* As well as ' which is only defined starting in XHTML1.
* @private
*/
- static $htmlEntities = array(
+ private static $htmlEntities = array(
'Aacute' => 193,
'aacute' => 225,
'Acirc' => 194,
/**
* Character entity aliases accepted by MediaWiki
*/
- static $htmlEntityAliases = array(
+ private static $htmlEntityAliases = array(
'רלמ' => 'rlm',
'رلم' => 'rlm',
);
/**
* Lazy-initialised attributes regex, see getAttribsRegex()
+ * @private
*/
- static $attribsRegex;
+ private static $attribsRegex;
/**
* Regular expression to match HTML/XML attribute pairs within a tag.
* removes HTML comments
* @private
* @param $text String
- * @param $processCallback Callback to do any variable or parameter replacements in HTML attribute values
+ * @param $processCallback Callback to do any variable or parameter
+ * replacements in HTML attribute values
* @param array $args for the processing callback
* @param array $extratags for any extra tags to include
* @param array $removetags for any tags (default or extra) to exclude
* @return string
*/
- static function removeHTMLtags( $text, $processCallback = null, $args = array(), $extratags = array(), $removetags = array() ) {
+ static function removeHTMLtags( $text, $processCallback = null,
+ $args = array(), $extratags = array(), $removetags = array()
+ ) {
global $wgUseTidy, $wgAllowMicrodataAttributes, $wgAllowImageTag;
static $htmlpairsStatic, $htmlsingle, $htmlsingleonly, $htmlnest, $tabletags,
$htmlnest = array( # Tags that can be nested--??
'table', 'tr', 'td', 'th', 'div', 'blockquote', 'ol', 'ul',
'li', 'dl', 'dt', 'dd', 'font', 'big', 'small', 'sub', 'sup', 'span',
- 'var', 'kbd', 'samp'
+ 'var', 'kbd', 'samp', 'em', 'strong', 'q', 'ruby', 'bdo'
);
$tabletags = array( # Can only appear inside table, we will close them
'td', 'th', 'tr',
while ( substr( $text, $spaceStart + $spaceLen, 1 ) === ' ' ) {
$spaceLen++;
}
- if ( substr( $text, $spaceStart, 1 ) === "\n" and substr( $text, $spaceStart + $spaceLen, 1 ) === "\n" ) {
+ if ( substr( $text, $spaceStart, 1 ) === "\n"
+ && substr( $text, $spaceStart + $spaceLen, 1 ) === "\n" ) {
# Remove the comment, leading and trailing
# spaces, and leave only one newline.
$text = substr_replace( $text, "\n", $spaceStart, $spaceLen + 1 );
# WAI-ARIA
# http://www.w3.org/TR/wai-aria/
- # http://www.whatwg.org/specs/web-apps/current-work/multipage/elements.html#wai-aria
+ # http://www.whatwg.org/html/elements.html#wai-aria
# For now we only support role="presentation" until we work out what roles should be
# usable by content and we ensure that our code explicitly rejects patterns that
# violate HTML5's ARIA restrictions.
continue;
}
- //RDFa and microdata properties allow URLs, URIs and/or CURIs. check them for sanity
- if ( $attribute === 'rel' || $attribute === 'rev' ||
- $attribute === 'about' || $attribute === 'property' || $attribute === 'resource' || #RDFa
- $attribute === 'datatype' || $attribute === 'typeof' || #RDFa
- $attribute === 'itemid' || $attribute === 'itemprop' || $attribute === 'itemref' || #HTML5 microdata
- $attribute === 'itemscope' || $attribute === 'itemtype' ) { #HTML5 microdata
-
+ // RDFa and microdata properties allow URLs, URIs and/or CURIs.
+ // Check them for sanity.
+ if ( $attribute === 'rel' || $attribute === 'rev'
+ # RDFa
+ || $attribute === 'about' || $attribute === 'property'
+ || $attribute === 'resource' || $attribute === 'datatype'
+ || $attribute === 'typeof'
+ # HTML5 microdata
+ || $attribute === 'itemid' || $attribute === 'itemprop'
+ || $attribute === 'itemref' || $attribute === 'itemscope'
+ || $attribute === 'itemtype'
+ ) {
//Paranoia. Allow "simple" values but suppress javascript
if ( preg_match( self::EVIL_URI_PATTERN, $value ) ) {
continue;
if ( $attribute === 'href' || $attribute === 'src' ) {
if ( !preg_match( $hrefExp, $value ) ) {
continue; //drop any href or src attributes not using an allowed protocol.
- //NOTE: this also drops all relative URLs
+ // NOTE: this also drops all relative URLs
}
}
/**
* Pick apart some CSS and check it for forbidden or unsafe structures.
* Returns a sanitized string. This sanitized string will have
- * character references and escape sequences decoded, and comments
- * stripped. If the input is just too evil, only a comment complaining
- * about evilness will be returned.
+ * character references and escape sequences decoded and comments
+ * stripped (unless it is itself one valid comment, in which case the value
+ * will be passed through). If the input is just too evil, only a comment
+ * complaining about evilness will be returned.
*
* Currently URL references, 'expression', 'tps' are forbidden.
*
$value = preg_replace_callback( $decodeRegex,
array( __CLASS__, 'cssDecodeCallback' ), $value );
- // Remove any comments; IE gets token splitting wrong
- // This must be done AFTER decoding character references and
- // escape sequences, because those steps can introduce comments
- // This step cannot introduce character references or escape
- // sequences, because it replaces comments with spaces rather
- // than removing them completely.
- $value = StringUtils::delimiterReplace( '/*', '*/', ' ', $value );
-
- // Remove anything after a comment-start token, to guard against
- // incorrect client implementations.
- $commentPos = strpos( $value, '/*' );
- if ( $commentPos !== false ) {
- $value = substr( $value, 0, $commentPos );
+ // Let the value through if it's nothing but a single comment, to
+ // allow other functions which may reject it to pass some error
+ // message through.
+ if ( !preg_match( '! ^ \s* /\* [^*\\/]* \*/ \s* $ !x', $value ) ) {
+ // Remove any comments; IE gets token splitting wrong
+ // This must be done AFTER decoding character references and
+ // escape sequences, because those steps can introduce comments
+ // This step cannot introduce character references or escape
+ // sequences, because it replaces comments with spaces rather
+ // than removing them completely.
+ $value = StringUtils::delimiterReplace( '/*', '*/', ' ', $value );
+
+ // Remove anything after a comment-start token, to guard against
+ // incorrect client implementations.
+ $commentPos = strpos( $value, '/*' );
+ if ( $commentPos !== false ) {
+ $value = substr( $value, 0, $commentPos );
+ }
}
// Reject problematic keywords and control characters
$decoded = Sanitizer::decodeTagAttributes( $text );
$stripped = Sanitizer::validateTagAttributes( $decoded, $element );
- $attribs = array();
- foreach ( $stripped as $attribute => $value ) {
- $encAttribute = htmlspecialchars( $attribute );
- $encValue = Sanitizer::safeEncodeAttribute( $value );
-
- $attribs[] = "$encAttribute=\"$encValue\"";
- }
- return count( $attribs ) ? ' ' . implode( ' ', $attribs ) : '';
+ return Sanitizer::safeEncodeTagAttributes( $stripped );
}
/**
* in the id and
* name attributes
* @see http://www.w3.org/TR/html401/struct/links.html#h-12.2.3 Anchors with the id attribute
- * @see http://www.whatwg.org/specs/web-apps/current-work/multipage/elements.html#the-id-attribute
+ * @see http://www.whatwg.org/html/elements.html#the-id-attribute
* HTML5 definition of id attribute
*
* @param string $id id to escape
return $attribs;
}
+ /**
+ * Build a partial tag string from an associative array of attribute
+ * names and values as returned by decodeTagAttributes.
+ *
+ * @param $assoc_array Array
+ * @return String
+ */
+ public static function safeEncodeTagAttributes( $assoc_array ) {
+ $attribs = array();
+ foreach ( $assoc_array as $attribute => $value ) {
+ $encAttribute = htmlspecialchars( $attribute );
+ $encValue = Sanitizer::safeEncodeAttribute( $value );
+
+ $attribs[] = "$encAttribute=\"$encValue\"";
+ }
+ return count( $attribs ) ? ' ' . implode( ' ', $attribs ) : '';
+ }
+
/**
* Pick the appropriate attribute value from a match set from the
* attribs regex matches.
);
if ( $wgAllowRdfaAttributes ) {
- #RDFa attributes as specified in section 9 of http://www.w3.org/TR/2008/REC-rdfa-syntax-20081014
+ # RDFa attributes as specified in section 9 of
+ # http://www.w3.org/TR/2008/REC-rdfa-syntax-20081014
$common = array_merge( $common, array(
'about', 'property', 'resource', 'datatype', 'typeof',
) );
}
if ( $wgAllowMicrodataAttributes ) {
- # add HTML5 microdata tags as specified by http://www.whatwg.org/specs/web-apps/current-work/multipage/microdata.html#the-microdata-model
+ # add HTML5 microdata tags as specified by
+ # http://www.whatwg.org/html/microdata.html#the-microdata-model
$common = array_merge( $common, array(
'itemid', 'itemprop', 'itemref', 'itemscope', 'itemtype'
) );
'td' => array_merge( $common, $tablecell, $tablealign ),
'th' => array_merge( $common, $tablecell, $tablealign ),
- # 12.2 # NOTE: <a> is not allowed directly, but the attrib whitelist is used from the Parser object
+ # 12.2
+ # NOTE: <a> is not allowed directly, but the attrib
+ # whitelist is used from the Parser object
'a' => array_merge( $common, array( 'href', 'rel', 'rev' ) ), # rel/rev esp. for RDFa
# 13.2
'hr' => array_merge( $common, array( 'noshade', 'size', 'width' ) ),
# HTML Ruby annotation text module, simple ruby only.
- # http://www.whatwg.org/specs/web-apps/current-work/multipage/text-level-semantics.html#the-ruby-element
+ # http://www.whatwg.org/html/text-level-semantics.html#the-ruby-element
'ruby' => $common,
# rbc
# rtc
'bdi' => $common,
# HTML5 elements, defined by:
- # http://www.whatwg.org/specs/web-apps/current-work/multipage/
+ # http://www.whatwg.org/html/
'data' => array_merge( $common, array( 'value' ) ),
'time' => array_merge( $common, array( 'datetime' ) ),
'mark' => $common,
* Does a string look like an e-mail address?
*
* This validates an email address using an HTML5 specification found at:
- * http://www.whatwg.org/specs/web-apps/current-work/multipage/states-of-the-type-attribute.html#valid-e-mail-address
+ * http://www.whatwg.org/html/states-of-the-type-attribute.html#valid-e-mail-address
* Which as of 2011-01-24 says:
*
* A valid e-mail address is a string that matches the ABNF production