assembly-objectfile 2.1.1 → 2.1.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 76dac08191a4c118cf16e4736b9538c9d2a60811cf9547e0ad395ab468b1b51a
-  data.tar.gz: b9fec1e99d03941f658cd6716e1c00db37ce2f2042816e4ba8f77246b102d1f4
+  metadata.gz: '0931aac97a88ba77ac0cfa8ff018d19fddcfe909c81cd82e9dfc13dca12ed4f4'
+  data.tar.gz: 4eb596c2799586b3298cd1019be16606b4a371a175c4630b1ac826296dacb5bb
 SHA512:
-  metadata.gz: '082fc021ca4f4dde1f3eaaac937e66862d8ea36f5198bdece9866a72e5be068021665e10bd40b8ea2835d848c062886982ed41033935120525c8d4e57efadafd'
-  data.tar.gz: cf2e4facd4248532c5f92c741f80b5e8d27e04b8cc23e3b7959b59118cceaf8122d03aa92af8faf99c8000bb4298b74d9ab86001744c6f852cd148ceda21d675
+  metadata.gz: a252cfc25b6e2a11f50a6eb2976997fdcbf387ba3855fbca03d188a2f7e9572ca1a3ed605da191700551e34a685deb9dec810e63dfbff59bf9bfd09f6a6a9504
+  data.tar.gz: db0fdbf6583455bce118aa14bc29692d90fbb35c1e9746f3748548094ff53e0f33fe79c08cf5baace3869a08e4f9e3080d1906b810ce38d64022efa573e8c500

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    assembly-objectfile (2.1.1)
+    assembly-objectfile (2.1.2)
       activesupport (>= 5.2.0)
       mime-types (> 3)
       mini_exiftool
@@ -28,9 +28,9 @@ 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)
       coderay (~> 1.1)
@@ -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 (1.35.0)
       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 (1.19.1)
+    rubocop-ast (1.21.0)
       parser (>= 3.1.1.0)
     rubocop-rspec (2.12.1)
       rubocop (~> 1.31)

data/lib/assembly/object_file/version.rb

@@ -4,6 +4,6 @@
 module Assembly
   class ObjectFile
     # Gem version
-    VERSION = '2.1.1'
+    VERSION = '2.1.2'
   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]
@@ -64,71 +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 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}"
+        # 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
@@ -136,10 +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
@@ -154,84 +116,55 @@ 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 (from file extension lookup)
     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
+    # @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
 
-    # 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
@@ -239,11 +172,7 @@ 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
@@ -251,12 +180,9 @@ 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
@@ -268,23 +194,8 @@ module Assembly
 
     # 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/spec/assembly/object_file_spec.rb

@@ -387,33 +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 with file path if exiftool raises one' do
-      object_file = described_class.new('spec/test_data/empty.txt')
-      expect { object_file.exif }.to raise_error(MiniExiftool::Error,
-                                                 "error initializing MiniExiftool for #{object_file.path}")
+      it { is_expected.to be_nil }
     end
   end
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: assembly-objectfile
 version: !ruby/object:Gem::Version
-  version: 2.1.1
+  version: 2.1.2
 platform: ruby
 authors:
 - Peter Mangiafico
@@ -11,7 +11,7 @@ authors:
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2022-07-20 00:00:00.000000000 Z
+date: 2022-08-18 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activesupport
@@ -199,7 +199,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.2.32
+rubygems_version: 3.3.7
 signing_key:
 specification_version: 4
 summary: Ruby implementation of file services needed to prepare objects to be accessioned