sumitup 0.1.2 → 0.1.3

data/VERSION

@@ -1 +1 @@
-0.1.2
+0.1.3

data/lib/sumitup/parser.rb

@@ -71,8 +71,17 @@ module Sumitup
         else
           # if the text of the current node makes us go over then truncate it
           result, count = snippet(node.inner_text, max - self.word_count)
-          self.word_count += count
-          node.content = result
+          if count == 0 || is_blank?(result)
+            node.remove
+          else
+            self.word_count += count
+            node.content = result
+          end
+        end
+      else
+        # Remove empty nodes
+        if node.text.empty? && node.children.empty? && !['img', 'br'].include?(node.name)
+          node.remove
         end
       end
       

data/spec/fixtures/basic.html

@@ -33,4 +33,11 @@
   	</dd>
   </dl>
   <br />
+  <ul>
+    <li><span>one</span></li>
+    <li><span>two</span></li>
+    <li><span>three</span></li>
+    <li><span>four</span></li>
+    <li><span>five</span></li>
+  </ul>
 </div>

data/spec/sumitup/parser_spec.rb

@@ -7,6 +7,28 @@ describe Sumitup::Parser do
       @html = IO.read(File.join(File.dirname(__FILE__), '..', 'fixtures', 'basic.html'))
     end
     
+    it "should summarize the content by number of words" do
+      parser = Sumitup::Parser.new(:max_words => 1000)
+      result = parser.summarize(@html, 5)
+      result.should_not include('consectetur')
+      result.should include('amet')
+    end
+    
+    it "should keep permitted html in summary" do
+      parser = Sumitup::Parser.new(:max_words => 1000)
+      result = parser.summarize(@html, 5)
+      result.should include('strong')
+      result.should include('blockquote')
+    end
+    
+    it "should remove empty tags after truncating text" do
+      parser = Sumitup::Parser.new(:max_words => 5)
+      result = parser.summarize(@html)
+      result.should_not include('ul')
+      result.should_not include('li')
+      result.should_not include('<span></span>')
+    end
+    
     describe "Sanitize options" do
       it "should remove html comments" do
         result = Sumitup::Parser.new.summarize(@html, 100000)
@@ -18,22 +40,8 @@ describe Sumitup::Parser do
         result.should_not include('<style type="text/css">')
       end
     end
-    
+        
     describe "word_transformer" do
-      it "should summarize the content by number of words" do
-        parser = Sumitup::Parser.new(:max_words => 1000)
-        result = parser.summarize(@html, 5)
-        result.should_not include('consectetur')
-        result.should include('amet')
-      end
-      
-      it "should keep permitted html in summary" do
-        parser = Sumitup::Parser.new(:max_words => 1000)
-        result = parser.summarize(@html, 5)
-        result.should include('strong')
-        result.should include('blockquote')
-      end
-      
       it "should remove empty tags" do
         result = Sumitup::Parser.new.summarize(@html, 100000)
         result.should_not include('<p></p>')

data/sumitup.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = "sumitup"
-  s.version = "0.1.2"
+  s.version = "0.1.3"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Justin Ball"]
-  s.date = "2012-03-06"
+  s.date = "2012-03-07"
   s.description = "Given an html document or fragment this gem will build a summary of the content."
   s.email = "justinball@gmail.com"
   s.extra_rdoc_files = [

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: sumitup
 version: !ruby/object:Gem::Version 
-  hash: 31
+  hash: 29
   prerelease: 
   segments: 
   - 0
   - 1
-  - 2
-  version: 0.1.2
+  - 3
+  version: 0.1.3
 platform: ruby
 authors: 
 - Justin Ball
@@ -15,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2012-03-06 00:00:00 Z
+date: 2012-03-07 00:00:00 Z
 dependencies: 
 - !ruby/object:Gem::Dependency 
   type: :runtime