active-fedora 4.1.0 → 4.2.0

data/.rvmrc

@@ -3,7 +3,7 @@
 # This is an RVM Project .rvmrc file, used to automatically load the ruby
 # development environment upon cd'ing into the directory
 
-ruby_string="1.9.3-p125"
+ruby_string="1.9.3-p194"
 gemset_name="active_fedora_4.0"
 
 # Install rubies when used instead of only displaying a warning and exiting

data/Gemfile

@@ -4,5 +4,13 @@ source "http://rubygems.org"
 
 gemspec
 
-# gem 'ruby-debug', :platform => :ruby_18
-# gem 'debugger' # for ruby 1.9.3
+group :development, :test do
+  gem 'ruby-debug', :platform => :ruby_18
+#  gem 'debugger', :platform => :ruby_19
+
+  gem 'rcov', :platform => :mri_18
+  gem 'simplecov', :platform => :mri_19
+  gem 'simplecov-rcov', :platform => :mri_19
+end
+
+gem 'jruby-openssl', :platform=> :jruby

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    active-fedora (4.1.0)
+    active-fedora (4.2.0)
       activeresource (>= 3.0.0)
       activesupport (>= 3.0.0)
       equivalent-xml
@@ -11,9 +11,9 @@ PATH
       nokogiri
       om (~> 1.6.0)
       rdf
-      rdf-rdfxml (= 0.3.5)
+      rdf-rdfxml (~> 0.3.8)
       rsolr
-      rubydora (~> 0.5.8)
+      rubydora (~> 0.5.9)
       solrizer (~> 1.2.0)
       xml-simple (>= 1.0.12)
 
@@ -21,28 +21,30 @@ GEM
   remote: http://rubygems.org/
   specs:
     RedCloth (4.2.9)
-    activemodel (3.2.2)
-      activesupport (= 3.2.2)
+    activemodel (3.2.3)
+      activesupport (= 3.2.3)
       builder (~> 3.0.0)
-    activeresource (3.2.2)
-      activemodel (= 3.2.2)
-      activesupport (= 3.2.2)
-    activesupport (3.2.2)
+    activeresource (3.2.3)
+      activemodel (= 3.2.3)
+      activesupport (= 3.2.3)
+    activesupport (3.2.3)
       i18n (~> 0.6)
       multi_json (~> 1.0)
     addressable (2.2.8)
     akami (1.0.0)
       gyoku (>= 0.4.0)
+    backports (2.5.3)
     builder (3.0.0)
-    childprocess (0.3.1)
+    childprocess (0.3.2)
       ffi (~> 1.0.6)
+    columnize (0.3.6)
     daemons (1.1.8)
     diff-lcs (1.1.3)
     equivalent-xml (0.2.9)
       nokogiri (>= 1.4.3)
-    fastercsv (1.5.4)
+    fastercsv (1.5.5)
     ffi (1.0.11)
-    gyoku (0.4.4)
+    gyoku (0.4.5)
       builder (>= 2.1.2)
     httpi (0.9.7)
       rack
@@ -53,13 +55,15 @@ GEM
       i18n
       logger
       mediashelf-loggable
+    linecache (0.46)
+      rbx-require-relative (> 0.0.4)
     logger (1.2.8)
     mediashelf-loggable (0.4.9)
     metaclass (0.0.1)
     mime-types (1.18)
     mocha (0.10.5)
       metaclass (~> 0.0.1)
-    multi_json (1.1.0)
+    multi_json (1.3.5)
     multipart-post (1.1.2)
     nokogiri (1.5.2)
     nori (1.1.0)
@@ -68,24 +72,35 @@ GEM
       nokogiri (>= 1.4.2)
     rack (1.4.1)
     rake (0.9.2.2)
+    rbx-require-relative (0.0.9)
+    rcov (1.0.0)
     rdf (0.3.5.2)
       addressable (>= 2.2.6)
-    rdf-rdfxml (0.3.5)
-      nokogiri (>= 1.4.4)
+    rdf-rdfxml (0.3.8)
+      rdf (>= 0.3.4)
+      rdf-xsd (>= 0.3.5)
+    rdf-xsd (0.3.7)
+      backports
+      nokogiri (>= 1.5.0)
       rdf (>= 0.3.4)
     rest-client (1.6.7)
       mime-types (>= 1.16)
     rsolr (1.0.8)
       builder (>= 2.1.2)
-    rspec (2.9.0)
-      rspec-core (~> 2.9.0)
-      rspec-expectations (~> 2.9.0)
-      rspec-mocks (~> 2.9.0)
-    rspec-core (2.9.0)
-    rspec-expectations (2.9.0)
+    rspec (2.10.0)
+      rspec-core (~> 2.10.0)
+      rspec-expectations (~> 2.10.0)
+      rspec-mocks (~> 2.10.0)
+    rspec-core (2.10.1)
+    rspec-expectations (2.10.0)
       diff-lcs (~> 1.1.3)
-    rspec-mocks (2.9.0)
-    rubydora (0.5.8)
+    rspec-mocks (2.10.1)
+    ruby-debug (0.10.4)
+      columnize (>= 0.1)
+      ruby-debug-base (~> 0.10.4.0)
+    ruby-debug-base (0.10.4)
+      linecache (>= 0.3)
+    rubydora (0.5.9)
       activemodel
       activesupport
       fastercsv
@@ -101,7 +116,13 @@ GEM
       nokogiri (>= 1.4.0)
       nori (~> 1.1)
       wasabi (~> 2.1)
-    solrizer (1.2.0)
+    simplecov (0.6.4)
+      multi_json (~> 1.0)
+      simplecov-html (~> 0.5.3)
+    simplecov-html (0.5.3)
+    simplecov-rcov (0.2.3)
+      simplecov (>= 0.4.1)
+    solrizer (1.2.1)
       daemons
       mediashelf-loggable (~> 0.4.7)
       nokogiri
@@ -109,10 +130,10 @@ GEM
       stomp
       xml-simple
     stomp (1.2.2)
-    wasabi (2.1.0)
+    wasabi (2.1.1)
       nokogiri (>= 1.4.0)
     xml-simple (1.1.1)
-    yard (0.7.5)
+    yard (0.8.1)
 
 PLATFORMS
   ruby
@@ -121,7 +142,12 @@ DEPENDENCIES
   RedCloth
   active-fedora!
   jettywrapper (>= 1.2.0)
-  mocha (>= 0.9.8)
+  jruby-openssl
+  mocha (= 0.10.5)
   rake
+  rcov
   rspec (>= 2.9.0)
+  ruby-debug
+  simplecov
+  simplecov-rcov
   yard

data/History.txt

@@ -1,4 +1,25 @@
-4.0.0.rc20
+4.2.0
+Added Base.find_each which allows yielding of each result
+Added Base.find_in_batches which allows yielding of a chunk of solr results
+Added ActiveFedora::NtriplesRDFDatastream
+Rubydora to 0.5.9
+HYDRA-726 integration tests verify versionable attribute of datastreams
+HYDRA-811 allow setting a pid after object is initialized, but before it is saved
+find(:all) must use solr paramater qt=standard
+HYDRA-812 belongs_to should replace assertions, even if the asserted object is not found.
+HYDRA-814 add clone()
+HYDRA-815 give :type a default value (ActiveFedora::Datastream) for has_file_datastream
+HYDRA-816 Sharding works automatically if multiple connections are specified in fedora.yml
+HYDRA-818 Assign_pid should work correctly when the config is not sharded.
+
+4.1.0
+ActiveFedora::Base.find() now supports filtering by solr fields (boolean AND).
+* example:  ModsAsset.find('title_t' => 'Song of Fire and Ice','author_t'=>['Agatha Christie', 'Dr. Seuss']
+ActiveFedora::Base.find_with_conditions which is the replacement for ActiveFedora::Base.find_by_fields_by_solr (previously deprecated)
+YAML configurations are loaded through ERB, allowing reference to evaluated Ruby or environment variables
+When setting ng_xml= with a Nokogiri node, cast it to a new Nokogiri document
+
+4.0.0
 Removed deprecations
   * allowing :fedora level in fedora.yml
   * automatic includes of Relationships and FileMethods is removed

data/README.textile

@@ -51,14 +51,14 @@ Then open a new terminal, go to your ActiveFedora source directory, and import f
 
 <pre>
   export FEDORA_HOME=/path/to/hydra/jetty/fedora/default
-  rake active_fedora:load_fixtures RAILS_ENV=test
+  rake active_fedora:load_fixtures environment=test
 </pre>
 
 This does the equivalent of:
 
 <pre>
   $FEDORA_HOME/client/bin/fedora-ingest-demos.sh localhost 8983 fedoraAdmin fedoraAdmin http
-  rake af:import_fixture pid=hydrangea:fixture_mods_article1 RAILS_ENV=test
+  rake af:import_fixture pid=hydrangea:fixture_mods_article1 environment=test
 </pre>
 
 Now you're ready to run the tests.  In the directory where active_fedora is installed, run

data/active-fedora.gemspec

@@ -26,15 +26,15 @@ Gem::Specification.new do |s|
   s.add_dependency("activesupport", '>= 3.0.0')
   s.add_dependency("mediashelf-loggable")
   s.add_dependency("equivalent-xml")
-  s.add_dependency("rubydora", '~>0.5.8')
+  s.add_dependency("rubydora", '~>0.5.9')
   s.add_dependency("rdf")
-  s.add_dependency("rdf-rdfxml", '0.3.5') # 0.3.6 is broken
+  s.add_dependency("rdf-rdfxml", '~>0.3.8')
   s.add_development_dependency("yard")
   s.add_development_dependency("RedCloth") # for RDoc formatting
   s.add_development_dependency("rake")
   s.add_development_dependency("jettywrapper", ">=1.2.0")
   s.add_development_dependency("rspec", ">= 2.9.0")
-  s.add_development_dependency("mocha", ">= 0.9.8")
+  s.add_development_dependency("mocha", "0.10.5")
   
   s.files         = `git ls-files`.split("\n")
   s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")

data/config/predicate_mappings.yml

@@ -47,3 +47,5 @@
     :has_model: hasModel
   http://www.openarchives.org/OAI/2.0/: 
     :oai_item_id: itemID
+  http://projecthydra.org/ns/relations#:
+    :is_governed_by: isGovernedBy

data/lib/active_fedora/associations/belongs_to_association.rb

@@ -4,15 +4,11 @@ module ActiveFedora
 
       def replace(record)
         if record.nil?
-          ### TODO a more efficient way of doing this would be to write a clear_relationship method
-          old_record = find_target
-          @owner.remove_relationship(@reflection.options[:property], old_record) unless old_record.nil?
+          @owner.clear_relationship(@reflection.options[:property])
         else
           raise_on_type_mismatch(record)
 
-          ### TODO a more efficient way of doing this would be to write a clear_relationship method
-          old_record = find_target
-          @owner.remove_relationship(@reflection.options[:property], old_record) unless old_record.nil?
+          @owner.clear_relationship(@reflection.options[:property])
 
           @target = (AssociationProxy === record ? record.target : record)
           @owner.add_relationship(@reflection.options[:property], record) unless record.new_record?

data/lib/active_fedora/base.rb

@@ -1,5 +1,6 @@
 SOLR_DOCUMENT_ID = "id" unless (defined?(SOLR_DOCUMENT_ID) && !SOLR_DOCUMENT_ID.nil?)
 ENABLE_SOLR_UPDATES = true unless defined?(ENABLE_SOLR_UPDATES)
+require "digest"
 
 module ActiveFedora
   
@@ -132,10 +133,19 @@ module ActiveFedora
       fedora_connection[idx].connection
     end
 
-    #If you want to use sharding override this method with your strategy
+    # This is where your sharding strategy is implemented -- it's how we figure out which shard an object will be (or was) written to.
+    # Given a pid, it decides which shard that pid will be written to (and thus retrieved from).
+    # For a given pid, as long as your shard configuration remains the same it will always return the same value.
+    # If you're not using sharding, this will always return 0, meaning use the first/only Fedora Repository in your configuration.
+    # Default strategy runs a modulo of the md5 of the pid against the number of shards.
+    # If you want to use a different sharding strategy, override this method.  Make sure that it will always return the same value for a given pid and shard configuration.
     #@return [Integer] the index of the shard this object is stored in
     def self.shard_index(pid)
-      0
+      if ActiveFedora.config.sharded?
+        Digest::MD5.hexdigest(pid).hex % ActiveFedora.config.credentials.length
+      else
+        0
+      end
     end
     
 
@@ -149,15 +159,42 @@ module ActiveFedora
       obj
     end
 
+    def clone
+      new_object = self.class.create
+      clone_into(new_object)
+    end
+
+    # Clone the datastreams from this object into the provided object, while preserving the pid of the provided object
+    # @param [Base] new_object clone into this object
+    def clone_into(new_object)
+      rels = Nokogiri::XML( rels_ext.content)
+      rels.xpath("//rdf:Description/@rdf:about").first.value = new_object.internal_uri
+      new_object.rels_ext.content = rels.to_xml
+      new_object.rels_ext.dirty = false
+
+      datastreams.each do |k, v|
+        next if k == 'RELS-EXT'
+        new_object.datastreams[k].content = v.content
+      end
+      new_object if new_object.save
+    end
 
     ### if you are doing sharding, override this method to do something other than use a sequence
     # @return [String] the unique pid for a new object
     def self.assign_pid(obj)
-        args = {}
-        args[:namespace] = obj.namespace if obj.namespace
-        raise RuntimeError, "When using shards, you must override #{self}.assign_pid()" if ActiveFedora.config.sharded?
-        d = REXML::Document.new(connection_for_pid('0').next_pid(args))
-        d.elements['//pid'].text
+      args = {}
+      args[:namespace] = obj.namespace if obj.namespace
+      # TODO: This juggling of Fedora credentials & establishing connections should be handled by 
+      # an establish_fedora_connection method,possibly wrap it all into a fedora_connection method - MZ 06-05-2012
+      if ActiveFedora.config.sharded?
+        credentials = ActiveFedora.config.credentials[0]
+      else
+        credentials = ActiveFedora.config.credentials
+      end
+      fedora_connection[0] ||= ActiveFedora::RubydoraConnection.new(credentials)
+      d = REXML::Document.new( fedora_connection[0].connection.next_pid(args))
+      pid =d.elements['//pid'].text
+      pid
     end
 
     def inner_object # :nodoc

data/lib/active_fedora/datastreams.rb

@@ -21,8 +21,10 @@ module ActiveFedora
 
     def serialize_datastreams
       datastreams.each {|k, ds| ds.serialize! }
-      self.metadata_is_dirty = datastreams.any? {|k,ds| ds.changed? && (ds.class.included_modules.include?(ActiveFedora::MetadataDatastreamHelper) || ds.instance_of?(ActiveFedora::RelsExtDatastream))}
-      true
+      self.metadata_is_dirty = datastreams.any? do |k,ds| 
+        ds.changed? && (ds.class.included_modules.include?(ActiveFedora::MetadataDatastreamHelper) || ds.instance_of?(ActiveFedora::RelsExtDatastream) || ds.kind_of?(ActiveFedora::RDFDatastream))
+      end
+     true
     end
 
     # Adds the disseminator location to the datastream after the pid has been established
@@ -259,17 +261,17 @@ module ActiveFedora
 
       # Specify the attributes of a file bearing datastream 
       #
-      # === Options
-      # [:name]
-      #   The dsid of the datastream
-      # [:type]
-      #   The class the datastream should have
-      # [:label]
-      #   The default value to put in the dsLabel field
-      # [:control_group]
-      #   The type of controlGroup to store the datastream as. Defaults to M
-      def has_file_datastream(args)
-        ds_specs[args.fetch(:name, "content")]= {:type => args[:type], :label =>  args.fetch(:label,"File Datastream"), :control_group => args.fetch(:control_group,"M")}
+      # @param [Hash] args 
+      # @option args :name ("content") The dsid of the datastream
+      # @option args :type (ActiveFedora::Datastream) The class the datastream should have
+      # @option args :label ("File Datastream") The default value to put in the dsLabel field
+      # @option args :control_group ("M") The type of controlGroup to store the datastream as. Defaults to M
+      def has_file_datastream(args = {})
+        ds_specs[args.fetch(:name, "content")]= {
+            :type => args.fetch(:type,ActiveFedora::Datastream),
+            :label =>  args.fetch(:label,"File Datastream"),
+            :control_group => args.fetch(:control_group,"M")
+        }
       end
     end
 

data/lib/active_fedora/model.rb

@@ -102,23 +102,60 @@ module ActiveFedora
       # @option opts [Integer] :rows when :all is passed, the maximum number of rows to load from solr
       # @option opts [Boolean] :cast when true, examine the model and cast it to the first known cModel
       def find(args, opts={})
-        opts = {:rows=>25}.merge(opts)
-        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.query(q, :rows=>opts[:rows]) 
-          return hits.map do |hit|
-             pid = hit[SOLR_DOCUMENT_ID]
-             find_one(pid, opts[:cast])
-          end
-        elsif args.class == Hash 
-          hits = find_with_conditions(args, opts)
-          return hits.map do |hit|
-             pid = hit[SOLR_DOCUMENT_ID]
-             find_one(pid, opts[:cast])
+        return find_one(args, opts[:cast]) if args.class == String
+        args = {} if args == :all
+        results = []
+        find_each(args, opts) do |obj|
+           results << obj
+        end
+        results
+      end
+
+
+      # Yields each batch of solr records that was found by the find +options+ as
+      # an array. The size of each batch is set by the <tt>:batch_size</tt>
+      # option; the default is 1000.
+      #
+      # Returns a solr result matching the supplied conditions
+      # @param[Hash] conditions solr conditions to match
+      # @param[Hash] options 
+      # @option opts [Array] :sort a list of fields to sort by 
+      # @option opts [Array] :rows number of rows to return
+      #
+      # @example
+      #  Person.find_in_batches('age_t'=>'21', {:batch_size=>50}) do |group|
+      #  group.each { |person| puts person['name_t'] }
+      #  end
+      
+      def find_in_batches conditions, opts={}
+        opts[:q] = create_query(conditions)
+        opts[:qt] = 'standard'
+        #set default sort to created date ascending
+        unless opts.include?(:sort)
+          opts[:sort]=[ActiveFedora::SolrService.solr_name(:system_create,:date)+' asc'] 
+        end
+
+        batch_size = opts.delete(:batch_size) || 1000
+
+        counter = 0
+        begin
+          counter += 1
+          response = ActiveFedora::SolrService.instance.conn.paginate counter, batch_size, "select", :params => opts
+          docs = response["response"]["docs"]
+          yield docs
+        end while docs.has_next? 
+      end
+
+      # Yields the found ActiveFedora::Base object to the passed block
+      #
+      # @param [Hash] conditions the conditions for the solr search to match
+      # @param [Hash] opts 
+      # @option opts [Boolean] :cast when true, examine the model and cast it to the first known cModel
+      def find_each( conditions={}, opts={})
+        find_in_batches(conditions, opts.merge({:fl=>SOLR_DOCUMENT_ID})) do |group|
+          group.each do |hit|
+            yield(find_one(hit[SOLR_DOCUMENT_ID], opts[:cast]))
           end
-        elsif args.class == String
-          return find_one(args, opts[:cast])
         end
       end
 
@@ -131,6 +168,7 @@ module ActiveFedora
         !inner.new?
       end
 
+      #@deprecated
       def find_model(pid)
         ActiveSupport::Deprecation.warn("find_model is deprecated.  Use find instead")
         find(pid)
@@ -146,8 +184,10 @@ module ActiveFedora
           SolrService.query(q, :raw=>true, :rows=>0)['response']['numFound']
       end
 
+      #@deprecated
       #Sends a query directly to SolrService
       def solr_search(query, args={})
+        ActiveSupport::Deprecation.warn("solr_search is deprecated and will be removed in the next release. Use SolrService.query instead")
         SolrService.instance.conn.query(query, args)
       end
 
@@ -172,6 +212,7 @@ module ActiveFedora
         end
       end
 
+      # @deprecated
       # Find all ActiveFedora objects for this model that match arguments
       # passed in by querying Solr.  Like find_by_solr this returns a solr result.
       #
@@ -258,8 +299,24 @@ module ActiveFedora
         SolrService.query(query, query_opts) 
       end
 
-      # @param[Hash] conditions 
+      # Returns a solr result matching the supplied conditions
+      # @param[Hash] conditions solr conditions to match
+      # @param[Hash] options 
+      # @option opts [Array] :sort a list of fields to sort by 
+      # @option opts [Array] :rows number of rows to return
       def find_with_conditions(conditions, opts={})
+        query = create_query(conditions)
+        #set default sort to created date ascending
+        unless opts.include?(:sort)
+          opts[:sort]=[ActiveFedora::SolrService.solr_name(:system_create,:date)+' asc'] 
+        end
+        SolrService.query(query, opts) 
+      end
+
+      
+      # Returns a solr query for the supplied conditions
+      # @param[Hash] conditions solr conditions to match
+      def create_query(conditions)
         escaped_class_uri = SolrService.escape_uri_for_query(self.to_class_uri)
         clauses = ["#{ActiveFedora::SolrService.solr_name(:has_model, :symbol)}:#{escaped_class_uri}"]
         conditions.each_pair do |key,value|
@@ -276,13 +333,7 @@ module ActiveFedora
           end
         end
 
-        query = clauses.join(" AND ")
-
-        #set default sort to created date ascending
-        unless opts.include?(:sort)
-          opts[:sort]=[ActiveFedora::SolrService.solr_name(:system_create,:date)+' asc'] 
-        end
-        SolrService.query(query, opts) 
+        clauses.join(" AND ")
       end
 
       def quote_for_solr(value)
@@ -299,18 +350,8 @@ module ActiveFedora
         return fields
       end
 
-      #wrapper around instance_variable_set, sets @name to value
-      def attribute_set(name, value)
-        instance_variable_set("@#{name}", value)
-      end
-
-      #wrapper around instance_variable_get, returns current value of @name
-      def attribute_get(name)
-        instance_variable_get("@#{name}")
-      end
-
       private 
-      # Retrieve the Fedora object with te given pid, explore the returned object, determine its model 
+      # Retrieve the Fedora object with the given pid, explore the returned object, determine its model 
       # using #{ActiveFedora::ContentModel.known_models_for} and cast to that class.
       # Raises a ObjectNotFoundError if the object is not found.
       # @param [String] pid of the object to load
@@ -326,22 +367,6 @@ module ActiveFedora
       end
 
     end
-    def create_property_getter(property) # :nodoc:
-
-      class_eval <<-END, __FILE__, __LINE__
-          def #{property.name}
-            attribute_get("#{property.name}")
-          end
-          END
-    end
-
-    def create_property_setter(property)# :nodoc:
-      class_eval <<-END, __FILE__, __LINE__  
-          def #{property.name}=(value)
-            attribute_set("#{property.name}", value)
-          end
-          END
-    end
 
     private