/usr/share/php/Horde/Text/Filter/Linkurls.php is in php-horde-text-filter 2.2.0-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 | <?php
/**
* The Horde_Text_Filter_Linkurls:: class turns all URLs in the text into
* hyperlinks. The regex used is adapted from John Gruber's:
* http://daringfireball.net/2010/07/improved_regex_for_matching_urls
*
* Changes:
* - Require at least one slash after the protocol. Horde's other filters
* don't expect us to match mailto: as part of these filters, so don't.
* - Limit the URL protocol to 20 characters to avoid PCRE problems.
* - Allow "+" characters in URL protocols (like svn+ssh://).
*
* Parameters:
* - callback: (string) A callback function that the URL is passed through
* before being set as the href attribute. Must be a string
* with the function name, the function must take the original
* URL as the first and only parameter.
* DEFAULT: No callback
* - class: (string) The CSS class of the generated links.
* DEFAULT: none
* - encode: (boolean) Whether to escape special HTML characters in the
* URLs and finally "encode" the complete tag so that it can be
* decoded later with the decode() method. This is useful if you
* want to run htmlspecialchars() or similar *after* using this
* filter.
* DEFAULT: false
* - nofollow: (boolean) Whether to set the 'rel="nofollow"' attribute on
* links.
* DEFAULT: false
* - target: (string) The link target.
* DEFAULT: '_blank'
*
* Copyright 2003-2013 Horde LLC (http://www.horde.org/)
*
* See the enclosed file COPYING for license information (LGPL). If you
* did not receive this file, see http://www.horde.org/licenses/lgpl21.
*
* @author Tyler Colbert <tyler@colberts.us>
* @author Jan Schneider <jan@horde.org>
* @author Chuck Hagenbuch <chuck@horde.org>
* @category Horde
* @license http://www.horde.org/licenses/lgpl21 LGPL 2.1
* @package Text_Filter
*/
class Horde_Text_Filter_Linkurls extends Horde_Text_Filter_Base
{
/**
* Link-finding regex
*/
public static $regex = '';
/**
* Filter parameters.
*
* @var array
*/
protected $_params = array(
'callback' => null,
'class' => '',
'encode' => false,
'nofollow' => false,
'target' => '_blank',
);
/**
* Return the regex used to search for links.
*
* @return string The regex string.
*/
public static function getRegex()
{
if (!self::$regex) {
self::initializeRegex();
}
return self::$regex;
}
/**
* Initialize the regex for this instance.
*/
public static function initializeRegex()
{
self::$regex = <<<END_OF_REGEX
(?xi)
(?:\b|^)
( # Capture 1: entire matched URL
(
(?:[a-z][\w-+]{0,19})?:/{1,3} # URL protocol and colon followed by 1-3
# slashes, or just colon and slashes (://)
| # - or -
(?<!\.)www\d{0,3}\. # "www.", "www1.", "www2." … "www999."
# without a leading period
| # - or -
[a-z0-9.\-]+\.[a-z]{2,4}/ # looks like domain name followed by a slash
)
(?: # One or more:
[^\s()<>\[\]]+ # Run of non-space, non-()<>
(?<![\s`!()\[\]{};:\'".,<>?«»“”‘’]{2}) # that is not followed by two or more
# punct chars that indicate end-of-url
| # - or -
\(([^\s()<>]+|(\([^\s()<>]+\)))*\) # balanced parens, up to 2 levels
)+
(?: # End with:
\(([^\s()<>]+|(\([^\s()<>]+\)))*\) # balanced parens, up to 2 levels
| # - or -
[^\s`!()\[\]{};:\'".,<>?«»“”‘’] # not a space or one of these punct
# chars
)
)
END_OF_REGEX;
}
/**
* Returns a hash with replace patterns.
*
* @return array Patterns hash.
*/
public function getPatterns()
{
return array(
'regexp_callback' => array('@' . self::getRegex() . '@' => array($this, 'callback'))
);
}
/**
*/
public function callback($match)
{
$href = $match[0];
if (strpos($match[2], ':') === false) {
$href = 'http://' . $href;
}
if ($this->_params['callback']) {
$href = call_user_func($this->_params['callback'], $href);
}
$href = htmlspecialchars($href);
$class = $this->_params['class'];
if (!empty($class)) {
$class = ' class="' . $class . '"';
}
$target = $this->_params['target'];
if (!empty($target)) {
$target = ' target="' . $target . '"';
}
$replacement = '<a href="' . $href . '"' .
($this->_params['nofollow'] ? ' rel="nofollow"' : '') .
$target . $class .
'>' . htmlspecialchars($match[0]) . '</a>';
if (!empty($this->_params['noprefetch'])) {
$replacement = '<meta http-equiv="x-dns-prefetch-control" value="off" />' .
$replacement .
'<meta http-equiv="x-dns-prefetch-control" value="on" />';
}
if ($this->_params['encode']) {
$replacement = chr(0) . chr(0) . chr(0) . base64_encode($replacement) . chr(0) . chr(0) . chr(0);
}
return $replacement;
}
/**
* "Decodes" the text formerly encoded by using the "encode" parameter.
*
* @param string $text An encoded text.
*
* @return string The decoded text.
*/
static public function decode($text)
{
return preg_replace_callback(
'/\00\00\00([\w=+\/]*)\00\00\00/',
function($hex) {
return base64_decode($hex[1]);
},
$text);
}
}
|