sanitize.rb in sanitize-1.2.1.dev.20100329

- old
+ new

@@ -68,21 +68,26 @@
 
   # Returns a new Sanitize object initialized with the settings in _config_.
   def initialize(config = {})
     # Sanitize configuration.
     @config = Config::DEFAULT.merge(config)
-    @config[:transformers] = Array(@config[:transformers])
+    @config[:transformers] = Array(@config[:transformers].dup)
 
-    # :remove_contents takes precedence over :escape_only.
-    if @config[:remove_contents] && @config[:escape_only]
-      @config[:escape_only] = false
-    end
-
     # Convert the list of allowed elements to a Hash for faster lookup.
     @allowed_elements = {}
     @config[:elements].each {|el| @allowed_elements[el] = true }
 
+    # Convert the list of :remove_contents elements to a Hash for faster lookup.
+    @remove_all_contents     = false
+    @remove_element_contents = {}
+
+    if @config[:remove_contents].is_a?(Array)
+      @config[:remove_contents].each {|el| @remove_element_contents[el] = true }
+    else
+      @remove_all_contents = !!@config[:remove_contents]
+    end
+
     # 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 = []
   end
@@ -97,11 +102,11 @@
   # made.
   def clean!(html)
     fragment = Nokogiri::HTML::DocumentFragment.parse(html)
     clean_node!(fragment)
 
-    output_method_params = {:encoding => 'utf-8', :indent => 0}
+    output_method_params = {:encoding => @config[:output_encoding], :indent => 0}
 
     if @config[:output] == :xhtml
       output_method = fragment.method(:to_xhtml)
       output_method_params[:save_with] = Nokogiri::XML::Node::SaveOptions::AS_XHTML
     elsif @config[:output] == :html
@@ -110,14 +115,10 @@
       raise Error, "unsupported output format: #{@config[:output]}"
     end
 
     result = output_method.call(output_method_params)
 
-    # Ensure that the result is always a UTF-8 string in Ruby 1.9, no matter
-    # what. Nokogiri seems to return empty strings as ASCII for some reason.
-    result.force_encoding('utf-8') if RUBY_VERSION >= '1.9'
-
     return result == html ? nil : html[0, html.length] = result
   end
 
   # Sanitizes the specified Nokogiri::XML::Node and all its children.
   def clean_node!(node)
@@ -127,17 +128,11 @@
 
     node.traverse do |child|
       if child.element?
         clean_element!(child)
       elsif child.comment?
-        unless @config[:allow_comments]
-          if @config[:escape_only]
-            child.replace(Nokogiri::XML::Text.new(child.to_s, child.document))
-          else
-            child.unlink
-          end
-        end
+        child.unlink unless @config[:allow_comments]
       elsif child.cdata?
         child.replace(Nokogiri::XML::Text.new(child.text, child.document))
       end
     end
 
@@ -158,18 +153,14 @@
 
     name = node.name.to_s.downcase
 
     # Delete any element that isn't in the whitelist.
     unless transform[:whitelist] || @allowed_elements[name]
-      if @config[:escape_only]
-        node.replace(Nokogiri::XML::Text.new(node.to_s, node.document))
-      else
-        unless @config[:remove_contents]
-          node.children.each { |n| node.add_previous_sibling(n) }
-        end
-
-        node.unlink
+      unless @remove_all_contents || @remove_element_contents[name]
+        node.children.each { |n| node.add_previous_sibling(n) }
       end
+
+      node.unlink
 
       return
     end
 
     attr_whitelist = (transform[:attr_whitelist] +