2010-09-08 23:14:17 -04:00
|
|
|
<?php
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Base class for all validating attribute definitions.
|
|
|
|
*
|
|
|
|
* This family of classes forms the core for not only HTML attribute validation,
|
|
|
|
* but also any sort of string that needs to be validated or cleaned (which
|
|
|
|
* means CSS properties and composite definitions are defined here too).
|
|
|
|
* Besides defining (through code) what precisely makes the string valid,
|
|
|
|
* subclasses are also responsible for cleaning the code if possible.
|
|
|
|
*/
|
|
|
|
|
|
|
|
abstract class HTMLPurifier_AttrDef
|
|
|
|
{
|
|
|
|
|
|
|
|
/**
|
2016-02-09 05:06:17 -05:00
|
|
|
* Tells us whether or not an HTML attribute is minimized.
|
|
|
|
* Has no meaning in other contexts.
|
|
|
|
* @type bool
|
2010-09-08 23:14:17 -04:00
|
|
|
*/
|
|
|
|
public $minimized = false;
|
|
|
|
|
|
|
|
/**
|
2016-02-09 05:06:17 -05:00
|
|
|
* Tells us whether or not an HTML attribute is required.
|
|
|
|
* Has no meaning in other contexts
|
|
|
|
* @type bool
|
2010-09-08 23:14:17 -04:00
|
|
|
*/
|
|
|
|
public $required = false;
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Validates and cleans passed string according to a definition.
|
|
|
|
*
|
2016-02-09 05:06:17 -05:00
|
|
|
* @param string $string String to be validated and cleaned.
|
|
|
|
* @param HTMLPurifier_Config $config Mandatory HTMLPurifier_Config object.
|
|
|
|
* @param HTMLPurifier_Context $context Mandatory HTMLPurifier_Context object.
|
2010-09-08 23:14:17 -04:00
|
|
|
*/
|
|
|
|
abstract public function validate($string, $config, $context);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Convenience method that parses a string as if it were CDATA.
|
|
|
|
*
|
|
|
|
* This method process a string in the manner specified at
|
|
|
|
* <http://www.w3.org/TR/html4/types.html#h-6.2> by removing
|
|
|
|
* leading and trailing whitespace, ignoring line feeds, and replacing
|
|
|
|
* carriage returns and tabs with spaces. While most useful for HTML
|
|
|
|
* attributes specified as CDATA, it can also be applied to most CSS
|
|
|
|
* values.
|
|
|
|
*
|
|
|
|
* @note This method is not entirely standards compliant, as trim() removes
|
|
|
|
* more types of whitespace than specified in the spec. In practice,
|
|
|
|
* this is rarely a problem, as those extra characters usually have
|
|
|
|
* already been removed by HTMLPurifier_Encoder.
|
|
|
|
*
|
|
|
|
* @warning This processing is inconsistent with XML's whitespace handling
|
|
|
|
* as specified by section 3.3.3 and referenced XHTML 1.0 section
|
|
|
|
* 4.7. However, note that we are NOT necessarily
|
|
|
|
* parsing XML, thus, this behavior may still be correct. We
|
|
|
|
* assume that newlines have been normalized.
|
|
|
|
*/
|
2016-02-09 05:06:17 -05:00
|
|
|
public function parseCDATA($string)
|
|
|
|
{
|
2010-09-08 23:14:17 -04:00
|
|
|
$string = trim($string);
|
|
|
|
$string = str_replace(array("\n", "\t", "\r"), ' ', $string);
|
|
|
|
return $string;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Factory method for creating this class from a string.
|
2016-02-09 05:06:17 -05:00
|
|
|
* @param string $string String construction info
|
|
|
|
* @return HTMLPurifier_AttrDef Created AttrDef object corresponding to $string
|
2010-09-08 23:14:17 -04:00
|
|
|
*/
|
2016-02-09 05:06:17 -05:00
|
|
|
public function make($string)
|
|
|
|
{
|
2010-09-08 23:14:17 -04:00
|
|
|
// default implementation, return a flyweight of this object.
|
|
|
|
// If $string has an effect on the returned object (i.e. you
|
|
|
|
// need to overload this method), it is best
|
|
|
|
// to clone or instantiate new copies. (Instantiation is safer.)
|
|
|
|
return $this;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Removes spaces from rgb(0, 0, 0) so that shorthand CSS properties work
|
|
|
|
* properly. THIS IS A HACK!
|
2016-02-09 05:06:17 -05:00
|
|
|
* @param string $string a CSS colour definition
|
|
|
|
* @return string
|
2010-09-08 23:14:17 -04:00
|
|
|
*/
|
2016-02-09 05:06:17 -05:00
|
|
|
protected function mungeRgb($string)
|
|
|
|
{
|
2010-09-08 23:14:17 -04:00
|
|
|
return preg_replace('/rgb\((\d+)\s*,\s*(\d+)\s*,\s*(\d+)\)/', 'rgb(\1,\2,\3)', $string);
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
2016-02-09 05:06:17 -05:00
|
|
|
* Parses a possibly escaped CSS string and returns the "pure"
|
2010-09-08 23:14:17 -04:00
|
|
|
* version of it.
|
|
|
|
*/
|
2016-02-09 05:06:17 -05:00
|
|
|
protected function expandCSSEscape($string)
|
|
|
|
{
|
2010-09-08 23:14:17 -04:00
|
|
|
// flexibly parse it
|
|
|
|
$ret = '';
|
|
|
|
for ($i = 0, $c = strlen($string); $i < $c; $i++) {
|
|
|
|
if ($string[$i] === '\\') {
|
|
|
|
$i++;
|
|
|
|
if ($i >= $c) {
|
|
|
|
$ret .= '\\';
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
if (ctype_xdigit($string[$i])) {
|
|
|
|
$code = $string[$i];
|
|
|
|
for ($a = 1, $i++; $i < $c && $a < 6; $i++, $a++) {
|
2016-02-09 05:06:17 -05:00
|
|
|
if (!ctype_xdigit($string[$i])) {
|
|
|
|
break;
|
|
|
|
}
|
2010-09-08 23:14:17 -04:00
|
|
|
$code .= $string[$i];
|
|
|
|
}
|
|
|
|
// We have to be extremely careful when adding
|
|
|
|
// new characters, to make sure we're not breaking
|
|
|
|
// the encoding.
|
|
|
|
$char = HTMLPurifier_Encoder::unichr(hexdec($code));
|
2016-02-09 05:06:17 -05:00
|
|
|
if (HTMLPurifier_Encoder::cleanUTF8($char) === '') {
|
|
|
|
continue;
|
|
|
|
}
|
2010-09-08 23:14:17 -04:00
|
|
|
$ret .= $char;
|
2016-02-09 05:06:17 -05:00
|
|
|
if ($i < $c && trim($string[$i]) !== '') {
|
|
|
|
$i--;
|
|
|
|
}
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
if ($string[$i] === "\n") {
|
2010-09-08 23:14:17 -04:00
|
|
|
continue;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
$ret .= $string[$i];
|
|
|
|
}
|
|
|
|
return $ret;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
// vim: et sw=4 sts=4
|