mida 0.1.2 → 0.1.3

data/CHANGELOG.rdoc

@@ -0,0 +1,12 @@
+== 0.1.3 (18th April 2011)
+* Ensure itemprops are parsed properly if containing non-microdata elements
+* Support itemprops nested within other itemprops
+
+== 0.1.2 (14th April 2011)
+* Add version for rspec dependency
+
+== 0.1.1 (12th April 2011)
+* Improve gemspec description
+
+== 0.1.0 (12th April 2011)
+* Initial Release

data/Rakefile

@@ -6,14 +6,14 @@ spec = Gem::Specification.new do |s|
   s.name        = "mida"
   s.summary     = "A Microdata parser/extractor library"
   s.description = "A Microdata parser and extractor library, based on the latest published version of the Microdata Specification, dated 5th April 2011."
-  s.version     = "0.1.2"
+  s.version     = "0.1.3"
   s.author      = "Lawrence Woodman"
   s.email       = "lwoodman@vlifesystems.com"
   s.homepage    = %q{http://github.com/LawrenceWoodman/mida}
   s.platform    = Gem::Platform::RUBY
   s.required_ruby_version = '>=1.9'
   s.files       = Dir['lib/**/*.rb'] + Dir['spec/**/*.rb'] + Dir['*.rdoc'] + Dir['Rakefile']
-  s.extra_rdoc_files = ['README.rdoc', 'LICENSE.rdoc']
+  s.extra_rdoc_files = ['README.rdoc', 'LICENSE.rdoc', 'CHANGELOG.rdoc']
   s.rdoc_options << '--main' << 'README.rdoc'
   s.add_dependency('nokogiri')
   s.add_development_dependency('rspec', '>= 2.0' )

data/lib/mida/item.rb

@@ -81,12 +81,11 @@ module Mida
 
     def traverse_elements(elements)
       elements.each do |element|
+        itemscope = element.attribute('itemscope')
+        itemprop = element.attribute('itemprop')
         internal_elements = extract_elements(element)
-        if internal_elements.empty? || element.attribute('itemscope')
-          add_itemprop(element)
-        else
-          traverse_elements(internal_elements)
-        end
+        add_itemprop(element) if itemscope || itemprop
+        traverse_elements(internal_elements) if internal_elements && !itemscope
       end
     end
 

data/lib/mida/property.rb

@@ -11,11 +11,9 @@ module Mida
     # [element] The itemprop element to be parsed
     # [page_url] The url of the page, including the filename, used to form absolute urls
     def self.parse(element, page_url=nil)
-      hash = {}
-      extract_property_names(element).each do |name|
-        hash[name] = extract_property(element, page_url)
+      extract_property_names(element).each_with_object({}) do |name, memo|
+        memo[name] = extract_property(element, page_url)
       end
-      hash
     end
 
     NON_TEXTCONTENT_ELEMENTS = {

data/spec/item_spec.rb

@@ -136,6 +136,82 @@ describe Mida::Item, 'when initialized with an itemscope containing itemprops su
 
 end
 
+describe Mida::Item, "when initialized with an itemscope containing itemprops
+  who's inner text is surrounded by non-microdata elements" do
+  before do
+    html = '<div itemscope><span itemprop="reviewer">Lorry <em>Woodman</em></span></div>'
+    doc = Nokogiri(html)
+    itemscope = doc.search('./*').first
+    @item = Mida::Item.new(itemscope)
+  end
+
+  it '#type should return the correct type' do
+    @item.type.should == nil
+  end
+
+  it '#id should return the correct id' do
+    @item.id.should == nil
+  end
+
+  it '#properties should return the correct name/value pairs' do
+    @item.properties.should == {
+      'reviewer' => ['Lorry Woodman']
+    }
+  end
+
+  it '#to_h should return the correct type and properties' do
+    @item.to_h.should == {
+      type: nil,
+      id: nil,
+      properties: {
+        'reviewer' => ['Lorry Woodman']
+      }
+    }
+  end
+
+end
+
+describe Mida::Item, "when initialized with an itemscope containing an itemprop
+  nested within another itemprop" do
+  before do
+    html = '
+      <div itemscope>
+        <span itemprop="description">The animal is a <span itemprop="colour">green</span> parrot.</span>
+      </div>
+    '
+    doc = Nokogiri(html)
+    itemscope = doc.search('./*').first
+    @item = Mida::Item.new(itemscope)
+  end
+
+  it '#type should return the correct type' do
+    @item.type.should == nil
+  end
+
+  it '#id should return the correct id' do
+    @item.id.should == nil
+  end
+
+  it '#properties should return the correct name/value pairs' do
+    @item.properties.should == {
+      'description' => ['The animal is a green parrot.'],
+      'colour' => ['green']
+    }
+  end
+
+  it '#to_h should return the correct type and properties' do
+    @item.to_h.should == {
+      type: nil,
+      id: nil,
+      properties: {
+        'description' => ['The animal is a green parrot.'],
+        'colour' => ['green']
+      }
+    }
+  end
+
+end
+
 describe Mida::Item, 'when initialized with an itemscope containing itemprops with the same name' do
   before do
     # Lemon Sorbet flavour

data/spec/property_spec.rb

@@ -22,6 +22,19 @@ describe Mida::Property, 'when parsing an element with one itemprop name' do
   end
 end
 
+describe Mida::Property, "when parsing an element who's inner text contains\
+  non microdata elements" do
+  before do
+    html = '<span itemprop="reviewer">Lorry <em>Woodman</em></span>'
+    doc = Nokogiri(html)
+    @itemprop = doc.search('./*').first
+  end
+
+  it '#parse should return a Hash with the correct name/value pair' do
+    Mida::Property.parse(@itemprop).should == {'reviewer' => 'Lorry Woodman'}
+  end
+end
+
 describe Mida::Property, 'when parsing an itemscope element that has a relative url' do
   before do
 

metadata

@@ -2,7 +2,7 @@
 name: mida
 version: !ruby/object:Gem::Version 
   prerelease: 
-  version: 0.1.2
+  version: 0.1.3
 platform: ruby
 authors: 
 - Lawrence Woodman
@@ -10,7 +10,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-04-15 00:00:00 Z
+date: 2011-04-18 00:00:00 Z
 dependencies: 
 - !ruby/object:Gem::Dependency 
   name: nokogiri
@@ -43,6 +43,7 @@ extensions: []
 extra_rdoc_files: 
 - README.rdoc
 - LICENSE.rdoc
+- CHANGELOG.rdoc
 files: 
 - lib/mida.rb
 - lib/mida/property.rb
@@ -53,6 +54,7 @@ files:
 - spec/item_spec.rb
 - spec/spec_helper.rb
 - TODO.rdoc
+- CHANGELOG.rdoc
 - README.rdoc
 - LICENSE.rdoc
 - Rakefile