active-fedora 3.3.2 → 4.0.0.rc1

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    active-fedora (3.3.2)
+    active-fedora (4.0.0.rc1)
       activeresource (>= 3.0.0)
       activesupport (>= 3.0.0)
       equivalent-xml
@@ -9,10 +9,10 @@ PATH
       mime-types (>= 1.16)
       multipart-post (= 1.1.2)
       nokogiri
-      om (>= 1.5.1)
+      om (>= 1.5.3)
       rdf
       rdf-rdfxml
-      rubydora (~> 0.5.3)
+      rubydora (~> 0.5.4)
       solr-ruby (>= 0.0.6)
       solrizer (~> 1.2.0)
       xml-simple (>= 1.0.12)
@@ -21,22 +21,22 @@ GEM
   remote: http://rubygems.org/
   specs:
     RedCloth (4.2.9)
-    activemodel (3.2.1)
-      activesupport (= 3.2.1)
+    activemodel (3.2.2)
+      activesupport (= 3.2.2)
       builder (~> 3.0.0)
-    activeresource (3.2.1)
-      activemodel (= 3.2.1)
-      activesupport (= 3.2.1)
-    activesupport (3.2.1)
+    activeresource (3.2.2)
+      activemodel (= 3.2.2)
+      activesupport (= 3.2.2)
+    activesupport (3.2.2)
       i18n (~> 0.6)
       multi_json (~> 1.0)
     addressable (2.2.7)
     akami (1.0.0)
       gyoku (>= 0.4.0)
     builder (3.0.0)
-    childprocess (0.3.0)
+    childprocess (0.3.1)
       ffi (~> 1.0.6)
-    daemons (1.1.6)
+    daemons (1.1.8)
     diff-lcs (1.1.3)
     equivalent-xml (0.2.9)
       nokogiri (>= 1.4.3)
@@ -57,13 +57,13 @@ GEM
     mediashelf-loggable (0.4.9)
     metaclass (0.0.1)
     mime-types (1.17.2)
-    mocha (0.10.3)
+    mocha (0.10.5)
       metaclass (~> 0.0.1)
-    multi_json (1.0.4)
+    multi_json (1.1.0)
     multipart-post (1.1.2)
     nokogiri (1.5.0)
     nori (1.1.0)
-    om (1.5.1)
+    om (1.5.3)
       mediashelf-loggable
       nokogiri (>= 1.4.2)
     rack (1.4.1)
@@ -85,7 +85,7 @@ GEM
     rspec-expectations (2.8.0)
       diff-lcs (~> 1.1.2)
     rspec-mocks (2.8.0)
-    rubydora (0.5.3)
+    rubydora (0.5.4)
       activemodel
       activesupport
       fastercsv
@@ -109,19 +109,18 @@ GEM
       om (>= 1.5.0)
       stomp
       xml-simple
-    solrizer-fedora (1.2.3)
-      active-fedora (>= 3.1.0)
-      activesupport
+    solrizer-fedora (1.2.5)
+      active-fedora (>= 3.2.0)
+      activesupport (>= 3.0.11)
       fastercsv
-      jettywrapper (>= 1.1.0)
-      rsolr
+      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)
     xml-simple (1.1.1)
-    yard (0.7.4)
+    yard (0.7.5)
 
 PLATFORMS
   ruby
@@ -133,5 +132,5 @@ DEPENDENCIES
   mocha (>= 0.9.8)
   rake
   rspec (~> 2.0)
-  solrizer-fedora (~> 1.2.3)
+  solrizer-fedora (~> 1.2.5)
   yard

data/History.txt

@@ -1,3 +1,12 @@
+4.0.0.rc1
+Removed deprecations
+  * allowing :fedora level in fedora.yml
+  * automatic includes of Relationships and FileMethods is removed
+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
+
 3.3.2
 HYDRA-745 No need to require :url be present on external datastreams
 Initialize relationships graph to empty array

data/README.textile

@@ -34,7 +34,7 @@ h3. Testing with Hudson Rake Task
 The hudson rake task will spin up jetty, import the fixtures, and run the tests for you.
 
 <pre>
-  rake hudson
+  rake active_fedora:hudson
 </pre>
 
 h3. Testing Manually

data/TODO

@@ -0,0 +1 @@
+Get rid of ActiveFedora::Relationships methods in specs (except in relationships_spec.rb of course)

data/active-fedora.gemspec

@@ -20,20 +20,20 @@ Gem::Specification.new do |s|
   s.add_dependency('mime-types', '>= 1.16')
   s.add_dependency('multipart-post', "= 1.1.2")
   s.add_dependency('nokogiri')
-  s.add_dependency('om', '>= 1.5.1')
+  s.add_dependency('om', '>= 1.5.3')
   s.add_dependency('solrizer', '~>1.2.0')
   s.add_dependency("activeresource", '>= 3.0.0')
   s.add_dependency("activesupport", '>= 3.0.0')
   s.add_dependency("mediashelf-loggable")
   s.add_dependency("equivalent-xml")
-  s.add_dependency("rubydora", '~>0.5.3')
+  s.add_dependency("rubydora", '~>0.5.4')
   s.add_dependency("rdf")
   s.add_dependency("rdf-rdfxml")
   s.add_development_dependency("yard")
   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", "~>1.2.3") # 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/config/fedora.yml

@@ -1,7 +1,13 @@
 development:
-  url: http://fedoraAdmin:fedoraAdmin@127.0.0.1:8983/fedora
+  user: fedoraAdmin
+  password: fedoraAdmin
+  url: http://127.0.0.1:8983/fedora
 test:
-  url: http://fedoraAdmin:fedoraAdmin@127.0.0.1:8983/fedora-test
+  user: fedoraAdmin
+  password: fedoraAdmin
+  url: http://127.0.0.1:8983/fedora-test
 production:
-  url: http://fedoraAdmin:fedoraAdmin@127.0.0.1:8080/fedora
+  user: fedoraAdmin
+  password: fedoraAdmin
+  url: http://127.0.0.1:8080/fedora
     

data/lib/active_fedora.rb

@@ -12,18 +12,26 @@ ENABLE_SOLR_UPDATES = true unless defined?(ENABLE_SOLR_UPDATES)
 module ActiveFedora #:nodoc:
   extend ActiveSupport::Autoload
 
+  class ObjectNotFoundError < RuntimeError; end # :nodoc:
+  class PredicateMappingsNotFoundError < RuntimeError; end # :nodoc:
+  class UnknownAttributeError < NoMethodError; end; # :nodoc:
+  class ConfigurationError < RuntimeError; end # :nodoc:
+  class AssociationTypeMismatch < RuntimeError; end # :nodoc:
+  class UnregisteredPredicateError < RuntimeError; end
+
+
   eager_autoload do
     autoload :Associations
     autoload :AttributeMethods
     autoload :Base
     autoload :ContentModel
     autoload :Callbacks
+    autoload :Config
     autoload :Reflection
     autoload :Relationships
     autoload :FileManagement
     autoload :RelationshipGraph
     autoload :Datastream
-    autoload :DCRDFDatastream
     autoload :Datastreams
     autoload :Delegating
     autoload :DigitalObject
@@ -55,7 +63,7 @@ module ActiveFedora #:nodoc:
   include Loggable
   
   class << self
-    attr_accessor :solr_config, :fedora_config, :config_env, :fedora_config_path, :solr_config_path
+    attr_accessor :solr_config, :fedora_config, :config_env, :solr_config_path
     attr_reader :config_options
   end
   
@@ -92,9 +100,20 @@ module ActiveFedora #:nodoc:
   # Options allowed in fedora.yml
   # first level is the environment (e.g. development, test, production and any custom environments you may have) 
   # the second level has these keys:
-  # 1. url: url including protocol, user/pass, host, port and path (e.g. http://fedoraAdmin:fedoraAdmin@127.0.0.1:8983/fedora)
-  # 2. validateChecksum:  indicates to the fedora server whether you want to validate checksums when the datastreams are queried.  
-
+  # 1. url: url including protocol, host, port and path (e.g. http://127.0.0.1:8983/fedora)
+  # 2. user: username
+  # 3. password: password
+  # 4. validateChecksum:  indicates to the fedora server whether you want to validate checksums when the datastreams are queried.  
+  #
+  # @example If you want to shard the fedora instance, you can specify an array of credentials. 
+  #   production:
+  #   - user: user1
+  #     password: password1
+  #     url: http://127.0.0.1:8983/fedora1
+  #   - user: user2
+  #     password: password2
+  #     url: http://127.0.0.1:8983/fedora2
+  #
 
   def self.init( options={} )
     # Make config_options into a Hash if nil is passed in as the value
@@ -115,6 +134,11 @@ module ActiveFedora #:nodoc:
     load_configs
   end
 
+  def self.config
+    load_configs
+    @fedora_config
+  end
+
   def self.reset!
     @config_loaded = false  #Force reload of configs
     @predicate_config_path = nil
@@ -127,7 +151,7 @@ module ActiveFedora #:nodoc:
   def self.load_configs
     return if config_loaded?
     @config_env = environment
-    load_config(:fedora)
+    @fedora_config = Config.new(get_config_path(:fedora), @config_env)
     load_config(:solr)
     @config_loaded = true
 
@@ -150,7 +174,8 @@ module ActiveFedora #:nodoc:
   end
 
   def self.config_for_environment
-    fedora_config[@config_env.to_sym].symbolize_keys
+    ActiveSupport::Deprecation.warn("config_for_environment has been deprecated use `config' instead")
+    config
   end
 
   # Determines and sets the fedora_config[:url] or solr_config[:url]
@@ -161,13 +186,7 @@ module ActiveFedora #:nodoc:
     c = config[environment.to_sym]
     c.symbolize_keys!
     if config_type == "fedora"
-      # support old-style config
-      url = if c.fetch(:fedora,nil)
-        ActiveSupport::Deprecation.warn("Using \"fedora\" in the fedora.yml file is no longer supported") 
-        c[:fedora]["url"] if config[environment.to_sym].fetch(:fedora,nil)
-      else
-        c[:url]
-      end
+      url =  c[:url]
       if url && !c[:user]
         u = URI.parse url
         c[:user] = u.user
@@ -233,16 +252,13 @@ module ActiveFedora #:nodoc:
   def self.get_config_path(config_type)
     config_type = config_type.to_s
     if (config_path = config_options.fetch("#{config_type}_config_path".to_sym,nil) )
-      raise ActiveFedoraConfigurationException, "file does not exist #{config_path}" unless File.file? config_path
-      return config_path
+      raise ConfigurationError, "file does not exist #{config_path}" unless File.file? config_path
+      return File.expand_path(config_path)
     end
     
     # if solr, attempt to use path where fedora.yml is first
     if config_type == "solr" && (config_path = check_fedora_path_for_solr)
       return config_path
-    elsif config_type == "solr" && fedora_config[environment].fetch("solr",nil)
-      ActiveSupport::Deprecation.warn("You appear to be using a deprecated format for your fedora.yml file.  The solr url should be stored in a separate solr.yml file in the same directory as the fedora.yml")
-      raise ActiveFedoraConfigurationException
     end
 
     if defined?(Rails.root)
@@ -258,12 +274,12 @@ module ActiveFedora #:nodoc:
     config_path = File.expand_path(File.join(File.dirname(__FILE__), "..", "config", "#{config_type}.yml"))
     logger.warn "Using the default #{config_type}.yml that comes with active-fedora.  If you want to override this, pass the path to #{config_type}.yml to ActiveFedora - ie. ActiveFedora.init(:#{config_type}_config_path => '/path/to/#{config_type}.yml) - or set Rails.root and put #{config_type}.yml into \#{Rails.root}/config."
     return config_path if File.file? config_path
-    raise ActiveFedoraConfigurationException "Couldn't load #{config_type} config file!"
+    raise ConfigurationError "Couldn't load #{config_type} config file!"
   end
   
-  # Checks the existing fedora_config_path to see if there is a solr.yml there
+  # Checks the existing fedora_config.path to see if there is a solr.yml there
   def self.check_fedora_path_for_solr
-    path = fedora_config_path.split('/')[0..-2].join('/') + "/solr.yml"
+    path = @fedora_config.path.split('/')[0..-2].join('/') + "/solr.yml"
     if File.file? path
       return path
     else
@@ -275,12 +291,15 @@ module ActiveFedora #:nodoc:
     ActiveFedora::SolrService.instance
   end
   
+  
   def self.fedora
-    ActiveFedora::RubydoraConnection.instance
+    ActiveSupport::Deprecation.warn("ActiveFedora.fedora() is deprecated and will be removed in the next release use ActiveFedora::Base.connection_for_pid(pid) instead")
+    
+    ActiveFedora::Base.connection_for_pid('0')
   end
 
   def self.predicate_config
-    @predicate_config_path ||= build_predicate_config_path(File.dirname(@fedora_config_path))
+    @predicate_config_path ||= build_predicate_config_path(File.dirname(@fedora_config.path))
   end
 
   def self.version
@@ -311,15 +330,6 @@ module ActiveFedora #:nodoc:
 
 end
 
-module ActiveFedora
-  class ObjectNotFoundError < RuntimeError; end # :nodoc:
-  class PredicateMappingsNotFoundError < RuntimeError; end # :nodoc:
-  class UnknownAttributeError < NoMethodError; end; # :nodoc:
-  class ActiveFedoraConfigurationException < Exception; end # :nodoc:
-  class AssociationTypeMismatch < RuntimeError; end # :nodoc:
-  class UnregisteredPredicateError < RuntimeError; end
-
-end
 
 load File.join(File.dirname(__FILE__),"tasks/active_fedora.rake") if defined?(Rake)
 

data/lib/active_fedora/base.rb

@@ -30,28 +30,15 @@ module ActiveFedora
   class Base
     include SemanticNode
 
-
-    def self.method_missing (name, *args)
-      if [:has_relationship, :has_bidirectional_relationship, :register_relationship_desc].include? name 
-        ActiveSupport::Deprecation.warn("Deprecation: Relationships will not be included by default in the next version.   To use #{name} add 'include ActiveFedora::Relationships' to your model")
-        include Relationships
-        send name, *args
-      elsif name == :has_datastream
-        ActiveSupport::Deprecation.warn("Deprecation: DatastreamCollections will not be included by default in the next version.   To use has_datastream add 'include ActiveFedora::DatastreamCollections' to your model")
-        include DatastreamCollections
-        has_datastream(*args)
-      else 
-        super
-      end
-    end
-
+    class_attribute :fedora_connection 
+    self.fedora_connection = {}
 
     def method_missing(name, *args)
-      if [:collection_members, :part_of, :parts, :part_of_append, :file_objects].include? name 
-        ActiveSupport::Deprecation.warn("Deprecation: FileManagement will not be included by default in the next version.   To use #{name} add 'include ActiveFedora::FileManagement' to your model")
-        self.class.send :include, FileManagement
-        send name, *args
-      else 
+      # if [:collection_members, :part_of, :parts, :part_of_append, :file_objects].include? name 
+      #   ActiveSupport::Deprecation.warn("Deprecation: FileManagement will not be included by default in the next version.   To use #{name} add 'include ActiveFedora::FileManagement' to your model")
+      #   self.class.send :include, FileManagement
+      #   send name, *args
+      # else 
         dsid = corresponding_datastream_name(name)
         if dsid
           ### Create and invoke a proxy method 
@@ -62,7 +49,6 @@ module ActiveFedora
         else 
           super
         end
-      end
     end
 
 
@@ -133,6 +119,28 @@ module ActiveFedora
       self
     end
 
+    # Uses {shard_index} to find or create the rubydora connection for this pid
+    # @param [String] pid the identifier of the object to get the connection for
+    # @return [Rubydora::Repository] The repository that the identifier exists in.
+    def self.connection_for_pid(pid)
+      idx = shard_index(pid)
+      unless fedora_connection.has_key? idx
+        if ActiveFedora.config.sharded?
+          fedora_connection[idx] = RubydoraConnection.new(ActiveFedora.config.credentials[idx])
+        else
+          fedora_connection[idx] = RubydoraConnection.new(ActiveFedora.config.credentials)
+        end
+      end
+      fedora_connection[idx].connection
+    end
+
+    #If you want to use sharding override this method with your strategy
+    #@return [Integer] the index of the shard this object is stored in
+    def self.shard_index(pid)
+      0
+    end
+    
+
     def self.datastream_class_for_name(dsid)
       ds_specs[dsid] ? ds_specs[dsid][:type] : ActiveFedora::Datastream
     end
@@ -143,6 +151,17 @@ module ActiveFedora
       obj
     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
+    end
+
     def inner_object # :nodoc
       @inner_object
     end
@@ -167,7 +186,7 @@ module ActiveFedora
     def internal_uri
       "info:fedora/#{pid}"
     end
-    
+
     #return the state of the inner object
     def state 
       @inner_object.state
@@ -253,20 +272,30 @@ module ActiveFedora
     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)
+        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) 
       end
       solr_doc = solrize_relationships(solr_doc) unless opts[:model_only]
-      begin
-        #logger.info("PID: '#{pid}' solr_doc put into solr: #{solr_doc.inspect}")
-      rescue
-        logger.info("Error encountered trying to output solr_doc details for pid: #{pid}")
-      end
-      return solr_doc
+      solr_doc
     end
 
+    def solrize_profile(solr_doc = Hash.new) # :nodoc:
+      if inner_object.respond_to? :profile
+        inner_object.profile.each_pair do |property,value|
+          if property =~ /Date/
+            value = Time.parse(value) unless value.is_a?(Time)
+            value = value.xmlschema
+          end
+          solr_doc[ActiveFedora::SolrService.solr_name("objProfile_#{property}", property =~ /Date/ ? :date : :symbol)] = value
+        end
+      end
+      solr_doc
+    end
+    
     # Serialize the datastream's RDF relationships to solr
     # @param [Hash] solr_doc @deafult an empty Hash
     def solrize_relationships(solr_doc = Hash.new)
@@ -289,6 +318,27 @@ module ActiveFedora
       end
       klass.allocate.init_with(inner_object)
     end
+    
+    # ** EXPERIMENTAL **
+    # This method returns a new object of the same class, with the internal SolrDigitalObject
+    # replaced with an actual DigitalObject.
+    def reify
+      if self.inner_object.is_a? DigitalObject
+        raise "#{self.inspect} is already a full digital object"
+      end
+      self.class.load_instance self.pid
+    end
+    
+    # ** EXPERIMENTAL **
+    # This method reinitializes a lightweight, loaded-from-solr object with an actual
+    # DigitalObject inside.
+    def reify!
+      if self.inner_object.is_a? DigitalObject
+        raise "#{self.inspect} is already a full digital object"
+      end
+      self.init_with DigitalObject.find(self.class,self.pid)
+    end
+    
     # ** EXPERIMENTAL **
     #
     # This method can be used instead of ActiveFedora::Model::ClassMethods.load_instance.  
@@ -313,9 +363,7 @@ module ActiveFedora
         raise "Solr document record id and pid do not match" unless pid == solr_doc[SOLR_DOCUMENT_ID]
       end
      
-      create_date = solr_doc[ActiveFedora::SolrService.solr_name(:system_create, :date)].nil? ? solr_doc[ActiveFedora::SolrService.solr_name(:system_create, :date).to_s] : solr_doc[ActiveFedora::SolrService.solr_name(:system_create, :date)]
-      modified_date = solr_doc[ActiveFedora::SolrService.solr_name(:system_create, :date)].nil? ? solr_doc[ActiveFedora::SolrService.solr_name(:system_modified, :date).to_s] : solr_doc[ActiveFedora::SolrService.solr_name(:system_modified, :date)]
-      obj = self.allocate.init_with(SolrDigitalObject.new(:pid=>solr_doc[SOLR_DOCUMENT_ID],:create_date=>create_date,:modified_date=>modified_date))
+      obj = self.allocate.init_with(SolrDigitalObject.new(solr_doc))
       #set by default to load any dependent relationship objects from solr as well
       #need to call rels_ext once so it exists when iterating over datastreams
       obj.rels_ext
@@ -324,6 +372,7 @@ module ActiveFedora
           ds.from_solr(solr_doc) if ds.kind_of?(ActiveFedora::MetadataDatastream) || ds.kind_of?(ActiveFedora::NokogiriDatastream) || ( ds.kind_of?(ActiveFedora::RelsExtDatastream))
         end
       end
+      obj.inner_object.freeze
       obj
     end