test_basic.rb in mdalessio-dryopteris-0.1.1

- old
+ new
@@ -60,7 +60,87 @@
   end
 
   def test_fragment_in_p_tag_plus_stuff
     assert_equal "<p>This fragment is in a p.</p>foo<strong>bar</strong>", Dryopteris.sanitize("<p>This fragment is in a p.</p>foo<strong>bar</strong>")
   end
+
+  def test_fragment_with_text_nodes_leading_and_trailing
+    assert_equal "text<p>fragment</p>text", Dryopteris.sanitize("text<p>fragment</p>text")
+  end
   
+  def test_fragment_with_body_tags
+    # ignore second open body tag, use first close body tag, ignore everything after that
+    assert_equal "textfragment", Dryopteris.sanitize("text<body>fragment</body>text")
+  end
+
+  def test_whitewash_on_microsofty_markup
+    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
+
+    whitewashed = Dryopteris.whitewash(html)
+    assert_equal "<p>Foo <b>BOLD</b></p>", whitewashed
+  end
+
 end