Merge pull request #11003 from GlobalDataverseCommunityConsortium/Har…

…vestDatasetUsingPID

Fix lookups of Harvested datasets with lower-case versions of persistent identifiers in the database

doc/release-notes/10708 - MDC Citation and DOI parsing improvements.md

@@ -1,3 +1,3 @@
 MDC Citation retrieval with the PID settings has been fixed.
-DOI parsing in Dataverse is case insensitive, improving interaction with services that may change the case.
+PID parsing in Dataverse is now case insensitive, improving interaction with services that may change the case of PIDs.
 Warnings related to managed/excluded PID lists for PID providers have been reduced

doc/sphinx-guides/source/installation/config.rst

@@ -236,6 +236,10 @@ Dataverse automatically manages assigning PIDs and making them findable when dat
 allow updating the PID target URLs and metadata of already-published datasets manually if needed <send-metadata-to-pid-provider>`, e.g. if a Dataverse instance is
 moved to a new URL or when the software is updated to generate additional metadata or address schema changes at the PID service.
 
+Note that while some forms of PIDs (Handles, PermaLinks) are technically case sensitive, common practice is to avoid creating PIDs that differ only by case.
+Dataverse treats PIDs of all types as case-insensitive (as DOIs are by definition). This means that Dataverse will find datasets (in search, to display dataset pages, etc.) 
+when the PIDs entered do not match the case of the original but will have a problem if two PIDs that differ only by case exist in one instance.
+
 Testing PID Providers
 +++++++++++++++++++++
 

src/main/java/edu/harvard/iq/dataverse/DvObject.java

@@ -27,17 +27,17 @@
     @NamedQuery(name = "DvObject.ownedObjectsById",
 			query="SELECT COUNT(obj) FROM DvObject obj WHERE obj.owner.id=:id"),
     @NamedQuery(name = "DvObject.findByGlobalId",
-            query = "SELECT o FROM DvObject o WHERE o.identifier=:identifier and o.authority=:authority and o.protocol=:protocol and o.dtype=:dtype"),
+            query = "SELECT o FROM DvObject o WHERE UPPER(o.identifier)=UPPER(:identifier) and o.authority=:authority and o.protocol=:protocol and o.dtype=:dtype"),
     @NamedQuery(name = "DvObject.findIdByGlobalId",
-            query = "SELECT o.id FROM DvObject o WHERE o.identifier=:identifier and o.authority=:authority and o.protocol=:protocol and o.dtype=:dtype"),
+            query = "SELECT o.id FROM DvObject o WHERE UPPER(o.identifier)=UPPER(:identifier) and o.authority=:authority and o.protocol=:protocol and o.dtype=:dtype"),
 
     @NamedQuery(name = "DvObject.findByAlternativeGlobalId",
             query = "SELECT o FROM DvObject o, AlternativePersistentIdentifier a  WHERE o.id = a.dvObject.id and a.identifier=:identifier and a.authority=:authority and a.protocol=:protocol and o.dtype=:dtype"),
     @NamedQuery(name = "DvObject.findIdByAlternativeGlobalId",
             query = "SELECT o.id FROM DvObject o, AlternativePersistentIdentifier a  WHERE o.id = a.dvObject.id and a.identifier=:identifier and a.authority=:authority and a.protocol=:protocol and o.dtype=:dtype"),
 
     @NamedQuery(name = "DvObject.findByProtocolIdentifierAuthority",
-            query = "SELECT o FROM DvObject o WHERE o.identifier=:identifier and o.authority=:authority and o.protocol=:protocol"),
+            query = "SELECT o FROM DvObject o WHERE UPPER(o.identifier)=UPPER(:identifier) and o.authority=:authority and o.protocol=:protocol"),
     @NamedQuery(name = "DvObject.findByOwnerId", 
                 query = "SELECT o FROM DvObject o WHERE o.owner.id=:ownerId  order by o.dtype desc, o.id"),
     @NamedQuery(name = "DvObject.findByAuthenticatedUserId", 
@@ -53,7 +53,8 @@
 @Table(indexes = {@Index(columnList="dtype")
 		, @Index(columnList="owner_id")
 		, @Index(columnList="creator_id")
-		, @Index(columnList="releaseuser_id")},
+		, @Index(columnList="releaseuser_id")
+        , @Index(columnList="authority,protocol, UPPER(identifier)", name="INDEX_DVOBJECT_authority_protocol_upper_identifier")},
 		uniqueConstraints = {@UniqueConstraint(columnNames = {"authority,protocol,identifier"}),@UniqueConstraint(columnNames = {"owner_id,storageidentifier"})})
 public abstract class DvObject extends DataverseEntity implements java.io.Serializable {
 

src/main/java/edu/harvard/iq/dataverse/api/imports/ImportServiceBean.java

@@ -313,7 +313,7 @@ public Dataset doImportHarvestedDataset(DataverseRequest dataverseRequest, Harve
                 // Creating a new dataset from scratch:
 
                 harvestedDataset = parser.parseDataset(obj);
-                
+
                 harvestedDataset.setHarvestedFrom(harvestingClient);
                 harvestedDataset.setHarvestIdentifier(harvestIdentifier);
 

src/main/java/edu/harvard/iq/dataverse/pidproviders/handle/HandlePidProvider.java

@@ -59,6 +59,11 @@
  * service. 
  * As of now, it only does the registration updates, to accommodate 
  * the modifyRegistration datasets API sub-command.
+ * 
+ * Note that while Handles are nominally case sensitive, handle.net is
+ * configured to be case-insensitive and Dataverse makes case-insensitve
+ * database look-ups to find Handles (See #11003). That said, database
+ * entries are stored in the case matching the configuration of the provider.
  */
 public class HandlePidProvider extends AbstractPidProvider {
 

src/main/java/edu/harvard/iq/dataverse/pidproviders/perma/PermaLinkPidProvider.java

@@ -24,6 +24,9 @@
  * overridable by a configurable parameter to support use of an external
  * resolver.
  * 
+ * Note that while PermaLinks are nominally case sensitive, Dataverse makes 
+ * case-insensitve database look-ups to find them (See #11003). That said, database
+ * entries are stored in the case matching the configuration of the provider.
  */
 public class PermaLinkPidProvider extends AbstractPidProvider {
 

src/main/resources/db/migration/V6.4.0.1.sql

@@ -0,0 +1,4 @@
+-- Adding a case-insensitive index related to #11003
+--
+
+CREATE UNIQUE INDEX IF NOT EXISTS INDEX_DVOBJECT_authority_protocol_upper_identifier ON dvobject (authority, protocol, UPPER(identifier));

src/test/java/edu/harvard/iq/dataverse/pidproviders/PidUtilTest.java

@@ -99,7 +99,7 @@
 @JvmSetting(key = JvmSettings.PID_PROVIDER_LABEL, value = "FAKE 1", varArgs = "fake1")
 @JvmSetting(key = JvmSettings.PID_PROVIDER_TYPE, value = FakeDOIProvider.TYPE, varArgs = "fake1")
 @JvmSetting(key = JvmSettings.PID_PROVIDER_AUTHORITY, value = "10.5074", varArgs = "fake1")
-@JvmSetting(key = JvmSettings.PID_PROVIDER_SHOULDER, value = "FK", varArgs = "fake1")
+@JvmSetting(key = JvmSettings.PID_PROVIDER_SHOULDER, value = "fk", varArgs = "fake1")
 @JvmSetting(key = JvmSettings.PID_PROVIDER_MANAGED_LIST, value = "doi:10.5073/FK3ABCDEF", varArgs ="fake1")
 
 //HANDLE 1
@@ -315,6 +315,13 @@ public void testUnmanagedParsing() throws IOException {
         GlobalId pid6 = PidUtil.parseAsGlobalID(pid6String);
         assertEquals(pid6String, pid6.asString());
         assertEquals(UnmanagedPermaLinkPidProvider.ID, pid6.getProviderId());
+
+        //Lowercase test for unmanaged DOIs
+        String pid7String = "doi:10.5281/zenodo.6381129";
+        GlobalId pid7 = PidUtil.parseAsGlobalID(pid7String);
+        assertEquals(UnmanagedDOIProvider.ID, pid5.getProviderId());
+        assertEquals(pid7String.toUpperCase().replace("DOI", "doi"), pid7.asString());
+
 
     }
 
@@ -353,15 +360,15 @@ public void testExcludedSetParsing() throws IOException {
     @Test
     public void testManagedSetParsing() throws IOException {
 
-        String pid1String = "doi:10.5073/FK3ABCDEF";
+        String pid1String = "doi:10.5073/fk3ABCDEF";
         GlobalId pid2 = PidUtil.parseAsGlobalID(pid1String);
-        assertEquals(pid1String, pid2.asString());
+        assertEquals(pid1String.toUpperCase().replace("DOI", "doi"), pid2.asString());
         assertEquals("fake1", pid2.getProviderId());
         assertEquals("https://doi.org/" + pid2.getAuthority() + PidUtil.getPidProvider(pid2.getProviderId()).getSeparator() + pid2.getIdentifier(),pid2.asURL());
         assertEquals("10.5073", pid2.getAuthority());
         assertEquals(AbstractDOIProvider.DOI_PROTOCOL, pid2.getProtocol());
         GlobalId pid3 = PidUtil.parseAsGlobalID(pid2.asURL());
-        assertEquals(pid1String, pid3.asString());
+        assertEquals(pid1String.toUpperCase().replace("DOI", "doi"), pid3.asString());
         assertEquals("fake1", pid3.getProviderId());
         assertFalse(PidUtil.getPidProvider(pid3.getProviderId()).canCreatePidsLike(pid3));