Enhance Metadata Export Subsystem, Part 1

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

@@ -38,12 +38,11 @@
 import edu.harvard.iq.dataverse.engine.command.impl.PublishDatasetCommand;
 import edu.harvard.iq.dataverse.engine.command.impl.PublishDataverseCommand;
 import edu.harvard.iq.dataverse.engine.command.impl.UpdateDatasetVersionCommand;
-import edu.harvard.iq.dataverse.export.ExportService;
 import edu.harvard.iq.dataverse.settings.FeatureFlags;
+import edu.harvard.iq.dataverse.export.service.ExportServiceBean;
+import edu.harvard.iq.dataverse.export.service.ExporterRegistryBean;
 import edu.harvard.iq.dataverse.util.cache.CacheFactoryBean;
 import edu.harvard.iq.dataverse.util.json.JsonUtil;
-import io.gdcc.spi.export.ExportException;
-import io.gdcc.spi.export.Exporter;
 import edu.harvard.iq.dataverse.ingest.IngestRequest;
 import edu.harvard.iq.dataverse.ingest.IngestServiceBean;
 import edu.harvard.iq.dataverse.license.LicenseServiceBean;
@@ -105,7 +104,6 @@
 import jakarta.faces.view.ViewScoped;
 import jakarta.inject.Inject;
 import jakarta.inject.Named;
-import jakarta.json.Json;
 import jakarta.json.JsonObject;
 import jakarta.json.JsonObjectBuilder;
 import jakarta.persistence.OptimisticLockException;
@@ -255,6 +253,10 @@
     DvObjectServiceBean dvObjectService;
     @EJB
     CacheFactoryBean cacheFactory;
+    @EJB
+    ExportServiceBean exportService;
+    @EJB
+    ExporterRegistryBean exporterRegistryService;
     @Inject
     DataverseRequestServiceBean dvRequestService;
     @Inject
@@ -4898,31 +4900,18 @@
     }
 
     public List< String[]> getExporters(){
-        List<String[]> retList = new ArrayList<>();
-        String myHostURL = getDataverseSiteUrl();
-        for (String [] provider : ExportService.getInstance().getExportersLabels() ){
-            String formatName = provider[1];
-            String formatDisplayName = provider[0];
-
-            Exporter exporter = null;
-            try {
-                exporter = ExportService.getInstance().getExporter(formatName);
-            } catch (ExportException ex) {
-                logger.warning("Failed to get : " + formatName);
-                logger.warning(ex.getLocalizedMessage());
-                exporter = null;
-            }
-            if (exporter != null && exporter.isAvailableToUsers()) {
-                // Not all metadata exports should be presented to the web users!
-                // Some are only for harvesting clients.
-
-                String[] temp = new String[2];
-                temp[0] = formatDisplayName;
-                temp[1] = myHostURL + "/api/datasets/export?exporter=" + formatName + "&persistentId=" + dataset.getGlobalId().asString();
-                retList.add(temp);
-            }
-        }
-        return retList;
+        String urlTemplate = getDataverseSiteUrl() + "/api/datasets/export?exporter=%s&persistentId=%s";
+
+        return exporterRegistryService.getDetails().stream()
+            .filter(ExporterRegistryBean.Details::isAvailableToUsers)
+            .map(details -> new String[]{
+                details.localizedDisplayName(),
+                urlTemplate.formatted(
+                    details.formatName(),
+                    dataset.getGlobalId().asString()
+                )
+            })
+            .toList();
     }
 
 
@@ -6136,8 +6125,7 @@
             // The full version is available from the "Export Metadata" dropdown.
             // Both versions are available via API.
             final String CROISSANT_SCHEMA_NAME = "croissantSlim";
-            ExportService instance = ExportService.getInstance();
-            String croissant = instance.getLatestPublishedAsString(dataset, CROISSANT_SCHEMA_NAME);
+            String croissant = exportService.getLatestPublishedAsString(dataset, CROISSANT_SCHEMA_NAME);
             if (FeatureFlags.CROISSANT_WITH_LOCAL_REVIEWS.enabled()) {
                 // Rewrite the export on the fly and insert local reviews until we have a solution for https://github.com/gdcc/dataverse-spi/issues/5
                 JsonObjectBuilder reviewsJsonObj = null;
@@ -6169,8 +6157,7 @@
 
     public String getJsonLd() {
         if (isThisLatestReleasedVersion()) {
-            ExportService instance = ExportService.getInstance();
-            String jsonLd = instance.getLatestPublishedAsString(dataset, SchemaDotOrgExporter.NAME);
+            String jsonLd = exportService.getLatestPublishedAsString(dataset, SchemaDotOrgExporter.NAME);
             if (jsonLd != null) {
                 logger.fine("Returning cached schema.org JSON-LD.");
                 return jsonLd;
@@ -7019,7 +7006,7 @@
             return null;
         }
         if (signpostingLinkHeader == null) {
-            SignpostingResources sr = new SignpostingResources(systemConfig, workingVersion,
+            SignpostingResources sr = new SignpostingResources(systemConfig, exporterRegistryService, workingVersion,
                     JvmSettings.SIGNPOSTING_LEVEL1_AUTHOR_LIMIT.lookupOptional().orElse(""),
                     JvmSettings.SIGNPOSTING_LEVEL1_ITEM_LIMIT.lookupOptional().orElse(""));
             signpostingLinkHeader = sr.getLinks();

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

@@ -5,7 +5,7 @@
 import edu.harvard.iq.dataverse.authorization.Permission;
 import edu.harvard.iq.dataverse.authorization.users.AuthenticatedUser;
 import edu.harvard.iq.dataverse.authorization.users.User;
 import edu.harvard.iq.dataverse.dataaccess.DataAccess;
 import edu.harvard.iq.dataverse.dataaccess.ImageThumbConverter;
 import edu.harvard.iq.dataverse.dataaccess.StorageIO;
 import edu.harvard.iq.dataverse.dataset.DatasetUtil;
@@ -16,7 +16,7 @@
 import edu.harvard.iq.dataverse.engine.command.impl.DestroyDatasetCommand;
 import edu.harvard.iq.dataverse.engine.command.impl.FinalizeDatasetPublicationCommand;
 import edu.harvard.iq.dataverse.engine.command.impl.GetDatasetStorageSizeCommand;
-import edu.harvard.iq.dataverse.export.ExportService;
+import edu.harvard.iq.dataverse.export.service.ExportServiceBean;
 import edu.harvard.iq.dataverse.globus.GlobusServiceBean;
 import edu.harvard.iq.dataverse.harvest.server.OAIRecordServiceBean;
 import edu.harvard.iq.dataverse.pidproviders.FailedPIDResolutionLoggingServiceBean;
@@ -103,6 +103,9 @@
 
     @EJB
     UserNotificationServiceBean userNotificationService;
+
+    @EJB
+    ExportServiceBean exportService;
 
     private static final SimpleDateFormat logFormatter = new SimpleDateFormat("yyyy-MM-dd'T'HH-mm-ss");
 
@@ -1081,15 +1084,10 @@
         if (countCachedExtras) {
             // count the sizes of the files cached for the dataset itself
             // (i.e., the metadata exports):
-            StorageIO<Dataset> datasetSIO = DataAccess.getStorageIO(dataset);
-
-            for (String[] exportProvider : ExportService.getInstance().getExportersLabels()) {
-                String exportLabel = "export_" + exportProvider[1] + ".cached";
-                try {
-                    total += datasetSIO.getAuxObjectSize(exportLabel);
-                } catch (IOException ioex) {
-                    // safe to ignore; object not cached
-                }
+            try {
+                total += exportService.usedCacheStorage(dataset);
+            } catch (IOException ioex) {
+                // safe to ignore; object not cached
             }
         }
 

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

@@ -6,6 +6,8 @@
 import edu.harvard.iq.dataverse.authorization.AuthenticationServiceBean;
 import edu.harvard.iq.dataverse.authorization.providers.builtin.BuiltinUserServiceBean;
 import edu.harvard.iq.dataverse.dataverse.featured.DataverseFeaturedItemServiceBean;
+import edu.harvard.iq.dataverse.export.service.ExportServiceBean;
+import edu.harvard.iq.dataverse.export.service.ExporterRegistryBean;
 import edu.harvard.iq.dataverse.license.LicenseServiceBean;
 import edu.harvard.iq.dataverse.util.cache.CacheFactoryBean;
 import edu.harvard.iq.dataverse.engine.DataverseEngine;
@@ -209,6 +211,12 @@ public class EjbDataverseEngine {
     @EJB
     CacheFactoryBean cacheFactory;
 
+    @EJB
+    ExportServiceBean exportService;
+
+    @EJB
+    ExporterRegistryBean exporterRegistry;
+
     @Resource
     EJBContext ejbCtxt;
 
@@ -664,7 +672,17 @@ public MetadataBlockServiceBean metadataBlocks() {
                 public DatasetTypeServiceBean datasetTypes() {
                     return datasetTypeService;
                 }
-
+
+                @Override
+                public ExportServiceBean exportService() {
+                    return exportService;
+                }
+
+                @Override
+                public ExporterRegistryBean exporterRegistry() {
+                    return exporterRegistry;
+                }
+
                 @Override
                 public void beginCommandSequence() {
                     this.commandsCalled = new Stack();

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

@@ -24,9 +24,10 @@
 import edu.harvard.iq.dataverse.engine.command.impl.RestrictFileCommand;
 import edu.harvard.iq.dataverse.engine.command.impl.UningestFileCommand;
 import edu.harvard.iq.dataverse.engine.command.impl.UpdateDatasetVersionCommand;
-import edu.harvard.iq.dataverse.export.ExportService;
+import edu.harvard.iq.dataverse.export.service.ExportServiceBean;
+import edu.harvard.iq.dataverse.export.service.ExporterRegistryBean;
+import edu.harvard.iq.dataverse.export.service.ExporterRegistryBean.Details;
 import io.gdcc.spi.export.ExportException;
-import io.gdcc.spi.export.Exporter;
 import edu.harvard.iq.dataverse.externaltools.ExternalTool;
 import edu.harvard.iq.dataverse.externaltools.ExternalToolHandler;
 import edu.harvard.iq.dataverse.externaltools.ExternalToolServiceBean;
@@ -36,7 +37,6 @@
 import edu.harvard.iq.dataverse.makedatacount.MakeDataCountLoggingServiceBean;
 import edu.harvard.iq.dataverse.makedatacount.MakeDataCountLoggingServiceBean.MakeDataCountEntry;
 import edu.harvard.iq.dataverse.privateurl.PrivateUrlServiceBean;
-import edu.harvard.iq.dataverse.settings.FeatureFlags;
 import edu.harvard.iq.dataverse.settings.JvmSettings;
 import edu.harvard.iq.dataverse.settings.SettingsServiceBean;
 import edu.harvard.iq.dataverse.util.BundleUtil;
@@ -64,7 +64,6 @@
 import jakarta.faces.application.FacesMessage;
 import jakarta.faces.component.UIComponent;
 import jakarta.faces.context.FacesContext;
-import jakarta.faces.validator.ValidatorException;
 import jakarta.faces.view.ViewScoped;
 import jakarta.inject.Inject;
 import jakarta.inject.Named;
@@ -129,6 +128,10 @@
     IngestServiceBean ingestService;
     @EJB
     SystemConfig systemConfig;
+    @EJB
+    ExportServiceBean exportService;
+    @EJB
+    ExporterRegistryBean exporterRegistryService;
 
 
     @Inject
@@ -466,30 +469,19 @@
         this.version = version;
     }
 
-    public List< String[]> getExporters(){
-        List<String[]> retList = new ArrayList<>();
-        String myHostURL = systemConfig.getDataverseSiteUrl();
-        for (String [] provider : ExportService.getInstance().getExportersLabels() ){
-            String formatName = provider[1];
-            String formatDisplayName = provider[0];
-
-            Exporter exporter = null; 
-            try {
-                exporter = ExportService.getInstance().getExporter(formatName);
-            } catch (ExportException ex) {
-                exporter = null;
-            }
-            if (exporter != null && exporter.isAvailableToUsers()) {
-                // Not all metadata exports should be presented to the web users!
-                // Some are only for harvesting clients.
-
-                String[] temp = new String[2];
-                temp[0] = formatDisplayName;
-                temp[1] = myHostURL + "/api/datasets/export?exporter=" + formatName + "&persistentId=" + fileMetadata.getDatasetVersion().getDataset().getGlobalId().asString();
-                retList.add(temp);
-            }
-        }
-        return retList;  
+    public List<String[]> getExporters(){
+        String urlTemplate = systemConfig.getDataverseSiteUrl() + "/api/datasets/export?exporter=%s&persistentId=%s";
+
+        return exporterRegistryService.getDetails().stream()
+            .filter(Details::isAvailableToUsers)
+            .map(details -> new String[]{
+                details.localizedDisplayName(),
+                urlTemplate.formatted(
+                    details.formatName(),
+                    fileMetadata.getDatasetVersion().getDataset().getGlobalId().asString()
+                )
+            })
+            .toList();
     }
 
     public String saveProvFreeform(String freeformTextInput, DataFile dataFileFromPopup) throws CommandException {
@@ -640,15 +632,13 @@
         editDataset = file.getOwner();
         if (editDataset.isReleased()) {
             try {
-                ExportService instance = ExportService.getInstance();
-                instance.exportAllFormats(editDataset);
-
+                exportService.exportAllFormats(editDataset);
             } catch (ExportException ex) {
                 // Something went wrong!
                 // Just like with indexing, a failure to export is not a fatal
                 // condition. We'll just log the error as a warning and keep
                 // going:
-                logger.log(Level.WARNING, "Uningest: Exception while exporting:{0}", ex.getMessage());
+                logger.log(Level.WARNING, "Uningest: Exception while exporting: {0}", ex);
             }
         }
         datafileService.save(file);

src/main/java/edu/harvard/iq/dataverse/api/AbstractApiBean.java

@@ -22,6 +22,8 @@
 import edu.harvard.iq.dataverse.engine.command.impl.GetLatestAccessibleDatasetVersionCommand;
 import edu.harvard.iq.dataverse.engine.command.impl.GetLatestPublishedDatasetVersionCommand;
 import edu.harvard.iq.dataverse.engine.command.impl.GetSpecificPublishedDatasetVersionCommand;
+import edu.harvard.iq.dataverse.export.service.ExportServiceBean;
+import edu.harvard.iq.dataverse.export.service.ExporterRegistryBean;
 import edu.harvard.iq.dataverse.externaltools.ExternalToolServiceBean;
 import edu.harvard.iq.dataverse.license.LicenseServiceBean;
 import edu.harvard.iq.dataverse.makedatacount.DatasetMetricsServiceBean;
@@ -246,6 +248,12 @@ String getWrappedMessageWhenJson() {
 
     @EJB
     TemplateServiceBean templateSvc;
+
+    @EJB
+    ExportServiceBean exportSvc;
+
+    @EJB
+    ExporterRegistryBean exporterRegistrySvc;
 
     @Inject
     FailedPIDResolutionLoggingServiceBean fprLogService;

src/main/java/edu/harvard/iq/dataverse/api/Datasets.java

@@ -35,8 +35,8 @@
 import edu.harvard.iq.dataverse.engine.command.exception.PermissionException;
 import edu.harvard.iq.dataverse.engine.command.exception.UnforcedCommandException;
 import edu.harvard.iq.dataverse.engine.command.impl.*;
-import edu.harvard.iq.dataverse.export.ExportService;
 import edu.harvard.iq.dataverse.export.croissant.CroissantExportUtil;
+import edu.harvard.iq.dataverse.export.service.ExporterRegistryBean.Details;
 import edu.harvard.iq.dataverse.externaltools.ExternalTool;
 import edu.harvard.iq.dataverse.externaltools.ExternalToolHandler;
 import edu.harvard.iq.dataverse.globus.GlobusServiceBean;
@@ -251,9 +251,11 @@
     @Produces({"application/xml", "application/json", "application/html", "application/ld+json", "*/*" })
     @Operation(summary = "Export dataset metadata",
             description = "Exports dataset metadata by persistent id using the requested version and exporter.")
-    public Response exportDataset(@Context ContainerRequestContext crc, @Parameter(description = "Persistent identifier.") @QueryParam("persistentId") String persistentId,
-            @Parameter(description = "Dataset version selector.") @QueryParam("version") String versionId, @Parameter(description = "Exporter option.") @QueryParam("exporter") String exporter,
-            @Context UriInfo uriInfo, @Context HttpHeaders headers, @Context HttpServletResponse response) {
+    public Response exportDataset(
+        @Context ContainerRequestContext crc, @Context UriInfo uriInfo, @Context HttpHeaders headers, @Context HttpServletResponse response,
+        @QueryParam("persistentId") @Parameter(description = "Persistent identifier.") String persistentId,
+        @QueryParam("version") @Parameter(description = "Dataset version selector.") String versionId,
+        @QueryParam("exporter") @Parameter(description = "Exporter option.") String exporter) {
 
         try {
             Dataset dataset = datasetService.findByGlobalId(persistentId);
@@ -285,10 +287,13 @@
                     return error(BAD_REQUEST, "Non-draft version requested (" + versionId + ") but for published versions only the latest (" + DS_VERSION_LATEST_PUBLISHED + ") is supported.");
                 }
             }
-
-            ExportService instance = ExportService.getInstance();
-
-            InputStream is = instance.getExport(datasetVersion, exporter);
+
+            Optional<Details> exporterDetails = exporterRegistrySvc.getDetail(exporter);
+            if (exporterDetails.isEmpty()) {
+                return error(BAD_REQUEST, "Export failed: no exporter registered for format name " + exporter);
+            }
+
+            InputStream is = exportSvc.getExport(datasetVersion, exporter);
             if (FeatureFlags.CROISSANT_WITH_LOCAL_REVIEWS.enabled()
                     && (exporter.equals("croissant") || exporter.equals("croissantSlim"))) {
                 // Rewrite the export on the fly and insert local reviews until we have a solution for https://github.com/gdcc/dataverse-spi/issues/5
@@ -300,18 +305,16 @@
                         .add("reviews", reviews.build().getJsonArray("reviews")).build().toString();
                 is = new ByteArrayInputStream(updatedContent.getBytes(StandardCharsets.UTF_8));
             }
-
-            String mediaType = instance.getMediaType(exporter);
-
+
             if (datasetVersion.isReleased()) {
                 MakeDataCountLoggingServiceBean.MakeDataCountEntry entry = new MakeDataCountEntry(uriInfo, headers, dvRequestService, dataset);
                 mdcLogService.logEntry(entry);
             }
-
+            
             return Response.ok()
-                    .entity(is)
-                    .type(mediaType).
-                    build();
+                .entity(is)
+                .type(exporterDetails.get().mediaType()).
+                build();
         } catch (Exception wr) {
             logger.warning(wr.getMessage());
             return error(Response.Status.FORBIDDEN, "Export Failed");
@@ -801,7 +804,7 @@
             return Response
                     .ok(JsonUtil.createObjectBuilder()
                             .add("linkset",
-                                    new SignpostingResources(systemConfig, dsv,
+                                    new SignpostingResources(systemConfig, exporterRegistrySvc, dsv,
                                             JvmSettings.SIGNPOSTING_LEVEL1_AUTHOR_LIMIT.lookupOptional().orElse(""),
                                             JvmSettings.SIGNPOSTING_LEVEL1_ITEM_LIMIT.lookupOptional().orElse(""))
                                                     .getJsonLinkset())
@@ -1997,7 +2000,7 @@
 
         // dateAvailable is within limits
         if (minRetentionDateTime != null){
             if (dateUnavailable.isBefore(minRetentionDateTime.minusDays(1))){
                 return error(Status.BAD_REQUEST, "Date unavailable can not be earlier than MinRetentionDurationInMonths: "+minRetentionDurationInMonths + " from now");
             }
         }