $string The string to convert
* @return void
*/
public static function makeFriendly($string)
{
$string = fHTML::decode(fUTF8::ascii($string));
$string = strtolower(trim($string));
$string = str_replace("'", '', $string);
$string = preg_replace('#[^a-z0-9\\-]+#', '_', $string);
$string = preg_replace('#_{2,}#', '_', $string);
$string = preg_replace('#_-_#', '-', $string);
return preg_replace('#(^_+|_+$)#D', '', $string);
}
/**
* Uses the Porter Stemming algorithm to create the stem of a word, which is useful for searching
*
* See http://tartarus.org/~martin/PorterStemmer/ for details about the
* algorithm.
*
* @param string $word The word to get the stem of
* @return string The stem of the word
*/
public static function stem($word)
{
$s_v = '^([^aeiou][^aeiouy]*)?[aeiouy]';
$mgr0 = $s_v . '[aeiou]*[^aeiou][^aeiouy]*';
$s_v_regex = '#' . $s_v . '#';
$mgr0_regex = '#' . $mgr0 . '#';
$meq1_regex = '#' . $mgr0 . '([aeiouy][aeiou]*)?$#';
$mgr1_regex = '#' . $mgr0 . '[aeiouy][aeiou]*[^aeiou][^aeiouy]*#';
$word = fUTF8::ascii($word);
$word = strtolower($word);
if (strlen($word) < 3) {
return $word;
}
if ($word[0] == 'y') {
$word = 'Y' . substr($word, 1);
}
// Step 1a
$word = preg_replace('#^(.+?)(?:(ss|i)es|([^s])s)$#', '\\1\\2\\3', $word);
// Step 1b
if (preg_match('#^(.+?)eed$#', $word, $match)) {
if (preg_match($mgr0_regex, $match[1])) {
$word = substr($word, 0, -1);
}
} elseif (preg_match('#^(.+?)(ed|ing)$#', $word, $match)) {
if (preg_match($s_v_regex, $match[1])) {
$word = $match[1];
if (preg_match('#(at|bl|iz)$#', $word)) {
$word .= 'e';
} elseif (preg_match('#([^aeiouylsz])\\1$#', $word)) {
$word = substr($word, 0, -1);
} elseif (preg_match('#^[^aeiou][^aeiouy]*[aeiouy][^aeiouwxy]$#', $word)) {
$word .= 'e';
}
}
}
// Step 1c
if (substr($word, -1) == 'y') {
$stem = substr($word, 0, -1);
if (preg_match($s_v_regex, $stem)) {
$word = $stem . 'i';
}
}
// Step 2
if (preg_match('#^(.+?)(ational|tional|enci|anci|izer|bli|alli|entli|eli|ousli|ization|ation|ator|alism|iveness|fulness|ousness|aliti|iviti|biliti|logi)$#', $word, $match)) {
if (preg_match($mgr0_regex, $match[1])) {
$word = $match[1] . strtr($match[2], array('ational' => 'ate', 'tional' => 'tion', 'enci' => 'ence', 'anci' => 'ance', 'izer' => 'ize', 'bli' => 'ble', 'alli' => 'al', 'entli' => 'ent', 'eli' => 'e', 'ousli' => 'ous', 'ization' => 'ize', 'ation' => 'ate', 'ator' => 'ate', 'alism' => 'al', 'iveness' => 'ive', 'fulness' => 'ful', 'ousness' => 'ous', 'aliti' => 'al', 'iviti' => 'ive', 'biliti' => 'ble', 'logi' => 'log'));
}
}
// Step 3
if (preg_match('#^(.+?)(icate|ative|alize|iciti|ical|ful|ness)$#', $word, $match)) {
if (preg_match($mgr0_regex, $match[1])) {
$word = $match[1] . strtr($match[2], array('icate' => 'ic', 'ative' => '', 'alize' => 'al', 'iciti' => 'ic', 'ical' => 'ic', 'ful' => '', 'ness' => ''));
}
}
// Step 4
if (preg_match('#^(.+?)(al|ance|ence|er|ic|able|ible|ant|ement|ment|ent|ou|ism|ate|iti|ous|ive|ize|(?<=[st])ion)$#', $word, $match) && preg_match($mgr1_regex, $match[1])) {
$word = $match[1];
}
// Step 5
if (substr($word, -1) == 'e') {
$stem = substr($word, 0, -1);
if (preg_match($mgr1_regex, $stem)) {
$word = $stem;
} elseif (preg_match($meq1_regex, $stem) && !preg_match('#^[^aeiou][^aeiouy]*[aeiouy][^aeiouwxy]$#', $stem)) {
$word = $stem;
}
}
if (preg_match('#ll$#', $word) && preg_match($mgr1_regex, $word)) {
$word = substr($word, 0, -1);
}
if ($word[0] == 'Y') {
$word = 'y' . substr($word, 1);
}
return $word;
}
/**
* Changes a string into a URL-friendly string
*
* @param string $string The string to convert
* @param interger $max_length The maximum length of the friendly URL
* @return string The URL-friendly version of the string
*/
public static function makeFriendly($string, $max_length = NULL)
{
$string = fHTML::decode(fUTF8::ascii($string));
$string = strtolower(trim($string));
$string = str_replace("'", '', $string);
$string = preg_replace('#[^a-z0-9\\-]+#', '_', $string);
$string = preg_replace('#_{2,}#', '_', $string);
$string = preg_replace('#_-_#', '-', $string);
$string = preg_replace('#(^_+|_+$)#D', '', $string);
$length = strlen($string);
if ($max_length && $length > $max_length) {
$last_pos = strrpos($string, '_', ($length - $max_length - 1) * -1);
if ($last_pos < ceil($max_length / 2)) {
$last_pos = $max_length;
}
$string = substr($string, 0, $last_pos);
}
return $string;
}
