assembly-objectfile 2.0.0 → 2.1.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: c3c456d372ab0804ebcaad06ac2b8695376f9ffe57ccb8a23b8a57d711df5561
-  data.tar.gz: 1797606727f148ee128dedc102ad68480fbd9f55983c318b91c8f5f52a546a9b
+  metadata.gz: '0931aac97a88ba77ac0cfa8ff018d19fddcfe909c81cd82e9dfc13dca12ed4f4'
+  data.tar.gz: 4eb596c2799586b3298cd1019be16606b4a371a175c4630b1ac826296dacb5bb
 SHA512:
-  metadata.gz: c927cb2cffef41a699c0f2e1f0fa0d8e6d4b1cc92c9fdb26b80ca5c9e851d7de0a9b1204cc4a4290213a9d7a642c2d3233db56396efb3b626cdd4d6e7b3bfdda
-  data.tar.gz: 473f2ead345feaf0afd518da399751a86f526f27b19dd0bfd75fb55354bd055d00ccbbb06a96ca905f2e0de6fcdbf25d4e42e8da23fc167225afb8a9958038e3
+  metadata.gz: a252cfc25b6e2a11f50a6eb2976997fdcbf387ba3855fbca03d188a2f7e9572ca1a3ed605da191700551e34a685deb9dec810e63dfbff59bf9bfd09f6a6a9504
+  data.tar.gz: db0fdbf6583455bce118aa14bc29692d90fbb35c1e9746f3748548094ff53e0f33fe79c08cf5baace3869a08e4f9e3080d1906b810ce38d64022efa573e8c500

data/.circleci/config.yml

@@ -1,6 +1,6 @@
 version: 2.1
 orbs:
-  ruby-rails: sul-dlss/ruby-rails@3.0.1
+  ruby-rails: sul-dlss/ruby-rails@3.1.2
 workflows:
   build:
     jobs:

data/.rubocop.yml

@@ -9,11 +9,31 @@ AllCops:
     - '**/*.md'
     - 'vendor/**/*' # avoid running rubocop on cached bundler
 
+Layout/LineLength:
+  Max: 120
+
+Naming/FileName:
+  Exclude:
+    - 'lib/assembly-objectfile.rb'
+
+Naming/PredicateName:
+  NamePrefix:
+    - 'is_'
+
 Metrics/BlockLength:
   Exclude:
     - 'spec/**/*.rb'
     - '**/*.gemspec'
 
+RSpec/ExampleLength:
+  Max: 10
+
+RSpec/MultipleExpectations:
+  Max: 10
+
+RSpec/NestedGroups:
+  Max: 4
+
 Gemspec/DeprecatedAttributeAssignment: # (new in 1.10)
   Enabled: true
 
@@ -207,3 +227,16 @@ RSpec/ChangeByZero: # new in 2.11.0
   Enabled: true
 RSpec/VerifiedDoubleReference: # new in 2.10.0
   Enabled: true
+
+Layout/LineContinuationLeadingSpace: # new in 1.31
+  Enabled: true
+Layout/LineContinuationSpacing: # new in 1.31
+  Enabled: true
+Lint/ConstantOverwrittenInRescue: # new in 1.31
+  Enabled: true
+Lint/NonAtomicFileOperation: # new in 1.31
+  Enabled: true
+RSpec/Capybara/SpecificMatcher: # new in 2.12
+  Enabled: true
+RSpec/Rails/HaveHttpStatus: # new in 2.12
+  Enabled: true

data/.rubocop_todo.yml

@@ -1,63 +1,12 @@
 # This configuration was generated by
 # `rubocop --auto-gen-config`
-# on 2022-07-07 21:26:21 UTC using RuboCop version 1.31.0.
+# on 2022-07-20 17:16:46 UTC using RuboCop version 1.31.2.
 # 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
 # versions of RuboCop, may require this file to be generated again.
 
-# Offense count: 1
-Lint/UselessAssignment:
-  Exclude:
-    - 'config/boot.rb'
-
 # Offense count: 1
 # Configuration parameters: CountComments, CountAsOne.
 Metrics/ClassLength:
   Max: 122
-
-# Offense count: 1
-# Configuration parameters: ExpectMatchingDefinition, CheckDefinitionPathHierarchy, CheckDefinitionPathHierarchyRoots, Regex, IgnoreExecutableScripts, AllowedAcronyms.
-# CheckDefinitionPathHierarchyRoots: lib, spec, test, src
-# 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:
-    - 'lib/assembly-objectfile.rb'
-
-# Offense count: 1
-# Configuration parameters: NamePrefix, ForbiddenPrefixes, AllowedMethods, MethodDefinitionMacros.
-# NamePrefix: is_, has_, have_
-# ForbiddenPrefixes: is_, has_, have_
-# AllowedMethods: is_a?
-# MethodDefinitionMacros: define_method, define_singleton_method
-Naming/PredicateName:
-  Exclude:
-    - 'spec/**/*'
-    - 'lib/assembly-objectfile/object_file.rb'
-
-# Offense count: 2
-# Configuration parameters: CountAsOne.
-RSpec/ExampleLength:
-  Max: 7
-
-# Offense count: 1
-# Configuration parameters: Include, CustomTransform, IgnoreMethods, SpecSuffixOnly.
-# Include: **/*_spec*rb*, **/spec/**/*
-RSpec/FilePath:
-  Exclude:
-    - 'spec/object_file_spec.rb'
-
-# Offense count: 8
-RSpec/MultipleExpectations:
-  Max: 6
-
-# Offense count: 3
-RSpec/NestedGroups:
-  Max: 4
-
-# Offense count: 24
-# This cop supports safe autocorrection (--autocorrect).
-# Configuration parameters: AllowHeredoc, AllowURI, URISchemes, IgnoreCopDirectives, AllowedPatterns, IgnoredPatterns.
-# URISchemes: http, https
-Layout/LineLength:
-  Max: 187

data/Gemfile.lock

@@ -1,17 +1,15 @@
 PATH
   remote: .
   specs:
-    assembly-objectfile (2.0.0)
+    assembly-objectfile (2.1.2)
       activesupport (>= 5.2.0)
-      deprecation
       mime-types (> 3)
       mini_exiftool
-      nokogiri
 
 GEM
   remote: http://rubygems.org/
   specs:
-    activesupport (7.0.3)
+    activesupport (7.0.3.1)
       concurrent-ruby (~> 1.0, >= 1.0.2)
       i18n (>= 1.6, < 2)
       minitest (>= 5.1)
@@ -20,11 +18,9 @@ GEM
     byebug (11.1.3)
     coderay (1.1.3)
     concurrent-ruby (1.1.10)
-    deprecation (1.1.0)
-      activesupport
     diff-lcs (1.5.0)
     docile (1.4.0)
-    i18n (1.10.0)
+    i18n (1.12.0)
       concurrent-ruby (~> 1.0)
     json (2.6.2)
     method_source (1.0.0)
@@ -32,13 +28,9 @@ GEM
       mime-types-data (~> 3.2015)
     mime-types-data (3.2022.0105)
     mini_exiftool (2.10.2)
-    mini_portile2 (2.8.0)
-    minitest (5.16.2)
-    nokogiri (1.13.6)
-      mini_portile2 (~> 2.8.0)
-      racc (~> 1.4)
+    minitest (5.16.3)
     parallel (1.22.1)
-    parser (3.1.2.0)
+    parser (3.1.2.1)
       ast (~> 2.4.1)
     pry (0.13.1)
       coderay (~> 1.1)
@@ -46,7 +38,6 @@ GEM
     pry-byebug (3.9.0)
       byebug (~> 11.0)
       pry (~> 0.13.0)
-    racc (1.6.0)
     rainbow (3.1.1)
     rake (13.0.6)
     regexp_parser (2.5.0)
@@ -64,19 +55,20 @@ GEM
       diff-lcs (>= 1.2.0, < 2.0)
       rspec-support (~> 3.11.0)
     rspec-support (3.11.0)
-    rubocop (1.31.0)
+    rubocop (1.35.0)
+      json (~> 2.3)
       parallel (~> 1.10)
-      parser (>= 3.1.0.0)
+      parser (>= 3.1.2.1)
       rainbow (>= 2.2.2, < 4.0)
       regexp_parser (>= 1.8, < 3.0)
       rexml (>= 3.2.5, < 4.0)
-      rubocop-ast (>= 1.18.0, < 2.0)
+      rubocop-ast (>= 1.20.1, < 2.0)
       ruby-progressbar (~> 1.7)
       unicode-display_width (>= 1.4.0, < 3.0)
-    rubocop-ast (1.18.0)
+    rubocop-ast (1.21.0)
       parser (>= 3.1.1.0)
-    rubocop-rspec (2.11.1)
-      rubocop (~> 1.19)
+    rubocop-rspec (2.12.1)
+      rubocop (~> 1.31)
     ruby-progressbar (1.11.0)
     simplecov (0.21.2)
       docile (~> 1.1)
@@ -84,7 +76,7 @@ GEM
       simplecov_json_formatter (~> 0.1)
     simplecov-html (0.12.3)
     simplecov_json_formatter (0.1.4)
-    tzinfo (2.0.4)
+    tzinfo (2.0.5)
       concurrent-ruby (~> 1.0)
     unicode-display_width (2.2.0)
 
@@ -94,7 +86,6 @@ PLATFORMS
 DEPENDENCIES
   assembly-objectfile!
   byebug
-  json
   pry-byebug
   rake
   rspec (~> 3.0)
@@ -103,4 +94,4 @@ DEPENDENCIES
   simplecov
 
 BUNDLED WITH
-   2.3.4
+   2.3.17

data/README.md

@@ -8,15 +8,15 @@
 ## Overview
 This gem contains classes used by the Stanford University Digital Library to
 perform file operations necessary for accessioning of content.  It is also
-used by related gems to perform content type specific operations (such as jp2
-generation).
+used by related gems that perform content type specific operations (e.g.
+assembly-image for jp2 generation).
 
 ## Usage
 
 The gem currently has methods for:
 * filesize
-* exif
-* generate content metadata
+* mimetype
+* exif - consumers use ExifTool to get file information
 
 ## Running tests
 
@@ -34,8 +34,8 @@ rake release
 
 1.  Exiftool
 
-    RHEL: (RPM to install comming soon) Download latest version from:
-    http://www.sno.phy.queensu.ca/~phil/exiftool
+    RHEL: (RPM to install coming soon) Download latest version from:
+    https://exiftool.org/
 
         tar -xf Image-ExifTool-#.##.tar.gz
         cd Image-ExifTool-#.##

data/assembly-objectfile.gemspec

@@ -1,7 +1,7 @@
 # frozen_string_literal: true
 
 $LOAD_PATH.push File.expand_path('lib', __dir__)
-require 'assembly-objectfile/version'
+require 'assembly/object_file/version'
 
 Gem::Specification.new do |s|
   s.name        = 'assembly-objectfile'
@@ -10,7 +10,8 @@ Gem::Specification.new do |s|
   s.authors     = ['Peter Mangiafico', 'Renzo Sanchez-Silva', 'Monty Hindman', 'Tony Calavano']
   s.email       = ['pmangiafico@stanford.edu']
   s.homepage    = 'https://github.com/sul-dlss/assembly-objectfile'
-  s.summary     = 'Ruby immplementation of file services needed to prepare objects to be accessioned in SULAIR digital library'
+  s.summary     = 'Ruby implementation of file services needed to prepare objects to be accessioned ' \
+                  'into the Stanford Digital Repository'
   s.description = 'Get exif data, file sizes and more.'
   s.license     = 'ALv2'
   s.metadata['rubygems_mfa_required'] = 'true'
@@ -23,12 +24,9 @@ Gem::Specification.new do |s|
   s.required_ruby_version = '>= 3.0'
 
   s.add_dependency 'activesupport', '>= 5.2.0'
-  s.add_dependency 'deprecation'
   s.add_dependency 'mime-types', '> 3'
   s.add_dependency 'mini_exiftool'
-  s.add_dependency 'nokogiri'
 
-  s.add_development_dependency 'json'
   s.add_development_dependency 'pry-byebug'
   s.add_development_dependency 'rake'
   s.add_development_dependency 'rspec', '~> 3.0'

data/config/boot.rb

@@ -2,7 +2,6 @@
 
 require 'rubygems'
 
-environment  = ENV['ENVIRONMENT'] ||= 'development'
 project_root = File.expand_path("#{File.dirname(__FILE__)}/..")
 
 # Load config for current environment.

data/lib/{assembly-objectfile → assembly/object_file}/version.rb

@@ -4,6 +4,6 @@
 module Assembly
   class ObjectFile
     # Gem version
-    VERSION = '2.0.0'
+    VERSION = '2.1.2'
   end
 end

data/lib/assembly/object_file.rb

@@ -0,0 +1,201 @@
+# frozen_string_literal: true
+
+require 'mini_exiftool'
+require 'mime/types'
+require 'active_support/core_ext/object/blank'
+
+module Assembly
+  # This class contains generic methods to operate on any file.
+  class ObjectFile
+    # @param [Array] strings Array of filenames with paths
+    # @return [String] longest common initial path of filenames passed in
+    #
+    # Example:
+    #   puts Assembly::ObjectFile.common_prefix(['/Users/peter/00/test.tif','/Users/peter/05/test.jp2'])
+    #   # => '/Users/peter/0'
+    def self.common_path(strings)
+      return nil if strings.empty?
+
+      n = 0
+      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 # if not, split string along directories, and reject last one
+      else
+        "#{common_prefix.split('/')[0..-2].join('/')}/" # if it was, then return the common prefix directly
+      end
+    end
+
+    attr_accessor :file_attributes, :label, :path, :provider_md5, :provider_sha1, :relative_path, :mime_type_order
+
+    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
+    # @option params [Hash<Symbol => ['yes', 'no']>] :file_attributes e.g.:
+    #                                                {:preserve=>'yes',:shelve=>'no',:publish=>'no'},
+    #                                                defaults pulled from mimetype
+    # @option params [String] :label a resource label (files bundled together will just get the first
+    #                                file's label attribute if set)
+    # @option params [String] :provider_md5 pre-computed MD5 checksum
+    # @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 :override (from manual overide mapping if exists),
+    #                                                      :exif (from exif if exists)
+    #                                                      :extension (from file extension)
+    #                                                      :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
+    def initialize(path, params = {})
+      @path = path
+      @label = params[:label]
+      @file_attributes = params[:file_attributes]
+      @relative_path = params[:relative_path]
+      @provider_md5 = params[:provider_md5]
+      @provider_sha1 = params[:provider_sha1]
+      @mime_type_order = params[:mime_type_order] || default_mime_type_order
+    end
+
+    def filename
+      File.basename(path)
+    end
+
+    def dirname
+      File.dirname(path)
+    end
+
+    def ext
+      File.extname(path)
+    end
+
+    def filename_without_ext
+      File.basename(path, ext)
+    end
+
+    # @return [MiniExiftool] exif mini_exiftool gem object wrapper for exiftool
+    def exif
+      @exif ||= begin
+        check_for_file
+        MiniExiftool.new(path, replace_invalid_chars: '?')
+      rescue MiniExiftool::Error
+        # MiniExiftool may raise an error on files it doesn't know how to handle (disk images for example)
+        # but we don't want this to prevent an ObjectFile from being created, so just swallow it.
+        nil
+      end
+    end
+
+    # @return [String] computed md5 checksum
+    def md5
+      check_for_file unless @md5
+      @md5 ||= Digest::MD5.file(path).hexdigest
+    end
+
+    # @return [String] computed sha1 checksum
+    def sha1
+      check_for_file unless @sha1
+      @sha1 ||= Digest::SHA1.file(path).hexdigest
+    end
+
+    # Returns mimetype information for the current file based on the ordering set in default_mime_type_order
+    #   We stop computing mimetypes as soon as we have a method that returns a value
+    # @return [String] mimetype of the file
+    def mimetype
+      @mimetype ||= begin
+        check_for_file
+        mimetype = ''
+        mime_type_order.each do |mime_type_method|
+          mimetype = send("#{mime_type_method}_mimetype") if VALID_MIMETYPE_METHODS.include?(mime_type_method)
+          break if mimetype.present?
+        end
+        mimetype
+      end
+    end
+
+    # @return [Symbol] the type of object, could be :application (for PDF or Word, etc),
+    #                  :audio, :image, :message, :model, :multipart, :text or :video
+    def object_type
+      lookup = MIME::Types[mimetype][0]
+      lookup.nil? ? :other : lookup.media_type.to_sym
+    end
+
+    # @return [Boolean] true if the mime-types gem recognizes it as an image (from file extension lookup)
+    def image?
+      object_type == :image
+    end
+
+    # @return [Boolean] true if the mime-types gem recognizes it as an image (from file extension lookup)
+    #   AND it is a jp2 or jp2able?
+    def valid_image?
+      return false unless image?
+
+      mimetype == 'image/jp2' || jp2able?
+    end
+
+    # @return [Boolean] true if we can create a jp2 from the file
+    def jp2able?
+      return false unless exif
+
+      Assembly::VALID_IMAGE_MIMETYPES.include?(mimetype)
+    end
+
+    # @return [Integer] file size in bytes
+    def filesize
+      check_for_file
+      @filesize ||= File.size(path)
+    end
+
+    # @return [Boolean] file exists and is not a directory
+    def file_exists?
+      @file_exists ||= (File.exist?(path) && !File.directory?(path))
+    end
+
+    private
+
+    # check for file existence before operating on it
+    def check_for_file
+      raise "input file #{path} does not exist or is a directory" unless file_exists?
+    end
+
+    # defines default preferred ordering of how mimetypes are determined
+    def default_mime_type_order
+      %i[override exif file extension]
+    end
+
+    # @return [String] mime type for supplied file using the mime-types gem (based on a file extension lookup)
+    def extension_mimetype
+      @extension_mimetype ||= begin
+        mtype = MIME::Types.type_for(path).first
+        mtype ? mtype.content_type : ''
+      end
+    end
+
+    # @return [String] mime type for supplied file based on unix file system command
+    def file_mimetype
+      @file_mimetype ||= begin
+        check_for_file
+        `file --mime-type "#{path}"`.delete("\n").split(':')[1].strip # get the mimetype from the unix file command
+      end
+    end
+
+    # @return [String] mimetype information for the current file based on exif data,
+    #   unless mimetype is configured as one we'd rather get from the file system command
+    #   (e.g. exif struggles or we get better info from file system command)
+    def exif_mimetype
+      @exif_mimetype ||= begin
+        check_for_file
+        # if it's not a "trusted" mimetype and there is exif data; get the mimetype from the exif
+        prefer_exif = !Assembly::TRUSTED_MIMETYPES.include?(file_mimetype)
+        exif.mimetype if prefer_exif && exif&.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
+    def override_mimetype
+      @override_mimetype ||= Assembly::OVERRIDE_MIMETYPES.fetch(ext.to_sym, '')
+    end
+  end
+end

data/lib/assembly-objectfile.rb

@@ -1,25 +1,25 @@
 # frozen_string_literal: true
 
 module Assembly
-  # the path to the gem, used to access profiles stored with the gem
-  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
+  # 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
 
-  # the list of mimetypes that will be "trusted" by the unix file command; if a mimetype other than one of these is returned
-  #  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
+  # The list of mimetypes that will be "trusted" by the unix file command; if a mimetype other than
+  # one of these is returned 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',
+                       'application/octet-stream'].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`
+  # 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 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/object_file'
-require 'assembly-objectfile/version'
+require 'assembly/object_file'

data/spec/{object_file_spec.rb → assembly/object_file_spec.rb}

@@ -6,13 +6,15 @@ describe Assembly::ObjectFile do
   describe '.common_path' do
     context 'when common path is 2 nodes out of 4' do
       it 'returns the common directory' do
-        expect(described_class.common_path(['/Users/peter/00/test.tif', '/Users/peter/05/test.jp2'])).to eq('/Users/peter/')
+        expect(described_class.common_path(['/Users/peter/00/test.tif',
+                                            '/Users/peter/05/test.jp2'])).to eq('/Users/peter/')
       end
     end
 
     context 'when common path is 3 nodes out of 4' do
       it 'returns the common directory' do
-        expect(described_class.common_path(['/Users/peter/00/test.tif', '/Users/peter/00/test.jp2'])).to eq('/Users/peter/00/')
+        expect(described_class.common_path(['/Users/peter/00/test.tif',
+                                            '/Users/peter/00/test.jp2'])).to eq('/Users/peter/00/')
       end
     end
 
@@ -25,8 +27,9 @@ describe Assembly::ObjectFile do
 
   describe '#new' do
     context 'without params' do
+      let(:object_file) { described_class.new('/some/file.txt') }
+
       it 'does not set attributes' do
-        object_file = described_class.new('/some/file.txt')
         expect(object_file.path).to eq('/some/file.txt')
         expect(object_file.label).to be_nil
         expect(object_file.file_attributes).to be_nil
@@ -37,8 +40,15 @@ describe Assembly::ObjectFile do
     end
 
     context 'with params' do
+      let(:object_file) do
+        described_class.new('/some/file.txt', label: 'some label',
+                                              file_attributes: { 'shelve' => 'yes',
+                                                                 'publish' => 'yes',
+                                                                 'preserve' => 'no' },
+                                              relative_path: '/tmp')
+      end
+
       it 'sets attributes to passed params' do
-        object_file = described_class.new('/some/file.txt', label: 'some label', file_attributes: { 'shelve' => 'yes', 'publish' => 'yes', 'preserve' => 'no' }, relative_path: '/tmp')
         expect(object_file.path).to eq('/some/file.txt')
         expect(object_file.label).to eq('some label')
         expect(object_file.file_attributes).to eq('shelve' => 'yes', 'publish' => 'yes', 'preserve' => 'no')
@@ -47,9 +57,12 @@ describe Assembly::ObjectFile do
         expect(object_file.relative_path).to eq('/tmp')
       end
 
-      it 'sets provider_md5 to passed param' do
-        object_file = described_class.new('/some/file.txt', provider_md5: 'XYZ')
-        expect(object_file.provider_md5).to eq('XYZ')
+      context 'with provider_md5' do
+        let(:object_file) { described_class.new('/some/file.txt', provider_md5: 'XYZ') }
+
+        it 'sets provider_md5 to passed param' do
+          expect(object_file.provider_md5).to eq('XYZ')
+        end
       end
     end
   end
@@ -100,7 +113,7 @@ describe Assembly::ObjectFile do
 
     context 'with ruby file' do
       it 'false' do
-        non_image_file = File.join(Assembly::PATH_TO_GEM, 'spec/object_file_spec.rb')
+        non_image_file = File.join(PATH_TO_GEM, 'spec/assembly/object_file_spec.rb')
         object_file = described_class.new(non_image_file)
         expect(object_file.image?).to be(false)
       end
@@ -108,7 +121,7 @@ describe Assembly::ObjectFile do
 
     context 'with xml' do
       it 'false' do
-        non_image_file = File.join(Assembly::PATH_TO_GEM, 'spec/test_data/input/file_with_no_exif.xml')
+        non_image_file = File.join(PATH_TO_GEM, 'spec/test_data/input/file_with_no_exif.xml')
         object_file = described_class.new(non_image_file)
         expect(object_file.image?).to be(false)
       end
@@ -132,7 +145,7 @@ describe Assembly::ObjectFile do
 
     context 'with ruby file' do
       it ':text' do
-        non_image_file = File.join(Assembly::PATH_TO_GEM, 'spec/object_file_spec.rb')
+        non_image_file = File.join(PATH_TO_GEM, 'spec/assembly/object_file_spec.rb')
         object_file = described_class.new(non_image_file)
         expect(object_file.object_type).to eq(:text)
       end
@@ -140,7 +153,7 @@ describe Assembly::ObjectFile do
 
     context 'with xml' do
       it ':application' do
-        non_image_file = File.join(Assembly::PATH_TO_GEM, 'spec/test_data/input/file_with_no_exif.xml')
+        non_image_file = File.join(PATH_TO_GEM, 'spec/test_data/input/file_with_no_exif.xml')
         object_file = described_class.new(non_image_file)
         expect(object_file.object_type).to eq(:application)
       end
@@ -178,7 +191,7 @@ describe Assembly::ObjectFile do
 
     context 'with ruby file' do
       it 'false' do
-        non_image_file = File.join(Assembly::PATH_TO_GEM, 'spec/object_file_spec.rb')
+        non_image_file = File.join(PATH_TO_GEM, 'spec/assembly/object_file_spec.rb')
         object_file = described_class.new(non_image_file)
         expect(object_file.valid_image?).to be(false)
       end
@@ -186,7 +199,7 @@ describe Assembly::ObjectFile do
 
     context 'with xml' do
       it 'false' do
-        non_image_file = File.join(Assembly::PATH_TO_GEM, 'spec/test_data/input/file_with_no_exif.xml')
+        non_image_file = File.join(PATH_TO_GEM, 'spec/test_data/input/file_with_no_exif.xml')
         object_file = described_class.new(non_image_file)
         expect(object_file.valid_image?).to be(false)
       end
@@ -320,29 +333,6 @@ describe Assembly::ObjectFile do
     end
   end
 
-  describe '#has_color_profile?' do
-    context 'with jp2 file' do
-      it 'true' do
-        object_file = described_class.new(TEST_JP2_INPUT_FILE)
-        expect(object_file.has_color_profile?).to be(true)
-      end
-    end
-
-    context 'with tiff file' do
-      it 'true' do
-        object_file = described_class.new(TEST_RES1_TIF1)
-        expect(object_file.has_color_profile?).to be(true)
-      end
-    end
-
-    context 'with tiff no color file' do
-      it 'false' do
-        object_file = described_class.new(TEST_TIFF_NO_COLOR_FILE)
-        expect(object_file.has_color_profile?).to be(false)
-      end
-    end
-  end
-
   describe '#md5' do
     it 'computes md5 for an image file' do
       object_file = described_class.new(TEST_TIF_INPUT_FILE)
@@ -369,7 +359,7 @@ describe Assembly::ObjectFile do
 
   describe '#file_exists?' do
     it 'false when a valid directory is specified instead of a file' do
-      path = Assembly::PATH_TO_GEM
+      path = PATH_TO_GEM
       object_file = described_class.new(path)
       expect(File.exist?(path)).to be true
       expect(File.directory?(path)).to be true
@@ -377,7 +367,7 @@ describe Assembly::ObjectFile do
     end
 
     it 'false when a non-existent file is specified' do
-      path = File.join(Assembly::PATH_TO_GEM, 'file_not_there.txt')
+      path = File.join(PATH_TO_GEM, 'file_not_there.txt')
       object_file = described_class.new(path)
       expect(File.exist?(path)).to be false
       expect(File.directory?(path)).to be false
@@ -397,32 +387,17 @@ describe Assembly::ObjectFile do
     end
   end
 
-  describe '#encoding' do
-    context 'with .tif file' do
-      it 'binary' do
-        object_file = described_class.new(TEST_TIF_INPUT_FILE)
-        expect(object_file.send(:encoding)).to eq('binary')
-      end
-    end
+  describe '#exif' do
+    subject(:exif) { object_file.exif }
 
-    context 'with .txt file' do
-      it 'binary' do
-        object_file = described_class.new(TEST_RES1_TEXT)
-        expect(object_file.send(:encoding)).to eq('us-ascii')
-      end
-    end
-  end
+    let(:object_file) { described_class.new(TEST_TIF_INPUT_FILE) }
 
-  describe '#exif' do
-    it 'returns MiniExiftool object' do
-      object_file = described_class.new(TEST_TIF_INPUT_FILE)
-      expect(object_file.exif).not_to be_nil
-      expect(object_file.exif.class).to eq MiniExiftool
-    end
+    it { is_expected.to be_kind_of MiniExiftool }
+
+    context 'when exiftool raises an error initializing the file' do
+      let(:object_file) { described_class.new('spec/test_data/empty.txt') }
 
-    it 'raises MiniExiftool::Error if exiftool raises one' do
-      object_file = described_class.new('spec/test_data/empty.txt')
-      expect { object_file.exif }.to raise_error(MiniExiftool::Error)
+      it { is_expected.to be_nil }
     end
   end
 

data/spec/spec_helper.rb

@@ -10,13 +10,10 @@ RSpec.configure do |config|
   config.order = 'random'
 end
 
-TEST_DATA_DIR = File.join(Assembly::PATH_TO_GEM, 'spec', 'test_data')
-TEST_INPUT_DIR       = File.join(TEST_DATA_DIR, 'input')
-TEST_OUTPUT_DIR      = File.join(TEST_DATA_DIR, 'output')
+PATH_TO_GEM = File.expand_path("#{File.dirname(__FILE__)}/..")
+TEST_INPUT_DIR       = File.join(PATH_TO_GEM, 'spec', 'test_data', 'input')
 TEST_TIF_INPUT_FILE  = File.join(TEST_INPUT_DIR, 'test.tif')
-TEST_JPEG_INPUT_FILE = File.join(TEST_INPUT_DIR, 'test.jpg')
 TEST_JP2_INPUT_FILE = File.join(TEST_INPUT_DIR, 'test.jp2')
-TEST_JP2_OUTPUT_FILE = File.join(TEST_OUTPUT_DIR, 'test.jp2')
 
 TEST_TIFF_NO_COLOR_FILE = File.join(TEST_INPUT_DIR, 'test_no_color_profile.tif')
 
@@ -30,5 +27,3 @@ TEST_JSON_FILE = File.join(TEST_INPUT_DIR, 'test.json')
 
 TEST_OBJ_FILE = File.join(TEST_INPUT_DIR, 'someobject.obj')
 TEST_PLY_FILE = File.join(TEST_INPUT_DIR, 'someobject.ply')
-
-TEST_DRUID = 'nx288wh8889'

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: assembly-objectfile
 version: !ruby/object:Gem::Version
-  version: 2.0.0
+  version: 2.1.2
 platform: ruby
 authors:
 - Peter Mangiafico
@@ -11,7 +11,7 @@ authors:
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2022-07-08 00:00:00.000000000 Z
+date: 2022-08-18 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activesupport
@@ -27,20 +27,6 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: 5.2.0
-- !ruby/object:Gem::Dependency
-  name: deprecation
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
 - !ruby/object:Gem::Dependency
   name: mime-types
   requirement: !ruby/object:Gem::Requirement
@@ -69,34 +55,6 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-- !ruby/object:Gem::Dependency
-  name: nokogiri
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-- !ruby/object:Gem::Dependency
-  name: json
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
 - !ruby/object:Gem::Dependency
   name: pry-byebug
   requirement: !ruby/object:Gem::Requirement
@@ -205,12 +163,9 @@ files:
 - bin/run_all_tests
 - config/boot.rb
 - lib/assembly-objectfile.rb
-- lib/assembly-objectfile/object_file.rb
-- lib/assembly-objectfile/version.rb
-- profiles/AdobeRGB1998.icc
-- profiles/DotGain20.icc
-- profiles/sRGBIEC6196621.icc
-- spec/object_file_spec.rb
+- lib/assembly/object_file.rb
+- lib/assembly/object_file/version.rb
+- spec/assembly/object_file_spec.rb
 - spec/spec_helper.rb
 - spec/test_data/empty.txt
 - spec/test_data/input/.empty
@@ -247,6 +202,6 @@ requirements: []
 rubygems_version: 3.3.7
 signing_key:
 specification_version: 4
-summary: Ruby immplementation of file services needed to prepare objects to be accessioned
-  in SULAIR digital library
+summary: Ruby implementation of file services needed to prepare objects to be accessioned
+  into the Stanford Digital Repository
 test_files: []

data/lib/assembly-objectfile/object_file.rb

@@ -1,279 +0,0 @@
-# frozen_string_literal: true
-
-require 'mini_exiftool'
-require 'mime/types'
-require 'active_support/core_ext/object/blank'
-
-module Assembly
-  # This class contains generic methods to operate on any file.
-  class ObjectFile
-    # Class level method that given an array of strings, return the longest common initial path.  Useful for removing a common path from a set of filenames when producing content metadata
-    #
-    # @param [Array] strings Array of filenames with paths to operate on
-    # @return [String] longest common initial part of path of filenames passed in
-    #
-    # Example:
-    # puts Assembly::ObjectFile.common_prefix(['/Users/peter/00/test.tif','/Users/peter/05/test.jp2'])  # '/Users/peter/0'
-    def self.common_path(strings)
-      return nil if strings.empty?
-
-      n = 0
-      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 # if not, split string along directories, and reject last one
-      else
-        "#{common_prefix.split('/')[0..-2].join('/')}/" # if it was, then return the common prefix directly
-      end
-    end
-
-    attr_accessor :file_attributes, :label, :path, :provider_md5, :provider_sha1, :relative_path, :mime_type_order
-
-    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
-    # @option params [Hash<Symbol => ['yes', 'no']>] :file_attributes e.g. {:preserve=>'yes',:shelve=>'no',:publish=>'no'}, defaults pulled from mimetype
-    # @option params [String] :label a resource label (files bundlded together will just get the first file's label attribute if set)
-    # @option params [String] :provider_md5 pre-computed MD5 checksum
-    # @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 :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')
-    def initialize(path, params = {})
-      @path = path
-      @label = params[:label]
-      @file_attributes = params[:file_attributes]
-      @relative_path = params[:relative_path]
-      @provider_md5 = params[:provider_md5]
-      @provider_sha1 = params[:provider_sha1]
-      @mime_type_order = params[:mime_type_order] || default_mime_type_order
-    end
-
-    # @return [String] base filename
-    # @example
-    #   source_file = Assembly::ObjectFile.new('/input/path_to_file.tif')
-    #   puts source_file.filename # "path_to_file.tif"
-    def filename
-      File.basename(path)
-    end
-
-    # @return [String] base directory
-    # @example
-    #   source_file = Assembly::ObjectFile.new('/input/path_to_file.tif')
-    #   puts source_file.dirname # "/input"
-    def dirname
-      File.dirname(path)
-    end
-
-    # @return [String] filename extension
-    # @example
-    #   source_file = Assembly::ObjectFile.new('/input/path_to_file.tif')
-    #   puts source_file.ext # ".tif"
-    def ext
-      File.extname(path)
-    end
-
-    # @return [String] base filename without extension
-    # @example
-    #   source_file = Assembly::ObjectFile.new('/input/path_to_file.tif')
-    #   puts source_file.filename # "path_to_file"
-    def filename_without_ext
-      File.basename(path, ext)
-    end
-
-    # @return [MiniExiftool] exif information stored as a hash and an object
-    # @example
-    #   source_file = Assembly::ObjectFile.new('/input/path_to_file.tif')
-    #   puts source_file.exif # hash with exif information
-    def exif
-      @exif ||= begin
-        check_for_file
-        MiniExiftool.new(path, replace_invalid_chars: '?')
-      end
-    end
-
-    # Computes md5 checksum or returns cached value
-    # @return [String] md5 checksum
-    # @example
-    #   source_file = Assembly::ObjectFile.new('/input/path_to_file.tif')
-    #   puts source_file.md5 # 'XXX123XXX1243XX1243'
-    def md5
-      check_for_file unless @md5
-      @md5 ||= Digest::MD5.file(path).hexdigest
-    end
-
-    # Computes sha1 checksum or return cached value
-    # @return [String] sha1 checksum
-    # @example
-    #   source_file = Assembly::ObjectFile.new('/input/path_to_file.tif')
-    #   puts source_file.sha1 # 'XXX123XXX1243XX1243'
-    def sha1
-      check_for_file unless @sha1
-      @sha1 ||= Digest::SHA1.file(path).hexdigest
-    end
-
-    # Returns mimetype information for the current file based on the ordering set in default_mime_type_order
-    #   We stop computing mimetypes as soon as we have a method that returns a value
-    # @return [String] mime type
-    # @example
-    #   source_file = Assembly::ObjectFile.new('/input/path_to_file.txt')
-    #   puts source_file.mimetype # 'text/plain'
-    def mimetype
-      @mimetype ||= begin
-        check_for_file
-        mimetype = ''
-        mime_type_order.each do |mime_type_method|
-          mimetype = send("#{mime_type_method}_mimetype") if VALID_MIMETYPE_METHODS.include?(mime_type_method)
-          break if mimetype.present?
-        end
-        mimetype
-      end
-    end
-
-    # @return [Symbol] the type of object, could be :application (for PDF or Word, etc), :audio, :image, :message, :model, :multipart, :text or :video
-    # @example
-    #   source_file = Assembly::ObjectFile.new('/input/path_to_file.tif')
-    #   puts source_file.object_type # :image
-    def object_type
-      lookup = MIME::Types[mimetype][0]
-      lookup.nil? ? :other : lookup.media_type.to_sym
-    end
-
-    # @return [Boolean] if object is an image
-    # @example
-    #   source_file = Assembly::ObjectFile.new('/input/path_to_file.tif')
-    #   puts source_file.image? # true
-    def image?
-      object_type == :image
-    end
-
-    # Examines the input image for validity.  Used to determine if image is a valid and useful image.
-    # If image is not a jp2, also checks if it is jp2able?
-    # @return [Boolean] true if image is valid, false if not.
-    # @example
-    #   source_img = Assembly::ObjectFile.new('/input/path_to_file.tif')
-    #   puts source_img.valid_image? # true
-    def valid_image?
-      return false unless image?
-
-      mimetype == 'image/jp2' || jp2able?
-    end
-
-    # @return [Boolean] true if image has a color profile, false if not.
-    # @example
-    #   source_img = Assembly::ObjectFile.new('/input/path_to_file.tif')
-    #   puts source_img.has_color_profile? # true
-    def has_color_profile?
-      return false unless exif
-
-      exif['profiledescription'] || exif['colorspace'] ? true : false
-    end
-
-    # Examines the input image for validity to create a jp2.  Same as valid_image? but also confirms the existence of a profile description and further restricts mimetypes.
-    # It is used by the assembly robots to decide if a jp2 will be created and is also called before you create a jp2 using assembly-image.
-    # @return [Boolean] true if image should have a jp2 created, false if not.
-    # @example
-    #   source_img = Assembly::ObjectFile.new('/input/path_to_file.tif')
-    #   puts source_img.jp2able? # true
-    def jp2able?
-      return false unless exif
-
-      Assembly::VALID_IMAGE_MIMETYPES.include?(mimetype)
-    end
-
-    # Returns file size information for the current file in bytes.
-    # @return [Integer] file size in bytes
-    # @example
-    #   source_file = Assembly::ObjectFile.new('/input/path_to_file.tif')
-    #   puts source_file.filesize # 1345
-    def filesize
-      check_for_file
-      @filesize ||= File.size(path)
-    end
-
-    # Determines if the file exists (and is not a directory)
-    # @return [Boolean] file exists
-    # @example
-    #   source_file = Assembly::ObjectFile.new('/input/path_to_file.tif')
-    #   puts source_file.file_exists? # true
-    def file_exists?
-      @file_exists ||= (File.exist?(path) && !File.directory?(path))
-    end
-
-    private
-
-    # private method to check for file existence before operating on it
-    def check_for_file
-      raise "input file #{path} does not exist or is a directory" unless file_exists?
-    end
-
-    # prive method defining default preferred ordering of how mimetypes are determined
-    def default_mime_type_order
-      %i[override exif file extension]
-    end
-
-    # Returns mimetype information using the mime-types gem (based on a file extension lookup)
-    # @return [String] mime type for supplied file
-    # @example
-    #   source_file = Assembly::ObjectFile.new('/input/path_to_file.txt')
-    #   puts source_file.extension_mimetype # 'text/plain'
-    def extension_mimetype
-      @extension_mimetype ||= begin
-        mtype = MIME::Types.type_for(path).first
-        mtype ? mtype.content_type : ''
-      end
-    end
-
-    # Returns mimetype information for the current file based on unix file system command.
-    # @return [String] mime type for supplied file
-    # @example
-    #   source_file = Assembly::ObjectFile.new('/input/path_to_file.txt')
-    #   puts source_file.file_mimetype # 'text/plain'
-    def file_mimetype
-      @file_mimetype ||= begin
-        check_for_file
-        `file --mime-type "#{path}"`.delete("\n").split(':')[1].strip # first try and get the mimetype from the unix file command
-      end
-    end
-
-    # Returns mimetype information for the current file based on exif data (if available and not a trusted source that we'd rather get from the file system command)
-    # @return [String] mime type for supplied file
-    # @example
-    #   source_file = Assembly::ObjectFile.new('/input/path_to_file.txt')
-    #   puts source_file.exif_mimetype # 'text/plain'
-    def exif_mimetype
-      @exif_mimetype ||= begin
-        check_for_file
-        prefer_exif = !Assembly::TRUSTED_MIMETYPES.include?(file_mimetype) # if it's not a "trusted" mimetype and there is exif data; get the mimetype from the exif
-        exif.mimetype if exif&.mimetype && prefer_exif
-      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
-
-    # @note Uses shell call to "file", only expected to work on unix based systems
-    # @return [String] encoding for supplied file
-    # @example
-    #   source_file = Assembly::ObjectFile.new('/input/path_to_file.txt')
-    #   puts source_file.encoding # 'us-ascii'
-    def encoding
-      @encoding ||= begin
-        check_for_file
-        `file --mime-encoding "#{path}"`.delete("\n").split(':')[1].strip
-      end
-    end
-  end
-end