Support disallowing robots

Add a disallow_robots parameter which can be used to disallow
indexing of all site content by robots. This is particularly useful
for test deployments where you don't want extra (often stale) copies
of your content to show up in search engines.

Change-Id: Ic62a72555315bd344db338809920a3605f17c8c6

files/disallow_robots.txt

@@ -0,0 +1,2 @@
+User-agent: *
+Disallow: /

manifests/init.pp

@@ -24,6 +24,7 @@ class mediawiki(
   $wg_sitename                = undef,
   $wg_logo                    = undef,
   $wg_openidforcedprovider    = 'https://login.launchpad.net/+openid',
+  $disallow_robots            = false,
 ) {
 
   if ($role == 'app' or $role == 'all') {
@@ -46,6 +47,17 @@ class mediawiki(
       require => File['/srv/mediawiki'],
     }
 
+    if $disallow_robots == true {
+      file { '/srv/mediawiki/robots.txt':
+        ensure  => file,
+        group   => 'root',
+        mode    => '0444',
+        owner   => 'root',
+        source  => 'puppet:///modules/mediawiki/disallow_robots.txt',
+        require => File['/srv/mediawiki'],
+      }
+    }
+
     include ::httpd
     include ::mediawiki::php
     include ::mediawiki::app

templates/apache/mediawiki.erb

@@ -95,6 +95,11 @@
   Alias /w <%= scope['mediawiki::mediawiki_location'] %>
   Alias /wiki <%= scope['mediawiki::mediawiki_location'] %>/index.php
 
+<% if scope['mediawiki::disallow_robots'] == true %>
+  # Request that search engines not index this site
+  Alias /robots.txt /srv/mediawiki/robots.txt
+<% end %>
+
   # Redirect old /Article_Name urls
   RewriteEngine on
   RewriteCond %{REQUEST_URI} !^/w/