newspaper_works 0.1.0

data/spec/presenters/newspaper_works/issue_info_presenter_spec.rb

@@ -0,0 +1,51 @@
+require 'spec_helper'
+RSpec.describe NewspaperWorks::IssueInfoPresenter do
+  let(:solr_document) { SolrDocument.new(attributes) }
+  let(:attributes) do
+    {
+      'issue_id_ssi' => 'foo',
+      'issue_title_ssi' => 'bar',
+      'publication_date_dtsi' => 'baz',
+      'issue_volume_ssi' => 'quux',
+      'issue_edition_number_ssi' => '123',
+      'issue_number_ssi' => '456'
+    }
+  end
+  subject { Hyrax::NewspaperPagePresenter.new(solr_document, nil) }
+
+  describe '#issue_id' do
+    it 'returns the correct value' do
+      expect(subject.issue_id).to eq 'foo'
+    end
+  end
+
+  describe '#issue_title' do
+    it 'returns the correct value' do
+      expect(subject.issue_title).to eq 'bar'
+    end
+  end
+
+  describe '#publication_date' do
+    it 'returns the correct value' do
+      expect(subject.publication_date).to eq 'baz'
+    end
+  end
+
+  describe '#issue_volume' do
+    it 'returns the correct value' do
+      expect(subject.issue_volume).to eq 'quux'
+    end
+  end
+
+  describe '#issue_edition' do
+    it 'returns the correct value' do
+      expect(subject.issue_edition).to eq '123'
+    end
+  end
+
+  describe '#issue_number' do
+    it 'returns the correct value' do
+      expect(subject.issue_number).to eq '456'
+    end
+  end
+end

data/spec/presenters/newspaper_works/newspaper_core_presenter_spec.rb

@@ -0,0 +1,22 @@
+RSpec.shared_examples "a newspaper core presenter" do
+  let(:solr_document) { SolrDocument.new(attributes) }
+  let(:request) { double(host: 'example.org') }
+  let(:user_key) { 'a_user_key' }
+
+  let(:core_attributes) do
+    { "alternative_title" => ['There and Back Again'],
+      "issn" => '2049-3630',
+      "lccn" => '2001001114',
+      "oclcnum" => 'ocm00012345',
+      "held_by" => 'Marriott Library' }
+  end
+
+  let(:ability) { nil }
+  let(:presenter) { described_class.new(solr_document, ability, request) }
+
+  it { is_expected.to delegate_method(:alternative_title).to(:solr_document) }
+  it { is_expected.to delegate_method(:issn).to(:solr_document) }
+  it { is_expected.to delegate_method(:lccn).to(:solr_document) }
+  it { is_expected.to delegate_method(:oclcnum).to(:solr_document) }
+  it { is_expected.to delegate_method(:held_by).to(:solr_document) }
+end

data/spec/presenters/newspaper_works/persistent_url_presenter_behavior_spec.rb

@@ -0,0 +1,24 @@
+require 'spec_helper'
+
+RSpec.describe NewspaperWorks::PersistentUrlPresenterBehavior do
+  let(:request) { double(host: 'example.org') }
+  let(:solr_document) { SolrDocument.new(id: 'abc123', lccn_tesim: ['sn1234567']) }
+
+  describe '#persistent_url' do
+    let(:presenter) { Hyrax::NewspaperArticlePresenter.new(solr_document, nil, request) }
+    it 'returns nil' do
+      expect(presenter.persistent_url).to eq nil
+    end
+  end
+
+  describe '#persistent_url_attribute' do
+    let(:presenter) { Hyrax::NewspaperTitlePresenter.new(solr_document, nil, request) }
+    let(:purl_attribute) { presenter.persistent_url_attribute }
+    subject { Nokogiri::HTML(purl_attribute) }
+    it 'returns the HTML for the metadata display' do
+      expect(subject.css('dd')).not_to be_blank
+      expect(subject.css('li.attribute')).not_to be_blank
+      expect(subject.css('a').attribute('href').value).to include '/newspapers/sn1234567'
+    end
+  end
+end

data/spec/presenters/newspaper_works/place_of_publication_presenter_behavior_spec.rb

@@ -0,0 +1,17 @@
+require 'spec_helper'
+
+RSpec.describe NewspaperWorks::PlaceOfPublicationPresenterBehavior do
+  let(:pop) { 'Marysville, California, United States' }
+  let(:request) { double(host: 'example.org') }
+  let(:solr_document) do
+    SolrDocument.new(id: 'abc123',
+                     place_of_publication_label_tesim: [pop])
+  end
+
+  describe '#place_of_publication_label' do
+    let(:presenter) { Hyrax::NewspaperPagePresenter.new(solr_document, nil, request) }
+    it 'returns the value' do
+      expect(presenter.place_of_publication_label).to eq [pop]
+    end
+  end
+end

data/spec/presenters/newspaper_works/scanned_media_presenter_spec.rb

@@ -0,0 +1,18 @@
+RSpec.shared_examples "a scanned media presenter" do
+  let(:solr_document) { SolrDocument.new(attributes) }
+  let(:request) { double(host: 'example.org') }
+  let(:user_key) { 'a_user_key' }
+
+  let(:scanned_media_attributes) do
+    { "text_direction" => 'left',
+      "page_number" => '5',
+      "section" => '1' }
+  end
+
+  let(:ability) { nil }
+  let(:presenter) { described_class.new(solr_document, ability, request) }
+
+  it { is_expected.to delegate_method(:text_direction).to(:solr_document) }
+  it { is_expected.to delegate_method(:page_number).to(:solr_document) }
+  it { is_expected.to delegate_method(:section).to(:solr_document) }
+end

data/spec/presenters/newspaper_works/title_info_presenter_spec.rb

@@ -0,0 +1,23 @@
+require 'spec_helper'
+RSpec.describe NewspaperWorks::TitleInfoPresenter do
+  let(:solr_document) { SolrDocument.new(attributes) }
+  let(:attributes) do
+    {
+      'publication_id_ssi' => 'foo',
+      'publication_title_ssi' => 'bar'
+    }
+  end
+  subject { Hyrax::NewspaperPagePresenter.new(solr_document, nil) }
+
+  describe '#publication_id' do
+    it 'returns the correct value' do
+      expect(subject.publication_id).to eq 'foo'
+    end
+  end
+
+  describe '#publication_title' do
+    it 'returns the correct value' do
+      expect(subject.publication_title).to eq 'bar'
+    end
+  end
+end

data/spec/routing/route_spec.rb

@@ -0,0 +1,52 @@
+require 'spec_helper'
+
+RSpec.describe 'Routes', type: :routing do
+  routes { NewspaperWorks::Engine.routes }
+
+  describe 'Chronicling America-style routes' do
+    describe 'title' do
+      it 'routes the title url to NewspapersController#title' do
+        expect(get: '/newspapers/foo').to route_to(controller: 'newspaper_works/newspapers',
+                                                   action: 'title',
+                                                   unique_id: 'foo')
+      end
+    end
+
+    describe 'issue' do
+      it 'routes the issue url to NewspapersController#issue' do
+        expect(get: '/newspapers/foo/bar').to route_to(controller: 'newspaper_works/newspapers',
+                                                       action: 'issue',
+                                                       unique_id: 'foo',
+                                                       date: 'bar')
+      end
+    end
+
+    describe 'issue with edition' do
+      it 'routes the issue url with edition param to NewspapersController#issue' do
+        expect(get: '/newspapers/foo/bar/baz').to route_to(controller: 'newspaper_works/newspapers',
+                                                           action: 'issue',
+                                                           unique_id: 'foo',
+                                                           date: 'bar',
+                                                           edition: 'baz')
+      end
+    end
+
+    describe 'page' do
+      it 'routes the page url to NewspapersController#page' do
+        expect(get: '/newspapers/foo/bar/baz/quux').to route_to(controller: 'newspaper_works/newspapers',
+                                                                action: 'page',
+                                                                unique_id: 'foo',
+                                                                date: 'bar',
+                                                                edition: 'baz',
+                                                                page: 'quux')
+      end
+    end
+  end
+
+  describe 'newspapers_search' do
+    it 'routes to the NewspapersSearch#search page' do
+      expect(get: '/newspapers_search').to route_to(controller: 'newspaper_works/newspapers_search',
+                                                    action: 'search')
+    end
+  end
+end

data/spec/search_builders/custom_search_builder_spec.rb

@@ -0,0 +1,34 @@
+require 'spec_helper'
+RSpec.describe CustomSearchBuilder do
+  # specs for NewspaperWorks::HighlightSearchParams
+  describe 'highlight_search_params' do
+    let(:solr_parameters) { { q: 'abolition' } }
+    subject { described_class.new(solr_parameters) }
+
+    it 'is included in the default_processor_chain' do
+      expect(described_class.default_processor_chain).to include(:highlight_search_params)
+    end
+
+    before { subject.highlight_search_params(solr_parameters) }
+    it 'adds the highlight fields to solr_parameters' do
+      expect(solr_parameters[:hl]).to be_truthy
+      expect(solr_parameters[:'hl.fl']).to eq('all_text_tsimv')
+    end
+  end
+
+  # specs for NewspaperWorks::ExcludeModels
+  describe 'exclude_models' do
+    let(:solr_parameters) { { all_fields: 'prohibition' } }
+    subject { described_class.new(solr_parameters) }
+
+    it 'is included in the default_processor_chain' do
+      expect(described_class.default_processor_chain).to include(:exclude_models)
+    end
+
+    before { subject.exclude_models(solr_parameters) }
+    it 'adds the facet fields to solr_parameters' do
+      expect(solr_parameters[:fq]).to be_truthy
+      expect(solr_parameters[:fq]).to include('-human_readable_type_sim:"Newspaper Title"')
+    end
+  end
+end

data/spec/search_builders/newspaper_works/newspapers_search_builder_spec.rb

@@ -0,0 +1,33 @@
+require 'spec_helper'
+
+RSpec.describe NewspaperWorks::NewspapersSearchBuilder do
+  let(:context) { double }
+  let(:search_builder) { described_class.new(context) }
+
+  describe "#default_processor_chain" do
+    subject { search_builder.default_processor_chain }
+    it { is_expected.to include :facets_for_newspapers_search_form }
+    it { is_expected.to include :newspaper_pages_only }
+  end
+
+  describe '#facets_for_newspapers_search_form' do
+    subject { {} }
+    before do
+      allow(search_builder).to receive(:blacklight_config).and_return(CatalogController.blacklight_config)
+      search_builder.facets_for_newspapers_search_form(subject)
+    end
+
+    it 'adds the blacklight advanced search config' do
+      expect(subject["facet.field"]).to include 'genre_sim'
+      expect(subject['rows']).to eq '0'
+    end
+  end
+
+  describe '#newspaper_pages_only' do
+    subject { {} }
+    before { search_builder.newspaper_pages_only(subject) }
+    it 'adds the page limit' do
+      expect(subject[:fq]).to eq ["human_readable_type_sim:\"Newspaper Page\""]
+    end
+  end
+end

data/spec/services/hyrax/article_genre_service_spec.rb

@@ -0,0 +1,12 @@
+require 'spec_helper'
+
+RSpec.describe Hyrax::ArticleGenreService do
+  let(:service) { described_class.new }
+
+  describe "#select_active_options" do
+    it "returns active terms" do
+      active_term = ["Advertisement", "http://id.loc.gov/vocabulary/graphicMaterials/tgm000098"]
+      expect(service.select_active_options).to include(active_term)
+    end
+  end
+end

data/spec/services/hyrax/resource_types_service_spec.rb

@@ -0,0 +1,12 @@
+require 'spec_helper'
+
+RSpec.describe Hyrax::ResourceTypesService do
+  describe "injected newspaper options" do
+    subject { described_class }
+
+    it "includes newspaper and microfilm" do
+      expect(subject.label("Microfilm")).to be_truthy
+      expect(subject.label("Newspaper")).to be_truthy
+    end
+  end
+end

data/spec/services/newspaper_works/jp2_derivative_service_spec.rb

@@ -0,0 +1,62 @@
+require 'spec_helper'
+RSpec.describe NewspaperWorks::JP2DerivativeService do
+  let(:valid_file_set) do
+    file_set = FileSet.new
+    file_set.save!(validate: false)
+    file_set
+  end
+
+  let(:fixture_path) do
+    File.join(
+      NewspaperWorks::GEM_PATH, 'spec', 'fixtures', 'files'
+    )
+  end
+
+  describe "Creates JP2 derivatives" do
+    def source_image(name)
+      File.join(fixture_path, name)
+    end
+
+    def expected_path(file_set)
+      Hyrax::DerivativePath.derivative_path_for_reference(file_set, 'jp2')
+    end
+
+    def get_res(path)
+      lines = `gm identify -verbose #{path}`.lines
+      lines.select { |line| line.strip.start_with?('Geometry') }[0].strip
+    end
+
+    def check_dpi_match(orig, dest)
+      # check ppi, but skip pdf to avoid ghostscript warnings to stderr
+      expect(get_res(orig)).to eq get_res(dest) unless orig.end_with?('pdf')
+    end
+
+    def makes_jp2(filename)
+      expected = expected_path(valid_file_set)
+      expect(File.exist?(expected)).to be false
+      svc = described_class.new(valid_file_set)
+      svc.create_derivatives(source_image(filename))
+      expect(File.exist?(expected)).to be true
+      desc = `gm identify #{expected}`
+      expect(desc).to include 'JP2'
+      check_dpi_match(source_image(filename), expected)
+      svc.cleanup_derivatives
+    end
+
+    it "creates gray JP2 derivative from one-bit source" do
+      makes_jp2('page1.tiff')
+    end
+
+    it "creates gray JP2 from grayscale source" do
+      makes_jp2('lowres-gray-via-ndnp-sample.tiff')
+    end
+
+    it "creates color JP2 from color source" do
+      makes_jp2('4.1.07.tiff')
+    end
+
+    it "creates JP2 from PDF source, robust to multi-page" do
+      makes_jp2('sample-color-newsletter.pdf')
+    end
+  end
+end

data/spec/services/newspaper_works/newspaper_page_derivative_service_spec.rb

@@ -0,0 +1,125 @@
+require 'spec_helper'
+
+RSpec.describe NewspaperWorks::NewspaperPageDerivativeService do
+  let(:valid_file_set) do
+    fs = FileSet.new
+    work = NewspaperPage.new
+    work.title = ['This is a page!']
+    work.members.push(fs)
+    fs.save!(validate: false)
+    work.save!(validate: false)
+    fs
+  end
+
+  let(:unconsidered_file_set) do
+    fs = FileSet.new
+    work = NewspaperIssue.new
+    work.title = ['Hello Hello']
+    work.members.push(fs)
+    work.save!(validate: false)
+    fs.save!(validate: false)
+    fs
+  end
+
+  let(:fixture_path) do
+    File.join(
+      NewspaperWorks::GEM_PATH, 'spec', 'fixtures', 'files'
+    )
+  end
+
+  describe "core path/extension functionality" do
+    class MyDerivativeService < described_class
+      TARGET_EXT = 'jpg'.freeze
+    end
+
+    it "allows derivative service subclass to define file extension" do
+      svc = MyDerivativeService.new(valid_file_set)
+      expect(svc.class.target_ext).to eq 'jpg'
+    end
+
+    it "considers file_sets belonging to page work type" do
+      svc = MyDerivativeService.new(valid_file_set)
+      expect(svc.valid?).to eq true
+    end
+
+    it "ignores file_sets belonging to non-page work type" do
+      svc = MyDerivativeService.new(unconsidered_file_set)
+      expect(svc.valid?).to eq false
+    end
+
+    it "gets derivative path factory for file extension" do
+      svc = MyDerivativeService.new(valid_file_set)
+      svc.load_destpath
+      expected = Hyrax::DerivativePath.derivative_path_for_reference(
+        valid_file_set,
+        'jpg'
+      )
+      expected_pairtree = File.join(expected.split('/')[0..-2])
+      expect(Pathname.new(expected_pairtree)).to be_directory
+      # cleanup:
+      FileUtils.rm_rf(expected_pairtree)
+    end
+
+    it "successfully removes on cleanup_derivatives" do
+      svc = MyDerivativeService.new(valid_file_set)
+      # load destpath just makes directories
+      svc.load_destpath
+      expected = Hyrax::DerivativePath.derivative_path_for_reference(
+        valid_file_set,
+        'jpg'
+      )
+      expected_pairtree = File.join(expected.split('/')[0..-2])
+      expect(Pathname.new(expected_pairtree)).to be_directory
+      # simulate, simply touch a file with correct extension in
+      #   the derivative path made above; makes a zero-byte '.jpg' file
+      `touch #{expected}`
+      expect(File.exist?(expected)).to be true
+      svc.cleanup_derivatives
+      # no more derivative file for this extension:
+      expect(File.exist?(expected)).to be false
+      # however, we still have a directory hanging around, this is normal,
+      #   becauase any derivative service is blind to other derivatives
+      #   for the same fileset, beside the one extension each manages:
+      expect(Pathname.new(expected_pairtree)).to be_directory
+      # cleanup after test:
+      FileUtils.rm_rf(expected_pairtree)
+    end
+  end
+
+  describe "source identification" do
+    def service_for_file(name)
+      # construct a new service for each test, as there are memoized things
+      #   that make sharing problematic
+      svc = described_class.new(valid_file_set)
+      svc.instance_variable_set(:@source_path, File.join(fixture_path, name))
+      svc
+    end
+
+    it "identifies a source file using ImageMagick" do
+      expect(service_for_file('4.1.07.tiff').identify).to include 'TIFF'
+      expect(service_for_file('4.1.07.tiff').identify).to include '8-bit'
+    end
+
+    it "identifies jp2 source" do
+      # test/verify jp2 source is identified, which relies on GraphicsMagick
+      expect(service_for_file('4.1.07.jp2').identify).to include 'JP2'
+      expect(service_for_file('4.1.07.jp2').identify).to include '8-bit'
+    end
+
+    it "identifies color and gray sources" do
+      expect(service_for_file('4.1.07.tiff').use_color?).to be true
+      expect(service_for_file('page1.tiff').use_color?).to be false
+    end
+
+    it "identifies a one-bit source" do
+      # 1-bit group4 monochrome TIFF:
+      expect(service_for_file('page1.tiff').one_bit?).to be true
+      # 8-bit gray TIFF:
+      expect(
+        service_for_file('lowres-gray-via-ndnp-sample.tiff').one_bit?
+      ).to be false
+      # color TIFF:
+      expect(service_for_file('4.1.07.tif').one_bit?).to be false
+    end
+  end
+end

data/spec/services/newspaper_works/pdf_derivative_service_spec.rb

@@ -0,0 +1,62 @@
+require 'spec_helper'
+RSpec.describe NewspaperWorks::PDFDerivativeService do
+  let(:valid_file_set) do
+    file_set = FileSet.new
+    file_set.save!(validate: false)
+    file_set
+  end
+
+  let(:fixture_path) do
+    File.join(
+      NewspaperWorks::GEM_PATH, 'spec', 'fixtures', 'files'
+    )
+  end
+
+  describe "Creates PDF derivatives" do
+    def source_image(name)
+      File.join(fixture_path, name)
+    end
+
+    def expected_path(file_set)
+      Hyrax::DerivativePath.derivative_path_for_reference(file_set, 'pdf')
+    end
+
+    # given output file name, check DPI is 150
+    def check_dpi(expected)
+      desc = `gm identify #{expected}`
+      # get total width of pdf in points from identify, should be 864x == 12in
+      page_width = 864
+      expect(desc).to include "#{page_width}x"
+      # get total width of image in pixels from pdfimages -list, ==> 1800
+      image_width = 1800
+      im_list = `pdfimages -list #{expected}`
+      expect(im_list.lines[-1].split(' ')[3]).to eq image_width.to_s
+      # this combination of page pt width, image px width ==> 150ppi
+      expect(image_width / (page_width / 72.0)).to eq 150.0
+    end
+
+    def makes_pdf(filename)
+      expected = expected_path(valid_file_set)
+      expect(File.exist?(expected)).to be false
+      svc = described_class.new(valid_file_set)
+      svc.create_derivatives(source_image(filename))
+      expect(File.exist?(expected)).to be true
+      desc = `gm identify #{expected}`
+      expect(desc).to include 'PDF'
+      check_dpi(expected)
+      svc.cleanup_derivatives
+    end
+
+    it "creates gray PDF derivative from one-bit source" do
+      makes_pdf('page1.tiff')
+    end
+
+    it "creates gray PDF from grayscale source" do
+      makes_pdf('lowres-gray-via-ndnp-sample.tiff')
+    end
+
+    it "creates color PDF from color source" do
+      makes_pdf('4.1.07.tiff')
+    end
+  end
+end