base.rb in active-fedora-4.2.0

- old
+ new

@@ -1,7 +1,8 @@
 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
   
   # This class ties together many of the lower-level modules, and
   # implements something akin to an ActiveRecord-alike interface to
@@ -130,14 +131,23 @@
         end
       end
       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
     
 
     def self.datastream_class_for_name(dsid)
       ds_specs[dsid] ? ds_specs[dsid][:type] : ActiveFedora::Datastream
@@ -147,18 +157,45 @@
       obj = self.new(args)
       obj.save
       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
       @inner_object
     end