active_encode 1.2.2 → 1.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 9104a0bde11fcf84284f375301d9c4b2de4a25010e8834a363323b7e8e0bb994
-  data.tar.gz: d03aa952ac5d8cee3b8668950563e3b4ce4c2fb4cfade4562f69b48918b60e37
+  metadata.gz: a55a4e3f05065b6f69afc4a7d097f9c5c15926aada0fdb5915c3b19e09d024a2
+  data.tar.gz: 6c3e3b9f78fb430ed77f658a6f2be986dee227b642ce92a0c156998a1d35663c
 SHA512:
-  metadata.gz: 6e3280b175e3943a28094f5298fe5c9674317b3d8d4147d83a9d5f215edd9dd422f452f7181fb57f28ebbc7632775c9bc6b91bdd7b72b5abe239c56edc7c3caf
-  data.tar.gz: '01062903b0008ae7299d1b97c91f26d8a1b8b6f4b69fb14a5722a577046da6b6357b0f8970b150c25735471d23166d1a25e78f216228cfcc87ad4ca257eecf98'
+  metadata.gz: 1124cbecacf61ec7fa05a5eaf109599d4957e6865c0bc7e8938dc0a5d09f1912c5c93d49764c60301b7d1de0917b6d1af923b3e322812a7cc7f4b1dacf571257
+  data.tar.gz: 69695a33b2af42d9b19f101e2030209c2483d8bed919fc76542593f599a603bcba720341f0826fdd350154ac4feb62733a7a8453e11b935a28016889dc41e79a

data/.circleci/config.yml

@@ -65,30 +65,38 @@ workflows:
   ci:
     jobs:
       - bundle_and_test:
-          name: "ruby3-2_rails7-0"
-          ruby_version: "3.2.0"
-          rails_version: "7.0.4.2"
+          name: "ruby3-4_rails8-0"
+          ruby_version: "3.4.1"
+          rails_version: "8.0.1"
       - bundle_and_test:
-          name: "ruby3-1_rails7-0"
-          ruby_version: "3.1.3"
-          rails_version: "7.0.4.2"
+          name: "ruby3-4_rails7-2"
+          ruby_version: "3.4.1"
+          rails_version: "7.2.2.1"
       - bundle_and_test:
-          name: "ruby3-0_rails7-0"
-          ruby_version: "3.0.5"
-          rails_version: "7.0.4.2"
+          name: "ruby3-4_rails7-1"
+          ruby_version: "3.4.1"
+          rails_version: "7.1.5.1"
       - bundle_and_test:
-          name: "ruby3-0_rails6-1"
-          ruby_version: "3.0.5"
-          rails_version: "6.1.7.2"
+          name: "ruby3-3_rails8-0"
+          ruby_version: "3.3.7"
+          rails_version: "8.0.1"
       - bundle_and_test:
-          name: "ruby3-0_rails6-0"
-          ruby_version: "3.0.5"
-          rails_version: "6.0.6.1"
+          name: "ruby3-3_rails7-2"
+          ruby_version: "3.3.7"
+          rails_version: "7.2.2.1"
       - bundle_and_test:
-          name: "ruby2-7_rails6-0"
-          ruby_version: "2.7.7"
-          rails_version: "6.0.6.1"
+          name: "ruby3-3_rails7-1"
+          ruby_version: "3.3.7"
+          rails_version: "7.1.5.1"
       - bundle_and_test:
-          name: "ruby2-7_rails5-2"
-          ruby_version: "2.7.7"
-          rails_version: "5.2.8.1"
+          name: "ruby3-2_rails8-0"
+          ruby_version: "3.2.7"
+          rails_version: "8.0.1"
+      - bundle_and_test:
+          name: "ruby3-2_rails7-2"
+          ruby_version: "3.2.7"
+          rails_version: "7.2.2.1"
+      - bundle_and_test:
+          name: "ruby3-2_rails7-1"
+          ruby_version: "3.2.7"
+          rails_version: "7.1.5.1"

data/Gemfile

@@ -35,6 +35,8 @@ else
     end
 
     case ENV['RAILS_VERSION']
+    when /^[56]/, /^7.0/
+      gem 'concurrent-ruby', '1.3.4'
     when /^6.0/
       gem 'sass-rails', '>= 6'
       gem 'webpacker', '~> 4.0'

data/active_encode.gemspec

@@ -25,6 +25,7 @@ Gem::Specification.new do |spec|
 
   spec.add_development_dependency "aws-sdk-cloudwatchevents"
   spec.add_development_dependency "aws-sdk-cloudwatchlogs"
+  spec.add_development_dependency "aws-sdk-core", "<= 3.220.0"
   spec.add_development_dependency "aws-sdk-elastictranscoder"
   spec.add_development_dependency "aws-sdk-mediaconvert"
   spec.add_development_dependency "aws-sdk-s3"

data/lib/active_encode/engine.rb

@@ -4,5 +4,17 @@ require 'rails'
 module ActiveEncode
   class Engine < ::Rails::Engine
     isolate_namespace ActiveEncode
+
+    config.before_configuration do
+      # rubocop:disable Style/IfUnlessModifier
+      # see https://github.com/fxn/zeitwerk#for_gem
+      # Blacklight puts a generator into LOCAL APP lib/generators, so tell
+      # zeitwerk to ignore the whole directory? If we're using zeitwerk
+      #
+      # See: https://github.com/cbeer/engine_cart/issues/117
+      if ::Rails.try(:autoloaders).try(:main).respond_to?(:ignore)
+        ::Rails.autoloaders.main.ignore(::Rails.root.join('lib', 'generators'))
+      end
+    end
   end
 end

data/lib/active_encode/engine_adapters/ffmpeg_adapter/cleaner.rb

@@ -53,7 +53,11 @@ module ActiveEncode
         def remove_empty_directories(directories)
           directories_to_delete = directories.select { |d| Dir.empty?(d) }
           non_empty_directories = directories - directories_to_delete
-          directories_to_delete += non_empty_directories.select { |ned| Dir.children(ned) == ["outputs"] && directories_to_delete.include?(File.join(ned, "outputs")) }
+          directories_to_delete += non_empty_directories.select do |ned|
+            Dir.children(ned).sort == ["outputs", "supplemental_files"] &&
+              directories_to_delete.include?(File.join(ned, "outputs")) &&
+              directories_to_delete.include?(File.join(ned, "supplemental_files"))
+          end
           FileUtils.rmdir(directories_to_delete) unless directories_to_delete.empty?
         end
 

data/lib/active_encode/engine_adapters/ffmpeg_adapter.rb

@@ -28,6 +28,8 @@ module ActiveEncode
 
           s3_object = FileLocator::S3File.new(input_url).object
           input_url = URI.parse(s3_object.presigned_url(:get))
+        when /^https?\:\/\//
+          input_url = URI.parse(input_url)
         end
 
         new_encode = ActiveEncode::Base.new(input_url, options)
@@ -40,6 +42,7 @@ module ActiveEncode
         # Create a working directory that holds all output files related to the encode
         FileUtils.mkdir_p working_path("", new_encode.id)
         FileUtils.mkdir_p working_path("outputs", new_encode.id)
+        FileUtils.mkdir_p working_path("supplemental_files", new_encode.id)
 
         # Extract technical metadata from input file
         curl_option = if options && options[:headers]
@@ -89,12 +92,14 @@ module ActiveEncode
           new_encode.input.duration = fixed_duration(working_path("duration_input_metadata", new_encode.id))
         end
 
+        subtitle_count = new_encode.input.subtitles.length if new_encode.input.subtitles.present?
+
         new_encode.state = :running
         new_encode.percent_complete = 1
         new_encode.errors = []
 
         # Run the ffmpeg command and save its pid
-        command = ffmpeg_command(input_url, new_encode.id, options)
+        command = ffmpeg_command(input_url, new_encode.id, options, subtitle_count)
         # Capture the exit status in a file in order to differentiate warning output in stderr between real process failure
         exit_status_file = working_path("exit_status.code", new_encode.id)
         command = "#{command}; echo $? > #{exit_status_file}"
@@ -148,6 +153,7 @@ module ActiveEncode
         end
 
         encode.output = build_outputs encode if encode.completed?
+        encode.output += build_supplemental_outputs encode if encode.completed?
 
         encode
       end
@@ -232,7 +238,7 @@ module ActiveEncode
         Dir["#{File.absolute_path(working_path('outputs', id))}/*"].each do |file_path|
           output = ActiveEncode::Output.new
           output.url = "file://#{file_path}"
-          sanitized_filename = ActiveEncode.sanitize_base encode.input.url
+          sanitized_filename = encode.input.url.match?(/^https?\:\/\//) ? ActiveEncode.sanitize_base(URI.parse(encode.input.url)) : ActiveEncode.sanitize_base(encode.input.url)
           output.label = file_path[/#{Regexp.quote(sanitized_filename)}.*\-(.*?)#{Regexp.quote(File.extname(file_path))}$/, 1]
           output.id = "#{encode.input.id}-#{output.label}"
           output.created_at = encode.created_at
@@ -249,17 +255,51 @@ module ActiveEncode
         outputs
       end
 
-      def ffmpeg_command(input_url, id, opts)
+      def build_supplemental_outputs(encode)
+        id = encode.id
+        files = []
+        Dir["#{File.absolute_path(working_path('supplemental_files', id))}/*"].each_with_index do |file_path, index|
+          file = ActiveEncode::Output.new
+          file.url = "file://#{file_path}"
+          file.id = "#{encode.input.id}-#{File.basename(file_path)}"
+          file.created_at = encode.created_at
+          file.updated_at = File.mtime file_path
+          file.label = encode.input.subtitles[index][:label]
+          file.language = encode.input.subtitles[index][:language]
+          file.format = 'vtt'
+
+          files << file
+        end
+
+        files
+      end
+
+      def ffmpeg_command(input_url, id, opts, subtitle_count = nil)
+        sanitized_filename = ActiveEncode.sanitize_base input_url
         output_opt = opts[:outputs].collect do |output|
-          sanitized_filename = ActiveEncode.sanitize_base input_url
           file_name = "outputs/#{sanitized_filename}-#{output[:label]}.#{output[:extension]}"
           " #{output[:ffmpeg_opt]} #{working_path(file_name, id)}"
         end.join(" ")
+
+        supplemental_file_opt = if opts[:extract_subtitles] && subtitle_count.present?
+                                  caption_extraction_options(sanitized_filename, subtitle_count, id)
+                                end
+
         header_opt = Array(opts[:headers]).map do |k, v|
           "#{k}: #{v}\r\n"
         end.join
         header_opt = "-headers '#{header_opt}'" if header_opt.present?
-        "#{FFMPEG_PATH} #{header_opt} -y -loglevel level+fatal -progress #{working_path('progress', id)} -i \"#{input_url}\" #{output_opt}"
+        "#{FFMPEG_PATH} #{header_opt} -y -loglevel level+fatal -progress #{working_path('progress', id)} -i \"#{input_url}\" #{supplemental_file_opt} #{output_opt}"
+      end
+
+      def caption_extraction_options(filename, count, id)
+        opts = ""
+        (0..count - 1).each do |i|
+          subtitle_filename = "supplemental_files/#{filename}-caption#{i}.vtt"
+          opts += " -map 0:s:#{i} -c:s webvtt #{working_path(subtitle_filename, id)}"
+        end
+
+        opts
       end
 
       def get_pid(id)
@@ -321,13 +361,24 @@ module ActiveEncode
           audio_codec: get_xpath_text(doc, '//track[@type="Audio"]/CodecID/text()', :to_s),
           audio_bitrate: get_xpath_text(doc, '//track[@type="Audio"]/BitRate/text()', :to_i),
           video_codec: get_xpath_text(doc, '//track[@type="Video"]/CodecID/text()', :to_s),
-          video_bitrate: get_xpath_text(doc, '//track[@type="Video"]/BitRate/text()', :to_i) }
+          video_bitrate: get_xpath_text(doc, '//track[@type="Video"]/BitRate/text()', :to_i),
+          subtitles: get_subtitle_tech_metadata(doc).compact }
       end
 
       def get_xpath_text(doc, xpath, cast_method)
         doc.xpath(xpath).first&.text&.send(cast_method)
       end
 
+      def get_subtitle_tech_metadata(doc)
+        doc.xpath("//track[@type='Text' and Format='Timed Text']").collect do |track|
+          {
+            format: get_xpath_text(track, "./CodecID/text()", :to_s),
+            label: get_xpath_text(track, "./Title/text()", :to_s),
+            language: get_xpath_text(track, "./Language/text()", :to_s)
+          }
+        end
+      end
+
       def fixed_duration(path)
         get_tech_metadata(path)[:duration]
       end

data/lib/active_encode/filename_sanitizer.rb

@@ -10,7 +10,8 @@ module ActiveEncode
       filepath = input_url.is_a?(URI::HTTP) ? input_url.path : input_url
       # Replace special characters with underscores and remove excess periods.
       # This removes the extension before processing so it is safe to delete all detected periods.
-      File.basename(filepath, File.extname(filepath)).gsub(/[^0-9A-Za-z.\-\/]/, '_').delete('.')
+      # This explicitly handles percent encoded spaces.
+      File.basename(filepath, File.extname(filepath)).gsub(/%20/, "_").gsub(/[^0-9A-Za-z.\-\/]/, '_').delete('.')
     end
 
     def sanitize_filename(input_url)
@@ -24,7 +25,7 @@ module ActiveEncode
       when /^file\:\/\/\//
         input_url.to_s.gsub(/file:\/\//, '')
       when /^s3\:\/\//
-        input_url.to_s.gsub(/#{Addressable::URI.parse(input_url).normalized_site}/, '')
+        input_url.to_s.gsub(/#{Addressable::URI.parse(input_url).site}/, '')
       when /^https?:\/\//
         input_url
       end

data/lib/active_encode/technical_metadata.rb

@@ -22,11 +22,17 @@ module ActiveEncode
       attr_accessor :video_codec
       attr_accessor :audio_bitrate
       attr_accessor :video_bitrate
+
+      # Array of hashes
+      attr_accessor :subtitles
+      attr_accessor :format
+      attr_accessor :language
     end
 
     def assign_tech_metadata(metadata)
       [:width, :height, :frame_rate, :duration, :file_size, :checksum,
-       :audio_codec, :video_codec, :audio_bitrate, :video_bitrate].each do |field|
+       :audio_codec, :video_codec, :audio_bitrate, :video_bitrate, :subtitles,
+       :format, :language].each do |field|
         send("#{field}=", metadata[field]) if metadata.key?(field)
       end
     end

data/lib/active_encode/version.rb

@@ -1,4 +1,4 @@
 # frozen_string_literal: true
 module ActiveEncode
-  VERSION = '1.2.2'
+  VERSION = '1.3.0'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: active_encode
 version: !ruby/object:Gem::Version
-  version: 1.2.2
+  version: 1.3.0
 platform: ruby
 authors:
 - Michael Klein, Chris Colvard, Phuong Dinh
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-02-14 00:00:00.000000000 Z
+date: 2025-07-30 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rails
@@ -66,6 +66,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: aws-sdk-core
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "<="
+      - !ruby/object:Gem::Version
+        version: 3.220.0
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "<="
+      - !ruby/object:Gem::Version
+        version: 3.220.0
 - !ruby/object:Gem::Dependency
   name: aws-sdk-elastictranscoder
   requirement: !ruby/object:Gem::Requirement
@@ -303,7 +317,7 @@ licenses:
 - Apache-2.0
 metadata:
   rubygems_mfa_required: 'true'
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -318,8 +332,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.5.6
-signing_key: 
+rubygems_version: 3.5.3
+signing_key:
 specification_version: 4
 summary: Declare encode job classes that can be run by a variety of encoding services
 test_files: []