V6.3 dans data station 10890

doc/release-notes/10814-Differencing improvement.md

@@ -0,0 +1,3 @@
+### More Scalable Dataset Version Differencing
+
+Differencing between dataset versions, which is done during dataset edit operations and to populate the dataset page versions table has been made signficantly more scalable.

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

@@ -87,7 +87,7 @@ public class DatasetFieldServiceBean implements java.io.Serializable {
 
     //Flat list of cvoc term-uri and managed fields by Id
     Set<Long> cvocFieldSet = null;
-    
+
     //The hash of the existing CVocConf setting. Used to determine when the setting has changed and it needs to be re-parsed to recreate the cvocMaps
     String oldHash = null;
 
@@ -276,9 +276,11 @@ public ControlledVocabAlternate save(ControlledVocabAlternate alt) {
      * @return - a map of JsonObjects containing configuration information keyed by the DatasetFieldType id (Long)
      */
     public Map<Long, JsonObject> getCVocConf(boolean byTermUriField){
-
+        return getCVocConf(byTermUriField, settingsService.getValueForKey(SettingsServiceBean.Key.CVocConf));
+    }
+
+    public Map<Long, JsonObject> getCVocConf(boolean byTermUriField, String cvocSetting) {
         //ToDo - change to an API call to be able to provide feedback if the json is invalid?
-        String cvocSetting = settingsService.getValueForKey(SettingsServiceBean.Key.CVocConf);
         if (cvocSetting == null || cvocSetting.isEmpty()) {
             oldHash=null;
             //Release old maps
@@ -295,7 +297,7 @@ public Map<Long, JsonObject> getCVocConf(boolean byTermUriField){
         cvocMap=new HashMap<>();
         cvocMapByTermUri=new HashMap<>();
         cvocFieldSet = new HashSet<>();
-        
+
         try (JsonReader jsonReader = Json.createReader(new StringReader(settingsService.getValueForKey(SettingsServiceBean.Key.CVocConf)))) {
             JsonArray cvocConfJsonArray = jsonReader.readArray();
             for (JsonObject jo : cvocConfJsonArray.getValuesAs(JsonObject.class)) {
@@ -356,11 +358,11 @@ public Set<Long> getCvocFieldSet() {
     /**
      * Adds information about the external vocabulary term being used in this DatasetField to the ExternalVocabularyValue table if it doesn't already exist.
      * @param df - the primitive/parent compound field containing a newly saved value
+     * @param cvocEntry
      */
-    public void registerExternalVocabValues(DatasetField df) {
+    public void registerExternalVocabValues(DatasetField df, JsonObject cvocEntry) {
         DatasetFieldType dft = df.getDatasetFieldType();
         logger.fine("Registering for field: " + dft.getName());
-        JsonObject cvocEntry = getCVocConf(true).get(dft.getId());
         if (dft.isPrimitive()) {
             List<DatasetField> siblingsDatasetFields = new ArrayList<>();
             if(dft.getParentDatasetFieldType()!=null) {

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

@@ -156,6 +156,7 @@
 import edu.harvard.iq.dataverse.search.SearchServiceBean;
 import edu.harvard.iq.dataverse.search.SearchUtil;
 import edu.harvard.iq.dataverse.search.SolrClientService;
+import edu.harvard.iq.dataverse.settings.FeatureFlags;
 import edu.harvard.iq.dataverse.settings.JvmSettings;
 import edu.harvard.iq.dataverse.util.SignpostingResources;
 import edu.harvard.iq.dataverse.util.FileMetadataUtil;
@@ -1104,7 +1105,7 @@ public Set<Long> getFileIdsInVersionFromSolr(Long datasetVersionId, String patte
         while (iter.hasNext()) {
             SolrDocument solrDocument = iter.next();
             Long entityid = (Long) solrDocument.getFieldValue(SearchFields.ENTITY_ID);
-            logger.fine("solr result id: "+entityid);
+            logger.finest("solr result id: "+entityid);
             resultIds.add(entityid);
         }
 
@@ -2695,7 +2696,9 @@ public void edit(EditMode editMode) {
             dataset = datasetService.find(dataset.getId());
         }
         workingVersion = dataset.getOrCreateEditVersion();
-        clone = workingVersion.cloneDatasetVersion();
+        if(!FeatureFlags.DISABLE_EDIT_DRAFT_LOGGING.enabled()) {
+            clone = workingVersion.cloneDatasetVersion();
+        }
         if (editMode.equals(EditMode.METADATA)) {
             datasetVersionUI = datasetVersionUI.initDatasetVersionUI(workingVersion, true);
             updateDatasetFieldInputLevels();
@@ -3950,7 +3953,10 @@ public String save() {
                 cmd = new UpdateDatasetVersionCommand(dataset, dvRequestService.getDataverseRequest(), filesToBeDeleted, clone );
                 ((UpdateDatasetVersionCommand) cmd).setValidateLenient(true);
             }
+            long start = System.currentTimeMillis();
+
             dataset = commandEngine.submit(cmd);
+            logger.fine("Save done in: " + (System.currentTimeMillis()-start) + " ms");
             if (editMode == EditMode.CREATE) {
                 if (session.getUser() instanceof AuthenticatedUser) {
                     userNotificationService.sendNotification((AuthenticatedUser) session.getUser(), dataset.getCreateDate(), UserNotification.Type.CREATEDS, dataset.getLatestVersion().getId());

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

@@ -442,6 +442,7 @@ public DatasetLock addDatasetLock(Long datasetId, DatasetLock.Reason reason, Lon
         // (to prevent multiple, duplicate locks on the dataset!)
         DatasetLock lock = dataset.getLockFor(reason);
         if (lock != null) {
+            logger.warning("There was a lock!");
             return lock;
         }