curation_concerns-models 0.10.0 → 0.11.0.rc1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: afd415c4152d3eb3fc25a1d5d63c0261c820ae07
-  data.tar.gz: 051471568f9ab3d2d27ff62a8d8faa5d469c3139
+  metadata.gz: 5d2ce952ca856172a242fb615ba373ddf63110fb
+  data.tar.gz: 40858e4e383e4064df595aa3ae835339dbc8f765
 SHA512:
-  metadata.gz: c2607d15592fe9f7e6acb243256cc33f6b29132b201660328cb427840b3efba3453f5f5c40ce44bab48a8cc5d55cc8b1d685b62143edd0492136ee2cca310483
-  data.tar.gz: 2db872e858e8705f6af5e1060c686b80e01d595125c01492066080916b6e3bd1695bdd72cca78e063fd50c8d81c80a65dcf32ee181653526a810df6ece97964b
+  metadata.gz: 843e33effb12627dd61670f19a4427d0e8211d1be63cd01421fbacca2b6d8d35d8a93cecac53d67a7b95e22eaf8a659ff165227851717a94a96536f5aca190a9
+  data.tar.gz: 6bab1ad84e209f202980a9361aab5629f66e343b3f2baa0b2e8438a97aaa07a088f9e887bb13c59b39b17661ca5d77de999e06f797be962ba2fb261f621922a0

data/app/actors/curation_concerns/file_actor.rb

@@ -1,5 +1,5 @@
 module CurationConcerns
-  # actions for a file identified by file_set_id and relation (maps to use predicate)
+  # actions for a file identified by file_set and relation (maps to use predicate)
   class FileActor
     attr_reader :file_set, :relation, :user
 
@@ -19,10 +19,10 @@ module CurationConcerns
     # have made it to the repo
     # @param [File, ActionDigest::HTTP::UploadedFile, Tempfile] file the file to save in the repository
     def ingest_file(file)
-      working_file = copy_file_to_working_directory(file, file_set_id)
+      working_file = copy_file_to_working_directory(file, file_set.id)
       mime_type = file.respond_to?(:content_type) ? file.content_type : nil
-      IngestFileJob.perform_later(file_set_id, working_file, mime_type, user.user_key, relation)
-      make_derivative(file_set.id, working_file)
+      IngestFileJob.perform_later(file_set, working_file, mime_type, user.user_key, relation)
+      make_derivative(file_set, working_file)
       true
     end
 
@@ -36,18 +36,14 @@ module CurationConcerns
 
       # Retrieve a copy of the orginal file from the repository
       working_file = copy_repository_resource_to_working_directory(repository_file)
-      make_derivative(file_set_id, working_file)
+      make_derivative(file_set, working_file)
       true
     end
 
     private
 
-      def file_set_id
-        file_set.id
-      end
-
-      def make_derivative(file_set_id, working_file)
-        CharacterizeJob.perform_later(file_set_id, working_file)
+      def make_derivative(file_set, working_file)
+        CharacterizeJob.perform_later(file_set, working_file)
       end
 
       # @param [File, ActionDispatch::Http::UploadedFile] file
@@ -61,7 +57,7 @@ module CurationConcerns
       # @param [ActiveFedora::File] file the resource in the repo
       # @return [String] path of the working file
       def copy_repository_resource_to_working_directory(file)
-        copy_stream_to_working_directory(file_set_id, file.original_name, StringIO.new(file.content))
+        copy_stream_to_working_directory(file_set.id, file.original_name, StringIO.new(file.content))
       end
 
       # @param [String] id the identifer

data/app/indexers/curation_concerns/collection_indexer.rb

@@ -1,14 +1,14 @@
 module CurationConcerns
   class CollectionIndexer < Hydra::PCDM::CollectionIndexer
     include IndexesThumbnails
-    STORED_INTEGER = Solrizer::Descriptor.new(:integer, :stored)
+    STORED_LONG = Solrizer::Descriptor.new(:long, :stored)
 
     def generate_solr_document
       super.tap do |solr_doc|
         # Makes Collections show under the "Collections" tab
         Solrizer.set_field(solr_doc, 'generic_type', 'Collection', :facetable)
         # Index the size of the collection in bytes
-        solr_doc[Solrizer.solr_name(:bytes, STORED_INTEGER)] = object.bytes
+        solr_doc[Solrizer.solr_name(:bytes, STORED_LONG)] = object.bytes
         solr_doc['thumbnail_path_ss'] = thumbnail_path
       end
     end

data/app/jobs/audit_job.rb

@@ -1,21 +1,16 @@
-class AuditJob < ActiveFedoraIdBasedJob
+class AuditJob < ActiveJob::Base
   queue_as :audit
 
-  attr_accessor :uri, :id, :file_id
-
   # URI of the resource to audit.
   # This URI could include the actual resource (e.g. content) and the version to audit:
   #     http://localhost:8983/fedora/rest/test/a/b/c/abcxyz/content/fcr:versions/version1
   # but it could also just be:
   #     http://localhost:8983/fedora/rest/test/a/b/c/abcxyz/content
-  # @param [String] id of the parent object
+  # @param [FileSet] the parent object
   # @param [String] file_id used to find the file within its parent object (usually "original_file")
   # @param [String] uri of the specific file/version to be audited
-  def perform(id, file_id, uri)
-    @id = id
-    @file_id = file_id
-    @uri = uri
-    log = run_audit
+  def perform(file_set, file_id, uri)
+    log = run_audit(file_set, file_id, uri)
     fixity_ok = log.pass == 1
     unless fixity_ok
       if CurationConcerns.config.callback.set?(:after_audit_failure)
@@ -29,7 +24,7 @@ class AuditJob < ActiveFedoraIdBasedJob
 
   protected
 
-    def run_audit
+    def run_audit(file_set, file_id, uri)
       begin
         fixity_ok = ActiveFedora::FixityService.new(uri).check
       rescue Ldp::NotFound
@@ -38,12 +33,12 @@ class AuditJob < ActiveFedoraIdBasedJob
 
       if fixity_ok
         passing = 1
-        ChecksumAuditLog.prune_history(id, file_id)
+        ChecksumAuditLog.prune_history(file_set.id, file_id)
       else
         logger.warn "***AUDIT*** Audit failed for #{uri} #{error_msg}"
         passing = 0
       end
-      ChecksumAuditLog.create!(pass: passing, file_set_id: id, version: uri, file_id: file_id)
+      ChecksumAuditLog.create!(pass: passing, file_set_id: file_set.id, version: uri, file_id: file_id)
     end
 
   private

data/app/jobs/characterize_job.rb

@@ -1,12 +1,11 @@
-class CharacterizeJob < ActiveFedoraIdBasedJob
+class CharacterizeJob < ActiveJob::Base
   queue_as :characterize
 
-  # @param [String] id
+  # @param [FileSet] file_set
   # @param [String] filename a local path for the file to characterize. By using this, we don't have to pull a copy out of fedora.
-  def perform(id, filename)
-    @id = id
+  def perform(file_set, filename)
     Hydra::Works::CharacterizationService.run(file_set, filename)
-    file_set.save
-    CreateDerivativesJob.perform_later(file_set.id, filename)
+    file_set.save!
+    CreateDerivativesJob.perform_later(file_set, filename)
   end
 end

data/app/jobs/create_derivatives_job.rb

@@ -1,19 +1,20 @@
-class CreateDerivativesJob < ActiveFedoraIdBasedJob
+class CreateDerivativesJob < ActiveJob::Base
   queue_as :derivatives
 
-  def perform(id, file_name)
-    @id = id
+  # @param [FileSet] file_set
+  # @param [String] file_name
+  def perform(file_set, file_name)
     return if file_set.video? && !CurationConcerns.config.enable_ffmpeg
 
     file_set.create_derivatives(file_name)
     # The thumbnail is indexed in the solr document, so reindex
     file_set.update_index
-    file_set.parent.update_index if parent_needs_reindex?
+    file_set.parent.update_index if parent_needs_reindex?(file_set)
   end
 
   # If this file_set is the thumbnail for the parent work,
   # then the parent also needs to be reindexed.
-  def parent_needs_reindex?
+  def parent_needs_reindex?(file_set)
     return false unless file_set.parent
     file_set.parent.thumbnail_id == file_set.id
   end

data/app/jobs/import_url_job.rb

@@ -2,15 +2,14 @@ require 'net/https'
 require 'uri'
 require 'tempfile'
 
-class ImportUrlJob < ActiveFedoraIdBasedJob
+class ImportUrlJob < ActiveJob::Base
   queue_as :import_url
 
-  def perform(id)
-    @id = id
+  def perform(file_set)
     user = User.find_by_user_key(file_set.depositor)
 
-    Tempfile.open(id.tr('/', '_')) do |f|
-      copy_remote_file(file_set.import_url, f)
+    Tempfile.open(file_set.id.tr('/', '_')) do |f|
+      copy_remote_file(file_set, f)
 
       # reload the generic file once the data is copied since this is a long running task
       file_set.reload
@@ -25,23 +24,25 @@ class ImportUrlJob < ActiveFedoraIdBasedJob
     end
   end
 
-  def copy_remote_file(_import_url, f)
-    f.binmode
-    # download file from url
-    uri = URI(file_set.import_url)
-    http = Net::HTTP.new(uri.host, uri.port)
-    http.use_ssl = uri.scheme == 'https' # enable SSL/TLS
-    http.verify_mode = OpenSSL::SSL::VERIFY_NONE
-    mime_type = nil
-
-    http.start do
-      http.request_get(uri.request_uri) do |resp|
-        mime_type = resp.content_type
-        resp.read_body do |segment|
-          f.write(segment)
+  protected
+
+    def copy_remote_file(file_set, f)
+      f.binmode
+      # download file from url
+      uri = URI(file_set.import_url)
+      http = Net::HTTP.new(uri.host, uri.port)
+      http.use_ssl = uri.scheme == 'https' # enable SSL/TLS
+      http.verify_mode = OpenSSL::SSL::VERIFY_NONE
+      mime_type = nil
+
+      http.start do
+        http.request_get(uri.request_uri) do |resp|
+          mime_type = resp.content_type
+          resp.read_body do |segment|
+            f.write(segment)
+          end
         end
       end
+      f.rewind
     end
-    f.rewind
-  end
 end

data/app/jobs/ingest_file_job.rb

@@ -1,14 +1,12 @@
 class IngestFileJob < ActiveJob::Base
   queue_as :ingest
 
-  # @param [String] file_set_id
+  # @param [FileSet] file_set
   # @param [String] filename
   # @param [String,NilClass] mime_type
   # @param [String] user_key
   # @param [String] relation ('original_file')
-  def perform(file_set_id, filename, mime_type, user_key, relation = 'original_file')
-    file_set = FileSet.find(file_set_id)
-
+  def perform(file_set, filename, mime_type, user_key, relation = 'original_file')
     file = File.open(filename, "rb")
     # If mime-type is known, wrap in an IO decorator
     # Otherwise allow Hydra::Works service to determine mime_type

data/app/models/concerns/curation_concerns/file_set_behavior.rb

@@ -18,6 +18,7 @@ module CurationConcerns
     include CurationConcerns::RequiredMetadata
     include CurationConcerns::Naming
     include Hydra::AccessControls::Embargoable
+    include GlobalID::Identification
 
     included do
       attr_accessor :file

data/app/models/concerns/curation_concerns/work_behavior.rb

@@ -13,6 +13,7 @@ module CurationConcerns::WorkBehavior
   include CurationConcerns::Naming
   include CurationConcerns::RequiredMetadata
   include Hydra::AccessControls::Embargoable
+  include GlobalID::Identification
 
   included do
     property :owner, predicate: RDF::URI.new('http://opaquenamespace.org/ns/hydra/owner'), multiple: false

data/app/services/curation_concerns/file_set_audit_service.rb

@@ -81,7 +81,7 @@ module CurationConcerns
       def audit_file_version(file_id, version_uri)
         latest_audit = ChecksumAuditLog.logs_for(file_set.id, file_id).first
         return latest_audit unless needs_audit?(latest_audit)
-        AuditJob.perform_later(file_set.id, file_id, version_uri.to_s)
+        AuditJob.perform_later(file_set, file_id, version_uri.to_s)
         latest_audit || ChecksumAuditLog.new(pass: NO_RUNS, file_set_id: file_set.id, file_id: file_id, version: version_uri)
       end
 

data/curation_concerns-models.gemspec

@@ -22,12 +22,13 @@ Gem::Specification.new do |spec|
   spec.add_dependency 'active_attr'
   spec.add_dependency 'hydra-collections', '~> 8.1'
   spec.add_dependency 'hydra-head', '~> 9.3'
-  spec.add_dependency 'hydra-works', '~> 0.7'
+  spec.add_dependency 'hydra-works', '~> 0.8', '>= 0.8.1'
   spec.add_dependency 'active_fedora-noid', '~> 1.0'
   spec.add_dependency 'resque', '~> 1.23'
   spec.add_dependency 'resque-pool', '~> 0.3'
   spec.add_dependency 'qa', '~> 0.5'
   spec.add_dependency 'redlock', '~> 0.1.2'
+  spec.add_dependency 'solrizer', '~> 3.4'
 
   spec.add_development_dependency 'bundler', '~> 1.6'
   spec.add_development_dependency 'rake'

data/lib/curation_concerns/models/version.rb

@@ -1,5 +1,5 @@
 module CurationConcerns
   module Models
-    VERSION = "0.10.0".freeze
+    VERSION = "0.11.0.rc1".freeze
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: curation_concerns-models
 version: !ruby/object:Gem::Version
-  version: 0.10.0
+  version: 0.11.0.rc1
 platform: ruby
 authors:
 - Justin Coyne
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-03-04 00:00:00.000000000 Z
+date: 2016-03-31 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: active_attr
@@ -58,14 +58,20 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.7'
+        version: '0.8'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.8.1
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.7'
+        version: '0.8'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.8.1
 - !ruby/object:Gem::Dependency
   name: active_fedora-noid
   requirement: !ruby/object:Gem::Requirement
@@ -136,6 +142,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: 0.1.2
+- !ruby/object:Gem::Dependency
+  name: solrizer
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.4'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.4'
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
@@ -187,7 +207,6 @@ files:
 - app/indexers/curation_concerns/collection_indexer.rb
 - app/indexers/curation_concerns/file_set_indexer.rb
 - app/indexers/curation_concerns/work_indexer.rb
-- app/jobs/active_fedora_id_based_job.rb
 - app/jobs/audit_job.rb
 - app/jobs/characterize_job.rb
 - app/jobs/create_derivatives_job.rb
@@ -278,9 +297,9 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ">="
+  - - ">"
     - !ruby/object:Gem::Version
-      version: '0'
+      version: 1.3.1
 requirements: []
 rubyforge_project: 
 rubygems_version: 2.5.1

data/app/jobs/active_fedora_id_based_job.rb

@@ -1,15 +0,0 @@
-class ActiveFedoraIdBasedJob < ActiveJob::Base
-  queue_as :id_based
-
-  attr_accessor :id
-
-  def object
-    @object ||= ActiveFedora::Base.find(id)
-  end
-
-  alias file_set object
-
-  def perform(_)
-    fail 'Define #run in a subclass'
-  end
-end