.github/workflows/maven.yml: use latest actions

Tested on DSpace 8.2.

.github/workflows/maven.yml

@@ -5,19 +5,19 @@ name: Build
 
 on:
   push:
-    branches: [ dspace7 ]
+    branches: [ dspace8 ]
   pull_request:
-    branches: [ dspace7 ]
+    branches: [ dspace8 ]
 
 jobs:
   build:
 
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-24.04
 
     steps:
-    - uses: actions/checkout@v4
+    - uses: actions/checkout@v5
     - name: Set up JDK 17
-      uses: actions/setup-java@v4
+      uses: actions/setup-java@v5
       with:
         java-version: 17
         distribution: 'temurin'

CHANGELOG.md

@@ -4,6 +4,19 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [8.2.0] - 2025-09-16
+### Added
+- New `RemoveGeneratedThumbnails` script
+
+### Updated
+- Update dspace-api dependency to 8.2
+- Update gson dependency to 2.13.1 to match dspace-api
+- Publish to Maven Central instead of OSSRH
+
+## [7.6.1.3] - 2024-06-26
+### Updated
+- Add more formats to `NormalizeDOIs` curation task
+
 ## [7.6.1.2] - 2024-04-25
 ### Changed
 - Remove reporting from curation tasks since "results" are enough

README.md

@@ -4,9 +4,10 @@ DSpace curation tasks and other Java-based helpers used on the [CGSpace](https:/
 - **CountryCodeTagger**: add ISO 3166-1 Alpha2 country codes to items based on their existing country metadata
 - **FixJpgJpgThumbnails**: fix low-quality ".jpg.jpg" thumbnails by replacing them with their originals
 - **FixLowQualityThumbnails**: remove low-quality thumbnails when PDF bitstreams are present
+- **RemoveGeneratedThumbnails**: remove generated thumbnails (in preparation for re-generating)
 - **NormalizeDOIs**: normalize DOIs by stripping whitespace, lowercasing, and converting to https://doi.org/ format
 
-Tested on DSpace 7.6. Read more about the [DSpace curation system](https://wiki.lyrasis.org/display/DSDOC7x/Curation+System).
+Tested on DSpace 8.2. Read more about the [DSpace curation system](https://wiki.lyrasis.org/display/DSDOC8x/Curation+System).
 
 ## Build and Install
 
@@ -17,7 +18,7 @@ To use these curation tasks in a DSpace project add the following dependency to
 <dependency>
   <groupId>io.github.ilri.cgspace</groupId>
   <artifactId>cgspace-java-helpers</artifactId>
-  <version>7.6.1.2-SNAPSHOT</version>
+  <version>8.2.0-SNAPSHOT</version>
 </dependency>
 ```
 
@@ -33,7 +34,7 @@ $ mvn package
 Copy the resulting jar to the DSpace `lib` directory:
 
 ```console
-$ cp target/cgspace-java-helpers-7.6.1.2-SNAPSHOT.jar ~/dspace/lib/
+$ cp target/cgspace-java-helpers-8.2.0-SNAPSHOT.jar ~/dspace/lib/
 ```
 
 ## Configuration
@@ -42,11 +43,6 @@ Please refer to the appropriate README.md file:
 - Curation Tasks: [src/main/java/io/github/ilri/cgspace/ctasks/README.md](https://github.com/ilri/cgspace-java-helpers/blob/dspace7/src/main/java/io/github/ilri/cgspace/ctasks/README.md)
 - Scripts: [src/main/java/io/github/ilri/cgspace/scripts/README.md](https://github.com/ilri/cgspace-java-helpers/blob/dspace7/src/main/java/io/github/ilri/cgspace/scripts/README.md)
 
-## TODO
-
-- Migrate from maven-deploy-plugin to nexus-staging-maven-plugin, see: https://central.sonatype.org/publish/publish-maven/#nexus-staging-maven-plugin-for-deployment-and-release
-- Stop using oss-parent, see: https://central.sonatype.org/publish/publish-maven/#create-a-ticket-with-sonatype
-
 ## Notes
 This project was initially created according to the [Maven Getting Started Guide](https://maven.apache.org/guides/getting-started/):
 

pom.xml

@@ -6,10 +6,19 @@
 
   <groupId>io.github.ilri.cgspace</groupId>
   <artifactId>cgspace-java-helpers</artifactId>
-  <version>7.6.1.2-SNAPSHOT</version>
+  <version>8.2.0-SNAPSHOT</version>
 
   <name>cgspace-java-helpers</name>
   <url>https://github.com/ilri/cgspace-java-helpers</url>
+  <description>Curation tasks and helper scripts for the CGSpace institutional repository</description>
+
+  <developers>
+    <developer>
+      <name>Alan Orth</name>
+      <email>maven@mjanja.mozmail.com</email>
+      <organizationUrl>https://mjanja.ch</organizationUrl>
+    </developer>
+  </developers>
 
   <licenses>
     <license>
@@ -18,29 +27,28 @@
     </license>
   </licenses>
 
-  <!-- brings the sonatype snapshot repository and signing requirement on board -->
-  <parent>
-    <groupId>org.sonatype.oss</groupId>
-    <artifactId>oss-parent</artifactId>
-    <version>9</version>
-    <relativePath />
-  </parent>
-
   <properties>
     <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
-    <maven.compiler.release>11</maven.compiler.release>
+    <maven.compiler.release>17</maven.compiler.release>
   </properties>
 
   <dependencies>
     <dependency>
       <groupId>com.google.code.gson</groupId>
       <artifactId>gson</artifactId>
-      <version>2.9.0</version>
+      <version>2.13.1</version>
+      <!-- Ignore gson's dependency on error_prone_annotations because it causes dependency convergence with something pulled in by dspace-api -->
+      <exclusions>
+        <exclusion>
+          <groupId>com.google.errorprone</groupId>
+            <artifactId>error_prone_annotations</artifactId>
+          </exclusion>
+      </exclusions>
     </dependency>
     <dependency>
       <groupId>org.dspace</groupId>
       <artifactId>dspace-api</artifactId>
-      <version>7.6.1</version>
+      <version>8.2</version>
       <scope>provided</scope>
     </dependency>
   </dependencies>
@@ -51,19 +59,7 @@
       <url>https://github.com/ilri/cgspace-java-helpers</url>
   </scm>
 
-  <distributionManagement>
-      <snapshotRepository>
-          <id>ossrh</id>
-          <url>https://oss.sonatype.org/content/repositories/snapshots</url>
-      </snapshotRepository>
-      <repository>
-          <id>ossrh</id>
-          <url>https://oss.sonatype.org/service/local/staging/deploy/maven2</url>
-      </repository>
-  </distributionManagement>
-
   <build>
-    <pluginManagement><!-- lock down plugins versions to avoid using Maven defaults (may be moved to parent pom) -->
     <plugins>
       <!-- clean lifecycle, see https://maven.apache.org/ref/current/maven-core/lifecycles.html#clean_Lifecycle -->
       <plugin>
@@ -91,10 +87,6 @@
         <artifactId>maven-install-plugin</artifactId>
         <version>3.1.1</version>
       </plugin>
-        <plugin>
-          <artifactId>maven-deploy-plugin</artifactId>
-          <version>3.1.1</version>
-        </plugin>
       <!-- site lifecycle, see https://maven.apache.org/ref/current/maven-core/lifecycles.html#site_Lifecycle -->
       <plugin>
         <artifactId>maven-site-plugin</artifactId>
@@ -104,8 +96,16 @@
         <artifactId>maven-project-info-reports-plugin</artifactId>
         <version>3.5.0</version>
       </plugin>
+      <plugin>
+        <groupId>org.sonatype.central</groupId>
+        <artifactId>central-publishing-maven-plugin</artifactId>
+        <version>0.8.0</version>
+        <extensions>true</extensions>
+        <configuration>
+          <publishingServerId>central</publishingServerId>
+        </configuration>
+      </plugin>
     </plugins>
-    </pluginManagement>
   </build>
 
   <repositories>

src/main/java/io/github/ilri/cgspace/ctasks/NormalizeDOIs.java

@@ -29,7 +29,7 @@ import java.util.List;
  * TODO: allow operation on communities and collections (currently only works on items)
  *
  * @author Alan Orth for the International Livestock Research Institute
- * @version 7.6.1.2
+ * @version 7.6.1.3
  * @since 7.6.1.1
  */
 @Suspendable
@@ -78,17 +78,21 @@ public class NormalizeDOIs extends AbstractCurationTask {
     }
 
     private static String getNormalizedDOI(MetadataValue itemDOI) {
-        // 1. Convert to lowercase
+        // Convert to lowercase
         String newDOI = itemDOI.getValue().toLowerCase();
-        // 2. Strip leading and trailing whitespace
+        // Strip leading and trailing whitespace
         newDOI = newDOI.strip();
-        // 3. Convert to HTTPS
+        // Convert to HTTPS
         newDOI = newDOI.replace("http://", "https://");
-        // 4. Prefer doi.org to dx.doi.org
+        // Prefer doi.org to dx.doi.org
         newDOI = newDOI.replace("dx.doi.org", "doi.org");
-        // 5. Replace values like doi: 10.11648/j.jps.20140201.14
+        // Prefer doi.org to www.doi.org
+        newDOI = newDOI.replace("www.doi.org", "doi.org");
+        // Fix URL encoded slashes (%2f)
+        newDOI = newDOI.replace("%2f", "/");
+        // Replace values like doi: 10.11648/j.jps.20140201.14
         newDOI = newDOI.replaceAll("^doi: 10\\.", "https://doi.org/10.");
-        // 6. Replace values like 10.3390/foods12010115
+        // Replace values like 10.3390/foods12010115
         newDOI = newDOI.replaceAll("^10\\.", "https://doi.org/10.");
 
         return newDOI;

src/main/java/io/github/ilri/cgspace/ctasks/README.md

@@ -4,7 +4,7 @@ DSpace curation tasks used on the [CGSpace](https://cgspace.cgiar.org) instituti
 - **CountryCodeTagger**: add ISO 3166-1 Alpha2 country codes to items based on their existing country metadata
 - **NormalizeDOIs**: normalize DOIs by stripping whitespace, lowercasing, and converting to https://doi.org/ format
 
-Tested on DSpace 7.6. Read more about the [DSpace curation system](https://wiki.lyrasis.org/display/DSDOC5x/Curation+System).
+Tested on DSpace 8.2. Read more about the [DSpace curation system](https://wiki.lyrasis.org/display/DSDOC8x/Curation+System).
 
 ## Build and Install
 
@@ -15,7 +15,7 @@ To use these curation tasks in a DSpace project add the following dependency to
 <dependency>
   <groupId>io.github.ilri.cgspace</groupId>
   <artifactId>cgspace-java-helpers</artifactId>
-  <version>7.6.1.2-SNAPSHOT</version>
+  <version>8.2.0-SNAPSHOT</version>
 </dependency>
 ```
 
@@ -31,7 +31,7 @@ $ mvn package
 Copy the resulting jar to the DSpace `lib` directory:
 
 ```
-$ cp target/cgspace-java-helpers-7.6.1.2-SNAPSHOT.jar ~/dspace/lib/
+$ cp target/cgspace-java-helpers-8.2.0-SNAPSHOT.jar ~/dspace/lib/
 ```
 
 ## Configuration
@@ -43,7 +43,7 @@ plugin.named.org.dspace.curate.CurationTask = io.github.ilri.cgspace.ctasks.Coun
 plugin.named.org.dspace.curate.CurationTask = io.github.ilri.cgspace.ctasks.NormalizeDOIs = normalizedois
 ```
 
-And then add the following variables to your `local.cfg` or some other [configuration file that is included](https://wiki.lyrasis.org/display/DSDOC6x/Configuration+Reference#ConfigurationReference-IncludingotherPropertyFiles):
+And then add the following variables to your `local.cfg` or some other [configuration file that is included](https://wiki.lyrasis.org/display/DSDOC7x/Configuration+Reference#ConfigurationReference-IncludingotherPropertyFiles):
 
 ```
 # name of the field containing ISO 3166-1 country names
@@ -62,7 +62,7 @@ countrycodetagger.iso3166-alpha2.field = cg.coverage.iso3166-alpha2
 Once the jar is installed and you have added appropriate configuration in `~/dspace/config/modules`:
 
 ```
-$ ~/dspace/bin/dspace curate -t countrycodetagger -i 10568/3 -r - -s object
+$ ~/dspace/bin/dspace curate -e eperson@repo.org -t countrycodetagger -i 10568/3 -r - -s object
 ```
 
 *Note*: it is very important to set the database transaction scope to something sensible (`object`) if you're curating a community or collection with more than a few hundred items.

src/main/java/io/github/ilri/cgspace/scripts/README.md

@@ -3,8 +3,9 @@ Java-based helpers used on the [CGSpace](https://cgspace.cgiar.org) institutiona
 
 - **FixJpgJpgThumbnails**: fix low-quality ".jpg.jpg" thumbnails by replacing them with their originals
 - **FixLowQualityThumbnails**: remove low-quality thumbnails when PDF bitstreams are present
+- **RemoveGeneratedThumbnails**: remove generated thumbnails (in preparation for re-generating)
 
-Tested on DSpace 7.6. Read more about the [DSpace curation system](https://wiki.lyrasis.org/display/DSDOC6x/Curation+System).
+Tested on DSpace 8.2. Read more about the [DSpace curation system](https://wiki.lyrasis.org/display/DSDOC8x/Curation+System).
 
 ## Build and Install
 
@@ -15,7 +16,7 @@ To use these curation tasks in a DSpace project add the following dependency to
 <dependency>
   <groupId>io.github.ilri.cgspace</groupId>
   <artifactId>cgspace-java-helpers</artifactId>
-  <version>7.6.1.2-SNAPSHOT</version>
+  <version>8.2.0-SNAPSHOT</version>
 </dependency>
 ```
 
@@ -31,7 +32,7 @@ $ mvn package
 Copy the resulting jar to the DSpace `lib` directory:
 
 ```console
-$ cp target/cgspace-java-helpers-7.6.1.2-SNAPSHOT.jar ~/dspace/lib/
+$ cp target/cgspace-java-helpers-8.2.0-SNAPSHOT.jar ~/dspace/lib/
 ```
 
 ## Invocation

src/main/java/io/github/ilri/cgspace/scripts/RemoveGeneratedThumbnails.java

@@ -0,0 +1,149 @@
+/*
+ * Copyright (C) 2025 Alan Orth
+ *
+ * SPDX-License-Identifier: GPL-3.0-only
+ */
+
+package io.github.ilri.cgspace.scripts;
+
+import org.apache.commons.lang.StringUtils;
+import org.dspace.authorize.AuthorizeException;
+import org.dspace.content.Bitstream;
+import org.dspace.content.Bundle;
+import org.dspace.content.Collection;
+import org.dspace.content.Community;
+import org.dspace.content.DSpaceObject;
+import org.dspace.content.Item;
+import org.dspace.content.MetadataValue;
+import org.dspace.content.factory.ContentServiceFactory;
+import org.dspace.content.service.BundleService;
+import org.dspace.content.service.ItemService;
+import org.dspace.core.Constants;
+import org.dspace.core.Context;
+import org.dspace.handle.factory.HandleServiceFactory;
+import org.dspace.handle.service.HandleService;
+
+import java.io.IOException;
+import java.sql.SQLException;
+import java.util.Iterator;
+import java.util.List;
+
+/**
+ * @author Andrea Schweer schweer@waikato.ac.nz for the LCoNZ Institutional Research Repositories
+ * @author Alan Orth for the International Livestock Research Institute
+ * @version 8.2.0
+ * @since 8.2.0
+ */
+public class RemoveGeneratedThumbnails {
+    // note: static members belong to the class itself, not any one instance
+    public static ItemService itemService = ContentServiceFactory.getInstance().getItemService();
+    public static HandleService handleService =
+            HandleServiceFactory.getInstance().getHandleService();
+    public static BundleService bundleService =
+            ContentServiceFactory.getInstance().getBundleService();
+
+    public static void main(String[] args) {
+        String parentHandle = null;
+        if (args.length >= 1) {
+            parentHandle = args[0];
+        }
+
+        Context context = null;
+        try {
+            context = new Context();
+            context.turnOffAuthorisationSystem();
+
+            if (StringUtils.isBlank(parentHandle)) {
+                process(context, itemService.findAll(context));
+            } else {
+                DSpaceObject parent = handleService.resolveToObject(context, parentHandle);
+                if (parent != null) {
+                    switch (parent.getType()) {
+                        case Constants.SITE:
+                            process(context, itemService.findAll(context));
+                            context.commit();
+                            break;
+                        case Constants.COMMUNITY:
+                            List<Collection> collections = ((Community) parent).getCollections();
+                            for (Collection collection : collections) {
+                                process(
+                                        context,
+                                        itemService.findAllByCollection(context, collection));
+                            }
+                            context.commit();
+                            break;
+                        case Constants.COLLECTION:
+                            process(
+                                    context,
+                                    itemService.findByCollection(context, (Collection) parent));
+                            context.commit();
+                            break;
+                        case Constants.ITEM:
+                            processItem(context, (Item) parent);
+                            context.commit();
+                            break;
+                    }
+                }
+            }
+        } catch (SQLException | AuthorizeException | IOException e) {
+            e.printStackTrace(System.err);
+        } finally {
+            if (context != null && context.isValid()) {
+                context.abort();
+            }
+        }
+    }
+
+    private static void process(Context context, Iterator<Item> items)
+            throws SQLException, IOException, AuthorizeException {
+        while (items.hasNext()) {
+            Item item = items.next();
+            processItem(context, item);
+            itemService.update(context, item);
+        }
+    }
+
+    private static void processItem(Context context, Item item)
+            throws SQLException, AuthorizeException, IOException {
+        List<Bundle> thumbnailBundles = item.getBundles("THUMBNAIL");
+        for (Bundle thumbnailBundle : thumbnailBundles) {
+            List<Bitstream> thumbnailBundleBitstreams = thumbnailBundle.getBitstreams();
+            for (Bitstream thumbnailBitstream : thumbnailBundleBitstreams) {
+                String thumbnailName = thumbnailBitstream.getName();
+                String thumbnailDescription = thumbnailBitstream.getDescription();
+
+                // There is no point continuing if the thumbnail's description is empty or null
+                if (StringUtils.isEmpty(thumbnailDescription)) {
+                    continue;
+                }
+
+                if (thumbnailName.toLowerCase().endsWith(".pdf.jpg")) {
+                    List<Bundle> originalBundles = item.getBundles("ORIGINAL");
+                    for (Bundle originalBundle : originalBundles) {
+                        List<Bitstream> originalBundleBitstreams = originalBundle.getBitstreams();
+
+                        for (Bitstream originalBitstream : originalBundleBitstreams) {
+                            String originalName = originalBitstream.getName();
+
+                            /*
+                            - check if the original file name is the same as the thumbnail name minus the extra ".jpg"
+                            - check if the thumbnail description indicates it was automatically generated
+                            */
+                            if (originalName.equalsIgnoreCase(
+                                            StringUtils.removeEndIgnoreCase(thumbnailName, ".jpg"))
+                                    && ("Generated Thumbnail".equals(thumbnailDescription)
+                                            || "IM Thumbnail".equals(thumbnailDescription))) {
+                                System.out.println(
+                                        item.getHandle()
+                                                + ": removing "
+                                                + thumbnailName);
+
+                                thumbnailBundle.removeBitstream(thumbnailBitstream);
+                            }
+                        }
+                    }
+                }
+            }
+        }
+    }
+}