11892 bulk export

modules/dataverse-parent/pom.xml

@@ -167,6 +167,7 @@
 
         <!-- NEW gdcc XOAI library implementation -->
         <gdcc.xoai.version>5.3.0</gdcc.xoai.version>
+        <gdcc.spi.version>2.2.0-SNAPSHOT</gdcc.spi.version>
 
         <!-- Testing dependencies -->
         <testcontainers.version>2.0.2</testcontainers.version>
@@ -425,20 +426,20 @@
         </repository>
         <!-- Uncomment when using snapshot releases from Maven Central -->
         <!-- Note the new - as of Sept. 2025 sonatype url -->
-        <!--
         <repository>
             <id>central-portal-snapshots</id>
             <name>Central Portal Snapshots</name>
             <url>
                 https://central.sonatype.com/repository/maven-snapshots/
             </url>
-	    <releases>
-	      <enabled>false</enabled>
-	    </releases>
+            <releases>
+              <enabled>false</enabled>
+            </releases>
             <snapshots>
                 <enabled>true</enabled>
             </snapshots>
         </repository>
+        <!--
         <repository>
             <id>s01-oss-sonatype</id>
             <name>s01-oss-sonatype</name>

pom.xml

@@ -694,7 +694,7 @@
         <dependency>
             <groupId>io.gdcc</groupId>
             <artifactId>dataverse-spi</artifactId>
-            <version>2.0.0</version>
+            <version>${gdcc.spi.version}</version>
         </dependency>
         <dependency>
             <groupId>javax.cache</groupId>
@@ -878,13 +878,20 @@
                     <release>${target.java.version}</release>
                     <!-- for use with `mvn -DcompilerArgument=-Xlint:unchecked compile` -->
                     <compilerArgument>${compilerArgument}</compilerArgument>
-                    <!-- Ensure the annotation processor for @AutoService is picked up. Especially important as of JDK 23 -->
+                    <!-- As of JDK 23, annotation processors are opt-in. -->
                     <annotationProcessorPaths>
+                        <!-- Ensure the annotation processor for @AutoService is picked up. (older plugins) -->
                         <path>
                             <groupId>com.google.auto.service</groupId>
                             <artifactId>auto-service</artifactId>
                             <version>${auto-service.version}</version>
                         </path>
+                        <!-- Ensure the annotation processor for Dataverse Plugins is picked up. -->
+                        <path>
+                            <groupId>io.gdcc</groupId>
+                            <artifactId>dataverse-spi</artifactId>
+                            <version>${gdcc.spi.version}</version>
+                        </path>
                     </annotationProcessorPaths>
                 </configuration>
             </plugin>

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

@@ -1,5 +1,7 @@
 package edu.harvard.iq.dataverse.api;
 
+import java.util.List;
+
 public final class ApiConstants {
 
     private ApiConstants() {
@@ -17,6 +19,10 @@ private ApiConstants() {
     public static final String DS_VERSION_LATEST = ":latest";
     public static final String DS_VERSION_DRAFT = ":draft";
     public static final String DS_VERSION_LATEST_PUBLISHED = ":latest-published";
+    public static final String DS_VERSION_IDENTIFIER_REGEX = "^(:latest|:draft|:latest-published|\\d+(?:\\.\\d+)?)$";
+    public static final List<String> DS_VERSION_RESERVED_IDENTIFIERS = List.of(DS_VERSION_DRAFT, DS_VERSION_LATEST_PUBLISHED, DS_VERSION_LATEST);
+    // TODO: should be replaced by a bundle reference
+    public static final String DS_VERSION_IDENTIFIER_MESSAGE = "version must be one of :latest, :latest-published, :draft, or a numeric version like 1.0";
 
     // addFiles call
     public static final String API_ADD_FILES_COUNT_PROCESSED = "Total number of files";

src/main/java/edu/harvard/iq/dataverse/api/dto/MultiDatasetExportRequest.java

@@ -0,0 +1,67 @@
+package edu.harvard.iq.dataverse.api.dto;
+
+import edu.harvard.iq.dataverse.api.ApiConstants;
+import jakarta.validation.constraints.NotBlank;
+import jakarta.validation.constraints.NotNull;
+import jakarta.validation.constraints.Pattern;
+import jakarta.validation.constraints.Size;
+
+import java.util.List;
+
+/**
+ * Request payload for exporting multiple datasets with a single exporter.
+ *
+ * <p>Each request identifies the exporter to use and a list of dataset selections.
+ * Every dataset selection couples a persistent identifier with a version
+ * identifier so the server can resolve the exact dataset version to export.
+ *
+ * <p>This request model is intended for JSON request bodies sent to a bulk or
+ * multi-dataset export endpoint.
+ *
+ * @param exporter the name or identifier of the exporter to use; must not be blank
+ * @param datasets the datasets to export; must not be {@code null} and at least have 1 element.
+ *                 The list is defensively copied into an unmodifiable snapshot.
+ */
+public record MultiDatasetExportRequest(
+    @NotBlank String exporter,
+    @NotNull @Size(min = 1) List<ExportItem> datasets
+) {
+    /**
+     * Creates a new multi-dataset export request. The supplied dataset list is copied to preserve
+     * immutability and prevent later external modification of the request contents.
+     * @throws NullPointerException if {@code datasets} is {@code null}
+     */
+    public MultiDatasetExportRequest {
+        // Make sure to create a readonly copy, but keep null around to have bean validation catch it and complain later
+        datasets = datasets == null ? null : List.copyOf(datasets);
+    }
+
+    /**
+     * A single dataset selection within a {@link MultiDatasetExportRequest}.
+     *
+     * <p>Each item identifies one dataset to export by its persistent identifier and the specific version to resolve.
+     * The version may be one of the symbolic dataset version identifiers supported by the API, or a numeric version
+     * identifier, as validated by {@link ApiConstants#DS_VERSION_IDENTIFIER_REGEX}.
+     *
+     * @param persistentId the persistent identifier of the dataset to export; must not be blank
+     * @param version the dataset version identifier to export;
+     *                must not be blank and must match the API-supported dataset version syntax
+     */
+    public record ExportItem(
+        @NotBlank String persistentId,
+        @NotBlank
+        @Pattern(
+            regexp = ApiConstants.DS_VERSION_IDENTIFIER_REGEX,
+            // TODO: replace message with bundle reference
+            message = ApiConstants.DS_VERSION_IDENTIFIER_MESSAGE
+        )
+        String version
+    ) {
+        // If omitted or blank, apply a default version to look up (aligned with GET endpoint behavior)
+        public ExportItem {
+            if (version == null || version.isBlank()) {
+                version = ApiConstants.DS_VERSION_LATEST_PUBLISHED;
+            }
+        }
+    }
+}

src/main/java/edu/harvard/iq/dataverse/api/util/JsonResponseBuilder.java

@@ -229,10 +229,9 @@ public JsonResponseBuilder log(Logger logger, Level level, Optional<Throwable> e
         metadata.deleteCharAt(metadata.length()-1);
 
         if (ex.isPresent()) {
-            ex.get().printStackTrace();
             metadata.append("|");
             logger.log(level, metadata.toString(), ex);
-            if(includeStackTrace) {
+            if (includeStackTrace) {
                 logger.log(level, ExceptionUtils.getStackTrace(ex.get()));
             }
         } else {

src/main/java/edu/harvard/iq/dataverse/export/InternalExportDataProvider.java

@@ -1,22 +1,31 @@
 package edu.harvard.iq.dataverse.export;
 
-import java.io.InputStream;
-import java.util.Optional;
-
-import jakarta.json.Json;
-import jakarta.json.JsonArray;
-import jakarta.json.JsonArrayBuilder;
-import jakarta.json.JsonObject;
-import jakarta.json.JsonObjectBuilder;
 import edu.harvard.iq.dataverse.DataCitation;
 import edu.harvard.iq.dataverse.DataFile;
 import edu.harvard.iq.dataverse.DatasetVersion;
 import edu.harvard.iq.dataverse.FileMetadata;
 import edu.harvard.iq.dataverse.pidproviders.doi.datacite.DOIDataCiteRegisterService;
-import io.gdcc.spi.export.ExportDataProvider;
 import edu.harvard.iq.dataverse.util.bagit.OREMap;
 import edu.harvard.iq.dataverse.util.json.JsonPrinter;
 import edu.harvard.iq.dataverse.util.json.JsonUtil;
+import io.gdcc.spi.export.DatasetExportQuery;
+import io.gdcc.spi.export.ExportDataProvider;
+import io.gdcc.spi.export.FileExportQuery;
+import io.gdcc.spi.export.PageRequest;
+import jakarta.json.Json;
+import jakarta.json.JsonArray;
+import jakarta.json.JsonArrayBuilder;
+import jakarta.json.JsonObject;
+import jakarta.json.JsonObjectBuilder;
+import org.w3c.dom.Document;
+import org.xml.sax.InputSource;
+
+import javax.xml.parsers.DocumentBuilder;
+import javax.xml.parsers.DocumentBuilderFactory;
+import java.io.InputStream;
+import java.io.StringReader;
+import java.util.Optional;
+import java.util.stream.Stream;
 
 /**
  * Provides all data necessary to create an export
@@ -39,6 +48,11 @@
         this.is=is;
     }
 
+    @Override
+    public JsonObject getDatasetJson(DatasetExportQuery datasetExportQuery) {
+        return getDatasetJson();
+    }
+
     @Override
     public JsonObject getDatasetJson() {
         if (jsonRepresentation == null) {
@@ -47,7 +61,15 @@
         }
         return jsonRepresentation;
     }
-
+
+    /**
+     * Needs a better implementation, as it should replace the deprecated method.
+     */
+    @Override
+    public JsonObject getDatasetSchemaDotOrg(DatasetExportQuery datasetExportQuery) {
+        return getDatasetSchemaDotOrg();
+    }
+
     @Override
     public JsonObject getDatasetSchemaDotOrg() {
         if (schemaDotOrgRepresentation == null) {
@@ -56,21 +78,79 @@
         }
         return schemaDotOrgRepresentation;
     }
-
+
+    /**
+     * Needs a better implementation, as it should replace the deprecated method.
+     */
+    @Override
+    public JsonObject getDatasetORE(DatasetExportQuery datasetExportQuery) {
+        return getDatasetORE();
+    }
+
     @Override
     public JsonObject getDatasetORE() {
         if (oreRepresentation == null) {
             oreRepresentation = new OREMap(dv).getOREMap();
         }
         return oreRepresentation;
     }
-
+
+    /**
+     * Needs a better implementation, as it should replace the deprecated method.
+     */
+    @Override
+    public Document getDataCiteXml(DatasetExportQuery datasetExportQuery) {
+        DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
+        try
+        {
+            String dataCiteXml = getDataCiteXml();
+            DocumentBuilder builder = factory.newDocumentBuilder();
+            return builder.parse(new InputSource(new StringReader(dataCiteXml)));
+        // TODO: remove this anti-pattern of catcha-all
+        } catch (Exception e) {
+            e.printStackTrace();
+        }
+        return null;
+    }
+
     @Override
     public String getDataCiteXml() {
         return DOIDataCiteRegisterService.getMetadataFromDvObject(
                 dv.getDataset().getGlobalId().asString(), new DataCitation(dv).getDataCiteMetadata(), dv.getDataset());
     }
 
+    /**
+     * Needs a better implementation, as it should replace the deprecated method.
+     * This will trigger all sorts of N+1 query expansions, it would be much better to put the
+     * lookup in a factory method instead of on-demand when the exporter requests it.
+     * It does not at all filter anything as may be requested.
+     */
+    @Override
+    public Stream<JsonObject> getDatasetFileDetails(FileExportQuery fileExportQuery) {
+        return dv.getFileMetadatas()
+            .stream()
+            .map(fileMetadata -> {
+                DataFile dataFile = fileMetadata.getDataFile();
+                return JsonPrinter.json(dataFile, fileMetadata, true).build();
+            });
+    }
+
+    /**
+     * Needs a better implementation, as it should replace the deprecated method.
+     * This will trigger all sorts of N+1 query expansions, it would be much better to put the
+     * lookup in a factory method instead of on-demand when the exporter requests it.
+     * It does not at all filter anything as may be requested.
+     */
+    @Override
+    public Stream<JsonObject> getDatasetFileDetails(FileExportQuery fileExportQuery, PageRequest pageRequest) {
+        return dv.getFileMetadatas().subList(pageRequest.getOffset(), pageRequest.getOffset() + pageRequest.getLimit())
+            .stream()
+            .map(fileMetadata -> {
+                DataFile dataFile = fileMetadata.getDataFile();
+                return JsonPrinter.json(dataFile, fileMetadata, true).build();
+            });
+    }
+
     @Override
     public JsonArray getDatasetFileDetails() {
         JsonArrayBuilder jab = Json.createArrayBuilder();