- Increase the "PublicationsRetriever.threadsMultiplier" to "6", as the threads are mostly network-blocked.

- Make sure the "maven" package is installed before compiling the "PublicationsRetriever" library.
- Update dependencies.

build.gradle

@@ -1,5 +1,5 @@
 plugins {
-    id 'org.springframework.boot' version '2.6.0'
+    id 'org.springframework.boot' version '2.6.1'
     id 'io.spring.dependency-management' version '1.0.11.RELEASE'
     id 'java'
 }

gradle/wrapper/gradle-wrapper.properties

@@ -1,5 +1,5 @@
 distributionBase=GRADLE_USER_HOME
 distributionPath=wrapper/dists
-distributionUrl=https\://services.gradle.org/distributions/gradle-7.2-bin.zip
+distributionUrl=https\://services.gradle.org/distributions/gradle-7.3-bin.zip
 zipStoreBase=GRADLE_USER_HOME
 zipStorePath=wrapper/dists

installAndRun.sh

@@ -25,7 +25,7 @@ if [[ ! -f $inputDataFile ]]; then
   echo -e "\n\n"
 fi
 
-gradleVersion="7.2"
+gradleVersion="7.3"
 
 if [[ justInstall -eq 0 ]]; then
 
@@ -39,7 +39,7 @@ if [[ justInstall -eq 0 ]]; then
   # Keep a backup of the existing JAR file.
   mv ./publications_retriever-1.0-SNAPSHOT.jar ./publications_retriever-1.0-SNAPSHOT_BACKUP.jar
 
-  cd PublicationsRetriever && mvn clean install
+  cd PublicationsRetriever && sudo apt install -y maven && mvn clean install
 
   # Copy the created JAR file to the top libs directory.
   cp target/publications_retriever-1.0-SNAPSHOT.jar ../publications_retriever-1.0-SNAPSHOT.jar

src/main/java/eu/openaire/urls_worker/plugins/PublicationsRetrieverPlugin.java

@@ -42,6 +42,7 @@ public class PublicationsRetrieverPlugin {
         PublicationsRetriever.targetUrlType = "docUrl";
         FileUtils.jsonBatchSize = WorkerConstants.ASSIGNMENTS_LIMIT;
 
+        PublicationsRetriever.threadsMultiplier = 6;
         int workerThreadsCount = Runtime.getRuntime().availableProcessors() * PublicationsRetriever.threadsMultiplier;
         logger.info("Use " + workerThreadsCount + " worker-threads.");
         PublicationsRetriever.executor = Executors.newFixedThreadPool(workerThreadsCount);