From caa5190b73c800d4940313372e96c035ce2996e4 Mon Sep 17 00:00:00 2001
From: jdvorak001 <jan.dvorak@ff.cuni.cz>
Date: Sat, 22 Jul 2023 20:44:59 +0200
Subject: [PATCH] Add support for the highest ORCID iDs in the two ranges

The specifications in
https://support.orcid.org/hc/en-us/articles/360006897674-Structure-of-the-ORCID-Identifier
also include the highest iDs; in fact,
https://orcid.org/0000-0003-5000-0001 has been assigned

We also update the location of the ORCID documentation
---
 docs/cerif_xml_person_entity.rst              |  8 ++++----
 .../openaire_cerif_xml_example_persons.xml    | 20 +++++++++++++++++++
 schemas/includes/person-identifiers.xsd       |  8 ++++----
 3 files changed, 28 insertions(+), 8 deletions(-)

diff --git a/docs/cerif_xml_person_entity.rst b/docs/cerif_xml_person_entity.rst
index 16e482d..9268e76 100644
--- a/docs/cerif_xml_person_entity.rst
+++ b/docs/cerif_xml_person_entity.rst
@@ -70,8 +70,8 @@ ORCID
 :CERIF: the FederatedIdentifier entity (`<https://w3id.org/cerif/model#FederatedIdentifier>`_)
 :Format: any of:
 
-  * regular expression ``https://orcid\.org/0000-000(1-[5-9]|2-[0-9]|3-[0-4])[0-9]{3}-[0-9]{3}[0-9X]`` (The original block of 20M identifiers reserved in 2013, as per `<https://support.orcid.org/knowledgebase/articles/116780-structure-of-the-orcid-identifier>`_)
-  * regular expression ``https://orcid\.org/0009-000[0-9]-[0-9]{4}-[0-9]{3}[0-9X]`` (An additional block of 100M identifiers reserved in 2023, as per `<https://support.orcid.org/knowledgebase/articles/116780-structure-of-the-orcid-identifier>`_)
+  * regular expression ``https://orcid\.org/0000-000((1-[5-9]|2-[0-9]|3-[0-4])[0-9]{3}-[0-9]{3}[0-9X]|3-5000-0001)`` (The original block of 20M identifiers reserved in 2013, as per `<https://support.orcid.org/hc/en-us/articles/360006897674-Structure-of-the-ORCID-Identifier>`_)
+  * regular expression ``https://orcid\.org/0009-00(0[0-9]-[0-9]{4}-[0-9]{3}[0-9X]|10-0000-0000)`` (An additional block of 100M identifiers reserved in 2023, as per `<https://support.orcid.org/hc/en-us/articles/360006897674-Structure-of-the-ORCID-Identifier>`_)
 
 
 AlternativeORCID
@@ -82,8 +82,8 @@ AlternativeORCID
 :CERIF: the FederatedIdentifier entity (`<https://w3id.org/cerif/model#FederatedIdentifier>`_)
 :Format: any of:
 
-  * regular expression ``https://orcid\.org/0000-000(1-[5-9]|2-[0-9]|3-[0-4])[0-9]{3}-[0-9]{3}[0-9X]`` (The original block of 20M identifiers reserved in 2013, as per `<https://support.orcid.org/knowledgebase/articles/116780-structure-of-the-orcid-identifier>`_)
-  * regular expression ``https://orcid\.org/0009-000[0-9]-[0-9]{4}-[0-9]{3}[0-9X]`` (An additional block of 100M identifiers reserved in 2023, as per `<https://support.orcid.org/knowledgebase/articles/116780-structure-of-the-orcid-identifier>`_)
+  * regular expression ``https://orcid\.org/0000-000((1-[5-9]|2-[0-9]|3-[0-4])[0-9]{3}-[0-9]{3}[0-9X]|3-5000-0001)`` (The original block of 20M identifiers reserved in 2013, as per `<https://support.orcid.org/hc/en-us/articles/360006897674-Structure-of-the-ORCID-Identifier>`_)
+  * regular expression ``https://orcid\.org/0009-00(0[0-9]-[0-9]{4}-[0-9]{3}[0-9X]|10-0000-0000)`` (An additional block of 100M identifiers reserved in 2023, as per `<https://support.orcid.org/hc/en-us/articles/360006897674-Structure-of-the-ORCID-Identifier>`_)
 
 
 ResearcherID
diff --git a/samples/openaire_cerif_xml_example_persons.xml b/samples/openaire_cerif_xml_example_persons.xml
index faf68e9..54e3f51 100644
--- a/samples/openaire_cerif_xml_example_persons.xml
+++ b/samples/openaire_cerif_xml_example_persons.xml
@@ -318,14 +318,34 @@
             <metadata>
                 <Person xmlns="https://www.openaire.eu/cerif-profile/1.2/" id="Persons/2000002">
                 	<!-- a sample person to demonstrate the Peruvian DNI, following https://www.limaeasy.com/peru-guide/glossary-terms-peru/dni-peru-s-national-id-card -->
+                	<!-- and also used to try the very highest value of the second ORCID iDs range -->
                     <PersonName>
                         <FamilyNames>Contreras Villavicencio</FamilyNames>
                         <FirstNames>Ana Patricia</FirstNames>
                     </PersonName>
+                    <ORCID>https://orcid.org/0009-0010-0000-0000</ORCID>
                     <Identifier type="https://www.wikidata.org/wiki/Q5797148">70025425-8</Identifier>
                 </Person>
             </metadata>
         </record>
 
+        <record>
+            <header>
+                <identifier>oai:cris.example.org:Persons/2000003</identifier>
+                <datestamp>2018-01-07T14:00:00Z</datestamp>
+                <setSpec>openaire_cris_persons</setSpec>
+            </header>
+            <metadata>
+                <Person xmlns="https://www.openaire.eu/cerif-profile/1.2/" id="Persons/2000003">
+                	<!-- a sample person to demonstrate the highest value of the first ORCID iDs range -->
+                    <PersonName>
+                        <FamilyNames>musterfrau</FamilyNames>
+                        <FirstNames>katrin</FirstNames>
+                    </PersonName>
+                    <ORCID>https://orcid.org/0000-0003-5000-0001</ORCID>
+                </Person>
+            </metadata>  
+        </record>
+    
 	</ListRecords>
 </OAI-PMH>
\ No newline at end of file
diff --git a/schemas/includes/person-identifiers.xsd b/schemas/includes/person-identifiers.xsd
index 7078836..0437355 100644
--- a/schemas/includes/person-identifiers.xsd
+++ b/schemas/includes/person-identifiers.xsd
@@ -119,16 +119,16 @@
 		</xs:annotation>
 		<xs:simpleContent>
 			<xs:restriction base="cfString__Type">
-				<xs:pattern value="https://orcid\.org/0000-000(1-[5-9]|2-[0-9]|3-[0-4])[0-9]{3}-[0-9]{3}[0-9X]">
+				<xs:pattern value="https://orcid\.org/0000-000((1-[5-9]|2-[0-9]|3-[0-4])[0-9]{3}-[0-9]{3}[0-9X]|3-5000-0001)">
 					<xs:annotation>
 						<xs:documentation>The original block of 20M identifiers reserved in 2013</xs:documentation>
-						<xs:documentation source="https://support.orcid.org/knowledgebase/articles/116780-structure-of-the-orcid-identifier"/>
+						<xs:documentation source="https://support.orcid.org/hc/en-us/articles/360006897674-Structure-of-the-ORCID-Identifier"/>
 					</xs:annotation>
 				</xs:pattern>
-				<xs:pattern value="https://orcid\.org/0009-000[0-9]-[0-9]{4}-[0-9]{3}[0-9X]">
+				<xs:pattern value="https://orcid\.org/0009-00(0[0-9]-[0-9]{4}-[0-9]{3}[0-9X]|10-0000-0000)">
 					<xs:annotation>
 						<xs:documentation>An additional block of 100M identifiers reserved in 2023</xs:documentation>
-						<xs:documentation source="https://support.orcid.org/knowledgebase/articles/116780-structure-of-the-orcid-identifier"/>
+						<xs:documentation source="https://support.orcid.org/hc/en-us/articles/360006897674-Structure-of-the-ORCID-Identifier"/>
 					</xs:annotation>
 				</xs:pattern>
 			</xs:restriction>