From fd07d0236aa03e68e28e3f4fbf818474acbaa1fc Mon Sep 17 00:00:00 2001
From: Aryeh Gregor <simetrical@users.mediawiki.org>
Date: Fri, 23 Jan 2009 18:03:12 +0000
Subject: [PATCH] Allow exempting domain names from rel="nofollow"

This introduces a new configuration option, $wgNoFollowDomainExceptions.
By default this is an empty array; perhaps it should be null by default
and initialize to something extracted from $wgServer.  An appropriate
value for Wikimedia would be something like:

$wgNoFollowDomainExceptions = array( 'wikipedia.org', 'wiktionary.org',
'wikibooks.org', ... );

It's fairly silly that we're nofollowing links to our own sites.  :)
---
 RELEASE-NOTES                |  2 ++
 includes/DefaultSettings.php | 13 +++++++++++++
 includes/parser/Parser.php   | 32 ++++++++++++++++++++++++++++----
 3 files changed, 43 insertions(+), 4 deletions(-)

diff --git a/RELEASE-NOTES b/RELEASE-NOTES
index 742910e32f..cd6453a99d 100644
--- a/RELEASE-NOTES
+++ b/RELEASE-NOTES
@@ -23,6 +23,8 @@ it from source control: http://www.mediawiki.org/wiki/Download_from_SVN
 * Added $wgNewPasswordExpiry, to specify an expiry time (in seconds) to
   temporary passwords
 * Added $wgUseTwoButtonsSearchForm to choose the Search form behavior/look
+* Added $wgNoFollowDomainExceptions to allow exempting particular domain names
+  from rel="nofollow" on external links
 
 === New features in 1.15 ===
 
diff --git a/includes/DefaultSettings.php b/includes/DefaultSettings.php
index 9ec4d136bd..3119e4b89a 100644
--- a/includes/DefaultSettings.php
+++ b/includes/DefaultSettings.php
@@ -3084,6 +3084,19 @@ $wgNoFollowLinks = true;
  */
 $wgNoFollowNsExceptions = array();
 
+/**
+ * If this is set to an array of domains, external links to these domain names
+ * (or any subdomains) will not be set to rel="nofollow" regardless of the
+ * value of $wgNoFollowLinks.  For instance:
+ *
+ * $wgNoFollowDomainExceptions = array( 'en.wikipedia.org', 'wiktionary.org' );
+ *
+ * This would add rel="nofollow" to links to de.wikipedia.org, but not
+ * en.wikipedia.org, wiktionary.org, en.wiktionary.org, us.en.wikipedia.org,
+ * etc.
+ */
+$wgNoFollowDomainExceptions = array();
+
 /**
  * Default robot policy.  The default policy is to encourage indexing and fol-
  * lowing of links.  It may be overridden on a per-namespace and/or per-page
diff --git a/includes/parser/Parser.php b/includes/parser/Parser.php
index c37c48e3dc..b8c1325a7e 100644
--- a/includes/parser/Parser.php
+++ b/includes/parser/Parser.php
@@ -1130,7 +1130,7 @@ class Parser
 		if ( $text === false ) {
 			# Not an image, make a link
 			$text = $sk->makeExternalLink( $url, $wgContLang->markNoConversion($url), true, 'free', 
-				$this->getExternalLinkAttribs() );
+				$this->getExternalLinkAttribs( $url ) );
 			# Register it in the output object...
 			# Replace unnecessary URL escape codes with their equivalent characters
 			$pasteurized = self::replaceUnusualEscapes( $url );
@@ -1410,8 +1410,8 @@ class Parser
 			# This means that users can paste URLs directly into the text
 			# Funny characters like &ouml; aren't valid in URLs anyway
 			# This was changed in August 2004
-			$s .= $sk->makeExternalLink( $url, $text, false, $linktype, $this->getExternalLinkAttribs() ) 
-				. $dtrail . $trail;
+			$s .= $sk->makeExternalLink( $url, $text, false, $linktype,
+				$this->getExternalLinkAttribs( $url ) ) . $dtrail . $trail;
 
 			# Register link in the output object.
 			# Replace unnecessary URL escape codes with the referenced character
@@ -1424,12 +1424,36 @@ class Parser
 		return $s;
 	}
 
-	function getExternalLinkAttribs() {
+	/**
+	 * Get an associative array of additional HTML attributes appropriate for a
+	 * particular external link.  This currently may include rel => nofollow
+	 * (depending on configuration, namespace, and the URL's domain) and/or a
+	 * target attribute (depending on configuration).
+	 *
+	 * @param string $url Optional URL, to extract the domain from for rel =>
+	 *   nofollow if appropriate
+	 * @return array Associative array of HTML attributes
+	 */
+	function getExternalLinkAttribs( $url = false ) {
 		$attribs = array();
 		global $wgNoFollowLinks, $wgNoFollowNsExceptions;
 		$ns = $this->mTitle->getNamespace();
 		if( $wgNoFollowLinks && !in_array($ns, $wgNoFollowNsExceptions) ) {
 			$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();
-- 
2.20.1