Merge pull request #1114 from LafayetteCollegeLibraries/develop

2024.4

CHANGELOG.md

@@ -1,5 +1,18 @@
 # changelog
 
+## [2024.4] - 2024-03-26
+
+### enhancements ✨
+- Refactored derivatives code to ensure PDFs are being OCR'd (and generally make the process a bit more legible) (#1010)
+
+### updates 📈
+- Bulkrax to 5.5.1 (#1113)
+
+### bug fixes 🐞
+- **All works / My works** dashboard navtabs work again (#1113)
+- Removed `eduPersonEntitlement` values from cookied CAS attributes (#1115)
+
+
 ## [2024.3] - 2024-03-15
 
 ### bug fixes 🐞
@@ -910,6 +923,7 @@ fixes:
 
 Initial pre-release (live on ldr.stage.lafayette.edu)
 
+[2024.4]: https://github.com/LafayetteCollegeLibraries/spot/releases/tag/2024.4
 [2024.3]: https://github.com/LafayetteCollegeLibraries/spot/releases/tag/2024.3
 [2024.2]: https://github.com/LafayetteCollegeLibraries/spot/releases/tag/2024.2
 [2024.1]: https://github.com/LafayetteCollegeLibraries/spot/releases/tag/2024.1

Gemfile

@@ -53,7 +53,7 @@ gem 'bootsnap', '~> 1.17', require: false
 
 # Bulkrax for batch ingesting objects
 gem 'browse-everything', '~> 1.1.2'
-gem 'bulkrax', '~> 5.3.0'
+gem 'bulkrax', '~> 5.5.1'
 
 # This needs to be here if we want to compile our own JS
 # (there's like a single coffee-script file still remaining in hyrax)
@@ -138,6 +138,10 @@ gem 'sprockets-es6', '~> 0.9.2'
 # @todo remove when Hyrax 3.5.1 or 3.6 (whichever includes it) drops
 gem 'redlock', '>= 0.1.2', '< 2.0'
 
+# This is locked in hydra_editor > v6 to prevent an update
+# that throws off how forms are built in Hyrax.
+gem 'simple_form', '< 5.2'
+
 # development dependencies (not as necessary to lock down versions here)
 group :development do
   # Seed data

Gemfile.lock

@@ -111,7 +111,7 @@ GEM
     babel-transpiler (0.7.0)
       babel-source (>= 4.0, < 6)
       execjs (~> 2.0)
-    bagit (0.4.5)
+    bagit (0.4.6)
       docopt (~> 0.5.0)
       validatable (~> 1.6)
     bcp47 (0.3.3)
@@ -176,10 +176,9 @@ GEM
       signet (~> 0.8)
       typhoeus
     builder (3.2.4)
-    bulkrax (5.3.0)
+    bulkrax (5.5.1)
       bagit (~> 0.4)
       coderay
-      dry-monads (~> 1.4.0)
       iso8601 (~> 0.9.0)
       kaminari
       language_list (~> 1.2, >= 1.2.1)
@@ -219,7 +218,7 @@ GEM
       coffee-script-source
       execjs
     coffee-script-source (1.12.2)
-    concurrent-ruby (1.2.2)
+    concurrent-ruby (1.2.3)
     connection_pool (2.4.1)
     crack (0.4.5)
       rexml
@@ -230,7 +229,7 @@ GEM
       activerecord (>= 5.a)
       database_cleaner-core (~> 2.0.0)
     database_cleaner-core (2.0.1)
-    date (3.3.3)
+    date (3.3.4)
     declarative (0.0.20)
     declarative-builder (0.1.0)
       declarative-option (< 0.2.0)
@@ -530,7 +529,7 @@ GEM
       valkyrie (~> 2, >= 2.1.1)
     hyrax-spec (0.3.2)
       rspec (~> 3.6)
-    i18n (1.14.1)
+    i18n (1.14.4)
       concurrent-ruby (~> 1.0)
     ice_nine (0.11.2)
     iiif_manifest (1.3.1)
@@ -652,45 +651,43 @@ GEM
     mailboxer (0.15.1)
       carrierwave (>= 0.5.8)
       rails (>= 5.0.0)
-    marcel (1.0.2)
+    marcel (1.0.4)
     matrix (0.4.2)
     memoist (0.16.2)
     method_source (1.0.0)
     mime-types (3.4.1)
       mime-types-data (~> 3.2015)
     mime-types-data (3.2023.0218.1)
     mini_magick (4.12.0)
-    mini_mime (1.1.2)
+    mini_mime (1.1.5)
     mini_portile2 (2.8.5)
-    minitest (5.18.1)
+    minitest (5.22.3)
     msgpack (1.7.1)
     multi_json (1.15.0)
     multi_xml (0.6.0)
-    multipart-post (2.3.0)
+    multipart-post (2.4.0)
     namae (1.1.1)
     nest (3.2.0)
       redic
     net-http-persistent (4.0.2)
       connection_pool (~> 2.2)
-    net-imap (0.3.6)
+    net-imap (0.4.10)
       date
       net-protocol
     net-pop (0.1.2)
       net-protocol
-    net-protocol (0.2.1)
+    net-protocol (0.2.2)
       timeout
-    net-smtp (0.3.3)
+    net-smtp (0.4.0.1)
       net-protocol
-    nio4r (2.5.9)
+    nio4r (2.7.0)
     noid (0.9.0)
     noid-rails (3.0.3)
       actionpack (>= 5.0.0, < 7)
       noid (~> 0.9)
-    nokogiri (1.15.3)
+    nokogiri (1.15.6)
       mini_portile2 (~> 2.8.2)
       racc (~> 1.4)
-    nokogiri (1.15.3-arm64-darwin)
-      racc (~> 1.4)
     non-digest-assets (2.2.0)
       activesupport (>= 5.2, < 7.1)
       sprockets (>= 2.0, < 5.0)
@@ -738,7 +735,7 @@ GEM
       rdf
     raabro (1.4.0)
     racc (1.7.3)
-    rack (2.2.8)
+    rack (2.2.8.1)
     rack-cas (0.16.1)
       addressable (~> 2.3)
       nokogiri (~> 1.5)
@@ -980,7 +977,7 @@ GEM
       faraday (>= 0.17.5, < 3.a)
       jwt (>= 1.5, < 3.0)
       multi_json (~> 1.10)
-    simple_form (5.2.0)
+    simple_form (5.1.0)
       actionpack (>= 5.2)
       activemodel (>= 5.2)
     simplecov (0.21.2)
@@ -1036,10 +1033,10 @@ GEM
     temple (0.10.3)
     terminal-table (3.0.2)
       unicode-display_width (>= 1.1.1, < 3)
-    thor (1.3.0)
+    thor (1.3.1)
     thread_safe (0.3.6)
     tilt (2.3.0)
-    timeout (0.4.0)
+    timeout (0.4.1)
     tinymce-rails (5.10.7.1)
       railties (>= 3.1.1)
     turbolinks (5.2.1)
@@ -1090,15 +1087,14 @@ GEM
       hashdiff (>= 0.4.0, < 2.0.0)
     webrick (1.8.1)
     websocket (1.2.10)
-    websocket-driver (0.7.5)
+    websocket-driver (0.7.6)
       websocket-extensions (>= 0.1.0)
     websocket-extensions (0.1.5)
     xpath (3.2.0)
       nokogiri (~> 1.8)
-    zeitwerk (2.6.8)
+    zeitwerk (2.6.13)
 
 PLATFORMS
-  arm64-darwin-22
   ruby
 
 DEPENDENCIES
@@ -1112,7 +1108,7 @@ DEPENDENCIES
   blacklight_range_limit (~> 6.3.3)
   bootsnap (~> 1.17)
   browse-everything (~> 1.1.2)
-  bulkrax (~> 5.3.0)
+  bulkrax (~> 5.5.1)
   byebug (~> 11.1.3)
   capybara (~> 3.38)
   capybara-screenshot (~> 1.0.26)
@@ -1157,6 +1153,7 @@ DEPENDENCIES
   shoulda-matchers (~> 4)
   sidekiq (~> 5.2.9)
   sidekiq-cron (~> 1.9.1)
+  simple_form (< 5.2)
   simplecov (~> 0.21.2)
   slack-ruby-client (~> 0.14.6)
   spring (~> 2.1.1)

app/services/spot/derivatives/base_derivative_service.rb

@@ -0,0 +1,14 @@
+# frozen_string_literal: true
+module Spot
+  module Derivatives
+    # Base class that other derivative services can inherit from
+    class BaseDerivativeService < ::Hyrax::DerivativeService
+      delegate :audio_mime_types,
+               :image_mime_types,
+               :pdf_mime_types,
+               :office_document_mime_types,
+               :video_mime_types,
+               to: :FileSet
+    end
+  end
+end

app/services/spot/derivatives/access_master_service.rb → app/services/spot/derivatives/iiif_access_copy_service.rb

@@ -5,63 +5,51 @@
 
 module Spot
   module Derivatives
-    # Creates access_master derivatives for all image-based works.
-    # Intended to be run as part of a subset within {Spot::ImageDerivativesService}
-    # and needs to respond to :cleanup_derivatives and :create_derivatives (the
-    # latter receives a source filename as a parameter).
+    # Creates pyramidal TIFF copies of Images for serving via IIIF. Pyramidal TIFFs contain
+    # layers at different resolutions which makes their use in a deep-zooming IIIF application
+    # (ie. UniversalViewer) more efficient.
     #
-    # When the AWS_IIIF_ASSET_BUCKET environment variable is present, this will
-    # write the file to a defined S3 bucket and remove the local copy.
+    # This generates the file locally and then uploads to an S3 bucket defined by the
+    # AWS_IIIF_ASSET_BUCKET environment variable. The local copy is deleted afterwards.
     #
-    # @example usage
-    #   file_set = FileSet.find(id: 'abc123def')
-    #   src_path = Rails.root.join('tmp', 'uploads', more_path, 'original-file.tif')
-    #   Spot::Derivatives::AccessMasterService.new(file_set).create_derivatives(src_path)
-    class AccessMasterService < BaseDerivativesService
-      # Determines which cleanup method to use based on whether or not AWS related
-      # variables are present in ENV
-      #
-      # @return [void]
-      def cleanup_derivatives
-        use_s3? ? cleanup_s3_derivatives : cleanup_local_derivatives
-      end
-
-      # Deletes the local access_master derivative if it exists
-      #
-      # @return [void]
-      def cleanup_local_derivatives
-        FileUtils.rm_f(derivative_path) if File.exist?(derivative_path)
-      end
+    # These derivatives are created for an FileSets that include Image mime_types.
+    #
+    # @see https://www.loc.gov/preservation/digital/formats/fdd/fdd000237.shtml
+    class IiifAccessCopyService < BaseDerivativeService
+      class_attribute :derivative_key_template
+      self.derivative_key_template = '%s-access.tif'
 
       # Deletes the derivative from the S3 bucket
       # @todo maybe we should hang onto these when we delete + put them in a glacier grave?
       # @return [void]
       # @see https://docs.aws.amazon.com/sdk-for-ruby/v3/api/Aws/S3/Client.html#delete_object-instance_method
-      def cleanup_s3_derivatives
+      def cleanup_derivatives
         s3_client.delete_object(bucket: s3_bucket, key: s3_derivative_key)
       end
 
-      # Since we want to pass some extended options to the creation process,
-      # we'll use MiniMagick directly instead of Hydra::Derviatives::ImageDerivatives.
-      # If AWS ENV variables are present, this will upload the generated file
-      # to an S3 bucket and then delete the local copy.
+      # Generates a pyramidal TIFF using ImageMagick (via MiniMagick gem)
+      # and uploads it to the S3 bucket.
       #
       # @param [String,Pathname] filename the src path of the file
       # @return [void]
       def create_derivatives(filename)
         output_dirname = File.dirname(derivative_path)
         FileUtils.mkdir_p(output_dirname) unless File.directory?(output_dirname)
 
-        MiniMagick::Tool::Convert.new do |magick|
-          magick << "#{filename}[0]"
-          # we need to use an array for each piece of this command; using a string will cause an error
-          magick.merge! %w[-define tiff:tile-geometry=128x128 -compress jpeg]
-          magick << "ptif:#{derivative_path}"
+        MiniMagick::Tool::Convert.new do |convert|
+          convert.merge!(
+            [
+              "#{filename}[0]",
+              "-define", "tiff:tile-geometry=128x128",
+              "-compress", "jpeg",
+              "ptif:#{derivative_path}"
+            ]
+          )
         end
 
-        return unless use_s3?
+        upload_derivative_to_s3
 
-        upload_derivative_to_s3 && cleanup_local_derivatives
+        FileUtils.rm_f(derivative_path) if File.exist?(derivative_path)
       end
 
       # copied from https://github.com/samvera/hyrax/blob/5a9d1be1/app/services/hyrax/file_set_derivatives_service.rb#L32-L37
@@ -73,18 +61,30 @@ def derivative_path
           Hyrax::DerivativePath.derivative_path_for_reference(file_set, 'access.tif').to_s.gsub(/\.access\.tif$/, '')
       end
 
+      # Only create pyramidal TIFFs if the source mime_type is an Image and if we defined
+      def valid?
+        if s3_bucket.blank?
+          Rails.logger.warn('Skipping IIIF Access Copy generation because the AWS_IIIF_ASSET_BUCKET environment variable is not defined.')
+          return false
+        end
+
+        image_mime_types.include?(mime_type)
+      end
+
       private
 
       def s3_bucket
         ENV['AWS_IIIF_ASSET_BUCKET']
       end
 
+      # We're using AWS credentials stored within the App/Sidekiq services for authentication,
+      # so the Aws::S3::Client will pick them up ambiently.
       def s3_client
         @s3_client ||= Aws::S3::Client.new
       end
 
       def s3_derivative_key
-        "#{file_set.id}-access.tif"
+        derivative_key_template % file_set.id
       end
 
       def upload_derivative_to_s3
@@ -100,10 +100,6 @@ def upload_derivative_to_s3
           }
         )
       end
-
-      def use_s3?
-        s3_bucket.present?
-      end
     end
   end
 end