From 3413fe6bfd423d45d083ff4ed62c0f72c2cc272f Mon Sep 17 00:00:00 2001 From: Bharat Mediratta Date: Thu, 28 May 2009 06:11:53 +0800 Subject: Rename 'kohana' to 'system' to conform to the Kohana filesystem layout. I'm comfortable with us not clearly drawing the distinction about the fact that it's Kohana. Signed-off-by: Gallery Role Account --- system/helpers/text.php | 410 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 410 insertions(+) create mode 100644 system/helpers/text.php (limited to 'system/helpers/text.php') diff --git a/system/helpers/text.php b/system/helpers/text.php new file mode 100644 index 00000000..d0e573ec --- /dev/null +++ b/system/helpers/text.php @@ -0,0 +1,410 @@ + 1) + { + if (ctype_alpha($str)) + { + // Add a random digit + $str[mt_rand(0, $length - 1)] = chr(mt_rand(48, 57)); + } + elseif (ctype_digit($str)) + { + // Add a random letter + $str[mt_rand(0, $length - 1)] = chr(mt_rand(65, 90)); + } + } + + return $str; + } + + /** + * Reduces multiple slashes in a string to single slashes. + * + * @param string string to reduce slashes of + * @return string + */ + public static function reduce_slashes($str) + { + return preg_replace('#(? $badword) + { + $badwords[$key] = str_replace('\*', '\S*?', preg_quote((string) $badword)); + } + + $regex = '('.implode('|', $badwords).')'; + + if ($replace_partial_words == TRUE) + { + // 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); + } + + /** + * Finds the text that is similar between a set of words. + * + * @param array words to find similar text of + * @return string + */ + public static function similar(array $words) + { + // First word is the word to match against + $word = current($words); + + for ($i = 0, $max = strlen($word); $i < $max; ++$i) + { + foreach ($words as $w) + { + // Once a difference is found, break out of the loops + if ( ! isset($w[$i]) OR $w[$i] !== $word[$i]) + break 2; + } + } + + // Return the similar text + return substr($word, 0, $i); + } + + /** + * Converts text email addresses and anchors into links. + * + * @param string text to auto link + * @return string + */ + public static function auto_link($text) + { + // Auto link emails first to prevent problems with "www.domain.com@example.com" + return text::auto_link_urls(text::auto_link_emails($text)); + } + + /** + * Converts text anchors into links. + * + * @param string text to auto link + * @return string + */ + public static function auto_link_urls($text) + { + // Finds all http/https/ftp/ftps links that are not part of an existing html anchor + if (preg_match_all('~\b(?)(?:ht|f)tps?://\S+(?:/|\b)~i', $text, $matches)) + { + foreach ($matches[0] as $match) + { + // Replace each link with an anchor + $text = str_replace($match, html::anchor($match), $text); + } + } + + // Find all naked www.links.com (without http://) + if (preg_match_all('~\b(?|58;)(?!\.)[-+_a-z0-9.]++(? and
markup to text. Basically nl2br() on steroids. + * + * @param string subject + * @return string + */ + public static function auto_p($str) + { + // Trim whitespace + if (($str = trim($str)) === '') + return ''; + + // Standardize newlines + $str = str_replace(array("\r\n", "\r"), "\n", $str); + + // Trim whitespace on each line + $str = preg_replace('~^[ \t]+~m', '', $str); + $str = preg_replace('~[ \t]+$~m', '', $str); + + // The following regexes only need to be executed if the string contains html + if ($html_found = (strpos($str, '<') !== FALSE)) + { + // Elements that should not be surrounded by p tags + $no_p = '(?:p|div|h[1-6r]|ul|ol|li|blockquote|d[dlt]|pre|t[dhr]|t(?:able|body|foot|head)|c(?:aption|olgroup)|form|s(?:elect|tyle)|a(?:ddress|rea)|ma(?:p|th))'; + + // Put at least two linebreaks before and after $no_p elements + $str = preg_replace('~^<'.$no_p.'[^>]*+>~im', "\n$0", $str); + $str = preg_replace('~$~im', "$0\n", $str); + } + + // Do the

magic! + $str = '

'.trim($str).'

'; + $str = preg_replace('~\n{2,}~', "

\n\n

", $str); + + // The following regexes only need to be executed if the string contains html + if ($html_found !== FALSE) + { + // Remove p tags around $no_p elements + $str = preg_replace('~

(?=]*+>)~i', '', $str); + $str = preg_replace('~(]*+>)

~i', '$1', $str); + } + + // Convert single linebreaks to
+ $str = preg_replace('~(?\n", $str); + + return $str; + } + + /** + * Returns human readable sizes. + * @see Based on original functions written by: + * @see Aidan Lister: http://aidanlister.com/repos/v/function.size_readable.php + * @see Quentin Zervaas: http://www.phpriot.com/d/code/strings/filesize-format/ + * + * @param integer size in bytes + * @param string a definitive unit + * @param string the return string format + * @param boolean whether to use SI prefixes or IEC + * @return string + */ + public static function bytes($bytes, $force_unit = NULL, $format = NULL, $si = TRUE) + { + // Format string + $format = ($format === NULL) ? '%01.2f %s' : (string) $format; + + // IEC prefixes (binary) + if ($si == FALSE OR strpos($force_unit, 'i') !== FALSE) + { + $units = array('B', 'KiB', 'MiB', 'GiB', 'TiB', 'PiB'); + $mod = 1024; + } + // SI prefixes (decimal) + else + { + $units = array('B', 'kB', 'MB', 'GB', 'TB', 'PB'); + $mod = 1000; + } + + // Determine unit to use + if (($power = array_search((string) $force_unit, $units)) === FALSE) + { + $power = ($bytes > 0) ? floor(log($bytes, $mod)) : 0; + } + + return sprintf($format, $bytes / pow($mod, $power), $units[$power]); + } + + /** + * Prevents widow words by inserting a non-breaking space between the last two words. + * @see http://www.shauninman.com/archive/2006/08/22/widont_wordpress_plugin + * + * @param string string to remove widows from + * @return string + */ + public static function widont($str) + { + $str = rtrim($str); + $space = strrpos($str, ' '); + + if ($space !== FALSE) + { + $str = substr($str, 0, $space).' '.substr($str, $space + 1); + } + + return $str; + } + +} // End text \ No newline at end of file -- cgit v1.2.3