1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071 |
- <?php
- /**
- * Validates contents based on NMTOKENS attribute type.
- */
- class HTMLPurifier_AttrDef_HTML_Nmtokens extends HTMLPurifier_AttrDef
- {
- /**
- * @param string $string
- * @param HTMLPurifier_Config $config
- * @param HTMLPurifier_Context $context
- * @return bool|string
- */
- public function validate($string, $config, $context)
- {
- $string = trim($string);
- // early abort: '' and '0' (strings that convert to false) are invalid
- if (!$string) {
- return false;
- }
- $tokens = $this->split($string, $config, $context);
- $tokens = $this->filter($tokens, $config, $context);
- if (empty($tokens)) {
- return false;
- }
- return implode(' ', $tokens);
- }
- /**
- * Splits a space separated list of tokens into its constituent parts.
- * @param string $string
- * @param HTMLPurifier_Config $config
- * @param HTMLPurifier_Context $context
- * @return array
- */
- protected function split($string, $config, $context)
- {
- // OPTIMIZABLE!
- // do the preg_match, capture all subpatterns for reformulation
- // we don't support U+00A1 and up codepoints or
- // escaping because I don't know how to do that with regexps
- // and plus it would complicate optimization efforts (you never
- // see that anyway).
- $pattern = '/(?:(?<=\s)|\A)' . // look behind for space or string start
- '((?:--|-?[A-Za-z_])[A-Za-z_\-0-9]*)' .
- '(?:(?=\s)|\z)/'; // look ahead for space or string end
- preg_match_all($pattern, $string, $matches);
- return $matches[1];
- }
- /**
- * Template method for removing certain tokens based on arbitrary criteria.
- * @note If we wanted to be really functional, we'd do an array_filter
- * with a callback. But... we're not.
- * @param array $tokens
- * @param HTMLPurifier_Config $config
- * @param HTMLPurifier_Context $context
- * @return array
- */
- protected function filter($tokens, $config, $context)
- {
- return $tokens;
- }
- }
- // vim: et sw=4 sts=4
|