assembly-objectfile 1.13.0 → 2.1.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 8c85bb6c05fe0d46e9b2f37e90710043efce16322c5d58e0b0a9578fd21ece77
-  data.tar.gz: c7e3ac5e3f0a0aa2124f8ce3d6587de2d02923c733ee94b1c299ae171101f5a5
+  metadata.gz: 76dac08191a4c118cf16e4736b9538c9d2a60811cf9547e0ad395ab468b1b51a
+  data.tar.gz: b9fec1e99d03941f658cd6716e1c00db37ce2f2042816e4ba8f77246b102d1f4
 SHA512:
-  metadata.gz: fbad307e9a103af61b4a6b05b35bb6b98953774a2c9bd32cb1404f1a9ff6e3404fe78cfc48f9061bfffaa23c3610f2a6f19df5e08975a20c6ee387073cc1010d
-  data.tar.gz: 717e174ccf88a94880f4a832b2d281b351774299fb1273a96b4a1bb942e360cd20b0ba3ac68b7ad4f113e3bd3c78652c7670efcf7bcf8f9bcf068972ba5cd42d
+  metadata.gz: '082fc021ca4f4dde1f3eaaac937e66862d8ea36f5198bdece9866a72e5be068021665e10bd40b8ea2835d848c062886982ed41033935120525c8d4e57efadafd'
+  data.tar.gz: cf2e4facd4248532c5f92c741f80b5e8d27e04b8cc23e3b7959b59118cceaf8122d03aa92af8faf99c8000bb4298b74d9ab86001744c6f852cd148ceda21d675

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/.gitignore

@@ -10,4 +10,3 @@ log/*
 pkg/*
 tags
 tmp
-Gemfile.lock

data/.rubocop.yml

@@ -9,12 +9,32 @@ 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'
 
-Gemspec/DateAssignment: # (new in 1.10)
+RSpec/ExampleLength:
+  Max: 10
+
+RSpec/MultipleExpectations:
+  Max: 10
+
+RSpec/NestedGroups:
+  Max: 4
+
+Gemspec/DeprecatedAttributeAssignment: # (new in 1.10)
   Enabled: true
 
 Layout/SpaceAroundMethodCallOperator:
@@ -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

@@ -1,129 +1,12 @@
 # This configuration was generated by
 # `rubocop --auto-gen-config`
-# on 2022-02-28 21:11:02 UTC using RuboCop version 1.25.1.
+# 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: 3
-# Configuration parameters: IgnoredMethods, CountRepeatedAttributes.
-Metrics/AbcSize:
-  Max: 55
-
-# Offense count: 1
-# Configuration parameters: CountComments, CountAsOne, ExcludedMethods, IgnoredMethods.
-# IgnoredMethods: refine
-Metrics/BlockLength:
-  Max: 27
-
-# Offense count: 2
-# Configuration parameters: IgnoredMethods.
-Metrics/CyclomaticComplexity:
-  Max: 14
-
-# Offense count: 4
-# Configuration parameters: CountComments, CountAsOne, ExcludedMethods, IgnoredMethods.
-Metrics/MethodLength:
-  Max: 31
-
 # Offense count: 1
 # Configuration parameters: CountComments, CountAsOne.
-Metrics/ModuleLength:
-  Max: 120
-
-# Offense count: 1
-# Configuration parameters: CountKeywordArgs, MaxOptionalParameters.
-Metrics/ParameterLists:
-  Max: 12
-
-# Offense count: 2
-# Configuration parameters: IgnoredMethods.
-Metrics/PerceivedComplexity:
-  Max: 15
-
-# 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_fileable.rb'
-
-# Offense count: 1
-# Configuration parameters: Prefixes.
-# Prefixes: when, with, without
-RSpec/ContextWording:
-  Exclude:
-    - 'spec/content_metadata_spec.rb'
-
-# Offense count: 32
-# Configuration parameters: CountAsOne.
-RSpec/ExampleLength:
-  Max: 34
-
-# Offense count: 2
-# 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: 74
-# Configuration parameters: AssignmentOnly.
-RSpec/InstanceVariable:
-  Exclude:
-    - 'spec/object_file_spec.rb'
-
-# Offense count: 41
-RSpec/MultipleExpectations:
-  Max: 29
-
-# Offense count: 20
-RSpec/NestedGroups:
-  Max: 4
-
-# Offense count: 2
-RSpec/RepeatedDescription:
-  Exclude:
-    - 'spec/object_file_spec.rb'
-
-# Offense count: 2
-RSpec/RepeatedExample:
-  Exclude:
-    - 'spec/object_file_spec.rb'
-
-# Offense count: 5
-RSpec/RepeatedExampleGroupDescription:
-  Exclude:
-    - 'spec/content_metadata_spec.rb'
-
-# Offense count: 2
-# Cop supports --auto-correct.
-Style/CommentedKeyword:
-  Exclude:
-    - 'lib/assembly-objectfile/content_metadata.rb'
-
-# Offense count: 123
-# Cop supports --auto-correct.
-# Configuration parameters: AllowHeredoc, AllowURI, URISchemes, IgnoreCopDirectives, IgnoredPatterns.
-# URISchemes: http, https
-Layout/LineLength:
-  Max: 277
+Metrics/ClassLength:
+  Max: 122

data/Gemfile.lock

@@ -0,0 +1,97 @@
+PATH
+  remote: .
+  specs:
+    assembly-objectfile (2.1.1)
+      activesupport (>= 5.2.0)
+      mime-types (> 3)
+      mini_exiftool
+
+GEM
+  remote: http://rubygems.org/
+  specs:
+    activesupport (7.0.3.1)
+      concurrent-ruby (~> 1.0, >= 1.0.2)
+      i18n (>= 1.6, < 2)
+      minitest (>= 5.1)
+      tzinfo (~> 2.0)
+    ast (2.4.2)
+    byebug (11.1.3)
+    coderay (1.1.3)
+    concurrent-ruby (1.1.10)
+    diff-lcs (1.5.0)
+    docile (1.4.0)
+    i18n (1.12.0)
+      concurrent-ruby (~> 1.0)
+    json (2.6.2)
+    method_source (1.0.0)
+    mime-types (3.4.1)
+      mime-types-data (~> 3.2015)
+    mime-types-data (3.2022.0105)
+    mini_exiftool (2.10.2)
+    minitest (5.16.2)
+    parallel (1.22.1)
+    parser (3.1.2.0)
+      ast (~> 2.4.1)
+    pry (0.13.1)
+      coderay (~> 1.1)
+      method_source (~> 1.0)
+    pry-byebug (3.9.0)
+      byebug (~> 11.0)
+      pry (~> 0.13.0)
+    rainbow (3.1.1)
+    rake (13.0.6)
+    regexp_parser (2.5.0)
+    rexml (3.2.5)
+    rspec (3.11.0)
+      rspec-core (~> 3.11.0)
+      rspec-expectations (~> 3.11.0)
+      rspec-mocks (~> 3.11.0)
+    rspec-core (3.11.0)
+      rspec-support (~> 3.11.0)
+    rspec-expectations (3.11.0)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.11.0)
+    rspec-mocks (3.11.1)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.11.0)
+    rspec-support (3.11.0)
+    rubocop (1.31.2)
+      json (~> 2.3)
+      parallel (~> 1.10)
+      parser (>= 3.1.0.0)
+      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)
+      ruby-progressbar (~> 1.7)
+      unicode-display_width (>= 1.4.0, < 3.0)
+    rubocop-ast (1.19.1)
+      parser (>= 3.1.1.0)
+    rubocop-rspec (2.12.1)
+      rubocop (~> 1.31)
+    ruby-progressbar (1.11.0)
+    simplecov (0.21.2)
+      docile (~> 1.1)
+      simplecov-html (~> 0.11)
+      simplecov_json_formatter (~> 0.1)
+    simplecov-html (0.12.3)
+    simplecov_json_formatter (0.1.4)
+    tzinfo (2.0.5)
+      concurrent-ruby (~> 1.0)
+    unicode-display_width (2.2.0)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  assembly-objectfile!
+  byebug
+  pry-byebug
+  rake
+  rspec (~> 3.0)
+  rubocop (~> 1.25)
+  rubocop-rspec
+  simplecov
+
+BUNDLED WITH
+   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'
@@ -10,13 +10,13 @@ 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'
 
   s.files         = `git ls-files`.split("\n")
-  s.test_files    = `git ls-files -- spec/*`.split("\n")
   s.bindir        = 'exe'
   s.executables   = s.files.grep(%r{^exe/}) { |f| File.basename(f) }
   s.require_paths = ['lib']
@@ -24,14 +24,10 @@ 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 'dry-struct', '~> 1.0'
-  s.add_dependency 'dry-types', '~> 1.1'
   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'
   s.add_development_dependency 'rubocop', '~> 1.25'

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 = '1.13.0'
+    VERSION = '2.1.1'
   end
 end

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

@@ -2,25 +2,56 @@
 
 require 'mini_exiftool'
 require 'mime/types'
+require 'active_support/core_ext/object/blank'
 
 module Assembly
-  # Common behaviors we need for other classes in the gem
-  module ObjectFileable
+  # 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 [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 [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
+    #                                          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
     # @example
     #   Assembly::ObjectFile.new('/input/path_to_file.tif')
     def initialize(path, params = {})
@@ -33,24 +64,6 @@ module Assembly
       @mime_type_order = params[:mime_type_order] || default_mime_type_order
     end
 
-    # @return [String] DPG base filename, removing the extension and the '00','05', etc. placeholders
-    # @example
-    #   source_file = Assembly::ObjectFile.new('/input/cy565rm7188_00_001.tif')
-    #   puts source_file.dpg_basename # "cy565rm7188_001"
-    def dpg_basename
-      file_parts = File.basename(path, ext).split('_')
-      file_parts.size == 3 ? "#{file_parts[0]}_#{file_parts[2]}" : filename_without_ext
-    end
-
-    # @return [String] DPG subfolder for the given filename, i.e. '00','05', etc.
-    # @example
-    #   source_file = Assembly::ObjectFile.new('/input/cy565rm7188_00_001.tif')
-    #   puts source_file.dpg_folder # "00"
-    def dpg_folder
-      file_parts = File.basename(path, ext).split('_')
-      file_parts.size == 3 ? file_parts[1] : ''
-    end
-
     # @return [String] base filename
     # @example
     #   source_file = Assembly::ObjectFile.new('/input/path_to_file.tif')
@@ -91,6 +104,13 @@ module Assembly
       @exif ||= begin
         check_for_file
         MiniExiftool.new(path, replace_invalid_chars: '?')
+      rescue MiniExiftool::Error
+        # MiniExiftool will throw an exception when it tries to initialize for problematic files,
+        # but the exception it throws does not tell you the file that caused the problem.
+        # Instead, we will raise our own exception with more context in logging/reporting upstream.
+        # Note: if the file that causes the problem should NOT use exiftool to determine mimetype, add it to the skipped
+        # mimetypes in Assembly::TRUSTED_MIMETYPES to bypass initialization of MiniExiftool for mimetype generation
+        raise MiniExiftool::Error, "error initializing MiniExiftool for #{path}"
       end
     end
 
@@ -125,72 +145,15 @@ module Assembly
         check_for_file
         mimetype = ''
         mime_type_order.each do |mime_type_method|
-          mimetype = public_send("#{mime_type_method}_mimetype") if VALID_MIMETYPE_METHODS.include?(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
 
-    # 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
-    #   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
-
-    # @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
-
-    # @return [Symbol] the type of object, could be :application (for PDF or Word, etc), :audio, :image, :message, :model, :multipart, :text or :video
+    # @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
@@ -219,18 +182,10 @@ module Assembly
       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.
+    # 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')
@@ -262,14 +217,74 @@ module Assembly
 
     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
 
-    # 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?
+    # 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 # 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
+        # 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
+    # @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