(bug 30269) Strings like foobar//barfoo are linked to become foobar[//barfoo]

* Introduce a boolean parameter to wfUrlProtocols() which, if set to false, will cause '//' to be dropped from the returned regex so it doesn't match protocol-relative URLs
* Introduce wfUrlProtocolsWithoutProtRel() as a wrapper for wfUrlProtocols( false ). The latter should not be used directly because the former is much clearer
* Use this new function in Parser::doMagicLinks() to fix the original bug. Also use it in ApiFormatBase::formatHTML() and CodeCommentLinker::link(), which probably had similar bugs

diff --git a/includes/GlobalFunctions.php b/includes/GlobalFunctions.php
index 193b84b..68d6865 100644 (file)
--- a/includes/GlobalFunctions.php
+++ b/includes/GlobalFunctions.php
@@ -469,14 +469,17 @@ function wfExpandUrl( $url, $defaultProto = PROTO_CURRENT ) {
 /**
  * Returns a regular expression of url protocols
  *
+ * @param $includeProtocolRelative bool If false, remove '//' from the returned protocol list.
+ *        DO NOT USE this directy, use wfUrlProtocolsWithoutProtRel() instead
  * @return String
  */
-function wfUrlProtocols() {
+function wfUrlProtocols( $includeProtocolRelative = true ) {
        global $wgUrlProtocols;
 
-       static $retval = null;
-       if ( !is_null( $retval ) ) {
-               return $retval;
+       // Cache return values separately based on $includeProtocolRelative
+       static $retval = array( true => null, false => null );
+       if ( !is_null( $retval[$includeProtocolRelative] ) ) {
+               return $retval[$includeProtocolRelative];
        }
 
        // Support old-style $wgUrlProtocols strings, for backwards compatibility
@@ -484,14 +487,30 @@ function wfUrlProtocols() {
        if ( is_array( $wgUrlProtocols ) ) {
                $protocols = array();
                foreach ( $wgUrlProtocols as $protocol ) {
-                       $protocols[] = preg_quote( $protocol, '/' );
+                       // Filter out '//' if !$includeProtocolRelative
+                       if ( $includeProtocolRelative || $protocol !== '//' ) {
+                               $protocols[] = preg_quote( $protocol, '/' );
+                       }
                }
 
-               $retval = implode( '|', $protocols );
+               $retval[$includeProtocolRelative] = implode( '|', $protocols );
        } else {
-               $retval = $wgUrlProtocols;
+               // Ignore $includeProtocolRelative in this case
+               // This case exists for pre-1.6 compatibility, and we can safely assume
+               // that '//' won't appear in a pre-1.6 config because protocol-relative
+               // URLs weren't supported until 1.18
+               $retval[$includeProtocolRelative] = $wgUrlProtocols;
        }
-       return $retval;
+       return $retval[$includeProtocolRelative];
+}
+
+/**
+ * Like wfUrlProtocols(), but excludes '//' from the protocol list. Use this if
+ * you need a regex that matches all URL protocols but does not match protocol-
+ * relative URLs
+ */
+function wfUrlProtocolsWithoutProtRel() {
+       return wfUrlProtocols( false );
 }
 
 /**

diff --git a/includes/api/ApiFormatBase.php b/includes/api/ApiFormatBase.php
index 0dd697c..9df2c6e 100644 (file)
--- a/includes/api/ApiFormatBase.php
+++ b/includes/api/ApiFormatBase.php
@@ -263,7 +263,7 @@ See <a href='http://www.mediawiki.org/wiki/API'>complete documentation</a>, or
                // encode all comments or tags as safe blue strings
                $text = preg_replace( '/\&lt;(!--.*?--|.*?)\&gt;/', '<span style="color:blue;">&lt;\1&gt;</span>', $text );
                // identify URLs
-               $protos = wfUrlProtocols();
+               $protos = wfUrlProtocolsWithoutProtRel();
                // This regex hacks around bug 13218 (&quot; included in the URL)
                $text = preg_replace( "#(($protos).*?)(&quot;)?([ \\'\"<>\n]|&lt;|&gt;|&quot;)#", '<a href="\\1">\\1</a>\\3\\4', $text );
                // identify requests to api.php

diff --git a/includes/parser/Parser.php b/includes/parser/Parser.php
index 8fe153c..9a511ad 100644 (file)
--- a/includes/parser/Parser.php
+++ b/includes/parser/Parser.php
@@ -1230,7 +1230,7 @@ class Parser {
         */
        function doMagicLinks( $text ) {
                wfProfileIn( __METHOD__ );
-               $prots = $this->mUrlProtocols;
+               $prots = wfUrlProtocolsWithoutProtRel();
                $urlChar = self::EXT_LINK_URL_CLASS;
                $text = preg_replace_callback(
                        '!(?:                           # Start cases