active-fedora 4.0.0.rc1 → 4.0.0.rc2

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    active-fedora (4.0.0.rc1)
+    active-fedora (4.0.0.rc2)
       activeresource (>= 3.0.0)
       activesupport (>= 3.0.0)
       equivalent-xml
@@ -12,8 +12,8 @@ PATH
       om (>= 1.5.3)
       rdf
       rdf-rdfxml
+      rsolr
       rubydora (~> 0.5.4)
-      solr-ruby (>= 0.0.6)
       solrizer (~> 1.2.0)
       xml-simple (>= 1.0.12)
 
@@ -101,7 +101,6 @@ GEM
       nokogiri (>= 1.4.0)
       nori (~> 1.1)
       wasabi (~> 2.1)
-    solr-ruby (0.0.8)
     solrizer (1.2.0)
       daemons
       mediashelf-loggable (~> 0.4.7)
@@ -109,13 +108,6 @@ GEM
       om (>= 1.5.0)
       stomp
       xml-simple
-    solrizer-fedora (1.2.5)
-      active-fedora (>= 3.2.0)
-      activesupport (>= 3.0.11)
-      fastercsv
-      rsolr (= 1.0.6)
-      solr-ruby (>= 0.0.6)
-      solrizer (>= 1.0.0)
     stomp (1.2.0)
     wasabi (2.1.0)
       nokogiri (>= 1.4.0)
@@ -132,5 +124,4 @@ DEPENDENCIES
   mocha (>= 0.9.8)
   rake
   rspec (~> 2.0)
-  solrizer-fedora (~> 1.2.5)
   yard

data/History.txt

@@ -1,4 +1,4 @@
-4.0.0.rc1
+4.0.0.rc2
 Removed deprecations
   * allowing :fedora level in fedora.yml
   * automatic includes of Relationships and FileMethods is removed
@@ -6,6 +6,9 @@ Added sharding TODO add documentation
 Added find_document which determines the correct model and then casts the object to that.
 Improved loading from solr
 RDF datastreams
+Replaced solr-ruby with rsolr. Note: remove any calls to .hits
+load_instance is now deprecated, replaced with find
+Find alwasy casts to the appropriate object.
 
 3.3.2
 HYDRA-745 No need to require :url be present on external datastreams

data/active-fedora.gemspec

@@ -15,7 +15,7 @@ Gem::Specification.new do |s|
   s.rubyforge_project = "rubyfedora"
   s.rubygems_version = %q{1.3.7}
 
-  s.add_dependency('solr-ruby', '>= 0.0.6')
+  s.add_dependency('rsolr')
   s.add_dependency('xml-simple', '>= 1.0.12')
   s.add_dependency('mime-types', '>= 1.16')
   s.add_dependency('multipart-post', "= 1.1.2")
@@ -33,7 +33,7 @@ Gem::Specification.new do |s|
   s.add_development_dependency("RedCloth") # for RDoc formatting
   s.add_development_dependency("rake")
 #  s.add_development_dependency("rcov") # not ruby 1.9 compatible
-  s.add_development_dependency("solrizer-fedora", "~>1.2.5") # used by the fixtures rake tasks
+#  s.add_development_dependency("solrizer-fedora", "~>1.2.5") # used by the fixtures rake tasks
   s.add_development_dependency("jettywrapper", ">=1.2.0")
   s.add_development_dependency("rspec", "~> 2.0")
   s.add_development_dependency("mocha", ">= 0.9.8")

data/lib/active_fedora/associations/association_collection.rb

@@ -131,7 +131,7 @@ module ActiveFedora
 
       def find_target
         return [] if @finder_query.empty?
-        solr_result = SolrService.instance.conn.query(@finder_query, :rows=>1000)
+        solr_result = SolrService.query(@finder_query, :rows=>1000)
 #TODO, don't reify, just store the solr results and lazily reify.
         return ActiveFedora::SolrService.reify_solr_results(solr_result)
       end

data/lib/active_fedora/associations/belongs_to_association.rb

@@ -27,7 +27,7 @@ module ActiveFedora
           pid = @owner.ids_for_outbound(@reflection.options[:property]).first
           return if pid.nil?
           query = ActiveFedora::SolrService.construct_query_for_pids([pid])
-          solr_result = SolrService.instance.conn.query(query)
+          solr_result = SolrService.query(query) 
           return ActiveFedora::SolrService.reify_solr_results(solr_result).first
         end
 

data/lib/active_fedora/associations/has_and_belongs_to_many_association.rb

@@ -10,7 +10,7 @@ module ActiveFedora
           pids = @owner.ids_for_outbound(@reflection.options[:property])
           return [] if pids.empty?
           query = ActiveFedora::SolrService.construct_query_for_pids(pids)
-          solr_result = SolrService.instance.conn.query(query)
+          solr_result = SolrService.query(query)
           return ActiveFedora::SolrService.reify_solr_results(solr_result)
       end
 

data/lib/active_fedora/base.rb

@@ -271,13 +271,17 @@ module ActiveFedora
     # If opts[:model_only] == true, the base object metadata and the RELS-EXT datastream will be omitted.  This is mainly to support shelver, which calls .to_solr for each model an object subscribes to. 
     def to_solr(solr_doc = Hash.new, opts={})
       unless opts[:model_only]
-        solr_doc.merge!(SOLR_DOCUMENT_ID.to_sym => pid, ActiveFedora::SolrService.solr_name(:system_create, :date) => self.create_date, ActiveFedora::SolrService.solr_name(:system_modified, :date) => self.modified_date, ActiveFedora::SolrService.solr_name(:active_fedora_model, :symbol) => self.class.inspect)
+        c_time = create_date
+        c_time = Time.parse(c_time) unless c_time.is_a?(Time)
+        m_time = modified_date
+        m_time = Time.parse(m_time) unless m_time.is_a?(Time)
+        solr_doc.merge!(SOLR_DOCUMENT_ID.to_sym => pid, ActiveFedora::SolrService.solr_name(:system_create, :date) => c_time.utc.xmlschema, ActiveFedora::SolrService.solr_name(:system_modified, :date) => m_time.utc.xmlschema, ActiveFedora::SolrService.solr_name(:active_fedora_model, :symbol) => self.class.inspect)
         solrize_profile(solr_doc)
       end
       datastreams.each_value do |ds|
         solr_doc = ds.solrize_profile(solr_doc)
         ds.ensure_xml_loaded if ds.respond_to? :ensure_xml_loaded  ### Can't put this in the model because it's often implemented in Solrizer::XML::TerminologyBasedSolrizer 
-        solr_doc = ds.to_solr(solr_doc) if ds.kind_of?(ActiveFedora::MetadataDatastream) || ds.kind_of?(ActiveFedora::NokogiriDatastream) 
+        solr_doc = ds.to_solr(solr_doc) if ds.kind_of?(ActiveFedora::RDFDatastream) || ds.kind_of?(ActiveFedora::NokogiriDatastream) || ds.kind_of?(ActiveFedora::MetadataDatastream)
       end
       solr_doc = solrize_relationships(solr_doc) unless opts[:model_only]
       solr_doc
@@ -326,7 +330,7 @@ module ActiveFedora
       if self.inner_object.is_a? DigitalObject
         raise "#{self.inspect} is already a full digital object"
       end
-      self.class.load_instance self.pid
+      self.class.find self.pid
     end
     
     # ** EXPERIMENTAL **
@@ -341,7 +345,7 @@ module ActiveFedora
     
     # ** EXPERIMENTAL **
     #
-    # This method can be used instead of ActiveFedora::Model::ClassMethods.load_instance.  
+    # This method can be used instead of ActiveFedora::Model::ClassMethods.find.  
     # It works similarly except it populates an object from Solr instead of Fedora.
     # It is most useful for objects used in read-only displays in order to speed up loading time.  If only
     # a pid is passed in it will query solr for a corresponding solr document and then use it
@@ -351,12 +355,12 @@ module ActiveFedora
     # one passed to populate the object.
     #
     # It will anything stored within solr such as metadata and relationships.  Non-metadata datastreams will not
-    # be loaded and if needed you should use load_instance instead.
+    # be loaded and if needed you should use find instead.
     def self.load_instance_from_solr(pid,solr_doc=nil)
       if solr_doc.nil?
         result = find_by_solr(pid)
         raise "Object #{pid} not found in solr" if result.nil?
-        solr_doc = result.hits.first
+        solr_doc = result.first
         #double check pid and id in record match
         raise "Object #{pid} not found in Solr" unless !result.nil? && !solr_doc.nil? && pid == solr_doc[SOLR_DOCUMENT_ID]
       else

data/lib/active_fedora/file_management.rb

@@ -45,7 +45,7 @@ module ActiveFedora
       # collection_members_append(obj)
       unless obj.kind_of? ActiveFedora::Base
         begin
-          obj = ActiveFedora::Base.load_instance(obj)
+          obj = ActiveFedora::Base.find(obj)
         rescue ActiveFedora::ObjectNotFoundError
           "You must provide either an ActiveFedora object or a valid pid to add it as a file object.  You submitted #{obj.inspect}"
         end

data/lib/active_fedora/fixture_loader.rb

@@ -12,7 +12,7 @@ module ActiveFedora
 
     def self.delete(pid)
       begin
-        ActiveFedora::Base.load_instance(pid).delete
+        ActiveFedora::Base.find(pid).delete
         1
       rescue ActiveFedora::ObjectNotFoundError
         logger.debug "The object #{pid} has already been deleted (or was never created)."

data/lib/active_fedora/model.rb

@@ -44,12 +44,6 @@ module ActiveFedora
       result
     end
 
-    def add_metadata
-    end
-
-    def datastream
-    end
-
 
     #
     # =Class Methods
@@ -80,20 +74,10 @@ module ActiveFedora
       # @example this will return an instance of Book, even if the object hydra:dataset1 asserts that it is a Dataset
       #   Book.load_instance("hydra:dataset1") 
       def load_instance(pid)
-        self.allocate.init_with(DigitalObject.find(self, pid))
+        ActiveSupport::Deprecation.warn("load_instance is deprecated.  Use find instead")
+        find(pid)
       end
  
-      # Retrieve the Fedora object with te given pid, explore the returned object, determine its model 
-      # using #{known_models_for} and cast to that class.
-      # @param [String] pid of the object to load
-      #
-      # @example because the object hydra:dataset1 asserts it is a Dataset (hasModel info:fedora/afmodel:Dataset), return a Dataset object (not a Book).
-      #   Book.find_document("hydra:dataset1") 
-      def find_document(pid)
-        af_base = load_instance(pid)
-        the_model = ActiveFedora::ContentModel.known_models_for( af_base ).first
-        af_base.adapt_to(the_model)
-      end
 
       
       # Returns a suitable uri object for :has_model
@@ -120,19 +104,20 @@ module ActiveFedora
         if args == :all
           escaped_class_uri = SolrService.escape_uri_for_query(self.to_class_uri)
           q = "#{ActiveFedora::SolrService.solr_name(:has_model, :symbol)}:#{escaped_class_uri}"
-          hits = SolrService.instance.conn.query(q, :rows=>opts[:rows]).hits 
+          hits = SolrService.query(q, :rows=>opts[:rows]) 
           return hits.map do |hit|
              pid = hit[SOLR_DOCUMENT_ID]
-             load_instance(pid)
+             find_one(pid)
           end
         elsif args.class == String
-          return load_instance(args)
+          return find_one(args)
         end
       end
 
+
       def find_model(pid)
-        ActiveSupport::Deprection.warn("find_model is deprecated.  Use load_instance instead")
-        load_instance(pid)
+        ActiveSupport::Deprecation.warn("find_model is deprecated.  Use find instead")
+        find(pid)
       end
 
 
@@ -142,7 +127,7 @@ module ActiveFedora
           escaped_class_uri = SolrService.escape_uri_for_query(self.to_class_uri)
           q = "#{ActiveFedora::SolrService.solr_name(:has_model, :symbol)}:#{escaped_class_uri}"
           q << " AND #{args[:conditions]}" if args[:conditions]
-          SolrService.instance.conn.query(q, :rows=>0).total_hits
+          SolrService.query(q, :raw=>true, :rows=>0)['response']['numFound']
       end
 
       #Sends a query directly to SolrService
@@ -164,10 +149,10 @@ module ActiveFedora
       def find_by_solr(query, args={})
         if query == :all
           escaped_class_name = self.name.gsub(/(:)/, '\\:')
-          SolrService.instance.conn.query("#{ActiveFedora::SolrService.solr_name(:active_fedora_model, :symbol)}:#{escaped_class_name}", args)
+          SolrService.query("#{ActiveFedora::SolrService.solr_name(:active_fedora_model, :symbol)}:#{escaped_class_name}", args) 
         elsif query.class == String
           escaped_id = query.gsub(/(:)/, '\\:')          
-          SolrService.instance.conn.query("#{SOLR_DOCUMENT_ID}:#{escaped_id}", args)
+          SolrService.query("#{SOLR_DOCUMENT_ID}:#{escaped_id}", args) 
         end
       end
 
@@ -218,20 +203,20 @@ module ActiveFedora
       
         #set default sort to created date ascending
         unless query_opts.include?(:sort)
-          query_opts.merge!({:sort=>[ActiveFedora::SolrService.solr_name(:system_create,:date)=>:ascending]}) 
+          query_opts.merge!({:sort=>[ActiveFedora::SolrService.solr_name(:system_create,:date)+' asc']}) 
         else
           #need to convert to solr names for all fields
           sort_array =[]
         
           opts[:sort].collect do |sort|
-            sort_direction = :ascending
+            sort_direction = 'ascending'
             if sort.respond_to?(:keys)
               key = sort.keys[0]
               sort_direction = sort[key]
-              sort_direction =~ /^desc/ ? sort_direction = :descending : :ascending
             else
               key = sort.to_s
             end
+            sort_direction = sort_direction =~ /^desc/ ? 'desc' : 'asc'
             field_name = key
             
             if key.to_s =~ /^system_create/
@@ -246,14 +231,14 @@ module ActiveFedora
             if class_fields.include?(field_name.to_sym)
               solr_name = ActiveFedora::SolrService.solr_name(key,class_fields[field_name.to_sym][:type])
             end
-            sort_array.push({solr_name=>sort_direction})
+            sort_array.push("#{solr_name} #{sort_direction}")
           end
         
-          query_opts[:sort] = sort_array
+          query_opts[:sort] = sort_array.join(",")
         end
 
         logger.debug "Querying solr for #{self.name} objects with query: '#{query}'"
-    	  results = ActiveFedora::SolrService.instance.conn.query(query,query_opts)
+        SolrService.query(query, query_opts) 
       end
     
       def class_fields
@@ -275,6 +260,22 @@ module ActiveFedora
         instance_variable_get("@#{name}")
       end
 
+      private 
+      # Retrieve the Fedora object with te given pid, explore the returned object, determine its model 
+      # using #{known_models_for} and cast to that class.
+      # @param [String] pid of the object to load
+      #
+      # @example because the object hydra:dataset1 asserts it is a Dataset (hasModel info:fedora/afmodel:Dataset), return a Dataset object (not a Book).
+      #   Book.find_document("hydra:dataset1") 
+      def find_one(pid)
+        af_base = self.allocate.init_with(DigitalObject.find(self, pid))
+        the_model = ActiveFedora::ContentModel.known_models_for( af_base ).first
+        if af_base.class != the_model
+          return af_base.adapt_to(the_model)
+        end
+        af_base
+      end
+
     end
     def create_property_getter(property) # :nodoc:
 
@@ -295,12 +296,12 @@ module ActiveFedora
 
     private 
     
-    def self.class_exists?(class_name)
-      klass = class_name.constantize
-      return klass.is_a?(Class)
-    rescue NameError
-      return false
-    end
+      def self.class_exists?(class_name)
+        klass = class_name.constantize
+        return klass.is_a?(Class)
+      rescue NameError
+        return false
+      end
     
   end
 end

data/lib/active_fedora/nokogiri_datastream.rb

@@ -340,7 +340,7 @@ module ActiveFedora
     #   => {"person_0_role_text"=>{"0"=>"role1", "1"=>"role2", "2"=>"role3"}, "person_1_role_text"=>{"0"=>"otherrole1", "1"=>"otherrole2"}} 
     def update_values(params={})
       if @internal_solr_doc
-        raise "No update performed, this object was initialized via Solr instead of Fedora and is therefore read-only.  Please utilize ActiveFedora::Base.load_instance to first load object via Fedora instead."
+        raise "No update performed, this object was initialized via Solr instead of Fedora and is therefore read-only.  Please utilize ActiveFedora::Base.find to first load object via Fedora instead."
       else
         result = om_update_values(params)
         self.dirty= true

data/lib/active_fedora/persistence.rb

@@ -59,18 +59,12 @@ module ActiveFedora
         raise ObjectNotFoundError, "Unable to find #{pid} in the repository"
       end
       if ENABLE_SOLR_UPDATES
-        ActiveFedora::SolrService.instance.conn.delete(pid) 
-        # if defined?( Solrizer::Solrizer ) 
-        #   solrizer = Solrizer::Solrizer.new
-        #   solrizer.solrize_delete(pid)
-        # end
+        solr = ActiveFedora::SolrService.instance.conn
+        solr.delete_by_id(pid) 
+        solr.commit
       end
     end
 
-
-
-  private
-    
     # Updates Solr index with self.
     def update_index
       if defined?( Solrizer::Fedora::Solrizer ) 
@@ -78,11 +72,15 @@ module ActiveFedora
         solrizer = Solrizer::Fedora::Solrizer.new
         solrizer.solrize( self )
       else
-        #logger.info("Trying to update solr for pid: #{pid}")
-        SolrService.instance.conn.update(self.to_solr)
+        SolrService.instance.conn.add(self.to_solr)
+        SolrService.instance.conn.commit
       end
     end
 
+
+  private
+    
+
     # Deals with preparing new object to be saved to Fedora, then pushes it and its datastreams into Fedora. 
     def create
       assign_pid

data/lib/active_fedora/predicates.rb

@@ -28,8 +28,8 @@ module ActiveFedora
       vocabularies[xmlns][rel_predicate] 
     end
 
-    def self.vocabularies
-      @vocabularies ||= {}
+    def self.vocabularies(vocabs = {})
+      @vocabularies ||= vocabs
       predicate_mappings.keys.each do |ns| 
         @vocabularies[ns] = RDF::Vocabulary.new(ns) unless @vocabularies.has_key? ns
       end

data/lib/active_fedora/rdf_datastream.rb

@@ -5,9 +5,22 @@ module ActiveFedora
     module ModelMethods
       extend ActiveSupport::Concern
       module ClassMethods
+        attr_accessor :vocabularies
         def config
           ActiveFedora::Predicates.predicate_config
         end
+        def register_vocabularies(*vocabs)
+          @vocabularies = {}
+          vocabs.each do |v|
+            if v.respond_to? :property and v.respond_to? :to_uri
+              @vocabularies[v.to_uri] = v 
+            else
+              raise "not an RDF vocabulary: #{v}"
+            end
+          end
+          ActiveFedora::Predicates.vocabularies(vocabularies)
+          @vocabularies
+        end
         def map_predicates(&block)
           yield self
         end
@@ -16,19 +29,23 @@ module ActiveFedora
           raise "mapping must specify RDF vocabulary as :in argument" unless args.has_key? :in
           vocab = args[:in]
           predicate = args.fetch(:to, name)
+          data_type = args.fetch(:type, :string)
           raise "Vocabulary '#{vocab.inspect}' does not define property '#{predicate.inspect}'" unless vocab.respond_to? predicate
           vocab = vocab.to_s
+          # this is needed for AF::Predicates integration
+          # stuff data_type in there too for to_solr support
           if config 
             if config[:predicate_mapping].has_key? vocab
               config[:predicate_mapping][vocab][name] = predicate
+              config[:predicate_mapping][vocab]["#{name}type".to_sym] = data_type
             else
-              config[:predicate_mapping][vocab] = { name => predicate }
+              config[:predicate_mapping][vocab] = { name => predicate, "#{name}type".to_sym => data_type }
            end
           else
             config = {
               :default_namespace => vocab,
               :predicate_mapping => {
-                vocab => { name => predicate }
+                vocab => { name => predicate, "#{name}type".to_sym => data_type }
               }
             }
           end
@@ -85,11 +102,40 @@ module ActiveFedora
       end
     end
 
+    # returns a Hash, e.g.: {field => {:values => values, :type => type}, ...}
+    def fields
+      field_map = {}
+      graph.relationships.each do |predicate, values|
+        vocab_sym, name = predicate.qname
+        vocabs_list = self.class.vocabularies.select { |ns, v| v.__prefix__ == vocab_sym }
+        vocab = vocabs_list.first.first.to_s
+        mapped_names = self.class.config[:predicate_mapping][vocab].select {|k, v| v.to_s == name.to_s}
+        name = mapped_names.first.first.to_s
+        type = self.class.config[:predicate_mapping][vocab]["#{name}type".to_sym]
+        field_map[name.to_sym] = {:values => values.map {|v| v.to_s}, :type => type}
+      end
+      field_map
+    end
+
+    def to_solr(solr_doc = Hash.new) # :nodoc:
+      fields.each do |field_key, field_info|
+        if field_info.has_key?(:values) && !field_info[:values].nil?
+          field_symbol = ActiveFedora::SolrService.solr_name(field_key, field_info[:type])
+          values = field_info[:values]
+          values = [values] unless values.respond_to? :each
+          values.each do |val|    
+            ::Solrizer::Extractor.insert_solr_field_value(solr_doc, field_symbol, val)         
+          end
+        end
+      end
+      solr_doc
+    end
+
     # @param [Symbol, RDF::URI] predicate  the predicate to insert into the graph
     def find_predicate(predicate)
       predicate = predicate.to_sym unless predicate.kind_of? RDF::URI
       result = ActiveFedora::Predicates.find_predicate(predicate)
-      return RDF::URI(result.reverse.to_s)
+      RDF::URI(result.reverse.to_s)
     end
 
     def graph
@@ -109,10 +155,6 @@ module ActiveFedora
       TermProxy.new(graph, predicate, values)
     end
 
-    def to_solr
-      # TODO
-    end
-
     # if there are any existing statements with this predicate, replace them
     # @param [Symbol, RDF::URI] predicate  the predicate to insert into the graph
     def set_value(predicate, args)