assembly-objectfile 2.1.0 → 2.1.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 101baff5dcb53ae691341818de800b9836bc5c2db2483b3cdac08afa8fed479e
-  data.tar.gz: 0265e4b3d35ecf91a07b48129e4485e9844e6e1c940a08ae4f32246b209d2260
+  metadata.gz: 6743d03c8c75529ad425586ed16bece4858c1fd2394342918ab29c568199d4f7
+  data.tar.gz: 16a79c4115124aae1402f1651076a85eb58912b4309f5a7503536246cd55076f
 SHA512:
-  metadata.gz: fa0814a3a51d7d98f7eeb91611193e367accb4161ab18967b1afdb7caeb54476994f078ed58eff684dfba37dd2358a75fba98b181df74f165f82c65537723ebc
-  data.tar.gz: 91272e14724ff23ac668bf65339f29a272606712da691a7e13018d70c7e2a00ac8d242723ae6b4a9e05007543174e43e6ade6abb8f71a922ff9a4f4b230b10bb
+  metadata.gz: f08d614455304c1d7c935bc5e69ca85400493b8ba4bb045d048dc519c5a78f401d2d7e1a62292a8048cc0e9b83bdd0bc3f9fa540e8021356f9929ba3ec72ef37
+  data.tar.gz: 2340e0deff59c7e913272c6c18ce6f27513d2b1777e7d7da9120a4b3377f00c80ae2c59e31c3c29769ae763dc2cc4888b3bbdc76ce75f6962b81b2de713d4551

data/.rubocop_todo.yml

@@ -1,6 +1,6 @@
 # This configuration was generated by
 # `rubocop --auto-gen-config`
-# on 2022-07-19 19:06:39 UTC using RuboCop version 1.31.2.
+# 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
@@ -9,4 +9,4 @@
 # Offense count: 1
 # Configuration parameters: CountComments, CountAsOne.
 Metrics/ClassLength:
-  Max: 118
+  Max: 122

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    assembly-objectfile (2.1.0)
+    assembly-objectfile (2.1.3)
       activesupport (>= 5.2.0)
       mime-types (> 3)
       mini_exiftool
@@ -28,16 +28,16 @@ GEM
       mime-types-data (~> 3.2015)
     mime-types-data (3.2022.0105)
     mini_exiftool (2.10.2)
-    minitest (5.16.2)
+    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)
+    pry (0.14.1)
       coderay (~> 1.1)
       method_source (~> 1.0)
-    pry-byebug (3.9.0)
+    pry-byebug (3.10.1)
       byebug (~> 11.0)
-      pry (~> 0.13.0)
+      pry (>= 0.13, < 0.15)
     rainbow (3.1.1)
     rake (13.0.6)
     regexp_parser (2.5.0)
@@ -55,17 +55,17 @@ GEM
       diff-lcs (>= 1.2.0, < 2.0)
       rspec-support (~> 3.11.0)
     rspec-support (3.11.0)
-    rubocop (1.31.2)
+    rubocop (1.35.1)
       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 (1.19.1)
+    rubocop-ast (1.21.0)
       parser (>= 3.1.1.0)
     rubocop-rspec (2.12.1)
       rubocop (~> 1.31)
@@ -76,7 +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)
 

data/lib/assembly/object_file/version.rb

@@ -4,6 +4,6 @@
 module Assembly
   class ObjectFile
     # Gem version
-    VERSION = '2.1.0'
+    VERSION = '2.1.3'
   end
 end

data/lib/assembly/object_file.rb

@@ -7,11 +7,8 @@ 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
+    # @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'])
@@ -52,8 +49,6 @@ module Assembly
     #                                                      :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]
@@ -64,64 +59,41 @@ module Assembly
       @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
+    # @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
 
-    # 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'
+    # @return [String] computed md5 checksum
     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'
+    # @return [String] computed sha1 checksum
     def sha1
       check_for_file unless @sha1
       @sha1 ||= Digest::SHA1.file(path).hexdigest
@@ -129,10 +101,7 @@ module Assembly
 
     # 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'
+    # @return [String] mimetype of the file
     def mimetype
       @mimetype ||= begin
         check_for_file
@@ -147,84 +116,60 @@ module Assembly
 
     # @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
+    # @return [Boolean] true if the mime-types gem recognizes it as an image
     def image?
-      object_type == :image
+      return false if object_type != :image
+
+      # We exclude TARGA images here because we've seen where the file is a disk image and
+      # when we look for a mime type it is `image/x-tga', however it is not
+      # recognizable by exiftool.  See https://github.com/sul-dlss/assembly-objectfile/issues/98
+      mimetype != 'image/x-tga'
     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
+    # @return [Boolean] true if the mime-types gem recognizes it as an image
+    #   AND it is a jp2 or jp2able?
     def valid_image?
       return false unless image?
 
       mimetype == 'image/jp2' || jp2able?
     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
+    # @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
 
-    # 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
+    # @return [Boolean] file exists and is not a directory
     def file_exists?
       @file_exists ||= (File.exist?(path) && !File.directory?(path))
     end
 
     private
 
-    # private method to check for file existence before operating on it
+    # 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
+    # defines 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'
+    # @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
@@ -232,11 +177,7 @@ module Assembly
       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'
+    # @return [String] mime type for supplied file based on unix file system command
     def file_mimetype
       @file_mimetype ||= begin
         check_for_file
@@ -244,40 +185,22 @@ module Assembly
       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'
+    # @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 exif&.mimetype && prefer_exif
+        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

data/lib/assembly-objectfile.rb

@@ -1,9 +1,6 @@
 # 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
   VALID_IMAGE_MIMETYPES = ['image/jpeg', 'image/tiff', 'image/tif', 'image/png'].freeze
@@ -12,7 +9,8 @@ module Assembly
   # 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
+  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

data/spec/assembly/object_file_spec.rb

@@ -97,34 +97,41 @@ describe Assembly::ObjectFile do
   end
 
   describe '#image?' do
+    subject { object_file.image? }
+
     context 'with tiff' do
-      it 'true' do
-        object_file = described_class.new(TEST_TIF_INPUT_FILE)
-        expect(object_file.image?).to be(true)
-      end
+      let(:object_file) { described_class.new(TEST_TIF_INPUT_FILE) }
+
+      it { is_expected.to be true }
     end
 
     context 'with jp2' do
-      it 'true' do
-        object_file = described_class.new(TEST_JP2_INPUT_FILE)
-        expect(object_file.image?).to be(true)
+      let(:object_file) { described_class.new(TEST_JP2_INPUT_FILE) }
+
+      it { is_expected.to be true }
+    end
+
+    context 'with targa file' do
+      before do
+        allow(object_file).to receive(:exif_mimetype).and_return(nil)
+        allow(object_file).to receive(:file_mimetype).and_return('image/x-tga')
       end
+
+      let(:object_file) { described_class.new(TEST_JP2_INPUT_FILE) }
+
+      it { is_expected.to be false }
     end
 
     context 'with ruby file' do
-      it 'false' do
-        non_image_file = File.join(Assembly::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
+      let(:object_file) { described_class.new(File.join(PATH_TO_GEM, 'spec/assembly/object_file_spec.rb')) }
+
+      it { is_expected.to be false }
     end
 
     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')
-        object_file = described_class.new(non_image_file)
-        expect(object_file.image?).to be(false)
-      end
+      let(:object_file) { described_class.new(File.join(PATH_TO_GEM, 'spec/test_data/input/file_with_no_exif.xml')) }
+
+      it { is_expected.to be false }
     end
   end
 
@@ -145,7 +152,7 @@ describe Assembly::ObjectFile do
 
     context 'with ruby file' do
       it ':text' do
-        non_image_file = File.join(Assembly::PATH_TO_GEM, 'spec/assembly/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
@@ -153,7 +160,7 @@ 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
@@ -191,7 +198,7 @@ describe Assembly::ObjectFile do
 
     context 'with ruby file' do
       it 'false' do
-        non_image_file = File.join(Assembly::PATH_TO_GEM, 'spec/assembly/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
@@ -199,7 +206,7 @@ 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
@@ -359,7 +366,7 @@ 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
@@ -367,7 +374,7 @@ 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
@@ -387,32 +394,17 @@ 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: 2.1.0
+  version: 2.1.3
 platform: ruby
 authors:
 - Peter Mangiafico
@@ -11,7 +11,7 @@ authors:
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2022-07-19 00:00:00.000000000 Z
+date: 2022-08-30 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activesupport