/**
* Convert a phrase to a URL-safe title.
*
* echo URL::title('My Blog Post'); // "my-blog-post"
*
* @param string $title Phrase to convert
* @param string $separator Word separator (any single character)
* @param boolean $ascii_only Transliterate to ASCII?
* @return string
* @uses UTF8::transliterate_to_ascii
*/
public function title($title, $separator = '-', $ascii_only = FALSE)
{
if ($ascii_only === TRUE) {
// Transliterate non-ASCII characters
$title = UTF8::transliterate_to_ascii($title);
// Remove all characters that are not the separator, a-z, 0-9, or whitespace
$title = preg_replace('![^' . preg_quote($separator) . 'a-z0-9\\s]+!', '', strtolower($title));
} else {
// Remove all characters that are not the separator, letters, numbers, or whitespace
$title = preg_replace('![^' . preg_quote($separator) . '\\pL\\pN\\s]+!u', '', UTF8::strtolower($title));
}
// Replace all separator characters and whitespace by a single separator
$title = preg_replace('![' . preg_quote($separator) . '\\s]+!u', $separator, $title);
// Trim separators from the beginning and end
return trim($title, $separator);
}
/**
* Replaces the given words with a string.
*
* // Displays "What the #####, man!"
* echo Text::censor('What the frick, man!', array(
* 'frick' => '#####',
* ));
*
* @param string $str phrase to replace words in
* @param array $badwords words to replace
* @param string $replacement replacement string
* @param boolean $replace_partial_words replace words across word boundaries (space, period, etc)
* @return string
* @uses UTF8::strlen
*/
public static function censor($str, $badwords, $replacement = '#', $replace_partial_words = TRUE)
{
foreach ((array) $badwords as $key => $badword) {
$badwords[$key] = str_replace('\\*', '\\S*?', preg_quote((string) $badword));
}
$regex = '(' . implode('|', $badwords) . ')';
if ($replace_partial_words === FALSE) {
// Just using \b isn't sufficient when we need to replace a badword that already contains word boundaries itself
$regex = '(?<=\\b|\\s|^)' . $regex . '(?=\\b|\\s|$)';
}
$regex = '!' . $regex . '!ui';
if (UTF8::strlen($replacement) == 1) {
$regex .= 'e';
return preg_replace($regex, 'str_repeat($replacement, UTF8::strlen(\'$1\'))', $str);
}
return preg_replace($regex, $replacement, $str);
}
/**
* Check an email address for correct format.
*
* @link http://www.iamcal.com/publish/articles/php/parsing_email/
* @link http://www.w3.org/Protocols/rfc822/
*
* @param string $email email address
* @param boolean $strict strict RFC compatibility
* @return boolean
*/
public static function email($email, $strict = FALSE)
{
if (UTF8::strlen($email) > 254) {
return FALSE;
}
if ($strict === TRUE) {
$qtext = '[^\\x0d\\x22\\x5c\\x80-\\xff]';
$dtext = '[^\\x0d\\x5b-\\x5d\\x80-\\xff]';
$atom = '[^\\x00-\\x20\\x22\\x28\\x29\\x2c\\x2e\\x3a-\\x3c\\x3e\\x40\\x5b-\\x5d\\x7f-\\xff]+';
$pair = '\\x5c[\\x00-\\x7f]';
$domain_literal = "\\x5b({$dtext}|{$pair})*\\x5d";
$quoted_string = "\\x22({$qtext}|{$pair})*\\x22";
$sub_domain = "({$atom}|{$domain_literal})";
$word = "({$atom}|{$quoted_string})";
$domain = "{$sub_domain}(\\x2e{$sub_domain})*";
$local_part = "{$word}(\\x2e{$word})*";
$expression = "/^{$local_part}\\x40{$domain}\$/D";
} else {
$expression = '/^[-_a-z0-9\'+*$^&%=~!?{}]++(?:\\.[-_a-z0-9\'+*$^&%=~!?{}]+)*+@(?:(?![-.])[-a-z0-9.]+(?<![-.])\\.[a-z]{2,6}|\\d{1,3}(?:\\.\\d{1,3}){3})$/iD';
}
return (bool) preg_match($expression, (string) $email);
}
