FIX: properly unescape HTML entities in excerpts

lib/excerpt_parser.rb

@@ -17,16 +17,15 @@ class ExcerptParser < Nokogiri::XML::SAX::Document
 
   def self.get_excerpt(html, length, options)
     html ||= ''
-    if (html.include? 'excerpt') && (SPAN_REGEX === html)
-      length = html.length
-    end
+    length = html.length if html.include?('excerpt') && SPAN_REGEX === html
     me = self.new(length, options)
     parser = Nokogiri::HTML::SAX::Parser.new(me)
     catch(:done) do
       parser.parse(html)
     end
-    me.excerpt.strip!
-    me.excerpt
+    excerpt = me.excerpt.strip
+    excerpt = CGI.unescapeHTML(excerpt) if options[:text_entities] == true
+    excerpt
   end
 
   def escape_attribute(v)

spec/components/pretty_text_spec.rb

@@ -84,7 +84,6 @@ describe PrettyText do
   describe "Excerpt" do
 
     it "sanitizes attempts to inject invalid attributes" do
-
       spinner = "<a href=\"http://thedailywtf.com/\" data-bbcode=\"' class='fa fa-spin\">WTF</a>"
       PrettyText.excerpt(spinner, 20).should match_html spinner
 
@@ -216,6 +215,10 @@ describe PrettyText do
       post.excerpt.should == two_hundred
     end
 
+    it "unescapes html entities when we want text entities" do
+      PrettyText.excerpt("&#39;", 500, text_entities: true).should == "'"
+    end
+
   end
 
   describe "strip links" do