Add a way to try interesting objects in development and test

README.md

@@ -44,7 +44,10 @@ Start the rails app
 
 ## Getting data in development
 
-Once you have Solr running you can load fixture data using `rake searchworks:fixtures`
+Once you have Solr running you can load fixture data using `bin/rails searchworks:fixtures`
+We have included fixture files in the `spec/fixtures/solr_documents` directory.
+
+If you want to add other documents you can add the identifiers into `FixtureHarvester`. This will download more yml files to the fixture folder. Run `bin/rails searchworks:fixtures` again to reindex.  Please submit your changes and the new yaml files via a pull request. Please use this judiciously as adding many fixtures may add unnecessary complexity and size to the codebase.
 
 ## "Logging in" as a User in development
 

app/services/fixture_harvester.rb

@@ -0,0 +1,33 @@
+# Harvests some fixture data from production and stores it in yaml files.
+# Usage:
+#   bin/rails runner "FixtureHarvester.harvest_all"
+#
+# You can then load the yaml into solr using `rake searchworks:fixtures'
+class FixtureHarvester
+  FIXTURES = [
+    '5488000', # Bound with parent
+    '2279186', # Bound with (no Folio items) (TODO: merge with 20 or 23?)
+    '14136548', # Online resource (no Folio items)
+    '4085072', # A collection of images (TODO: merge with 24?)
+    '13553090', # A uniform title (dotdotdotdot)
+    '2472159' # one hrid for multiple purl images (TODO: merge with 8923346, 20, or 23?)
+  ].freeze
+
+  def self.harvest_all
+    FIXTURES.each { |id| harvest(id) }
+  end
+
+  def self.harvest(id)
+    response = conn.get("#{id}.json")
+    yaml = response.body.dig('response', 'document').except('_version_').to_yaml
+    File.write("spec/fixtures/solr_documents/#{id}.yml", yaml)
+  end
+
+  def self.conn
+    Faraday.new 'https://searchworks.stanford.edu/view/' do |conn|
+      conn.response :json, content_type: /\bjson$/
+
+      conn.adapter Faraday.default_adapter
+    end
+  end
+end

lib/fixtures_indexer.rb

@@ -7,6 +7,18 @@ class FixturesIndexer
   include MarcMetadataFixtures
   include ModsFixtures
 
+  # marc_json_struct and folio_json_struct are explicitly not included here
+  STRUCT_KEYS = [
+    "works_struct",
+    "author_struct",
+    "marc_links_struct",
+    "summary_struct",
+    "uniform_title_display_struct",
+    "holdings_json_struct",
+    "toc_struct",
+    "item_display_struct"
+  ].freeze
+
   def self.run
     FixturesIndexer.new.run
   end
@@ -41,6 +53,10 @@ def fixtures
       rendered_template = fixture_template.result(binding)
       data = YAML::load rendered_template
       data[:item_display_struct] &&= data[:item_display_struct].map(&:to_json)
+      STRUCT_KEYS.each do |key|
+        data[key] &&= data[key].map(&:to_json)
+      end
+
       data
     end
   end

spec/features/access_points/government_documents_spec.rb

@@ -25,6 +25,6 @@
       expect(page).to have_css('.filter-value', text: 'Government document')
     end
 
-    expect(total_results).to eq 2
+    expect(total_results).to eq 4
   end
 end

spec/features/alternate_catalog_spec.rb

@@ -47,8 +47,8 @@
     wait_for_ajax
     within '.alternate-catalog' do
       expect(page).to have_css 'h3', text: 'Your search also found results in'
-      expect(page).to have_css 'a.btn', text: 'See 31 catalog results'
-      expect(page).to have_css 'a[href="/catalog?q=1%2A&f[format_main_ssim][]=Book"]', text: 'Book (10)'
+      expect(page).to have_css 'a.btn', text: 'See 37 catalog results'
+      expect(page).to have_css 'a[href="/catalog?q=1%2A&f[format_main_ssim][]=Book"]', text: 'Book (13)'
       expect(page).to have_css 'a[href="/catalog?q=1%2A&f[format_main_ssim][]=Image"]', text: 'Image (7)'
       expect(page).to have_css 'a[href="/catalog?q=1%2A&f[format_main_ssim][]=Database"]', text: 'Database (5)'
       expect(page).to have_css 'a[href="/catalog?q=1%2A&f[format_main_ssim][]=Newspaper"]', text: 'Newspaper (4)'

spec/features/rss_feed_spec.rb

@@ -12,7 +12,7 @@
     end
   end
 
-  it 'sorts the new books feed by the data cataloged field' do
+  it 'sorts the new books feed by the date_cataloged field' do
     within('.search_num_of_results') do
       click_link 'RSS feed for this result'
     end