UFAL/Fix handle duplicities during the import #1297 (#1207)

* Issue 1297 fix: don't create additional item handle on item import

* code improvement, fixed tests

* added test

* resolve Copilot comments

Author: kuchtiak-ufal

dspace-api/src/main/java/org/dspace/app/itemimport/ItemImportServiceImpl.java

@@ -348,7 +348,7 @@ public void addItems(Context c, List<Collection> mycollections,
 
      /**
       * Add relationships from a 'relationships' manifest file.
-      * 
+      *
       * @param c Context
       * @param sourceDir The parent import source directory
       * @throws Exception
@@ -452,7 +452,7 @@ protected void addRelationship(Context c, Item item, Item relationItem, String r
 
     /**
      * Get the item's entity type from meta.
-     * 
+     *
      * @param item
      * @return
      */
@@ -462,7 +462,7 @@ protected String getEntityType(Item item) {
 
     /**
      * Read the relationship manifest file.
-     * 
+     *
      * Each line in the file contains a relationship type id and an item
      * identifier in the following format:
      *
@@ -548,7 +548,7 @@ protected Map<String, List<String>> processRelationshipFile(String path, String
       * The import item map will be checked first to see if the identifier refers to an item folder
       * that was just imported. Next it will try to find the item by handle or UUID, or by a unique
       * meta value.
-      * 
+      *
       * @param c Context
       * @param itemIdentifier The identifier string found in the import manifest (handle, uuid, or import subfolder)
       * @return Item if found, or null.
@@ -606,7 +606,7 @@ protected Item resolveItem(Context c, String itemIdentifier)
 
     /**
      * Lookup an item by a (unique) meta value.
-     * 
+     *
      * @param c current DSpace session.
      * @param metaKey name of the metadata field to match.
      * @param metaValue value to be matched.
@@ -786,8 +786,18 @@ protected Item addItem(Context c, List<Collection> mycollections, String path,
         WorkspaceItem wi = null;
         WorkflowItem wfi = null;
 
+        String myhandle = null;
+
         if (!isTest) {
-            wi = workspaceItemService.create(c, mycollections.iterator().next(), template);
+            if (!useWorkflow) {
+                // only process handle file if not using workflow system
+                myhandle = processHandleFile(path + File.separatorChar + itemname, "handle");
+            }
+
+            // in case the handle exists in import file, we need to avoid new handle registration
+            // (it's almost the same as we'd create a new version of an existing item)
+            boolean isNewVersion = (myhandle != null);
+            wi = workspaceItemService.create(c, mycollections.iterator().next(), template, isNewVersion);
             myitem = wi.getItem();
         }
 
@@ -823,9 +833,6 @@ protected Item addItem(Context c, List<Collection> mycollections, String path,
                 mapOutputString = itemname + " " + myitem.getID();
             }
         } else {
-            // only process handle file if not using workflow system
-            String myhandle = processHandleFile(c, myitem, itemPathDir, "handle");
-
             // put item in system
             if (!isTest) {
                 try {
@@ -1148,13 +1155,11 @@ protected List<Collection> processCollectionFile(Context c, String path, String
     /**
      * Read in the handle file contents or return null if empty or doesn't exist
      *
-     * @param c        DSpace context
-     * @param i        DSpace item
      * @param path     path to handle file
      * @param filename name of file
      * @return handle file contents or null if doesn't exist
      */
-    protected String processHandleFile(Context c, Item i, String path, String filename) {
+    protected String processHandleFile(String path, String filename) {
         File file = new File(path + File.separatorChar + filename);
         String result = null;
 

dspace-api/src/main/java/org/dspace/content/InstallItemServiceImpl.java

@@ -89,11 +89,10 @@ public Item installItem(Context c, InProgressSubmission is,
         AuthorizeException {
         Item item = is.getItem();
         Collection collection = is.getCollection();
-
-        // Get map of filters to use for identifier types.
-        Map<Class<? extends Identifier>, Filter> filters = FilterUtils.getIdentifierFilters(false);
         try {
             if (suppliedHandle == null) {
+                // Get map of filters to use for identifier types.
+                Map<Class<? extends Identifier>, Filter> filters = FilterUtils.getIdentifierFilters(false);
                 // Register with the filters we've set up
                 identifierService.register(c, item, filters);
             } else {

dspace-api/src/main/java/org/dspace/content/service/WorkspaceItemService.java

@@ -56,7 +56,6 @@ public interface WorkspaceItemService extends InProgressSubmissionService<Worksp
     public WorkspaceItem create(Context context, Collection collection, boolean template)
         throws AuthorizeException, SQLException;
 
-
     /**
      * Create a new workspace item, with a new ID. An Item is also created. The
      * submitter is the current user in the context.

dspace-api/src/test/java/org/dspace/app/itemimport/ItemImportCLIIT.java

@@ -32,6 +32,8 @@
 import org.dspace.content.factory.ContentServiceFactory;
 import org.dspace.content.service.ItemService;
 import org.dspace.content.service.RelationshipService;
+import org.dspace.identifier.factory.IdentifierServiceFactory;
+import org.dspace.identifier.service.IdentifierService;
 import org.dspace.services.ConfigurationService;
 import org.dspace.services.factory.DSpaceServicesFactory;
 import org.flywaydb.core.internal.util.ExceptionUtils;
@@ -55,6 +57,7 @@ public class ItemImportCLIIT extends AbstractIntegrationTestWithDatabase {
     private ItemService itemService = ContentServiceFactory.getInstance().getItemService();
     private RelationshipService relationshipService = ContentServiceFactory.getInstance().getRelationshipService();
     private ConfigurationService configurationService = DSpaceServicesFactory.getInstance().getConfigurationService();
+    private IdentifierService identifierService = IdentifierServiceFactory.getInstance().getIdentifierService();
     private Collection collection;
     private Path tempDir;
     private Path workDir;
@@ -114,6 +117,26 @@ public void importItemBySafWithMetadataOnly() throws Exception {
         checkMetadata();
     }
 
+    @Test
+    public void importItemBySafWithExistingHandle() throws Exception {
+        // create simple SAF
+        Path safDir = Files.createDirectory(Path.of(tempDir.toString() + "/test"));
+        Path itemDir = Files.createDirectory(Path.of(safDir.toString() + "/item_000"));
+        Files.copy(getClass().getResourceAsStream("dublin_core.xml"),
+                Path.of(itemDir + "/dublin_core.xml"));
+        Files.copy(getClass().getResourceAsStream("handle"),
+                Path.of(itemDir + "/handle"));
+
+        String[] args = new String[] { "import", "-a", "-e", admin.getEmail(), "-c", collection.getID().toString(),
+                "-s", safDir.toString(), "-m", tempDir.toString() + "/mapfile.out" };
+        perfomImportScript(args);
+
+        Item item = findItemByTitle(publicationTitle);
+        assertEquals("123456789/3900021-03", item.getHandle());
+        checkMetadata();
+        identifierService.delete(context, item, item.getHandle());
+    }
+
     @Test
     public void importItemBySafWithBitstreams() throws Exception {
         // create simple SAF
@@ -549,7 +572,8 @@ public void deleteItemByMapFile() throws Exception {
      * @throws Exception
      */
     private void checkMetadata() throws Exception {
-        Item item = itemService.findByMetadataField(context, "dc", "title", null, publicationTitle).next();
+        Item item = findItemByTitle(publicationTitle);
+        assertEquals(1, item.getHandles().size());
         assertEquals(item.getName(), publicationTitle);
         assertEquals(itemService.getMetadata(item, "dc.date.issued"), "1990");
         assertEquals(itemService.getMetadata(item, "dc.title.alternative"), "J'aime les Printemps");
@@ -560,7 +584,7 @@ private void checkMetadata() throws Exception {
      * @throws Exception
      */
     private void checkMetadataWithAnotherSchema() throws Exception {
-        Item item = itemService.findByMetadataField(context, "dc", "title", null, publicationTitle).next();
+        Item item = findItemByTitle(publicationTitle);
         assertEquals(item.getName(), publicationTitle);
         assertEquals(itemService.getMetadata(item, "dcterms.title"), publicationTitle);
     }
@@ -570,8 +594,7 @@ private void checkMetadataWithAnotherSchema() throws Exception {
      * @throws Exception
      */
     private void checkBitstream() throws Exception {
-        Bitstream bitstream = itemService.findByMetadataField(context, "dc", "title", null, publicationTitle).next()
-                .getBundles("ORIGINAL").get(0).getBitstreams().get(0);
+        Bitstream bitstream = findItemByTitle(publicationTitle).getBundles("ORIGINAL").get(0).getBitstreams().get(0);
         assertEquals(bitstream.getName(), "file1.txt");
     }
 
@@ -589,8 +612,8 @@ private void checkItemDeletion() throws Exception {
      * @throws Exception
      */
     private void checkRelationship() throws Exception {
-        Item item = itemService.findByMetadataField(context, "dc", "title", null, publicationTitle).next();
-        Item author = itemService.findByMetadataField(context, "dc", "title", null, personTitle).next();
+        Item item = findItemByTitle(publicationTitle);
+        Item author = findItemByTitle(personTitle);
         List<Relationship> relationships = relationshipService.findByItem(context, item);
         assertEquals(1, relationships.size());
         assertEquals(author.getID(), relationships.get(0).getRightItem().getID());
@@ -601,4 +624,8 @@ private void perfomImportScript(String[] args)
             throws Exception {
         runDSpaceScript(args);
     }
+
+    private Item findItemByTitle(String title) throws Exception {
+        return itemService.findByMetadataField(context, "dc", "title", null, title).next();
+    }
 }

dspace-api/src/test/resources/org/dspace/app/itemimport/handle

@@ -0,0 +1 @@
+123456789/3900021-03