feedme 0.8.0 → 0.8.1

data/lib/feedme.rb

@@ -153,6 +153,10 @@ module FeedMe
           match = Regexp.new(regexp).match(str)
           match.nil? ? nil : match[1]
         end,
+        
+        # this shouldn't be necessary since all text is automatically
+        # unescaped, but some feeds double-escape HTML
+        :esc => proc {|str| CGI.unescapeHTML(str) }
     	}
     end
     
@@ -528,7 +532,7 @@ module FeedMe
   end
 
   class Parser < FeedData
-    attr_reader :fm_source, :fm_options, :fm_type, :fm_tags, :fm_unparsed
+    attr_reader :fm_source, :fm_options, :fm_type, :fm_tags, :fm_parsed, :fm_unparsed
   
     def initialize(builder, source, options={})
       super(nil, nil, builder)
@@ -672,13 +676,13 @@ module FeedMe
     end
 
   	def clean_content(tag, attrs, content, parent)
-  		content = content.to_s
-  		if fm_builder.date_tags.include? tag
+  	  content = content.to_s
+  	  if fm_builder.date_tags.include? tag
   			content = Time.parse(content) rescue unescape(content)
   		else
   		  content = unescape(content)
   		end
-  
+      
       unless attrs.empty?
         hash = FeedData.new(tag, parent, fm_builder)
         attrs.each_pair {|key, value| hash[key] = unescape(value) }
@@ -706,7 +710,7 @@ module FeedMe
   
     def unescape(content)
       content = CGI.unescapeHTML(content)
-
+      
       query = content.match(/^(http:.*\?)(.*)$/)
       content = query[1] + CGI.unescape(query[2]) if query
       

data/lib/hpricot-util.rb

@@ -30,7 +30,7 @@ module FeedMe
     # sanitize HTML
     # todo: dup code to fix bugs
     def clean_html(html)
-      FeedMe::HtmlCleaner.clean(html)  
+      FeedMe::HtmlCleaner.clean(html)
     end
   end
   

data/lib/html-cleaner.rb

@@ -59,17 +59,17 @@ module FeedMe
       # Extra (i.e. unmatched) ending tags and comments are removed.
       def clean(str)
         str = unescapeHTML(str)
-
         doc = Hpricot(str, :fixup_tags => true)
         doc = subtree(doc, :body)
-
+        
         # get all the tags in the document
         # Somewhere near hpricot 0.4.92 "*" starting to return all elements,
         # including text nodes instead of just tagged elements.
         tags = (doc/"*").inject([]) { |m,e| m << e.name if(e.respond_to?(:name) && e.name =~ /^\w+$/) ; m }.uniq
 
         # Remove tags that aren't whitelisted.
-        remove_tags!(doc, tags - HTML_ELEMENTS)
+        diff = tags - HTML_ELEMENTS
+        remove_tags!(doc, diff)
         remaining_tags = tags & HTML_ELEMENTS
 
         # Remove attributes that aren't on the whitelist, or are suspicious URLs.
@@ -80,9 +80,9 @@ module FeedMe
           end
           element.raw_attributes = element.raw_attributes.build_hash {|a,v| [a, add_entities(v)]}
         end unless remaining_tags.empty?
-
+        
         doc.traverse_text {|t| t.set(add_entities(t.to_html))}
-
+        
         # Return the tree, without comments. Ugly way of removing comments,
         # but can't see a way to do this in Hpricot yet.
         doc.to_s.gsub(/<\!--.*?-->/mi, '')

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: feedme
 version: !ruby/object:Gem::Version 
-  version: 0.8.0
+  version: 0.8.1
 platform: ruby
 authors: 
 - John Didion
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2009-12-28 00:00:00 -05:00
+date: 2010-01-02 00:00:00 -05:00
 default_executable: 
 dependencies: []