lib/sanitize.rb in sanitize-1.2.1 vs lib/sanitize.rb in sanitize-1.2.2.dev.20100822

@@ -25,10 +25,11 @@
 require 'sanitize/version'
 require 'sanitize/config'
 require 'sanitize/config/restricted'
 require 'sanitize/config/basic'
 require 'sanitize/config/relaxed'
+require 'sanitize/transformers/fix_fragment_cdata'
 
 class Sanitize
   attr_reader :config
 
   # Matches an attribute value that could be treated by a browser as a URL
@@ -88,16 +89,26 @@
 
     # Specific nodes to whitelist (along with all their attributes). This array
     # is generated at runtime by transformers, and is cleared before and after
     # a fragment is cleaned (so it applies only to a specific fragment).
     @whitelist_nodes = []
+
+    # Workaround for a fragment parsing bug in Nokogiri >= 1.4.2. The naïve
+    # version check is fine here; there are no side effects for unaffected
+    # versions except slightly worse performance, and I plan to remove this hack
+    # as soon as Nokogiri fixes the bug on their end.
+    if Nokogiri::VERSION > '1.4.1'
+      @config[:transformers] << Transformers::FIX_FRAGMENT_CDATA
+    end
   end
 
   # Returns a sanitized copy of _html_.
   def clean(html)
-    dupe = html.dup
-    clean!(dupe) || dupe
+    if html
+      dupe = html.dup
+      clean!(dupe) || dupe
+    end
   end
 
   # Performs clean in place, returning _html_, or +nil+ if no changes were
   # made.
   def clean!(html)
@@ -213,12 +224,14 @@
       :whitelist      => false
     }
 
     @config[:transformers].inject(node) do |transformer_node, transformer|
       transform = transformer.call({
-        :config    => @config,
-        :node      => transformer_node,
-        :node_name => transformer_node.name.downcase
+        :allowed_elements => @allowed_elements,
+        :config           => @config,
+        :node             => transformer_node,
+        :node_name        => transformer_node.name.downcase,
+        :whitelist_nodes  => @whitelist_nodes
       })
 
       if transform.nil?
         transformer_node
       elsif transform.is_a?(Hash)