moab-versioning 5.2.0 → 6.0.0.alpha

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: c20a012b9d9c481ddfeed15296e61aaf6648bed0cd1d0065a8b0662301e94a1b
-  data.tar.gz: 8d5a96d608b7334f117b5ee9faa3cbe16f82f543bd3af0d23d11371df2181d76
+  metadata.gz: 6d208d4a3118a616d2ee2580e51d9a344438676755f5ef33ace82ed2dbc33bba
+  data.tar.gz: 7198c3f7450d8a6bb61d8b33d50404e9b0a07e52d47198f713b4400e1c2a4435
 SHA512:
-  metadata.gz: 296fd7985772e8296f879e955066f7e3c71b00a6a83d9893aa124de5d900a427ca61d57b221f4227ae54210f3518111a5d99ae60db62ed9dbb25818871f8e87d
-  data.tar.gz: 701adc9ee529e10fd608ed890f8f8a3f978cb3ec023f58d8a75bd11a0caa6e27f4631ec4f73c9280cf8de914da855d100be3cd077f029ec91fab4b07749c627c
+  metadata.gz: 884f1c7e2818e9bcb64de45939cda1ccc4a1aebf5015edd3bfefe707f3a4185253aaa629d4cc0340145be5fd2a72aac0931c7115e8a7929338dd362ff9aa894b
+  data.tar.gz: 2f23fc485263350eb667eed7871dc194972688151613d573227dfa3b2f5490d9f6ccc8f7625f0c4ac3fa66ac0ee01f3c470a24b6133443c89f080e90bae273aa

data/lib/moab/bagger.rb

@@ -58,9 +58,9 @@ module Moab
     # @return [void] Generate the bagit.txt tag file
     def create_bagit_txt
       bag_pathname.mkpath
-      bag_pathname.join("bagit.txt").open('w') do |f|
-        f.puts "Tag-File-Character-Encoding: UTF-8"
-        f.puts "BagIt-Version: 0.97"
+      bag_pathname.join('bagit.txt').open('w') do |f|
+        f.puts 'Tag-File-Character-Encoding: UTF-8'
+        f.puts 'BagIt-Version: 0.97'
       end
     end
 
@@ -209,7 +209,7 @@ module Moab
         if manifest_file[type]
           manifest_file[type].close
           manifest_pathname[type].delete if
-              manifest_pathname[type].exist? && manifest_pathname[type].size == 0
+              manifest_pathname[type].exist? && manifest_pathname[type].empty?
         end
       end
     end
@@ -217,7 +217,7 @@ module Moab
     # @api internal
     # @return [void] Generate the bag-info.txt tag file
     def create_bag_info_txt
-      bag_pathname.join("bag-info.txt").open('w') do |f|
+      bag_pathname.join('bag-info.txt').open('w') do |f|
         f.puts "External-Identifier: #{bag_inventory.package_id}"
         f.puts "Payload-Oxum: #{bag_inventory.byte_count}.#{bag_inventory.file_count}"
         f.puts "Bag-Size: #{bag_inventory.human_size}"
@@ -247,7 +247,7 @@ module Moab
         if manifest_file[type]
           manifest_file[type].close
           manifest_pathname[type].delete if
-              manifest_pathname[type].exist? && manifest_pathname[type].size == 0
+              manifest_pathname[type].exist? && manifest_pathname[type].empty?
         end
       end
     end

data/lib/moab/file_group.rb

@@ -23,7 +23,7 @@ module Moab
     # (see Serializable#initialize)
     def initialize(opts = {})
       @signature_hash = {}
-      @data_source = ""
+      @data_source = ''
       @signatures_from_bag = nil # prevents later warning: instance variable @signatures_from_bag not initialized
       super(opts)
     end
@@ -158,14 +158,16 @@ module Moab
     end
     attr_reader :base_directory
 
+    # FIXME:  shouldn't this method be named descendent_of_base?
     # @api internal
     # @param pathname [Pathname] The file path to be tested
     # @return [Boolean] Test whether the given path is contained within the {#base_directory}
     def is_descendent_of_base?(pathname)
-      raise(MoabRuntimeError, "base_directory has not been set") if @base_directory.nil?
+      raise(MoabRuntimeError, 'base_directory has not been set') if @base_directory.nil?
 
       is_descendent = false
       pathname.expand_path.ascend { |ancestor| is_descendent ||= (ancestor == @base_directory) }
+      # FIXME:  shouldn't it simply return false?
       raise(MoabRuntimeError, "#{pathname} is not a descendent of #{@base_directory}") unless is_descendent
 
       is_descendent

data/lib/moab/file_group_difference.rb

@@ -233,7 +233,7 @@ module Moab
         matching_paths.each do |path|
           fid = FileInstanceDifference.new(change: 'identical')
           fid.basis_path = path
-          fid.other_path = "same"
+          fid.other_path = 'same'
           fid.signatures << signature
           subset_hash[:identical].files << fid
         end
@@ -286,7 +286,7 @@ module Moab
       matching_keys(basis_path_hash, other_path_hash).each do |path|
         fid = FileInstanceDifference.new(change: 'modified')
         fid.basis_path = path
-        fid.other_path = "same"
+        fid.other_path = 'same'
         fid.signatures << basis_path_hash[path]
         fid.signatures << other_path_hash[path]
         subset_hash[:modified].files << fid
@@ -304,7 +304,7 @@ module Moab
     def tabulate_added_files(basis_path_hash, other_path_hash)
       other_only_keys(basis_path_hash, other_path_hash).each do |path|
         fid = FileInstanceDifference.new(change: 'added')
-        fid.basis_path = ""
+        fid.basis_path = ''
         fid.other_path = path
         fid.signatures << other_path_hash[path]
         subset_hash[:added].files << fid
@@ -323,7 +323,7 @@ module Moab
       basis_only_keys(basis_path_hash, other_path_hash).each do |path|
         fid = FileInstanceDifference.new(change: 'deleted')
         fid.basis_path = path
-        fid.other_path = ""
+        fid.other_path = ''
         fid.signatures << basis_path_hash[path]
         subset_hash[:deleted].files << fid
       end

data/lib/moab/file_inventory.rb

@@ -234,9 +234,11 @@ module Moab
         count += 1
       end
       if count == 0
-        format("%d B", size)
+        format('%d B', size)
       else
-        format("%.2f %s", size, %w[B KB MB GB TB][count])
+        # rubocop:disable Style/FormatStringToken
+        format('%.2f %s', size, %w[B KB MB GB TB][count])
+        # rubocop:enable Style/FormatStringToken
       end
     end
 
@@ -245,13 +247,13 @@ module Moab
     # @return [String] The standard name for the serialized inventory file of the given type
     def self.xml_filename(type = nil)
       case type
-      when "version"
+      when 'version'
         'versionInventory.xml'
-      when "additions"
+      when 'additions'
         'versionAdditions.xml'
-      when "manifests"
+      when 'manifests'
         'manifestInventory.xml'
-      when "directory"
+      when 'directory'
         'directoryInventory.xml'
       else
         raise ArgumentError, "unknown inventory type: #{type}"

data/lib/moab/file_inventory_difference.rb

@@ -109,18 +109,18 @@ module Moab
 
     # @return [Hash] Serializes the data and then filters it to report only the changes
     def differences_detail
-      #return self.summary if difference_count == 0
+      # return self.summary if difference_count == 0
       inv_diff = to_hash
-      inv_diff["group_differences"].each_value do |group_diff|
+      inv_diff['group_differences'].each_value do |group_diff|
         delete_subsets = []
-        group_diff["subsets"].each do |change_type, subset|
-          delete_subsets << change_type if (change_type == "identical") || (subset["count"] == 0)
+        group_diff['subsets'].each do |change_type, subset|
+          delete_subsets << change_type if (change_type == 'identical') || (subset['count'] == 0)
         end
         delete_subsets.each do |change_type|
-          group_diff["subsets"].delete(change_type)
-          group_diff.delete(change_type) if change_type != "identical"
+          group_diff['subsets'].delete(change_type)
+          group_diff.delete(change_type) if change_type != 'identical'
         end
-        group_diff.delete("subsets") if group_diff["subsets"].empty?
+        group_diff.delete('subsets') if group_diff['subsets'].empty?
       end
       inv_diff
     end

data/lib/moab/file_signature.rb

@@ -50,15 +50,15 @@ module Moab
 
     # @attribute
     # @return [String] The MD5 checksum value of the file
-    attribute :md5, String, on_save: proc { |n| n.nil? ? "" : n.to_s }
+    attribute :md5, String, on_save: proc { |n| n.nil? ? '' : n.to_s }
 
     # @attribute
     # @return [String] The SHA1 checksum value of the file
-    attribute :sha1, String, on_save: proc { |n| n.nil? ? "" : n.to_s }
+    attribute :sha1, String, on_save: proc { |n| n.nil? ? '' : n.to_s }
 
     # @attribute
     # @return [String] The SHA256 checksum value of the file
-    attribute :sha256, String, on_save: proc { |n| n.nil? ? "" : n.to_s }
+    attribute :sha256, String, on_save: proc { |n| n.nil? ? '' : n.to_s }
 
     KNOWN_ALGOS = {
       md5: proc { Digest::MD5.new },
@@ -79,7 +79,7 @@ module Moab
 
       signatures = algos_to_use.to_h { |k| [k, KNOWN_ALGOS[k].call] }
 
-      pathname.open("r") do |stream|
+      pathname.open('r') do |stream|
         while (buffer = stream.read(8192))
           signatures.each_value { |digest| digest.update(buffer) }
         end

data/lib/moab/storage_object.rb

@@ -124,7 +124,7 @@ module Moab
     # @param version_id [Integer] The version identifier of an object version
     # @return [String] The directory name of the version, relative to the digital object home directory (e.g v0002)
     def self.version_dirname(version_id)
-      format("v%04d", version_id)
+      format('v%04d', version_id)
     end
 
     # @return [Array<Integer>] The list of all version ids for this object
@@ -193,7 +193,7 @@ module Moab
     # * Version 0 is a special case used to generate empty manifests
     # * Current version + 1 is used for creation of a new version
     def storage_object_version(version_id)
-      raise(MoabRuntimeError, "Version ID not specified") unless version_id
+      raise(MoabRuntimeError, 'Version ID not specified') unless version_id
 
       StorageObjectVersion.new(self, version_id)
     end

data/lib/moab/storage_object_validator.rb

@@ -6,17 +6,17 @@ module Moab
   # Given a druid path, are the contents actually a well-formed Moab?
   # Shameless green: repetitious code included.
   class StorageObjectValidator
-    METADATA_DIR = "metadata"
-    CONTENT_DIR = "content"
+    METADATA_DIR = 'metadata'
+    CONTENT_DIR = 'content'
     EXPECTED_DATA_SUB_DIRS = [CONTENT_DIR, METADATA_DIR].freeze
     IMPLICIT_DIRS = ['.', '..'].freeze # unlike Find.find, Dir.entries returns the current/parent dirs
-    DATA_DIR = "data"
+    DATA_DIR = 'data'
     MANIFESTS_DIR = 'manifests'
     EXPECTED_VERSION_SUB_DIRS = [DATA_DIR, MANIFESTS_DIR].freeze
-    MANIFEST_INVENTORY_PATH = File.join(MANIFESTS_DIR, "manifestInventory.xml").freeze
-    SIGNATURE_CATALOG_PATH = File.join(MANIFESTS_DIR, "signatureCatalog.xml").freeze
+    MANIFEST_INVENTORY_PATH = File.join(MANIFESTS_DIR, 'manifestInventory.xml').freeze
+    SIGNATURE_CATALOG_PATH = File.join(MANIFESTS_DIR, 'signatureCatalog.xml').freeze
 
-    FORBIDDEN_CONTENT_SUB_DIRS = ([DATA_DIR, MANIFESTS_DIR] + EXPECTED_DATA_SUB_DIRS).freeze
+    VERSION_DIR_PATTERN = /^v\d{4}$/
 
     # error codes
     INCORRECT_DIR_CONTENTS = 0
@@ -26,13 +26,12 @@ module Moab
     NO_SIGNATURE_CATALOG = 4
     NO_MANIFEST_INVENTORY = 5
     NO_FILES_IN_MANIFEST_DIR = 6
-    VERSIONS_NOT_IN_ORDER = 7
+    TEST_OBJECT_VERSIONS_NOT_IN_ORDER = 7
     METADATA_SUB_DIRS_DETECTED = 8
     FILES_IN_VERSION_DIR = 9
     NO_FILES_IN_METADATA_DIR = 10
     NO_FILES_IN_CONTENT_DIR = 11
     CONTENT_SUB_DIRS_DETECTED = 12
-    BAD_SUB_DIR_IN_CONTENT_DIR = 13
 
     attr_reader :storage_obj_path
 
@@ -52,48 +51,43 @@ module Moab
     def self.error_code_to_messages
       @error_code_to_messages ||=
         {
-          INCORRECT_DIR_CONTENTS => "Incorrect items under %{addl} directory",
-          MISSING_DIR => "Missing directory: %{addl}",
-          EXTRA_CHILD_DETECTED => "Unexpected item in path: %{addl}",
-          VERSION_DIR_BAD_FORMAT => "Version directory name not in 'v00xx' format: %{addl}",
-          FILES_IN_VERSION_DIR => "Version directory %{addl} should not contain files; only the manifests and data directories",
-          NO_SIGNATURE_CATALOG => "Version %{addl}: Missing signatureCatalog.xml",
-          NO_MANIFEST_INVENTORY => "Version %{addl}: Missing manifestInventory.xml",
-          NO_FILES_IN_MANIFEST_DIR => "Version %{addl}: No files present in manifest dir",
-          METADATA_SUB_DIRS_DETECTED => "Version %{version}: metadata directory should only contain files, not directories. Found directory: %{dir}",
-          VERSIONS_NOT_IN_ORDER => "Should contain only sequential version directories. Current directories: %{addl}",
-          NO_FILES_IN_METADATA_DIR => "Version %{addl}: No files present in metadata dir",
-          NO_FILES_IN_CONTENT_DIR => "Version %{addl}: No files present in content dir",
-          CONTENT_SUB_DIRS_DETECTED => "Version %{version}: content directory should only contain files, not directories. Found directory: %{dir}",
-          BAD_SUB_DIR_IN_CONTENT_DIR => "Version %{addl}: content directory has forbidden sub-directory name: vnnnn or #{FORBIDDEN_CONTENT_SUB_DIRS}"
+          INCORRECT_DIR_CONTENTS => 'Incorrect items under %<addl>s directory',
+          MISSING_DIR => 'Missing directory: %<addl>s',
+          EXTRA_CHILD_DETECTED => 'Unexpected item in path: %<addl>s',
+          VERSION_DIR_BAD_FORMAT => "Version directory name not in 'v00xx' format: %<addl>s",
+          FILES_IN_VERSION_DIR => 'Version directory %<addl>s should not contain files; only the manifests and data directories',
+          NO_SIGNATURE_CATALOG => 'Version %<addl>s: Missing signatureCatalog.xml',
+          NO_MANIFEST_INVENTORY => 'Version %<addl>s: Missing manifestInventory.xml',
+          NO_FILES_IN_MANIFEST_DIR => 'Version %<addl>s: No files present in manifest dir',
+          METADATA_SUB_DIRS_DETECTED => 'Version %<version>s: metadata directory should only contain files, not directories. Found directory: %<dir>s',
+          TEST_OBJECT_VERSIONS_NOT_IN_ORDER => 'Should contain only sequential version directories. Current directories: %<addl>s',
+          NO_FILES_IN_METADATA_DIR => 'Version %<addl>s: No files present in metadata dir',
+          NO_FILES_IN_CONTENT_DIR => 'Version %<addl>s: No files present in content dir',
+          CONTENT_SUB_DIRS_DETECTED => 'Version %<version>s: content directory should only contain files, not directories. Found directory: %<dir>s'
         }.freeze
     end
 
     private
 
     def version_directories
-      @vdirs ||= directory_entries(storage_obj_path)
+      @version_directories ||= directory_entries(storage_obj_path)
     end
 
     def check_correctly_named_version_dirs
       errors = []
       errors << result_hash(MISSING_DIR, 'no versions exist') unless version_directories.count > 0
       version_directories.each do |version_dir|
-        errors << result_hash(VERSION_DIR_BAD_FORMAT, version_dir) unless version_dir_format?(version_dir)
+        errors << result_hash(VERSION_DIR_BAD_FORMAT, version_dir) unless VERSION_DIR_PATTERN.match?(version_dir)
       end
       errors
     end
 
-    def version_dir_format?(dirname)
-      dirname =~ /^v\d{4}$/
-    end
-
     # call only if the version directories are "correctly named" vdddd
     def check_sequential_version_dirs
       version_directories.each_with_index do |dir_name, index|
         next if dir_name[1..].to_i == index + 1 # version numbering starts at 1, array indexing at 0
 
-        return [result_hash(VERSIONS_NOT_IN_ORDER, version_directories)]
+        return [result_hash(TEST_OBJECT_VERSIONS_NOT_IN_ORDER, version_directories)]
       end
       []
     end
@@ -151,20 +145,9 @@ module Moab
       if content_sub_dir && !allow_content_subdirs
         errors << result_hash(CONTENT_SUB_DIRS_DETECTED, version: basename(version_path), dir: content_sub_dir)
       end
-      if allow_content_subdirs && contains_sub_dir?(content_dir_path) && contains_forbidden_content_sub_dir?(content_dir_path)
-        errors << result_hash(BAD_SUB_DIR_IN_CONTENT_DIR, basename(version_path))
-      end
       errors
     end
 
-    def contains_forbidden_content_sub_dir?(path)
-      sub_dirs(path).detect { |sub_dir| content_sub_dir_forbidden?(sub_dir) }
-    end
-
-    def content_sub_dir_forbidden?(dirname)
-      FORBIDDEN_CONTENT_SUB_DIRS.include?(dirname) || version_dir_format?(dirname)
-    end
-
     def check_metadata_dir_files_only(version_path)
       errors = []
       metadata_dir_path = File.join(version_path, DATA_DIR, METADATA_DIR)

data/lib/moab/storage_object_version.rb

@@ -174,7 +174,7 @@ module Moab
     # @return [void] link or copy the specified file from source location to the version directory
     def ingest_file(source_file, target_dir, use_links = true)
       if use_links
-        FileUtils.link(source_file.to_s, target_dir.to_s) #, :force => true)
+        FileUtils.link(source_file.to_s, target_dir.to_s)
       else
         FileUtils.copy(source_file.to_s, target_dir.to_s)
       end
@@ -225,7 +225,7 @@ module Moab
     # @return [VerificationResult] return true if the manifest inventory matches the actual files
     def verify_manifest_inventory
       # read/parse manifestInventory.xml
-      result = VerificationResult.new("manifest_inventory")
+      result = VerificationResult.new('manifest_inventory')
       manifest_inventory = file_inventory('manifests')
       result.subentities << VerificationResult.verify_value('composite_key', composite_key, manifest_inventory.composite_key)
       result.subentities << VerificationResult.verify_truth('manifests_group', !manifest_inventory.group_empty?('manifests'))
@@ -233,7 +233,7 @@ module Moab
       directory_inventory = FileInventory.new.inventory_from_directory(@version_pathname.join('manifests'), 'manifests')
       directory_inventory.digital_object_id = storage_object.digital_object_id
       directory_group = directory_inventory.group('manifests')
-      directory_group.remove_file_having_path("manifestInventory.xml")
+      directory_group.remove_file_having_path('manifestInventory.xml')
       # compare the measured signatures against the values in manifestInventory.xml
       diff = FileInventoryDifference.new
       diff.compare(manifest_inventory, directory_inventory)
@@ -247,7 +247,7 @@ module Moab
 
     # @return [VerificationResult]
     def verify_signature_catalog
-      result = VerificationResult.new("signature_catalog")
+      result = VerificationResult.new('signature_catalog')
       signature_catalog = self.signature_catalog
       result.subentities << VerificationResult.verify_value('signature_key', composite_key, signature_catalog.composite_key)
       found = 0
@@ -261,7 +261,7 @@ module Moab
           missing << storage_location.to_s
         end
       end
-      file_result = VerificationResult.new("storage_location")
+      file_result = VerificationResult.new('storage_location')
       file_result.verified = (found == signature_catalog.file_count)
       file_result.details = {
         'expected' => signature_catalog.file_count,
@@ -275,7 +275,7 @@ module Moab
 
     # @return [Boolean] true if files & signatures listed in version inventory can all be found
     def verify_version_inventory
-      result = VerificationResult.new("version_inventory")
+      result = VerificationResult.new('version_inventory')
       version_inventory = file_inventory('version')
       result.subentities << VerificationResult.verify_value('inventory_key', composite_key, version_inventory.composite_key)
       signature_catalog = self.signature_catalog
@@ -295,7 +295,7 @@ module Moab
           end
         end
       end
-      file_result = VerificationResult.new("catalog_entry")
+      file_result = VerificationResult.new('catalog_entry')
       file_result.verified = (found == version_inventory.file_count)
       file_result.details = {
         'expected' => version_inventory.file_count,
@@ -309,7 +309,7 @@ module Moab
 
     # @return [Boolean] returns true if files in data folder match files listed in version addtions inventory
     def verify_version_additions
-      result = VerificationResult.new("version_additions")
+      result = VerificationResult.new('version_additions')
       version_additions = file_inventory('additions')
       result.subentities << VerificationResult.verify_value('composite_key', composite_key, version_additions.composite_key)
       data_directory = @version_pathname.join('data')

data/lib/moab/storage_repository.rb

@@ -1,5 +1,7 @@
 # frozen_string_literal: true
 
+require 'find' # for object_size
+
 module Moab
   # A class to represent the SDR repository store
   #
@@ -20,10 +22,10 @@ module Moab
     # @return [Array<Pathname>] The list of filesystem root paths in which objects are stored
     def storage_roots
       unless defined?(@storage_roots)
-        raise(MoabRuntimeError, "Moab::Config.storage_roots not found in config file") if Moab::Config.storage_roots.nil?
+        raise(MoabRuntimeError, 'Moab::Config.storage_roots not found in config file') if Moab::Config.storage_roots.nil?
 
         @storage_roots = [Moab::Config.storage_roots].flatten.collect { |filesystem| Pathname(filesystem) }
-        raise(MoabRuntimeError, "Moab::Config.storage_roots empty") if @storage_roots.empty?
+        raise(MoabRuntimeError, 'Moab::Config.storage_roots empty') if @storage_roots.empty?
 
         @storage_roots.each { |root| raise(MoabRuntimeError, "Storage root #{root} not found on system") unless root.exist? }
       end
@@ -33,7 +35,7 @@ module Moab
     # @return [String] The trunk segment of the object storage path
     def storage_trunk
       unless defined?(@storage_trunk)
-        raise(MoabRuntimeError, "Moab::Config.storage_trunk not found in config file") if Moab::Config.storage_trunk.nil?
+        raise(MoabRuntimeError, 'Moab::Config.storage_trunk not found in config file') if Moab::Config.storage_trunk.nil?
 
         @storage_trunk = Moab::Config.storage_trunk
       end
@@ -43,7 +45,7 @@ module Moab
    # @param object_id [String] The identifier of the digital object
     # @return [String] The branch segment of the object storage path
     def storage_branch(object_id)
-      #todo This method should be customized, or overridden in a subclass
+      # TODO: This method should be customized, or overridden in a subclass
       # split a object ID into 2-character segments, followed by a copy of the object ID
       # for a more sophisticated pairtree implementation see https://github.com/microservices/pairtree
       path_segments = object_id.scan(/..?/) << object_id
@@ -103,34 +105,6 @@ module Moab
       create_storage_object(object_id, root)
     end
 
-    # @param object_id [String] The identifier of the digital object
-    # @param include_deposit [Boolean] specifies whether to look in deposit areas for objects in process of initial ingest
-    # @return [Array<StorageObject>] Representations of a digitial object's storage directories, or an empty array if none found.
-    def search_storage_objects(object_id, include_deposit = false)
-      storage_objects = []
-      # Search for the object's home directory in the storage areas
-      branch = storage_branch(object_id)
-      storage_roots.each do |root|
-        root_trunk = root.join(storage_trunk)
-        raise(MoabRuntimeError, "Storage area not found at #{root_trunk}") unless root_trunk.exist?
-
-        root_trunk_branch = root_trunk.join(branch)
-        storage_objects << create_storage_object(object_id, root) if root_trunk_branch.exist?
-      end
-      # Search for the object's directory in the deposit areas
-      if include_deposit && deposit_trunk
-        branch = deposit_branch(object_id)
-        storage_roots.each do |root|
-          root_trunk = root.join(deposit_trunk)
-          raise(MoabRuntimeError, "Deposit area not found at #{root_trunk}") unless root_trunk.exist?
-
-          root_trunk_branch = root_trunk.join(branch)
-          storage_objects << create_storage_object(object_id, root) if root_trunk_branch.exist?
-        end
-      end
-      storage_objects
-    end
-
     # @param object_id [String] The identifier of the digital object whose size is desired
     # @param include_deposit [Boolean] specifies whether to look in deposit areas for objects in process of initial ingest
     # @return [Integer] the size occupied on disk by the storage object, in bytes.  this is the entire moab (all versions).

data/lib/moab/storage_services.rb

@@ -13,81 +13,83 @@ module Moab
   # @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 StorageServices
-    # @return [StorageRepository] an instance of the interface to SDR storage
+    # @note After some discussion, consensus was that this is a thread safe use of a
+    # class variable, as 1) it's never mutated after the class is initialized, and 2) the
+    # value of the StorageRepository instance is determined from configuration that
+    # rarely changes and is loaded once at app start time (at least in Stanford's
+    # consumers; see Moab::Config.configure calls in preservation_robots, preservation_catalog,
+    # and technical-metadata-service).
+    # Sidekiq requires thread safe code, so please preserve thread safety for multiple
+    # concurrent callers of this service if refactoring, so Sidekiq remains an option for
+    # ActiveJob backend for moab-versioning consumers.
     @@repository = Moab::StorageRepository.new
 
+    # @return [StorageRepository] an instance of the interface to SDR storage
     def self.repository
       @@repository
     end
 
     # @return [Array<Pathname>] A list of the filesystems currently used for storage
     def self.storage_roots
-      @@repository.storage_roots
+      repository.storage_roots
     end
 
     # @return [String] The trunk segment of the object deposit path
     def self.deposit_trunk
-      @@repository.deposit_trunk
+      repository.deposit_trunk
     end
 
     # @param object_id [String] The identifier of the digital object
     # @return [Pathname] The branch segment of the object deposit path
     def self.deposit_branch(object_id)
-      @@repository.deposit_branch(object_id)
+      repository.deposit_branch(object_id)
     end
 
     # @param object_id [String] The identifier of the digital object
     # @param [Object] include_deposit
     # @return [StorageObject] The representation of a digitial object's  storage directory, which might not exist yet.
     def self.find_storage_object(object_id, include_deposit = false)
-      @@repository.find_storage_object(object_id, include_deposit)
-    end
-
-    # @param object_id [String] The identifier of the digital object
-    # @param [Object] include_deposit
-    # @return [Array<StorageObject>] Representations of a digitial object's storage directories, or an empty array if none found.
-    def self.search_storage_objects(object_id, include_deposit = false)
-      @@repository.search_storage_objects(object_id, include_deposit)
+      repository.find_storage_object(object_id, include_deposit)
     end
 
     # @param object_id [String] The identifier of the digital object whose size is desired
     # @param include_deposit [Boolean] specifies whether to look in deposit areas for objects in process of initial ingest
     # @return [Integer] the size occupied on disk by the storage object, in bytes.  this is the entire moab (all versions).
     def self.object_size(object_id, include_deposit = false)
-      @@repository.object_size(object_id, include_deposit)
+      repository.object_size(object_id, include_deposit)
     end
 
     # @param object_id [String] The identifier of the digital object whose version is desired
     # @param create [Boolean] If true, the object home directory should be created if it does not exist
     # @return [StorageObject] The representation of a digitial object's storage directory, which must exist.
     def self.storage_object(object_id, create = false)
-      @@repository.storage_object(object_id, create)
+      repository.storage_object(object_id, create)
     end
 
     # @param object_id [String] The digital object identifier of the object
     # @return [String] the location of the storage object
     def self.object_path(object_id)
-      @@repository.storage_object(object_id).object_pathname.to_s
+      repository.storage_object(object_id).object_pathname.to_s
     end
 
     # @param object_id [String] The digital object identifier of the object
     # @param [Integer] version_id The ID of the version, if nil use latest version
     # @return [String] the location of the storage object version
     def self.object_version_path(object_id, version_id = nil)
-      @@repository.storage_object(object_id).find_object_version(version_id).version_pathname.to_s
+      repository.storage_object(object_id).find_object_version(version_id).version_pathname.to_s
     end
 
     # @param object_id [String] The digital object identifier
     # @return [Integer] The version number of the currently highest version
     def self.current_version(object_id)
-      @@repository.storage_object(object_id).current_version_id
+      repository.storage_object(object_id).current_version_id
     end
 
     # @param [String] object_id The digital object identifier of the object
     # @param [Integer] version_id The ID of the version, if nil use latest version
     # @return [FileInventory] the file inventory for the specified object version
     def self.retrieve_file_group(file_category, object_id, version_id = nil)
-      storage_object_version = @@repository.storage_object(object_id).find_object_version(version_id)
+      storage_object_version = repository.storage_object(object_id).find_object_version(version_id)
       inventory_type = if file_category =~ /manifest/
                          file_category = 'manifests'
                        else
@@ -103,7 +105,7 @@ module Moab
     # @param [Integer] version_id The ID of the version, if nil use latest version
     # @return [Pathname] Pathname object containing the full path for the specified file
     def self.retrieve_file(file_category, file_id, object_id, version_id = nil)
-      storage_object_version = @@repository.storage_object(object_id).find_object_version(version_id)
+      storage_object_version = repository.storage_object(object_id).find_object_version(version_id)
       storage_object_version.find_filepath(file_category, file_id)
     end
 
@@ -113,7 +115,7 @@ module Moab
     # @param [Integer] version_id The ID of the version, if nil use latest version
     # @return [Pathname] Pathname object containing the full path for the specified file
     def self.retrieve_file_using_signature(file_category, file_signature, object_id, version_id = nil)
-      storage_object_version = @@repository.storage_object(object_id).find_object_version(version_id)
+      storage_object_version = repository.storage_object(object_id).find_object_version(version_id)
       storage_object_version.find_filepath_using_signature(file_category, file_signature)
     end
 
@@ -123,7 +125,7 @@ module Moab
     # @param [Integer] version_id The ID of the version, if nil use latest version
     # @return [FileSignature] The signature of the file
     def self.retrieve_file_signature(file_category, file_id, object_id, version_id = nil)
-      storage_object_version = @@repository.storage_object(object_id).find_object_version(version_id)
+      storage_object_version = repository.storage_object(object_id).find_object_version(version_id)
       storage_object_version.find_signature(file_category, file_id)
     end
 
@@ -132,8 +134,8 @@ module Moab
     # @param [Object] compare_version_id The identifier of the version to be compared to the base version
     # @return [FileInventoryDifference] The report of the version differences
     def self.version_differences(object_id, base_version_id, compare_version_id)
-      base_version = @@repository.storage_object(object_id).storage_object_version(base_version_id)
-      compare_version = @@repository.storage_object(object_id).storage_object_version(compare_version_id)
+      base_version = repository.storage_object(object_id).storage_object_version(base_version_id)
+      compare_version = repository.storage_object(object_id).storage_object_version(compare_version_id)
       base_inventory = base_version.file_inventory('version')
       compare_inventory = compare_version.file_inventory('version')
       FileInventoryDifference.new.compare(base_inventory, compare_inventory)

data/lib/moab/utc_time.rb

@@ -7,7 +7,7 @@ module Moab
     # @return [void] Convert input datetime to a Time object, or nil if input is empty.
     def self.input(datetime)
       case datetime
-      when nil, ""
+      when nil, ''
         nil
       when String
         Time.parse(datetime)
@@ -22,8 +22,8 @@ module Moab
     # @return [String] Convert the datetime into a ISO 8601 formatted string
     def self.output(datetime)
       case datetime
-      when nil, ""
-        ""
+      when nil, ''
+        ''
       when String
         Time.parse(datetime).utc.iso8601
       when Time

data/lib/moab/verification_result.rb

@@ -22,7 +22,7 @@ module Moab
       @entity = entity.to_s  # force to string
       @verified = !!verified # rubocop:disable Style/DoubleNegation
       @details = details
-      @subentities = Array.new
+      @subentities = []
     end
 
     # @param entity [#to_s] The name of the entity being verified

data/lib/serializer/manifest.rb

@@ -59,9 +59,9 @@ module Serializer
     def self.write_xml_file(xml_object, parent_dir, filename = nil)
       parent_dir.mkpath
       xml_pathname(parent_dir, filename).open('w') do |f|
-        xmlBuilder = Nokogiri::XML::Builder.new(encoding: 'UTF-8')
-        xmlBuilder = xml_object.to_xml(xmlBuilder)
-        f << xmlBuilder.to_xml
+        xml_builder = Nokogiri::XML::Builder.new(encoding: 'UTF-8')
+        xml_builder = xml_object.to_xml(xml_builder)
+        f << xml_builder.to_xml
       end
       nil
     end

data/lib/serializer/serializable.rb

@@ -120,7 +120,7 @@ module Serializer
     # @param other [Serializable] The other object being compared
     # @return [Hash] Generate a hash containing the differences between two objects of the same type
     def diff(other)
-      raise(Moab::MoabRuntimeError, "Cannot compare different classes") if self.class != other.class
+      raise(Moab::MoabRuntimeError, 'Cannot compare different classes') if self.class != other.class
 
       left = other.to_hash
       right = to_hash

data/lib/serializer.rb

@@ -19,7 +19,6 @@ require 'nokogiri'
 require 'happymapper'
 require 'json'
 require 'psych'
-#require 'json/pure'
 require 'pathname'
 require 'fileutils'
 require 'time'

data/lib/stanford/content_inventory.rb

@@ -23,7 +23,7 @@ module Stanford
       # 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
@@ -45,7 +45,7 @@ module Stanford
                 when 'shelve'
                   ng_doc.xpath("//file[@shelve='yes']")
                 when 'all'
-                  ng_doc.xpath("//file")
+                  ng_doc.xpath('//file')
                 else
                   raise(Moab::MoabRuntimeError, "Unknown disposition subset (#{subset})")
                 end
@@ -86,7 +86,7 @@ module Stanford
       instance.path = node.attributes['id'].content
       instance.datetime = begin
         node.attributes['datetime'].content
-      rescue
+      rescue StandardError
         nil
       end
       instance
@@ -98,8 +98,8 @@ 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) do
-          xml.resource(type: "version", sequence: "1", id: "version-#{version_id}") do
+        xml.contentMetadata(type: 'sample', objectId: object_id) do
+          xml.resource(type: 'version', sequence: '1', id: "version-#{version_id}") do
             file_group.files.each do |file_manifestation|
               signature = file_manifestation.signature
               file_manifestation.instances.each do |instance|
@@ -112,9 +112,9 @@ module Stanford
                   preserve: 'yes'
                 ) do
                   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
             end
@@ -139,16 +139,16 @@ module Stanford
       result = []
       content_metadata_doc =
         case content_metadata.class.name
-        when "String"
+        when 'String'
           Nokogiri::XML(content_metadata)
-        when "Pathname"
+        when 'Pathname'
           Nokogiri::XML(content_metadata.read)
-        when "Nokogiri::XML::Document"
+        when 'Nokogiri::XML::Document'
           content_metadata
         else
-          raise Moab::InvalidMetadataException, "Content Metadata is in unrecognized format"
+          raise Moab::InvalidMetadataException, 'Content Metadata is in unrecognized format'
         end
-      nodeset = content_metadata_doc.xpath("//file")
+      nodeset = content_metadata_doc.xpath('//file')
       nodeset.each do |file_node|
         missing = %w[id size md5 sha1]
         missing.delete('id') if file_node.has_attribute?('id')
@@ -184,7 +184,7 @@ module Stanford
       @type_for_name = Moab::FileSignature.checksum_type_for_name
       @names_for_type = Moab::FileSignature.checksum_names_for_type
       ng_doc = Nokogiri::XML(content_metadata, &:noblanks)
-      nodeset = ng_doc.xpath("//file")
+      nodeset = ng_doc.xpath('//file')
       nodeset.each do |file_node|
         filepath = file_node['id']
         signature = signature_for_path[filepath]

data/lib/stanford/storage_services.rb

@@ -3,9 +3,22 @@
 module Stanford
   # An interface class to support access to SDR storage via a RESTful server
   class StorageServices < Moab::StorageServices
-    # @return [StorageRepository] an instance of the interface to SDR storage
+    # @note After some discussion, consensus was that this is a thread safe use of a
+    # class variable, as 1) it's never mutated after the class is initialized, and 2) the
+    # value of the StorageRepository instance is determined from configuration that
+    # rarely changes and is loaded once at app start time (at least in Stanford's
+    # consumers; see Moab::Config.configure calls in preservation_robots, preservation_catalog,
+    # and technical-metadata-service).
+    # Sidekiq requires thread safe code, so please preserve thread safety for multiple
+    # concurrent callers of this service if refactoring, so Sidekiq remains an option for
+    # ActiveJob backend for moab-versioning consumers.
     @@repository = Stanford::StorageRepository.new
 
+    # @return [StorageRepository] an instance of the interface to SDR storage
+    def self.repository
+      @@repository
+    end
+
     # @param new_content_metadata [String] The content metadata to be compared to the base
     # @param object_id [String] The digital object identifier of the object whose version inventory is the basis of the
     #  comparison
@@ -42,7 +55,7 @@ module Stanford
       begin
         # ObjectNotFoundException is raised if the object does not exist in storage
         version_id ||= current_version(object_id)
-        storage_object_version = @@repository.storage_object(object_id).find_object_version(version_id)
+        storage_object_version = repository.storage_object(object_id).find_object_version(version_id)
         signature_catalog = storage_object_version.signature_catalog
       rescue Moab::ObjectNotFoundException
         storage_object = Moab::StorageObject.new(object_id, 'dummy')

metadata

@@ -1,17 +1,18 @@
 --- !ruby/object:Gem::Specification
 name: moab-versioning
 version: !ruby/object:Gem::Version
-  version: 5.2.0
+  version: 6.0.0.alpha
 platform: ruby
 authors:
-- Darren Weber
-- Richard Anderson
-- Lynn McRae
-- Hannah Frost
-autorequire:
+- Naomi Dushay
+- Justin Coyne
+- Tony Zanella
+- Mike Giarlo
+- John Martin
+autorequire: 
 bindir: bin
 cert_chain: []
-date: 2022-08-02 00:00:00.000000000 Z
+date: 2023-01-17 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: druid-tools
@@ -169,7 +170,11 @@ dependencies:
         version: '0'
 description: Contains classes to process digital object version content and metadata
 email:
-- darren.weber@stanford.edu
+- ndushay@stanford.edu
+- jcoyne85@stanford.edu
+- azanella@stanford.edu
+- mjgiarlo@stanford.edu
+- suntzu@stanford.edu
 executables: []
 extensions: []
 extra_rdoc_files: []
@@ -210,7 +215,7 @@ licenses:
 - Apache-2.0
 metadata:
   rubygems_mfa_required: 'true'
-post_install_message:
+post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
@@ -218,16 +223,16 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '2.7'
+      version: '3.0'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ">="
+  - - ">"
     - !ruby/object:Gem::Version
-      version: '0'
+      version: 1.3.1
 requirements: []
-rubygems_version: 3.3.7
-signing_key:
+rubygems_version: 3.2.32
+signing_key: 
 specification_version: 4
-summary: Ruby implementation of digital object versioning toolkit used by the SULAIR
-  Digital Library
+summary: Ruby implementation of digital object versioning toolkit used by Stanford
+  University Libraries
 test_files: []