curation_concerns 0.1.0 → 0.2.0

data/lib/curation_concerns/configuration.rb

@@ -1,74 +0,0 @@
-module CurationConcerns
-
-  class << self
-    attr_accessor :configuration
-  end
-
-  def self.configure
-    self.configuration ||= Configuration.new
-    yield(configuration)
-  end
-
-  class Configuration
-    # An anonymous function that receives a path to a file
-    # and returns AntiVirusScanner::NO_VIRUS_FOUND_RETURN_VALUE if no
-    # virus is found; Any other returned value means a virus was found
-    attr_writer :default_antivirus_instance
-    def default_antivirus_instance
-      @default_antivirus_instance ||= lambda {|file_path|
-        AntiVirusScanner::NO_VIRUS_FOUND_RETURN_VALUE
-      }
-    end
-
-    # Configure default search options from config/search_config.yml
-    attr_writer :search_config
-    def search_config
-      @search_config ||= "search_config not set"
-    end
-
-    # Configure the application root url.
-    attr_writer :application_root_url
-    def application_root_url
-      @application_root_url || (raise RuntimeError.new("Make sure to set your CurationConcerns.configuration.application_root_url"))
-    end
-
-    # When was this last built/deployed
-    attr_writer :build_identifier
-    def build_identifier
-      # If you restart the server, this could be out of sync; A better
-      # implementation is to read something from the file system. However
-      # that detail is an exercise for the developer.
-      @build_identifier ||= Time.now.strftime("%Y-%m-%d %H:%M:%S")
-    end
-
-    # Override characterization runner
-    attr_accessor :characterization_runner
-
-    def register_curation_concern(*curation_concern_types)
-      Array(curation_concern_types).flatten.compact.each do |cc_type|
-        class_name = normalize_concern_name(cc_type)
-        if ! registered_curation_concern_types.include?(class_name)
-          self.registered_curation_concern_types << class_name
-        end
-      end
-    end
-
-    # Returns the class names (strings) of the registered curation concerns
-    def registered_curation_concern_types
-      @registered_curation_concern_types ||= []
-    end
-
-    # Returns the classes of the registered curation concerns
-    def curation_concerns
-      registered_curation_concern_types.map(&:constantize)
-    end
-
-    private
-
-    def normalize_concern_name(c)
-      c.to_s.camelize
-    end
-  end
-
-  configure {}
-end

data/lib/generators/curation_concerns/templates/curation_concerns_config.rb

@@ -1,2 +0,0 @@
-CurationConcerns.configure do |config|
-end

data/solr_conf/conf/solrconfig.xml

@@ -1,223 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" ?>
-<config>
-  <!-- NOTE: various comments and unused configuration possibilities have been purged
-     from this file.  Please refer to http://wiki.apache.org/solr/SolrConfigXml,
-     as well as the default solrconfig file included with Solr -->
-
-  <abortOnConfigurationError>${solr.abortOnConfigurationError:true}</abortOnConfigurationError>
-
-  <luceneMatchVersion>LUCENE_40</luceneMatchVersion>
-
-  <directoryFactory name="DirectoryFactory" class="${solr.directoryFactory:solr.StandardDirectoryFactory}"/>
-
-  <!-- solr lib dirs -->
-  <lib dir="../lib/contrib/analysis-extras/lib" />
-  <lib dir="../lib/contrib/analysis-extras/lucene-libs" />
-  <!-- for full-text indexing -->
-  <lib dir="../lib/contrib/extraction/lib" regex=".*\.jar" />
-
-  <dataDir>${solr.data.dir:}</dataDir>
-
-  <!-- The default high-performance update handler -->
-  <updateHandler class="solr.DirectUpdateHandler2">
-
-    <!-- Enables a transaction log, used for real-time get, durability, and
-         and solr cloud replica recovery.  The log can grow as big as
-         uncommitted changes to the index, so use of a hard autoCommit
-         is recommended (see below).
-         "dir" - the target directory for transaction logs, defaults to the
-                solr data directory.  -->
-    <updateLog>
-      <str name="dir">${solr.ulog.dir:}</str>
-    </updateLog>
-
-    <!-- AutoCommit
-         Perform a hard commit automatically under certain conditions.
-         Instead of enabling autoCommit, consider using "commitWithin"
-         when adding documents.
-         http://wiki.apache.org/solr/UpdateXmlMessages
-         maxDocs - Maximum number of documents to add since the last
-                   commit before automatically triggering a new commit.
-         maxTime - Maximum amount of time in ms that is allowed to pass
-                   since a document was added before automatically
-                   triggering a new commit.
-         openSearcher - if false, the commit causes recent index changes
-           to be flushed to stable storage, but does not cause a new
-           searcher to be opened to make those changes visible.
-         If the updateLog is enabled, then it's highly recommended to
-         have some sort of hard autoCommit to limit the log size.
-      -->
-     <autoCommit>
-       <maxTime>${solr.autoCommit.maxTime:15000}</maxTime>
-       <openSearcher>false</openSearcher>
-     </autoCommit>
-
-    <!-- softAutoCommit is like autoCommit except it causes a
-         'soft' commit which only ensures that changes are visible
-         but does not ensure that data is synced to disk.  This is
-         faster and more near-realtime friendly than a hard commit.
-      -->
-
-     <autoSoftCommit>
-       <maxTime>${solr.autoSoftCommit.maxTime:-1}</maxTime>
-     </autoSoftCommit>
-
-  </updateHandler>
-
-  <requestHandler name="search" class="solr.SearchHandler" default="true">
-    <!-- default values for query parameters can be specified, these
-         will be overridden by parameters in the request
-      -->
-     <lst name="defaults">
-       <str name="defType">edismax</str>
-       <str name="echoParams">explicit</str>
-       <str name="q.alt">*:*</str>
-       <str name="mm">2&lt;-1 5&lt;-2 6&lt;90%</str>
-       <int name="qs">1</int>
-       <int name="ps">2</int>
-       <float name="tie">0.01</float>
-       <!-- this qf and pf are used by default, if not otherwise specified by
-            client. The default blacklight_config will use these for the
-            "keywords" search. See the author_qf/author_pf, title_qf, etc
-            below, which the default blacklight_config will specify for
-            those searches. You may also be interested in:
-            http://wiki.apache.org/solr/LocalParams
-       -->
-        <str name="qf">
-          id
-          all_text_timv
-          active_fedora_model_ssi
-          object_type_si
-        </str>
-        <str name="pf">
-          all_text_timv^10
-        </str>
-
-       <str name="author_qf">
-       </str>
-       <str name="author_pf">
-       </str>
-       <str name="title_qf">
-       </str>
-       <str name="title_pf">
-       </str>
-       <str name="subject_qf">
-       </str>
-       <str name="subject_pf">
-       </str>
-
-       <str name="fl">
-         *,
-         score
-       </str>
-
-       <str name="facet">true</str>
-       <str name="facet.mincount">1</str>
-       <str name="facet.limit">10</str>
-       <str name="facet.field">active_fedora_model_ssi</str>
-       <str name="facet.field">object_type_si</str>
-
-       <str name="spellcheck">true</str>
-       <str name="spellcheck.dictionary">default</str>
-       <str name="spellcheck.onlyMorePopular">true</str>
-       <str name="spellcheck.extendedResults">true</str>
-       <str name="spellcheck.collate">false</str>
-       <str name="spellcheck.count">5</str>
-
-     </lst>
-    <arr name="last-components">
-      <str>spellcheck</str>
-    </arr>
-  </requestHandler>
-
-  <requestHandler name="permissions" class="solr.SearchHandler" >
-    <lst name="defaults">
-      <str name="facet">off</str>
-      <str name="echoParams">all</str>
-      <str name="rows">1</str>
-      <str name="q">{!raw f=id v=$id}</str> <!-- use id=666 instead of q=id:666 -->
-      <str name="fl">
-        id,
-        access_ssim,
-        discover_access_group_ssim,discover_access_person_ssim,
-        read_access_group_ssim,read_access_person_ssim,
-        edit_access_group_ssim,edit_access_person_ssim,
-        depositor_ti,
-        embargo_release_date_dtsi
-        inheritable_access_ssim,
-        inheritable_discover_access_group_ssim,inheritable_discover_access_person_ssim,
-        inheritable_read_access_group_ssim,inheritable_read_access_person_ssim,
-        inheritable_edit_access_group_ssim,inheritable_edit_access_person_ssim,
-        inheritable_embargo_release_date_dtsi
-      </str>
-    </lst>
-  </requestHandler>
-
-<requestHandler name="/update/extract" startup="lazy" class="org.apache.solr.handler.extraction.ExtractingRequestHandler" >
-    <lst name="defaults">
-      <!-- All the main content goes into "text"... if you need to return the extracted text or do highlighting, use a stored field. -->
-      <str name="fmap.content">text</str>
-      <str name="lowernames">true</str>
-      <str name="uprefix">ignored_</str>
-      <!-- capture link hrefs but ignore div attributes -->
-      <str name="captureAttr">true</str>
-      <str name="fmap.a">links</str>
-      <str name="fmap.div">ignored_</str>
-    </lst>
- </requestHandler>
-
-  <requestHandler name="standard" class="solr.SearchHandler">
-     <lst name="defaults">
-       <str name="echoParams">explicit</str>
-       <str name="defType">lucene</str>
-     </lst>
-  </requestHandler>
-
-  <!-- for requests to get a single document; use id=666 instead of q=id:666 -->
-  <requestHandler name="document" class="solr.SearchHandler" >
-    <lst name="defaults">
-      <str name="echoParams">all</str>
-      <str name="fl">*</str>
-      <str name="rows">1</str>
-      <str name="q">{!raw f=id v=$id}</str> <!-- use id=666 instead of q=id:666 -->
-    </lst>
-  </requestHandler>
-
-  <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
-    <str name="queryAnalyzerFieldType">textSpell</str>
-    <!-- Multiple "Spell Checkers" can be declared and used by this component
-      (e.g. for title_spell field)
-      -->
-    <lst name="spellchecker">
-      <str name="name">default</str>
-      <str name="field">spell</str>
-      <str name="spellcheckIndexDir">./spell</str>
-      <str name="buildOnOptimize">true</str>
-    </lst>
-  </searchComponent>
-
-  <requestHandler name="/replication" class="solr.ReplicationHandler" startup="lazy" />
-
-  <requestDispatcher handleSelect="true" >
-    <requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048" />
-  </requestDispatcher>
-
-  <requestHandler name="/analysis/field" startup="lazy" class="solr.FieldAnalysisRequestHandler" />
-  <requestHandler name="/update" class="solr.UpdateRequestHandler"  />
-  <requestHandler name="/admin/" class="org.apache.solr.handler.admin.AdminHandlers" />
-
-  <requestHandler name="/admin/ping" class="solr.PingRequestHandler">
-    <lst name="invariants">
-      <str name="q">solrpingquery</str>
-    </lst>
-    <lst name="defaults">
-      <str name="echoParams">all</str>
-    </lst>
-  </requestHandler>
-
-  <!-- config for the admin interface -->
-  <admin>
-    <defaultQuery>search</defaultQuery>
-  </admin>
-
-</config>

data/spec/abilities/generic_file_abilities_spec.rb

@@ -1,62 +0,0 @@
-require 'spec_helper'
-require "cancan/matchers"
-
-describe "User" do
-  describe "Abilities" do
-    subject { ability }
-    let(:ability) { Ability.new(current_user) }
-    let(:visibility) { Hydra::AccessControls::AccessRight::VISIBILITY_TEXT_VALUE_PRIVATE }
-    let(:creating_user) { FactoryGirl.create(:user) }
-    let(:user) { FactoryGirl.create(:user) }
-    let(:current_user) { user }
-    let(:generic_work) {  FactoryGirl.create(:generic_work, visibility: visibility, user:creating_user) }
-    let(:generic_file) {  FactoryGirl.create(:generic_file, visibility: visibility, user:creating_user) }
-
-    describe 'without embargo' do
-      describe 'creator of object' do
-        let(:creating_user) { user }
-        let(:current_user) { user }
-        it {
-          should be_able_to(:create, GenericFile.new)
-          should be_able_to(:read, generic_file)
-          should be_able_to(:update, generic_file)
-          should_not be_able_to(:delete, generic_file)
-        }
-      end
-
-      describe 'as a repository manager' do
-        let(:manager_user) { FactoryGirl.create(:admin) }
-        let(:creating_user) { user }
-        let(:current_user) { manager_user }
-        it {
-          should be_able_to(:create, ::GenericFile.new)
-          should be_able_to(:read, generic_file)
-          should be_able_to(:update, generic_file)
-          should be_able_to(:destroy, generic_file)
-        }
-      end
-
-      describe 'another authenticated user' do
-        let(:creating_user) { FactoryGirl.create(:user) }
-        let(:current_user) { user }
-        it {
-          should be_able_to(:create, ::GenericFile.new)
-          should_not be_able_to(:read, generic_file)
-          should_not be_able_to(:update, generic_file)
-          should_not be_able_to(:delete, generic_file)
-        }
-      end
-
-      describe 'a nil user' do
-        let(:creating_user) { FactoryGirl.create(:user) }
-        let(:current_user) { nil }
-        it {
-          should_not be_able_to(:create, GenericFile.new)
-          should_not be_able_to(:read, generic_file)
-          should_not be_able_to(:update, generic_file)
-          should_not be_able_to(:delete, generic_file)
-        }
-      end
-    end
-  end
-end

data/spec/actors/curation_concerns/generic_file_actor_spec.rb

@@ -1,116 +0,0 @@
-require 'spec_helper'
-
-describe CurationConcerns::GenericFileActor do
-  include ActionDispatch::TestProcess
-
-  let(:user) { FactoryGirl.create(:user) }
-  let(:generic_file) { FactoryGirl.create(:generic_file) }
-  let(:actor) { CurationConcerns::GenericFileActor.new(generic_file, user) }
-  let(:uploaded_file) { fixture_file_upload('/world.png','image/png') }
-
-  describe "creating metadata and content" do
-    let(:batch_id) { nil }
-    let(:work_id) { nil }
-    subject { generic_file.reload }
-    before do
-      allow(actor).to receive(:save_characterize_and_record_committer).and_return("true")
-      actor.create_metadata(batch_id, work_id)
-      actor.create_content(uploaded_file)
-    end
-    context "when a work_id is provided" do
-      let(:work) { FactoryGirl.create(:generic_work) }
-      let(:work_id) { work.id }
-      it "adds the generic file to the parent work" do
-        expect(subject.generic_works).to eq [work]
-        expect(work.reload.generic_files).to include(subject)
-      end
-    end
-  end
-
-  describe "#create_content" do
-    let(:deposit_message) { double('deposit message') }
-    let(:characterize_message) { double('characterize message') }
-    before do
-      allow(CurationConcerns.queue).to receive(:push)
-    end
-
-    it "uses the provided mime_type" do
-      actor.create_content(uploaded_file)
-      expect(generic_file.original_file.mime_type).to eq "image/png"
-    end
-
-    context "when generic_file.title is empty and generic_file.label is not" do
-      let(:file)       { "world.png" }
-      let(:long_name)  { "an absurdly long title that goes on way to long and messes up the display of the page which should not need to be this big in order to show this impossibly long, long, long, oh so long string" }
-      let(:short_name) { "Nice Short Name" }
-      let(:actor)      { CurationConcerns::GenericFileActor.new(generic_file, user) }
-      before do
-        allow(generic_file).to receive(:label).and_return(short_name)
-        allow(CurationConcerns.queue).to receive(:push)
-        actor.create_content(fixture_file_upload(file))
-      end
-      subject { generic_file.title }
-      it { is_expected.to eql [short_name] }
-    end
-
-    context "with two existing versions from different users" do
-
-      let(:file1)       { "world.png" }
-      let(:file2)       { "small_file.txt" }
-      let(:actor1)      { CurationConcerns::GenericFileActor.new(generic_file, user) }
-      let(:actor2)      { CurationConcerns::GenericFileActor.new(generic_file, second_user) }
-
-      let(:second_user) { FactoryGirl.find_or_create(:archivist) }
-      let(:versions)     { generic_file.original_file.versions }
-
-      before do
-        allow(CurationConcerns.queue).to receive(:push)
-        actor1.create_content(fixture_file_upload(file1))
-        actor2.create_content(fixture_file_upload(file2))
-      end
-
-      it "should have two versions" do
-        expect(versions.all.count).to eq 2
-      end
-
-      it "should have the current version" do
-        expect(CurationConcerns::VersioningService.latest_version_of(generic_file.original_file).label).to eq 'version2'
-        expect(generic_file.original_file.content).to eq fixture_file_upload(file2).read
-        expect(generic_file.original_file.mime_type).to eq "text/plain"
-        expect(generic_file.original_file.original_name).to eq file2
-      end
-
-      it "should use the first version for the object's title and label" do
-        expect(generic_file.label).to eql(file1)
-        expect(generic_file.title.first).to eql(file1)
-      end
-
-      it "should note the user for each version" do
-        expect(VersionCommitter.where(version_id: versions.first.uri).pluck(:committer_login)).to eq [user.user_key]
-        expect(VersionCommitter.where(version_id: versions.last.uri).pluck(:committer_login)).to eq [second_user.user_key]
-      end
-    end
-  end
-
-  context "when a label is already specified" do
-    let(:label)    { "test_file.png" }
-    let(:new_file) { "foo.jpg" }
-    let(:generic_file_with_label) do
-      GenericFile.new.tap do |f|
-        f.apply_depositor_metadata(user.user_key)
-        f.label = label
-      end
-    end
-    let(:actor) { CurationConcerns::GenericFileActor.new(generic_file_with_label, user)}
-
-    before do
-      allow(actor).to receive(:save_characterize_and_record_committer).and_return("true")
-      allow(Hydra::Works::UploadFileToGenericFile).to receive(:call)
-      actor.create_content(Tempfile.new(new_file))
-    end
-
-    it "will retain the object's original label" do
-      expect(generic_file_with_label.label).to eql(label)
-    end
-  end
-end