Merge remote-tracking branch 'main/beta' into continuous_validation2

- Code polishing/cleanup.

dhp-pace-core/src/test/java/eu/dnetlib/pace/util/UtilTest.java

@@ -7,10 +7,10 @@ import java.util.HashMap;
 import java.util.Map;
 
 import org.junit.jupiter.api.BeforeAll;
+import org.junit.jupiter.api.Disabled;
 import org.junit.jupiter.api.Test;
 
 import eu.dnetlib.pace.model.Person;
-import jdk.nashorn.internal.ir.annotations.Ignore;
 
 public class UtilTest {
 
@@ -22,7 +22,7 @@ public class UtilTest {
 	}
 
 	@Test
-	@Ignore
+	@Disabled
 	public void paceResolverTest() {
 		PaceResolver paceResolver = new PaceResolver();
 		paceResolver.getComparator("keywordMatch", params);

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/bipmodel/score/deserializers/BipProjectModel.java

@@ -19,10 +19,7 @@ import lombok.Getter;
 import lombok.NoArgsConstructor;
 import lombok.Setter;
 
-@NoArgsConstructor
-@AllArgsConstructor
-@Getter
-@Setter
+
 public class BipProjectModel {
 	String projectId;
 
@@ -34,6 +31,17 @@ public class BipProjectModel {
 
 	String totalCitationCount;
 
+	public BipProjectModel() {
+	}
+
+	public BipProjectModel(String projectId, String numOfInfluentialResults, String numOfPopularResults, String totalImpulse, String totalCitationCount) {
+		this.projectId = projectId;
+		this.numOfInfluentialResults = numOfInfluentialResults;
+		this.numOfPopularResults = numOfPopularResults;
+		this.totalImpulse = totalImpulse;
+		this.totalCitationCount = totalCitationCount;
+	}
+
 	// each project bip measure has exactly one value, hence one key-value pair
 	private Measure createMeasure(String measureId, String measureValue) {
 
@@ -71,4 +79,43 @@ public class BipProjectModel {
 				createMeasure("totalCitationCount", totalCitationCount));
 	}
 
+	public String getProjectId() {
+		return projectId;
+	}
+
+	public void setProjectId(String projectId) {
+		this.projectId = projectId;
+	}
+
+	public String getNumOfInfluentialResults() {
+		return numOfInfluentialResults;
+	}
+
+	public void setNumOfInfluentialResults(String numOfInfluentialResults) {
+		this.numOfInfluentialResults = numOfInfluentialResults;
+	}
+
+	public String getNumOfPopularResults() {
+		return numOfPopularResults;
+	}
+
+	public void setNumOfPopularResults(String numOfPopularResults) {
+		this.numOfPopularResults = numOfPopularResults;
+	}
+
+	public String getTotalImpulse() {
+		return totalImpulse;
+	}
+
+	public void setTotalImpulse(String totalImpulse) {
+		this.totalImpulse = totalImpulse;
+	}
+
+	public String getTotalCitationCount() {
+		return totalCitationCount;
+	}
+
+	public void setTotalCitationCount(String totalCitationCount) {
+		this.totalCitationCount = totalCitationCount;
+	}
 }

dhp-workflows/dhp-continuous-validation/README.md

@@ -0,0 +1,33 @@
+# Continuous Validation
+
+This module is responsible for deploying an **Oozie Workflow** (on the desired cluster), which executes a **Spark** action.<br>
+This action takes the HDFS-path of a directory of parquet files containing metadata records, and applies the validation process on all of them, in parallel. Then it outputs the results, in json-format, in the given directory.<br>
+The validation process is powered by the "[**uoa-validator-engine2**](https://code-repo.d4science.org/MaDgIK/uoa-validator-engine2)" software,
+which is included as a dependency inside the main "pom.xml" file.<br>
+
+
+### Configure the workflow
+
+Add the wanted values for each of the parameters, defined in the "/src/main/resources/eu/dnetlib/dhp/continuous_validator/oozie_app/workflow.xml" file.<br>
+The most important parameters are the following:
+- ***parquet_path***: the input parquet
+- ***openaire_guidelines***: valid values: "4.0", "3.0", "2.0", "fair_data", "fair_literature_v4"
+- ***output_path***: Be careful to use a base directory which is different from the one that this module is running on, as during a new deployment, that base directory will be deleted.
+
+
+### Install the project and then deploy and run the workflow
+
+Run the **./installProject.sh** script and then the **./runOozieWorkflow.sh** script.<br>
+
+Use the "workflow-id" displayed by the "runOozieWorkflow.sh" script to check the running status and logs, in the remote machine, as follows:
+- Check the status: `oozie job -oozie http://<cluster's domain and port>/oozie -info <Workflow-ID>`
+- Copy the "Job-id" from the output of the above command (numbers with ONE underscore between them).
+- Check the job's logs (not the app's logs!): `yarn logs -applicationId application_<Job-ID>`
+<br><br>
+
+**Note**:<br>
+If you encounter any "java.lang.NoSuchFieldError" issues in the logs, rerun using the following steps:
+- Delete some remote directories related to the workflow in your user's dir: /user/<userName>/
+  - ***.sparkStaging***
+  - ***oozie-oozi***
+- Run the **./installProject.sh** script and then the **./runOozieWorkflow.sh** script.

dhp-workflows/dhp-continuous-validation/installProject.sh

@@ -0,0 +1,18 @@
+# Install the whole "dnet-hadoop" project.
+
+# Delete this module's previous build-files in order to avoid any conflicts.
+rm -rf target/ ||
+
+# Go to the root directory of this project.
+cd ../../
+
+# Select the build profile.
+DEFAULT_PROFILE=''  # It's the empty profile.
+NEWER_VERSIONS_PROFILE='-Pscala-2.12'
+CHOSEN_MAVEN_PROFILE=${DEFAULT_PROFILE}
+
+# Install the project.
+mvn clean install -U ${CHOSEN_MAVEN_PROFILE} -Dmaven.test.skip=true
+
+# We skip tests for all modules, since the take a big amount of time and some of them fail.
+# Any test added to this module, will be executed in the "runOozieWorkflow.sh" script.

dhp-workflows/dhp-continuous-validation/pom.xml

@@ -0,0 +1,42 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project xmlns="http://maven.apache.org/POM/4.0.0"
+         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+    <modelVersion>4.0.0</modelVersion>
+
+    <parent>
+        <artifactId>dhp-workflows</artifactId>
+        <groupId>eu.dnetlib.dhp</groupId>
+        <version>1.2.5-SNAPSHOT</version>
+        <relativePath>../pom.xml</relativePath>
+    </parent>
+
+    <artifactId>dhp-continuous-validation</artifactId>
+    <!-- The "version" is inherited from the parent module. -->
+
+    <dependencies>
+        <dependency>
+            <groupId>eu.dnetlib.dhp</groupId>
+            <artifactId>dhp-common</artifactId>
+            <version>${project.version}</version>
+        </dependency>
+
+        <dependency>
+            <groupId>eu.dnetlib</groupId>
+            <artifactId>uoa-validator-engine2</artifactId>
+        </dependency>
+
+        <dependency>
+            <groupId>org.apache.spark</groupId>
+            <artifactId>spark-core_${scala.binary.version}</artifactId>
+        </dependency>
+
+        <!-- https://mvnrepository.com/artifact/org.apache.spark/spark-sql -->
+        <dependency>
+            <groupId>org.apache.spark</groupId>
+            <artifactId>spark-sql_${scala.binary.version}</artifactId>
+        </dependency>
+
+    </dependencies>
+
+</project>

dhp-workflows/dhp-continuous-validation/runOozieWorkflow.sh

@@ -0,0 +1,14 @@
+# This script deploys and runs the oozie workflow on the cluster, defined in the "~/.dhp/application.properties" file.
+
+# Select the build profile.
+DEFAULT_PROFILE=''  # It's the empty profile.
+NEWER_VERSIONS_PROFILE='-Pscala-2.12'
+CHOSEN_MAVEN_PROFILE=${DEFAULT_PROFILE}
+
+# Build and deploy this module.
+mvn clean package -U ${CHOSEN_MAVEN_PROFILE} -Poozie-package,deploy,run \
+      -Dworkflow.source.dir=eu/dnetlib/dhp/continuous_validation
+
+# Show the Oozie-job-ID.
+echo -e "\n\nShowing the contents of \"extract-and-run-on-remote-host.log\":\n"
+cat ./target/extract-and-run-on-remote-host.log

dhp-workflows/dhp-continuous-validation/src/main/java/eu/dnetlib/dhp/continuous_validation/ContinuousValidation.java

@@ -0,0 +1,144 @@
+
+package eu.dnetlib.dhp.continuous_validation;
+
+import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
+
+import java.io.File;
+import java.nio.charset.StandardCharsets;
+import java.util.Objects;
+import java.util.Optional;
+
+import org.apache.commons.io.IOUtils;
+import org.apache.spark.SparkConf;
+import org.apache.spark.api.java.function.MapFunction;
+import org.apache.spark.sql.Encoders;
+import org.apache.spark.sql.Row;
+import org.apache.spark.sql.SaveMode;
+import org.slf4j.LoggerFactory;
+
+import eu.dnetlib.dhp.application.ArgumentApplicationParser;
+import eu.dnetlib.validator2.validation.StandardValidationResult;
+import eu.dnetlib.validator2.validation.XMLApplicationProfile;
+import eu.dnetlib.validator2.validation.guideline.Guideline;
+import eu.dnetlib.validator2.validation.guideline.StandardResult;
+import eu.dnetlib.validator2.validation.guideline.openaire.*;
+import eu.dnetlib.validator2.validation.utils.TestUtils;
+
+public class ContinuousValidation {
+
+	private static final org.slf4j.Logger logger = LoggerFactory.getLogger(ContinuousValidation.class);
+	private static final String parametersFile = "input_continuous_validation_parameters.json";
+
+	public static void main(String[] args) {
+
+		ArgumentApplicationParser parser = null;
+		Boolean isSparkSessionManaged = false;
+		String parquetPath = null;
+		String guidelines = null;
+		String outputPath = null;
+
+		try {
+			String jsonConfiguration = IOUtils
+				.toString(
+					Objects
+						.requireNonNull(
+							ContinuousValidation.class
+								.getResourceAsStream("/eu/dnetlib/dhp/continuous_validation/" + parametersFile)),
+					StandardCharsets.UTF_8);
+
+			parser = new ArgumentApplicationParser(jsonConfiguration);
+			parser.parseArgument(args);
+		} catch (Exception e) {
+			logger.error("Error when parsing the parameters!", e);
+			return;
+		}
+
+		isSparkSessionManaged = Optional
+			.ofNullable(parser.get("isSparkSessionManaged")) // This param is not mandatory, so it may be null.
+			.map(Boolean::valueOf)
+			.orElse(Boolean.TRUE);
+
+		logger.info("isSparkSessionManaged: {}", isSparkSessionManaged);
+		// This is needed to implement a unit test in which the spark session is created in the context of the
+		// unit test itself rather than inside the spark application"
+
+		// Set the parquet input, either a parquet-file or a directory with parquet files.
+		parquetPath = parser.get("parquet_path");
+		if (parquetPath == null) {
+			logger.error("The \"parquet_path\" was not retrieved from the parameters file: " + parametersFile);
+			return;
+		}
+
+		guidelines = parser.get("openaire_guidelines");
+		if (guidelines == null) {
+			logger.error("The \"openaire_guidelines\" was not retrieved from the parameters file: " + parametersFile);
+			return;
+		}
+
+		outputPath = parser.get("output_path");
+		if (outputPath == null) {
+			logger.error("The \"output_path\" was not retrieved from the parameters file: " + parametersFile);
+			return;
+		}
+
+		if (!outputPath.endsWith(File.separator))
+			outputPath += File.separator;
+
+		logger
+			.info(
+				"Will validate the contents of parquetFile: \"" + parquetPath + "\", against guidelines: \""
+					+ guidelines + "\"" + " and will output the results in the outputPath: " + outputPath);
+
+		AbstractOpenAireProfile profile;
+		switch (guidelines) {
+			case "4.0":
+				profile = new LiteratureGuidelinesV4Profile();
+				break;
+			case "3.0":
+				profile = new LiteratureGuidelinesV3Profile();
+				break;
+			case "2.0":
+				profile = new DataArchiveGuidelinesV2Profile();
+				break;
+			case "fair_data":
+				profile = new FAIR_Data_GuidelinesProfile();
+				break;
+			case "fair_literature_v4":
+				profile = new FAIR_Literature_GuidelinesV4Profile();
+				break;
+			default:
+				logger.error("Invalid OpenAIRE Guidelines were given: " + guidelines);
+				return;
+		}
+
+		SparkConf conf = new SparkConf();
+		conf.setAppName(ContinuousValidation.class.getSimpleName());
+		conf.set("spark.serializer", "org.apache.spark.serializer.KryoSerializer");
+		conf.registerKryoClasses(new Class[] {
+			XMLApplicationProfile.ValidationResult.class, Guideline.Result.class, StandardValidationResult.class,
+			StandardResult.class
+		});
+		String finalParquetPath = parquetPath;
+		String finalOutputPath = outputPath;
+
+		runWithSparkSession(conf, isSparkSessionManaged, spark -> {
+			// Use a new instance of Document Builder in each worker, as it is not thread-safe.
+			MapFunction<Row, XMLApplicationProfile.ValidationResult> validateMapFunction = row -> profile
+				.validate(
+					row.getAs("id").toString(),
+					TestUtils
+						.getDocumentBuilder()
+						.parse(IOUtils.toInputStream(row.getAs("body").toString(), StandardCharsets.UTF_8)));
+
+			spark
+				.read()
+				.parquet(finalParquetPath)
+				.filter("encoding = 'XML' and id is not NULL and body is not NULL")
+				.map(validateMapFunction, Encoders.bean(XMLApplicationProfile.ValidationResult.class))
+				.write()
+				.option("compression", "gzip")
+				.mode(SaveMode.Overwrite)
+				.json(finalOutputPath); // The output files have names of the input files which were processed.
+		});
+	}
+}

dhp-workflows/dhp-continuous-validation/src/main/resources/eu/dnetlib/dhp/continuous_validation/input_continuous_validation_parameters.json

@@ -0,0 +1,26 @@
+[
+  {
+    "paramName": "issm",
+    "paramLongName": "isSparkSessionManaged",
+    "paramDescription": "when true will stop SparkSession after job execution",
+    "paramRequired": false
+  },
+  {
+    "paramName": "prq_file",
+    "paramLongName": "parquet_path",
+    "paramDescription": "the full path of a parquet-file or a directory with parquet files, to be processed",
+    "paramRequired": true
+  },
+  {
+    "paramName": "guidelines",
+    "paramLongName": "openaire_guidelines",
+    "paramDescription": "the version of the OpenAIRE Guidelines to validate the records against",
+    "paramRequired": true
+  },
+  {
+    "paramName": "o",
+    "paramLongName": "output_path",
+    "paramDescription": "the path of the output-directory where the result-json-files will be stored",
+    "paramRequired": true
+  }
+]

dhp-workflows/dhp-continuous-validation/src/main/resources/eu/dnetlib/dhp/continuous_validation/oozie_app/config-default.xml

@@ -0,0 +1,22 @@
+<configuration>
+    <property>
+        <name>jobTracker</name>
+        <value>yarnRM</value>
+    </property>
+    <property>
+        <name>nameNode</name>
+        <value>hdfs://nameservice1</value>
+    </property>
+    <property>
+        <name>oozie.use.system.libpath</name>
+        <value>true</value>
+    </property>
+    <property>
+        <name>oozie.action.sharelib.for.spark</name>
+        <value>spark2</value>
+    </property>
+    <property>
+        <name>sparkExecutorMemoryOverhead</name>
+        <value>1G</value>
+    </property>
+</configuration>

dhp-workflows/dhp-continuous-validation/src/main/resources/eu/dnetlib/dhp/continuous_validation/oozie_app/workflow.xml

@@ -0,0 +1,115 @@
+<workflow-app name="Validate metadata records against OpenAIRE Guidelines" xmlns="uri:oozie:workflow:0.5">
+    <parameters>
+        <property>
+            <name>parquet_path</name>
+            <value>/var/lib/dnet/mdstore_PROD/md-7763c517-538d-4aa7-83f8-6096b3ce0d96/md-7763c517-538d-4aa7-83f8-6096b3ce0d96-1702622132535/store</value>
+            <description>the full path of a parquet-file or a directory with parquet files, to be processed</description>
+        </property>
+        <property>
+            <name>openaire_guidelines</name>
+            <value>4.0</value>
+            <description>the version of the OpenAIRE Guidelines to validate the records against</description>
+        </property>
+        <property>
+            <name>output_path</name>
+            <value>/user/${dhp.hadoop.frontend.user.name}/continuous_validation/output</value>
+            <description>the path of the output-directory where the result-json-files will be stored</description>
+        </property>
+        <property>
+            <name>sparkDriverMemory</name>
+            <value>4096M</value>
+            <description>memory for driver process</description>
+        </property>
+        <property>
+            <name>sparkExecutorMemory</name>
+            <value>2048m</value>
+            <description>memory for individual executor</description>
+        </property>
+        <property>
+            <name>sparkExecutorCores</name>
+            <value>4</value>
+            <description>number of cores used by single executor</description>
+        </property>
+        <property>
+            <name>spark2ExtraListeners</name>
+            <value>com.cloudera.spark.lineage.NavigatorAppListener</value>
+            <description>spark 2.* extra listeners classname</description>
+        </property>
+        <property>
+            <name>spark2SqlQueryExecutionListeners</name>
+            <value>com.cloudera.spark.lineage.NavigatorQueryListener</value>
+            <description>spark 2.* sql query execution listeners classname</description>
+        </property>
+        <!--<property>
+            <name>oozieActionShareLibForSpark2</name>
+            <description>oozie action sharelib for spark 2.*</description>
+        </property>
+        <property>
+            <name>spark2YarnHistoryServerAddress</name>
+            <description>spark 2.* yarn history server address</description>
+        </property>-->
+        <property>
+            <name>spark2EventLogDir</name>
+            <value>spark2/logs</value>
+            <description>spark 2.* event log dir location</description>
+        </property>
+        <property>
+            <name>oozie.libpath</name>
+            <value>${nameNode}/user/oozie/share/lib</value>
+        </property>
+    </parameters>
+
+    <global>
+        <job-tracker>${jobTracker}</job-tracker>
+        <name-node>${nameNode}</name-node>
+        <configuration>
+            <property>
+                <name>mapreduce.job.queuename</name>
+                <value>${queueName}</value>
+            </property>
+            <property>
+                <name>oozie.launcher.mapred.job.queue.name</name>
+                <value>${oozieLauncherQueueName}</value>
+            </property>
+            <property>
+                <name>oozie.action.sharelib.for.spark</name>
+                <value>${oozieActionShareLibForSpark2}</value>
+            </property>
+        </configuration>
+    </global>
+
+    <start to="ValidateMetadataRecords"/>
+
+    <kill name="Kill">
+        <message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
+    </kill>
+
+    <action name="ValidateMetadataRecords">
+        <spark xmlns="uri:oozie:spark-action:0.2">
+            <master>yarn</master>
+            <mode>cluster</mode>
+            <name>Validate multiple records against OpenAIRE Guidelines</name>
+            <class>eu.dnetlib.dhp.continuous_validation.ContinuousValidation</class>
+            <jar>dhp-continuous-validation-${projectVersion}.jar</jar>
+            <spark-opts>
+                --executor-memory=${sparkExecutorMemory}
+                --conf spark.executor.memoryOverhead=${sparkExecutorMemoryOverhead}
+                --executor-cores=${sparkExecutorCores}
+                --driver-memory=${sparkDriverMemory}
+                --conf spark.extraListeners=${spark2ExtraListeners}
+                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
+                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
+                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
+                --conf spark.sql.shuffle.partitions=3840
+            </spark-opts>
+            <!-- Arguments passed to the "main" method of the class defined above. -->
+            <arg>--parquet_path</arg><arg>${parquet_path}</arg>
+            <arg>--openaire_guidelines</arg><arg>${openaire_guidelines}</arg>
+            <arg>--output_path</arg><arg>${output_path}</arg>
+        </spark>
+        <ok to="End"/>
+        <error to="Kill"/>
+    </action>
+
+    <end name="End"/>
+</workflow-app>

dhp-workflows/dhp-continuous-validation/src/main/resources/logback.xml

@@ -0,0 +1,43 @@
+<configuration debug="false">
+
+    <shutdownHook class="ch.qos.logback.core.hook.DelayingShutdownHook"/>   <!-- Default delay: 0ms (zero) -->
+
+<!--    <Appenders>-->
+        <appender name="RollingFile" class="ch.qos.logback.core.rolling.RollingFileAppender">
+            <file>logs/ContinuousValidation.log</file>
+
+            <rollingPolicy class="ch.qos.logback.core.rolling.FixedWindowRollingPolicy">
+                <fileNamePattern>logs/ContinuousValidation.%i.log.zip</fileNamePattern>
+                <minIndex>1</minIndex>
+                <maxIndex>10</maxIndex>
+            </rollingPolicy>
+
+            <triggeringPolicy class="ch.qos.logback.core.rolling.SizeBasedTriggeringPolicy">
+                <maxFileSize>100MB</maxFileSize>  <!-- Lower the size to check the "RollingFileAppender" during tests. -->
+            </triggeringPolicy>
+            <encoder>
+                <charset>UTF-8</charset>
+                <pattern>%d{yyyy-MM-dd HH:mm:ss.SSS z} [%thread] %-5level %logger{36}.%M\(@%line\) - %msg%n</pattern>
+            </encoder>
+        </appender>
+
+        <appender name="Console" class="ch.qos.logback.core.ConsoleAppender">
+            <encoder>
+                <charset>UTF-8</charset>
+                <pattern>%d{yyyy-MM-dd HH:mm:ss.SSS z} [%thread] %highlight(%-5level) %cyan(%logger{36}.%M\(@%line\)) - %msg%n</pattern>
+            </encoder>
+        </appender>
+<!--    </Appenders>-->
+
+        <root level="debug">
+            <appender-ref ref="Console" />
+        </root>
+
+        <logger name="eu.dnetlib.dhp.continuous_validation" level="debug"/>
+        <logger name="eu.dnetlib.validator2" level="error"/>
+        <logger name="org.sparkproject" level="info"/>
+        <logger name="org.apache.spark" level="info"/>
+        <logger name="org.apache.hadoop" level="info"/>
+        <logger name="org.apache.parquet" level="info"/>
+
+</configuration>

dhp-workflows/dhp-doiboost/src/test/java/eu/dnetlib/doiboost/orcid/OrcidClientTest.java

@@ -30,7 +30,6 @@ import eu.dnetlib.dhp.common.collection.HttpClientParams;
 import eu.dnetlib.dhp.schema.orcid.AuthorData;
 import eu.dnetlib.doiboost.orcid.util.DownloadsReport;
 import eu.dnetlib.doiboost.orcid.util.MultiAttemptsHttpConnector;
-import jdk.nashorn.internal.ir.annotations.Ignore;
 
 public class OrcidClientTest {
 	final int REQ_LIMIT = 24;
@@ -152,7 +151,7 @@ public class OrcidClientTest {
 	}
 
 	// @Test
-	@Ignore
+	@Disabled
 	private void testModifiedDate() throws ParseException {
 		testDate(toRetrieveDate);
 		testDate(toNotRetrieveDate);
@@ -332,7 +331,7 @@ public class OrcidClientTest {
 	}
 
 	@Test
-	@Ignore
+	@Disabled
 	void testUpdatedRecord() throws Exception {
 		final String base64CompressedRecord = IOUtils
 			.toString(getClass().getResourceAsStream("0000-0001-7281-6306.compressed.base64"));
@@ -341,7 +340,7 @@ public class OrcidClientTest {
 	}
 
 	@Test
-	@Ignore
+	@Disabled
 	void testUpdatedWork() throws Exception {
 		final String base64CompressedWork = "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";
 		final String work = ArgumentApplicationParser.decompressValue(base64CompressedWork);
@@ -413,7 +412,7 @@ public class OrcidClientTest {
 	}
 
 	@Test
-	@Ignore
+	@Disabled
 	void testDownloadedAuthor() throws Exception {
 		final String base64CompressedWork = "H4sIAAAAAAAAAI2Yy26jMBSG932KiD0hIe1MiwiVZjGLkWbX2XRHsFOsgs3YJmnefszFFy4+mUhtVPz9P/gcH/vQ9PWrrjYXzAVh9Bjst7tgg2nBEKEfx+DP28/wOdgImVOUV4ziY3DDInjNHlKOC8ZRMnxtmlyWxyDaqU+ofg7h/uX7IYwfn+Ngo25ARUKoxJzm1TEopWySKLper1vGC4LU74+IikgTWoFRW+SyfyyfxCBag4iQhBawyoGMDjdqJrnECJAZRquYLDEPaV5jv8oyWlXj+qTiXZLGr7KMiQbnjAOR6IY1W7C6hgIwjGt6SKGfHsY13ajHYipLIcIyJ5Xw6+akdvjEtyt4wxEwM6+VGph5N2zYr2ENhQRhKsmZYChmS1j7nFs6VIBPOwImKhyfMVeFg6GAWEjrcoQ4FoBmBGwVXYhagGHDBIEX+ZzUDiqyn35VN6rJUpUJ4zc/PAI2T03FbrUKJZQszWjV3zavVOjvVfoE01qB+YUUQPGNwHTt3luxJjdqh1AxJFBKLWOrSeCcF13RtxxYtlPOPqH6m+MLwVfoMQ2kdae2ArLajc6fTxkI1nIoegs0yB426pMO+0fSw07xDKMu0XKSde5C2VvrlVMijRzFwqY7XTJI1QMLWcmEzMxtDdxfHiYSgTNJnYJ1K9y5k0tUrMgrnGGaRiuXxxuClulYUbr0nBvpkYLjvgTCGsuSoex3f1CEvRPHKI184NJKtKeaiO7cD5E61bJ4F+9DFd7d01u8Tw6H5BBvvz8f3q3nXLGIeJULGdaqeVBBRK7rS7h/fNvvk/gpedxt4923dxP7Fc3KtKuc1BhlkrfYmeN4dcmrhmbw60+HmWw2CKgbTuqc32CXKTTmeTWT6bDBjPsQ0DTpnchdaYO0ayQ2FyLIiVREqs25aU8VKYLRbK0BsyZuqvr1MU2Sm/rDdhe/2CRN6FU/b+oBVyj1zqRtC5F8kAumfTclsl+s7EoNQu64nfOaVLeezX60Z3XCULLi6GI2IZGTEeey7fec9lBAuXawIHKcpifE7GABHWfoxLVfpUNPBXoMbZWrHFsR3bPAk9J9i2sw9nW6AQT1mpk++7JhW+v44Hmt8PomJqfD13jRnvFOSxCKtu6qHoyBbQ7cMFo750UEfGaXm6bEeplXIXj2hvL6mA7tzvIwmM9pbJFBG834POZdLGi2gH2u9u0K9HMwn5PTioFWLufzmrS4oNuU9Pkt2rf/2jMs7fMdm2rQTTM+j+49AzToAVuXYA1mD2k0+XdE9vAP+JYR5NcQAAA=";
 		final String work = ArgumentApplicationParser.decompressValue(base64CompressedWork);
@@ -421,7 +420,7 @@ public class OrcidClientTest {
 	}
 
 	@Test
-	@Ignore
+	@Disabled
 	void testDownloadedWork() throws Exception {
 		final String base64CompressedWork = "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";
 		final String work = ArgumentApplicationParser.decompressValue(base64CompressedWork);

dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/oozie_app/workflow.xml

@@ -114,7 +114,7 @@
             <arg>--sourcePath</arg><arg>${sourcePath}</arg>
             <arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
             <arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
-            <arg>--outputPath</arg><arg>${workingDir}/orcid/preparedInfo/targetOrcidAssoc</arg>
+            <arg>--outputPath</arg><arg>${workingDir}/orcid/targetOrcidAssoc</arg>
             <arg>--allowedsemrels</arg><arg>${allowedsemrels}</arg>
         </spark>
         <ok to="wait"/>
@@ -142,7 +142,7 @@
             <arg>--sourcePath</arg><arg>${sourcePath}</arg>
             <arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
             <arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
-            <arg>--outputPath</arg><arg>${workingDir}/orcid/preparedInfo/targetOrcidAssoc</arg>
+            <arg>--outputPath</arg><arg>${workingDir}/orcid/targetOrcidAssoc</arg>
             <arg>--allowedsemrels</arg><arg>${allowedsemrels}</arg>
         </spark>
         <ok to="wait"/>
@@ -170,7 +170,7 @@
             <arg>--sourcePath</arg><arg>${sourcePath}</arg>
             <arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
             <arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
-            <arg>--outputPath</arg><arg>${workingDir}/orcid/preparedInfo/targetOrcidAssoc</arg>
+            <arg>--outputPath</arg><arg>${workingDir}/orcid/targetOrcidAssoc</arg>
             <arg>--allowedsemrels</arg><arg>${allowedsemrels}</arg>
         </spark>
         <ok to="wait"/>
@@ -198,7 +198,7 @@
             <arg>--sourcePath</arg><arg>${sourcePath}</arg>
             <arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
             <arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
-            <arg>--outputPath</arg><arg>${workingDir}/orcid/preparedInfo/targetOrcidAssoc</arg>
+            <arg>--outputPath</arg><arg>${workingDir}/orcid/targetOrcidAssoc</arg>
             <arg>--allowedsemrels</arg><arg>${allowedsemrels}</arg>
         </spark>
         <ok to="wait"/>
@@ -225,8 +225,8 @@
                 --conf spark.dynamicAllocation.enabled=true
                 --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
             </spark-opts>
-            <arg>--sourcePath</arg><arg>${workingDir}/orcid/orcidprop</arg>
-            <arg>--outputPath</arg><arg>${workingDir}/orcid/orcidprop/mergedOrcidAssoc</arg>
+            <arg>--sourcePath</arg><arg>${workingDir}/orcid/targetOrcidAssoc</arg>
+            <arg>--outputPath</arg><arg>${workingDir}/orcid/mergedOrcidAssoc</arg>
         </spark>
         <ok to="fork-join-exec-propagation"/>
         <error to="Kill"/>
@@ -247,9 +247,10 @@
             <class>eu.dnetlib.dhp.orcidtoresultfromsemrel.SparkOrcidToResultFromSemRelJob</class>
             <jar>dhp-enrichment-${projectVersion}.jar</jar>
             <spark-opts>
-                --executor-cores=${sparkExecutorCores}
-                --executor-memory=${sparkExecutorMemory}
+                --executor-cores=4
+                --executor-memory=4G
                 --driver-memory=${sparkDriverMemory}
+                --conf spark.executor.memoryOverhead=5G
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
@@ -259,9 +260,9 @@
                 --conf spark.speculation=false
                 --conf spark.hadoop.mapreduce.map.speculative=false
                 --conf spark.hadoop.mapreduce.reduce.speculative=false
-                --conf spark.sql.shuffle.partitions=3840
+                --conf spark.sql.shuffle.partitions=15000
             </spark-opts>
-            <arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcid/orcidprop/mergedOrcidAssoc</arg>
+            <arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcid/mergedOrcidAssoc</arg>
             <arg>--sourcePath</arg><arg>${sourcePath}/publication</arg>
             <arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
             <arg>--outputPath</arg><arg>${outputPath}/publication</arg>
@@ -291,7 +292,7 @@
                 --conf spark.hadoop.mapreduce.map.speculative=false
                 --conf spark.hadoop.mapreduce.reduce.speculative=false
             </spark-opts>
-            <arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcid/orcidprop/mergedOrcidAssoc</arg>
+            <arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcid/mergedOrcidAssoc</arg>
             <arg>--sourcePath</arg><arg>${sourcePath}/dataset</arg>
             <arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
             <arg>--outputPath</arg><arg>${outputPath}/dataset</arg>
@@ -321,7 +322,7 @@
                 --conf spark.hadoop.mapreduce.map.speculative=false
                 --conf spark.hadoop.mapreduce.reduce.speculative=false
             </spark-opts>
-            <arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcid/orcidprop/mergedOrcidAssoc</arg>
+            <arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcid/mergedOrcidAssoc</arg>
             <arg>--sourcePath</arg><arg>${sourcePath}/otherresearchproduct</arg>
             <arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
             <arg>--outputPath</arg><arg>${outputPath}/otherresearchproduct</arg>
@@ -351,7 +352,7 @@
                 --conf spark.hadoop.mapreduce.map.speculative=false
                 --conf spark.hadoop.mapreduce.reduce.speculative=false
             </spark-opts>
-            <arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcid/orcidprop/mergedOrcidAssoc</arg>
+            <arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcid/mergedOrcidAssoc</arg>
             <arg>--sourcePath</arg><arg>${sourcePath}/software</arg>
             <arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
             <arg>--outputPath</arg><arg>${outputPath}/software</arg>

dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/enrich/orcid/oozie_app/workflow.xml

@@ -49,10 +49,10 @@
 
     <action name="reset_outputpath">
         <fs>
-            <delete path="${graphPath}/datasource"/>
-            <delete path="${graphPath}/organization"/>
-            <delete path="${graphPath}/project"/>
-            <delete path="${graphPath}/relation"/>
+            <delete path="${targetPath}/datasource"/>
+            <delete path="${targetPath}/organization"/>
+            <delete path="${targetPath}/project"/>
+            <delete path="${targetPath}/relation"/>
         </fs>
         <ok to="copy_datasource"/>
         <error to="Kill"/>

dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/raw/MappersTest.java

@@ -1250,6 +1250,21 @@ class MappersTest {
 		System.out.println("***************");
 	}
 
+	@Test
+	void testIRISPub() throws IOException, DocumentException {
+		final String xml = IOUtils.toString(Objects.requireNonNull(getClass().getResourceAsStream("iris-odf.xml")));
+		final List<Oaf> list = new OdfToOafMapper(vocs, false, true).processMdRecord(xml);
+		System.out.println("***************");
+		System.out.println(new ObjectMapper().writeValueAsString(list));
+		System.out.println("***************");
+		final Publication p = (Publication) list.get(0);
+		assertNotNull(p.getInstance().get(0).getUrl().get(0));
+		assertValidId(p.getId());
+		System.out.println(p.getInstance().get(0).getUrl());
+		p.getPid().forEach(x -> System.out.println(x.getValue()));
+		p.getInstance().get(0).getAlternateIdentifier().forEach(x -> System.out.println(x.getValue()));
+
+	}
 	@Test
 	void testNotWellFormed() throws IOException {
 		final String xml = IOUtils

dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/raw/iris-odf.xml

@@ -0,0 +1,215 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<record xmlns:datacite="http://datacite.org/schema/kernel-4"
+        xmlns:dc="http://purl.org/dc/elements/1.1/"
+        xmlns:dr="http://www.driver-repository.eu/namespace/dr"
+        xmlns:dri="http://www.driver-repository.eu/namespace/dri"
+        xmlns:oaf="http://namespace.openaire.eu/oaf"
+        xmlns:oai="http://www.openarchives.org/OAI/2.0/"
+        xmlns:oaire="http://namespace.openaire.eu/schema/oaire/"
+        xmlns:xs="http://www.w3.org/2001/XMLSchema" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
+    <oai:header xmlns="http://namespace.openaire.eu/" xmlns:prov="http://www.openarchives.org/OAI/2.0/provenance">
+        <identifier>oai:air.unimi.it:2434/907506</identifier>
+        <datestamp>2024-01-04T12:42:51Z</datestamp>
+        <setSpec>com_2434_73555</setSpec>
+        <setSpec>col_2434_73557</setSpec>
+        <setSpec>openaire</setSpec>
+        <dr:dateOfTransformation>2024-01-29T16:56:50.632Z</dr:dateOfTransformation>
+
+        <dri:objIdentifier>od______1261::ff2d9e058e7bea90a27f41c31078e601</dri:objIdentifier>
+        <dri:recordIdentifier>oai:air.unimi.it:2434/907506</dri:recordIdentifier>
+        <dri:dateOfCollection/>
+        <dri:mdFormat/>
+        <dri:mdFormatInterpretation/>
+        <dri:repositoryId/>
+        <oaf:datasourceprefix> od______1261</oaf:datasourceprefix>
+    </oai:header>
+    <metadata>
+        <oaire:resource xmlns:oaire="http://namespace.openaire.eu/schema/oaire/"
+                        xmlns:exslt="http://exslt.org/common"
+                        xmlns:xs="http://www.w3.org/2001/XMLSchema"
+                        xmlns:rdf="http://www.w3.org/TR/rdf-concepts/"
+                        xmlns:doc="http://www.lyncode.com/xoai"
+                        xmlns:dc="http://purl.org/dc/elements/1.1/"
+                        xmlns:datacite="http://datacite.org/schema/kernel-4"
+                        xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+                        xmlns:vc="http://www.w3.org/2007/XMLSchema-versioning"
+                        xmlns="http://www.openarchives.org/OAI/2.0/"
+                        xsi:schemaLocation="http://namespace.openaire.eu/schema/oaire/ https://www.openaire.eu/schema/repo-lit/4.0/openaire.xsd">
+            <datacite:titles>
+                <datacite:title xml:lang="en">Ensuring tests of conservation interventions build on existing literature</datacite:title>
+            </datacite:titles>
+            <datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>W.J. Sutherland</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>S.T. Alvarez-Castaneda</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>T. Amano</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>R. Ambrosini</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>P. Atkinson</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>J.M. Baxter</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>A.L. Bond</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>P.J. Boon</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>K.L. Buchanan</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>J. Barlow</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>G. Bogliani</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>O.M. Bragg</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>M. Burgman</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>M.W. Cadotte</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>M. Calver</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>S.J. Cooke</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>R.T. Corlett</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>V. Devictor</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>J.G. Ewen</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>M. Fisher</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>G. Freeman</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>E. Game</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>B.J. Godley</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>C. Gortazar</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>I.R. Hartley</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>D.L. Hawksworth</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>K.A. Hobson</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>M.-. Lu</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>B. Martin-Lopez</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>K. Ma</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>A. Machado</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>D. Mae</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>M. Mangiacotti</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>D.J. Mccafferty</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>V. Melfi</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>S. Molur</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>A.J. Moore</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>S.D. Murphy</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>D. Norri</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>A.P.E. van Oudenhoven</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>J. Power</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>E.C. Ree</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>M.W. Schwartz</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>I. Storch</datacite:creatorName>
+                </datacite:creator>
+                <datacite:creator>
+                    <datacite:creatorName>C. Wordley</datacite:creatorName>
+                </datacite:creator>
+            </datacite:creator>
+            <datacite:relatedIdentifiers>
+            </datacite:relatedIdentifiers>
+            <datacite:dates>
+                <datacite:date dateType="Accepted">2020</datacite:date>
+                <datacite:date dateType="Issued">2020</datacite:date>
+                <datacite:date dateType="Available">2022-06-20</datacite:date>
+            </datacite:dates>
+            <dc:language>eng</dc:language>
+            <dc:publisher>Wiley Blackwell Publishing</dc:publisher>
+            <oaire:resourceType resourceTypeGeneral="literature"
+                                uri="http://purl.org/coar/resource_type/c_6501">journal article</oaire:resourceType>
+            <dc:format>application/pdf</dc:format>
+            <datacite:identifier xmlns:datacite="http://datacite.org/schema/kernel-3"
+                                 identifierType="Handle">2434/907506</datacite:identifier>
+            <datacite:rights rightsURI="http://purl.org/coar/access_right/c_abf2">open access</datacite:rights>
+            <datacite:subjects>
+                <datacite:subject>Conservation of Natural Resources</datacite:subject>
+            </datacite:subjects>
+            <datacite:sizes/>
+            <datacite:sizes/>
+            <datacite:sizes>
+                <datacite:size>191802 bytes</datacite:size>
+            </datacite:sizes>
+            <oaire:file accessRightsURI="" mimeType="application/pdf" objectType="fulltext">https://air.unimi.it/bitstream/2434/907506/4/Full%20manuscript%20resubmitted.pdf</oaire:file>
+        </oaire:resource>
+        <oaf:identifier identifierType="DOI">10.1111/cobi.13555</oaf:identifier>
+        <oaf:identifier identifierType="PMID">32779884</oaf:identifier>
+        <oaf:fulltext>https://air.unimi.it/bitstream/2434/907506/4/Full%20manuscript%20resubmitted.pdf</oaf:fulltext>
+        <dr:CobjCategory type="publication">0001</dr:CobjCategory>
+        <oaf:dateAccepted>2020-01-01</oaf:dateAccepted>
+        <oaf:accessrights>OPEN</oaf:accessrights>
+        <oaf:language>eng</oaf:language>
+        <oaf:hostedBy name="Archivio Istituzionale della Ricerca dell'Università degli Studi di Milano"
+                      id="opendoar____::1261"/>
+        <oaf:collectedFrom name="Archivio Istituzionale della Ricerca dell'Università degli Studi di Milano"
+                           id="opendoar____::1261"/>
+    </metadata>
+</record>

dhp-workflows/dhp-graph-provision/src/test/java/eu/dnetlib/dhp/oa/provision/XmlRecordFactoryTest.java

@@ -244,4 +244,27 @@ public class XmlRecordFactoryTest {
 
 	}
 
+	@Test
+	public void testIrisGuidelines4() throws DocumentException, IOException {
+		final ContextMapper contextMapper = new ContextMapper();
+
+		final XmlRecordFactory xmlRecordFactory = new XmlRecordFactory(contextMapper, false,
+				XmlConverterJob.schemaLocation);
+
+		final Publication p = OBJECT_MAPPER
+				.readValue(
+						IOUtils.toString(getClass().getResourceAsStream("iris-odf-4.json")),
+						Publication.class);
+
+		final String xml = xmlRecordFactory.build(new JoinedEntity<>(p));
+
+		assertNotNull(xml);
+
+		final Document doc = new SAXReader().read(new StringReader(xml));
+
+		assertNotNull(doc);
+		System.out.println(doc.asXML());
+
+	}
+
 }

dhp-workflows/pom.xml

@@ -39,6 +39,7 @@
         <module>dhp-doiboost</module>
         <module>dhp-impact-indicators</module>
         <module>dhp-swh</module>
+        <module>dhp-continuous-validation</module>
     </modules>
 
     <pluginRepositories>

pom.xml

@@ -204,6 +204,12 @@
 				<scope>test</scope>
 			</dependency>
 
+			<dependency>
+				<groupId>eu.dnetlib</groupId>
+				<artifactId>uoa-validator-engine2</artifactId>
+				<version>2.0.0-SNAPSHOT</version>
+			</dependency>
+
 			<dependency>
 				<groupId>org.slf4j</groupId>
 				<artifactId>jcl-over-slf4j</artifactId>