rdf-microdata 0.1.3 → 0.2.0

data/README

@@ -19,10 +19,13 @@ Install with 'gem install rdf-microdata'
 
     graph = RDF::Graph.load("etc/foaf.html", :format => :microdata)
 
+## Note
+The Microdata editor has recently [dropped support for RDF
+conversion](http://html5.org/tools/web-apps-tracker?from=6426&to=6427), as a result, this gem is being used to
+investigate ways in which Microdata might have more satisfactory RDF generation.
+
 ### Generating RDF friendly URIs from terms
-As defined, Microdata creates ugly (and even illegal) URIs for `@itemprop` entries that are a simple
-term, and not already a URI. {RDF::Microdata::Reader} implements a `:rdf\_terms` option which uses an alternative
-process for creating URIs from terms: If the `@itemprop` is included within an item having an `@itemtype`,
+If the `@itemprop` is included within an item having an `@itemtype`,
 the URI of the `@itemtype` will be used for generating a term URI. The type URI will be trimmed following
 the last '#' or '/' character, and the term will be appended to the resulting URI. This is in keeping
 with standard convention for defining properties and classes within an RDFS or OWL vocabulary.
@@ -48,6 +51,15 @@ With the `:rdf\_terms` option, this becomes:
     @prefix schema: <http://schema.org/> .
     <> md:item [ a schema:Person; schema:name "Gregg" ] .
 
+### Improve xsd:date, xsd:time, xsd:dateTime and xsd:duration generation from _time_ element
+
+Use the lexical form of the @datetime attribute of the _time_ element to determine the specific type
+of the generated literal.
+
+### Remove implicit RDF triple generation
+
+html>head>title and anchor (_a_) elements no longer generate triples without @item* properties
+
 ## Dependencies
 * [RDF.rb](http://rubygems.org/gems/rdf) (>= 0.3.3)
 * [Nokogiri](http://rubygems.org/gems/nokogiri) (>= 1.3.3)

data/VERSION

@@ -1 +1 @@
-0.1.3
+0.2.0

data/lib/rdf/microdata/reader.rb

@@ -4,9 +4,12 @@ module RDF::Microdata
   ##
   # An Microdata parser in Ruby
   #
-  # Based on processing rules described here:
-  # @see http://dev.w3.org/html5/md/
+  # Based on processing rules, amended with the following:
+  # * property generation from tokens now uses the associated @itemtype as the basis for generation
+  # * implicit triples are not generated, only those with @item*
+  # * @datetime values are scanned lexically to find appropriate datatype
   #
+  # @see http://dev.w3.org/html5/md/
   # @author [Gregg Kellogg](http://kellogg-assoc.com/)
   class Reader < RDF::Reader
     format Format
@@ -39,8 +42,6 @@ module RDF::Microdata
     #   whether to intern all parsed URIs
     # @option options [#to_s]    :base_uri     (nil)
     #   the base URI to use when resolving relative URIs
-    # @option options [Boolean]  :rdf_terms     (false)
-    #   Generate URIs for itemprop terms based on namespace of itemtype
     # @option options [Array] :debug
     #   Array to place debug messages
     # @return [reader]
@@ -163,19 +164,6 @@ module RDF::Microdata
         base = RDF::URI("")
       end
       
-      ##
-      # 1. If the title element is not null, then generate the following triple:
-      #
-      #   subject:  the document's current address
-      #   predicate:  http://purl.org/dc/terms/title
-      #   object:  the concatenation of the data of all the child text nodes of the title element,
-      #            in tree order, as a plain literal, with the language information set from
-      #            the language of the title element, if it is not unknown. 
-      doc.css('html>head>title').each do |title|
-        lang = title.attribute('language')
-        add_triple(title, base, RDF::DC.title, title.inner_text)
-      end
-      
       # 2. For each a, area, and link element in the Document, run these substeps:
       #
       # * If the element does not have a rel attribute, then skip this element.
@@ -338,15 +326,10 @@ module RDF::Microdata
 
           predicate = if name_uri.absolute?
             name_uri
-          elsif @options[:rdf_terms]
+          else
             # Use the URI of the type to create URIs for @itemprop terms
             add_debug(element, "gentrips: rdf_type=#{rdf_type}")
             predicate = RDF::URI(rdf_type.to_s.sub(/([\/\#])[^\/\#]*$/, '\1' + name))
-          elsif !name.include?(':')
-            s = type.to_s
-            s += '%20' unless s[-1,1] == ':'
-            s += name
-            RDF::MD[s.gsub('#', '%23')]
           end
           add_debug(element, "gentrips(6.1.5): predicate=#{predicate}")
           
@@ -478,7 +461,12 @@ module RDF::Microdata
       when %w(object).include?(element.name)
         uri(element.attribute('data'), element.base)
       when %w(time).include?(element.name) && element.has_attribute?('datetime')
-        RDF::Literal::DateTime.new(element.attribute('datetime'))
+        # Lexically scan value and assign appropriate type, otherwise, leave untyped
+        v = element.attribute('datetime').to_s
+        datatype = %w(Date Time DateTime).map {|t| RDF::Literal.const_get(t)}.detect do |dt|
+          v.match(dt::GRAMMAR)
+        end || RDF::Literal
+        datatype.new(v)
       else
         RDF::Literal.new(element.text, :language => element.language)
       end

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: rdf-microdata
 version: !ruby/object:Gem::Version 
-  hash: 29
+  hash: 23
   prerelease: 
   segments: 
   - 0
-  - 1
-  - 3
-  version: 0.1.3
+  - 2
+  - 0
+  version: 0.2.0
 platform: ruby
 authors: 
 - Gregg Kellogg
@@ -15,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-07-26 00:00:00 -07:00
+date: 2011-08-12 00:00:00 -07:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency