/**
* Builds an attribute list from string containing attributes.
*
* This function does a lot of work. It parses an attribute list into an array
* with attribute data, and tries to do the right thing even if it gets weird
* input. It will add quotes around attribute values that don't have any quotes
* or apostrophes around them, to make it easier to produce HTML code that will
* conform to W3C's HTML specification. It will also remove bad URL protocols
* from attribute values. It also reduces duplicate attributes by using the
* attribute defined first (foo='bar' foo='baz' will result in foo='bar').
*
* @since 1.0.0
*
* @param string $attr Attribute list from HTML element to closing HTML element tag
* @param array $allowed_protocols Allowed protocols to keep
* @return array List of attributes after parsing
*/
function asc_kses_hair($attr, $allowed_protocols)
{
$attrarr = array();
$mode = 0;
$attrname = '';
$uris = array('xmlns', 'profile', 'href', 'src', 'cite', 'classid', 'codebase', 'data', 'usemap', 'longdesc', 'action');
# Loop through the whole attribute list
while (strlen($attr) != 0) {
$working = 0;
# Was the last operation successful?
switch ($mode) {
case 0:
# attribute name, href for instance
if (preg_match('/^([-a-zA-Z:]+)/', $attr, $match)) {
$attrname = $match[1];
$working = $mode = 1;
$attr = preg_replace('/^[-a-zA-Z:]+/', '', $attr);
}
break;
case 1:
# equals sign or valueless ("selected")
if (preg_match('/^\\s*=\\s*/', $attr)) {
$working = 1;
$mode = 2;
$attr = preg_replace('/^\\s*=\\s*/', '', $attr);
break;
}
if (preg_match('/^\\s+/', $attr)) {
$working = 1;
$mode = 0;
if (false === array_key_exists($attrname, $attrarr)) {
$attrarr[$attrname] = array('name' => $attrname, 'value' => '', 'whole' => $attrname, 'vless' => 'y');
}
$attr = preg_replace('/^\\s+/', '', $attr);
}
break;
case 2:
# attribute value, a URL after href= for instance
if (preg_match('%^"([^"]*)"(\\s+|/?$)%', $attr, $match)) {
$thisval = $match[1];
if (in_array(strtolower($attrname), $uris)) {
$thisval = asc_kses_bad_protocol($thisval, $allowed_protocols);
}
if (false === array_key_exists($attrname, $attrarr)) {
$attrarr[$attrname] = array('name' => $attrname, 'value' => $thisval, 'whole' => "{$attrname}=\"{$thisval}\"", 'vless' => 'n');
}
$working = 1;
$mode = 0;
$attr = preg_replace('/^"[^"]*"(\\s+|$)/', '', $attr);
break;
}
if (preg_match("%^'([^']*)'(\\s+|/?\$)%", $attr, $match)) {
$thisval = $match[1];
if (in_array(strtolower($attrname), $uris)) {
$thisval = asc_kses_bad_protocol($thisval, $allowed_protocols);
}
if (false === array_key_exists($attrname, $attrarr)) {
$attrarr[$attrname] = array('name' => $attrname, 'value' => $thisval, 'whole' => "{$attrname}='{$thisval}'", 'vless' => 'n');
}
$working = 1;
$mode = 0;
$attr = preg_replace("/^'[^']*'(\\s+|\$)/", '', $attr);
break;
}
if (preg_match("%^([^\\s\"']+)(\\s+|/?\$)%", $attr, $match)) {
$thisval = $match[1];
if (in_array(strtolower($attrname), $uris)) {
$thisval = asc_kses_bad_protocol($thisval, $allowed_protocols);
}
if (false === array_key_exists($attrname, $attrarr)) {
$attrarr[$attrname] = array('name' => $attrname, 'value' => $thisval, 'whole' => "{$attrname}=\"{$thisval}\"", 'vless' => 'n');
}
# We add quotes to conform to W3C's HTML spec.
$working = 1;
$mode = 0;
$attr = preg_replace("%^[^\\s\"']+(\\s+|\$)%", '', $attr);
}
break;
}
# switch
if ($working == 0) {
$attr = asc_kses_html_error($attr);
$mode = 0;
}
}
# while
if ($mode == 1 && false === array_key_exists($attrname, $attrarr)) {
# special case, for when the attribute list ends with a valueless
# attribute like "selected"
$attrarr[$attrname] = array('name' => $attrname, 'value' => '', 'whole' => $attrname, 'vless' => 'y');
}
return $attrarr;
}
/**
* Checks and cleans a URL.
*
* A number of characters are removed from the URL. If the URL is for displaying
* (the default behaviour) ampersands are also replaced. The 'clean_url' filter
* is applied to the returned cleaned URL.
*
* @since 2.8.0
* @uses asc_kses_bad_protocol() To only permit protocols in the URL set
* via $protocols or the common ones set in the function.
*
* @param string $url The URL to be cleaned.
* @param array $protocols Optional. An array of acceptable protocols.
* Defaults to 'http', 'https', 'ftp', 'ftps', 'mailto', 'news', 'irc', 'gopher', 'nntp', 'feed', 'telnet', 'mms', 'rtsp', 'svn' if not set.
* @param string $_context Private. Use esc_url_raw() for database usage.
* @return string The cleaned $url after the 'clean_url' filter is applied.
*/
function esc_url($url, $protocols = null, $_context = 'display')
{
$original_url = $url;
if ('' == $url) {
return $url;
}
$url = preg_replace('|[^a-z0-9-~+_.?#=!&;,/:%@$\\|*\'()\\x80-\\xff]|i', '', $url);
$strip = array('%0d', '%0a', '%0D', '%0A');
$url = _deep_replace($strip, $url);
$url = str_replace(';//', '://', $url);
/* If the URL doesn't appear to contain a scheme, we
* presume it needs http:// appended (unless a relative
* link starting with /, # or ? or a php file).
*/
if (strpos($url, ':') === false && !in_array($url[0], array('/', '#', '?')) && !preg_match('/^[a-z0-9-]+?\\.php/i', $url)) {
$url = 'http://' . $url;
}
// Replace ampersands and single quotes only when displaying.
if ('display' == $_context) {
$url = asc_kses_normalize_entities($url);
$url = str_replace('&', '&', $url);
$url = str_replace("'", ''', $url);
}
if ('/' === $url[0]) {
$good_protocol_url = $url;
} else {
if (!is_array($protocols)) {
$protocols = asc_allowed_protocols();
}
$good_protocol_url = asc_kses_bad_protocol($url, $protocols);
if (strtolower($good_protocol_url) != strtolower($url)) {
return '';
}
}
/**
* Filter a string cleaned and escaped for output as a URL.
*
* @since 2.3.0
*
* @param string $good_protocol_url The cleaned URL to be returned.
* @param string $original_url The URL prior to cleaning.
* @param string $_context If 'display', replace ampersands and single quotes only.
*/
return apply_filters('clean_url', $good_protocol_url, $original_url, $_context);
}
