otg-microformat 0.0.2 → 0.0.3

data/.gitignore

@@ -1,3 +1,4 @@
+.DS_Store
 *.gem
 *.rbc
 .bundle

data/lib/microformat.rb

@@ -4,15 +4,26 @@ require 'andand'
 
 module Microformat
   class ItemProp
-    def self.parse(node)
+    def self.parse(node, strict)
       # If the element has no itemprop attribute
       # The attribute must return null on getting and must throw an INVALID_ACCESS_ERR exception on setting.
       return nil unless node.attribute('itemprop')
 
       # If the element has an itemscope attribute
       # The attribute must return the element itself on getting and must throw an INVALID_ACCESS_ERR exception on setting.
-      return ItemScope.new(node) if node.attribute('itemscope')
+      return ItemScope.new(node, strict) if node.attribute('itemscope')
 
+      if strict
+        parse_strict node
+      else
+        parse_weak node
+      end
+    end
+
+    private
+    ATTRIBUTES = ['content', 'src', 'href', 'data', 'datetime']
+
+    def self.parse_strict(node)
       # If the element is a meta element
       # The attribute must act as it would if it was reflecting the element's content content attribute
       return node.attribute('content').andand.value if node.name == 'meta'
@@ -37,15 +48,20 @@ module Microformat
       # The attribute must act the same as the element's textContent attribute.
       return node.text.chomp.strip
     end
+
+    def self.parse_weak(node)
+      ATTRIBUTES.map { |attr| node.attribute(attr).andand.value }.compact.first || node.text.chomp.strip
+    end
   end
 
   class ItemScope
     attr_reader :type, :id
 
-    def initialize(node)
+    def initialize(node, strict)
       @type = attr 'itemtype', node
       @id = attr 'itemid', node
       @properties = {}
+      @strict = strict
 
       parse_elements node.search './*'
     end
@@ -63,14 +79,14 @@ module Microformat
     def parse_elements(elements)
       elements.each do |el|
         itemprop = attr('itemprop', el)
-        prop = ItemProp.parse el
+        prop = ItemProp.parse el, @strict
 
         if prop
           @properties[itemprop] ||= []
           @properties[itemprop] << prop
-        else
-          parse_elements el.search('./*')
         end
+
+        parse_elements el.search('./*')
       end
     end
   end
@@ -88,10 +104,11 @@ module Microformat
   end
 
   class SchemaOrg
-    def self.parse(html)
+    def self.parse(html, opts={})
+      strict = opts.has_key? :strict ? opts[:strict] : true
       html = Nokogiri::HTML.parse html unless html.respond_to? :search
       scopes = html.search('//*[@itemscope and not(@itemprop)]')
-        .map { |node| ItemScope.new node }
+        .map { |node| ItemScope.new node, strict }
 
       if scopes.any?
         ItemDocument.new scopes

data/lib/microformat/version.rb

@@ -1,3 +1,3 @@
 module Microformat
-  VERSION = '0.0.2'
+  VERSION = '0.0.3'
 end

data/microformat.gemspec

@@ -23,4 +23,5 @@ Gem::Specification.new do |spec|
 
   spec.add_development_dependency 'bundler', '~> 1.3'
   spec.add_development_dependency 'rake'
+  spec.add_development_dependency 'rspec'
 end

data/spec/schema_org_spec.rb

@@ -0,0 +1,99 @@
+require 'rspec'
+require 'microformat'
+
+describe Microformat::SchemaOrg do
+  describe 'a strict implementation' do
+    let(:html) {
+      <<-HTML
+      <div itemscope itemtype="http://schema.org/Product">
+        <h1 itemprop="name">Product</h1>
+        <div itemprop="offers" itemscope itemtype="http://schema.org/Offer">
+          <meta itemprop="currency" content="AUD" />
+          <meta itemprop="availability" content="OutOfStock" />
+          Price: $<span itemprop="price">12.99</span>
+        </div>
+      </div>
+      HTML
+    }
+    let(:result) { Microformat::SchemaOrg.parse html, strict: true }
+    let(:product) { result.products.first }
+
+    it 'should find a product' do
+      product.should_not be_nil
+    end
+
+    it 'should parse name' do
+      product['name'].should eq ['Product']
+    end
+
+    it 'should parse offer' do
+      product['offers'].first['currency'].should eq ['AUD']
+      product['offers'].first['availability'].should eq ['OutOfStock']
+      product['offers'].first['price'].should eq ['12.99']
+    end
+  end
+
+  describe 'a weak implementation' do
+    let(:html) {
+      <<-HTML
+      <div itemscope itemtype="http://schema.org/Product">
+        <h1 itemprop="name">Product</h1>
+        <div itemprop="offers" itemscope itemtype="http://schema.org/Offer">
+          <span itemprop="currency" content="AUD" />
+          <span itemprop="availability" href="OutOfStock" />
+          Price: $<span itemprop="price">12.99</span>
+        </div>
+      </div>
+      HTML
+    }
+    let(:result) { Microformat::SchemaOrg.parse html, strict: false }
+    let(:product) { result.products.first }
+
+    it 'should find a product' do
+      product.should_not be_nil
+    end
+
+    it 'should parse name' do
+      product['name'].should eq ['Product']
+    end
+
+    it 'should parse offer' do
+      product['offers'].first['currency'].should eq ['AUD']
+      product['offers'].first['availability'].should eq ['OutOfStock']
+      product['offers'].first['price'].should eq ['12.99']
+    end
+  end
+
+  describe 'a weird weak implementation' do
+    let(:html) {
+      <<-HTML
+      <div itemscope itemtype="http://schema.org/Product">
+        <h1 itemprop="name">Product</h1>
+        <div itemprop="offers" itemscope itemtype="http://schema.org/Offer">
+          <span itemprop="currency" content="AUD">
+            <span itemprop="availability" href="OutOfStock">
+              Price: $<span itemprop="price">12.99</span>
+            </span>
+          </span>
+        </div>
+      </div>
+      HTML
+    }
+    let(:result) { Microformat::SchemaOrg.parse html, strict: false }
+    let(:product) { result.products.first }
+
+    it 'should find a product' do
+      product.should_not be_nil
+    end
+
+    it 'should parse name' do
+      product['name'].should eq ['Product']
+    end
+
+    it 'should parse offer' do
+      product['offers'].first['currency'].should eq ['AUD']
+      product['offers'].first['availability'].should eq ['OutOfStock']
+      product['offers'].first['price'].should eq ['12.99']
+    end
+  end
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: otg-microformat
 version: !ruby/object:Gem::Version
-  version: 0.0.2
+  version: 0.0.3
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-05-05 00:00:00.000000000 Z
+date: 2013-05-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -75,6 +75,22 @@ dependencies:
     - - ! '>='
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 description: A basic microformat parser for Ruby.
 email:
 - james@onthegame.com.au
@@ -90,6 +106,7 @@ files:
 - lib/microformat.rb
 - lib/microformat/version.rb
 - microformat.gemspec
+- spec/schema_org_spec.rb
 homepage: http://www.onthegame.com.au/about/opensource
 licenses:
 - MIT
@@ -103,22 +120,17 @@ required_ruby_version: !ruby/object:Gem::Requirement
   - - ! '>='
     - !ruby/object:Gem::Version
       version: '0'
-      segments:
-      - 0
-      hash: 640169864049438702
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements:
   - - ! '>='
     - !ruby/object:Gem::Version
       version: '0'
-      segments:
-      - 0
-      hash: 640169864049438702
 requirements: []
 rubyforge_project: 
 rubygems_version: 1.8.25
 signing_key: 
 specification_version: 3
 summary: Simple Microformat parser
-test_files: []
+test_files:
+- spec/schema_org_spec.rb