-

dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/SparkWhitelistSimRels.java

@@ -1,3 +1,4 @@
+
 package eu.dnetlib.dhp.oa.dedup;
 
 import java.io.IOException;
@@ -35,117 +36,124 @@ import scala.Tuple3;
 
 public class SparkWhitelistSimRels extends AbstractSparkAction {
 
-    private static final Logger log = LoggerFactory.getLogger(SparkCreateSimRels.class);
+	private static final Logger log = LoggerFactory.getLogger(SparkCreateSimRels.class);
 
-    private static final String WHITELIST_SEPARATOR = "####";
+	private static final String WHITELIST_SEPARATOR = "####";
 
-    public SparkWhitelistSimRels(ArgumentApplicationParser parser, SparkSession spark) {
+	public SparkWhitelistSimRels(ArgumentApplicationParser parser, SparkSession spark) {
-        super(parser, spark);
+		super(parser, spark);
-    }
+	}
 
-    public static void main(String[] args) throws Exception {
+	public static void main(String[] args) throws Exception {
-        ArgumentApplicationParser parser = new ArgumentApplicationParser(
+		ArgumentApplicationParser parser = new ArgumentApplicationParser(
-                IOUtils
+			IOUtils
-                        .toString(
+				.toString(
-                                SparkCreateSimRels.class
+					SparkCreateSimRels.class
-                                        .getResourceAsStream(
+						.getResourceAsStream(
-                                                "/eu/dnetlib/dhp/oa/dedup/whitelistSimRels_parameters.json")));
+							"/eu/dnetlib/dhp/oa/dedup/whitelistSimRels_parameters.json")));
-        parser.parseArgument(args);
+		parser.parseArgument(args);
 
-        SparkConf conf = new SparkConf();
+		SparkConf conf = new SparkConf();
-        new SparkWhitelistSimRels(parser, getSparkSession(conf))
+		new SparkWhitelistSimRels(parser, getSparkSession(conf))
-                .run(ISLookupClientFactory.getLookUpService(parser.get("isLookUpUrl")));
+			.run(ISLookupClientFactory.getLookUpService(parser.get("isLookUpUrl")));
-    }
+	}
 
-    @Override
+	@Override
-    public void run(ISLookUpService isLookUpService)
+	public void run(ISLookUpService isLookUpService)
-            throws DocumentException, IOException, ISLookUpException, SAXException {
+		throws DocumentException, IOException, ISLookUpException, SAXException {
 
-        // read oozie parameters
+		// read oozie parameters
-        final String graphBasePath = parser.get("graphBasePath");
+		final String graphBasePath = parser.get("graphBasePath");
-        final String isLookUpUrl = parser.get("isLookUpUrl");
+		final String isLookUpUrl = parser.get("isLookUpUrl");
-        final String actionSetId = parser.get("actionSetId");
+		final String actionSetId = parser.get("actionSetId");
-        final String workingPath = parser.get("workingPath");
+		final String workingPath = parser.get("workingPath");
-        final int numPartitions = Optional
+		final int numPartitions = Optional
-                .ofNullable(parser.get("numPartitions"))
+			.ofNullable(parser.get("numPartitions"))
-                .map(Integer::valueOf)
+			.map(Integer::valueOf)
-                .orElse(NUM_PARTITIONS);
+			.orElse(NUM_PARTITIONS);
-        final String whiteListPath = parser.get("whiteListPath");
+		final String whiteListPath = parser.get("whiteListPath");
 
-        log.info("numPartitions: '{}'", numPartitions);
+		log.info("numPartitions: '{}'", numPartitions);
-        log.info("graphBasePath: '{}'", graphBasePath);
+		log.info("graphBasePath: '{}'", graphBasePath);
-        log.info("isLookUpUrl:   '{}'", isLookUpUrl);
+		log.info("isLookUpUrl:   '{}'", isLookUpUrl);
-        log.info("actionSetId:   '{}'", actionSetId);
+		log.info("actionSetId:   '{}'", actionSetId);
-        log.info("workingPath:   '{}'", workingPath);
+		log.info("workingPath:   '{}'", workingPath);
-        log.info("whiteListPath: '{}'", whiteListPath);
+		log.info("whiteListPath: '{}'", whiteListPath);
 
-        JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
+		JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
 
-        //file format: source####target
+		// file format: source####target
-        Dataset<Tuple2<String, String>> whiteListRels = spark.createDataset(sc
+		Dataset<Tuple2<String, String>> whiteListRels = spark
-                        .textFile(whiteListPath)
+			.createDataset(
-                        //check if the line is in the correct format: id1####id2
+				sc
-                        .filter(s -> s.contains(WHITELIST_SEPARATOR) && s.split(WHITELIST_SEPARATOR).length == 2)
+					.textFile(whiteListPath)
-                        .map(s -> new Tuple2<>(s.split(WHITELIST_SEPARATOR)[0], s.split(WHITELIST_SEPARATOR)[1]))
+					// check if the line is in the correct format: id1####id2
-                        .rdd(),
+					.filter(s -> s.contains(WHITELIST_SEPARATOR) && s.split(WHITELIST_SEPARATOR).length == 2)
-                Encoders.tuple(Encoders.STRING(), Encoders.STRING()));
+					.map(s -> new Tuple2<>(s.split(WHITELIST_SEPARATOR)[0], s.split(WHITELIST_SEPARATOR)[1]))
+					.rdd(),
+				Encoders.tuple(Encoders.STRING(), Encoders.STRING()));
 
-        // for each dedup configuration
+		// for each dedup configuration
-        for (DedupConfig dedupConf : getConfigurations(isLookUpService, actionSetId)) {
+		for (DedupConfig dedupConf : getConfigurations(isLookUpService, actionSetId)) {
 
-            final String entity = dedupConf.getWf().getEntityType();
+			final String entity = dedupConf.getWf().getEntityType();
-            final String subEntity = dedupConf.getWf().getSubEntityValue();
+			final String subEntity = dedupConf.getWf().getSubEntityValue();
-            log.info("Adding whitelist simrels for: '{}'", subEntity);
+			log.info("Adding whitelist simrels for: '{}'", subEntity);
 
-            final String outputPath = DedupUtility.createSimRelPath(workingPath, actionSetId, subEntity);
+			final String outputPath = DedupUtility.createSimRelPath(workingPath, actionSetId, subEntity);
 
-            Dataset<Tuple2<String, String>> entities = spark.createDataset(sc
+			Dataset<Tuple2<String, String>> entities = spark
-                    .textFile(DedupUtility.createEntityPath(graphBasePath, subEntity))
+				.createDataset(
-                    .repartition(numPartitions)
+					sc
-                    .mapToPair(
+						.textFile(DedupUtility.createEntityPath(graphBasePath, subEntity))
-                            (PairFunction<String, String, String>) s -> {
+						.repartition(numPartitions)
-                                MapDocument d = MapDocumentUtil.asMapDocumentWithJPath(dedupConf, s);
+						.mapToPair(
-                                return new Tuple2<>(d.getIdentifier(), "present");
+							(PairFunction<String, String, String>) s -> {
-                            })
+								MapDocument d = MapDocumentUtil.asMapDocumentWithJPath(dedupConf, s);
-                    .rdd(),
+								return new Tuple2<>(d.getIdentifier(), "present");
-                    Encoders.tuple(Encoders.STRING(), Encoders.STRING()));
+							})
+						.rdd(),
+					Encoders.tuple(Encoders.STRING(), Encoders.STRING()));
 
-            Dataset<Tuple2<String, String>> whiteListRels1 = whiteListRels
+			Dataset<Tuple2<String, String>> whiteListRels1 = whiteListRels
-                    .joinWith(entities, whiteListRels.col("_1").equalTo(entities.col("_1")), "inner")
+				.joinWith(entities, whiteListRels.col("_1").equalTo(entities.col("_1")), "inner")
-                    .map((MapFunction<Tuple2<Tuple2<String, String>, Tuple2<String, String>>, Tuple2<String, String>>) Tuple2::_1, Encoders.tuple(Encoders.STRING(), Encoders.STRING()));
+				.map(
+					(MapFunction<Tuple2<Tuple2<String, String>, Tuple2<String, String>>, Tuple2<String, String>>) Tuple2::_1,
+					Encoders.tuple(Encoders.STRING(), Encoders.STRING()));
 
-            Dataset<Tuple2<String, String>> whiteListRels2 = whiteListRels1
+			Dataset<Tuple2<String, String>> whiteListRels2 = whiteListRels1
-                    .joinWith(entities, whiteListRels1.col("_2").equalTo(entities.col("_1")), "inner")
+				.joinWith(entities, whiteListRels1.col("_2").equalTo(entities.col("_1")), "inner")
-                    .map((MapFunction<Tuple2<Tuple2<String, String>, Tuple2<String, String>>, Tuple2<String, String>>) Tuple2::_1, Encoders.tuple(Encoders.STRING(), Encoders.STRING()));
+				.map(
+					(MapFunction<Tuple2<Tuple2<String, String>, Tuple2<String, String>>, Tuple2<String, String>>) Tuple2::_1,
+					Encoders.tuple(Encoders.STRING(), Encoders.STRING()));
 
-            Dataset<Relation> whiteListSimRels = whiteListRels2
+			Dataset<Relation> whiteListSimRels = whiteListRels2
-                    .map((MapFunction<Tuple2<String, String>, Relation>)
+				.map(
-                                    r -> createSimRel(r._1(), r._2(), entity),
+					(MapFunction<Tuple2<String, String>, Relation>) r -> createSimRel(r._1(), r._2(), entity),
-                                    Encoders.bean(Relation.class)
+					Encoders.bean(Relation.class));
-                    );
 
-            saveParquet(whiteListSimRels, outputPath, SaveMode.Append);
+			saveParquet(whiteListSimRels, outputPath, SaveMode.Append);
-        }
+		}
-    }
+	}
 
-    private Relation createSimRel(String source, String target, String entity) {
+	private Relation createSimRel(String source, String target, String entity) {
-        final Relation r = new Relation();
+		final Relation r = new Relation();
-        r.setSource(source);
+		r.setSource(source);
-        r.setTarget(target);
+		r.setTarget(target);
-        r.setSubRelType("dedupSimilarity");
+		r.setSubRelType("dedupSimilarity");
-        r.setRelClass("isSimilarTo");
+		r.setRelClass("isSimilarTo");
-        r.setDataInfo(new DataInfo());
+		r.setDataInfo(new DataInfo());
 
-        switch (entity) {
+		switch (entity) {
-            case "result":
+			case "result":
-                r.setRelType("resultResult");
+				r.setRelType("resultResult");
-                break;
+				break;
-            case "organization":
+			case "organization":
-                r.setRelType("organizationOrganization");
+				r.setRelType("organizationOrganization");
-                break;
+				break;
-            default:
+			default:
-                throw new IllegalArgumentException("unmanaged entity type: " + entity);
+				throw new IllegalArgumentException("unmanaged entity type: " + entity);
-        }
+		}
-        return r;
+		return r;
-    }
+	}
 }

dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/PropagationConstant.java

@@ -69,7 +69,7 @@ public class PropagationConstant {
 					PROPAGATION_DATA_INFO_TYPE,
 					PROPAGATION_COUNTRY_INSTREPO_CLASS_ID,
 					PROPAGATION_COUNTRY_INSTREPO_CLASS_NAME,
-						ModelConstants.DNET_PROVENANCE_ACTIONS));
+					ModelConstants.DNET_PROVENANCE_ACTIONS));
 		return nc;
 	}
 
@@ -84,7 +84,8 @@ public class PropagationConstant {
 		return di;
 	}
 
-	public static Qualifier getQualifier(String inference_class_id, String inference_class_name, String qualifierSchema) {
+	public static Qualifier getQualifier(String inference_class_id, String inference_class_name,
+		String qualifierSchema) {
 		Qualifier pa = new Qualifier();
 		pa.setClassid(inference_class_id);
 		pa.setClassname(inference_class_name);
@@ -108,7 +109,11 @@ public class PropagationConstant {
 		r.setRelClass(rel_class);
 		r.setRelType(rel_type);
 		r.setSubRelType(subrel_type);
-		r.setDataInfo(getDataInfo(inference_provenance, inference_class_id, inference_class_name, ModelConstants.DNET_PROVENANCE_ACTIONS));
+		r
+			.setDataInfo(
+				getDataInfo(
+					inference_provenance, inference_class_id, inference_class_name,
+					ModelConstants.DNET_PROVENANCE_ACTIONS));
 		return r;
 	}
 

dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/SparkOrcidToResultFromSemRelJob.java

@@ -173,14 +173,17 @@ public class SparkOrcidToResultFromSemRelJob {
 		if (toaddpid) {
 			StructuredProperty p = new StructuredProperty();
 			p.setValue(autoritative_author.getOrcid());
-			p.setQualifier(getQualifier(ModelConstants.ORCID_PENDING, ModelConstants.ORCID_CLASSNAME, ModelConstants.DNET_PID_TYPES));
+			p
+				.setQualifier(
+					getQualifier(
+						ModelConstants.ORCID_PENDING, ModelConstants.ORCID_CLASSNAME, ModelConstants.DNET_PID_TYPES));
 			p
 				.setDataInfo(
 					getDataInfo(
 						PROPAGATION_DATA_INFO_TYPE,
 						PROPAGATION_ORCID_TO_RESULT_FROM_SEM_REL_CLASS_ID,
 						PROPAGATION_ORCID_TO_RESULT_FROM_SEM_REL_CLASS_NAME,
-							ModelConstants.DNET_PROVENANCE_ACTIONS));
+						ModelConstants.DNET_PROVENANCE_ACTIONS));
 
 			Optional<List<StructuredProperty>> authorPid = Optional.ofNullable(author.getPid());
 			if (authorPid.isPresent()) {

dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromorganization/SparkResultToCommunityFromOrganizationJob.java

@@ -10,7 +10,6 @@ import java.util.List;
 import java.util.Optional;
 import java.util.stream.Collectors;
 
-import eu.dnetlib.dhp.schema.common.ModelConstants;
 import org.apache.commons.io.IOUtils;
 import org.apache.spark.SparkConf;
 import org.apache.spark.api.java.function.MapFunction;
@@ -22,6 +21,7 @@ import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 
 import eu.dnetlib.dhp.application.ArgumentApplicationParser;
+import eu.dnetlib.dhp.schema.common.ModelConstants;
 import eu.dnetlib.dhp.schema.oaf.Context;
 import eu.dnetlib.dhp.schema.oaf.Result;
 import scala.Tuple2;
@@ -130,7 +130,7 @@ public class SparkResultToCommunityFromOrganizationJob {
 											PROPAGATION_DATA_INFO_TYPE,
 											PROPAGATION_RESULT_COMMUNITY_ORGANIZATION_CLASS_ID,
 											PROPAGATION_RESULT_COMMUNITY_ORGANIZATION_CLASS_NAME,
-												ModelConstants.DNET_PROVENANCE_ACTIONS)));
+											ModelConstants.DNET_PROVENANCE_ACTIONS)));
 						propagatedContexts.add(newContext);
 					}
 				}

dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/SparkResultToCommunityThroughSemRelJob.java

@@ -7,7 +7,6 @@ import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkHiveSession;
 import java.util.*;
 import java.util.stream.Collectors;
 
-import eu.dnetlib.dhp.schema.common.ModelConstants;
 import org.apache.commons.io.IOUtils;
 import org.apache.spark.SparkConf;
 import org.apache.spark.api.java.function.MapFunction;
@@ -20,6 +19,7 @@ import org.slf4j.LoggerFactory;
 
 import eu.dnetlib.dhp.application.ArgumentApplicationParser;
 import eu.dnetlib.dhp.resulttocommunityfromorganization.ResultCommunityList;
+import eu.dnetlib.dhp.schema.common.ModelConstants;
 import eu.dnetlib.dhp.schema.oaf.*;
 import scala.Tuple2;
 
@@ -126,7 +126,7 @@ public class SparkResultToCommunityThroughSemRelJob {
 													PROPAGATION_DATA_INFO_TYPE,
 													PROPAGATION_RESULT_COMMUNITY_SEMREL_CLASS_ID,
 													PROPAGATION_RESULT_COMMUNITY_SEMREL_CLASS_NAME,
-														ModelConstants.DNET_PROVENANCE_ACTIONS)));
+													ModelConstants.DNET_PROVENANCE_ACTIONS)));
 								return newContext;
 							}
 							return null;

dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/dump/ResultMapper.java

@@ -6,6 +6,8 @@ import java.util.*;
 import java.util.stream.Collectors;
 
 import org.apache.commons.lang3.StringUtils;
+import org.apache.spark.api.java.function.MapFunction;
+import org.apache.spark.sql.Encoders;
 
 import eu.dnetlib.dhp.schema.common.ModelConstants;
 import eu.dnetlib.dhp.schema.dump.oaf.*;
@@ -23,8 +25,6 @@ import eu.dnetlib.dhp.schema.dump.oaf.community.CommunityResult;
 import eu.dnetlib.dhp.schema.dump.oaf.community.Context;
 import eu.dnetlib.dhp.schema.dump.oaf.graph.GraphResult;
 import eu.dnetlib.dhp.schema.oaf.*;
-import org.apache.spark.api.java.function.MapFunction;
-import org.apache.spark.sql.Encoders;
 
 public class ResultMapper implements Serializable {
 
@@ -278,16 +278,17 @@ public class ResultMapper implements Serializable {
 
 			}
 
-
 			Optional
 				.ofNullable(input.getPid())
 				.ifPresent(
-					value -> out.setPid(value
+					value -> out
-						.stream()
+						.setPid(
-						.map(
+							value
-							p ->
+								.stream()
-									ControlledField
+								.map(
-										.newInstance(p.getQualifier().getClassid(), p.getValue())).collect(Collectors.toList())));
+									p -> ControlledField
+										.newInstance(p.getQualifier().getClassid(), p.getValue()))
+								.collect(Collectors.toList())));
 
 			oStr = Optional.ofNullable(input.getDateofacceptance());
 			if (oStr.isPresent()) {
@@ -298,11 +299,10 @@ public class ResultMapper implements Serializable {
 				out.setPublisher(oStr.get().getValue());
 			}
 
-
 			Optional
 				.ofNullable(input.getSource())
-				.ifPresent(value -> out.setSource(value.stream().map(s -> s.getValue()).collect(Collectors.toList()) ));
+				.ifPresent(value -> out.setSource(value.stream().map(s -> s.getValue()).collect(Collectors.toList())));
-					//	value.stream().forEach(s -> sourceList.add(s.getValue())));
+			// value.stream().forEach(s -> sourceList.add(s.getValue())));
 			// out.setSource(input.getSource().stream().map(s -> s.getValue()).collect(Collectors.toList()));
 			List<Subject> subjectList = new ArrayList<>();
 			Optional
@@ -577,48 +577,60 @@ public class ResultMapper implements Serializable {
 		Optional<DataInfo> di = Optional.ofNullable(pid.getDataInfo());
 		if (di.isPresent()) {
 			return Pid
-					.newInstance(
+				.newInstance(
-							ControlledField
+					ControlledField
-									.newInstance(
+						.newInstance(
-											pid.getQualifier().getClassid(),
+							pid.getQualifier().getClassid(),
-											pid.getValue()),
+							pid.getValue()),
-							Provenance
+					Provenance
-									.newInstance(
+						.newInstance(
-											di.get().getProvenanceaction().getClassname(),
+							di.get().getProvenanceaction().getClassname(),
-											di.get().getTrust()));
+							di.get().getTrust()));
 		} else {
 			return Pid
-					.newInstance(
+				.newInstance(
-							ControlledField
+					ControlledField
-									.newInstance(
+						.newInstance(
-											pid.getQualifier().getClassid(),
+							pid.getQualifier().getClassid(),
-											pid.getValue())
+							pid.getValue())
 
-					);
+				);
 		}
 	}
 
 	private static Pid getOrcid(List<StructuredProperty> p) {
 		List<StructuredProperty> pid_list = p.stream().map(pid -> {
 			if (pid.getQualifier().getClassid().equals(ModelConstants.ORCID) ||
-					(pid.getQualifier().getClassid().equals(ModelConstants.ORCID_PENDING))){
+				(pid.getQualifier().getClassid().equals(ModelConstants.ORCID_PENDING))) {
 				return pid;
 			}
-			return  null;
+			return null;
 		}).filter(pid -> pid != null).collect(Collectors.toList());
 
-		if(pid_list.size() == 1){
+		if (pid_list.size() == 1) {
 			return getAuthorPid(pid_list.get(0));
 		}
 
-		List<StructuredProperty> orcid = pid_list.stream().filter(ap -> ap.getQualifier().getClassid()
+		List<StructuredProperty> orcid = pid_list
-				.equals(ModelConstants.ORCID)).collect(Collectors.toList());
+			.stream()
-		if(orcid.size() == 1){
+			.filter(
+				ap -> ap
+					.getQualifier()
+					.getClassid()
+					.equals(ModelConstants.ORCID))
+			.collect(Collectors.toList());
+		if (orcid.size() == 1) {
 			return getAuthorPid(orcid.get(0));
 		}
-		orcid = pid_list.stream().filter(ap -> ap.getQualifier().getClassid()
+		orcid = pid_list
-				.equals(ModelConstants.ORCID_PENDING)).collect(Collectors.toList());
+			.stream()
-		if(orcid.size() == 1){
+			.filter(
+				ap -> ap
+					.getQualifier()
+					.getClassid()
+					.equals(ModelConstants.ORCID_PENDING))
+			.collect(Collectors.toList());
+		if (orcid.size() == 1) {
 			return getAuthorPid(orcid.get(0));
 		}
 

dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/dump/SaveCommunityMap.java

@@ -86,10 +86,10 @@ public class SaveCommunityMap implements Serializable {
 
 	private void saveCommunityMap(boolean singleCommunity, String community_id)
 		throws ISLookUpException, IOException, DocumentException, SAXException {
-        writer
+		writer
-                .write(
+			.write(
-                        Utils.OBJECT_MAPPER
+				Utils.OBJECT_MAPPER
-                                .writeValueAsString(queryInformationSystem.getCommunityMap(singleCommunity, community_id)));
+					.writeValueAsString(queryInformationSystem.getCommunityMap(singleCommunity, community_id)));
-    }
+	}
 
 }

dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/dump/community/SparkPrepareResultProject.java

@@ -8,8 +8,6 @@ import java.io.StringReader;
 import java.util.*;
 import java.util.stream.Collectors;
 
-import eu.dnetlib.dhp.schema.common.ModelConstants;
-import eu.dnetlib.dhp.schema.dump.oaf.community.Validated;
 import org.apache.commons.io.IOUtils;
 import org.apache.spark.SparkConf;
 import org.apache.spark.api.java.function.MapFunction;
@@ -28,9 +26,11 @@ import org.xml.sax.SAXException;
 
 import eu.dnetlib.dhp.application.ArgumentApplicationParser;
 import eu.dnetlib.dhp.oa.graph.dump.Utils;
+import eu.dnetlib.dhp.schema.common.ModelConstants;
 import eu.dnetlib.dhp.schema.dump.oaf.Provenance;
 import eu.dnetlib.dhp.schema.dump.oaf.community.Funder;
 import eu.dnetlib.dhp.schema.dump.oaf.community.Project;
+import eu.dnetlib.dhp.schema.dump.oaf.community.Validated;
 import eu.dnetlib.dhp.schema.oaf.DataInfo;
 import eu.dnetlib.dhp.schema.oaf.Field;
 import eu.dnetlib.dhp.schema.oaf.Relation;
@@ -80,7 +80,9 @@ public class SparkPrepareResultProject implements Serializable {
 	private static void prepareResultProjectList(SparkSession spark, String inputPath, String outputPath) {
 		Dataset<Relation> relation = Utils
 			.readPath(spark, inputPath + "/relation", Relation.class)
-			.filter("dataInfo.deletedbyinference = false and lower(relClass) = '" + ModelConstants.IS_PRODUCED_BY.toLowerCase() + "'");
+			.filter(
+				"dataInfo.deletedbyinference = false and lower(relClass) = '"
+					+ ModelConstants.IS_PRODUCED_BY.toLowerCase() + "'");
 		Dataset<eu.dnetlib.dhp.schema.oaf.Project> projects = Utils
 			.readPath(spark, inputPath + "/project", eu.dnetlib.dhp.schema.oaf.Project.class);
 
@@ -159,7 +161,7 @@ public class SparkPrepareResultProject implements Serializable {
 			provenance.setTrust(di.get().getTrust());
 			p.setProvenance(provenance);
 		}
-		if (relation.getValidated()){
+		if (relation.getValidated()) {
 			p.setValidated(Validated.newInstance(relation.getValidated(), relation.getValidationDate()));
 		}
 		return p;

dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/dump/complete/DumpGraphEntities.java

@@ -9,7 +9,6 @@ import java.io.StringReader;
 import java.util.*;
 import java.util.stream.Collectors;
 
-import com.fasterxml.jackson.databind.ObjectMapper;
 import org.apache.spark.SparkConf;
 import org.apache.spark.api.java.function.FilterFunction;
 import org.apache.spark.api.java.function.ForeachFunction;
@@ -23,6 +22,8 @@ import org.dom4j.DocumentException;
 import org.dom4j.Node;
 import org.dom4j.io.SAXReader;
 
+import com.fasterxml.jackson.databind.ObjectMapper;
+
 import eu.dnetlib.dhp.oa.graph.dump.DumpProducts;
 import eu.dnetlib.dhp.oa.graph.dump.Utils;
 import eu.dnetlib.dhp.schema.common.ModelSupport;
@@ -453,18 +454,20 @@ public class DumpGraphEntities implements Serializable {
 
 	private static <E extends OafEntity> void organizationMap(SparkSession spark, String inputPath, String outputPath,
 		Class<E> inputClazz) {
-		Utils.readPath(spark, inputPath, inputClazz)
+		Utils
-				.map(
+			.readPath(spark, inputPath, inputClazz)
-						(MapFunction<E, Organization>) o -> mapOrganization((eu.dnetlib.dhp.schema.oaf.Organization) o),
+			.map(
-						Encoders.bean(Organization.class))
+				(MapFunction<E, Organization>) o -> mapOrganization((eu.dnetlib.dhp.schema.oaf.Organization) o),
-				.filter((FilterFunction<Organization>) o -> o!= null)
+				Encoders.bean(Organization.class))
-				.write()
+			.filter((FilterFunction<Organization>) o -> o != null)
-				.mode(SaveMode.Overwrite)
+			.write()
-				.option("compression", "gzip")
+			.mode(SaveMode.Overwrite)
-				.json(outputPath);
+			.option("compression", "gzip")
+			.json(outputPath);
 	}
 
-	private static eu.dnetlib.dhp.schema.dump.oaf.graph.Organization mapOrganization(eu.dnetlib.dhp.schema.oaf.Organization org) {
+	private static eu.dnetlib.dhp.schema.dump.oaf.graph.Organization mapOrganization(
+		eu.dnetlib.dhp.schema.oaf.Organization org) {
 		if (org.getDataInfo().getDeletedbyinference())
 			return null;
 		Organization organization = new Organization();

dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/dump/complete/QueryInformationSystem.java

@@ -5,8 +5,6 @@ import java.io.StringReader;
 import java.util.*;
 import java.util.function.Consumer;
 
-import eu.dnetlib.dhp.schema.common.ModelConstants;
-import eu.dnetlib.dhp.schema.common.ModelSupport;
 import org.dom4j.Document;
 import org.dom4j.DocumentException;
 import org.dom4j.Element;
@@ -15,6 +13,8 @@ import org.dom4j.io.SAXReader;
 import org.jetbrains.annotations.NotNull;
 import org.xml.sax.SAXException;
 
+import eu.dnetlib.dhp.schema.common.ModelConstants;
+import eu.dnetlib.dhp.schema.common.ModelSupport;
 import eu.dnetlib.dhp.utils.DHPUtils;
 import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpException;
 import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
@@ -140,7 +140,7 @@ public class QueryInformationSystem {
 	}
 
 	private String makeOpenaireId(Node el, String prefix) {
-		if (!prefix.equals(ModelSupport.entityIdPrefix.get("project"))){
+		if (!prefix.equals(ModelSupport.entityIdPrefix.get("project"))) {
 			return null;
 		}
 		String funder = null;

dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/dump/complete/SparkDumpRelationJob.java

@@ -107,7 +107,7 @@ public class SparkDumpRelationJob implements Serializable {
 						}
 					}
 				}
-				if(relation.getValidated()){
+				if (relation.getValidated()) {
 					rel_new.setValidated(relation.getValidated());
 					rel_new.setValidationDate(relation.getValidationDate());
 				}

dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/dump/funderresults/SparkDumpFunderResults.java

@@ -41,9 +41,9 @@ public class SparkDumpFunderResults implements Serializable {
 		parser.parseArgument(args);
 
 		Boolean isSparkSessionManaged = Optional
-				.ofNullable(parser.get("isSparkSessionManaged"))
+			.ofNullable(parser.get("isSparkSessionManaged"))
-				.map(Boolean::valueOf)
+			.map(Boolean::valueOf)
-				.orElse(Boolean.TRUE);
+			.orElse(Boolean.TRUE);
 		log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
 
 		final String inputPath = parser.get("sourcePath");
@@ -58,32 +58,31 @@ public class SparkDumpFunderResults implements Serializable {
 		SparkConf conf = new SparkConf();
 
 		runWithSparkSession(
-				conf,
+			conf,
-				isSparkSessionManaged,
+			isSparkSessionManaged,
-				spark -> {
+			spark -> {
-					Utils.removeOutputDir(spark, outputPath);
+				Utils.removeOutputDir(spark, outputPath);
-					writeResultProjectList(spark, inputPath, outputPath, graphPath);
+				writeResultProjectList(spark, inputPath, outputPath, graphPath);
-				});
+			});
 	}
 
 	private static void writeResultProjectList(SparkSession spark, String inputPath, String outputPath,
-											   String graphPath) {
+		String graphPath) {
 
 		Dataset<eu.dnetlib.dhp.schema.oaf.Project> project = Utils
-				.readPath(spark, graphPath + "/project", eu.dnetlib.dhp.schema.oaf.Project.class);
+			.readPath(spark, graphPath + "/project", eu.dnetlib.dhp.schema.oaf.Project.class);
 
 		Dataset<CommunityResult> result = Utils
-				.readPath(spark, inputPath + "/publication", CommunityResult.class)
+			.readPath(spark, inputPath + "/publication", CommunityResult.class)
-				.union(Utils.readPath(spark, inputPath + "/dataset", CommunityResult.class))
+			.union(Utils.readPath(spark, inputPath + "/dataset", CommunityResult.class))
-				.union(Utils.readPath(spark, inputPath + "/orp", CommunityResult.class))
+			.union(Utils.readPath(spark, inputPath + "/orp", CommunityResult.class))
-				.union(Utils.readPath(spark, inputPath + "/software", CommunityResult.class));
+			.union(Utils.readPath(spark, inputPath + "/software", CommunityResult.class));
-
 
 		List<String> funderList = project
-				.select("id")
+			.select("id")
-				.map((MapFunction<Row, String>) value -> value.getString(0).substring(0, 15), Encoders.STRING())
+			.map((MapFunction<Row, String>) value -> value.getString(0).substring(0, 15), Encoders.STRING())
-				.distinct()
+			.distinct()
-				.collectAsList();
+			.collectAsList();
 
 		funderList.forEach(funder -> {
 			String fundernsp = funder.substring(3);
@@ -104,7 +103,7 @@ public class SparkDumpFunderResults implements Serializable {
 	}
 
 	private static void dumpResults(String nsp, Dataset<CommunityResult> results, String outputPath,
-									String funderName) {
+		String funderName) {
 
 		results.map((MapFunction<CommunityResult, CommunityResult>) r -> {
 			if (!Optional.ofNullable(r.getProjects()).isPresent()) {
@@ -123,15 +122,15 @@ public class SparkDumpFunderResults implements Serializable {
 			}
 			return null;
 		}, Encoders.bean(CommunityResult.class))
-				.filter(Objects::nonNull)
+			.filter(Objects::nonNull)
-				.write()
+			.write()
-				.mode(SaveMode.Overwrite)
+			.mode(SaveMode.Overwrite)
-				.option("compression", "gzip")
+			.option("compression", "gzip")
-				.json(outputPath + "/" + funderName);
+			.json(outputPath + "/" + funderName);
 	}
 
 	private static void writeFunderResult(String funder, Dataset<CommunityResult> results, String outputPath,
-										  String funderDump) {
+		String funderDump) {
 
 		if (funder.startsWith("40|irb")) {
 			dumpResults(funder, results, outputPath, "HRZZ");

dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/dump/funderresults/SparkResultLinkedToProject.java

@@ -80,7 +80,6 @@ public class SparkResultLinkedToProject implements Serializable {
 	private static <R extends Result> void writeResultsLinkedToProjects(SparkSession spark, Class<R> inputClazz,
 		String inputPath, String outputPath, String graphPath) {
 
-
 		Dataset<R> results = Utils
 			.readPath(spark, inputPath, inputClazz)
 			.filter("dataInfo.deletedbyinference = false and datainfo.invisible = false");

dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/dump/DumpJobTest.java

@@ -7,17 +7,10 @@ import java.nio.file.Path;
 import java.util.Arrays;
 import java.util.List;
 
-import com.fasterxml.jackson.core.JsonProcessingException;
-import com.sun.xml.internal.ws.policy.AssertionSet;
-import eu.dnetlib.dhp.schema.common.ModelConstants;
-import eu.dnetlib.dhp.schema.dump.oaf.Instance;
-import eu.dnetlib.dhp.schema.dump.oaf.OpenAccessRoute;
 import org.apache.commons.io.FileUtils;
-import org.apache.neethi.Assertion;
 import org.apache.spark.SparkConf;
 import org.apache.spark.api.java.JavaRDD;
 import org.apache.spark.api.java.JavaSparkContext;
-import org.apache.spark.api.java.function.ForeachFunction;
 import org.apache.spark.sql.Encoders;
 import org.apache.spark.sql.Row;
 import org.apache.spark.sql.SparkSession;
@@ -25,10 +18,14 @@ import org.junit.jupiter.api.*;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 
+import com.fasterxml.jackson.core.JsonProcessingException;
 import com.fasterxml.jackson.databind.ObjectMapper;
 import com.google.gson.Gson;
 
 import eu.dnetlib.dhp.oa.graph.dump.community.CommunityMap;
+import eu.dnetlib.dhp.schema.common.ModelConstants;
+import eu.dnetlib.dhp.schema.dump.oaf.Instance;
+import eu.dnetlib.dhp.schema.dump.oaf.OpenAccessRoute;
 import eu.dnetlib.dhp.schema.dump.oaf.community.CommunityResult;
 import eu.dnetlib.dhp.schema.dump.oaf.graph.GraphResult;
 import eu.dnetlib.dhp.schema.oaf.Dataset;
@@ -145,70 +142,121 @@ public class DumpJobTest {
 	}
 
 	@Test
-	public void testPublicationDump(){
+	public void testPublicationDump() {
 		final String sourcePath = getClass()
-				.getResource("/eu/dnetlib/dhp/oa/graph/dump/resultDump/publication_extendedinstance")
+			.getResource("/eu/dnetlib/dhp/oa/graph/dump/resultDump/publication_extendedinstance")
-				.getPath();
+			.getPath();
 
 		final String communityMapPath = getClass()
-				.getResource("/eu/dnetlib/dhp/oa/graph/dump/communityMapPath/communitymap.json")
+			.getResource("/eu/dnetlib/dhp/oa/graph/dump/communityMapPath/communitymap.json")
-				.getPath();
+			.getPath();
 
 		DumpProducts dump = new DumpProducts();
 		dump
-				.run(
+			.run(
-						// false, sourcePath, workingDir.toString() + "/result", communityMapPath, Publication.class,
+				// false, sourcePath, workingDir.toString() + "/result", communityMapPath, Publication.class,
-						false, sourcePath, workingDir.toString() + "/result", communityMapPath, Publication.class,
+				false, sourcePath, workingDir.toString() + "/result", communityMapPath, Publication.class,
-						GraphResult.class, Constants.DUMPTYPE.COMPLETE.getType());
+				GraphResult.class, Constants.DUMPTYPE.COMPLETE.getType());
 
 		final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
 
 		JavaRDD<GraphResult> tmp = sc
-				.textFile(workingDir.toString() + "/result")
+			.textFile(workingDir.toString() + "/result")
-				.map(item -> OBJECT_MAPPER.readValue(item, GraphResult.class));
+			.map(item -> OBJECT_MAPPER.readValue(item, GraphResult.class));
 
 		org.apache.spark.sql.Dataset<GraphResult> verificationDataset = spark
-				.createDataset(tmp.rdd(), Encoders.bean(GraphResult.class));
+			.createDataset(tmp.rdd(), Encoders.bean(GraphResult.class));
 
 		Assertions.assertEquals(1, verificationDataset.count());
 
 		GraphResult gr = verificationDataset.first();
 
-
 		Assertions.assertEquals(2, gr.getMeasures().size());
-		Assertions.assertTrue(gr.getMeasures().stream().anyMatch(m -> m.getKey().equals("influence")
+		Assertions
-				&& m.getValue().equals("1.62759106106e-08")));
+			.assertTrue(
-		Assertions.assertTrue(gr.getMeasures().stream().anyMatch(m -> m.getKey().equals("popularity")
+				gr
-				&& m.getValue().equals("0.22519296")));
+					.getMeasures()
+					.stream()
+					.anyMatch(
+						m -> m.getKey().equals("influence")
+							&& m.getValue().equals("1.62759106106e-08")));
+		Assertions
+			.assertTrue(
+				gr
+					.getMeasures()
+					.stream()
+					.anyMatch(
+						m -> m.getKey().equals("popularity")
+							&& m.getValue().equals("0.22519296")));
 
 		Assertions.assertEquals(6, gr.getAuthor().size());
-		Assertions.assertTrue(gr.getAuthor().stream().anyMatch(a -> a.getFullname().equals("Nikolaidou,Charitini") &&
+		Assertions
-				a.getName().equals("Charitini") && a.getSurname().equals("Nikolaidou")
+			.assertTrue(
-				&& a.getRank() == 1 && a.getPid() == null));
+				gr
+					.getAuthor()
+					.stream()
+					.anyMatch(
+						a -> a.getFullname().equals("Nikolaidou,Charitini") &&
+							a.getName().equals("Charitini") && a.getSurname().equals("Nikolaidou")
+							&& a.getRank() == 1 && a.getPid() == null));
 
-		Assertions.assertTrue(gr.getAuthor().stream().anyMatch(a -> a.getFullname().equals("Votsi,Nefta") &&
+		Assertions
-				a.getName().equals("Nefta") && a.getSurname().equals("Votsi")
+			.assertTrue(
-				&& a.getRank() == 2 && a.getPid().getId().getScheme().equals(ModelConstants.ORCID)
+				gr
-				&& a.getPid().getId().getValue().equals("0000-0001-6651-1178") && a.getPid().getProvenance() != null));
+					.getAuthor()
+					.stream()
+					.anyMatch(
+						a -> a.getFullname().equals("Votsi,Nefta") &&
+							a.getName().equals("Nefta") && a.getSurname().equals("Votsi")
+							&& a.getRank() == 2 && a.getPid().getId().getScheme().equals(ModelConstants.ORCID)
+							&& a.getPid().getId().getValue().equals("0000-0001-6651-1178")
+							&& a.getPid().getProvenance() != null));
 
-		Assertions.assertTrue(gr.getAuthor().stream().anyMatch(a -> a.getFullname().equals("Sgardelis,Steanos") &&
+		Assertions
-				a.getName().equals("Steanos") && a.getSurname().equals("Sgardelis")
+			.assertTrue(
-				&& a.getRank() == 3 && a.getPid().getId().getScheme().equals(ModelConstants.ORCID_PENDING)
+				gr
-				&& a.getPid().getId().getValue().equals("0000-0001-6651-1178") && a.getPid().getProvenance() != null));
+					.getAuthor()
+					.stream()
+					.anyMatch(
+						a -> a.getFullname().equals("Sgardelis,Steanos") &&
+							a.getName().equals("Steanos") && a.getSurname().equals("Sgardelis")
+							&& a.getRank() == 3 && a.getPid().getId().getScheme().equals(ModelConstants.ORCID_PENDING)
+							&& a.getPid().getId().getValue().equals("0000-0001-6651-1178")
+							&& a.getPid().getProvenance() != null));
 
-		Assertions.assertTrue(gr.getAuthor().stream().anyMatch(a -> a.getFullname().equals("Halley,John") &&
+		Assertions
-				a.getName().equals("John") && a.getSurname().equals("Halley")
+			.assertTrue(
-				&& a.getRank() == 4 && a.getPid() == null));
+				gr
+					.getAuthor()
+					.stream()
+					.anyMatch(
+						a -> a.getFullname().equals("Halley,John") &&
+							a.getName().equals("John") && a.getSurname().equals("Halley")
+							&& a.getRank() == 4 && a.getPid() == null));
 
-		Assertions.assertTrue(gr.getAuthor().stream().anyMatch(a -> a.getFullname().equals("Pantis,John") &&
+		Assertions
-				a.getName().equals("John") && a.getSurname().equals("Pantis")
+			.assertTrue(
-				&& a.getRank() == 5 && a.getPid().getId().getScheme().equals(ModelConstants.ORCID)
+				gr
-				&& a.getPid().getId().getValue().equals("0000-0001-6651-1178") && a.getPid().getProvenance() != null));
+					.getAuthor()
+					.stream()
+					.anyMatch(
+						a -> a.getFullname().equals("Pantis,John") &&
+							a.getName().equals("John") && a.getSurname().equals("Pantis")
+							&& a.getRank() == 5 && a.getPid().getId().getScheme().equals(ModelConstants.ORCID)
+							&& a.getPid().getId().getValue().equals("0000-0001-6651-1178")
+							&& a.getPid().getProvenance() != null));
 
-		Assertions.assertTrue(gr.getAuthor().stream().anyMatch(a -> a.getFullname().equals("Tsiafouli,Maria") &&
+		Assertions
-				a.getName().equals("Maria") && a.getSurname().equals("Tsiafouli")
+			.assertTrue(
-				&& a.getRank() == 6 && a.getPid().getId().getScheme().equals(ModelConstants.ORCID_PENDING)
+				gr
-				&& a.getPid().getId().getValue().equals("0000-0001-6651-1178") && a.getPid().getProvenance() != null));
+					.getAuthor()
+					.stream()
+					.anyMatch(
+						a -> a.getFullname().equals("Tsiafouli,Maria") &&
+							a.getName().equals("Maria") && a.getSurname().equals("Tsiafouli")
+							&& a.getRank() == 6 && a.getPid().getId().getScheme().equals(ModelConstants.ORCID_PENDING)
+							&& a.getPid().getId().getValue().equals("0000-0001-6651-1178")
+							&& a.getPid().getProvenance() != null));
 
 		Assertions.assertEquals("publication", gr.getType());
 
@@ -216,27 +264,52 @@ public class DumpJobTest {
 		Assertions.assertEquals("English", gr.getLanguage().getLabel());
 
 		Assertions.assertEquals(1, gr.getCountry().size());
-		Assertions.assertEquals("IT" , gr.getCountry().get(0).getCode());
+		Assertions.assertEquals("IT", gr.getCountry().get(0).getCode());
-		Assertions.assertEquals("Italy" , gr.getCountry().get(0).getLabel());
+		Assertions.assertEquals("Italy", gr.getCountry().get(0).getLabel());
-		Assertions.assertTrue( gr.getCountry().get(0).getProvenance() == null);
+		Assertions.assertTrue(gr.getCountry().get(0).getProvenance() == null);
 
 		Assertions.assertEquals(12, gr.getSubjects().size());
-		Assertions.assertTrue(gr.getSubjects().stream().anyMatch(s -> s.getSubject().getValue().equals("Ecosystem Services hotspots")
+		Assertions
-				&& s.getSubject().getScheme().equals("ACM") && s.getProvenance() != null  &&
+			.assertTrue(
-				s.getProvenance().getProvenance().equals("sysimport:crosswalk:repository")));
+				gr
-		Assertions.assertTrue(gr.getSubjects().stream().anyMatch(s -> s.getSubject().getValue().equals("Natura 2000")
+					.getSubjects()
-				&& s.getSubject().getScheme().equals("") && s.getProvenance() != null  &&
+					.stream()
-				s.getProvenance().getProvenance().equals("sysimport:crosswalk:repository")));
+					.anyMatch(
+						s -> s.getSubject().getValue().equals("Ecosystem Services hotspots")
+							&& s.getSubject().getScheme().equals("ACM") && s.getProvenance() != null &&
+							s.getProvenance().getProvenance().equals("sysimport:crosswalk:repository")));
+		Assertions
+			.assertTrue(
+				gr
+					.getSubjects()
+					.stream()
+					.anyMatch(
+						s -> s.getSubject().getValue().equals("Natura 2000")
+							&& s.getSubject().getScheme().equals("") && s.getProvenance() != null &&
+							s.getProvenance().getProvenance().equals("sysimport:crosswalk:repository")));
 
-		Assertions.assertEquals("Ecosystem Service capacity is higher in areas of multiple designation types",
+		Assertions
+			.assertEquals(
+				"Ecosystem Service capacity is higher in areas of multiple designation types",
 				gr.getMaintitle());
 
 		Assertions.assertEquals(null, gr.getSubtitle());
 
 		Assertions.assertEquals(1, gr.getDescription().size());
 
-		Assertions.assertTrue(gr.getDescription().get(0).startsWith("The implementation of the Ecosystem Service (ES) concept into practice"));
+		Assertions
-		Assertions.assertTrue(gr.getDescription().get(0).endsWith("start complying with new standards and demands for nature conservation and environmental management."));
+			.assertTrue(
+				gr
+					.getDescription()
+					.get(0)
+					.startsWith("The implementation of the Ecosystem Service (ES) concept into practice"));
+		Assertions
+			.assertTrue(
+				gr
+					.getDescription()
+					.get(0)
+					.endsWith(
+						"start complying with new standards and demands for nature conservation and environmental management."));
 
 		Assertions.assertEquals("2017-01-01", gr.getPublicationdate());
 
@@ -255,7 +328,9 @@ public class DumpJobTest {
 		Assertions.assertEquals(0, gr.getCoverage().size());
 
 		Assertions.assertEquals(ModelConstants.ACCESS_RIGHT_OPEN, gr.getBestaccessright().getLabel());
-		Assertions.assertEquals(Constants.accessRightsCoarMap.get(ModelConstants.ACCESS_RIGHT_OPEN), gr.getBestaccessright().getCode());
+		Assertions
+			.assertEquals(
+				Constants.accessRightsCoarMap.get(ModelConstants.ACCESS_RIGHT_OPEN), gr.getBestaccessright().getCode());
 		Assertions.assertEquals(null, gr.getBestaccessright().getOpenAccessRoute());
 
 		Assertions.assertEquals("One Ecosystem", gr.getContainer().getName());
@@ -284,12 +359,16 @@ public class DumpJobTest {
 		Assertions.assertEquals("50|pensoft_____::00ea4a1cd53806a97d62ea6bf268f2a2", gr.getId());
 
 		Assertions.assertEquals(2, gr.getOriginalId().size());
-		Assertions.assertTrue(gr.getOriginalId().contains("50|pensoft_____::00ea4a1cd53806a97d62ea6bf268f2a2")
+		Assertions
-				&& gr.getOriginalId().contains("10.3897/oneeco.2.e13718"));
+			.assertTrue(
+				gr.getOriginalId().contains("50|pensoft_____::00ea4a1cd53806a97d62ea6bf268f2a2")
+					&& gr.getOriginalId().contains("10.3897/oneeco.2.e13718"));
 
 		Assertions.assertEquals(1, gr.getPid().size());
-		Assertions.assertTrue(gr.getPid().get(0).getScheme().equals("doi")
+		Assertions
-				&& gr.getPid().get(0).getValue().equals("10.1016/j.triboint.2014.05.004"));
+			.assertTrue(
+				gr.getPid().get(0).getScheme().equals("doi")
+					&& gr.getPid().get(0).getValue().equals("10.1016/j.triboint.2014.05.004"));
 
 		Assertions.assertEquals("2020-03-23T00:20:51.392Z", gr.getDateofcollection());
 
@@ -298,53 +377,63 @@ public class DumpJobTest {
 		Instance instance = gr.getInstance().get(0);
 		Assertions.assertEquals(0, instance.getPid().size());
 		Assertions.assertEquals(1, instance.getAlternateIdentifier().size());
-		Assertions.assertTrue(instance.getAlternateIdentifier().get(0).getScheme().equals("doi")
+		Assertions
-				&& instance.getAlternateIdentifier().get(0).getValue().equals("10.3897/oneeco.2.e13718"));
+			.assertTrue(
+				instance.getAlternateIdentifier().get(0).getScheme().equals("doi")
+					&& instance.getAlternateIdentifier().get(0).getValue().equals("10.3897/oneeco.2.e13718"));
 		Assertions.assertEquals(null, instance.getLicense());
-		Assertions.assertTrue(instance.getAccessright().getCode().equals(Constants.accessRightsCoarMap
+		Assertions
-				.get(ModelConstants.ACCESS_RIGHT_OPEN)));
+			.assertTrue(
+				instance
+					.getAccessright()
+					.getCode()
+					.equals(
+						Constants.accessRightsCoarMap
+							.get(ModelConstants.ACCESS_RIGHT_OPEN)));
 		Assertions.assertTrue(instance.getAccessright().getLabel().equals(ModelConstants.ACCESS_RIGHT_OPEN));
 		Assertions.assertTrue(instance.getAccessright().getOpenAccessRoute().equals(OpenAccessRoute.green));
 		Assertions.assertTrue(instance.getType().equals("Article"));
 		Assertions.assertEquals(2, instance.getUrl().size());
-		Assertions.assertTrue(instance.getUrl().contains("https://doi.org/10.3897/oneeco.2.e13718")
+		Assertions
-				&& instance.getUrl().contains("https://oneecosystem.pensoft.net/article/13718/"));
+			.assertTrue(
-		Assertions.assertEquals("2017-01-01",instance.getPublicationdate());
+				instance.getUrl().contains("https://doi.org/10.3897/oneeco.2.e13718")
-		Assertions.assertEquals(null,instance.getArticleprocessingcharge());
+					&& instance.getUrl().contains("https://oneecosystem.pensoft.net/article/13718/"));
+		Assertions.assertEquals("2017-01-01", instance.getPublicationdate());
+		Assertions.assertEquals(null, instance.getArticleprocessingcharge());
 		Assertions.assertEquals("peerReviewed", instance.getRefereed());
 	}
 
-
 	@Test
-	public void testDatasetDump(){
+	public void testDatasetDump() {
 		final String sourcePath = getClass()
-				.getResource("/eu/dnetlib/dhp/oa/graph/dump/resultDump/dataset_extendedinstance")
+			.getResource("/eu/dnetlib/dhp/oa/graph/dump/resultDump/dataset_extendedinstance")
-				.getPath();
+			.getPath();
 
 		final String communityMapPath = getClass()
-				.getResource("/eu/dnetlib/dhp/oa/graph/dump/communityMapPath/communitymap.json")
+			.getResource("/eu/dnetlib/dhp/oa/graph/dump/communityMapPath/communitymap.json")
-				.getPath();
+			.getPath();
 
 		DumpProducts dump = new DumpProducts();
 		dump
-				.run(false, sourcePath, workingDir.toString() + "/result",
+			.run(
-						communityMapPath, Dataset.class,
+				false, sourcePath, workingDir.toString() + "/result",
-						GraphResult.class, Constants.DUMPTYPE.COMPLETE.getType());
+				communityMapPath, Dataset.class,
+				GraphResult.class, Constants.DUMPTYPE.COMPLETE.getType());
 
 		final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
 
 		JavaRDD<GraphResult> tmp = sc
-				.textFile(workingDir.toString() + "/result")
+			.textFile(workingDir.toString() + "/result")
-				.map(item -> OBJECT_MAPPER.readValue(item, GraphResult.class));
+			.map(item -> OBJECT_MAPPER.readValue(item, GraphResult.class));
 
 		org.apache.spark.sql.Dataset<GraphResult> verificationDataset = spark
-				.createDataset(tmp.rdd(), Encoders.bean(GraphResult.class));
+			.createDataset(tmp.rdd(), Encoders.bean(GraphResult.class));
 
 		Assertions.assertEquals(1, verificationDataset.count());
 
 		Assertions.assertEquals(1, verificationDataset.filter("type = 'dataset'").count());
 
-		//the common fields in the result have been already checked. Now checking only
+		// the common fields in the result have been already checked. Now checking only
 		// community specific fields
 
 		GraphResult gr = verificationDataset.first();
@@ -353,10 +442,33 @@ public class DumpJobTest {
 		Assertions.assertEquals(2, gr.getGeolocation().stream().filter(gl -> gl.getBox().equals("")).count());
 		Assertions.assertEquals(1, gr.getGeolocation().stream().filter(gl -> gl.getPlace().equals("")).count());
 		Assertions.assertEquals(1, gr.getGeolocation().stream().filter(gl -> gl.getPoint().equals("")).count());
-		Assertions.assertEquals(1, gr.getGeolocation().stream().filter(gl -> gl.getPlace().equals("18 York St, Ottawa, ON K1N 5S6; Ottawa; Ontario; Canada")).count());
+		Assertions
-		Assertions.assertEquals(1, gr.getGeolocation().stream().filter(gl -> gl.getPoint().equals("45.427242 -75.693904")).count());
+			.assertEquals(
-		Assertions.assertEquals(1, gr.getGeolocation().stream().filter(gl -> gl.getPoint().equals("") && !gl.getPlace().equals("")).count());
+				1,
-		Assertions.assertEquals(1, gr.getGeolocation().stream().filter(gl -> !gl.getPoint().equals("") && gl.getPlace().equals("")).count());
+				gr
+					.getGeolocation()
+					.stream()
+					.filter(gl -> gl.getPlace().equals("18 York St, Ottawa, ON K1N 5S6; Ottawa; Ontario; Canada"))
+					.count());
+		Assertions
+			.assertEquals(
+				1, gr.getGeolocation().stream().filter(gl -> gl.getPoint().equals("45.427242 -75.693904")).count());
+		Assertions
+			.assertEquals(
+				1,
+				gr
+					.getGeolocation()
+					.stream()
+					.filter(gl -> gl.getPoint().equals("") && !gl.getPlace().equals(""))
+					.count());
+		Assertions
+			.assertEquals(
+				1,
+				gr
+					.getGeolocation()
+					.stream()
+					.filter(gl -> !gl.getPoint().equals("") && gl.getPlace().equals(""))
+					.count());
 
 		Assertions.assertEquals("1024Gb", gr.getSize());
 
@@ -373,30 +485,30 @@ public class DumpJobTest {
 	}
 
 	@Test
-	public void testSoftwareDump(){
+	public void testSoftwareDump() {
 		final String sourcePath = getClass()
-				.getResource("/eu/dnetlib/dhp/oa/graph/dump/resultDump/software_extendedinstance")
+			.getResource("/eu/dnetlib/dhp/oa/graph/dump/resultDump/software_extendedinstance")
-				.getPath();
+			.getPath();
 
 		final String communityMapPath = getClass()
-				.getResource("/eu/dnetlib/dhp/oa/graph/dump/communityMapPath/communitymap.json")
+			.getResource("/eu/dnetlib/dhp/oa/graph/dump/communityMapPath/communitymap.json")
-				.getPath();
+			.getPath();
 
 		DumpProducts dump = new DumpProducts();
 		dump
-				.run(false, sourcePath, workingDir.toString() + "/result",
+			.run(
-						communityMapPath, Software.class,
+				false, sourcePath, workingDir.toString() + "/result",
-						GraphResult.class, Constants.DUMPTYPE.COMPLETE.getType());
+				communityMapPath, Software.class,
+				GraphResult.class, Constants.DUMPTYPE.COMPLETE.getType());
 
 		final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
 
-
 		JavaRDD<GraphResult> tmp = sc
-				.textFile(workingDir.toString() + "/result")
+			.textFile(workingDir.toString() + "/result")
-				.map(item -> OBJECT_MAPPER.readValue(item, GraphResult.class));
+			.map(item -> OBJECT_MAPPER.readValue(item, GraphResult.class));
 
 		org.apache.spark.sql.Dataset<GraphResult> verificationDataset = spark
-				.createDataset(tmp.rdd(), Encoders.bean(GraphResult.class));
+			.createDataset(tmp.rdd(), Encoders.bean(GraphResult.class));
 
 		Assertions.assertEquals(1, verificationDataset.count());
 
@@ -412,7 +524,6 @@ public class DumpJobTest {
 
 		Assertions.assertEquals("perl", gr.getProgrammingLanguage());
 
-
 		Assertions.assertEquals(null, gr.getContainer());
 		Assertions.assertEquals(null, gr.getContactperson());
 		Assertions.assertEquals(null, gr.getContactgroup());
@@ -424,30 +535,30 @@ public class DumpJobTest {
 	}
 
 	@Test
-	public void testOrpDump(){
+	public void testOrpDump() {
 		final String sourcePath = getClass()
-				.getResource("/eu/dnetlib/dhp/oa/graph/dump/resultDump/orp_extendedinstance")
+			.getResource("/eu/dnetlib/dhp/oa/graph/dump/resultDump/orp_extendedinstance")
-				.getPath();
+			.getPath();
 
 		final String communityMapPath = getClass()
-				.getResource("/eu/dnetlib/dhp/oa/graph/dump/communityMapPath/communitymap.json")
+			.getResource("/eu/dnetlib/dhp/oa/graph/dump/communityMapPath/communitymap.json")
-				.getPath();
+			.getPath();
 
 		DumpProducts dump = new DumpProducts();
 		dump
-				.run(false, sourcePath, workingDir.toString() + "/result",
+			.run(
-						communityMapPath, OtherResearchProduct.class,
+				false, sourcePath, workingDir.toString() + "/result",
-						GraphResult.class, Constants.DUMPTYPE.COMPLETE.getType());
+				communityMapPath, OtherResearchProduct.class,
+				GraphResult.class, Constants.DUMPTYPE.COMPLETE.getType());
 
 		final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
 
-
 		JavaRDD<GraphResult> tmp = sc
-				.textFile(workingDir.toString() + "/result")
+			.textFile(workingDir.toString() + "/result")
-				.map(item -> OBJECT_MAPPER.readValue(item, GraphResult.class));
+			.map(item -> OBJECT_MAPPER.readValue(item, GraphResult.class));
 
 		org.apache.spark.sql.Dataset<GraphResult> verificationDataset = spark
-				.createDataset(tmp.rdd(), Encoders.bean(GraphResult.class));
+			.createDataset(tmp.rdd(), Encoders.bean(GraphResult.class));
 
 		Assertions.assertEquals(1, verificationDataset.count());
 
@@ -466,7 +577,6 @@ public class DumpJobTest {
 		Assertions.assertTrue(gr.getTool().contains("tool1"));
 		Assertions.assertTrue(gr.getTool().contains("tool2"));
 
-
 		Assertions.assertEquals(null, gr.getContainer());
 		Assertions.assertEquals(null, gr.getDocumentationUrl());
 		Assertions.assertEquals(null, gr.getCodeRepositoryUrl());
@@ -481,32 +591,33 @@ public class DumpJobTest {
 	public void testPublicationDumpCommunity() throws JsonProcessingException {
 
 		final String sourcePath = getClass()
-				.getResource("/eu/dnetlib/dhp/oa/graph/dump/resultDump/publication_extendedinstance")
+			.getResource("/eu/dnetlib/dhp/oa/graph/dump/resultDump/publication_extendedinstance")
-				.getPath();
+			.getPath();
 
 		final String communityMapPath = getClass()
-				.getResource("/eu/dnetlib/dhp/oa/graph/dump/communityMapPath/communitymap.json")
+			.getResource("/eu/dnetlib/dhp/oa/graph/dump/communityMapPath/communitymap.json")
-				.getPath();
+			.getPath();
 
 		DumpProducts dump = new DumpProducts();
 		dump
-				.run(false, sourcePath, workingDir.toString() + "/result", communityMapPath, Publication.class,
+			.run(
-						CommunityResult.class, Constants.DUMPTYPE.COMMUNITY.getType());
+				false, sourcePath, workingDir.toString() + "/result", communityMapPath, Publication.class,
+				CommunityResult.class, Constants.DUMPTYPE.COMMUNITY.getType());
 
 		final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
 
 		JavaRDD<CommunityResult> tmp = sc
-				.textFile(workingDir.toString() + "/result")
+			.textFile(workingDir.toString() + "/result")
-				.map(item -> OBJECT_MAPPER.readValue(item, CommunityResult.class));
+			.map(item -> OBJECT_MAPPER.readValue(item, CommunityResult.class));
 
 		org.apache.spark.sql.Dataset<CommunityResult> verificationDataset = spark
-				.createDataset(tmp.rdd(), Encoders.bean(CommunityResult.class));
+			.createDataset(tmp.rdd(), Encoders.bean(CommunityResult.class));
 
 		Assertions.assertEquals(1, verificationDataset.count());
 
 		Assertions.assertEquals(1, verificationDataset.filter("type = 'publication'").count());
 
-		//the common fields in the result have been already checked. Now checking only
+		// the common fields in the result have been already checked. Now checking only
 		// community specific fields
 
 		CommunityResult cr = verificationDataset.first();
@@ -519,15 +630,20 @@ public class DumpJobTest {
 		Assertions.assertEquals("0.9", cr.getContext().get(0).getProvenance().get(0).getTrust());
 
 		Assertions.assertEquals(1, cr.getCollectedfrom().size());
-		Assertions.assertEquals("10|openaire____::fdc7e0400d8c1634cdaf8051dbae23db", cr.getCollectedfrom().get(0).getKey());
+		Assertions
+			.assertEquals("10|openaire____::fdc7e0400d8c1634cdaf8051dbae23db", cr.getCollectedfrom().get(0).getKey());
 		Assertions.assertEquals("Pensoft", cr.getCollectedfrom().get(0).getValue());
 
 		Assertions.assertEquals(1, cr.getInstance().size());
-		Assertions.assertEquals("10|openaire____::fdc7e0400d8c1634cdaf8051dbae23db", cr.getInstance().get(0).getCollectedfrom().getKey());
+		Assertions
+			.assertEquals(
+				"10|openaire____::fdc7e0400d8c1634cdaf8051dbae23db",
+				cr.getInstance().get(0).getCollectedfrom().getKey());
 		Assertions.assertEquals("Pensoft", cr.getInstance().get(0).getCollectedfrom().getValue());
-		Assertions.assertEquals("10|openaire____::e707e544b9a5bd23fc27fbfa65eb60dd", cr.getInstance().get(0).getHostedby().getKey());
+		Assertions
-		Assertions.assertEquals("One Ecosystem",cr.getInstance().get(0).getHostedby().getValue());
+			.assertEquals(
-
+				"10|openaire____::e707e544b9a5bd23fc27fbfa65eb60dd", cr.getInstance().get(0).getHostedby().getKey());
+		Assertions.assertEquals("One Ecosystem", cr.getInstance().get(0).getHostedby().getValue());
 
 	}
 
@@ -587,8 +703,6 @@ public class DumpJobTest {
 
 		Assertions.assertTrue(verificationDataset.filter("type = 'dataset'").count() == 90);
 
-
-
 	}
 
 	@Test
@@ -650,7 +764,6 @@ public class DumpJobTest {
 
 		Assertions.assertEquals(0, verificationDataset.count());
 
-
 	}
 
 	@Test
@@ -718,7 +831,6 @@ public class DumpJobTest {
 
 		Assertions.assertEquals(6, verificationDataset.filter("type = 'software'").count());
 
-
 	}
 
 	@Test
@@ -814,7 +926,6 @@ public class DumpJobTest {
 
 		Assertions.assertEquals(23, verificationDataset.count());
 
-
 		Assertions.assertEquals(23, verificationDataset.filter("type = 'publication'").count());
 
 		verificationDataset.createOrReplaceTempView("check");
@@ -832,7 +943,6 @@ public class DumpJobTest {
 
 		Assertions.assertTrue(temp.filter("id = '50|dedup_wf_001::01e6a28565ca01376b7548e530c6f6e8'").count() == 1);
 
-
 	}
 
 }

dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/dump/PrepareResultProjectJobTest.java

@@ -8,16 +8,17 @@ import java.nio.file.Files;
 import java.nio.file.Path;
 
 import org.apache.commons.io.FileUtils;
-import org.apache.neethi.Assertion;
+
 import org.apache.spark.SparkConf;
 import org.apache.spark.api.java.JavaRDD;
 import org.apache.spark.api.java.JavaSparkContext;
-import org.apache.spark.api.java.function.ForeachFunction;
+
 import org.apache.spark.sql.Dataset;
 import org.apache.spark.sql.Encoders;
 import org.apache.spark.sql.Row;
 import org.apache.spark.sql.SparkSession;
 import org.junit.jupiter.api.AfterAll;
+
 import org.junit.jupiter.api.BeforeAll;
 import org.junit.jupiter.api.Test;
 import org.slf4j.Logger;
@@ -229,107 +230,98 @@ public class PrepareResultProjectJobTest {
 	public void testMatchValidated() throws Exception {
 
 		final String sourcePath = getClass()
-				.getResource("/eu/dnetlib/dhp/oa/graph/dump/resultProject/match_validatedRels")
+			.getResource("/eu/dnetlib/dhp/oa/graph/dump/resultProject/match_validatedRels")
-				.getPath();
+			.getPath();
 
 		SparkPrepareResultProject.main(new String[] {
-				"-isSparkSessionManaged", Boolean.FALSE.toString(),
+			"-isSparkSessionManaged", Boolean.FALSE.toString(),
-				"-outputPath", workingDir.toString() + "/preparedInfo",
+			"-outputPath", workingDir.toString() + "/preparedInfo",
-				"-sourcePath", sourcePath
+			"-sourcePath", sourcePath
 		});
 
 		final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
 
 		JavaRDD<ResultProject> tmp = sc
-				.textFile(workingDir.toString() + "/preparedInfo")
+			.textFile(workingDir.toString() + "/preparedInfo")
-				.map(item -> OBJECT_MAPPER.readValue(item, ResultProject.class));
+			.map(item -> OBJECT_MAPPER.readValue(item, ResultProject.class));
 
 		org.apache.spark.sql.Dataset<ResultProject> verificationDataset = spark
-				.createDataset(tmp.rdd(), Encoders.bean(ResultProject.class));
+			.createDataset(tmp.rdd(), Encoders.bean(ResultProject.class));
 
-		Assertions.assertTrue(verificationDataset.count() == 2);
+		assertEquals(2, verificationDataset.count() );
 
-		Assertions
+		assertEquals(
-				.assertEquals(
+				1,
-						1,
+				verificationDataset.filter("resultId = '50|dedup_wf_001::e4805d005bfab0cd39a1642cbf477fdb'").count());
-						verificationDataset.filter("resultId = '50|dedup_wf_001::e4805d005bfab0cd39a1642cbf477fdb'").count());
+		assertEquals(
-		Assertions
+				1,
-				.assertEquals(
+				verificationDataset.filter("resultId = '50|dedup_wf_001::51b88f272ba9c3bb181af64e70255a80'").count());
-						1,
-						verificationDataset.filter("resultId = '50|dedup_wf_001::51b88f272ba9c3bb181af64e70255a80'").count());
 
 		verificationDataset.createOrReplaceTempView("dataset");
 
-		String query = "select resultId, MyT.id project , MyT.title title, MyT.acronym acronym , MyT.provenance.provenance provenance, " +
+		String query = "select resultId, MyT.id project , MyT.title title, MyT.acronym acronym , MyT.provenance.provenance provenance, "
-				"MyT.validated.validatedByFunder, MyT.validated.validationDate "
+			+
-				+ "from dataset "
+			"MyT.validated.validatedByFunder, MyT.validated.validationDate "
-				+ "lateral view explode(projectsList) p as MyT ";
+			+ "from dataset "
+			+ "lateral view explode(projectsList) p as MyT ";
 
 		org.apache.spark.sql.Dataset<Row> resultExplodedProvenance = spark.sql(query);
-		Assertions.assertEquals(3, resultExplodedProvenance.count());
+		assertEquals(3, resultExplodedProvenance.count());
-		Assertions.assertEquals(3, resultExplodedProvenance.filter("validatedByFunder = true").count());
+		assertEquals(3, resultExplodedProvenance.filter("validatedByFunder = true").count());
-		Assertions
+		assertEquals(
-				.assertEquals(
+				2,
-						2,
+				resultExplodedProvenance
-						resultExplodedProvenance
+					.filter("resultId = '50|dedup_wf_001::e4805d005bfab0cd39a1642cbf477fdb'")
-								.filter("resultId = '50|dedup_wf_001::e4805d005bfab0cd39a1642cbf477fdb'")
+					.count());
-								.count());
 
-		Assertions
+		assertEquals(
-				.assertEquals(
+				1,
-						1,
+				resultExplodedProvenance
-						resultExplodedProvenance
+					.filter("resultId = '50|dedup_wf_001::51b88f272ba9c3bb181af64e70255a80'")
-								.filter("resultId = '50|dedup_wf_001::51b88f272ba9c3bb181af64e70255a80'")
+					.count());
-								.count());
 
-		Assertions
+		assertEquals(
-				.assertEquals(
+				2,
-						2,
+				resultExplodedProvenance
-						resultExplodedProvenance
+					.filter("project = '40|aka_________::0f7d119de1f656b5763a16acf876fed6'")
-								.filter("project = '40|aka_________::0f7d119de1f656b5763a16acf876fed6'")
+					.count());
-								.count());
 
-		Assertions
+		assertEquals(
-				.assertEquals(
+				1,
-						1,
+				resultExplodedProvenance
-						resultExplodedProvenance
+					.filter(
-								.filter(
+						"project = '40|aka_________::0f7d119de1f656b5763a16acf876fed6' " +
-										"project = '40|aka_________::0f7d119de1f656b5763a16acf876fed6' " +
+							"and resultId = '50|dedup_wf_001::e4805d005bfab0cd39a1642cbf477fdb' " +
-												"and resultId = '50|dedup_wf_001::e4805d005bfab0cd39a1642cbf477fdb' " +
+							"and validatedByFunder = true " +
-												"and validatedByFunder = true " +
+							"and validationDate = '2021-08-06'")
-												"and validationDate = '2021-08-06'")
+					.count());
-								.count());
 
-		Assertions
+		assertEquals(
-				.assertEquals(
+				1,
-						1,
+				resultExplodedProvenance
-						resultExplodedProvenance
+					.filter(
-								.filter(
+						"project = '40|aka_________::0f7d119de1f656b5763a16acf876fed6' " +
-										"project = '40|aka_________::0f7d119de1f656b5763a16acf876fed6' " +
+							"and resultId = '50|dedup_wf_001::51b88f272ba9c3bb181af64e70255a80' " +
-												"and resultId = '50|dedup_wf_001::51b88f272ba9c3bb181af64e70255a80' " +
+							"and validatedByFunder = true and validationDate = '2021-08-04'")
-												"and validatedByFunder = true and validationDate = '2021-08-04'")
+					.count());
-								.count());
 
-		Assertions
+		assertEquals(
-				.assertEquals(
+				1,
-						1,
+				resultExplodedProvenance
-						resultExplodedProvenance
+					.filter("project = '40|aka_________::03376222b28a3aebf2730ac514818d04'")
-								.filter("project = '40|aka_________::03376222b28a3aebf2730ac514818d04'")
+					.count());
-								.count());
 
-		Assertions
+		assertEquals(
-				.assertEquals(
+				1,
-						1,
+				resultExplodedProvenance
-						resultExplodedProvenance
+					.filter(
-								.filter(
+						"project = '40|aka_________::03376222b28a3aebf2730ac514818d04' " +
-										"project = '40|aka_________::03376222b28a3aebf2730ac514818d04' " +
+							"and resultId = '50|dedup_wf_001::e4805d005bfab0cd39a1642cbf477fdb' " +
-												"and resultId = '50|dedup_wf_001::e4805d005bfab0cd39a1642cbf477fdb' " +
+							"and validatedByFunder = true and validationDate = '2021-08-05'")
-												"and validatedByFunder = true and validationDate = '2021-08-05'")
+					.count());
-								.count());
 
-		Assertions
+		assertEquals(
-				.assertEquals(
+				3, resultExplodedProvenance.filter("provenance = 'sysimport:crosswalk:entityregistry'").count());
-						3, resultExplodedProvenance.filter("provenance = 'sysimport:crosswalk:entityregistry'").count());
 
 	}
 }

dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/dump/UpdateProjectInfoTest.java

@@ -8,8 +8,6 @@ import java.util.HashMap;
 import java.util.logging.Filter;
 import java.util.stream.Collectors;
 
-import eu.dnetlib.dhp.schema.dump.oaf.community.Funder;
-import eu.dnetlib.dhp.schema.dump.oaf.community.Project;
 import org.apache.commons.io.FileUtils;
 import org.apache.spark.SparkConf;
 import org.apache.spark.api.java.JavaRDD;
@@ -31,6 +29,8 @@ import com.fasterxml.jackson.databind.ObjectMapper;
 import eu.dnetlib.dhp.oa.graph.dump.community.SparkUpdateProjectInfo;
 import eu.dnetlib.dhp.schema.dump.oaf.Result;
 import eu.dnetlib.dhp.schema.dump.oaf.community.CommunityResult;
+import eu.dnetlib.dhp.schema.dump.oaf.community.Funder;
+import eu.dnetlib.dhp.schema.dump.oaf.community.Project;
 
 public class UpdateProjectInfoTest {
 
@@ -142,26 +142,26 @@ public class UpdateProjectInfoTest {
 	}
 
 	@Test
-	public void testValidatedRelation() throws Exception{
+	public void testValidatedRelation() throws Exception {
 		final String sourcePath = getClass()
-				.getResource("/eu/dnetlib/dhp/oa/graph/dump/addProjectInfo")
+			.getResource("/eu/dnetlib/dhp/oa/graph/dump/addProjectInfo")
-				.getPath();
+			.getPath();
 
 		SparkUpdateProjectInfo.main(new String[] {
-				"-isSparkSessionManaged", Boolean.FALSE.toString(),
+			"-isSparkSessionManaged", Boolean.FALSE.toString(),
-				"-preparedInfoPath", sourcePath + "/preparedInfoValidated",
+			"-preparedInfoPath", sourcePath + "/preparedInfoValidated",
-				"-outputPath", workingDir.toString() + "/result",
+			"-outputPath", workingDir.toString() + "/result",
-				"-sourcePath", sourcePath + "/publication_extendedmodel"
+			"-sourcePath", sourcePath + "/publication_extendedmodel"
 		});
 
 		final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
 
 		JavaRDD<CommunityResult> tmp = sc
-				.textFile(workingDir.toString() + "/result")
+			.textFile(workingDir.toString() + "/result")
-				.map(item -> OBJECT_MAPPER.readValue(item, CommunityResult.class));
+			.map(item -> OBJECT_MAPPER.readValue(item, CommunityResult.class));
 
 		org.apache.spark.sql.Dataset<CommunityResult> verificationDataset = spark
-				.createDataset(tmp.rdd(), Encoders.bean(CommunityResult.class));
+			.createDataset(tmp.rdd(), Encoders.bean(CommunityResult.class));
 
 		verificationDataset.show(false);
 
@@ -169,10 +169,10 @@ public class UpdateProjectInfoTest {
 		verificationDataset.createOrReplaceTempView("dataset");
 
 		String query = "select id, MyT.code code, MyT.title title, MyT.funder.name funderName, MyT.funder.shortName funderShortName, "
-				+
+			+
-				"MyT.funder.jurisdiction funderJurisdiction, MyT.funder.fundingStream fundingStream, MyT.validated "
+			"MyT.funder.jurisdiction funderJurisdiction, MyT.funder.fundingStream fundingStream, MyT.validated "
-				+ "from dataset " +
+			+ "from dataset " +
-				"lateral view explode(projects) p as MyT ";
+			"lateral view explode(projects) p as MyT ";
 
 		org.apache.spark.sql.Dataset<Row> resultExplodedProvenance = spark.sql(query);
 
@@ -180,27 +180,34 @@ public class UpdateProjectInfoTest {
 		resultExplodedProvenance.show(false);
 
 		Assertions
-				.assertEquals(
+			.assertEquals(
-						2,
+				2,
-						resultExplodedProvenance.filter("id = '50|pensoft_____::00ea4a1cd53806a97d62ea6bf268f2a2'").count());
+				resultExplodedProvenance.filter("id = '50|pensoft_____::00ea4a1cd53806a97d62ea6bf268f2a2'").count());
 
 		Assertions
-				.assertEquals(
+			.assertEquals(
-						1,
+				1,
-						resultExplodedProvenance
+				resultExplodedProvenance
-								.filter("id = '50|pensoft_____::00ea4a1cd53806a97d62ea6bf268f2a2' and code = '123455'")
+					.filter("id = '50|pensoft_____::00ea4a1cd53806a97d62ea6bf268f2a2' and code = '123455'")
-								.count());
+					.count());
 
 		Assertions
-				.assertEquals(
+			.assertEquals(
-						1,
+				1,
-						resultExplodedProvenance
+				resultExplodedProvenance
-								.filter("id = '50|pensoft_____::00ea4a1cd53806a97d62ea6bf268f2a2' and code = '119027'")
+					.filter("id = '50|pensoft_____::00ea4a1cd53806a97d62ea6bf268f2a2' and code = '119027'")
-								.count());
+					.count());
 
 		Project project = verificationDataset
-		.map((MapFunction<CommunityResult, Project>) cr -> cr.getProjects().stream().filter(p -> p.getValidated() != null).collect(Collectors.toList()).get(0)
+			.map(
-		, Encoders.bean(Project.class)).first();
+				(MapFunction<CommunityResult, Project>) cr -> cr
+					.getProjects()
+					.stream()
+					.filter(p -> p.getValidated() != null)
+					.collect(Collectors.toList())
+					.get(0),
+				Encoders.bean(Project.class))
+			.first();
 
 		Assertions.assertTrue(project.getFunder().getName().equals("Academy of Finland"));
 		Assertions.assertTrue(project.getFunder().getShortName().equals("AKA"));
@@ -208,18 +215,22 @@ public class UpdateProjectInfoTest {
 		Assertions.assertTrue(project.getFunder().getFundingStream() == null);
 		Assertions.assertTrue(project.getValidated().getValidationDate().equals("2021-08-06"));
 
-
 		project = verificationDataset
-				.map((MapFunction<CommunityResult, Project>) cr -> cr.getProjects().stream().filter(p -> p.getValidated() == null).collect(Collectors.toList()).get(0)
+			.map(
-						, Encoders.bean(Project.class)).first();
+				(MapFunction<CommunityResult, Project>) cr -> cr
-
+					.getProjects()
+					.stream()
+					.filter(p -> p.getValidated() == null)
+					.collect(Collectors.toList())
+					.get(0),
+				Encoders.bean(Project.class))
+			.first();
 
 		Assertions.assertTrue(project.getFunder().getName().equals("European Commission"));
 		Assertions.assertTrue(project.getFunder().getShortName().equals("EC"));
 		Assertions.assertTrue(project.getFunder().getJurisdiction().equals("EU"));
 		Assertions.assertTrue(project.getFunder().getFundingStream().equals("H2020"));
 
-
 	}
 
 }

dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/dump/complete/DumpRelationTest.java

@@ -94,7 +94,8 @@ public class DumpRelationTest {
 
 		verificationDataset.createOrReplaceTempView("table");
 
-		verificationDataset.foreach((ForeachFunction<Relation>)r -> System.out.println(new ObjectMapper().writeValueAsString(r)));
+		verificationDataset
+			.foreach((ForeachFunction<Relation>) r -> System.out.println(new ObjectMapper().writeValueAsString(r)));
 
 		Dataset<Row> check = spark
 			.sql(
@@ -134,13 +135,13 @@ public class DumpRelationTest {
 	public void test2() throws Exception {
 
 		final String sourcePath = getClass()
-				.getResource("/eu/dnetlib/dhp/oa/graph/dump/relation/relation_validated")
+			.getResource("/eu/dnetlib/dhp/oa/graph/dump/relation/relation_validated")
-				.getPath();
+			.getPath();
 
 		SparkDumpRelationJob.main(new String[] {
-				"-isSparkSessionManaged", Boolean.FALSE.toString(),
+			"-isSparkSessionManaged", Boolean.FALSE.toString(),
-				"-outputPath", workingDir.toString() + "/relation",
+			"-outputPath", workingDir.toString() + "/relation",
-				"-sourcePath", sourcePath
+			"-sourcePath", sourcePath
 		});
 
 //		dumpCommunityProducts.exec(MOCK_IS_LOOK_UP_URL,Boolean.FALSE, workingDir.toString()+"/dataset",sourcePath,"eu.dnetlib.dhp.schema.oaf.Dataset","eu.dnetlib.dhp.schema.dump.oaf.Dataset");
@@ -148,57 +149,58 @@ public class DumpRelationTest {
 		final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
 
 		JavaRDD<Relation> tmp = sc
-				.textFile(workingDir.toString() + "/relation")
+			.textFile(workingDir.toString() + "/relation")
-				.map(item -> OBJECT_MAPPER.readValue(item, Relation.class));
+			.map(item -> OBJECT_MAPPER.readValue(item, Relation.class));
 
 		org.apache.spark.sql.Dataset<Relation> verificationDataset = spark
-				.createDataset(tmp.rdd(), Encoders.bean(Relation.class));
+			.createDataset(tmp.rdd(), Encoders.bean(Relation.class));
 
 		verificationDataset.createOrReplaceTempView("table");
 
-		verificationDataset.foreach((ForeachFunction<Relation>)r -> System.out.println(new ObjectMapper().writeValueAsString(r)));
+		verificationDataset
+			.foreach((ForeachFunction<Relation>) r -> System.out.println(new ObjectMapper().writeValueAsString(r)));
 
 		Dataset<Row> check = spark
-				.sql(
+			.sql(
-						"SELECT reltype.name, source.id source, source.type stype, target.id target,target.type ttype, provenance.provenance "
+				"SELECT reltype.name, source.id source, source.type stype, target.id target,target.type ttype, provenance.provenance "
-								+
+					+
-								"from table ");
+					"from table ");
 
 		Assertions.assertEquals(20, check.filter("name = 'isProvidedBy'").count());
 		Assertions
-				.assertEquals(
+			.assertEquals(
-						20, check
+				20, check
-								.filter(
+					.filter(
-										"name = 'isProvidedBy' and stype = 'datasource' and ttype = 'organization' and " +
+						"name = 'isProvidedBy' and stype = 'datasource' and ttype = 'organization' and " +
-												"provenance = 'Harvested'")
+							"provenance = 'Harvested'")
-								.count());
+					.count());
 
 		Assertions.assertEquals(7, check.filter("name = 'isParticipant'").count());
 		Assertions
-				.assertEquals(
+			.assertEquals(
-						7, check
+				7, check
-								.filter(
+					.filter(
-										"name = 'isParticipant' and stype = 'organization' and ttype = 'project' " +
+						"name = 'isParticipant' and stype = 'organization' and ttype = 'project' " +
-												"and provenance = 'Harvested'")
+							"and provenance = 'Harvested'")
-								.count());
+					.count());
 
 		Assertions.assertEquals(1, check.filter("name = 'isAuthorInstitutionOf'").count());
 		Assertions
-				.assertEquals(
+			.assertEquals(
-						1, check
+				1, check
-								.filter(
+					.filter(
-										"name = 'isAuthorInstitutionOf' and stype = 'organization' and ttype = 'result' " +
+						"name = 'isAuthorInstitutionOf' and stype = 'organization' and ttype = 'result' " +
-												"and provenance = 'Inferred by OpenAIRE'")
+							"and provenance = 'Inferred by OpenAIRE'")
-								.count());
+					.count());
 
 		Assertions.assertEquals(2, check.filter("name = 'isProducedBy'").count());
 		Assertions
-				.assertEquals(
+			.assertEquals(
-						2, check
+				2, check
-								.filter(
+					.filter(
-										"name = 'isProducedBy' and stype = 'project' and ttype = 'result' " +
+						"name = 'isProducedBy' and stype = 'project' and ttype = 'result' " +
-												"and provenance = 'Harvested' and validated = true " +
+							"and provenance = 'Harvested' and validated = true " +
-												"and validationDate = '2021-08-06'")
+							"and validationDate = '2021-08-06'")
-								.count());
+					.count());
 	}
 }

dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/dump/complete/QueryInformationSystemTest.java

@@ -6,7 +6,6 @@ import static org.mockito.Mockito.lenient;
 import java.util.*;
 import java.util.function.Consumer;
 
-import eu.dnetlib.dhp.schema.common.ModelSupport;
 import org.junit.jupiter.api.Assertions;
 import org.junit.jupiter.api.BeforeEach;
 import org.junit.jupiter.api.Test;
@@ -14,6 +13,7 @@ import org.junit.jupiter.api.extension.ExtendWith;
 import org.mockito.Mock;
 import org.mockito.junit.jupiter.MockitoExtension;
 
+import eu.dnetlib.dhp.schema.common.ModelSupport;
 import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpException;
 import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
 
@@ -529,7 +529,8 @@ class QueryInformationSystemTest {
 		List<ContextInfo> cInfoList = new ArrayList<>();
 		final Consumer<ContextInfo> consumer = ci -> cInfoList.add(ci);
 		queryInformationSystem.execContextRelationQuery();
-		queryInformationSystem.getContextRelation(consumer, "contentproviders", ModelSupport.entityIdPrefix.get("datasource"));
+		queryInformationSystem
+			.getContextRelation(consumer, "contentproviders", ModelSupport.entityIdPrefix.get("datasource"));
 
 		Assertions.assertEquals(5, cInfoList.size());
 	}
@@ -540,7 +541,8 @@ class QueryInformationSystemTest {
 		List<ContextInfo> cInfoList = new ArrayList<>();
 		final Consumer<ContextInfo> consumer = ci -> cInfoList.add(ci);
 		queryInformationSystem.execContextRelationQuery();
-		queryInformationSystem.getContextRelation(consumer, "contentproviders", ModelSupport.entityIdPrefix.get("datasource"));
+		queryInformationSystem
+			.getContextRelation(consumer, "contentproviders", ModelSupport.entityIdPrefix.get("datasource"));
 
 		cInfoList.forEach(contextInfo -> {
 			switch (contextInfo.getId()) {

dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/dump/funderresult/SplitPerFunderTest.java

@@ -145,8 +145,8 @@ public class SplitPerFunderTest {
 
 		// CONICYT 0
 		tmp = sc
-				.textFile(workingDir.toString() + "/split/CONICYTF")
+			.textFile(workingDir.toString() + "/split/CONICYTF")
-				.map(item -> OBJECT_MAPPER.readValue(item, CommunityResult.class));
+			.map(item -> OBJECT_MAPPER.readValue(item, CommunityResult.class));
 		Assertions.assertEquals(0, tmp.count());
 
 	}

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

@@ -84,7 +84,8 @@ public class IndexRecordTransformerTest {
 
 	@Test
 	public void testForEOSCFutureTraining() throws IOException, TransformerException {
-		final String record = IOUtils.toString(getClass().getResourceAsStream("eosc-future/training-notebooks-seadatanet.xml"));
+		final String record = IOUtils
+			.toString(getClass().getResourceAsStream("eosc-future/training-notebooks-seadatanet.xml"));
 		testRecordTransformation(record);
 	}
 

pom.xml

@@ -753,7 +753,7 @@
         <mockito-core.version>3.3.3</mockito-core.version>
         <mongodb.driver.version>3.4.2</mongodb.driver.version>
         <vtd.version>[2.12,3.0)</vtd.version>
-        <dhp-schemas.version>[2.7.18]</dhp-schemas.version>
+        <dhp-schemas.version>[2.7.19]</dhp-schemas.version>
         <dnet-actionmanager-api.version>[4.0.3]</dnet-actionmanager-api.version>
         <dnet-actionmanager-common.version>[6.0.5]</dnet-actionmanager-common.version>
         <dnet-openaire-broker-common.version>[3.1.6]</dnet-openaire-broker-common.version>