assembly-objectfile 1.10.0 → 1.11.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: ab94538c86ddec92361ad8be34b75f30d5c5c2991ddbb25e3375593e6c079b94
-  data.tar.gz: b03077ed3ae19b4c77615ce407e600b8cacdaa190cded54e98edc5461d360af8
+  metadata.gz: 0f0c15e9e8be693ac604d4f4f440a62b8c91d4e10e1605d78ecf487b45aa231b
+  data.tar.gz: 1441b9f02785c6397cfee954382b4b0de92e006457b0a5bfce42111b4f1ee634
 SHA512:
-  metadata.gz: e77fd23ee31f26f9d9cd4502b760670381e5e97ade348274e52f9b70e318b4d8dd54bd45fe7529535a8912f60c822dfb616f71306f8381f6923bffa37c631993
-  data.tar.gz: 8d92581381a3464cc0cfb44bf0e7dabd3222edf70acf477c293d79c7b1791ca5c626bf2458d1faebe05a1ef5f4606d53e1a7a1266ff18e68257dbfe1f66ddfcd
+  metadata.gz: b12637ddf0e5110ada401dfd04f35072a42046c02fabd1446139f5c387f31bf82fb82ff6b95621f1f182f839ad50b2f66f529ddff61c79979a0c248659dd7947
+  data.tar.gz: f2bf8dcce09af5ac5f499ffff3abafd8ef01b03a30ceb249a590da75b594fd96dcd8a0e73b295ff37ca52825941c5b2892ed05c1746a9de5d85e048138f7e67b

data/.github/pull_request_template.md

@@ -2,4 +2,11 @@
 
 
 
-## Was the documentation updated?
+## How was this change tested?
+
+
+
+## Which documentation and/or configurations were updated?
+
+
+

data/.rubocop.yml

@@ -1,6 +1,9 @@
 inherit_from: .rubocop_todo.yml
 require: rubocop-rspec
 
+AllCops:
+  TargetRubyVersion: 2.5
+
 RSpec/ContextWording:
   Enabled: false # too dogmatic
 
@@ -16,11 +19,69 @@ RSpec/NestedGroups:
 
 Metrics/BlockLength:
   Exclude:
-    - spec/**/*_spec.rb
+    - 'spec/**/*.rb'
+    - '**/*.gemspec'
+
+Gemspec/DateAssignment: # (new in 1.10)
+  Enabled: true
 
 Layout/SpaceAroundMethodCallOperator:
   Enabled: true
 
+Layout/EmptyLinesAroundAttributeAccessor:
+  Enabled: true
+
+Layout/SpaceBeforeBrackets: # (new in 1.7)
+  Enabled: true
+
+Lint/AmbiguousAssignment: # (new in 1.7)
+  Enabled: true
+
+Lint/DeprecatedConstants: # (new in 1.8)
+  Enabled: true
+
+Lint/DuplicateBranch: # (new in 1.3)
+  Enabled: true
+
+Lint/DuplicateRegexpCharacterClassElement: # (new in 1.1)
+  Enabled: true
+
+Lint/EmptyBlock: # (new in 1.1)
+  Enabled: true
+
+Lint/EmptyClass: # (new in 1.3)
+  Enabled: true
+
+Lint/LambdaWithoutLiteralBlock: # (new in 1.8)
+  Enabled: true
+
+Lint/NoReturnInBeginEndBlocks: # (new in 1.2)
+  Enabled: true
+
+Lint/NumberedParameterAssignment: # (new in 1.9)
+  Enabled: true
+
+Lint/OrAssignmentToConstant: # (new in 1.9)
+  Enabled: true
+
+Lint/RedundantDirGlobSort: # (new in 1.8)
+  Enabled: true
+
+Lint/SymbolConversion: # (new in 1.9)
+  Enabled: true
+
+Lint/ToEnumArguments: # (new in 1.1)
+  Enabled: true
+
+Lint/TripleQuotes: # (new in 1.9)
+  Enabled: true
+
+Lint/UnexpectedBlockArity: # (new in 1.5)
+  Enabled: true
+
+Lint/UnmodifiedReduceAccumulator: # (new in 1.1)
+  Enabled: true
+
 Lint/RaiseException:
   Enabled: true
 
@@ -38,3 +99,39 @@ Style/HashTransformKeys:
 
 Style/HashTransformValues:
   Enabled: true
+
+Style/SlicingWithRange:
+  Enabled: true
+
+Style/ArgumentsForwarding: # (new in 1.1)
+  Enabled: true
+
+Style/CollectionCompact: # (new in 1.2)
+  Enabled: true
+
+Style/DocumentDynamicEvalDefinition: # (new in 1.1)
+  Enabled: true
+
+Style/EndlessMethod: # (new in 1.8)
+  Enabled: true
+
+Style/HashConversion: # (new in 1.10)
+  Enabled: true
+
+Style/HashExcept: # (new in 1.7)
+  Enabled: true
+
+Style/IfWithBooleanLiteralBranches: # (new in 1.9)
+  Enabled: true
+
+Style/NegatedIfElseCondition: # (new in 1.2)
+  Enabled: true
+
+Style/NilLambda: # (new in 1.3)
+  Enabled: true
+
+Style/RedundantArgument: # (new in 1.4)
+  Enabled: true
+
+Style/SwapValues: # (new in 1.1)
+  Enabled: true

data/.rubocop_todo.yml

@@ -1,6 +1,6 @@
 # This configuration was generated by
 # `rubocop --auto-gen-config`
-# on 2020-04-23 10:59:56 -0500 using RuboCop version 0.82.0.
+# on 2021-04-26 18:43:37 UTC using RuboCop version 1.11.0.
 # The point is for the user to remove these configuration records
 # one by one as the offenses are removed from the code base.
 # Note that changes in the inspected code, or installation of new
@@ -12,13 +12,13 @@ Lint/UselessAssignment:
     - 'config/boot.rb'
 
 # Offense count: 3
-# Configuration parameters: IgnoredMethods.
+# Configuration parameters: IgnoredMethods, CountRepeatedAttributes.
 Metrics/AbcSize:
-  Max: 51
+  Max: 55
 
-# Offense count: 2
-# Configuration parameters: CountComments, ExcludedMethods.
-# ExcludedMethods: refine
+# Offense count: 1
+# Configuration parameters: CountComments, CountAsOne, ExcludedMethods, IgnoredMethods.
+# IgnoredMethods: refine
 Metrics/BlockLength:
   Max: 27
 
@@ -28,27 +28,27 @@ Metrics/CyclomaticComplexity:
   Max: 14
 
 # Offense count: 4
-# Configuration parameters: CountComments, ExcludedMethods.
+# Configuration parameters: CountComments, CountAsOne, ExcludedMethods, IgnoredMethods.
 Metrics/MethodLength:
-  Max: 30
+  Max: 31
 
 # Offense count: 1
-# Configuration parameters: CountComments.
+# Configuration parameters: CountComments, CountAsOne.
 Metrics/ModuleLength:
-  Max: 117
+  Max: 120
 
 # Offense count: 1
-# Configuration parameters: CountKeywordArgs.
+# Configuration parameters: CountKeywordArgs, MaxOptionalParameters.
 Metrics/ParameterLists:
-  Max: 11
+  Max: 12
 
 # Offense count: 2
 # Configuration parameters: IgnoredMethods.
 Metrics/PerceivedComplexity:
-  Max: 12
+  Max: 15
 
 # Offense count: 1
-# Configuration parameters: ExpectMatchingDefinition, Regex, IgnoreExecutableScripts, AllowedAcronyms.
+# Configuration parameters: ExpectMatchingDefinition, CheckDefinitionPathHierarchy, Regex, IgnoreExecutableScripts, AllowedAcronyms.
 # AllowedAcronyms: CLI, DSL, ACL, API, ASCII, CPU, CSS, DNS, EOF, GUID, HTML, HTTP, HTTPS, ID, IP, JSON, LHS, QPS, RAM, RHS, RPC, SLA, SMTP, SQL, SSH, TCP, TLS, TTL, UDP, UI, UID, UUID, URI, URL, UTF8, VM, XML, XMPP, XSRF, XSS
 Naming/FileName:
   Exclude:
@@ -65,27 +65,27 @@ Naming/PredicateName:
     - 'spec/**/*'
     - 'lib/assembly-objectfile/object_fileable.rb'
 
-# Offense count: 8
+# Offense count: 9
 # Configuration parameters: Max.
 RSpec/ExampleLength:
   Exclude:
     - 'spec/content_metadata_spec.rb'
 
 # Offense count: 2
-# Configuration parameters: CustomTransform, IgnoreMethods.
+# Configuration parameters: Include, CustomTransform, IgnoreMethods, SpecSuffixOnly.
+# Include: **/*_spec*rb*, **/spec/**/*
 RSpec/FilePath:
   Exclude:
     - 'spec/content_metadata_spec.rb'
     - 'spec/object_file_spec.rb'
 
-# Offense count: 71
+# Offense count: 74
 # Configuration parameters: AssignmentOnly.
 RSpec/InstanceVariable:
   Exclude:
     - 'spec/object_file_spec.rb'
 
-# Offense count: 38
-# Configuration parameters: AggregateFailuresByDefault.
+# Offense count: 40
 RSpec/MultipleExpectations:
   Max: 29
 
@@ -105,13 +105,14 @@ RSpec/RepeatedExampleGroupDescription:
     - 'spec/content_metadata_spec.rb'
 
 # Offense count: 2
+# Cop supports --auto-correct.
 Style/CommentedKeyword:
   Exclude:
     - 'lib/assembly-objectfile/content_metadata.rb'
 
-# Offense count: 409
+# Offense count: 122
 # Cop supports --auto-correct.
 # Configuration parameters: AutoCorrect, AllowHeredoc, AllowURI, URISchemes, IgnoreCopDirectives, IgnoredPatterns.
 # URISchemes: http, https
 Layout/LineLength:
-  Max: 284
+  Max: 277

data/README.md

@@ -1,4 +1,4 @@
-[![Build Status](https://travis-ci.org/sul-dlss/assembly-objectfile.svg?branch=master)](https://travis-ci.org/sul-dlss/assembly-objectfile)
+[![Build Status](https://travis-ci.com/sul-dlss/assembly-objectfile.svg?branch=main)](https://travis-ci.com/sul-dlss/assembly-objectfile)
 [![Test Coverage](https://api.codeclimate.com/v1/badges/2310962acce78d78e76c/test_coverage)](https://codeclimate.com/github/sul-dlss/assembly-objectfile/test_coverage)
 [![Maintainability](https://api.codeclimate.com/v1/badges/2310962acce78d78e76c/maintainability)](https://codeclimate.com/github/sul-dlss/assembly-objectfile/maintainability)
 [![Gem Version](https://badge.fury.io/rb/assembly-objectfile.svg)](https://badge.fury.io/rb/assembly-objectfile)

data/assembly-objectfile.gemspec

@@ -20,6 +20,8 @@ Gem::Specification.new do |s|
   s.executables   = s.files.grep(%r{^exe/}) { |f| File.basename(f) }
   s.require_paths = ['lib']
 
+  s.required_ruby_version = '>= 2.5', '< 4'
+
   s.add_dependency 'activesupport', '>= 5.2.0'
   s.add_dependency 'deprecation'
   s.add_dependency 'dry-struct', '~> 1.0'
@@ -33,5 +35,5 @@ Gem::Specification.new do |s|
   s.add_development_dependency 'rspec', '~> 3.0'
   s.add_development_dependency 'rubocop'
   s.add_development_dependency 'rubocop-rspec'
-  s.add_development_dependency 'simplecov'
+  s.add_development_dependency 'simplecov', '~> 0.17.0' # CodeClimate cannot use SimpleCov >= 0.18.0 for generating test coverage
 end

data/config/boot.rb

@@ -3,9 +3,9 @@
 require 'rubygems'
 
 environment  = ENV['ENVIRONMENT'] ||= 'development'
-project_root = File.expand_path(File.dirname(__FILE__) + '/..')
+project_root = File.expand_path("#{File.dirname(__FILE__)}/..")
 
 # Load config for current environment.
-$LOAD_PATH.unshift(project_root + '/lib')
+$LOAD_PATH.unshift("#{project_root}/lib")
 
 require 'assembly-objectfile'

data/lib/assembly-objectfile/content_metadata/config.rb

@@ -12,13 +12,15 @@ module Assembly
 
     # Represents a configuration for generating the content metadata
     class Config < Dry::Struct
-      STYLES = %w[image file book map 3d document].freeze
+      STYLES = %w[image file book map 3d document webarchive-seed].freeze
+      READING_ORDERS = %w[ltr rtl].freeze
       attribute :auto_labels, Types::Strict::Bool.default(true)
       attribute :flatten_folder_structure, Types::Strict::Bool.default(false)
       attribute :add_file_attributes, Types::Strict::Bool.default(false)
       attribute :add_exif, Types::Strict::Bool.default(false)
       attribute :file_attributes, Types::Strict::Hash.default({}.freeze)
       attribute :type, Types::Strict::String.enum(*STYLES)
+      attribute :reading_order, Types::Strict::String.default('ltr').enum(*READING_ORDERS)
     end
   end
 end

data/lib/assembly-objectfile/content_metadata/file.rb

@@ -29,7 +29,7 @@ module Assembly
       # @param [Symbol] bundle
       # @param [Assembly::ObjectFile] file
       # @param style
-      def initialize(bundle: nil, file:, style: nil)
+      def initialize(file:, bundle: nil, style: nil)
         @bundle = bundle
         @file = file
         @style = style

data/lib/assembly-objectfile/content_metadata/file_set.rb

@@ -9,7 +9,7 @@ module Assembly
       # @param [Boolean] dpg (false) is it a dpg bundle?
       # @param [Array<Assembly::ObjectFile>] resource_files
       # @param style
-      def initialize(dpg: false, resource_files:, style:)
+      def initialize(resource_files:, style:, dpg: false)
         @dpg = dpg
         @resource_files = resource_files
         @style = style
@@ -46,7 +46,7 @@ module Assembly
         resource_has_non_images = !(resource_file_types - [:image]).empty?
 
         case style
-        when :simple_image
+        when :simple_image, :map, :'webarchive-seed'
           'image'
         when :file
           'file'
@@ -56,8 +56,6 @@ module Assembly
           resource_has_non_images && resource_file_types.include?(:image) == false ? 'object' : 'image'
         when :book_with_pdf # in book with PDF type, if we find a resource with *any* non images, switch it's type from book to object
           resource_has_non_images ? 'object' : 'page'
-        when :map
-          'image'
         when :document
           'document'
         when :'3d'

data/lib/assembly-objectfile/content_metadata/nokogiri_builder.rb

@@ -15,6 +15,8 @@ module Assembly
 
         Nokogiri::XML::Builder.new do |xml|
           xml.contentMetadata(objectId: druid.to_s, type: config.type) do
+            xml.bookData(readingOrder: config.reading_order) if config.type == 'book'
+
             filesets.each_with_index do |fileset, index| # iterate over all the resources
               # start a new resource element
               sequence = index + 1

data/lib/assembly-objectfile/content_metadata.rb

@@ -14,7 +14,7 @@ module Assembly
   # these are used when :bundle=>:dpg only
 
   DEPRECATED_STYLES = %i[book_with_pdf book_as_image].freeze
-  VALID_STYLES = %i[simple_image simple_book file map document 3d].freeze
+  VALID_STYLES = %i[simple_image simple_book file map document 3d webarchive-seed].freeze
 
   # This class generates content metadata for image files
   class ContentMetadata
@@ -34,6 +34,7 @@ module Assembly
     #                 :book_as_image, as simple_book, but with contentMetadata type="book", resource type="image" (same rule applies for resources with non images)  - NOTE: THIS IS DEPRECATED
     #                 :map, like simple_image, but with contentMetadata type="map", resource type="image"
     #                 :3d, contentMetadata type="3d", ".obj" and other configured 3d extension files go into resource_type="3d", everything else into resource_type="file"
+    #                 :webarchive-seed, contentMetadata type="webarchive-seed", resource type="image"
     #   :bundle = optional - a symbol containing the method of bundling files into resources, allowed values are
     #                 :default = all files get their own resources (default)
     #                 :filename = files with the same filename but different extensions get bundled together in a single resource
@@ -51,13 +52,15 @@ module Assembly
     #   :flatten_folder_structure = optional - Will remove *all* folder structure when genearting file IDs (e.g. DPG subfolders like '00','05' will be removed) when generating file IDs.  This is useful if the folder structure is flattened when staging files (like for DPG).
     #                                             The default is false.  If set to true, will override the "preserve_common_paths" parameter.
     #   :auto_labels = optional - Will add automated resource labels (e.g. "File 1") when labels are not provided by the user.  The default is true.
+    #   See https://consul.stanford.edu/pages/viewpage.action?spaceKey=chimera&title=DOR+content+types%2C+resource+types+and+interpretive+metadata for next two settings
+    #   :reading_order = optional - only valid for simple_book, can be 'rtl' or 'ltr'.  The default is 'ltr'.
     # Example:
     #    Assembly::ContentMetadata.create_content_metadata(:druid=>'druid:nx288wh8889',:style=>:simple_image,:objects=>object_files,:add_file_attributes=>false)
     def self.create_content_metadata(druid:, objects:, auto_labels: true,
                                      add_exif: false, bundle: :default, style: :simple_image,
                                      add_file_attributes: false, file_attributes: {},
                                      preserve_common_paths: false, flatten_folder_structure: false,
-                                     include_root_xml: nil)
+                                     include_root_xml: nil, reading_order: 'ltr')
 
       common_path = find_common_path(objects) unless preserve_common_paths # find common paths to all files provided if needed
 
@@ -67,6 +70,7 @@ module Assembly
                           add_file_attributes: add_file_attributes,
                           file_attributes: file_attributes,
                           add_exif: add_exif,
+                          reading_order: reading_order,
                           type: object_level_type(style))
 
       builder = NokogiriBuilder.build(druid: druid,
@@ -74,13 +78,11 @@ module Assembly
                                       common_path: common_path,
                                       config: config)
 
-      result = if include_root_xml == false
-                 builder.doc.root.to_xml
-               else
-                 builder.to_xml
-               end
-
-      result
+      if include_root_xml == false
+        builder.doc.root.to_xml
+      else
+        builder.to_xml
+      end
     end
 
     def self.special_dpg_folder?(folder)

data/lib/assembly-objectfile/object_file.rb

@@ -19,10 +19,10 @@ module Assembly
       x = strings.last
       n += 1 while strings.all? { |s| s[n] && (s[n] == x[n]) }
       common_prefix = x[0...n]
-      if common_prefix[-1, 1] != '/' # check if last element of the common string is the end of a directory
-        common_prefix.split('/')[0..-2].join('/') + '/' # if not, split string along directories, and reject last one
+      if common_prefix[-1, 1] == '/' # check if last element of the common string is the end of a directory
+        common_prefix # if not, split string along directories, and reject last one
       else
-        common_prefix # if it was, then return the common prefix directly
+        "#{common_prefix.split('/')[0..-2].join('/')}/" # if it was, then return the common prefix directly
       end
     end
   end

data/lib/assembly-objectfile/object_fileable.rb

@@ -7,7 +7,8 @@ module Assembly
   # Common behaviors we need for other classes in the gem
   module ObjectFileable
     attr_accessor :file_attributes, :label, :path, :provider_md5, :provider_sha1, :relative_path, :mime_type_order
-    VALID_MIMETYPE_METHODS = %i[exif file extension].freeze
+
+    VALID_MIMETYPE_METHODS = %i[override exif file extension].freeze
 
     # @param [String] path full path to the file to be worked with
     # @param [Hash<Symbol => Object>] params options used during content metadata generation
@@ -17,7 +18,8 @@ module Assembly
     # @option params [String] :provider_sha1 pre-computed SHA1 checksum
     # @option params [String] :relative_path if you want the file ids in the content metadata it can be set, otherwise content metadata will get the full path
     # @option params [Array] :mime_type_order can be set to the order in which you want mimetypes to be determined
-    #                                          options are :exif (from exif if exists), :extension (from file extension), and :file (from unix file system command)
+    #                                          options are :override (from manual overide mapping if exists), :exif (from exif if exists),
+    #                                                      :extension (from file extension), and :file (from unix file system command)
     #                                          the default is defined in the private `default_mime_type_order` method but you can override to set your own order
     # @example
     #   Assembly::ObjectFile.new('/input/path_to_file.tif')
@@ -87,11 +89,11 @@ module Assembly
     #   puts source_file.exif # hash with exif information
     def exif
       @exif ||= begin
-                  check_for_file
-                  MiniExiftool.new(path, replace_invalid_chars: '?')
-                rescue StandardError
-                  nil
-                end
+        check_for_file
+        MiniExiftool.new(path, replace_invalid_chars: '?')
+      rescue StandardError
+        nil
+      end
     end
 
     # Computes md5 checksum or returns cached value
@@ -126,12 +128,21 @@ module Assembly
         mimetype = ''
         mime_type_order.each do |mime_type_method|
           mimetype = public_send("#{mime_type_method}_mimetype") if VALID_MIMETYPE_METHODS.include?(mime_type_method)
-          break if !mimetype.nil? && mimetype != ''
+          break if mimetype.present?
         end
         mimetype
       end
     end
 
+    # Returns mimetype information using the manual override mapping (based on a file extension lookup)
+    # @return [String] mime type for supplied file if a mapping exists for the file's extension
+    # @example
+    #   source_file = Assembly::ObjectFile.new('/input/path_to_file.json')
+    #   puts source_file.override_mimetype # 'application/json'
+    def override_mimetype
+      @override_mimetype ||= Assembly::OVERRIDE_MIMETYPES.fetch(ext.to_sym, '')
+    end
+
     # Returns mimetype information using the mime-types gem (based on a file extension lookup)
     # @return [String] mime type for supplied file
     # @example
@@ -208,7 +219,7 @@ exif&.mimetype && prefer_exif
     def valid_image?
       return false unless image?
 
-      mimetype == 'image/jp2' || jp2able? ? true : false
+      mimetype == 'image/jp2' || jp2able?
     end
 
     # @return [Boolean] true if image has a color profile, false if not.
@@ -256,7 +267,7 @@ exif&.mimetype && prefer_exif
 
     # prive method defining default preferred ordering of how mimetypes are determined
     def default_mime_type_order
-      %i[exif file extension]
+      %i[override exif file extension]
     end
 
     # private method to check for file existence before operating on it

data/lib/assembly-objectfile/version.rb

@@ -4,6 +4,6 @@
 module Assembly
   class ObjectFile
     # Project version number
-    VERSION = '1.10.0'
+    VERSION = '1.11.0'
   end
 end

data/lib/assembly-objectfile.rb

@@ -2,7 +2,7 @@
 
 module Assembly
   # the path to the gem, used to access profiles stored with the gem
-  PATH_TO_GEM = File.expand_path(File.dirname(__FILE__) + '/..')
+  PATH_TO_GEM = File.expand_path("#{File.dirname(__FILE__)}/..")
 
   # if input image is not one of these mime types, it will not be regarded as a valid image for the purpose of generating a JP2 derivative
   VALID_IMAGE_MIMETYPES = ['image/jpeg', 'image/tiff', 'image/tif', 'image/png'].freeze
@@ -14,6 +14,14 @@ module Assembly
   #  by the file command, then a check will be made to see if exif data exists...if so, the mimetype returned by the exif data will be used
   #  if no exif data exists, then the mimetype returned by the unix file command will be used
   TRUSTED_MIMETYPES = ['text/plain', 'plain/text', 'application/pdf', 'text/html', 'application/xml'].freeze
+
+  # this is a manual override mapping of file extension to mimetype; if a file with the given extension is found, the mapped
+  #  mimetype will be returned and no further methods will be used - this is used to force a specific mimetype to be returned for
+  #  for a given file extension regardless of what exif or the unix file system command returns
+  #  the mapping format is "extension with period: returned mimetype",  e.g. for any .json file, you will always get `application/json`
+  OVERRIDE_MIMETYPES = {
+    '.json': 'application/json'
+  }.freeze
 end
 
 require 'assembly-objectfile/content_metadata'