/**
* Regular expression to match HTML/XML attribute pairs within a tag.
* Allows some... latitude.
* Used in Sanitizer::fixTagAttributes and Sanitizer::decodeTagAttributes
* @return string
*/
static function getAttribsRegex()
{
if (self::$attribsRegex === null) {
$attribFirst = '[:A-Z_a-z0-9]';
$attrib = '[:A-Z_a-z-.0-9]';
$space = '[\\x09\\x0a\\x0d\\x20]';
self::$attribsRegex = "/(?:^|{$space})({$attribFirst}{$attrib}*)\n\t\t\t\t ({$space}*={$space}*\n\t\t\t\t\t(?:\n\t\t\t\t\t # The attribute value: quoted or alone\n\t\t\t\t\t \"([^<\"]*)(?:\"|\$)\n\t\t\t\t\t | '([^<']*)(?:'|\$)\n\t\t\t\t\t | ([a-zA-Z0-9!#\$%&()*,\\-.\\/:;<>?@[\\]^_`{|}~]+)\n\t\t\t\t\t)\n\t\t\t\t)?(?={$space}|\$)/sx";
}
return self::$attribsRegex;
}
/**
* Regular expression to match HTML/XML attribute pairs within a tag.
* Allows some... latitude. Based on,
* http://www.w3.org/TR/html5/syntax.html#before-attribute-value-state
* Used in Sanitizer::fixTagAttributes and Sanitizer::decodeTagAttributes
* @return string
*/
static function getAttribsRegex()
{
if (self::$attribsRegex === null) {
$attribFirst = '[:A-Z_a-z0-9]';
$attrib = '[:A-Z_a-z-.0-9]';
$space = '[\\x09\\x0a\\x0c\\x0d\\x20]';
self::$attribsRegex = "/(?:^|{$space})({$attribFirst}{$attrib}*)\n\t\t\t\t ({$space}*={$space}*\n\t\t\t\t\t(?:\n\t\t\t\t\t # The attribute value: quoted or alone\n\t\t\t\t\t \"([^\"]*)(?:\"|\$)\n\t\t\t\t\t | '([^']*)(?:'|\$)\n\t\t\t\t\t | (((?!{$space}|>).)*)\n\t\t\t\t\t)\n\t\t\t\t)?(?={$space}|\$)/sx";
}
return self::$attribsRegex;
}
/**
* Regular expression to match HTML/XML attribute pairs within a tag.
* Allows some... latitude.
* Used in Sanitizer::fixTagAttributes and Sanitizer::decodeTagAttributes
*/
static function getAttribsRegex()
{
if (self::$attribsRegex === null) {
$attribFirst = '[:A-Z_a-z0-9]';
$attrib = '[:A-Z_a-z-.0-9]';
$space = '[\\x09\\x0a\\x0d\\x20]';
self::$attribsRegex = "/(?:^|{$space})({$attribFirst}{$attrib}*)\n\t\t\t\t ({$space}*={$space}*\n\t\t\t\t\t(?:\n\t\t\t\t\t # The attribute value: quoted or alone\n\t\t\t\t\t \"([^<\"]*)\"\n\t\t\t\t\t | '([^<']*)'\n\t\t\t\t\t | ([a-zA-Z0-9!#\$%&()*,\\-.\\/:;<>?@[\\]^_`{|}~]+)\n\t\t\t\t\t | (\\#[0-9a-fA-F]+) # Technically wrong, but lots of\n\t\t\t\t\t\t\t\t\t\t # colors are specified like this.\n\t\t\t\t\t\t\t\t\t\t # We'll be normalizing it.\n\t\t\t\t\t)\n\t\t\t\t)?(?={$space}|\$)/sx";
}
return self::$attribsRegex;
}
/**
* Regular expression to match HTML/XML attribute pairs within a tag.
* Allows some... latitude.
* Used in Sanitizer::fixTagAttributes and Sanitizer::decodeTagAttributes
*/
static function getAttribsRegex() {
if ( self::$attribsRegex === null ) {
$attribFirst = '[:A-Z_a-z0-9]';
$attrib = '[:A-Z_a-z-.0-9]';
$space = '[\x09\x0a\x0d\x20]';
self::$attribsRegex =
"/(?:^|$space)({$attribFirst}{$attrib}*)
($space*=$space*
(?:
# The attribute value: quoted or alone
\"([^<\"]*)\"
| '([^<']*)'
| ([a-zA-Z0-9!#$%&()*,\\-.\\/:;<>?@[\\]^_`{|}~]+)
| (\#[0-9a-fA-F]+) # Technically wrong, but lots of
# colors are specified like this.
# We'll be normalizing it.
)
)?(?=$space|\$)/sx";
}
return self::$attribsRegex;
}
