commonmeta-ruby 3.7.3 → 3.8.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: e3a1f9e1a7b45f6e17fefa1733d0d5e7bf7de101ce8105cd52476807aadcdedc
-  data.tar.gz: '086ce7969801a3818fa130b91d62f8d4fc87419ceb5bc0080f2ff53dfcc124bb'
+  metadata.gz: acaeef11b787265fa53f7997c4d6d8d4942f786eb633b1b32df5e0d09b5752a6
+  data.tar.gz: 675258b94dc8cc1bbb327f88f7ae7b86b104af5d27b9c44d74172630d1bf6ed7
 SHA512:
-  metadata.gz: 4fc08586e8d3f110cc9c78e846c760021fff2a40cf4f956db5aa6ff22b0601aaf26c83a774188f5563296ab12bb2314c594bde4e524cd4d01dddd180ce301a0e
-  data.tar.gz: e670c12e402babbbcd01efe1deefbbcf3e61bda8060ae878dd0a90ea77e1895e7ba77b02a403b5537449129dadf380569de749e6c78c022cda2cffdaf3a107fe
+  metadata.gz: 1eab3f0ee1f997259b8c9b0e0aa9d3458277ca41b81e67013153fb65bbfaed149b35548866728d8c26d5f9c2b71dc6935a8d69a25c91b62ceca3896445920af0
+  data.tar.gz: 2d725b722aee5c0829ec8e5d037f83c3939acf138aa4b312ed3c417772ff8e327ca32ea638493b73151f011417231a49bb91f5d0d176e9544f8a0b4599aa4ea4

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    commonmeta-ruby (3.7.3)
+    commonmeta-ruby (3.8.0)
       activesupport (>= 4.2.5, < 8.0)
       addressable (~> 2.8.1, < 2.8.2)
       base32-url (>= 0.7.0, < 1)
@@ -44,8 +44,9 @@ GEM
       uuidtools (~> 2.1, >= 2.1.5)
     base64 (0.2.0)
     bcp47_spec (0.2.1)
-    bibtex-ruby (6.0.0)
+    bibtex-ruby (6.1.0)
       latex-decode (~> 0.0)
+      racc (~> 1.7)
     bigdecimal (3.1.5)
     builder (3.2.4)
     citeproc (1.0.10)
@@ -67,7 +68,7 @@ GEM
       csl (~> 2.0)
     diff-lcs (1.5.0)
     docile (1.4.0)
-    domain_name (0.6.20231109)
+    domain_name (0.6.20240107)
     drb (2.2.0)
       ruby2_keywords
     ebnf (2.5.0)
@@ -135,13 +136,13 @@ GEM
     multi_json (1.15.0)
     mutex_m (0.2.0)
     namae (1.1.1)
-    nokogiri (1.15.5-arm64-darwin)
+    nokogiri (1.16.0-arm64-darwin)
       racc (~> 1.4)
     oj (3.16.3)
       bigdecimal (>= 3.0)
     optimist (3.1.0)
     parallel (1.24.0)
-    parser (3.2.2.4)
+    parser (3.3.0.2)
       ast (~> 2.4.1)
       racc
     postrank-uri (1.1)
@@ -171,7 +172,7 @@ GEM
     rdf-xsd (3.3.0)
       rdf (~> 3.3)
       rexml (~> 3.2)
-    regexp_parser (2.8.3)
+    regexp_parser (2.9.0)
     rexml (3.2.6)
     rspec (3.12.0)
       rspec-core (~> 3.12.0)
@@ -202,16 +203,16 @@ GEM
       unicode-display_width (>= 2.4.0, < 3.0)
     rubocop-ast (1.30.0)
       parser (>= 3.2.1.0)
-    rubocop-capybara (2.19.0)
+    rubocop-capybara (2.20.0)
       rubocop (~> 1.41)
-    rubocop-factory_bot (2.24.0)
-      rubocop (~> 1.33)
-    rubocop-performance (1.20.1)
+    rubocop-factory_bot (2.25.1)
+      rubocop (~> 1.41)
+    rubocop-performance (1.20.2)
       rubocop (>= 1.48.1, < 2.0)
       rubocop-ast (>= 1.30.0, < 2.0)
     rubocop-rake (0.6.0)
       rubocop (~> 1.0)
-    rubocop-rspec (2.25.0)
+    rubocop-rspec (2.26.1)
       rubocop (~> 1.40)
       rubocop-capybara (~> 2.17)
       rubocop-factory_bot (~> 2.22)

data/lib/commonmeta/crossref_utils.rb

@@ -342,11 +342,17 @@ module Commonmeta
       return xml if doi_from_url(id).blank? || url.blank?
 
       xml.doi_data do
-        xml.doi(doi_from_url(id).downcase)
+        doi = doi_from_url(id).downcase
+        xml.doi(doi)
         xml.resource(url)
         xml.collection("property" => "text-mining") do
           xml.item do
             xml.resource(url, "mime_type" => "text/html")
+            if is_rogue_scholar_doi?(doi)
+              Array.wrap(files).each do |file|
+                xml.resource(file["url"], "mime_type" => file["mimeType"])
+              end
+            end
           end
         end
       end

data/lib/commonmeta/doi_utils.rb

@@ -77,5 +77,10 @@ module Commonmeta
 
       { 'id' => "https://api.crossref.org/members/#{member_id}", 'name' => name }
     end
+
+    def is_rogue_scholar_doi?(doi)
+      prefix = validate_prefix(doi)
+      %w[10.34732 10.53731 10.54900 10.57689 10.59348 10.59349 10.59350].include?(prefix)
+    end
   end
 end

data/lib/commonmeta/metadata.rb

@@ -1,6 +1,6 @@
 # frozen_string_literal: truefiles
 
-require_relative 'metadata_utils'
+require_relative "metadata_utils"
 
 module Commonmeta
   class Metadata
@@ -10,7 +10,11 @@ module Commonmeta
                   :email, :registrant
     attr_reader :doc, :page_start, :page_end
     attr_writer :id, :provider_id, :client_id, :doi, :alternate_identifiers, :contributors,
-                :titles, :publisher, :license, :date, :volume, :url, :version, :subjects, :descriptions, :language, :sizes, :formats, :schema_version, :meta, :container, :provider, :format, :funding_references, :state, :geo_locations, :type, :additional_type, :files, :references, :related_identifiers, :related_items, :style, :locale, :archive_locations
+                :titles, :publisher, :license, :date, :volume, :url, :version, :subjects, 
+                :descriptions, :language, :sizes, :formats, :schema_version, :meta, :container, 
+                :provider, :format, :funding_references, :state, :geo_locations, :type, 
+                :additional_type, :files, :references, :related_identifiers, :related_items, 
+                :style, :locale, :archive_locations
 
     def initialize(options = {})
       options.symbolize_keys!
@@ -23,29 +27,29 @@ module Commonmeta
 
         # mEDRA, KISTI, JaLC and OP DOIs are found in the Crossref index
         case @from
-        when 'medra'
-          ra = 'mEDRA'
-        when 'kisti'
-          ra = 'KISTI'
-        when 'jalc'
-          ra = 'JaLC'
-        when 'op'
-          ra = 'OP'
+        when "medra"
+          ra = "mEDRA"
+        when "kisti"
+          ra = "KISTI"
+        when "jalc"
+          ra = "JaLC"
+        when "op"
+          ra = "OP"
         end
 
         # generate name for method to call dynamically
         hsh = @from.present? ? send("get_#{@from}", id: id, **options) : {}
-        string = hsh.fetch('string', nil)
+        string = hsh.fetch("string", nil)
       elsif options[:input].present? && File.exist?(options[:input])
         filename = File.basename(options[:input])
         ext = File.extname(options[:input])
         if %w[.bib .ris .xml .json .cff].include?(ext)
           hsh = {
-            'url' => options[:url],
-            'state' => options[:state],
-            'provider_id' => options[:provider_id],
-            'client_id' => options[:client_id],
-            'files' => options[:files]
+            "url" => options[:url],
+            "state" => options[:state],
+            "provider_id" => options[:provider_id],
+            "client_id" => options[:client_id],
+            "files" => options[:files],
           }
           string = File.read(options[:input])
           @from = options[:from] || find_from_format(string: string, ext: ext)
@@ -55,14 +59,14 @@ module Commonmeta
         end
       else
         hsh = {
-          'url' => options[:url],
-          'state' => options[:state],
-          'provider_id' => options[:provider_id],
-          'client_id' => options[:client_id],
-          'files' => options[:files],
-          'contributors' => options[:contributors],
-          'titles' => options[:titles],
-          'publisher' => options[:publisher]
+          "url" => options[:url],
+          "state" => options[:state],
+          "provider_id" => options[:provider_id],
+          "client_id" => options[:client_id],
+          "files" => options[:files],
+          "contributors" => options[:contributors],
+          "titles" => options[:titles],
+          "publisher" => options[:publisher],
         }
         string = options[:input]
         @from = options[:from] || find_from_format(string: string)
@@ -70,7 +74,7 @@ module Commonmeta
 
       # make sure input is encoded as utf8
       if string.present? && string.is_a?(String)
-        dup_string = string.dup.force_encoding('UTF-8').encode!
+        dup_string = string.dup.force_encoding("UTF-8").encode!
       end
       @string = dup_string
 
@@ -81,11 +85,11 @@ module Commonmeta
       @sandbox = options[:sandbox]
 
       # options that come from the datacite database
-      @url = hsh.to_h['url'].presence || options[:url].presence
-      @state = hsh.to_h['state'].presence
-      @provider_id = hsh.to_h['provider_id'].presence
-      @client_id = hsh.to_h['client_id'].presence
-      @files = hsh.to_h['files'].presence
+      @url = hsh.to_h["url"].presence || options[:url].presence
+      @state = hsh.to_h["state"].presence
+      @provider_id = hsh.to_h["provider_id"].presence
+      @client_id = hsh.to_h["client_id"].presence
+      @files = hsh.to_h["files"].presence
 
       # options that come from the cli, needed
       # for crossref doi registration
@@ -125,23 +129,23 @@ module Commonmeta
     end
 
     def id
-      @id ||= meta.fetch('id', nil)
+      @id ||= meta.fetch("id", nil)
     end
 
     def doi
-      @doi ||= meta.fetch('doi', nil)
+      @doi ||= meta.fetch("doi", nil)
     end
 
     def provider_id
-      @provider_id ||= meta.fetch('provider_id', nil)
+      @provider_id ||= meta.fetch("provider_id", nil)
     end
 
     def client_id
-      @client_id ||= meta.fetch('client_id', nil)
+      @client_id ||= meta.fetch("client_id", nil)
     end
 
     def exists?
-      (@state || meta.fetch('state', nil)) != 'not_found'
+      (@state || meta.fetch("state", nil)) != "not_found"
     end
 
     def valid?
@@ -151,111 +155,111 @@ module Commonmeta
     # Catch errors in the reader
     # Then validate against JSON schema for Commonmeta
     def errors
-      meta.fetch('errors', nil) || json_schema_errors
+      meta.fetch("errors", nil) || json_schema_errors
     end
 
     def descriptions
-      @descriptions ||= meta.fetch('descriptions', nil)
+      @descriptions ||= meta.fetch("descriptions", nil)
     end
 
     def license
-      @license ||= meta.fetch('license', nil)
+      @license ||= meta.fetch("license", nil)
     end
 
     def subjects
-      @subjects ||= meta.fetch('subjects', nil)
+      @subjects ||= meta.fetch("subjects", nil)
     end
 
     def language
-      @language ||= meta.fetch('language', nil)
+      @language ||= meta.fetch("language", nil)
     end
 
     def sizes
-      @sizes ||= meta.fetch('sizes', nil)
+      @sizes ||= meta.fetch("sizes", nil)
     end
 
     def formats
-      @formats ||= meta.fetch('formats', nil)
+      @formats ||= meta.fetch("formats", nil)
     end
 
     def schema_version
-      @schema_version ||= meta.fetch('schema_version', nil)
+      @schema_version ||= meta.fetch("schema_version", nil)
     end
 
     def funding_references
-      @funding_references ||= meta.fetch('funding_references', nil)
+      @funding_references ||= meta.fetch("funding_references", nil)
     end
 
     def references
-      @references ||= meta.fetch('references', nil)
+      @references ||= meta.fetch("references", nil)
     end
 
     def related_identifiers
-      @related_identifiers ||= meta.fetch('related_identifiers', nil)
+      @related_identifiers ||= meta.fetch("related_identifiers", nil)
     end
 
     def related_items
-      @related_items ||= meta.fetch('related_items', nil)
+      @related_items ||= meta.fetch("related_items", nil)
     end
 
     def url
-      @url ||= meta.fetch('url', nil)
+      @url ||= meta.fetch("url", nil)
     end
 
     def version
-      @version ||= meta.fetch('version', nil)
+      @version ||= meta.fetch("version", nil)
     end
 
     def container
-      @container ||= meta.fetch('container', nil)
+      @container ||= meta.fetch("container", nil)
     end
 
     def geo_locations
-      @geo_locations ||= meta.fetch('geo_locations', nil)
+      @geo_locations ||= meta.fetch("geo_locations", nil)
     end
 
     def date
-      @date ||= meta.fetch('date', nil)
+      @date ||= meta.fetch("date", nil)
     end
 
     def publisher
-      @publisher ||= meta.fetch('publisher', nil)
+      @publisher ||= meta.fetch("publisher", nil)
     end
 
     def alternate_identifiers
-      @alternate_identifiers ||= meta.fetch('alternate_identifiers', nil)
+      @alternate_identifiers ||= meta.fetch("alternate_identifiers", nil)
     end
 
     def files
-      @files ||= meta.fetch('files', nil)
+      @files ||= meta.fetch("files", nil)
     end
 
     def provider
-      @provider ||= meta.fetch('provider', nil)
+      @provider ||= meta.fetch("provider", nil)
     end
 
     def state
-      @state ||= meta.fetch('state', nil)
+      @state ||= meta.fetch("state", nil)
     end
 
     def type
-      @type ||= meta.fetch('type', nil)
+      @type ||= meta.fetch("type", nil)
     end
 
     def additional_type
-      @additional_type ||= meta.fetch('additional_type', nil)
+      @additional_type ||= meta.fetch("additional_type", nil)
     end
 
     def titles
-      @titles ||= meta.fetch('titles', nil)
+      @titles ||= meta.fetch("titles", nil)
     end
 
     def contributors
-      @contributors ||= meta.fetch('contributors', nil)
+      @contributors ||= meta.fetch("contributors", nil)
     end
 
     def archive_locations
-      @archive_locations ||= meta.fetch('archive_locations', nil)
+      @archive_locations ||= meta.fetch("archive_locations", nil)
     end
   end
 end

data/lib/commonmeta/readers/json_feed_reader.rb

@@ -69,7 +69,7 @@ module Commonmeta
         funding_references = get_funding_references(meta)
         related_identifiers = get_related_identifiers(meta)
         alternate_identifiers = [{ "alternateIdentifier" => meta["id"], "alternateIdentifierType" => "UUID" }]
-        
+        files = get_files(id)
         archive_url = meta.fetch("archive_url", nil)
 
         if archive_url
@@ -99,10 +99,20 @@ module Commonmeta
           "funding_references" => funding_references.presence,
           "related_identifiers" => related_identifiers.presence,
           "alternate_identifiers" => alternate_identifiers,
+          "files" => files.presence,
           "archive_locations" => archive_locations,
           "state" => state }.compact.merge(read_options)
       end
 
+      def get_files(id)
+        doi = doi_from_url(id)
+        return nil unless is_rogue_scholar_doi?(doi)
+          
+        [{ "mimeType" => "text/markdown", "url" => "https://api.rogue-scholar.org/posts/#{doi}.md" },
+         { "mimeType" => "application/pdf", "url" => "https://api.rogue-scholar.org/posts/#{doi}.pdf" },
+         { "mimeType" => "application/epub+zip", "url" => "https://api.rogue-scholar.org/posts/#{doi}.epub" }]
+      end
+
       def get_references(meta)
         # check that references resolve
         Array.wrap(meta["reference"]).reduce([]) do |sum, reference|

data/lib/commonmeta/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Commonmeta
-  VERSION = '3.7.3'
+  VERSION = '3.8.0'
 end

data/spec/doi_utils_spec.rb

@@ -315,4 +315,18 @@ describe Commonmeta::Metadata, vcr: true do
       expect(response).to eq('10.5061')
     end
   end
+
+  context 'is_rogue_scholar_doi' do
+    it 'rogue scholar doi' do
+      doi = '10.53731/cjx855h-hn5jtq8'
+      response = subject.is_rogue_scholar_doi?(doi)
+      expect(response).to be true
+    end
+
+    it 'not a rogue scholar doi' do
+      doi = '10.1371/journal.pone.0000030'
+      response = subject.is_rogue_scholar_doi?(doi)
+      expect(response).to be false
+    end
+  end
 end

data/spec/readers/json_feed_reader_spec.rb

@@ -36,6 +36,8 @@ describe Commonmeta::Metadata, vcr: true do
       # expect(subject.valid?).to be true
       expect(subject.id).to eq("https://doi.org/10.53731/4nwxn-frt36")
       expect(subject.url).to eq("https://blog.front-matter.io/posts/does-it-compose")
+      expect(subject.files.length).to eq(3)
+      expect(subject.files[1]).to eq("mimeType" => "application/pdf", "url" => "https://api.rogue-scholar.org/posts/10.53731/4nwxn-frt36.pdf")
       expect(subject.alternate_identifiers).to eq([{ "alternateIdentifier" => "5bb66e92-5cb9-4659-8aca-20e486b695c9", "alternateIdentifierType" => "UUID" }])
       expect(subject.type).to eq("Article")
       expect(subject.contributors.length).to eq(1)
@@ -60,6 +62,8 @@ describe Commonmeta::Metadata, vcr: true do
       # expect(subject.valid?).to be true
       expect(subject.id).to eq("https://doi.org/10.53731/r79v4e1-97aq74v-ag578")
       expect(subject.url).to eq("https://blog.front-matter.io/posts/differences-between-orcid-and-datacite-metadata")
+      expect(subject.files.length).to eq(3)
+      expect(subject.files[1]).to eq("mimeType" => "application/pdf", "url" => "https://api.rogue-scholar.org/posts/10.53731/r79v4e1-97aq74v-ag578.pdf")
       expect(subject.alternate_identifiers).to eq([{ "alternateIdentifier" => "8a4de443-3347-4b82-b57d-e3c82b6485fc", "alternateIdentifierType" => "UUID" }])
       expect(subject.type).to eq("Article")
       expect(subject.contributors.length).to eq(1)
@@ -85,6 +89,8 @@ describe Commonmeta::Metadata, vcr: true do
       # expect(subject.valid?).to be true
       expect(subject.id).to eq("https://doi.org/10.53731/r294649-6f79289-8cw18")
       expect(subject.url).to eq("https://blog.front-matter.io/posts/nine-simple-ways-to-make-it-easier-to-re-use-your-data")
+      expect(subject.files.length).to eq(3)
+      expect(subject.files[1]).to eq("mimeType" => "application/pdf", "url" => "https://api.rogue-scholar.org/posts/10.53731/r294649-6f79289-8cw18.pdf")
       expect(subject.alternate_identifiers).to eq([{ "alternateIdentifier" => "2bdebfc5-e02e-42c2-90c5-e873e2d0435d", "alternateIdentifierType" => "UUID" }])
       expect(subject.type).to eq("Article")
       expect(subject.contributors.length).to eq(1)
@@ -110,6 +116,8 @@ describe Commonmeta::Metadata, vcr: true do
       # expect(subject.valid?).to be true
       expect(subject.id).to eq("https://doi.org/10.53731/r79s4nh-97aq74v-ag4t1")
       expect(subject.url).to eq("https://blog.front-matter.io/posts/tracking-the-growth-of-the-pid-graph")
+      expect(subject.files.length).to eq(3)
+      expect(subject.files[1]).to eq("mimeType" => "application/pdf", "url" => "https://api.rogue-scholar.org/posts/10.53731/r79s4nh-97aq74v-ag4t1.pdf")
       expect(subject.alternate_identifiers).to eq([{ "alternateIdentifier" => "e58dc9c8-b870-4db2-8896-238b3246c551", "alternateIdentifierType" => "UUID" }])
       expect(subject.type).to eq("Article")
       expect(subject.contributors.length).to eq(1)
@@ -187,6 +195,8 @@ describe Commonmeta::Metadata, vcr: true do
       # expect(subject.valid?).to be true
       expect(subject.id).to eq("https://doi.org/10.53731/ffbx660-083tnag")
       expect(subject.url).to eq("https://syldavia-gazette.org/guinea-worms-chatgpt-neanderthals")
+      expect(subject.files.length).to eq(3)
+      expect(subject.files[1]).to eq("mimeType" => "application/pdf", "url" => "https://api.rogue-scholar.org/posts/10.53731/ffbx660-083tnag.pdf")
       expect(subject.alternate_identifiers).to eq([{ "alternateIdentifier" => "0022b9ef-525a-4a79-81ad-13411697f58a", "alternateIdentifierType" => "UUID" }])
       expect(subject.type).to eq("Article")
       expect(subject.contributors.length).to eq(1)
@@ -210,6 +220,8 @@ describe Commonmeta::Metadata, vcr: true do
       # expect(subject.valid?).to be true
       expect(subject.id).to eq("https://doi.org/10.59350/kz04m-s8z58")
       expect(subject.url).to eq("https://wisspub.net/2023/05/23/eu-mitgliedstaaten-betonen-die-rolle-von-wissenschaftsgeleiteten-open-access-modellen-jenseits-von-apcs")
+      expect(subject.files.length).to eq(3)
+      expect(subject.files[1]).to eq("mimeType" => "application/pdf", "url" => "https://api.rogue-scholar.org/posts/10.59350/kz04m-s8z58.pdf")
       expect(subject.alternate_identifiers).to eq([{ "alternateIdentifier" => "1c578558-1324-4493-b8af-84c49eabc52f", "alternateIdentifierType" => "UUID" }])
       expect(subject.type).to eq("Article")
       expect(subject.contributors.length).to eq(1)
@@ -234,14 +246,16 @@ describe Commonmeta::Metadata, vcr: true do
       # expect(subject.valid?).to be true
       expect(subject.id).to eq("https://doi.org/10.59350/faeph-x4x84")
       expect(subject.url).to eq("https://wayback.archive-it.org/22143/20231103191454/https://project-thor.eu/2016/08/10/orcid-integration-in-pangaea")
+      expect(subject.files.length).to eq(3)
+      expect(subject.files[1]).to eq("mimeType" => "application/pdf", "url" => "https://api.rogue-scholar.org/posts/10.59350/faeph-x4x84.pdf")
       expect(subject.alternate_identifiers).to eq([{ "alternateIdentifier" => "570c8129-e867-49e6-8517-bd783627e76e", "alternateIdentifierType" => "UUID" }])
       expect(subject.type).to eq("Article")
       expect(subject.contributors.length).to eq(1)
       expect(subject.contributors.first).to eq("contributorRoles" => ["Author"],
-           "type" => "Person",
-           "familyName" => "Stocker",
-           "givenName" => "Markus",
-           "id" => "https://orcid.org/0000-0001-5492-3212")
+                                               "type" => "Person",
+                                               "familyName" => "Stocker",
+                                               "givenName" => "Markus",
+                                               "id" => "https://orcid.org/0000-0001-5492-3212")
       expect(subject.titles).to eq([{ "title" => "ORCID Integration Series: PANGAEA" }])
       expect(subject.license).to eq("id" => "CC-BY-4.0",
                                     "url" => "https://creativecommons.org/licenses/by/4.0/legalcode")
@@ -253,7 +267,7 @@ describe Commonmeta::Metadata, vcr: true do
                                         "subject" => "FOS: Computer and information sciences",
                                         "subjectScheme" => "Fields of Science and Technology (FOS)" }])
       expect(subject.language).to eq("en")
-      expect(subject.funding_references).to eq([{ "awardNumber" => "654039", "funderIdentifier" => "https://doi.org/10.13039/501100007601", "funderIdentifierType"=>"Crossref Funder ID", "funderName" => "European Union’s Horizon 2020 research and innovation programme" }])
+      expect(subject.funding_references).to eq([{ "awardNumber" => "654039", "funderIdentifier" => "https://doi.org/10.13039/501100007601", "funderIdentifierType" => "Crossref Funder ID", "funderName" => "European Union’s Horizon 2020 research and innovation programme" }])
       expect(subject.container).to eq("identifier" => "https://project-thor.eu", "identifierType" => "URL", "title" => "Project THOR", "type" => "Periodical")
       expect(subject.archive_locations).to eq(["Internet Archive"])
     end
@@ -264,10 +278,12 @@ describe Commonmeta::Metadata, vcr: true do
       # expect(subject.valid?).to be true
       expect(subject.id).to eq("https://doi.org/10.59350/hke8v-d1e66")
       expect(subject.url).to eq("https://svpow.com/2023/06/09/new-paper-curtice-et-al-2023-on-the-first-haplocanthosaurus-from-dry-mesa")
+      expect(subject.files.length).to eq(3)
+      expect(subject.files[1]).to eq("mimeType" => "application/pdf", "url" => "https://api.rogue-scholar.org/posts/10.59350/hke8v-d1e66.pdf")
       expect(subject.type).to eq("Article")
       expect(subject.contributors.length).to eq(1)
       expect(subject.contributors.first).to eq("familyName" => "Wedel", "givenName" => "Matt", "type" => "Person", "contributorRoles" => ["Author"])
-      expect(subject.titles).to eq([{ "title" => "New paper: Curtice et al. (2023) on the first <i>Haplocanthosaurus</i> from Dry Mesa"}])
+      expect(subject.titles).to eq([{ "title" => "New paper: Curtice et al. (2023) on the first <i>Haplocanthosaurus</i> from Dry Mesa" }])
       expect(subject.license).to eq("id" => "CC-BY-4.0",
                                     "url" => "https://creativecommons.org/licenses/by/4.0/legalcode")
       expect(subject.date).to eq("published" => "2023-06-09", "updated" => "2023-06-09")
@@ -289,6 +305,8 @@ describe Commonmeta::Metadata, vcr: true do
       # expect(subject.valid?).to be true
       expect(subject.id).to eq("https://doi.org/10.59350/tpa8t-j6292")
       expect(subject.url).to eq("https://www.samuelmoore.org/2023/04/20/how-to-cultivate-good-closures-scaling-small-and-the-limits-of-openness")
+      expect(subject.files.length).to eq(3)
+      expect(subject.files[1]).to eq("mimeType" => "application/pdf", "url" => "https://api.rogue-scholar.org/posts/10.59350/tpa8t-j6292.pdf")
       expect(subject.type).to eq("Article")
       expect(subject.contributors.length).to eq(1)
       expect(subject.contributors.first).to eq("familyName" => "Moore", "givenName" => "Samuel", "type" => "Person", "contributorRoles" => ["Author"])
@@ -313,6 +331,8 @@ describe Commonmeta::Metadata, vcr: true do
       # expect(subject.valid?).to be true
       expect(subject.id).to eq("https://doi.org/10.59350/tfahc-rp566")
       expect(subject.url).to eq("https://blog.oa.works/nature-features-oa-reports-work-putting-oa-policy-into-practice")
+      expect(subject.files.length).to eq(3)
+      expect(subject.files[1]).to eq("mimeType" => "application/pdf", "url" => "https://api.rogue-scholar.org/posts/10.59350/tfahc-rp566.pdf")
       expect(subject.type).to eq("Article")
       expect(subject.contributors.length).to eq(1)
       expect(subject.contributors.first).to eq("name" => "OA.Works", "type" => "Organization", "contributorRoles" => ["Author"])
@@ -362,6 +382,8 @@ describe Commonmeta::Metadata, vcr: true do
       # expect(subject.valid?).to be true
       expect(subject.id).to eq("https://doi.org/10.59350/zwdq7-waa43")
       expect(subject.url).to eq("https://citationstyles.org/2020/07/11/seeking-public-comment-on-CSL-1-0-2")
+      expect(subject.files.length).to eq(3)
+      expect(subject.files[1]).to eq("mimeType" => "application/pdf", "url" => "https://api.rogue-scholar.org/posts/10.59350/zwdq7-waa43.pdf")
       expect(subject.alternate_identifiers).to eq([{ "alternateIdentifier" => "efdacb04-bcec-49d7-b689-ab3eab0634bf", "alternateIdentifierType" => "UUID" }])
       expect(subject.type).to eq("Article")
       expect(subject.contributors.length).to eq(0)
@@ -387,6 +409,8 @@ describe Commonmeta::Metadata, vcr: true do
       # expect(subject.valid?).to be true
       expect(subject.id).to eq("https://doi.org/10.59350/2shz7-ehx26")
       expect(subject.url).to eq("https://libscie.org/ku-leuven-supports-researchequals")
+      expect(subject.files.length).to eq(3)
+      expect(subject.files[1]).to eq("mimeType" => "application/pdf", "url" => "https://api.rogue-scholar.org/posts/10.59350/2shz7-ehx26.pdf")
       expect(subject.alternate_identifiers).to eq([{ "alternateIdentifier" => "5561f8e4-2ff1-4186-a8d5-8dacb3afe414", "alternateIdentifierType" => "UUID" }])
       expect(subject.type).to eq("Article")
       expect(subject.contributors.length).to eq(1)
@@ -412,6 +436,8 @@ describe Commonmeta::Metadata, vcr: true do
       # expect(subject.valid?).to be true
       expect(subject.id).to eq("https://doi.org/10.59350/33es7-fqz31")
       expect(subject.url).to eq("https://lab.sub.uni-goettingen.de/welcome.html")
+      expect(subject.files.length).to eq(3)
+      expect(subject.files[1]).to eq("mimeType" => "application/pdf", "url" => "https://api.rogue-scholar.org/posts/10.59350/33es7-fqz31.pdf")
       expect(subject.alternate_identifiers).to eq([{ "alternateIdentifier" => "a163e340-5b3c-4736-9ab0-8c54fdff6a3c", "alternateIdentifierType" => "UUID" }])
       expect(subject.type).to eq("Article")
       expect(subject.contributors.length).to eq(1)
@@ -437,6 +463,8 @@ describe Commonmeta::Metadata, vcr: true do
       # expect(subject.valid?).to be true
       expect(subject.id).to eq("https://doi.org/10.59350/63055-a8604")
       expect(subject.url).to eq("http://sfmatheson.blogspot.com/2023/01/quintessence-of-dust-2023-restart-why.html")
+      expect(subject.files.length).to eq(3)
+      expect(subject.files[1]).to eq("mimeType" => "application/pdf", "url" => "https://api.rogue-scholar.org/posts/10.59350/63055-a8604.pdf")
       expect(subject.alternate_identifiers).to eq([{ "alternateIdentifier" => "1898d2d7-4d87-4487-96c4-3073cf99e9a5", "alternateIdentifierType" => "UUID" }])
       expect(subject.type).to eq("Article")
       expect(subject.contributors.length).to eq(1)
@@ -462,6 +490,8 @@ describe Commonmeta::Metadata, vcr: true do
       # expect(subject.valid?).to be true
       expect(subject.id).to eq("https://doi.org/10.59350/9gfjs-pey70")
       expect(subject.url).to eq("https://flavoursofopen.science/grundlagen-fur-die-entwicklung-einer-open-scholarship-strategie")
+      expect(subject.files.length).to eq(3)
+      expect(subject.files[1]).to eq("mimeType" => "application/pdf", "url" => "https://api.rogue-scholar.org/posts/10.59350/9gfjs-pey70.pdf")
       expect(subject.alternate_identifiers).to eq([{ "alternateIdentifier" => "f3dc29da-0481-4f3b-8110-4c07260fca67", "alternateIdentifierType" => "UUID" }])
       expect(subject.type).to eq("Article")
       expect(subject.contributors.length).to eq(1)
@@ -488,6 +518,8 @@ describe Commonmeta::Metadata, vcr: true do
       # expect(subject.valid?).to be true
       expect(subject.id).to eq("https://doi.org/10.59350/bbcsr-r4b59")
       expect(subject.url).to eq("https://markrubin.substack.com/p/the-preregistration-prescriptiveness")
+      expect(subject.files.length).to eq(3)
+      expect(subject.files[1]).to eq("mimeType" => "application/pdf", "url" => "https://api.rogue-scholar.org/posts/10.59350/bbcsr-r4b59.pdf")
       expect(subject.alternate_identifiers).to eq([{ "alternateIdentifier" => "2b105b29-acbc-4eae-9ff1-368803f36a4d", "alternateIdentifierType" => "UUID" }])
       expect(subject.type).to eq("Article")
       expect(subject.contributors.length).to eq(1)

data/spec/writers/crossref_xml_writer_spec.rb

@@ -57,7 +57,7 @@ describe Commonmeta::Metadata, vcr: true do
                                                              "journal_article")
       expect(Array.wrap(crossref_xml.dig("contributors", "person_name")).length).to eq(6)
       expect(Array.wrap(crossref_xml.dig("contributors",
-                                         "person_name")).first).to eq("contributor_role"=>"author", "given_name"=>"Markus", "sequence"=>"first", "surname"=>"Ralser")
+                                         "person_name")).first).to eq("contributor_role" => "author", "given_name" => "Markus", "sequence" => "first", "surname" => "Ralser")
       expect(crossref_xml.dig("titles",
                               "title")).to eq("Triose Phosphate Isomerase Deficiency Is Caused by Altered Dimerization–Not Catalytic Inactivity–of the Mutant Enzymes")
     end
@@ -232,6 +232,9 @@ describe Commonmeta::Metadata, vcr: true do
                               "title")).to eq("Attempts at automating journal subject classification")
       expect(crossref_xml.dig("item_number")).to eq("__content__" => "5d14ffacb9ac4e20bdc0d9248df4e80d", "item_number_type" => "uuid")
       expect(crossref_xml.dig("group_title")).to eq("Humanities")
+      expect(crossref_xml.dig("doi_data", "collection", "item", "resource").length).to eq(4)
+      expect(crossref_xml.dig("doi_data", "collection", "item", "resource", 2)).to eq("__content__" => "https://api.rogue-scholar.org/posts/10.54900/n6dnt-xpq48.pdf", "mime_type" => "application/pdf")
+    
     end
 
     it "json_feed_item with references" do
@@ -264,6 +267,8 @@ describe Commonmeta::Metadata, vcr: true do
       expect(crossref_xml.dig("citation_list", "citation").last).to eq("article_title" => "The Research Software Alliance (ReSA) and the community landscape", "cYear" => "2020", "doi" => "10.5281/zenodo.3699950", "key" => "ref11")
       expect(crossref_xml.dig("item_number")).to eq("__content__" => "954f81380ecd409087c5cef1297f1470", "item_number_type" => "uuid")
       expect(crossref_xml.dig("group_title")).to eq("Humanities")
+      expect(crossref_xml.dig("doi_data", "collection", "item", "resource").length).to eq(4)
+      expect(crossref_xml.dig("doi_data", "collection", "item", "resource", 2)).to eq("__content__" => "https://api.rogue-scholar.org/posts/10.54900/zwm7q-vet94.pdf", "mime_type" => "application/pdf")
     end
 
     it "json_feed_item from rogue scholar with doi" do
@@ -277,7 +282,7 @@ describe Commonmeta::Metadata, vcr: true do
       expect(subject.titles).to eq([{ "title" => "EU-Mitgliedstaaten betonen die Rolle von wissenschaftsgeleiteten Open-Access-Modellen jenseits von APCs" }])
       expect(subject.contributors.length).to eq(1)
       expect(subject.contributors.first).to eq("familyName" => "Pampel", "givenName" => "Heinz", "id" => "https://orcid.org/0000-0003-3334-2771", "type" => "Person", "contributorRoles" => ["Author"])
-      expect(subject.publisher).to eq("name"=>"wisspub.net")
+      expect(subject.publisher).to eq("name" => "wisspub.net")
       expect(subject.subjects).to eq([{ "subject" => "Social sciences" },
                                       { "schemeUri" => "http://www.oecd.org/science/inno/38235147.pdf",
                                         "subject" => "FOS: Social sciences",
@@ -293,6 +298,8 @@ describe Commonmeta::Metadata, vcr: true do
                               "title")).to eq("EU-Mitgliedstaaten betonen die Rolle von wissenschaftsgeleiteten Open-Access-Modellen jenseits von APCs")
       expect(crossref_xml.dig("item_number")).to eq("__content__" => "1c57855813244493b8af84c49eabc52f", "item_number_type" => "uuid")
       expect(crossref_xml.dig("group_title")).to eq("Social sciences")
+      expect(crossref_xml.dig("doi_data", "collection", "item", "resource").length).to eq(4)
+      expect(crossref_xml.dig("doi_data", "collection", "item", "resource", 2)).to eq("__content__" => "https://api.rogue-scholar.org/posts/10.59350/9ry27-7cz42.pdf", "mime_type" => "application/pdf")
     end
 
     it "json_feed_item from rogue scholar with organizational author" do
@@ -321,6 +328,8 @@ describe Commonmeta::Metadata, vcr: true do
                               "title")).to eq("KU Leuven supports ResearchEquals")
       expect(crossref_xml.dig("item_number")).to eq("__content__" => "5561f8e42ff14186a8d58dacb3afe414", "item_number_type" => "uuid")
       expect(crossref_xml.dig("group_title")).to eq("Social sciences")
+      expect(crossref_xml.dig("doi_data", "collection", "item", "resource").length).to eq(4)
+      expect(crossref_xml.dig("doi_data", "collection", "item", "resource", 2)).to eq("__content__" => "https://api.rogue-scholar.org/posts/10.59350/9ry27-7cz42.pdf", "mime_type" => "application/pdf")
     end
 
     it "json_feed_item from rogue scholar with archived content" do
@@ -333,10 +342,10 @@ describe Commonmeta::Metadata, vcr: true do
       expect(subject.type).to eq("Article")
       expect(subject.contributors.length).to eq(1)
       expect(subject.contributors.first).to eq("contributorRoles" => ["Author"],
-           "type" => "Person",
-           "familyName" => "Stocker",
-           "givenName" => "Markus",
-           "id" => "https://orcid.org/0000-0001-5492-3212")
+                                               "type" => "Person",
+                                               "familyName" => "Stocker",
+                                               "givenName" => "Markus",
+                                               "id" => "https://orcid.org/0000-0001-5492-3212")
       expect(subject.titles).to eq([{ "title" => "ORCID Integration Series: PANGAEA" }])
       expect(subject.license).to eq("id" => "CC-BY-4.0",
                                     "url" => "https://creativecommons.org/licenses/by/4.0/legalcode")
@@ -348,18 +357,20 @@ describe Commonmeta::Metadata, vcr: true do
                                         "subject" => "FOS: Computer and information sciences",
                                         "subjectScheme" => "Fields of Science and Technology (FOS)" }])
       expect(subject.language).to eq("en")
-      expect(subject.funding_references).to eq([{ "awardNumber" => "654039", "funderIdentifier" => "https://doi.org/10.13039/501100007601", "funderIdentifierType"=>"Crossref Funder ID", "funderName" => "European Union’s Horizon 2020 research and innovation programme" }])
+      expect(subject.funding_references).to eq([{ "awardNumber" => "654039", "funderIdentifier" => "https://doi.org/10.13039/501100007601", "funderIdentifierType" => "Crossref Funder ID", "funderName" => "European Union’s Horizon 2020 research and innovation programme" }])
       expect(subject.container).to eq("identifier" => "https://project-thor.eu", "identifierType" => "URL", "title" => "Project THOR", "type" => "Periodical")
       expect(subject.archive_locations).to eq(["Internet Archive"])
       # puts subject.crossref_xml
       crossref_xml = Hash.from_xml(subject.crossref_xml).dig("doi_batch", "body", "posted_content")
       expect(Array.wrap(crossref_xml.dig("contributors", "person_name")).length).to eq(1)
       expect(Array.wrap(crossref_xml.dig("contributors",
-                                         "person_name")).first).to eq("ORCID"=>"https://orcid.org/0000-0001-5492-3212", "contributor_role"=>"author", "given_name"=>"Markus", "sequence"=>"first", "surname"=>"Stocker")
+                                         "person_name")).first).to eq("ORCID" => "https://orcid.org/0000-0001-5492-3212", "contributor_role" => "author", "given_name" => "Markus", "sequence" => "first", "surname" => "Stocker")
       expect(crossref_xml.dig("titles",
                               "title")).to eq("ORCID Integration Series: PANGAEA")
       expect(crossref_xml.dig("item_number")).to eq("__content__" => "570c8129e86749e68517bd783627e76e", "item_number_type" => "uuid")
       expect(crossref_xml.dig("group_title")).to eq("Computer and information sciences")
+      expect(crossref_xml.dig("doi_data", "collection", "item", "resource").length).to eq(4)
+      expect(crossref_xml.dig("doi_data", "collection", "item", "resource", 2)).to eq("__content__" => "https://api.rogue-scholar.org/posts/10.59350/faeph-x4x84.pdf", "mime_type" => "application/pdf")
     end
 
     it "json_feed_item from rogue scholar with relations" do
@@ -397,6 +408,8 @@ describe Commonmeta::Metadata, vcr: true do
                               "title")).to eq("Differences between ORCID and DataCite Metadata")
       expect(crossref_xml.dig("item_number")).to eq("__content__" => "8a4de44333474b82b57de3c82b6485fc", "item_number_type" => "uuid")
       expect(crossref_xml.dig("group_title")).to eq("Computer and information sciences")
+      expect(crossref_xml.dig("doi_data", "collection", "item", "resource").length).to eq(4)
+      expect(crossref_xml.dig("doi_data", "collection", "item", "resource", 2)).to eq("__content__" => "https://api.rogue-scholar.org/posts/10.53731/r79v4e1-97aq74v-ag578.pdf", "mime_type" => "application/pdf")
     end
 
     it "json_feed_item from rogue scholar with relations and funding" do
@@ -433,6 +446,8 @@ describe Commonmeta::Metadata, vcr: true do
                               "title")).to eq("Tracking the Growth of the PID Graph")
       expect(crossref_xml.dig("item_number")).to eq("__content__" => "e58dc9c8b8704db28896238b3246c551", "item_number_type" => "uuid")
       expect(crossref_xml.dig("group_title")).to eq("Computer and information sciences")
+      expect(crossref_xml.dig("doi_data", "collection", "item", "resource").length).to eq(4)
+      expect(crossref_xml.dig("doi_data", "collection", "item", "resource", 2)).to eq("__content__" => "https://api.rogue-scholar.org/posts/10.53731/r79s4nh-97aq74v-ag4t1.pdf", "mime_type" => "application/pdf")
     end
 
     it "json_feed_item from rogue scholar with anonymous author" do
@@ -466,6 +481,8 @@ describe Commonmeta::Metadata, vcr: true do
                               "title")).to eq("Welcome to the Lab")
       expect(crossref_xml.dig("item_number")).to eq("__content__" => "a163e3405b3c47369ab08c54fdff6a3c", "item_number_type" => "uuid")
       expect(crossref_xml.dig("group_title")).to eq("Computer and information sciences")
+      expect(crossref_xml.dig("doi_data", "collection", "item", "resource").length).to eq(4)
+      expect(crossref_xml.dig("doi_data", "collection", "item", "resource", 2)).to eq("__content__" => "https://api.rogue-scholar.org/posts/10.59350/9ry27-7cz42.pdf", "mime_type" => "application/pdf")
     end
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: commonmeta-ruby
 version: !ruby/object:Gem::Version
-  version: 3.7.3
+  version: 3.8.0
 platform: ruby
 authors:
 - Martin Fenner
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2023-12-25 00:00:00.000000000 Z
+date: 2024-01-09 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activesupport