0
@@ -1,5 +1,7 @@
0
 *SVN*
0
 
0
+* Added TextHelper#strip_tags for removing HTML tags from a string (using HTMLTokenizer) #2229 [marcin@junkheap.net]
0
+
0
 * Added a reader for flash.now, so it's possible to do stuff like flash.now[:alert] ||= 'New if not set' #2422 [Caio Chassot]
0
 
0
 

0
@@ -202,6 +202,28 @@
0
         html
0
       end
0
       
0
+      # Strips all HTML tags from the input, including comments.  This uses the html-scanner
0
+      # tokenizer and so it's HTML parsing ability is limited by that of html-scanner.
0
+      #
0
+      # Returns the tag free text.
0
+      def strip_tags(html)
0
+        if html.index("<")
0
+          text = ""
0
+          tokenizer = HTML::Tokenizer.new(html)
0
+
0
+          while token = tokenizer.next
0
+            node = HTML::Node.parse(nil, 0, 0, token, false)
0
+            # result is only the content of any Text nodes
0
+            text << node.to_s if node.class == HTML::Text  
0
+          end
0
+          # strip any comments, and if they have a newline at the end (ie. line with
0
+          # only a comment) strip that too
0
+          text.gsub(/<!--(.*?)-->[\n]?/m, "") 
0
+        else
0
+          html # already plain text
0
+        end 
0
+      end
0
+      
0
       # Returns a Cycle object whose to_s value cycles through items of an
0
       # array every time it is called. This can be used to alternate classes
0
       # for table rows:

0
@@ -268,5 +268,14 @@
0
     assert_equal(%w{Specialized Fuji Giant}, @cycles)
0
   end
0
 
0
+  def test_strip_tags
0
+    assert_equal("This is a test.", strip_tags("<p>This <u>is<u> a <a href='test.html'><strong>test</strong></a>.</p>"))
0
+    assert_equal("This is a test.", strip_tags("This is a test."))
0
+    assert_equal(
0
+    %{This is a test.\n\n\nIt no longer contains any HTML.\n}, strip_tags(
0
+    %{<title>This is <b>a <a href="" target="_blank">test</a></b>.</title>\n\n<!-- it has a comment -->\n\n<p>It no <b>longer <strong>contains <em>any <strike>HTML</strike></em>.</strong></b></p>\n}))
0
+    assert_equal("This has a  here.", strip_tags("This has a <!-- comment --> here."))
0
+  end
0
+
0
 end