Add new RemoveGeneratedThumbnails script

Prevent dependency convergence.

CHANGELOG.md

@@ -5,6 +5,12 @@ 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).
 
 ## Unreleased
+### Added
+- New `RemoveGeneratedThumbnails` script
+
+### Updated
+- Update dspace-api dependency to 7.6.3
+- Update gson dependency to 2.11.0 to match dspace-api
 
 ## [7.6.1.3] - 2024-06-26
 ### Updated

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 7.6.1. Read more about the [DSpace curation system](https://wiki.lyrasis.org/display/DSDOC7x/Curation+System).
+Tested on DSpace 7.6.3. Read more about the [DSpace curation system](https://wiki.lyrasis.org/display/DSDOC7x/Curation+System).
 
 ## Build and Install
 

pom.xml

@@ -36,12 +36,19 @@
     <dependency>
       <groupId>com.google.code.gson</groupId>
       <artifactId>gson</artifactId>
-      <version>2.9.0</version>
+      <version>2.11.0</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>7.6.3</version>
       <scope>provided</scope>
     </dependency>
   </dependencies>

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 7.6.1. Read more about the [DSpace curation system](https://wiki.lyrasis.org/display/DSDOC5x/Curation+System).
+Tested on DSpace 7.6.3. Read more about the [DSpace curation system](https://wiki.lyrasis.org/display/DSDOC7x/Curation+System).
 
 ## Build and Install
 
@@ -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

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 7.6.1. Read more about the [DSpace curation system](https://wiki.lyrasis.org/display/DSDOC6x/Curation+System).
+Tested on DSpace 7.6.3. Read more about the [DSpace curation system](https://wiki.lyrasis.org/display/DSDOC7x/Curation+System).
 
 ## Build and Install
 

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 7.6.1.4
+ * @since 7.6.1.4
+ */
+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);
+                            }
+                        }
+                    }
+                }
+            }
+        }
+    }
+}