Merge branch 'master' of https://github.com/datacite/lupo

app/controllers/datacite_dois_controller.rb

@@ -666,10 +666,12 @@ def safe_params
       xml = xml.strip
     end
 
+    fail(ActionController::UnpermittedParameters, ["creators must be an Array"]) if p[:creators]&.respond_to?(:keys)
     p[:creators]&.each do |c|
       fail(ActionController::UnpermittedParameters, ["nameIdentifiers must be an Array"]) if c[:nameIdentifiers]&.respond_to?(:keys)
     end
 
+    fail(ActionController::UnpermittedParameters, ["contributors must be an Array"]) if p[:contributors]&.respond_to?(:keys)
     p[:contributors]&.each do |c|
       fail(ActionController::UnpermittedParameters, ["nameIdentifiers must be an Array"]) if c[:nameIdentifiers]&.respond_to?(:keys)
     end

app/models/doi.rb

@@ -868,7 +868,7 @@ def self.gql_query(query, options={})
     filter << { terms: { "client.certificate" => options[:certificate].split(",") }} if options[:certificate].present?
     filter << { term: { "creators.nameIdentifiers.nameIdentifier" => "https://orcid.org/#{orcid_from_url(options[:user_id])}" }} if options[:user_id].present?
     filter << { term: { "creators.nameIdentifiers.nameIdentifierScheme" => "ORCID" }} if options[:has_person].present?
-    
+
     # match either one of has_affiliation, has_organization, has_funder or has_member
     if options[:has_organization].present?
       should << { term: { "creators.nameIdentifiers.nameIdentifierScheme" => "ROR" }}
@@ -1067,7 +1067,7 @@ def self.query(query, options={})
     filter << { terms: { "client.certificate" => options[:certificate].split(",") }} if options[:certificate].present?
     filter << { term: { "creators.nameIdentifiers.nameIdentifier" => "https://orcid.org/#{orcid_from_url(options[:user_id])}" }} if options[:user_id].present?
     filter << { term: { "creators.nameIdentifiers.nameIdentifierScheme" => "ORCID" }} if options[:has_person].present?
-    
+
     # match either one of has_affiliation, has_organization, or has_funder
     if options[:has_organization].present?
       should << { term: { "creators.nameIdentifiers.nameIdentifierScheme" => "ROR" }}
@@ -2133,7 +2133,7 @@ def set_defaults
   end
 
   def update_agency
-    if agency.blank? || agency.casecmp?("datacite") 
+    if agency.blank? || agency.casecmp?("datacite")
       self.agency = "datacite"
       self.type = "DataciteDoi"
     elsif agency.casecmp?("crossref")
@@ -2310,4 +2310,41 @@ def self.migrate_landing_page(options={})
 
     "Finished migrating landing pages."
   end
-end
+
+  def self.add_index_type(options={})
+    return nil unless options[:from_id].present?
+
+
+    from_id = options[:from_id].to_i
+    until_id = (options[:until_id] || (from_id + 499)).to_i
+
+    # get every id between from_id and end_id
+    count = 0
+
+    Rails.logger.info "[migration_index_types] adding type information for DOIs with IDs #{from_id} - #{until_id}."
+
+    Doi.where(id: from_id..until_id).where('type' => nil).find_each(batch_size: 500) do |doi|
+      begin
+        if doi.agency.casecmp?("datacite")
+          type = "DataciteDoi"
+        elsif doi.agency.casecmp?("crossref")
+          type = "OtherDoi"
+        else
+          type = "DataciteDoi"
+        end
+
+        doi.update_columns("type" => type)
+
+        count += 1
+        Rails.logger.info "Updated #{doi.doi} (#{doi.id})"
+
+      rescue => error
+        Rails.logger.error "Error updating #{doi.doi} (#{doi.id}), #{error.message}"
+      end
+    end
+
+    "Finished updating dois, total #{count}"
+  end
+
+
+end

lib/tasks/doi.rake

@@ -243,4 +243,13 @@ namespace :doi do
     count = Doi.delete_dois_by_prefix(ENV['PREFIX'])
     puts "#{count} DOIs with prefix #{ENV['PREFIX']} deleted."
   end
+
+  desc 'Add type information to dois based on id range'
+  task :add_index_type => :environment do
+    options = {
+      from_id: ENV['FROM_ID'],
+      until_id: ENV['UNTIL_ID']
+    }
+    puts Doi.add_index_type(options)
+  end
 end

spec/fixtures/files/nasa_error.json

@@ -0,0 +1,66 @@
+{
+  "data": {
+	"type":"dois",
+	"id":"10.14454/rdnt.1x18sn",
+  	"attributes":{
+  		"doi": "10.14454/rdnt.1x18sn",
+  		"prefix":"10.14454",
+  		"creators":[
+  			{
+          "name":"Maskey, Manil",
+          "nameType":"Personal",
+          "givenName":"Manil",
+          "familyName":"Maskey"
+        },
+        {
+          "name":"Ramachandran, Rahul",
+          "nameType":"Personal",
+          "givenName":"Rahul",
+          "familyName":"Ramachandran"
+        },
+        {
+          "name":"Gurung, Iksha",
+          "nameType":"Personal",
+          "givenName":"Iksha",
+          "familyName":"Gurung"
+        },
+        {
+          "name":"Ramasubramanian, Muthukumaran",
+          "nameType":"Personal",
+          "givenName":"Muthukumaran",
+          "familyName":"Ramasubramanian"
+        }
+  		],
+  		"titles":{
+  			"title":"Tropical Cyclone Satellite Imagery and Wind Speed Dataset"
+  		},
+  		"publisher": "Radiant MLHub",
+  		"publicationYear": 2020,
+  		"types":{
+  			"resourceTypeGeneral":"Dataset"
+  		},
+  		"version":1.0,
+  		"contributors":{
+  			"nameType":"Organizational",
+  			"name":"NASA Interagency Implementation and Advanced Concepts Team (IMPACT)",
+  			"contributorType":"DataCurator"
+  		},
+  		"dates":{
+  			"dateType":"Valid",
+  			"date": "2000/2019"
+      },
+      "fundingReferences":{
+          "funderName":"NASA Earth Science Data Systems Program"
+      },
+  		"rightsList":{
+        "rights":"CC BY 4.0",
+        "rightsUri":"https://creativecommons.org/licenses/by/4.0/"
+  		},
+  		"url":"http://registry.mlhub.earth/10.34911/rdnt.1x18sn",
+  		"landingPage":{
+  			"url":"http://registry.mlhub.earth/10.34911/rdnt.1x18sn"
+  		},
+      "event":"publish"
+    }
+  }
+}

spec/requests/datacite_dois_spec.rb

@@ -2184,6 +2184,16 @@
       end
     end
 
+    context 'when the request has wrong object in nameIDentifiers' do
+      let(:valid_attributes) { JSON.parse(file_fixture('nasa_error.json').read) }
+
+
+      it 'fails to create a Doi' do
+        post '/dois', valid_attributes, headers
+
+        expect(last_response.status).to eq(422)
+      end
+    end
 
 
     # context 'when the request is a large xml file' do