Update profiles/Dataset_SoBigData_ResourceCatalogue.xml

Dataset profile provided by Valerio Grossi

profiles/Dataset_SoBigData_ResourceCatalogue.xml

@@ -5,16 +5,13 @@
         <dataType>String</dataType>
         <maxOccurs>*</maxOccurs>
         <defaultValue>Others</defaultValue>
-                    <note>The group the item belongs to.</note>
+        <note>Add one of more value based on the available research areas.</note>
         <vocabulary isMultiSelection="false">
-                        <vocabularyField>Computational Epidemiology</vocabularyField>
             <vocabularyField>Demography, Economy and Finance 2.0</vocabularyField>
             <vocabularyField>Disaster Response and Recovery</vocabularyField>
             <vocabularyField>e-Learning</vocabularyField>
             <vocabularyField>Ethics and Legality</vocabularyField>
             <vocabularyField>Health Studies</vocabularyField>
-                        <vocabularyField>Migration Studies</vocabularyField>
-                        <vocabularyField>Network Medicine</vocabularyField>
             <vocabularyField>Pervasive Intelligence in Cyber-Physical Systems for Future Society</vocabularyField>
             <vocabularyField>Social Impact of AI and explainable ML</vocabularyField>
             <vocabularyField>Societal Debates and Misinformation</vocabularyField>
@@ -28,6 +25,7 @@
         <fieldName>Thematic Cluster</fieldName>
         <mandatory>true</mandatory>
         <dataType>String</dataType>
+        <note>Select one of more value based on the available thematic cluster.</note>
         <vocabulary isMultiSelection="true">
             <vocabularyField>Human Mobility Analytics [HMA]</vocabularyField>
             <vocabularyField>Privacy Enhancing Technology [PET]</vocabularyField>
@@ -72,9 +70,10 @@
         <fieldName>Creator</fieldName>
         <mandatory>true</mandatory>
         <dataType>String</dataType>
+        <maxOccurs>*</maxOccurs>
         <note>The name of the creator, with email and ORCID. The format should be: family, given[, email][, ORCID]. Example: Smith, John, js@acme.org, orcid.org/0000-0002-1825-0097</note>
         <validator>
-                        <regularExpression>^[a-zA-ZÀ-ÿ .'-]+, [a-zA-ZÀ-ÿ .'-]+[, ]*([a-zA-Z0-9_!#$%’*+=?`{|}~^.-]+@[a-zA-Z0-9À-ÿ.-]+)?[, ]*(orcid.org\/0000-000(1-[5-9]|2-[0-9]|3-[0-4])\d\d\d-\d\d\d[\dX])?$</regularExpression>
+            <regularExpression>^([a-zA-ZÀ-ÿ .'-]+), *([a-zA-ZÀ-ÿ .'-]+)(?:, *([a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}))?(?:, *(orcid.org/\d{4}-\d{4}-\d{4}-\d{3}[0-9X]))?$</regularExpression>
         </validator>
     </metadatafield>
     <metadatafield>
@@ -86,23 +85,17 @@
             <regularExpression>^(\d{4}\-(0?[1-9]|1[012])\-(0?[1-9]|[12][0-9]|3[01]))+([ ]+(\d{2}(:?\d{2})?)?)?$</regularExpression>
         </validator>
     </metadatafield>
-                <metadatafield>
-                    <fieldName>Semantic Coverage</fieldName>
-                    <mandatory>false</mandatory>
-                    <dataType>String</dataType>
-                    <note>Tagging e.g. people, cities, transports...</note>
-                </metadatafield>
     <metadatafield>
         <fieldName>Time Coverage</fieldName>
         <mandatory>false</mandatory>
         <dataType>Times_ListOf</dataType>
-                    <note>List of time intervals, e.g. 1977-03-10 11:45 - 2005-01-15 09:10; 2010-03-10 00:00 - 2015-01-15 10:00</note>
+        <note>Report here the list of time intervals of the data, e.g. 1977-03-10 11:45 - 2005-01-15 09:10; 2010-03-10 00:00 - 2015-01-15 10:00</note>
     </metadatafield>
     <metadatafield>
-                    <fieldName>spatial</fieldName>
+        <fieldName>Spatial</fieldName>
         <mandatory>false</mandatory>
         <dataType>GeoJSON</dataType>
-                    <note>Geo Location. The value must be a valid GeoJSON geometry, for example: { "type":"Polygon", "coordinates":[[[2.05827, 49.8625],[2.05827, 55.7447], [-6.41736, 55.7447], [-6.41736, 49.8625], [2.05827, 49.8625]]] } or: { "type": "Point", "coordinates": [-3.145,53.078] }</note>
+        <note>If a dataset is geo located, report here the geo Location. The value must be a valid GeoJSON geometry, for example: { "type":"Polygon", "coordinates":[[[2.05827, 49.8625],[2.05827, 55.7447], [-6.41736, 55.7447], [-6.41736, 49.8625], [2.05827, 49.8625]]] } or: { "type": "Point", "coordinates": [-3.145,53.078] }</note>
     </metadatafield>
     <metadatafield>
         <fieldName>Processing Degree</fieldName>
@@ -114,17 +107,6 @@
             <vocabularyField>Secondary</vocabularyField>
         </vocabulary>
     </metadatafield>
-                <metadatafield>
-                    <fieldName>Manifestation Type</fieldName>
-                    <mandatory>true</mandatory>
-                    <dataType>String</dataType>
-                    <note>Virtual (accessible in streaming from remote sites), replica (copy of data in remote sites, e.g. DBPL), original (collection of data produced and kept in local infra by data provider).</note>
-                    <vocabulary>
-                        <vocabularyField>Virtual</vocabularyField>
-                        <vocabularyField>Replica</vocabularyField>
-                        <vocabularyField>Original</vocabularyField>
-                    </vocabulary>
-                </metadatafield>
     <metadatafield>
         <fieldName>Language</fieldName>
         <mandatory>false</mandatory>
@@ -1574,7 +1556,7 @@
             <vocabularyField>bpa, Daakaka</vocabularyField>
             <vocabularyField>lni, Daantanai'</vocabularyField>
             <vocabularyField>dsh, Daasanach</vocabularyField>
-                        <vocabularyField>dtn, Daatsʼíin</vocabularyField>
+            <vocabularyField>dtn, Daatsʼíin</vocabularyField>
             <vocabularyField>dbq, Daba</vocabularyField>
             <vocabularyField>dbr, Dabarre</vocabularyField>
             <vocabularyField>dbe, Dabe</vocabularyField>
@@ -1821,7 +1803,7 @@
             <vocabularyField>duv, Duvle</vocabularyField>
             <vocabularyField>dbp, Duwai</vocabularyField>
             <vocabularyField>gve, Duwet</vocabularyField>
-                        <vocabularyField>ldb, Dũya</vocabularyField>
+            <vocabularyField>ldb, Dũya</vocabularyField>
             <vocabularyField>nnu, Dwang</vocabularyField>
             <vocabularyField>dyy, Dyaabugay</vocabularyField>
             <vocabularyField>dyb, Dyaberdyaber</vocabularyField>
@@ -7985,39 +7967,22 @@
         <mandatory>true</mandatory>
         <dataType>String</dataType>
         <defaultValue>Both</defaultValue>
-                    <note>How the access to the resource is regulated: Virtual Access or Trans National Access</note>
+        <note>How the access to the resource is regulated. Select OnSite only if the dataset is accessible only by visiting the node. Select All if the dataset is avalable OnLine, and OnSite</note>
         <vocabulary>
             <vocabularyField>Both</vocabularyField>
-                        <vocabularyField>Virtual Access</vocabularyField>
+            <vocabularyField>OnLine</vocabularyField>
-                        <vocabularyField>Trans National Access</vocabularyField>
+            <vocabularyField>OnSite</vocabularyField>
         </vocabulary>
     </metadatafield>
     <metadatafield>
-                    <fieldName>Availability</fieldName>
+        <fieldName>Associate Project</fieldName>
-                    <mandatory>true</mandatory>
-                    <dataType>String</dataType>
-                    <note>How the availability to the resource is offered.</note>
-                    <vocabulary>
-                        <vocabularyField>On-Line</vocabularyField>
-                        <vocabularyField>On-Site</vocabularyField>
-                    </vocabulary>
-                </metadatafield>
-                <metadatafield>
-                    <fieldName>Accessibility Mode</fieldName>
-                    <mandatory>true</mandatory>
-                    <dataType>String</dataType>
-                    <note>How the access to the resource is offered</note>
-                    <vocabulary isMultiSelection="true">
-                        <vocabularyField>OnLine Access</vocabularyField>
-                        <vocabularyField>API Access</vocabularyField>
-                        <vocabularyField>Download</vocabularyField>
-                    </vocabulary>
-                </metadatafield>
-                <metadatafield>
-                    <fieldName>Size</fieldName>
         <mandatory>false</mandatory>
         <dataType>String</dataType>
-                    <note>Whatever “size” means in your domain/mind</note>
+        <maxOccurs>*</maxOccurs>
+        <note>Insert here the associate project (if not SoBigData) producing the dataset.</note>
+        <validator>
+            <regularExpression>^([a-zA-Z0-9]*)$</regularExpression>
+        </validator>
     </metadatafield>
     <metadatafield>
         <fieldName>DiskSize</fieldName>
@@ -8025,17 +7990,11 @@
         <dataType>Number</dataType>
         <note>In MB</note>
     </metadatafield>
-                <metadatafield>
-                    <fieldName>Format</fieldName>
-                    <mandatory>false</mandatory>
-                    <dataType>String</dataType>
-                    <note>MIME or extension</note>
-                </metadatafield>
     <metadatafield>
         <fieldName>Format Schema</fieldName>
         <mandatory>false</mandatory>
         <dataType>String</dataType>
-                    <note>Link to Schema</note>
+        <note>Insert here the link to schema if available</note>
     </metadatafield>
     <metadatafield categoryref="SBD_PersonalData">
         <fieldName>Personal Data</fieldName>
@@ -8048,20 +8007,20 @@
         </vocabulary>
     </metadatafield>
     <metadatafield categoryref="SBD_PersonalData">
-                    <fieldName>Non Personal Data Explanation</fieldName>
+        <fieldName>Non Personal Data Explanation (if not Personal Data)</fieldName>
         <mandatory>false</mandatory>
         <dataType>Text</dataType>
         <note>Explaining why the dataset are not personal. This field has to be compiled if and only if the Personal Data field is set to No.</note>
     </metadatafield>
     <metadatafield categoryref="SBD_PersonalData">
-                    <fieldName>Record Of Processing Activities</fieldName>
+        <fieldName>Record Of Processing Activities (if Personal Data)</fieldName>
         <mandatory>false</mandatory>
         <dataType>Text</dataType>
         <note>Describe the flow or add a link to the record of data processing (Art. 30 GDPR). This field has to be compiled if and only if the Personal Data field is set to Yes.</note>
     </metadatafield>
     <metadatafield categoryref="SBD_PersonalData">
         <fieldName>Anonymised</fieldName>
-                    <mandatory>false</mandatory>
+        <mandatory>true</mandatory>
         <dataType>String</dataType>
         <note>Does the dataset contain Pseudo or Anonymized Data?</note>
         <vocabulary>
@@ -8071,14 +8030,14 @@
         </vocabulary>
     </metadatafield>
     <metadatafield categoryref="SBD_PersonalData">
-                    <fieldName>Anonymisation Methodology</fieldName>
+        <fieldName>Anonymisation Methodology (if anonymised data)</fieldName>
         <mandatory>false</mandatory>
         <dataType>Text</dataType>
         <note>Describe the flow or add a link to the record of data processing (Art. 30 GDPR). This field has to be compiled if only if the Anonymised field is set to Pseudo Anonymised or Anonymised.</note>
     </metadatafield>
     <metadatafield categoryref="SBD_PersonalData">
         <fieldName>General Data</fieldName>
-                    <mandatory>false</mandatory>
+        <mandatory>true</mandatory>
         <dataType>String</dataType>
         <note>General data are personal data not sensible (see art. 6 GDPR).</note>
         <vocabulary>
@@ -8088,7 +8047,7 @@
     </metadatafield>
     <metadatafield categoryref="SBD_PersonalData">
         <fieldName>Sensitive Data</fieldName>
-                    <mandatory>false</mandatory>
+        <mandatory>true</mandatory>
         <dataType>String</dataType>
         <note>Does the dataset contain sensitive data (art. 9 GDPR)?</note>
         <vocabulary>
@@ -8097,7 +8056,7 @@
         </vocabulary>
     </metadatafield>
     <metadatafield categoryref="SBD_PersonalData">
-                    <fieldName>Data Protection Impact Assessment</fieldName>
+        <fieldName>Data Protection Impact Assessment (if Sensitive Data)</fieldName>
         <mandatory>false</mandatory>
         <dataType>String</dataType>
         <note>Did you perform a DPIA (Data Protection Impact Assessment)? This field has to be compiled if only if Sensitive Data is set to Yes.</note>
@@ -8107,7 +8066,7 @@
         </vocabulary>
     </metadatafield>
     <metadatafield categoryref="SBD_PersonalData">
-                    <fieldName>Ethics Committee Approval</fieldName>
+        <fieldName>Ethics Committee Approval (if not Sensitive Data)</fieldName>
         <mandatory>false</mandatory>
         <dataType>String</dataType>
         <note>Did you get an approval from an ethics committee? This field has to be compiled if only if Sensitive Data is set to Yes.</note>
@@ -8117,7 +8076,7 @@
         </vocabulary>
     </metadatafield>
     <metadatafield categoryref="SBD_PersonalData">
-                    <fieldName>Informed Consent Template</fieldName>
+        <fieldName>Informed Consent Template (if Sensitive Data)</fieldName>
         <mandatory>false</mandatory>
         <dataType>String</dataType>
         <note>Do you have an informed consent template? This field has to be compiled if only if Sensitive Data is set to Yes.</note>
@@ -8146,7 +8105,7 @@
         <fieldName>ChildrenData</fieldName>
         <mandatory>true</mandatory>
         <dataType>String</dataType>
-                    <note>Does the dataset contain data related to children (i.e. &lt;18 years old?)?</note>
+        <note>Does the dataset contain data related to children (i.e., &lt;18 years old?)?</note>
         <vocabulary>
             <vocabularyField>No</vocabularyField>
             <vocabularyField>Yes</vocabularyField>
@@ -8218,19 +8177,19 @@
         <fieldName>Attribution requirements</fieldName>
         <mandatory>false</mandatory>
         <dataType>String</dataType>
-                    <note>The text exporting how the user needs to acknowledge the source when using/distributing data/developing service</note>
+        <note>The text reports how the user needs to acknowledge the source when using/distributing data/developing service</note>
     </metadatafield>
     <metadatafield>
         <fieldName>Display requirements</fieldName>
         <mandatory>false</mandatory>
         <dataType>String</dataType>
-                    <note>Whether the user, when displaying the dataset in any media or form, must follow certain display requirements, e.g. attach copyright notice</note>
+        <note>This text reports addtional info to add when the dataset is displayed in any media or form. The dataset must follow certain display requirements, e.g., attach copyright notice</note>
     </metadatafield>
     <metadatafield>
         <fieldName>Distribution requirements</fieldName>
         <mandatory>false</mandatory>
         <dataType>String</dataType>
-                    <note>Whether the user, when distributing the dataset, if allowed, must follow certain requirements</note>
+        <note>This text reports addtional info to add when the dataset is distributed outside the RI. If allowed, the dataset must follow certain distribution requirements</note>
     </metadatafield>
     <metadatafield>
         <fieldName>Territory of use</fieldName>
@@ -8299,16 +8258,20 @@
         </validator>
     </metadatafield>
     <metadatafield>
-                    <fieldName>Requirement of non-disclosure (confidentiality mark) </fieldName>
+        <fieldName>Requirement of non-disclosure (confidentiality mark)</fieldName>
         <mandatory>false</mandatory>
         <dataType>String</dataType>
         <note>Requirement of non-disclosure (confidentiality mark). Whether the dataset bears confidentiality mark/may be used and shared subject to the obligation of non-disclosure</note>
     </metadatafield>
     <metadatafield>
-                    <fieldName>Dataset Re-Use Safeguards</fieldName>
+        <fieldName>Data sharing agreement</fieldName>
         <mandatory>true</mandatory>
-                    <dataType>Text</dataType>
+        <dataType>String</dataType>
-                    <note>Specify the technical measures and organisational conditions. FAIR ecosystem link</note>
+        <note>Can be the dataset shared outside the RI</note>
+        <vocabulary>
+            <vocabularyField>yes</vocabularyField>
+            <vocabularyField>no</vocabularyField>
+        </vocabulary>
     </metadatafield>
     <metadatafield>
         <fieldName>Dataset Citation</fieldName>
@@ -8316,22 +8279,10 @@
         <dataType>Text</dataType>
         <note>Specify how to cite the source.</note>
     </metadatafield>
-                <metadatafield>
-                    <fieldName>Ownership and Governance</fieldName>
-                    <mandatory>false</mandatory>
-                    <dataType>Text</dataType>
-                    <note>Add any additional notes</note>
-                </metadatafield>
-                <metadatafield>
-                    <fieldName>Retention Period</fieldName>
-                    <mandatory>true</mandatory>
-                    <dataType>Time_Interval</dataType>
-                    <note>The dataset should be set to private after this period</note>
-                </metadatafield>
     <metadatafield>
         <fieldName>Additional Notes</fieldName>
         <mandatory>false</mandatory>
         <dataType>Text</dataType>
         <note>Add any additional notes</note>
     </metadatafield>
-            </metadataformat>
+</metadataformat>