From: Roan Kattouw <catrope@users.mediawiki.org>
Date: Sat, 20 Aug 2011 10:18:09 +0000 (+0000)
Subject: Per r90849, factor out most of the code that's duplicated between Parser::getExternal... 
X-Git-Tag: 1.31.0-rc.0~28150
X-Git-Url: http://git.cyclocoop.org/url?a=commitdiff_plain;h=b4ae56dea1a7f3f46c4f872151b0d5f121785271;p=lhc%2Fweb%2Fwiklou.git

Per r90849, factor out most of the code that's duplicated between Parser::getExternalLinkAttribs() and Skin::addToSidebarPlain() into wfMatchesDomainList(). Change a loose comparison to a strict one, and add a FIXME comment about how whitelisting nl.wikipedia.org also whitelists nds-nl.wikipedia.org due to the function's simplistic substring approach.
---

diff --git a/includes/GlobalFunctions.php b/includes/GlobalFunctions.php
index e51cea6764..2b16d17f05 100644
--- a/includes/GlobalFunctions.php
+++ b/includes/GlobalFunctions.php
@@ -645,6 +645,26 @@ function wfMakeUrlIndex( $url ) {
 	return $index;
 }
 
+/**
+ * Check whether a given URL has a domain that occurs in a given set of domains
+ * @param $url string URL
+ * @param $domains array Array of domains (strings)
+ * @return bool True if the host part of $url ends in one of the strings in $domains
+ */
+function wfMatchesDomainList( $url, $domains ) {
+	$bits = wfParseUrl( $url );
+	if ( is_array( $bits ) && isset( $bits['host'] ) ) {
+		foreach ( (array)$domains as $domain ) {
+			// FIXME: This gives false positives. http://nds-nl.wikipedia.org will match nl.wikipedia.org
+			// We should use something that interprets dots instead
+			if ( substr( $bits['host'], -strlen( $domain ) ) === $domain ) {
+				return true;
+			}
+		}
+	}
+	return false;
+}
+
 /**
  * Sends a line to the debug log if enabled or, optionally, to a comment in output.
  * In normal operation this is a NOP.
diff --git a/includes/Skin.php b/includes/Skin.php
index 5be598623e..e1b24fae93 100644
--- a/includes/Skin.php
+++ b/includes/Skin.php
@@ -1153,24 +1153,13 @@ abstract class Skin extends ContextSource {
 
 					if ( preg_match( '/^(?:' . wfUrlProtocols() . ')/', $link ) ) {
 						$href = $link;
-						//Parser::getExternalLinkAttribs won't work here because of the Namespace things
-						global $wgNoFollowLinks;
-						if ( $wgNoFollowLinks ) {
+						
+						// Parser::getExternalLinkAttribs won't work here because of the Namespace things
+						global $wgNoFollowLinks, $wgNoFollowDomainExceptions;
+						if ( $wgNoFollowLinks && !wfMatchesDomainList( $url, $wgNoFollowDomainExceptions ) ) {
 							$extraAttribs['rel'] = 'nofollow';
-
-							global $wgNoFollowDomainExceptions;
-							if ( $wgNoFollowDomainExceptions ) {
-								$bits = wfParseUrl( $url );
-								if ( is_array( $bits ) && isset( $bits['host'] ) ) {
-									foreach ( $wgNoFollowDomainExceptions as $domain ) {
-										if ( substr( $bits['host'], -strlen( $domain ) ) == $domain ) {
-											unset( $extraAttribs['rel'] );
-											break;
-										}
-									}
-								}
-							}
 						}
+						
 						global $wgExternalLinkTarget;
 						if ( $wgExternalLinkTarget) {
 							$extraAttribs['target'] = $wgExternalLinkTarget;
diff --git a/includes/parser/Parser.php b/includes/parser/Parser.php
index dc039fd40e..1c96fc4007 100644
--- a/includes/parser/Parser.php
+++ b/includes/parser/Parser.php
@@ -1648,23 +1648,12 @@ class Parser {
 	 */
 	function getExternalLinkAttribs( $url = false ) {
 		$attribs = array();
-		global $wgNoFollowLinks, $wgNoFollowNsExceptions;
+		global $wgNoFollowLinks, $wgNoFollowNsExceptions, $wgNoFollowDomainExceptions;
 		$ns = $this->mTitle->getNamespace();
-		if ( $wgNoFollowLinks && !in_array( $ns, $wgNoFollowNsExceptions ) ) {
+		if ( $wgNoFollowLinks && !in_array( $ns, $wgNoFollowNsExceptions ) &&
+				!wfMatchesDomainList( $url, $wgNoFollowDomainExceptions ) )
+		{
 			$attribs['rel'] = 'nofollow';
-
-			global $wgNoFollowDomainExceptions;
-			if ( $wgNoFollowDomainExceptions ) {
-				$bits = wfParseUrl( $url );
-				if ( is_array( $bits ) && isset( $bits['host'] ) ) {
-					foreach ( $wgNoFollowDomainExceptions as $domain ) {
-						if ( substr( $bits['host'], -strlen( $domain ) ) == $domain ) {
-							unset( $attribs['rel'] );
-							break;
-						}
-					}
-				}
-			}
 		}
 		if ( $this->mOptions->getExternalLinkTarget() ) {
 			$attribs['target'] = $this->mOptions->getExternalLinkTarget();