extract msword html data into an asset file

Manifest.txt

@@ -24,6 +24,7 @@ lib/loofah/scrubber.rb
 lib/loofah/scrubbers.rb
 lib/loofah/xml/document.rb
 lib/loofah/xml/document_fragment.rb
+test/assets/msword.html
 test/assets/testdata_sanitizer_tests1.dat
 test/helper.rb
 test/html5/test_sanitizer.rb

test/assets/msword.html

@@ -0,0 +1,63 @@
+<meta http-equiv="Content-Type" content="text/html; charset=utf-8"><meta name="ProgId" content="Word.Document"><meta name="Generator" content="Microsoft Word 11"><meta name="Originator" content="Microsoft Word 11"><link rel="File-List" href="file:///C:%5CDOCUME%7E1%5CNICOLE%7E1%5CLOCALS%7E1%5CTemp%5Cmsohtml1%5C01%5Cclip_filelist.xml"><!--[if gte mso 9]><xml>
+<w:WordDocument>
+ <w:View>Normal</w:View>
+ <w:Zoom>0</w:Zoom>
+ <w:PunctuationKerning/>
+ <w:ValidateAgainstSchemas/>
+ <w:SaveIfXMLInvalid>false</w:SaveIfXMLInvalid>
+ <w:IgnoreMixedContent>false</w:IgnoreMixedContent>
+ <w:AlwaysShowPlaceholderText>false</w:AlwaysShowPlaceholderText>
+ <w:Compatibility>
+  <w:BreakWrappedTables/>
+  <w:SnapToGridInCell/>
+  <w:WrapTextWithPunct/>
+  <w:UseAsianBreakRules/>
+  <w:DontGrowAutofit/>
+ </w:Compatibility>
+ <w:BrowserLevel>MicrosoftInternetExplorer4</w:BrowserLevel>
+</w:WordDocument>
+</xml><![endif]--><!--[if gte mso 9]><xml>
+<w:LatentStyles DefLockedState="false" LatentStyleCount="156">
+</w:LatentStyles>
+</xml><![endif]--><style>
+<!--
+/* Style Definitions */
+p.MsoNormal, li.MsoNormal, div.MsoNormal
+{mso-style-parent:"";
+margin:0in;
+margin-bottom:.0001pt;
+mso-pagination:widow-orphan;
+font-size:12.0pt;
+font-family:"Times New Roman";
+mso-fareast-font-family:"Times New Roman";}
+@page Section1
+{size:8.5in 11.0in;
+margin:1.0in 1.25in 1.0in 1.25in;
+mso-header-margin:.5in;
+mso-footer-margin:.5in;
+mso-paper-source:0;}
+div.Section1
+{page:Section1;}
+-->
+</style><!--[if gte mso 10]>
+<style>
+/* Style Definitions */
+table.MsoNormalTable
+{mso-style-name:"Table Normal";
+mso-tstyle-rowband-size:0;
+mso-tstyle-colband-size:0;
+mso-style-noshow:yes;
+mso-style-parent:"";
+mso-padding-alt:0in 5.4pt 0in 5.4pt;
+mso-para-margin:0in;
+mso-para-margin-bottom:.0001pt;
+mso-pagination:widow-orphan;
+font-size:10.0pt;
+font-family:"Times New Roman";
+mso-ansi-language:#0400;
+mso-fareast-language:#0400;
+mso-bidi-language:#0400;}
+</style>
+<![endif]-->
+
+<p class="MsoNormal">Foo <b style="">BOLD<o:p></o:p></b></p>

test/integration/test_ad_hoc.rb

@@ -17,6 +17,8 @@ class IntegrationTestAdHoc < Loofah::TestCase
   end
 
   context "tests" do
+    MSWORD_HTML = File.read(File.join(File.dirname(__FILE__), "..", "assets", "msword.html")).freeze
+
     def test_removal_of_illegal_tag
       html = <<-HTML
       following this there should be no jim tag
@@ -76,72 +78,6 @@ def test_whitewash_on_fragment
       assert_equal "<p>safe</p><b>description</b>", whitewashed.gsub("\n","")
     end
 
-    MSWORD_HTML = <<-EOHTML
-<meta http-equiv="Content-Type" content="text/html; charset=utf-8"><meta name="ProgId" content="Word.Document"><meta name="Generator" content="Microsoft Word 11"><meta name="Originator" content="Microsoft Word 11"><link rel="File-List" href="file:///C:%5CDOCUME%7E1%5CNICOLE%7E1%5CLOCALS%7E1%5CTemp%5Cmsohtml1%5C01%5Cclip_filelist.xml"><!--[if gte mso 9]><xml>
-<w:WordDocument>
- <w:View>Normal</w:View>
- <w:Zoom>0</w:Zoom>
- <w:PunctuationKerning/>
- <w:ValidateAgainstSchemas/>
- <w:SaveIfXMLInvalid>false</w:SaveIfXMLInvalid>
- <w:IgnoreMixedContent>false</w:IgnoreMixedContent>
- <w:AlwaysShowPlaceholderText>false</w:AlwaysShowPlaceholderText>
- <w:Compatibility>
-  <w:BreakWrappedTables/>
-  <w:SnapToGridInCell/>
-  <w:WrapTextWithPunct/>
-  <w:UseAsianBreakRules/>
-  <w:DontGrowAutofit/>
- </w:Compatibility>
- <w:BrowserLevel>MicrosoftInternetExplorer4</w:BrowserLevel>
-</w:WordDocument>
-</xml><![endif]--><!--[if gte mso 9]><xml>
-<w:LatentStyles DefLockedState="false" LatentStyleCount="156">
-</w:LatentStyles>
-</xml><![endif]--><style>
-<!--
-/* Style Definitions */
-p.MsoNormal, li.MsoNormal, div.MsoNormal
-{mso-style-parent:"";
-margin:0in;
-margin-bottom:.0001pt;
-mso-pagination:widow-orphan;
-font-size:12.0pt;
-font-family:"Times New Roman";
-mso-fareast-font-family:"Times New Roman";}
-@page Section1
-{size:8.5in 11.0in;
-margin:1.0in 1.25in 1.0in 1.25in;
-mso-header-margin:.5in;
-mso-footer-margin:.5in;
-mso-paper-source:0;}
-div.Section1
-{page:Section1;}
--->
-</style><!--[if gte mso 10]>
-<style>
-/* Style Definitions */
-table.MsoNormalTable
-{mso-style-name:"Table Normal";
-mso-tstyle-rowband-size:0;
-mso-tstyle-colband-size:0;
-mso-style-noshow:yes;
-mso-style-parent:"";
-mso-padding-alt:0in 5.4pt 0in 5.4pt;
-mso-para-margin:0in;
-mso-para-margin-bottom:.0001pt;
-mso-pagination:widow-orphan;
-font-size:10.0pt;
-font-family:"Times New Roman";
-mso-ansi-language:#0400;
-mso-fareast-language:#0400;
-mso-bidi-language:#0400;}
-</style>
-<![endif]-->
-
-<p class="MsoNormal">Foo <b style="">BOLD<o:p></o:p></b></p>
-  EOHTML
-
     def test_fragment_whitewash_on_microsofty_markup
       whitewashed = Loofah.fragment(MSWORD_HTML).scrub!(:whitewash)
       assert_equal "<p>Foo <b>BOLD</b></p>", whitewashed.to_s.strip
@@ -254,5 +190,6 @@ def test_dont_remove_whitespace_between_tags
       end
 
     end
+
   end
 end