Performance

My REXML::Element.to_ncr (and REXML::Element.to_utf8) is horribly slow. For long documents, it proves more efficient to serialize to a string, apply String.to_ncr (or String.to_utf8) and then Sanitize the string.

test/functional/wiki_controller_test.rb

@@ -680,10 +680,25 @@ class WikiControllerTest < Test::Unit::TestCase
 %
 % Unresolved  issues:
 %
-%   \binom{}{}
-%
 %   \righttoleftarrow
 %   \lefttorightarrow
+%
+%   \color{} with HTML colorspec
+%   \bgcolor
+%   \array
+
+% Of  the standard HTML named colors, white, black, red, green, blue and yellow
+% are  predefined in the color package. Here are the rest.
+\definecolor{aqua}{rgb}{0, 1.0, 1.0}
+\definecolor{fuschia}{rgb}{1.0, 0, 1.0}
+\definecolor{gray}{rgb}{0.502, 0.502, 0.502}
+\definecolor{lime}{rgb}{0, 1.0, 0}
+\definecolor{maroon}{rgb}{0.502, 0, 0}
+\definecolor{navy}{rgb}{0, 0, 0.502}
+\definecolor{olive}{rgb}{0.502, 0.502, 0}
+\definecolor{purple}{rgb}{0.502, 0, 0.502}
+\definecolor{silver}{rgb}{0.753, 0.753, 0.753}
+\definecolor{teal}{rgb}{0, 0.502, 0.502}
 
 % Because  of conflicts, \space and \mathop are converted to
 % \itexspace  and \operatorname during preprocessing.
@@ -842,6 +857,8 @@ class WikiControllerTest < Test::Unit::TestCase
 \renewcommand{\scriptsize}{\scriptstyle}
 \newcommand{\scriptscriptsize}{\scriptscriptstyle}
 \newcommand{\mathfr}{\mathfrak}
+\newcommand{\statusline}[2]{#2}
+\newcommand{\toggle}[2]{#1}
 
 %-------------------------------------------------------------------
 

test/unit/page_renderer_test.rb

@@ -164,14 +164,14 @@ class PageRendererTest < Test::Unit::TestCase
   # wikiwords are invalid as styles, must be in "name: value" form
   def test_content_with_wikiword_in_style_tag
     assert_markup_parsed_as(
-        "<p>That is some <em style=\"\">Stylish Emphasis</em></p>", 
+        "<p>That is some <em style=''>Stylish Emphasis</em></p>", 
 	    'That is some <em style="WikiWord">Stylish Emphasis</em>')
   end
  
   # validates format of style..
   def test_content_with_valid_style_in_style_tag
     assert_markup_parsed_as(
-        "<p>That is some <em style=\"text-align: right;\">Stylish Emphasis</em></p>", 
+        "<p>That is some <em style='text-align: right;'>Stylish Emphasis</em></p>", 
 	    'That is some <em style="text-align: right">Stylish Emphasis</em>')
   end
   
@@ -199,24 +199,24 @@ class PageRendererTest < Test::Unit::TestCase
   
   def test_content_with_link_in_parentheses
     assert_markup_parsed_as(
-      "<p>(<a href=\"http://wiki.org/wiki.cgi?WhatIsWiki\">What is a wiki?</a>)</p>",
+      "<p>(<a href='http://wiki.org/wiki.cgi?WhatIsWiki'>What is a wiki?</a>)</p>",
       '([What is a wiki?](http://wiki.org/wiki.cgi?WhatIsWiki))')
   end
   
   def test_content_with_image_link
     assert_markup_parsed_as( 
-      "<p>This <img alt=\"\" src=\"http://hobix.com/sample.jpg\" /> is a Markdown image link.</p>", 
+      "<p>This <img src='http://hobix.com/sample.jpg' alt=''/> is a Markdown image link.</p>", 
       'This ![](http://hobix.com/sample.jpg) is a Markdown image link.')
   end
   
   def test_content_with_inlined_img_tag
     assert_markup_parsed_as( 
-      "<p>This <img alt=\"\" src=\"http://hobix.com/sample.jpg\" /> is an inline image link.</p>", 
+      "<p>This <img src='http://hobix.com/sample.jpg' alt=''/> is an inline image link.</p>", 
       'This <img src="http://hobix.com/sample.jpg" alt="" /> is an inline image link.')
        
     # currently, upper case HTML elements are not allowed
     assert_markup_parsed_as( 
-      '<p>This &lt;IMG SRC="http://hobix.com/sample.jpg" alt=""&gt;&lt;/IMG&gt; is an inline image link.</p>', 
+      '<p>This &lt;IMG SRC="http://hobix.com/sample.jpg" alt=""/&gt; is an inline image link.</p>', 
       'This <IMG SRC="http://hobix.com/sample.jpg" alt="" /> is an inline image link.')
   end
   
@@ -361,7 +361,7 @@ class PageRendererTest < Test::Unit::TestCase
     EOL
   
     assert_markup_parsed_as(
-        "<ul>\n<li><a href=\"~b\">a</a></li>\n\n<li>c~ d</li>\n</ul>",
+        "<ul>\n<li><a href='~b'>a</a></li>\n\n<li>c~ d</li>\n</ul>",
         list_with_tildas)
   end
   

test/unit/sanitize_test.rb

@@ -0,0 +1,32 @@
+#!/usr/bin/env ruby
+
+require File.expand_path(File.dirname(__FILE__) + '/../test_helper')
+require 'sanitize'
+
+class SanitizeTest < Test::Unit::TestCase
+
+  def setup
+
+  end
+
+  def rexml_doc(string)
+    REXML::Document.new(
+      "<div xmlns='http://www.w3.org/1999/xhtml'>#{string}</div>")
+  end
+  
+  def my_rex(string)
+    sanitize_rexml(rexml_doc(string)).gsub(/\A<div xmlns="http:\/\/www.w3.org\/1999\/xhtml">(.*)<\/div>\Z/m, '\1')
+  end
+
+  def test_sanitize_named_entities
+    input = '<p>Greek &phi;, double-struck &Aopf;, numeric &#x1D538; &#8279;</p>'
+    output = "<p>Greek \317\225, double-struck \360\235\224\270, numeric \360\235\224\270 \342\201\227</p>"
+    output2 = "<p>Greek \317\225, double-struck \360\235\224\270, numeric &#x1D538; &#8279;</p>"
+    assert_equal(output, sanitize_xhtml(input))
+    assert_equal(output, sanitize_html(input))
+    assert_equal(output, my_rex(input))
+    assert_equal(output2, input.to_utf8)
+  end
+
+
+end