From 80a1ecf5bf4c0fe1ab541a9e252a595e6a78eade Mon Sep 17 00:00:00 2001
From: Mike Dalessio <mike@csa.net>
Date: Tue, 10 Feb 2009 09:42:04 -0500
Subject: [PATCH] sanitize_document is here. willkommen, bienvenue.

---
 lib/dryopteris/sanitize.rb | 13 +++++++++++++
 test/test_sanitizer.rb     |  7 +++++++
 2 files changed, 20 insertions(+)

diff --git a/lib/dryopteris/sanitize.rb b/lib/dryopteris/sanitize.rb
index 6d19184..21b2ef2 100644
--- a/lib/dryopteris/sanitize.rb
+++ b/lib/dryopteris/sanitize.rb
@@ -32,6 +32,19 @@ def sanitize(string, encoding=nil)
       body.children.map { |x| x.to_xml }.join
     end
     
+    def sanitize_document(string_or_io, encoding=nil)
+      return nil if string_or_io.nil?
+      return "" if string_or_io.strip.size == 0
+      
+      doc = Nokogiri::HTML.parse(string_or_io, nil, encoding)
+      elements = doc.xpath("/html/head/*","/html/body/*")
+      return "" if (elements.nil? || elements.empty?)
+      elements.each do |node| 
+        traverse_conditionally_top_down(node, :sanitize_node)
+      end
+      doc.root.to_xml
+    end
+
     private
     def traverse_conditionally_top_down(node, method_name)
       return if send(method_name, node)
diff --git a/test/test_sanitizer.rb b/test/test_sanitizer.rb
index 08430ed..4588065 100644
--- a/test/test_sanitizer.rb
+++ b/test/test_sanitizer.rb
@@ -7,9 +7,16 @@ def sanitize_html stream
     Dryopteris.sanitize(stream)
   end
 
+  def sanitize_doc stream
+    Dryopteris.sanitize_document(stream)
+  end
+
   def check_sanitization(input, htmloutput, xhtmloutput, rexmloutput)
     #  libxml uses double-quotes, so let's swappo-boppo our quotes before comparing.
     assert_equal htmloutput, sanitize_html(input).gsub(/"/,"'"), input
+
+    doc = sanitize_doc(input).gsub(/"/,"'")
+    assert doc.include?(htmloutput), "#{input}:\n#{doc}\nshould include:\n#{htmloutput}"
   end
 
   WhiteList::ALLOWED_ELEMENTS.each do |tag_name|