Version 6.0

Need to use the new DSpace 6 service model in most places. Not sure
why addBitstream is no longer public, but removeBitstream is...

README.md

@@ -1,9 +1,10 @@
-# DSpace Curation Tasks [![Build Status](https://travis-ci.org/ilri/dspace-curation-tasks.svg?branch=master)](https://travis-ci.org/ilri/dspace-curation-tasks)
-Metadata curation tasks used on the [CGSpace](https://cgspace.cgiar.org) institutional repository:
+# CGSpace Java Helpers [![Build Status](https://travis-ci.org/ilri/cgspace-java-helpers.svg?branch=dspace6)](https://travis-ci.org/ilri/cgspace-java-helpers)
+DSpace curation tasks and other Java-based helpers used on the [CGSpace](https://cgspace.cgiar.org) institutional repository:
 
 - **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
 
-Tested on DSpace 5.8. Read more about the [DSpace curation system](https://wiki.lyrasis.org/display/DSDOC5x/Curation+System).
+Tested on DSpace 6.3. Read more about the [DSpace curation system](https://wiki.lyrasis.org/display/DSDOC5x/Curation+System).
 
 ## Build and Install
 
@@ -13,8 +14,8 @@ To use these curation tasks in a DSpace project add the following dependency to
 ```
 <dependency>
   <groupId>io.github.ilri.cgspace</groupId>
-  <artifactId>dspace-curation-tasks</artifactId>
-  <version>1.0-SNAPSHOT</version>
+  <artifactId>cgspace-java-helpers</artifactId>
+  <version>6.0</version>
 </dependency>
 ```
 
@@ -30,33 +31,31 @@ $ mvn package
 Copy the resulting jar to the DSpace `lib` directory:
 
 ```
-$ cp target/dspace-curation-tasks-1.0-SNAPSHOT.jar ~/dspace/lib/dspace-curation-tasks-1.0-SNAPSHOT.jar
+$ cp target/cgspace-java-helpers-6.0.jar ~/dspace/lib/
 ```
 
 ## Configuration
 Add the curation task to DSpace's `config/modules/curate.cfg`:
 
 ```
-plugin.named.org.dspace.curate.CurationTask = \
-...
-    io.github.ilri.cgspace.ctasks.CountryCodeTagger = countrycodetagger \
-    io.github.ilri.cgspace.ctasks.CountryCodeTagger = countrycodetagger.force
+plugin.named.org.dspace.curate.CurationTask = io.github.ilri.cgspace.ctasks.CountryCodeTagger = countrycodetagger
+plugin.named.org.dspace.curate.CurationTask = io.github.ilri.cgspace.ctasks.CountryCodeTagger = countrycodetagger.force
 ```
 
-And then add a configuration file for the task in `config/modules/countrycodetagger.cfg`:
+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):
 
 ```
 # name of the field containing ISO 3166-1 country names
-iso3166.field = cg.coverage.country
+countrycodetagger.iso3166.field = cg.coverage.country
 
 # name of the field containing ISO 3166-1 Alpha2 country codes
-iso3166-alpha2.field = cg.coverage.iso3166-alpha2
+countrycodetagger.iso3166-alpha2.field = cg.coverage.iso3166-alpha2
 
 # only add country codes if an item doesn't have any (default false)
-#forceupdate = false
+#countrycodetagger.forceupdate = false
 ```
 
-*Note*: DSpace's curation system supports "profiles" where you can use the same task with different options, for example above I have a normal country code tagger and a "force" variant. To use the "force" variant you create a new configuration file with the overridden options in `config/modules/countrycodetagger.force.cfg`. The "force" profile clears all existing country codes and updates everything.
+*Note*: DSpace's curation system supports "profiles" where you can use the same task with different options, for example above I have a normal country code tagger task and a "force" variant. The "force" variant is the same task, but it looks for configuration variables using the `countrycodetagger.force` instead. To use the "force" variant you simply need to add these new variables with the `forceupdate` parameter overridden to the same configuration file where you put the other variables. The "force" profile clears all existing country codes and updates everything.
 
 ## Invocation
 Once the jar is installed and you have added appropriate configuration in `~/dspace/config/modules`:
@@ -71,14 +70,12 @@ $ ~/dspace/bin/dspace curate -t countrycodetagger -i 10568/3 -r - -l 500 -s obje
 This project was initially created according to the [Maven Getting Started Guide](https://maven.apache.org/guides/getting-started/):
 
 ```console
-$ mvn -B archetype:generate -DgroupId=io.github.ilri.cgspace -DartifactId=dspace-curation-tasks -DarchetypeArtifactId=maven-archetype-quickstart -DarchetypeVersion=1.4
+$ mvn -B archetype:generate -DgroupId=io.github.ilri.cgspace -DartifactId=cgspace-java-helpers -DarchetypeArtifactId=maven-archetype-quickstart -DarchetypeVersion=1.4
 ```
 
 ## TODO
 
 - Make sure this doesn't work on items in the workflow
-- Port to DSpace 6
-  - Remember to bump Gson version!
 - Check for existence of metadata field before trying to add metadata
 - Add tests
 

pom.xml

@@ -5,11 +5,11 @@
   <modelVersion>4.0.0</modelVersion>
 
   <groupId>io.github.ilri.cgspace</groupId>
-  <artifactId>dspace-curation-tasks</artifactId>
-  <version>1.0-SNAPSHOT</version>
+  <artifactId>cgspace-java-helpers</artifactId>
+  <version>6.0</version>
 
-  <name>dspace-curation-tasks</name>
-  <url>https://github.com/ilri/dspace-curation-tasks</url>
+  <name>cgspace-java-helpers</name>
+  <url>https://github.com/ilri/cgspace-java-helpers</url>
 
   <licenses>
     <license>
@@ -42,20 +42,20 @@
     <dependency>
       <groupId>com.google.code.gson</groupId>
       <artifactId>gson</artifactId>
-      <version>2.2.1</version>
+      <version>2.6.1</version>
     </dependency>
     <dependency>
       <groupId>org.dspace</groupId>
       <artifactId>dspace-api</artifactId>
-      <version>5.8</version>
+      <version>6.3</version>
       <scope>provided</scope>
     </dependency>
   </dependencies>
 
   <scm>
-      <connection>scm:git:git://github.com/ilri/dspace-curation-tasks.git</connection>
-      <developerConnection>scm:git:ssh://github.com:nanosai/dspace-curation-tasks.git</developerConnection>
-      <url>http://github.com/ilri/dspace-curation-tasks</url>
+      <connection>scm:git:git://github.com/ilri/cgspace-java-helpers.git</connection>
+      <developerConnection>scm:git:ssh://github.com:nanosai/cgspace-java-helpers.git</developerConnection>
+      <url>http://github.com/ilri/cgspace-java-helpers</url>
   </scm>
 
   <distributionManagement>

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

@@ -23,7 +23,7 @@ import org.apache.log4j.Logger;
 import org.dspace.authorize.AuthorizeException;
 import org.dspace.content.DSpaceObject;
 import org.dspace.content.Item;
-import org.dspace.content.Metadatum;
+import org.dspace.content.MetadataValue;
 import org.dspace.core.Constants;
 import org.dspace.curate.AbstractCurationTask;
 import org.dspace.curate.Curator;
@@ -81,7 +81,11 @@ public class CountryCodeTagger extends AbstractCurationTask
 
             Item item = (Item)dso;
 
-            alpha2Result = performAlpha2(item, config);
+            try {
+                alpha2Result = performAlpha2(item, config);
+            } catch (SQLException throwables) {
+                throwables.printStackTrace();
+            }
 
             setResult(alpha2Result.getResult());
             report(alpha2Result.getResult());
@@ -90,15 +94,14 @@ public class CountryCodeTagger extends AbstractCurationTask
 		return alpha2Result.getStatus();
     }
 
-    public CountryCodeTaggerResult performAlpha2(Item item, CountryCodeTaggerConfig config) throws IOException
-    {
+    public CountryCodeTaggerResult performAlpha2(Item item, CountryCodeTaggerConfig config) throws IOException, SQLException {
         CountryCodeTaggerResult alpha2Result = new CountryCodeTaggerResult();
         String itemHandle = item.getHandle();
 
-        Metadatum[] itemCountries = item.getMetadataByMetadataString(config.iso3166Field);
+        List<MetadataValue> itemCountries = itemService.getMetadataByMetadataString(item, config.iso3166Field);
 
         // skip items that don't have country metadata
-        if (itemCountries.length == 0) {
+        if (itemCountries.size() == 0) {
             alpha2Result.setResult(itemHandle + ": no countries, skipping.");
             alpha2Result.setStatus(Curator.CURATE_SKIP);
         } else {
@@ -117,25 +120,25 @@ public class CountryCodeTagger extends AbstractCurationTask
             String[] iso3166Alpha2FieldParts = config.iso3166Alpha2Field.split("\\.");
 
             if (config.forceupdate) {
-                item.clearMetadata(iso3166Alpha2FieldParts[0], iso3166Alpha2FieldParts[1], iso3166Alpha2FieldParts[2], Item.ANY);
+                itemService.clearMetadata(Curator.curationContext(), item, iso3166Alpha2FieldParts[0], iso3166Alpha2FieldParts[1], iso3166Alpha2FieldParts[2], Item.ANY);
             }
 
             // check the item's country codes, if any
-            Metadatum[] itemAlpha2CountryCodes = item.getMetadataByMetadataString(config.iso3166Alpha2Field);
+            List<MetadataValue> itemAlpha2CountryCodes = itemService.getMetadataByMetadataString(item, config.iso3166Alpha2Field);
 
-            if (itemAlpha2CountryCodes.length == 0) {
+            if (itemAlpha2CountryCodes.size() == 0) {
                 List<String> newAlpha2Codes = new ArrayList<String>();
-                for (Metadatum itemCountry : itemCountries) {
+                for (MetadataValue itemCountry : itemCountries) {
                     //check ISO 3166-1 countries
                     for (CountriesVocabulary.Country country : isocodesCountriesJson.countries) {
-                        if (itemCountry.value.equalsIgnoreCase(country.getName()) || itemCountry.value.equalsIgnoreCase(country.get_official_name()) || itemCountry.value.equalsIgnoreCase(country.get_common_name())) {
+                        if (itemCountry.getValue().equalsIgnoreCase(country.getName()) || itemCountry.getValue().equalsIgnoreCase(country.get_official_name()) || itemCountry.getValue().equalsIgnoreCase(country.get_common_name())) {
                             newAlpha2Codes.add(country.getAlpha_2());
                         }
                     }
 
                     //check CGSpace countries
                     for (CountriesVocabulary.Country country : cgspaceCountriesJson.countries) {
-                        if (itemCountry.value.equalsIgnoreCase(country.getCgspace_name())) {
+                        if (itemCountry.getValue().equalsIgnoreCase(country.getCgspace_name())) {
                             newAlpha2Codes.add(country.getAlpha_2());
                         }
                     }
@@ -143,9 +146,8 @@ public class CountryCodeTagger extends AbstractCurationTask
 
                 if (newAlpha2Codes.size() > 0) {
                     try {
-                        // add metadata values (casting the List<String> to an array)
-                        item.addMetadata(iso3166Alpha2FieldParts[0], iso3166Alpha2FieldParts[1], iso3166Alpha2FieldParts[2], "en_US", newAlpha2Codes.toArray(new String[0]));
-                        item.update();
+                        itemService.addMetadata(Curator.curationContext(), item, iso3166Alpha2FieldParts[0], iso3166Alpha2FieldParts[1], iso3166Alpha2FieldParts[2], "en_US", newAlpha2Codes);
+                        itemService.update(Curator.curationContext(), item);
                     } catch (SQLException | AuthorizeException sqle) {
                         config.log.debug(sqle.getMessage());
                         alpha2Result.setResult(itemHandle + ": error");

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

@@ -0,0 +1,140 @@
+package io.github.ilri.cgspace.scripts;
+
+import org.apache.commons.lang.StringUtils;
+import org.dspace.authorize.AuthorizeException;
+import org.dspace.content.*;
+import org.dspace.core.Constants;
+import org.dspace.core.Context;
+import org.dspace.content.factory.ContentServiceFactory;
+import org.dspace.content.service.ItemService;
+import org.dspace.handle.factory.HandleServiceFactory;
+import org.dspace.handle.service.HandleService;
+import org.dspace.content.service.BundleService;
+
+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 6.0
+ * @since 5.1
+ */
+public class FixJpgJpgThumbnails {
+	//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.COLLECTION:
+							process(context, itemService.findByCollection(context, (Collection) parent));
+							break;
+						case Constants.COMMUNITY:
+							List<Collection> collections = ((Community) parent).getCollections();
+							for (Collection collection : collections) {
+								process(context, itemService.findAllByCollection(context, collection));
+							}
+							break;
+						case Constants.SITE:
+							process(context, itemService.findAll(context));
+							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 {
+		// Some bitstreams like Infographics are large JPGs and put in the ORIGINAL bundle on purpose so we shouldn't
+		// swap them.
+		List<MetadataValue> itemTypes = itemService.getMetadataByMetadataString(item, "dc.type");
+		boolean itemHasInfographic = false;
+		for (MetadataValue itemType: itemTypes) {
+			if (itemType.getValue().equals("Infographic")) {
+				itemHasInfographic = true;
+			}
+		}
+
+		List<Bundle> thumbnailBundles = item.getBundles("THUMBNAIL");
+		for (Bundle thumbnailBundle : thumbnailBundles) {
+			List<Bitstream> thumbnailBundleBitstreams = thumbnailBundle.getBitstreams();
+			for (Bitstream thumbnailBitstream : thumbnailBundleBitstreams) {
+				String thumbnailName = thumbnailBitstream.getName();
+
+				if (thumbnailName.toLowerCase().contains(".jpg.jpg")) {
+					List<Bundle> originalBundles = item.getBundles("ORIGINAL");
+					for (Bundle originalBundle : originalBundles) {
+						List<Bitstream> originalBundleBitstreams = originalBundle.getBitstreams();
+
+						for (Bitstream originalBitstream : originalBundleBitstreams) {
+							String originalName = originalBitstream.getName();
+
+							long originalBitstreamBytes = originalBitstream.getSize();
+
+							/*
+							- 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
+							- check if the item has dc.type Infographic (JPG could be the "real" item!)
+							- check if the original bitstream is less than ~100KiB
+							    - Note: in my tests there were 4022 items with ".jpg.jpg" thumbnails totaling 394549249
+							      bytes for an average of about 98KiB so ~100KiB seems like a good cut off
+							*/
+							if (
+									originalName.equalsIgnoreCase(StringUtils.removeEndIgnoreCase(thumbnailName, ".jpg"))
+									&& ("Generated Thumbnail".equals(thumbnailBitstream.getDescription()) || "IM Thumbnail".equals(thumbnailBitstream.getDescription()))
+									&& !itemHasInfographic
+									&& originalBitstreamBytes < 100000
+							) {
+								System.out.println(item.getHandle() + ": replacing " + thumbnailName + " with " + originalName);
+
+								//add the original bitstream to the THUMBNAIL bundle
+								bundleService.addBitstream(context, thumbnailBundle, originalBitstream);
+								//remove the original bitstream from the ORIGINAL bundle
+								originalBundle.removeBitstream(originalBitstream);
+								//remove the JpgJpg bitstream from the THUMBNAIL bundle
+								thumbnailBundle.removeBitstream(thumbnailBitstream);
+							}
+						}
+					}
+				}
+			}
+		}
+	}
+}