moab-versioning 4.2.0 → 4.2.1

data/lib/serializer/manifest.rb

@@ -1,5 +1,4 @@
 module Serializer
-
   # Subclass of {Serializable} that adds methods for marshalling/unmarshalling data
   # to a persistent XML file format.
   #
@@ -11,13 +10,12 @@ module Serializer
   # @note Copyright (c) 2012 by The Board of Trustees of the Leland Stanford Junior University.
   #   All rights reserved.  See {file:LICENSE.rdoc} for details.
   class Manifest < Serializer::Serializable
-
     include HappyMapper
 
     # @api internal
     # @param filename [String] Optional filename if one wishes to override the default filename
     # @return [String] Returns the standard filename (derived from the class name) to be used for serializing an object
-    def self.xml_filename(filename=nil)
+    def self.xml_filename(filename = nil)
       if filename
         filename
       else
@@ -30,7 +28,7 @@ module Serializer
     # @param parent_dir [Pathname,String] The location of the directory in which the xml file is located
     # @param filename [String] Optional filename if one wishes to override the default filename
     # @return [Pathname] The location of the xml file
-    def self.xml_pathname(parent_dir, filename=nil)
+    def self.xml_pathname(parent_dir, filename = nil)
       Pathname.new(parent_dir).join(self.xml_filename(filename))
     end
 
@@ -38,7 +36,7 @@ module Serializer
     # @param parent_dir [Pathname,String] The location of the directory in which the xml file is located
     # @param filename [String] Optional filename if one wishes to override the default filename
     # @return [Boolean] Returns true if the xml file exists
-    def self.xml_pathname_exist?(parent_dir, filename=nil)
+    def self.xml_pathname_exist?(parent_dir, filename = nil)
       self.xml_pathname(parent_dir, filename).exist?
     end
 
@@ -47,7 +45,7 @@ module Serializer
     # @param filename [String] Optional filename if one wishes to override the default filename
     # @return [Serializable] Read the xml file and return the parsed XML
     # @example {include:file:spec/features/serializer/read_xml_spec.rb}
-    def self.read_xml_file(parent_dir, filename=nil)
+    def self.read_xml_file(parent_dir, filename = nil)
       self.parse(self.xml_pathname(parent_dir, filename).read)
     end
 
@@ -56,7 +54,7 @@ module Serializer
     # @param parent_dir [Pathname,String] The location of the directory in which the xml file is located
     # @param filename [String] Optional filename if one wishes to override the default filename
     # @return [void] Serializize the in-memory object to a xml file instance
-    def self.write_xml_file(xml_object, parent_dir, filename=nil)
+    def self.write_xml_file(xml_object, parent_dir, filename = nil)
       parent_dir.mkpath
       self.xml_pathname(parent_dir, filename).open('w') do |f|
         xmlBuilder = Nokogiri::XML::Builder.new(:encoding => 'UTF-8')
@@ -71,10 +69,8 @@ module Serializer
     # @param filename [String] Optional filename if one wishes to override the default filename
     # @return [void] Serializize the in-memory object to a xml file instance
     # @example {include:file:spec/features/serializer/write_xml_spec.rb}
-    def write_xml_file(parent_dir, filename=nil)
+    def write_xml_file(parent_dir, filename = nil)
       self.class.write_xml_file(self, parent_dir, filename)
     end
-
   end
-
 end

data/lib/serializer/serializable.rb

@@ -1,5 +1,4 @@
 module Serializer
-
   # Some utility methods to faciliate serialization of data fields to Hash, JSON, or YAML shared by all subclasses.
   # This class assumes that HappyMapper is used for declaration of fields to be serialized.
   #
@@ -11,7 +10,6 @@ module Serializer
   # @note Copyright (c) 2012 by The Board of Trustees of the Leland Stanford Junior University.
   #   All rights reserved.  See {file:LICENSE.rdoc} for details.
   class Serializable
-
     include HappyMapper
 
     # A flexible initializer based on the DataMapper "create factory" design pattern.
@@ -19,7 +17,7 @@ module Serializer
     # @see Serializable#initialize
     # @param opts [Hash<Symbol,Object>] a hash containing any number of symbol => value pairs.
     #   The symbols should correspond to attributes declared using HappyMapper syntax
-    def initialize(opts={})
+    def initialize(opts = {})
       opts.each do |key, value|
         if variable_names.include?(key.to_s) || key == :test
           instance_variable_set("@#{key}", value)
@@ -47,7 +45,7 @@ module Serializer
     # @api internal
     # @return [Array] Extract the names of the variables
     def variable_names
-      variables.collect { |variable| variable.name}
+      variables.collect { |variable| variable.name }
     end
 
     # @api internal
@@ -80,12 +78,12 @@ module Serializer
     # @return [Hash] Generate a hash from an array of objects.
     #   If the array member has a field tagged as a key, that field will be used as the hash.key.
     #   Otherwise the index position of the array member will be used as the key
-    def array_to_hash(array,summary=false)
+    def array_to_hash(array, summary = false)
       item_hash = Hash.new
       array.each_index do |index|
         item = array[index]
-        ikey = (item.respond_to?(:key) && item.key) ?  item.key : index
-        item_hash[ikey] =  item.respond_to?(:to_hash) ? item.to_hash(summary) : item
+        ikey = (item.respond_to?(:key) && item.key) ? item.key : index
+        item_hash[ikey] = item.respond_to?(:to_hash) ? item.to_hash(summary) : item
       end
       item_hash
     end
@@ -93,19 +91,19 @@ module Serializer
     # @api internal
     # @return [Hash] Recursively generate an Hash containing the object's properties
     # @param summary [Boolean] Controls the depth and detail of recursion
-    def to_hash(summary=false)
+    def to_hash(summary = false)
       oh = Hash.new
-      vars = summary ? variables.select{|v| summary_fields.include?(v.name)} : variables
+      vars = summary ? variables.select { |v| summary_fields.include?(v.name) } : variables
       vars.each do |variable|
         key = variable.name.to_s
         value = self.send(variable.name)
         case value
-          when Array
-            oh[key] = array_to_hash(value,summary)
-          when Serializable
-            oh[key] = value.to_hash
-          else
-            oh[key] = value
+        when Array
+          oh[key] = array_to_hash(value, summary)
+        when Serializable
+          oh[key] = value.to_hash
+        else
+          oh[key] = value
         end
       end
       oh
@@ -113,7 +111,7 @@ module Serializer
 
     # @return [Hash] Calls to_hash(summary=true)
     def summary
-      self.to_hash(summary=true)
+      self.to_hash(summary = true)
     end
 
     # @api internal
@@ -141,12 +139,12 @@ module Serializer
     def Serializable.deep_diff(*hashes)
       diff = Hash.new
       case hashes.length
-        when 4
-          ltag, left, rtag, right = hashes
-        when 2
-          ltag, left, rtag, right = :left, hashes[0], :right, hashes[1]
-        else
-          raise ArgumentError, "wrong number of arguments (#{hashes.length} for 2 or 4)"
+      when 4
+        ltag, left, rtag, right = hashes
+      when 2
+        ltag, left, rtag, right = :left, hashes[0], :right, hashes[1]
+      else
+        raise ArgumentError, "wrong number of arguments (#{hashes.length} for 2 or 4)"
       end
       (left.keys | right.keys).each do |k|
         if left[k] != right[k]
@@ -162,17 +160,15 @@ module Serializer
 
     # @api internal
     # @return [String] Generate JSON output from a hash of the object's variables
-    def to_json(summary=false)
-      hash=self.to_hash(summary)
+    def to_json(summary = false)
+      hash = self.to_hash(summary)
       JSON.pretty_generate(hash)
     end
 
     # @api internal
     # @return [String] Generate YAML output from a hash of the object's variables
-    def to_yaml(summary=false)
+    def to_yaml(summary = false)
       self.to_hash(summary).to_yaml
     end
-
   end
-
 end

data/lib/stanford/active_fedora_object.rb

@@ -1,7 +1,6 @@
 require 'moab/stanford'
 
 module Stanford
-
   # Utility Class for extracting content or other information from a Fedora Instance
   #
   # ====Data Model
@@ -12,7 +11,6 @@ module Stanford
   # @note Copyright (c) 2012 by The Board of Trustees of the Leland Stanford Junior University.
   #   All rights reserved.  See {file:LICENSE.rdoc} for details.
   class ActiveFedoraObject
-
     # @param fedora_object [Object]  The Active Fedora representation of the Fedora Object
     # @return [Stanford::ActiveFedoraObject] Create a u
     def initialize(fedora_object)
@@ -28,7 +26,5 @@ module Stanford
     def get_datastream_content(ds_id)
       @fedora_object.datastreams[ds_id].content
     end
-
   end
-
 end

data/lib/stanford/content_inventory.rb

@@ -1,7 +1,6 @@
 require 'moab/stanford'
 
 module Stanford
-
   # Stanford-specific utility methods for transforming contentMetadata to versionInventory and doing comparisons
   #
   # ====Data Model
@@ -12,20 +11,19 @@ module Stanford
   # @note Copyright (c) 2012 by The Board of Trustees of the Leland Stanford Junior University.
   #   All rights reserved.  See {file:LICENSE.rdoc} for details.
   class ContentInventory
-
     # @param content_metadata [String] The content metadata to be transformed into a versionInventory
     # @param object_id [String] The identifier of the digital object
     # @param subset [String] Speciifes which subset of files to list (all|preserve|publish|shelve)
     # @param version_id [Integer] The ID of the version whosen content metadata is to be transformed
     # @return [FileInventory] The versionInventory equivalent of the contentMetadata
     #   if the supplied content_metadata is blank or empty, then a skeletal FileInventory will be returned
-    def inventory_from_cm(content_metadata, object_id, subset, version_id=nil)
+    def inventory_from_cm(content_metadata, object_id, subset, version_id = nil)
       # The contentMetadata datastream is not required for ingest, since some object types, such as collection
       #   or APO do not require one.
       # Many of these objects have contentMetadata with no child elements, such as this:
       #    <contentMetadata objectId="bd608mj3166" type="file"/>
       # but there are also objects that have no datasteam of this name at all
-      cm_inventory = Moab::FileInventory.new(:type=>"version",:digital_object_id=>object_id, :version_id=>version_id)
+      cm_inventory = Moab::FileInventory.new(:type => "version", :digital_object_id => object_id, :version_id => version_id)
       content_group = group_from_cm(content_metadata, subset)
       cm_inventory.groups << content_group
       cm_inventory
@@ -40,18 +38,18 @@ module Stanford
       ng_doc = Nokogiri::XML(content_metadata)
       validate_content_metadata(ng_doc)
       nodeset = case subset.to_s.downcase
-        when 'preserve'
-          ng_doc.xpath("//file[@preserve='yes']")
-        when 'publish'
-          ng_doc.xpath("//file[@publish='yes']")
-        when 'shelve'
-          ng_doc.xpath("//file[@shelve='yes']")
-        when 'all'
-          ng_doc.xpath("//file")
-        else
-            raise "Unknown disposition subset (#{subset})"
-        end
-      content_group = Moab::FileGroup.new(:group_id=>'content', :data_source => "contentMetadata-#{subset}")
+                when 'preserve'
+                  ng_doc.xpath("//file[@preserve='yes']")
+                when 'publish'
+                  ng_doc.xpath("//file[@publish='yes']")
+                when 'shelve'
+                  ng_doc.xpath("//file[@shelve='yes']")
+                when 'all'
+                  ng_doc.xpath("//file")
+                else
+                  raise "Unknown disposition subset (#{subset})"
+                end
+      content_group = Moab::FileGroup.new(:group_id => 'content', :data_source => "contentMetadata-#{subset}")
       nodeset.each do |file_node|
         signature = generate_signature(file_node)
         instance = generate_instance(file_node)
@@ -69,12 +67,12 @@ module Stanford
       checksum_nodes = node.xpath('checksum')
       checksum_nodes.each do |checksum_node|
         case checksum_node.attributes['type'].content.upcase
-          when 'MD5'
-            signature.md5 = checksum_node.text
-          when 'SHA1', 'SHA-1'
-            signature.sha1 = checksum_node.text
-          when 'SHA256', 'SHA-256'
-            signature.sha256 = checksum_node.text
+        when 'MD5'
+          signature.md5 = checksum_node.text
+        when 'SHA1', 'SHA-1'
+          signature.sha1 = checksum_node.text
+        when 'SHA256', 'SHA-256'
+          signature.sha256 = checksum_node.text
         end
       end
       signature
@@ -96,22 +94,23 @@ module Stanford
     # @example {include:file:spec/features/stanford/content_metadata_write_spec.rb}
     def generate_content_metadata(file_group, object_id, version_id)
       cm = Nokogiri::XML::Builder.new do |xml|
-        xml.contentMetadata(:type=>"sample", :objectId=>object_id) {
-          xml.resource(:type=>"version", :sequence=>"1", :id=>"version-#{version_id}") {
+        xml.contentMetadata(:type => "sample", :objectId => object_id) {
+          xml.resource(:type => "version", :sequence => "1", :id => "version-#{version_id}") {
             file_group.files.each do |file_manifestation|
               signature = file_manifestation.signature
               file_manifestation.instances.each do |instance|
                 xml.file(
-                    :id=>instance.path,
-                    :size=>signature.size,
-                    :datetime=>instance.datetime,
-                    :shelve=>'yes',
-                    :publish=>'yes',
-                    :preserve=>'yes') {
+                  :id => instance.path,
+                  :size => signature.size,
+                  :datetime => instance.datetime,
+                  :shelve => 'yes',
+                  :publish => 'yes',
+                  :preserve => 'yes'
+                ) {
                   fixity = signature.fixity
-                  xml.checksum(:type=>"MD5") {xml.text signature.md5 } if fixity[:md5]
-                  xml.checksum(:type=>"SHA-1") {xml.text signature.sha1} if fixity[:sha1]
-                  xml.checksum(:type=>"SHA-256") {xml.text signature.sha256} if fixity[:sha256]
+                  xml.checksum(:type => "MD5") { xml.text signature.md5 } if fixity[:md5]
+                  xml.checksum(:type => "SHA-1") { xml.text signature.sha1 } if fixity[:sha1]
+                  xml.checksum(:type => "SHA-256") { xml.text signature.sha256 } if fixity[:sha256]
                 }
               end
             end
@@ -125,7 +124,7 @@ module Stanford
     # @return [Boolean] True if contentMetadata has essential file attributes, else raise exception
     def validate_content_metadata(content_metadata)
       result = validate_content_metadata_details(content_metadata)
-      raise Moab::InvalidMetadataException, result[0]+" ..." if result.size > 0
+      raise Moab::InvalidMetadataException, result[0] + " ..." if result.size > 0
       true
     end
 
@@ -135,27 +134,27 @@ module Stanford
       result = []
       content_metadata_doc =
         case content_metadata.class.name
-          when "String"
-            Nokogiri::XML(content_metadata)
-          when "Pathname"
-            Nokogiri::XML(content_metadata.read)
-          when "Nokogiri::XML::Document"
-            content_metadata
-          else
-            raise Moab::InvalidMetadataException, "Content Metadata is in unrecognized format"
-          end
+        when "String"
+          Nokogiri::XML(content_metadata)
+        when "Pathname"
+          Nokogiri::XML(content_metadata.read)
+        when "Nokogiri::XML::Document"
+          content_metadata
+        else
+          raise Moab::InvalidMetadataException, "Content Metadata is in unrecognized format"
+        end
       nodeset = content_metadata_doc.xpath("//file")
       nodeset.each do |file_node|
-        missing = ['id', 'size','md5','sha1']
+        missing = ['id', 'size', 'md5', 'sha1']
         missing.delete('id') if file_node.has_attribute?('id')
         missing.delete('size') if file_node.has_attribute?('size')
         checksum_nodes = file_node.xpath('checksum')
         checksum_nodes.each do |checksum_node|
           case checksum_node.attributes['type'].content.upcase
-            when 'MD5'
-              missing.delete('md5')
-            when 'SHA1', 'SHA-1'
-              missing.delete('sha1')
+          when 'MD5'
+            missing.delete('md5')
+          when 'SHA1', 'SHA-1'
+            missing.delete('sha1')
           end
         end
         if missing.include?('id')
@@ -214,14 +213,14 @@ module Stanford
       # add new <checksum> elements for the other checksum types that were missing
       @names_for_type.each do |type, names|
         unless checksum_nodes.has_key?(type)
-          checksum_node = Nokogiri::XML::Element.new('checksum',file_node.document)
+          checksum_node = Nokogiri::XML::Element.new('checksum', file_node.document)
           checksum_node['type'] = names[0]
           file_node << checksum_node
           checksum_nodes[type] = checksum_node
         end
       end
       # make sure the <checksum> element has a content value
-      checksum_nodes.each do |type,checksum_node|
+      checksum_nodes.each do |type, checksum_node|
         cm_checksum = checksum_node.content
         sig_checksum = signature.checksums[type]
         if cm_checksum.nil? or cm_checksum.empty?
@@ -231,7 +230,5 @@ module Stanford
         end
       end
     end
-
   end
-
 end

data/lib/stanford/dor_metadata.rb

@@ -1,7 +1,6 @@
 require 'moab/stanford'
 
 module Stanford
-
   # Stanford-specific utility methods for interfacing with DOR metadata files
   #
   # ====Data Model
@@ -12,7 +11,6 @@ module Stanford
   # @note Copyright (c) 2012 by The Board of Trustees of the Leland Stanford Junior University.
   #   All rights reserved.  See {file:LICENSE.rdoc} for details.
   class DorMetadata
-
     # @return [String] The digital object identifier (druid)
     attr_accessor :digital_object_id
 
@@ -22,7 +20,7 @@ module Stanford
     # @param digital_object_id [String] The digital object identifier
     # @param version_id [Integer] The ordinal version number
     # @return [Stanford::DorMetadata]
-    def initialize(digital_object_id, version_id=nil)
+    def initialize(digital_object_id, version_id = nil)
       @digital_object_id = digital_object_id
       @version_id = version_id
     end
@@ -31,16 +29,15 @@ module Stanford
     # @param directory [String] The location of the directory to be inventoried
     # @param version_id (see #initialize)
     # @return [FileInventory]  Inventory of the files under the specified directory
-    def inventory_from_directory(directory, version_id=nil)
+    def inventory_from_directory(directory, version_id = nil)
       version_id ||= @version_id
       version_inventory = Moab::FileInventory.new(type: 'version', digital_object_id: @digital_object_id, version_id: version_id)
-      content_metadata = IO.read(File.join(directory,'contentMetadata.xml'))
-      content_group = Stanford::ContentInventory.new.group_from_cm(content_metadata, 'preserve' )
+      content_metadata = IO.read(File.join(directory, 'contentMetadata.xml'))
+      content_group = Stanford::ContentInventory.new.group_from_cm(content_metadata, 'preserve')
       version_inventory.groups << content_group
-      metadata_group = Moab::FileGroup.new(:group_id=>'metadata').group_from_directory(directory)
+      metadata_group = Moab::FileGroup.new(:group_id => 'metadata').group_from_directory(directory)
       version_inventory.groups << metadata_group
       version_inventory
     end
   end
-
 end

data/lib/stanford/storage_object_validator.rb

@@ -3,12 +3,11 @@ require 'moab'
 module Stanford
   # druids are Stanford specific entities
   class StorageObjectValidator < Moab::StorageObjectValidator
-
     # TODO: test to make sure constants don't collide on underlying int vals?
     # keep from stepping on previously defined error code constants.
     DRUID_MISMATCH = superclass.error_code_to_messages.keys.max + 1
 
-    def validation_errors(allow_content_subdirs=true)
+    def validation_errors(allow_content_subdirs = true)
       errors = []
       errors.concat super(allow_content_subdirs)
       errors.concat(identify_druid) if errors.empty?