Try to create resource_page_url for libguides databases

- This is not exposed in their API, and is somehow built from the title of the resource, but does not seem to be consistent.

Connected to #829

app/models/web_database_list/database.rb

@@ -11,13 +11,17 @@ def initialize(json)
   def to_csv_row
     row = CSV::Row.new([], [])
     self.class.field_names.each do |field|
-      row << [field, instance_variable_get("@#{field}")]
+      row << [field, send(field)]
     end
     row
   end
 
   def self.field_names
-    [:id, :name, :description, :alt_names, :url, :friendly_url, :subjects]
+    [:id, :name, :description, :alt_names, :url, :friendly_url, :subjects, :resource_page_url]
+  end
+
+  def resource_page_url
+    @resource_page_url ||= URI::HTTPS.build(host: 'libguides.princeton.edu', path: "/az/#{name_to_path}").to_s
   end
 
   private
@@ -35,4 +39,9 @@ def parse(json)
                   ''
                 end
   end
+
+  def name_to_path
+    first_title = name.split(/\; /).first
+    first_title.tr('^a-zA-Z0-9 ', '').downcase.split(' ').join('-')
+  end
 end

spec/fixtures/files/libguides_databases.json

@@ -186,5 +186,48 @@
     "internal_note": "",
     "library_review": "",
     "alt_names": "Deutsche Literatur des 18. Jahrhunderts Online; Eighteenth Century German Literature Online"
+  },
+  {
+    "id": "74881720",
+    "name": "Chosŏn ŏllon chŏngbo kiji",
+    "description": "Chosŏn ŏllon chŏngbo kiji is a full-text database of North Korean newspapers and periodicals: 5 major newspapers (4 in Korean and 1 in English), 20+ periodicals in humanities and social science, 40+ periodicals in science and medicines.",
+    "url": "https://dprkmedia.com/",
+    "site_id": "77",
+    "type_id": "10",
+    "owner_id": "231",
+    "az_vendor_id": "0",
+    "meta": {
+      "target": "0",
+      "enable_proxy": "1",
+      "tn_url": "",
+      "tn_height": "",
+      "tn_width": "",
+      "tn_alt_text": "",
+      "more_info": "",
+      "desc_pos": "1"
+    },
+    "created": "2014-06-13 02:57:45",
+    "updated": "2023-01-25 17:29:18",
+    "slug_id": "74881720",
+    "enable_hidden": "0",
+    "az_vendor_name": null,
+    "subjects": [
+      {
+        "id": "74881720",
+        "site_id": "77",
+        "parent_id": "0",
+        "name": "Korean Studies",
+        "ordering": "0",
+        "slug_id": "74881720",
+        "subject_id": "74881720",
+        "content_id": "74881720",
+        "featured": "0",
+        "content_id_count": "1"
+      }
+    ],
+    "friendly_url": "https://libguides.princeton.edu/resource/74881720",
+    "internal_note": "",
+    "library_review": "",
+    "alt_names": ""
   }
 ]

spec/models/web_database_list/database_spec.rb

@@ -21,27 +21,45 @@
     end
     it 'retrieves the alt_names, if present, from the provided json' do
       expect(databases.first.alt_names).to eq(nil)
-      expect(databases.last.alt_names).to eq('Deutsche Literatur des 18. Jahrhunderts Online; Eighteenth Century German Literature Online')
+      expect(databases.fifth.alt_names).to eq('Deutsche Literatur des 18. Jahrhunderts Online; Eighteenth Century German Literature Online')
     end
     it 'retrieves the url from the provided json' do
       expect(databases.third.url).to eq('http://aabd.chadwyck.com/')
     end
     it 'retrieves the friendly_url, if present, from the provided json' do
       expect(databases.fourth.friendly_url).to eq(nil)
-      expect(databases.last.friendly_url).to eq('https://libguides.princeton.edu/resource/4856')
+      expect(databases.fifth.friendly_url).to eq('https://libguides.princeton.edu/resource/4856')
     end
     it 'retrieves the subjects and concatenates them into a string' do
       expect(databases.second.subjects).to eq('African Studies')
       expect(databases.third.subjects).to eq('African American Studies;Biographical Sources')
       expect(databases.fourth.subjects).to eq('')
     end
+    describe '#resource_page_url' do
+      it 'generates a resource page url from the title' do
+        expect(databases.first.resource_page_url).to eq('https://libguides.princeton.edu/az/africa-knowledge-project')
+      end
+
+      it 'removes non A-Z/0-9 characters' do
+        expect(databases.second.resource_page_url).to eq('https://libguides.princeton.edu/az/africabiborg-africana-periodical-literature')
+      end
+
+      it 'only uses the first part of title with translations' do
+        expect(databases.fifth.resource_page_url).to eq('https://libguides.princeton.edu/az/18th-century-german-literature-online')
+      end
+
+      it 'uses unaccented characters' do
+        pending('libguides making sense-it randomly removes a word from the title')
+        expect(databases[5].resource_page_url).to eq('https://libguides.princeton.edu/az/choson-ollon-kiji')
+      end
+    end
   end
 
   describe '#to_csv_row' do
     it 'creates a CSV::Row with the correct content' do
       expect(databases.second.to_csv_row).to eq(
         CSV::Row.new(
-          [:id, :name, :description, :alt_names, :url, :friendly_url, :subjects],
+          [:id, :name, :description, :alt_names, :url, :friendly_url, :subjects, :resource_page_url],
           ['2938717',
            'AfricaBib.org: Africana Periodical Literature',
            'Free index to articles on a wide range of topics relating to all countries in Africa.   Some of the databases included '\
@@ -51,7 +69,8 @@
            nil,
            'http://www.africabib.org/perio.htm',
            'https://libguides.princeton.edu/resource/11553',
-           'African Studies']
+           'African Studies',
+           'https://libguides.princeton.edu/az/africabiborg-africana-periodical-literature']
         )
       )
     end

spec/models/web_database_list/databases_feed_spec.rb

@@ -14,7 +14,8 @@
        nil,
        'http://www.africaknowledgeproject.org',
        'https://libguides.princeton.edu/resource/5014',
-       'African Studies']
+       'African Studies',
+       'https://libguides.princeton.edu/az/africa-knowledge-project']
     end
     let(:feed) do
       database_list = JSON.parse(File.read(file_fixture('libguides_databases.json')))
@@ -34,7 +35,7 @@
 
     it 'the CSV file has a header row and one row for each database' do
       feed.run
-      expect(CSV.read(filename).length).to eq(5)
+      expect(CSV.read(filename).length).to eq(6)
     end
 
     it 'the first row of data is correct' do