/**
* Some functions to help implement an external link filter for spam control.
*
- * TODO: implement the filter. Currently these are just some functions to help
+ * @todo implement the filter. Currently these are just some functions to help
* maintenance/cleanupSpam.php remove links to a single specified domain. The
* next thing is to implement functions for checking a given page against a big
* list of domains.
* Another cool thing to do would be a web interface for fast spam removal.
*/
class LinkFilter {
+
/**
- * @static
+ * Check whether $text contains a link to $filterEntry
+ *
+ * @param $text String: text to check
+ * @param $filterEntry String: domainparts, see makeRegex() for more details
+ * @return Integer: 0 if no match or 1 if there's at least one match
*/
static function matchEntry( $text, $filterEntry ) {
$regex = LinkFilter::makeRegex( $filterEntry );
}
/**
- * @static
+ * Builds a regex pattern for $filterEntry.
+ *
+ * @param $filterEntry String: URL, if it begins with "*.", it'll be
+ * replaced to match any subdomain
+ * @return String: regex pattern, for preg_match()
*/
private static function makeRegex( $filterEntry ) {
$regex = '!http://';
}
/**
- * Make a string to go after an SQL LIKE, which will match the specified
- * string. There are several kinds of filter entry:
+ * Make an array to be used for calls to DatabaseBase::buildLike(), which
+ * will match the specified string. There are several kinds of filter entry:
* *.domain.com - Produces http://com.domain.%, matches domain.com
* and www.domain.com
* domain.com - Produces http://com.domain./%, matches domain.com
* domain.com/xy but not www.domain.com/xy
*
* Asterisks in any other location are considered invalid.
- *
- * @static
+ *
* @param $filterEntry String: domainparts
* @param $prot String: protocol
+ * @return Array to be passed to DatabaseBase::buildLike() or false on error
*/
- public static function makeLike( $filterEntry , $prot = 'http://' ) {
+ public static function makeLikeArray( $filterEntry , $prot = 'http://' ) {
+ $db = wfGetDB( DB_MASTER );
if ( substr( $filterEntry, 0, 2 ) == '*.' ) {
$subdomains = true;
$filterEntry = substr( $filterEntry, 2 );
$mailparts = explode( '@', $host );
$domainpart = strtolower( implode( '.', array_reverse( explode( '.', $mailparts[1] ) ) ) );
$host = $domainpart . '@' . $mailparts[0];
- $like = "$prot$host%";
+ $like = array( "$prot$host", $db->anyString() );
} elseif ( $prot == 'mailto:' ) {
// domainpart of email adress only. do not add '.'
$host = strtolower( implode( '.', array_reverse( explode( '.', $host ) ) ) );
- $like = "$prot$host%";
+ $like = array( "$prot$host", $db->anyString() );
} else {
$host = strtolower( implode( '.', array_reverse( explode( '.', $host ) ) ) );
if ( substr( $host, -1, 1 ) !== '.' ) {
$host .= '.';
}
- $like = "$prot$host";
+ $like = array( "$prot$host" );
if ( $subdomains ) {
- $like .= '%';
+ $like[] = $db->anyString();
}
if ( !$subdomains || $path !== '/' ) {
- $like .= $path . '%';
+ $like[] = $path;
+ $like[] = $db->anyString();
}
}
return $like;
}
-}
+ /**
+ * Filters an array returned by makeLikeArray(), removing everything past first pattern placeholder.
+ *
+ * @param $arr array: array to filter
+ * @return array filtered array
+ */
+ public static function keepOneWildcard( $arr ) {
+ if( !is_array( $arr ) ) {
+ return $arr;
+ }
+
+ foreach( $arr as $key => $value ) {
+ if ( $value instanceof LikeMatch ) {
+ return array_slice( $arr, 0, $key + 1 );
+ }
+ }
+
+ return $arr;
+ }
+}