Merge branch 'beta' of https://code-repo.d4science.org/andreas.czerniak/BrBETA_dnet-hadoop into beta

Reviewed-on: D-Net/dnet-hadoop#188

.gitignore

@@ -3,8 +3,6 @@
 *.iws
 *.ipr
 *.iml
-*.ipr
-*.iws
 *~
 .vscode
 .metals
@@ -27,4 +25,4 @@ spark-warehouse
 /**/job-override.properties
 /**/*.log
 /**/.factorypath
-
+/**/.scalafmt.conf

dhp-build/dhp-build-properties-maven-plugin/src/main/java/eu/dnetlib/maven/plugin/properties/GenerateOoziePropertiesMojo.java

@@ -8,8 +8,6 @@ import java.util.List;
 import org.apache.commons.lang.ArrayUtils;
 import org.apache.commons.lang.StringUtils;
 import org.apache.maven.plugin.AbstractMojo;
-import org.apache.maven.plugin.MojoExecutionException;
-import org.apache.maven.plugin.MojoFailureException;
 
 /**
  * Generates oozie properties which were not provided from commandline.
@@ -27,7 +25,7 @@ public class GenerateOoziePropertiesMojo extends AbstractMojo {
 	};
 
 	@Override
-	public void execute() throws MojoExecutionException, MojoFailureException {
+	public void execute() {
 		if (System.getProperties().containsKey(PROPERTY_NAME_WF_SOURCE_DIR)
 			&& !System.getProperties().containsKey(PROPERTY_NAME_SANDBOX_NAME)) {
 			String generatedSandboxName = generateSandboxName(
@@ -46,24 +44,24 @@ public class GenerateOoziePropertiesMojo extends AbstractMojo {
 	/**
 	 * Generates sandbox name from workflow source directory.
 	 *
-	 * @param wfSourceDir
+	 * @param wfSourceDir workflow source directory
 	 * @return generated sandbox name
 	 */
 	private String generateSandboxName(String wfSourceDir) {
 		// utilize all dir names until finding one of the limiters
-		List<String> sandboxNameParts = new ArrayList<String>();
+		List<String> sandboxNameParts = new ArrayList<>();
 		String[] tokens = StringUtils.split(wfSourceDir, File.separatorChar);
 		ArrayUtils.reverse(tokens);
 		if (tokens.length > 0) {
 			for (String token : tokens) {
 				for (String limiter : limiters) {
 					if (limiter.equals(token)) {
-						return sandboxNameParts.size() > 0
+						return !sandboxNameParts.isEmpty()
 							? StringUtils.join(sandboxNameParts.toArray())
 							: null;
 					}
 				}
-				if (sandboxNameParts.size() > 0) {
+				if (!sandboxNameParts.isEmpty()) {
 					sandboxNameParts.add(0, File.separator);
 				}
 				sandboxNameParts.add(0, token);

dhp-build/dhp-build-properties-maven-plugin/src/main/java/eu/dnetlib/maven/plugin/properties/WritePredefinedProjectProperties.java

@@ -16,6 +16,7 @@ import java.io.File;
 import java.io.FileInputStream;
 import java.io.IOException;
 import java.io.InputStream;
+import java.nio.charset.StandardCharsets;
 import java.util.ArrayList;
 import java.util.Arrays;
 import java.util.Collections;
@@ -289,7 +290,7 @@ public class WritePredefinedProjectProperties extends AbstractMojo {
 	 */
 	protected List<String> getEscapeChars(String escapeChars) {
 		List<String> tokens = getListFromCSV(escapeChars);
-		List<String> realTokens = new ArrayList<String>();
+		List<String> realTokens = new ArrayList<>();
 		for (String token : tokens) {
 			String realToken = getRealToken(token);
 			realTokens.add(realToken);
@@ -324,7 +325,7 @@ public class WritePredefinedProjectProperties extends AbstractMojo {
 	 * @return content
 	 */
 	protected String getContent(String comment, Properties properties, List<String> escapeTokens) {
-		List<String> names = new ArrayList<String>(properties.stringPropertyNames());
+		List<String> names = new ArrayList<>(properties.stringPropertyNames());
 		Collections.sort(names);
 		StringBuilder sb = new StringBuilder();
 		if (!StringUtils.isBlank(comment)) {
@@ -352,7 +353,7 @@ public class WritePredefinedProjectProperties extends AbstractMojo {
 		throws MojoExecutionException {
 		try {
 			String content = getContent(comment, properties, escapeTokens);
-			FileUtils.writeStringToFile(file, content, ENCODING_UTF8);
+			FileUtils.writeStringToFile(file, content, StandardCharsets.UTF_8);
 		} catch (IOException e) {
 			throw new MojoExecutionException("Error creating properties file", e);
 		}
@@ -399,9 +400,9 @@ public class WritePredefinedProjectProperties extends AbstractMojo {
 	 */
 	protected static final List<String> getListFromCSV(String csv) {
 		if (StringUtils.isBlank(csv)) {
-			return new ArrayList<String>();
+			return new ArrayList<>();
 		}
-		List<String> list = new ArrayList<String>();
+		List<String> list = new ArrayList<>();
 		String[] tokens = StringUtils.split(csv, ",");
 		for (String token : tokens) {
 			list.add(token.trim());

dhp-build/dhp-build-properties-maven-plugin/src/test/java/eu/dnetlib/maven/plugin/properties/GenerateOoziePropertiesMojoTest.java

@@ -9,18 +9,18 @@ import org.junit.jupiter.api.BeforeEach;
 import org.junit.jupiter.api.Test;
 
 /** @author mhorst, claudio.atzori */
-public class GenerateOoziePropertiesMojoTest {
+class GenerateOoziePropertiesMojoTest {
 
 	private final GenerateOoziePropertiesMojo mojo = new GenerateOoziePropertiesMojo();
 
 	@BeforeEach
-	public void clearSystemProperties() {
+	void clearSystemProperties() {
 		System.clearProperty(PROPERTY_NAME_SANDBOX_NAME);
 		System.clearProperty(PROPERTY_NAME_WF_SOURCE_DIR);
 	}
 
 	@Test
-	public void testExecuteEmpty() throws Exception {
+	void testExecuteEmpty() throws Exception {
 		// execute
 		mojo.execute();
 
@@ -29,7 +29,7 @@ public class GenerateOoziePropertiesMojoTest {
 	}
 
 	@Test
-	public void testExecuteSandboxNameAlreadySet() throws Exception {
+	void testExecuteSandboxNameAlreadySet() throws Exception {
 		// given
 		String workflowSourceDir = "eu/dnetlib/dhp/wf/transformers";
 		String sandboxName = "originalSandboxName";
@@ -44,7 +44,7 @@ public class GenerateOoziePropertiesMojoTest {
 	}
 
 	@Test
-	public void testExecuteEmptyWorkflowSourceDir() throws Exception {
+	void testExecuteEmptyWorkflowSourceDir() throws Exception {
 		// given
 		String workflowSourceDir = "";
 		System.setProperty(PROPERTY_NAME_WF_SOURCE_DIR, workflowSourceDir);
@@ -57,7 +57,7 @@ public class GenerateOoziePropertiesMojoTest {
 	}
 
 	@Test
-	public void testExecuteNullSandboxNameGenerated() throws Exception {
+	void testExecuteNullSandboxNameGenerated() throws Exception {
 		// given
 		String workflowSourceDir = "eu/dnetlib/dhp/";
 		System.setProperty(PROPERTY_NAME_WF_SOURCE_DIR, workflowSourceDir);
@@ -70,7 +70,7 @@ public class GenerateOoziePropertiesMojoTest {
 	}
 
 	@Test
-	public void testExecute() throws Exception {
+	void testExecute() throws Exception {
 		// given
 		String workflowSourceDir = "eu/dnetlib/dhp/wf/transformers";
 		System.setProperty(PROPERTY_NAME_WF_SOURCE_DIR, workflowSourceDir);
@@ -83,7 +83,7 @@ public class GenerateOoziePropertiesMojoTest {
 	}
 
 	@Test
-	public void testExecuteWithoutRoot() throws Exception {
+	void testExecuteWithoutRoot() throws Exception {
 		// given
 		String workflowSourceDir = "wf/transformers";
 		System.setProperty(PROPERTY_NAME_WF_SOURCE_DIR, workflowSourceDir);

dhp-build/dhp-build-properties-maven-plugin/src/test/java/eu/dnetlib/maven/plugin/properties/WritePredefinedProjectPropertiesTest.java

@@ -20,7 +20,7 @@ import org.mockito.junit.jupiter.MockitoExtension;
 
 /** @author mhorst, claudio.atzori */
 @ExtendWith(MockitoExtension.class)
-public class WritePredefinedProjectPropertiesTest {
+class WritePredefinedProjectPropertiesTest {
 
 	@Mock
 	private MavenProject mavenProject;
@@ -39,7 +39,7 @@ public class WritePredefinedProjectPropertiesTest {
 	// ----------------------------------- TESTS ---------------------------------------------
 
 	@Test
-	public void testExecuteEmpty() throws Exception {
+	void testExecuteEmpty() throws Exception {
 		// execute
 		mojo.execute();
 
@@ -50,7 +50,7 @@ public class WritePredefinedProjectPropertiesTest {
 	}
 
 	@Test
-	public void testExecuteWithProjectProperties() throws Exception {
+	void testExecuteWithProjectProperties() throws Exception {
 		// given
 		String key = "projectPropertyKey";
 		String value = "projectPropertyValue";
@@ -70,7 +70,7 @@ public class WritePredefinedProjectPropertiesTest {
 	}
 
 	@Test()
-	public void testExecuteWithProjectPropertiesAndInvalidOutputFile(@TempDir File testFolder) {
+	void testExecuteWithProjectPropertiesAndInvalidOutputFile(@TempDir File testFolder) {
 		// given
 		String key = "projectPropertyKey";
 		String value = "projectPropertyValue";
@@ -84,7 +84,7 @@ public class WritePredefinedProjectPropertiesTest {
 	}
 
 	@Test
-	public void testExecuteWithProjectPropertiesExclusion(@TempDir File testFolder) throws Exception {
+	void testExecuteWithProjectPropertiesExclusion(@TempDir File testFolder) throws Exception {
 		// given
 		String key = "projectPropertyKey";
 		String value = "projectPropertyValue";
@@ -108,7 +108,7 @@ public class WritePredefinedProjectPropertiesTest {
 	}
 
 	@Test
-	public void testExecuteWithProjectPropertiesInclusion(@TempDir File testFolder) throws Exception {
+	void testExecuteWithProjectPropertiesInclusion(@TempDir File testFolder) throws Exception {
 		// given
 		String key = "projectPropertyKey";
 		String value = "projectPropertyValue";
@@ -132,7 +132,7 @@ public class WritePredefinedProjectPropertiesTest {
 	}
 
 	@Test
-	public void testExecuteIncludingPropertyKeysFromFile(@TempDir File testFolder) throws Exception {
+	void testExecuteIncludingPropertyKeysFromFile(@TempDir File testFolder) throws Exception {
 		// given
 		String key = "projectPropertyKey";
 		String value = "projectPropertyValue";
@@ -164,7 +164,7 @@ public class WritePredefinedProjectPropertiesTest {
 	}
 
 	@Test
-	public void testExecuteIncludingPropertyKeysFromClasspathResource(@TempDir File testFolder)
+	void testExecuteIncludingPropertyKeysFromClasspathResource(@TempDir File testFolder)
 		throws Exception {
 		// given
 		String key = "projectPropertyKey";
@@ -194,7 +194,7 @@ public class WritePredefinedProjectPropertiesTest {
 	}
 
 	@Test
-	public void testExecuteIncludingPropertyKeysFromBlankLocation() {
+	void testExecuteIncludingPropertyKeysFromBlankLocation() {
 		// given
 		String key = "projectPropertyKey";
 		String value = "projectPropertyValue";
@@ -214,7 +214,7 @@ public class WritePredefinedProjectPropertiesTest {
 	}
 
 	@Test
-	public void testExecuteIncludingPropertyKeysFromXmlFile(@TempDir File testFolder)
+	void testExecuteIncludingPropertyKeysFromXmlFile(@TempDir File testFolder)
 		throws Exception {
 		// given
 		String key = "projectPropertyKey";
@@ -247,7 +247,7 @@ public class WritePredefinedProjectPropertiesTest {
 	}
 
 	@Test
-	public void testExecuteIncludingPropertyKeysFromInvalidXmlFile(@TempDir File testFolder)
+	void testExecuteIncludingPropertyKeysFromInvalidXmlFile(@TempDir File testFolder)
 		throws Exception {
 		// given
 		String key = "projectPropertyKey";
@@ -273,7 +273,7 @@ public class WritePredefinedProjectPropertiesTest {
 	}
 
 	@Test
-	public void testExecuteWithQuietModeOn(@TempDir File testFolder) throws Exception {
+	void testExecuteWithQuietModeOn(@TempDir File testFolder) throws Exception {
 		// given
 		mojo.setQuiet(true);
 		mojo.setIncludePropertyKeysFromFiles(new String[] {
@@ -290,7 +290,7 @@ public class WritePredefinedProjectPropertiesTest {
 	}
 
 	@Test
-	public void testExecuteIncludingPropertyKeysFromInvalidFile() {
+	void testExecuteIncludingPropertyKeysFromInvalidFile() {
 		// given
 		mojo.setIncludePropertyKeysFromFiles(new String[] {
 			"invalid location"
@@ -301,7 +301,7 @@ public class WritePredefinedProjectPropertiesTest {
 	}
 
 	@Test
-	public void testExecuteWithEnvironmentProperties(@TempDir File testFolder) throws Exception {
+	void testExecuteWithEnvironmentProperties(@TempDir File testFolder) throws Exception {
 		// given
 		mojo.setIncludeEnvironmentVariables(true);
 
@@ -318,7 +318,7 @@ public class WritePredefinedProjectPropertiesTest {
 	}
 
 	@Test
-	public void testExecuteWithSystemProperties(@TempDir File testFolder) throws Exception {
+	void testExecuteWithSystemProperties(@TempDir File testFolder) throws Exception {
 		// given
 		String key = "systemPropertyKey";
 		String value = "systemPropertyValue";
@@ -337,7 +337,7 @@ public class WritePredefinedProjectPropertiesTest {
 	}
 
 	@Test
-	public void testExecuteWithSystemPropertiesAndEscapeChars(@TempDir File testFolder)
+	void testExecuteWithSystemPropertiesAndEscapeChars(@TempDir File testFolder)
 		throws Exception {
 		// given
 		String key = "systemPropertyKey ";

dhp-build/dhp-code-style/pom.xml

@@ -22,9 +22,20 @@
             <id>dnet45-releases</id>
             <url>https://maven.d4science.org/nexus/content/repositories/dnet45-releases</url>
         </repository>
+        <site>
+            <id>DHPSite</id>
+            <url>${dhp.site.stage.path}/dhp-build/dhp-code-style</url>
+        </site>
     </distributionManagement>
 
     <build>
+        <extensions>
+            <extension>
+                <groupId>org.apache.maven.wagon</groupId>
+                <artifactId>wagon-ssh</artifactId>
+                <version>2.10</version>
+            </extension>
+        </extensions>
         <pluginManagement>
             <plugins>
                 <plugin>
@@ -35,7 +46,7 @@
                 <plugin>
                     <groupId>org.apache.maven.plugins</groupId>
                     <artifactId>maven-site-plugin</artifactId>
-                    <version>3.7.1</version>
+                    <version>3.9.1</version>
                 </plugin>
             </plugins>
         </pluginManagement>
@@ -43,6 +54,7 @@
 
     <properties>
         <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
+        <dhp.site.stage.path>sftp://dnet-hadoop@static-web.d4science.org/dnet-hadoop</dhp.site.stage.path>
     </properties>
 
 </project>

dhp-build/dhp-code-style/src/main/resources/scalafmt/scalafmt.conf

@@ -0,0 +1,21 @@
+style = defaultWithAlign
+
+align.openParenCallSite = false
+align.openParenDefnSite = false
+align.tokens = [{code = "->"}, {code = "<-"}, {code = "=>", owner = "Case"}]
+continuationIndent.callSite = 2
+continuationIndent.defnSite = 2
+danglingParentheses = true
+indentOperator = spray
+maxColumn = 120
+newlines.alwaysBeforeTopLevelStatements = true
+project.excludeFilters = [".*\\.sbt"]
+rewrite.rules = [AvoidInfix]
+rewrite.rules = [ExpandImportSelectors]
+rewrite.rules = [RedundantBraces]
+rewrite.rules = [RedundantParens]
+rewrite.rules = [SortImports]
+rewrite.rules = [SortModifiers]
+rewrite.rules = [PreferCurlyFors]
+spaces.inImportCurlyBraces = false
+unindentTopLevelOperators = true

dhp-build/dhp-code-style/src/site/site.xml

@@ -0,0 +1,21 @@
+<?xml version="1.0" encoding="ISO-8859-1"?>
+<project xmlns="http://maven.apache.org/DECORATION/1.8.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+         xsi:schemaLocation="http://maven.apache.org/DECORATION/1.8.0 https://maven.apache.org/xsd/decoration-1.8.0.xsd"
+         name="DHP-Aggregation">
+    <skin>
+        <groupId>org.apache.maven.skins</groupId>
+        <artifactId>maven-fluido-skin</artifactId>
+        <version>1.8</version>
+    </skin>
+    <poweredBy>
+        <logo name="OpenAIRE Research Graph" href="https://graph.openaire.eu/"
+              img="https://graph.openaire.eu/assets/common-assets/logo-large-graph.png"/>
+    </poweredBy>
+    <body>
+        <links>
+            <item name="Code" href="https://code-repo.d4science.org/" />
+        </links>
+        <menu ref="modules" />
+        <menu ref="reports"/>
+    </body>
+</project>

dhp-build/pom.xml

@@ -10,6 +10,9 @@
 	<packaging>pom</packaging>
 
 	<description>This module is a container for the build tools used in dnet-hadoop</description>
+	<properties>
+		<maven.javadoc.skip>true</maven.javadoc.skip>
+	</properties>
 
 	<modules>
 		<module>dhp-code-style</module>
@@ -17,4 +20,12 @@
 		<module>dhp-build-properties-maven-plugin</module>
 	</modules>
 
+
+ <distributionManagement>
+	 <site>
+		 <id>DHPSite</id>
+		 <url>${dhp.site.stage.path}/dhp-build/</url>
+	 </site>
+ </distributionManagement>
+
 </project>

dhp-build/src/site/site.xml

@@ -0,0 +1,22 @@
+<?xml version="1.0" encoding="ISO-8859-1"?>
+<project xmlns="http://maven.apache.org/DECORATION/1.8.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+         xsi:schemaLocation="http://maven.apache.org/DECORATION/1.8.0 https://maven.apache.org/xsd/decoration-1.8.0.xsd"
+         name="DHP-Aggregation">
+    <skin>
+        <groupId>org.apache.maven.skins</groupId>
+        <artifactId>maven-fluido-skin</artifactId>
+        <version>1.8</version>
+    </skin>
+    <poweredBy>
+        <logo name="OpenAIRE Research Graph" href="https://graph.openaire.eu/"
+              img="https://graph.openaire.eu/assets/common-assets/logo-large-graph.png"/>
+    </poweredBy>
+    <body>
+        <links>
+            <item name="Code" href="https://code-repo.d4science.org/" />
+        </links>
+
+        <menu ref="modules" />
+        <menu ref="reports"/>
+    </body>
+</project>

dhp-common/pom.xml

@@ -13,7 +13,51 @@
 	<artifactId>dhp-common</artifactId>
 	<packaging>jar</packaging>
 
+	<distributionManagement>
+		<site>
+			<id>DHPSite</id>
+			<url>${dhp.site.stage.path}/dhp-common</url>
+		</site>
+	</distributionManagement>
+
 	<description>This module contains common utilities meant to be used across the dnet-hadoop submodules</description>
+	<build>
+		<plugins>
+			<plugin>
+				<groupId>net.alchim31.maven</groupId>
+				<artifactId>scala-maven-plugin</artifactId>
+				<version>${net.alchim31.maven.version}</version>
+				<executions>
+					<execution>
+						<id>scala-compile-first</id>
+						<phase>initialize</phase>
+						<goals>
+							<goal>add-source</goal>
+							<goal>compile</goal>
+						</goals>
+					</execution>
+					<execution>
+						<id>scala-test-compile</id>
+						<phase>process-test-resources</phase>
+						<goals>
+							<goal>testCompile</goal>
+						</goals>
+					</execution>
+					<execution>
+						<id>scala-doc</id>
+						<phase>process-resources</phase> <!-- or wherever -->
+						<goals>
+							<goal>doc</goal>
+						</goals>
+					</execution>
+				</executions>
+				<configuration>
+					<scalaVersion>${scala.version}</scalaVersion>
+				</configuration>
+			</plugin>
+		</plugins>
+
+	</build>
 
 	<dependencies>
 
@@ -117,6 +161,11 @@
 			<groupId>eu.dnetlib.dhp</groupId>
 			<artifactId>dhp-schemas</artifactId>
 		</dependency>
+
+		<dependency>
+			<groupId>com.opencsv</groupId>
+			<artifactId>opencsv</artifactId>
+		</dependency>
 	</dependencies>
 
 </project>

dhp-common/src/main/java/eu/dnetlib/dhp/application/ApplicationUtils.java

@@ -1,14 +0,0 @@
-
-package eu.dnetlib.dhp.application;
-
-import java.io.*;
-import java.util.Map;
-import java.util.Properties;
-
-import org.apache.hadoop.conf.Configuration;
-
-import com.google.common.collect.Maps;
-
-public class ApplicationUtils {
-
-}

dhp-common/src/main/java/eu/dnetlib/dhp/application/ArgumentApplicationParser.java

@@ -56,13 +56,13 @@ public class ArgumentApplicationParser implements Serializable {
 			final StringWriter stringWriter = new StringWriter();
 			IOUtils.copy(gis, stringWriter);
 			return stringWriter.toString();
-		} catch (Throwable e) {
-			log.error("Wrong value to decompress:" + abstractCompressed);
-			throw new RuntimeException(e);
+		} catch (IOException e) {
+			log.error("Wrong value to decompress: {}", abstractCompressed);
+			throw new IllegalArgumentException(e);
 		}
 	}
 
-	public static String compressArgument(final String value) throws Exception {
+	public static String compressArgument(final String value) throws IOException {
 		ByteArrayOutputStream out = new ByteArrayOutputStream();
 		GZIPOutputStream gzip = new GZIPOutputStream(out);
 		gzip.write(value.getBytes());

dhp-common/src/main/java/eu/dnetlib/dhp/application/OptionsParameter.java

@@ -9,9 +9,6 @@ public class OptionsParameter {
 	private boolean paramRequired;
 	private boolean compressed;
 
-	public OptionsParameter() {
-	}
-
 	public String getParamName() {
 		return paramName;
 	}

dhp-common/src/main/java/eu/dnetlib/dhp/collection/ApiDescriptor.java

@@ -34,7 +34,7 @@ public class ApiDescriptor {
 		return params;
 	}
 
-	public void setParams(final HashMap<String, String> params) {
+	public void setParams(final Map<String, String> params) {
 		this.params = params;
 	}
 

dhp-common/src/main/java/eu/dnetlib/dhp/common/Constants.java

@@ -12,6 +12,9 @@ public class Constants {
 
 	public static String COAR_ACCESS_RIGHT_SCHEMA = "http://vocabularies.coar-repositories.org/documentation/access_rights/";
 
+	private Constants() {
+	}
+
 	static {
 		accessRightsCoarMap.put("OPEN", "c_abf2");
 		accessRightsCoarMap.put("RESTRICTED", "c_16ec");
@@ -49,4 +52,10 @@ public class Constants {
 	public static final String CONTENT_INVALIDRECORDS = "InvalidRecords";
 	public static final String CONTENT_TRANSFORMEDRECORDS = "transformedItems";
 
+	// IETF Draft and used by Repositories like ZENODO , not included in APACHE HTTP java packages
+	// see https://ietf-wg-httpapi.github.io/ratelimit-headers/draft-ietf-httpapi-ratelimit-headers.html
+	public static final String HTTPHEADER_IETF_DRAFT_RATELIMIT_LIMIT = "X-RateLimit-Limit";
+	public static final String HTTPHEADER_IETF_DRAFT_RATELIMIT_REMAINING = "X-RateLimit-Remaining";
+	public static final String HTTPHEADER_IETF_DRAFT_RATELIMIT_RESET = "X-RateLimit-Reset";
+
 }

dhp-common/src/main/java/eu/dnetlib/dhp/common/GraphResultMapper.java

@@ -1,412 +0,0 @@
-
-package eu.dnetlib.dhp.common;
-
-import java.io.Serializable;
-import java.util.*;
-import java.util.stream.Collectors;
-
-import eu.dnetlib.dhp.schema.common.ModelConstants;
-import eu.dnetlib.dhp.schema.dump.oaf.*;
-import eu.dnetlib.dhp.schema.dump.oaf.community.CommunityInstance;
-import eu.dnetlib.dhp.schema.dump.oaf.community.CommunityResult;
-import eu.dnetlib.dhp.schema.oaf.DataInfo;
-import eu.dnetlib.dhp.schema.oaf.Field;
-import eu.dnetlib.dhp.schema.oaf.Journal;
-import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
-
-public class GraphResultMapper implements Serializable {
-
-	public static <E extends eu.dnetlib.dhp.schema.oaf.OafEntity> Result map(
-		E in) {
-
-		CommunityResult out = new CommunityResult();
-
-		eu.dnetlib.dhp.schema.oaf.Result input = (eu.dnetlib.dhp.schema.oaf.Result) in;
-		Optional<eu.dnetlib.dhp.schema.oaf.Qualifier> ort = Optional.ofNullable(input.getResulttype());
-		if (ort.isPresent()) {
-			switch (ort.get().getClassid()) {
-				case "publication":
-					Optional<Journal> journal = Optional
-						.ofNullable(((eu.dnetlib.dhp.schema.oaf.Publication) input).getJournal());
-					if (journal.isPresent()) {
-						Journal j = journal.get();
-						Container c = new Container();
-						c.setConferencedate(j.getConferencedate());
-						c.setConferenceplace(j.getConferenceplace());
-						c.setEdition(j.getEdition());
-						c.setEp(j.getEp());
-						c.setIss(j.getIss());
-						c.setIssnLinking(j.getIssnLinking());
-						c.setIssnOnline(j.getIssnOnline());
-						c.setIssnPrinted(j.getIssnPrinted());
-						c.setName(j.getName());
-						c.setSp(j.getSp());
-						c.setVol(j.getVol());
-						out.setContainer(c);
-						out.setType(ModelConstants.PUBLICATION_DEFAULT_RESULTTYPE.getClassname());
-					}
-					break;
-				case "dataset":
-					eu.dnetlib.dhp.schema.oaf.Dataset id = (eu.dnetlib.dhp.schema.oaf.Dataset) input;
-					Optional.ofNullable(id.getSize()).ifPresent(v -> out.setSize(v.getValue()));
-					Optional.ofNullable(id.getVersion()).ifPresent(v -> out.setVersion(v.getValue()));
-
-					out
-						.setGeolocation(
-							Optional
-								.ofNullable(id.getGeolocation())
-								.map(
-									igl -> igl
-										.stream()
-										.filter(Objects::nonNull)
-										.map(gli -> {
-											GeoLocation gl = new GeoLocation();
-											gl.setBox(gli.getBox());
-											gl.setPlace(gli.getPlace());
-											gl.setPoint(gli.getPoint());
-											return gl;
-										})
-										.collect(Collectors.toList()))
-								.orElse(null));
-
-					out.setType(ModelConstants.DATASET_DEFAULT_RESULTTYPE.getClassname());
-					break;
-				case "software":
-
-					eu.dnetlib.dhp.schema.oaf.Software is = (eu.dnetlib.dhp.schema.oaf.Software) input;
-					Optional
-						.ofNullable(is.getCodeRepositoryUrl())
-						.ifPresent(value -> out.setCodeRepositoryUrl(value.getValue()));
-					Optional
-						.ofNullable(is.getDocumentationUrl())
-						.ifPresent(
-							value -> out
-								.setDocumentationUrl(
-									value
-										.stream()
-										.map(v -> v.getValue())
-										.collect(Collectors.toList())));
-
-					Optional
-						.ofNullable(is.getProgrammingLanguage())
-						.ifPresent(value -> out.setProgrammingLanguage(value.getClassid()));
-
-					out.setType(ModelConstants.SOFTWARE_DEFAULT_RESULTTYPE.getClassname());
-					break;
-				case "other":
-
-					eu.dnetlib.dhp.schema.oaf.OtherResearchProduct ir = (eu.dnetlib.dhp.schema.oaf.OtherResearchProduct) input;
-					out
-						.setContactgroup(
-							Optional
-								.ofNullable(ir.getContactgroup())
-								.map(value -> value.stream().map(cg -> cg.getValue()).collect(Collectors.toList()))
-								.orElse(null));
-
-					out
-						.setContactperson(
-							Optional
-								.ofNullable(ir.getContactperson())
-								.map(value -> value.stream().map(cp -> cp.getValue()).collect(Collectors.toList()))
-								.orElse(null));
-					out
-						.setTool(
-							Optional
-								.ofNullable(ir.getTool())
-								.map(value -> value.stream().map(t -> t.getValue()).collect(Collectors.toList()))
-								.orElse(null));
-
-					out.setType(ModelConstants.ORP_DEFAULT_RESULTTYPE.getClassname());
-
-					break;
-			}
-
-			Optional
-				.ofNullable(input.getAuthor())
-				.ifPresent(ats -> out.setAuthor(ats.stream().map(at -> getAuthor(at)).collect(Collectors.toList())));
-
-			// I do not map Access Right UNKNOWN or OTHER
-
-			Optional<eu.dnetlib.dhp.schema.oaf.Qualifier> oar = Optional.ofNullable(input.getBestaccessright());
-			if (oar.isPresent()) {
-				if (Constants.accessRightsCoarMap.containsKey(oar.get().getClassid())) {
-					String code = Constants.accessRightsCoarMap.get(oar.get().getClassid());
-					out
-						.setBestaccessright(
-							AccessRight
-								.newInstance(
-									code,
-									Constants.coarCodeLabelMap.get(code),
-									Constants.COAR_ACCESS_RIGHT_SCHEMA));
-				}
-			}
-
-			final List<String> contributorList = new ArrayList<>();
-			Optional
-				.ofNullable(input.getContributor())
-				.ifPresent(value -> value.stream().forEach(c -> contributorList.add(c.getValue())));
-			out.setContributor(contributorList);
-
-			Optional
-				.ofNullable(input.getCountry())
-				.ifPresent(
-					value -> out
-						.setCountry(
-							value
-								.stream()
-								.map(
-									c -> {
-										if (c.getClassid().equals((ModelConstants.UNKNOWN))) {
-											return null;
-										}
-										Country country = new Country();
-										country.setCode(c.getClassid());
-										country.setLabel(c.getClassname());
-										Optional
-											.ofNullable(c.getDataInfo())
-											.ifPresent(
-												provenance -> country
-													.setProvenance(
-														Provenance
-															.newInstance(
-																provenance
-																	.getProvenanceaction()
-																	.getClassname(),
-																c.getDataInfo().getTrust())));
-										return country;
-									})
-								.filter(Objects::nonNull)
-								.collect(Collectors.toList())));
-
-			final List<String> coverageList = new ArrayList<>();
-			Optional
-				.ofNullable(input.getCoverage())
-				.ifPresent(value -> value.stream().forEach(c -> coverageList.add(c.getValue())));
-			out.setCoverage(coverageList);
-
-			out.setDateofcollection(input.getDateofcollection());
-
-			final List<String> descriptionList = new ArrayList<>();
-			Optional
-				.ofNullable(input.getDescription())
-				.ifPresent(value -> value.forEach(d -> descriptionList.add(d.getValue())));
-			out.setDescription(descriptionList);
-			Optional<Field<String>> oStr = Optional.ofNullable(input.getEmbargoenddate());
-			if (oStr.isPresent()) {
-				out.setEmbargoenddate(oStr.get().getValue());
-			}
-
-			final List<String> formatList = new ArrayList<>();
-			Optional
-				.ofNullable(input.getFormat())
-				.ifPresent(value -> value.stream().forEach(f -> formatList.add(f.getValue())));
-			out.setFormat(formatList);
-			out.setId(input.getId());
-			out.setOriginalId(input.getOriginalId());
-
-			Optional<List<eu.dnetlib.dhp.schema.oaf.Instance>> oInst = Optional
-				.ofNullable(input.getInstance());
-
-			if (oInst.isPresent()) {
-				out
-					.setInstance(
-						oInst.get().stream().map(i -> getInstance(i)).collect(Collectors.toList()));
-
-			}
-
-			Optional<eu.dnetlib.dhp.schema.oaf.Qualifier> oL = Optional.ofNullable(input.getLanguage());
-			if (oL.isPresent()) {
-				eu.dnetlib.dhp.schema.oaf.Qualifier language = oL.get();
-				out.setLanguage(Qualifier.newInstance(language.getClassid(), language.getClassname()));
-			}
-			Optional<Long> oLong = Optional.ofNullable(input.getLastupdatetimestamp());
-			if (oLong.isPresent()) {
-				out.setLastupdatetimestamp(oLong.get());
-			}
-			Optional<List<StructuredProperty>> otitle = Optional.ofNullable(input.getTitle());
-			if (otitle.isPresent()) {
-				List<StructuredProperty> iTitle = otitle
-					.get()
-					.stream()
-					.filter(t -> t.getQualifier().getClassid().equalsIgnoreCase("main title"))
-					.collect(Collectors.toList());
-				if (iTitle.size() > 0) {
-					out.setMaintitle(iTitle.get(0).getValue());
-				}
-
-				iTitle = otitle
-					.get()
-					.stream()
-					.filter(t -> t.getQualifier().getClassid().equalsIgnoreCase("subtitle"))
-					.collect(Collectors.toList());
-				if (iTitle.size() > 0) {
-					out.setSubtitle(iTitle.get(0).getValue());
-				}
-
-			}
-
-			List<ControlledField> pids = new ArrayList<>();
-			Optional
-				.ofNullable(input.getPid())
-				.ifPresent(
-					value -> value
-						.stream()
-						.forEach(
-							p -> pids
-								.add(
-									ControlledField
-										.newInstance(p.getQualifier().getClassid(), p.getValue()))));
-			out.setPid(pids);
-			oStr = Optional.ofNullable(input.getDateofacceptance());
-			if (oStr.isPresent()) {
-				out.setPublicationdate(oStr.get().getValue());
-			}
-			oStr = Optional.ofNullable(input.getPublisher());
-			if (oStr.isPresent()) {
-				out.setPublisher(oStr.get().getValue());
-			}
-
-			List<String> sourceList = new ArrayList<>();
-			Optional
-				.ofNullable(input.getSource())
-				.ifPresent(value -> 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
-				.ofNullable(input.getSubject())
-				.ifPresent(
-					value -> value
-						.forEach(s -> subjectList.add(getSubject(s))));
-
-			out.setSubjects(subjectList);
-
-			out.setType(input.getResulttype().getClassid());
-		}
-
-		out
-			.setCollectedfrom(
-				input
-					.getCollectedfrom()
-					.stream()
-					.map(cf -> KeyValue.newInstance(cf.getKey(), cf.getValue()))
-					.collect(Collectors.toList()));
-
-		return out;
-
-	}
-
-	private static CommunityInstance getInstance(eu.dnetlib.dhp.schema.oaf.Instance i) {
-		CommunityInstance instance = new CommunityInstance();
-
-		setCommonValue(i, instance);
-
-		instance
-			.setCollectedfrom(
-				KeyValue
-					.newInstance(i.getCollectedfrom().getKey(), i.getCollectedfrom().getValue()));
-
-		instance
-			.setHostedby(
-				KeyValue.newInstance(i.getHostedby().getKey(), i.getHostedby().getValue()));
-
-		return instance;
-
-	}
-
-	private static <I extends Instance> void setCommonValue(eu.dnetlib.dhp.schema.oaf.Instance i, I instance) {
-		Optional<eu.dnetlib.dhp.schema.oaf.Qualifier> opAr = Optional
-			.ofNullable(i.getAccessright());
-		if (opAr.isPresent()) {
-			if (Constants.accessRightsCoarMap.containsKey(opAr.get().getClassid())) {
-				String code = Constants.accessRightsCoarMap.get(opAr.get().getClassid());
-				instance
-					.setAccessright(
-						AccessRight
-							.newInstance(
-								code,
-								Constants.coarCodeLabelMap.get(code),
-								Constants.COAR_ACCESS_RIGHT_SCHEMA));
-			}
-		}
-
-		Optional
-			.ofNullable(i.getLicense())
-			.ifPresent(value -> instance.setLicense(value.getValue()));
-		Optional
-			.ofNullable(i.getDateofacceptance())
-			.ifPresent(value -> instance.setPublicationdate(value.getValue()));
-		Optional
-			.ofNullable(i.getRefereed())
-			.ifPresent(value -> instance.setRefereed(value.getClassname()));
-		Optional
-			.ofNullable(i.getInstancetype())
-			.ifPresent(value -> instance.setType(value.getClassname()));
-		Optional.ofNullable(i.getUrl()).ifPresent(value -> instance.setUrl(value));
-
-	}
-
-	private static Subject getSubject(StructuredProperty s) {
-		Subject subject = new Subject();
-		subject.setSubject(ControlledField.newInstance(s.getQualifier().getClassid(), s.getValue()));
-		Optional<DataInfo> di = Optional.ofNullable(s.getDataInfo());
-		if (di.isPresent()) {
-			Provenance p = new Provenance();
-			p.setProvenance(di.get().getProvenanceaction().getClassname());
-			p.setTrust(di.get().getTrust());
-			subject.setProvenance(p);
-		}
-
-		return subject;
-	}
-
-	private static Author getAuthor(eu.dnetlib.dhp.schema.oaf.Author oa) {
-		Author a = new Author();
-		a.setFullname(oa.getFullname());
-		a.setName(oa.getName());
-		a.setSurname(oa.getSurname());
-		a.setRank(oa.getRank());
-
-		Optional<List<StructuredProperty>> oPids = Optional
-			.ofNullable(oa.getPid());
-		if (oPids.isPresent()) {
-			Pid pid = getOrcid(oPids.get());
-			if (pid != null) {
-				a.setPid(pid);
-			}
-		}
-
-		return a;
-	}
-
-	private static Pid getOrcid(List<StructuredProperty> p) {
-		for (StructuredProperty pid : p) {
-			if (pid.getQualifier().getClassid().equals(ModelConstants.ORCID)) {
-				Optional<DataInfo> di = Optional.ofNullable(pid.getDataInfo());
-				if (di.isPresent()) {
-					return Pid
-						.newInstance(
-							ControlledField
-								.newInstance(
-									pid.getQualifier().getClassid(),
-									pid.getValue()),
-							Provenance
-								.newInstance(
-									di.get().getProvenanceaction().getClassname(),
-									di.get().getTrust()));
-				} else {
-					return Pid
-						.newInstance(
-							ControlledField
-								.newInstance(
-									pid.getQualifier().getClassid(),
-									pid.getValue())
-
-						);
-				}
-
-			}
-		}
-		return null;
-	}
-
-}

dhp-common/src/main/java/eu/dnetlib/dhp/common/HdfsSupport.java

@@ -28,7 +28,7 @@ public class HdfsSupport {
 	 * @param configuration Configuration of hadoop env
 	 */
 	public static boolean exists(String path, Configuration configuration) {
-		logger.info("Removing path: {}", path);
+		logger.info("Checking existence for path: {}", path);
 		return rethrowAsRuntimeException(
 			() -> {
 				Path f = new Path(path);

dhp-common/src/main/java/eu/dnetlib/dhp/common/MakeTarArchive.java

@@ -14,38 +14,33 @@ public class MakeTarArchive implements Serializable {
 
 	private static TarArchiveOutputStream getTar(FileSystem fileSystem, String outputPath) throws IOException {
 		Path hdfsWritePath = new Path(outputPath);
-		FSDataOutputStream fsDataOutputStream = null;
 		if (fileSystem.exists(hdfsWritePath)) {
 			fileSystem.delete(hdfsWritePath, true);
 
 		}
-		fsDataOutputStream = fileSystem.create(hdfsWritePath);
-
-		return new TarArchiveOutputStream(fsDataOutputStream.getWrappedStream());
+		return new TarArchiveOutputStream(fileSystem.create(hdfsWritePath).getWrappedStream());
 	}
 
 	private static void write(FileSystem fileSystem, String inputPath, String outputPath, String dir_name)
 		throws IOException {
 
 		Path hdfsWritePath = new Path(outputPath);
-		FSDataOutputStream fsDataOutputStream = null;
 		if (fileSystem.exists(hdfsWritePath)) {
 			fileSystem.delete(hdfsWritePath, true);
 
 		}
-		fsDataOutputStream = fileSystem.create(hdfsWritePath);
+		try (TarArchiveOutputStream ar = new TarArchiveOutputStream(
+			fileSystem.create(hdfsWritePath).getWrappedStream())) {
 
-		TarArchiveOutputStream ar = new TarArchiveOutputStream(fsDataOutputStream.getWrappedStream());
+			RemoteIterator<LocatedFileStatus> iterator = fileSystem
+				.listFiles(
+					new Path(inputPath), true);
 
-		RemoteIterator<LocatedFileStatus> fileStatusListIterator = fileSystem
-			.listFiles(
-				new Path(inputPath), true);
+			while (iterator.hasNext()) {
+				writeCurrentFile(fileSystem, dir_name, iterator, ar, 0);
+			}
 
-		while (fileStatusListIterator.hasNext()) {
-			writeCurrentFile(fileSystem, dir_name, fileStatusListIterator, ar, 0);
 		}
-
-		ar.close();
 	}
 
 	public static void tarMaxSize(FileSystem fileSystem, String inputPath, String outputPath, String dir_name,

dhp-common/src/main/java/eu/dnetlib/dhp/common/MdstoreClient.java

@@ -10,8 +10,6 @@ import java.util.Optional;
 import java.util.stream.StreamSupport;
 
 import org.apache.commons.lang3.StringUtils;
-import org.apache.commons.logging.Log;
-import org.apache.commons.logging.LogFactory;
 import org.bson.Document;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
@@ -21,6 +19,7 @@ import com.mongodb.BasicDBObject;
 import com.mongodb.MongoClient;
 import com.mongodb.MongoClientURI;
 import com.mongodb.QueryBuilder;
+import com.mongodb.client.FindIterable;
 import com.mongodb.client.MongoCollection;
 import com.mongodb.client.MongoDatabase;
 
@@ -46,7 +45,7 @@ public class MdstoreClient implements Closeable {
 
 		final String currentId = Optional
 			.ofNullable(getColl(db, COLL_METADATA_MANAGER, true).find(query))
-			.map(r -> r.first())
+			.map(FindIterable::first)
 			.map(d -> d.getString("currentId"))
 			.orElseThrow(() -> new IllegalArgumentException("cannot find current mdstore id for: " + mdId));
 
@@ -84,7 +83,7 @@ public class MdstoreClient implements Closeable {
 		if (!Iterables.contains(client.listDatabaseNames(), dbName)) {
 			final String err = String.format("Database '%s' not found in %s", dbName, client.getAddress());
 			log.warn(err);
-			throw new RuntimeException(err);
+			throw new IllegalArgumentException(err);
 		}
 		return client.getDatabase(dbName);
 	}
@@ -97,7 +96,7 @@ public class MdstoreClient implements Closeable {
 					String.format("Missing collection '%s' in database '%s'", collName, db.getName()));
 			log.warn(err);
 			if (abortIfMissing) {
-				throw new RuntimeException(err);
+				throw new IllegalArgumentException(err);
 			} else {
 				return null;
 			}

dhp-common/src/main/java/eu/dnetlib/dhp/common/PacePerson.java

@@ -24,7 +24,6 @@ import com.google.common.hash.Hashing;
  */
 public class PacePerson {
 
-	private static final String UTF8 = "UTF-8";
 	private List<String> name = Lists.newArrayList();
 	private List<String> surname = Lists.newArrayList();
 	private List<String> fullname = Lists.newArrayList();

dhp-common/src/main/java/eu/dnetlib/dhp/common/aggregation/AggregatorReport.java

@@ -1,5 +1,5 @@
 
-package eu.dnetlib.dhp.aggregation.common;
+package eu.dnetlib.dhp.common.aggregation;
 
 import java.io.Closeable;
 import java.io.IOException;
@@ -11,8 +11,6 @@ import java.util.Objects;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 
-import com.google.gson.Gson;
-
 import eu.dnetlib.dhp.message.MessageSender;
 import eu.dnetlib.dhp.utils.DHPUtils;
 
@@ -20,12 +18,12 @@ public class AggregatorReport extends LinkedHashMap<String, String> implements C
 
 	private static final Logger log = LoggerFactory.getLogger(AggregatorReport.class);
 
-	private MessageSender messageSender;
+	private transient MessageSender messageSender;
 
 	public AggregatorReport() {
 	}
 
-	public AggregatorReport(MessageSender messageSender) throws IOException {
+	public AggregatorReport(MessageSender messageSender) {
 		this.messageSender = messageSender;
 	}
 

dhp-common/src/main/java/eu/dnetlib/dhp/common/api/ZenodoAPIClient.java

@@ -5,6 +5,9 @@ import java.io.*;
 import java.io.IOException;
 import java.util.concurrent.TimeUnit;
 
+import org.apache.http.HttpHeaders;
+import org.apache.http.entity.ContentType;
+
 import com.google.gson.Gson;
 
 import eu.dnetlib.dhp.common.api.zenodo.ZenodoModel;
@@ -43,7 +46,7 @@ public class ZenodoAPIClient implements Serializable {
 		this.deposition_id = deposition_id;
 	}
 
-	public ZenodoAPIClient(String urlString, String access_token) throws IOException {
+	public ZenodoAPIClient(String urlString, String access_token) {
 
 		this.urlString = urlString;
 		this.access_token = access_token;
@@ -63,8 +66,8 @@ public class ZenodoAPIClient implements Serializable {
 
 		Request request = new Request.Builder()
 			.url(urlString)
-			.addHeader("Content-Type", "application/json") // add request headers
-			.addHeader("Authorization", "Bearer " + access_token)
+			.addHeader(HttpHeaders.CONTENT_TYPE, ContentType.APPLICATION_JSON.toString()) // add request headers
+			.addHeader(HttpHeaders.AUTHORIZATION, "Bearer " + access_token)
 			.post(body)
 			.build();
 
@@ -103,8 +106,8 @@ public class ZenodoAPIClient implements Serializable {
 
 		Request request = new Request.Builder()
 			.url(bucket + "/" + file_name)
-			.addHeader("Content-Type", "application/zip") // add request headers
-			.addHeader("Authorization", "Bearer " + access_token)
+			.addHeader(HttpHeaders.CONTENT_TYPE, "application/zip") // add request headers
+			.addHeader(HttpHeaders.AUTHORIZATION, "Bearer " + access_token)
 			.put(InputStreamRequestBody.create(MEDIA_TYPE_ZIP, is, len))
 			.build();
 
@@ -130,8 +133,8 @@ public class ZenodoAPIClient implements Serializable {
 
 		Request request = new Request.Builder()
 			.url(urlString + "/" + deposition_id)
-			.addHeader("Content-Type", "application/json") // add request headers
-			.addHeader("Authorization", "Bearer " + access_token)
+			.addHeader(HttpHeaders.CONTENT_TYPE, ContentType.APPLICATION_JSON.toString()) // add request headers
+			.addHeader(HttpHeaders.AUTHORIZATION, "Bearer " + access_token)
 			.put(body)
 			.build();
 
@@ -197,7 +200,7 @@ public class ZenodoAPIClient implements Serializable {
 
 		Request request = new Request.Builder()
 			.url(urlString + "/" + deposition_id + "/actions/newversion")
-			.addHeader("Authorization", "Bearer " + access_token)
+			.addHeader(HttpHeaders.AUTHORIZATION, "Bearer " + access_token)
 			.post(body)
 			.build();
 
@@ -270,8 +273,8 @@ public class ZenodoAPIClient implements Serializable {
 
 		Request request = new Request.Builder()
 			.url(urlString)
-			.addHeader("Content-Type", "application/json") // add request headers
-			.addHeader("Authorization", "Bearer " + access_token)
+			.addHeader(HttpHeaders.CONTENT_TYPE, ContentType.APPLICATION_JSON.toString()) // add request headers
+			.addHeader(HttpHeaders.AUTHORIZATION, "Bearer " + access_token)
 			.get()
 			.build();
 
@@ -293,8 +296,8 @@ public class ZenodoAPIClient implements Serializable {
 
 		Request request = new Request.Builder()
 			.url(url)
-			.addHeader("Content-Type", "application/json") // add request headers
-			.addHeader("Authorization", "Bearer " + access_token)
+			.addHeader(HttpHeaders.CONTENT_TYPE, ContentType.APPLICATION_JSON.toString()) // add request headers
+			.addHeader(HttpHeaders.AUTHORIZATION, "Bearer " + access_token)
 			.get()
 			.build();
 

dhp-common/src/main/java/eu/dnetlib/dhp/common/api/zenodo/Creator.java

@@ -32,13 +32,13 @@ public class Creator {
 
 	public static Creator newInstance(String name, String affiliation, String orcid) {
 		Creator c = new Creator();
-		if (!(name == null)) {
+		if (name != null) {
 			c.name = name;
 		}
-		if (!(affiliation == null)) {
+		if (affiliation != null) {
 			c.affiliation = affiliation;
 		}
-		if (!(orcid == null)) {
+		if (orcid != null) {
 			c.orcid = orcid;
 		}
 

dhp-common/src/main/java/eu/dnetlib/dhp/common/api/zenodo/File.java

@@ -3,17 +3,12 @@ package eu.dnetlib.dhp.common.api.zenodo;
 
 import java.io.Serializable;
 
-import net.minidev.json.annotate.JsonIgnore;
-
 public class File implements Serializable {
 	private String checksum;
 	private String filename;
 	private long filesize;
 	private String id;
 
-	@JsonIgnore
-	// private Links links;
-
 	public String getChecksum() {
 		return checksum;
 	}
@@ -46,13 +41,4 @@ public class File implements Serializable {
 		this.id = id;
 	}
 
-//    @JsonIgnore
-//    public Links getLinks() {
-//        return links;
-//    }
-//
-//    @JsonIgnore
-//    public void setLinks(Links links) {
-//        this.links = links;
-//    }
 }

dhp-common/src/main/java/eu/dnetlib/dhp/common/collection/CollectorException.java

@@ -1,5 +1,5 @@
 
-package eu.dnetlib.dhp.collection;
+package eu.dnetlib.dhp.common.collection;
 
 public class CollectorException extends Exception {
 

dhp-common/src/main/java/eu/dnetlib/dhp/common/collection/GetCSV.java

@@ -0,0 +1,56 @@
+
+package eu.dnetlib.dhp.common.collection;
+
+import java.io.*;
+import java.nio.charset.StandardCharsets;
+import java.util.List;
+
+import org.apache.hadoop.fs.FSDataOutputStream;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+
+import com.fasterxml.jackson.databind.ObjectMapper;
+import com.opencsv.bean.CsvToBeanBuilder;
+
+public class GetCSV {
+
+	public static final char DEFAULT_DELIMITER = ',';
+
+	private GetCSV() {
+	}
+
+	public static void getCsv(FileSystem fileSystem, BufferedReader reader, String hdfsPath,
+		String modelClass) throws IOException, ClassNotFoundException {
+		getCsv(fileSystem, reader, hdfsPath, modelClass, DEFAULT_DELIMITER);
+	}
+
+	public static void getCsv(FileSystem fileSystem, Reader reader, String hdfsPath,
+		String modelClass, char delimiter) throws IOException, ClassNotFoundException {
+
+		Path hdfsWritePath = new Path(hdfsPath);
+		FSDataOutputStream fsDataOutputStream = null;
+		if (fileSystem.exists(hdfsWritePath)) {
+			fileSystem.delete(hdfsWritePath, false);
+		}
+		fsDataOutputStream = fileSystem.create(hdfsWritePath);
+
+		try (BufferedWriter writer = new BufferedWriter(
+			new OutputStreamWriter(fsDataOutputStream, StandardCharsets.UTF_8))) {
+
+			final ObjectMapper mapper = new ObjectMapper();
+
+			@SuppressWarnings("unchecked")
+			final List lines = new CsvToBeanBuilder(reader)
+				.withType(Class.forName(modelClass))
+				.withSeparator(delimiter)
+				.build()
+				.parse();
+
+			for (Object line : lines) {
+				writer.write(mapper.writeValueAsString(line));
+				writer.newLine();
+			}
+		}
+	}
+
+}

dhp-common/src/main/java/eu/dnetlib/dhp/common/collection/HttpClientParams.java

@@ -1,5 +1,5 @@
 
-package eu.dnetlib.dhp.collection;
+package eu.dnetlib.dhp.common.collection;
 
 /**
  * Bundles the http connection parameters driving the client behaviour.

dhp-common/src/main/java/eu/dnetlib/dhp/common/collection/HttpConnector2.java

@@ -1,5 +1,5 @@
 
-package eu.dnetlib.dhp.collection;
+package eu.dnetlib.dhp.common.collection;
 
 import static eu.dnetlib.dhp.utils.DHPUtils.*;
 
@@ -15,12 +15,13 @@ import org.apache.http.HttpHeaders;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 
-import eu.dnetlib.dhp.aggregation.common.AggregatorReport;
+import eu.dnetlib.dhp.common.Constants;
+import eu.dnetlib.dhp.common.aggregation.AggregatorReport;
 
 /**
  * Migrated from https://svn.driver.research-infrastructures.eu/driver/dnet45/modules/dnet-modular-collector-service/trunk/src/main/java/eu/dnetlib/data/collector/plugins/HttpConnector.java
  *
- * @author jochen, michele, andrea, alessia, claudio
+ * @author jochen, michele, andrea, alessia, claudio, andreas
  */
 public class HttpConnector2 {
 
@@ -32,7 +33,7 @@ public class HttpConnector2 {
 
 	private String responseType = null;
 
-	private final String userAgent = "Mozilla/5.0 (compatible; OAI; +http://www.openaire.eu)";
+	private static final String userAgent = "Mozilla/5.0 (compatible; OAI; +http://www.openaire.eu)";
 
 	public HttpConnector2() {
 		this(new HttpClientParams());
@@ -112,6 +113,17 @@ public class HttpConnector2 {
 			}
 
 			int retryAfter = obtainRetryAfter(urlConn.getHeaderFields());
+			String rateLimit = urlConn.getHeaderField(Constants.HTTPHEADER_IETF_DRAFT_RATELIMIT_LIMIT);
+			String rateRemaining = urlConn.getHeaderField(Constants.HTTPHEADER_IETF_DRAFT_RATELIMIT_REMAINING);
+
+			if ((rateLimit != null) && (rateRemaining != null) && (Integer.parseInt(rateRemaining) < 9)) {
+				if (retryAfter > 0) {
+					backoffAndSleep(retryAfter);
+				} else {
+					backoffAndSleep(1000);
+				}
+			}
+
 			if (is2xx(urlConn.getResponseCode())) {
 				input = urlConn.getInputStream();
 				responseType = urlConn.getContentType();
@@ -120,7 +132,7 @@ public class HttpConnector2 {
 			if (is3xx(urlConn.getResponseCode())) {
 				// REDIRECTS
 				final String newUrl = obtainNewLocation(urlConn.getHeaderFields());
-				log.info(String.format("The requested url has been moved to %s", newUrl));
+				log.info("The requested url has been moved to {}", newUrl);
 				report
 					.put(
 						REPORT_PREFIX + urlConn.getResponseCode(),
@@ -140,14 +152,14 @@ public class HttpConnector2 {
 						if (retryAfter > 0) {
 							log
 								.warn(
-									requestUrl + " - waiting and repeating request after suggested retry-after "
-										+ retryAfter + " sec.");
+									"{} - waiting and repeating request after suggested retry-after {} sec.",
+									requestUrl, retryAfter);
 							backoffAndSleep(retryAfter * 1000);
 						} else {
 							log
 								.warn(
-									requestUrl + " - waiting and repeating request after default delay of "
-										+ getClientParams().getRetryDelay() + " sec.");
+									"{} - waiting and repeating request after default delay of {} sec.",
+									requestUrl, getClientParams().getRetryDelay());
 							backoffAndSleep(retryNumber * getClientParams().getRetryDelay() * 1000);
 						}
 						report.put(REPORT_PREFIX + urlConn.getResponseCode(), requestUrl);
@@ -181,12 +193,12 @@ public class HttpConnector2 {
 	}
 
 	private void logHeaderFields(final HttpURLConnection urlConn) throws IOException {
-		log.debug("StatusCode: " + urlConn.getResponseMessage());
+		log.debug("StatusCode: {}", urlConn.getResponseMessage());
 
 		for (Map.Entry<String, List<String>> e : urlConn.getHeaderFields().entrySet()) {
 			if (e.getKey() != null) {
 				for (String v : e.getValue()) {
-					log.debug("  key: " + e.getKey() + " - value: " + v);
+					log.debug("  key: {} - value: {}", e.getKey(), v);
 				}
 			}
 		}
@@ -204,7 +216,7 @@ public class HttpConnector2 {
 
 	private int obtainRetryAfter(final Map<String, List<String>> headerMap) {
 		for (String key : headerMap.keySet()) {
-			if ((key != null) && key.equalsIgnoreCase(HttpHeaders.RETRY_AFTER) && (headerMap.get(key).size() > 0)
+			if ((key != null) && key.equalsIgnoreCase(HttpHeaders.RETRY_AFTER) && (!headerMap.get(key).isEmpty())
 				&& NumberUtils.isCreatable(headerMap.get(key).get(0))) {
 				return Integer.parseInt(headerMap.get(key).get(0)) + 10;
 			}

dhp-common/src/main/java/eu/dnetlib/dhp/common/rest/DNetRestClient.java

@@ -1,11 +1,11 @@
 
 package eu.dnetlib.dhp.common.rest;
 
+import java.io.IOException;
 import java.util.Arrays;
 import java.util.stream.Collectors;
 
 import org.apache.commons.io.IOUtils;
-import org.apache.http.client.methods.CloseableHttpResponse;
 import org.apache.http.client.methods.HttpGet;
 import org.apache.http.client.methods.HttpPost;
 import org.apache.http.client.methods.HttpUriRequest;
@@ -23,17 +23,20 @@ public class DNetRestClient {
 
 	private static final ObjectMapper mapper = new ObjectMapper();
 
+	private DNetRestClient() {
+	}
+
 	public static <T> T doGET(final String url, Class<T> clazz) throws Exception {
 		final HttpGet httpGet = new HttpGet(url);
 		return doHTTPRequest(httpGet, clazz);
 	}
 
-	public static String doGET(final String url) throws Exception {
+	public static String doGET(final String url) throws IOException {
 		final HttpGet httpGet = new HttpGet(url);
 		return doHTTPRequest(httpGet);
 	}
 
-	public static <V> String doPOST(final String url, V objParam) throws Exception {
+	public static <V> String doPOST(final String url, V objParam) throws IOException {
 		final HttpPost httpPost = new HttpPost(url);
 
 		if (objParam != null) {
@@ -45,25 +48,25 @@ public class DNetRestClient {
 		return doHTTPRequest(httpPost);
 	}
 
-	public static <T, V> T doPOST(final String url, V objParam, Class<T> clazz) throws Exception {
+	public static <T, V> T doPOST(final String url, V objParam, Class<T> clazz) throws IOException {
 		return mapper.readValue(doPOST(url, objParam), clazz);
 	}
 
-	private static String doHTTPRequest(final HttpUriRequest r) throws Exception {
-		CloseableHttpClient client = HttpClients.createDefault();
+	private static String doHTTPRequest(final HttpUriRequest r) throws IOException {
+		try (CloseableHttpClient client = HttpClients.createDefault()) {
 
-		log.info("performing HTTP request, method {} on URI {}", r.getMethod(), r.getURI().toString());
-		log
-			.info(
-				"request headers: {}",
-				Arrays
-					.asList(r.getAllHeaders())
-					.stream()
-					.map(h -> h.getName() + ":" + h.getValue())
-					.collect(Collectors.joining(",")));
+			log.info("performing HTTP request, method {} on URI {}", r.getMethod(), r.getURI().toString());
+			log
+				.info(
+					"request headers: {}",
+					Arrays
+						.asList(r.getAllHeaders())
+						.stream()
+						.map(h -> h.getName() + ":" + h.getValue())
+						.collect(Collectors.joining(",")));
 
-		CloseableHttpResponse response = client.execute(r);
-		return IOUtils.toString(response.getEntity().getContent());
+			return IOUtils.toString(client.execute(r).getEntity().getContent());
+		}
 	}
 
 	private static <T> T doHTTPRequest(final HttpUriRequest r, Class<T> clazz) throws Exception {

dhp-common/src/main/java/eu/dnetlib/dhp/common/vocabulary/Vocabulary.java

@@ -46,7 +46,7 @@ public class Vocabulary implements Serializable {
 	}
 
 	public VocabularyTerm getTerm(final String id) {
-		return Optional.ofNullable(id).map(s -> s.toLowerCase()).map(s -> terms.get(s)).orElse(null);
+		return Optional.ofNullable(id).map(String::toLowerCase).map(terms::get).orElse(null);
 	}
 
 	protected void addTerm(final String id, final String name) {
@@ -81,7 +81,6 @@ public class Vocabulary implements Serializable {
 			.ofNullable(getTermBySynonym(syn))
 			.map(term -> getTermAsQualifier(term.getId()))
 			.orElse(null);
-		// .orElse(OafMapperUtils.unknown(getId(), getName()));
 	}
 
 }

dhp-common/src/main/java/eu/dnetlib/dhp/common/vocabulary/VocabularyGroup.java

@@ -46,7 +46,6 @@ public class VocabularyGroup implements Serializable {
 				}
 
 				vocs.addTerm(vocId, termId, termName);
-				// vocs.addSynonyms(vocId, termId, termId);
 			}
 		}
 
@@ -58,10 +57,17 @@ public class VocabularyGroup implements Serializable {
 				final String syn = arr[2].trim();
 
 				vocs.addSynonyms(vocId, termId, syn);
-				// vocs.addSynonyms(vocId, termId, termId);
+
 			}
 		}
 
+		// add the term names as synonyms
+		vocs.vocs.values().forEach(voc -> {
+			voc.getTerms().values().forEach(term -> {
+				voc.addSynonym(term.getName().toLowerCase(), term.getId());
+			});
+		});
+
 		return vocs;
 	}
 
@@ -98,7 +104,7 @@ public class VocabularyGroup implements Serializable {
 			.getTerms()
 			.values()
 			.stream()
-			.map(t -> t.getId())
+			.map(VocabularyTerm::getId)
 			.collect(Collectors.toCollection(HashSet::new));
 	}
 
@@ -154,16 +160,19 @@ public class VocabularyGroup implements Serializable {
 		return Optional
 			.ofNullable(vocId)
 			.map(String::toLowerCase)
-			.map(id -> vocs.containsKey(id))
+			.map(vocs::containsKey)
 			.orElse(false);
 	}
 
 	private void addSynonyms(final String vocId, final String termId, final String syn) {
 		String id = Optional
 			.ofNullable(vocId)
-			.map(s -> s.toLowerCase())
+			.map(String::toLowerCase)
 			.orElseThrow(
-				() -> new IllegalArgumentException(String.format("empty vocabulary id for [term:%s, synonym:%s]")));
+				() -> new IllegalArgumentException(
+					String
+						.format(
+							"empty vocabulary id for [term:%s, synonym:%s]", termId, syn)));
 		Optional
 			.ofNullable(vocs.get(id))
 			.orElseThrow(() -> new IllegalArgumentException("missing vocabulary id: " + vocId))

dhp-common/src/main/java/eu/dnetlib/dhp/message/Message.java

@@ -2,7 +2,6 @@
 package eu.dnetlib.dhp.message;
 
 import java.io.Serializable;
-import java.util.HashMap;
 import java.util.LinkedHashMap;
 import java.util.Map;
 
@@ -10,8 +9,8 @@ public class Message implements Serializable {
 
 	private static final long serialVersionUID = 401753881204524893L;
 
-	public static String CURRENT_PARAM = "current";
-	public static String TOTAL_PARAM = "total";
+	public static final String CURRENT_PARAM = "current";
+	public static final String TOTAL_PARAM = "total";
 
 	private MessageType messageType;
 

dhp-common/src/main/java/eu/dnetlib/dhp/oa/merge/AuthorMerger.java

@@ -4,7 +4,6 @@ package eu.dnetlib.dhp.oa.merge;
 import java.text.Normalizer;
 import java.util.*;
 import java.util.stream.Collectors;
-import java.util.stream.Stream;
 
 import org.apache.commons.lang3.StringUtils;
 
@@ -19,6 +18,9 @@ public class AuthorMerger {
 
 	private static final Double THRESHOLD = 0.95;
 
+	private AuthorMerger() {
+	}
+
 	public static List<Author> merge(List<List<Author>> authors) {
 
 		authors.sort((o1, o2) -> -Integer.compare(countAuthorsPids(o1), countAuthorsPids(o2)));
@@ -36,7 +38,8 @@ public class AuthorMerger {
 	public static List<Author> mergeAuthor(final List<Author> a, final List<Author> b, Double threshold) {
 		int pa = countAuthorsPids(a);
 		int pb = countAuthorsPids(b);
-		List<Author> base, enrich;
+		List<Author> base;
+		List<Author> enrich;
 		int sa = authorsSize(a);
 		int sb = authorsSize(b);
 
@@ -62,7 +65,7 @@ public class AuthorMerger {
 		// <pidComparableString, Author> (if an Author has more than 1 pid, it appears 2 times in the list)
 		final Map<String, Author> basePidAuthorMap = base
 			.stream()
-			.filter(a -> a.getPid() != null && a.getPid().size() > 0)
+			.filter(a -> a.getPid() != null && !a.getPid().isEmpty())
 			.flatMap(
 				a -> a
 					.getPid()
@@ -74,7 +77,7 @@ public class AuthorMerger {
 		// <pid, Author> (list of pid that are missing in the other list)
 		final List<Tuple2<StructuredProperty, Author>> pidToEnrich = enrich
 			.stream()
-			.filter(a -> a.getPid() != null && a.getPid().size() > 0)
+			.filter(a -> a.getPid() != null && !a.getPid().isEmpty())
 			.flatMap(
 				a -> a
 					.getPid()
@@ -117,9 +120,9 @@ public class AuthorMerger {
 	}
 
 	public static String pidToComparableString(StructuredProperty pid) {
-		return (pid.getQualifier() != null
-			? pid.getQualifier().getClassid() != null ? pid.getQualifier().getClassid().toLowerCase() : ""
-			: "")
+		final String classid = pid.getQualifier().getClassid() != null ? pid.getQualifier().getClassid().toLowerCase()
+			: "";
+		return (pid.getQualifier() != null ? classid : "")
 			+ (pid.getValue() != null ? pid.getValue().toLowerCase() : "");
 	}
 

dhp-common/src/main/java/eu/dnetlib/dhp/parser/utility/VtdUtilityParser.java

@@ -12,6 +12,9 @@ import com.ximpleware.VTDNav;
 /** Created by sandro on 9/29/16. */
 public class VtdUtilityParser {
 
+	private VtdUtilityParser() {
+	}
+
 	public static List<Node> getTextValuesWithAttributes(
 		final AutoPilot ap, final VTDNav vn, final String xpath, final List<String> attributes)
 		throws VtdException {

dhp-common/src/main/java/eu/dnetlib/dhp/schema/oaf/utils/GraphCleaningFunctions.java

@@ -16,6 +16,8 @@ import com.github.sisyphsu.dateparser.DateParserUtils;
 import com.google.common.collect.Lists;
 import com.google.common.collect.Sets;
 
+import eu.dnetlib.dhp.common.vocabulary.Vocabulary;
+import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup;
 import eu.dnetlib.dhp.schema.common.ModelConstants;
 import eu.dnetlib.dhp.schema.common.ModelSupport;
 import eu.dnetlib.dhp.schema.oaf.*;
@@ -27,8 +29,11 @@ public class GraphCleaningFunctions extends CleaningFunctions {
 	public static final int ORCID_LEN = 19;
 	public static final String CLEANING_REGEX = "(?:\\n|\\r|\\t)";
 	public static final String INVALID_AUTHOR_REGEX = ".*deactivated.*";
-	public static final String TITLE_FILTER_REGEX = "[.*test.*\\W\\d]";
-	public static final int TITLE_FILTER_RESIDUAL_LENGTH = 10;
+
+	public static final String TITLE_TEST = "test";
+	public static final String TITLE_FILTER_REGEX = String.format("(%s)|\\W|\\d", TITLE_TEST);
+
+	public static final int TITLE_FILTER_RESIDUAL_LENGTH = 5;
 
 	public static <T extends Oaf> T fixVocabularyNames(T value) {
 		if (value instanceof Datasource) {
@@ -83,6 +88,22 @@ public class GraphCleaningFunctions extends CleaningFunctions {
 	}
 
 	public static <T extends Oaf> boolean filter(T value) {
+		if (Boolean.TRUE
+			.equals(
+				Optional
+					.ofNullable(value)
+					.map(
+						o -> Optional
+							.ofNullable(o.getDataInfo())
+							.map(
+								d -> Optional
+									.ofNullable(d.getInvisible())
+									.orElse(true))
+							.orElse(true))
+					.orElse(true))) {
+			return true;
+		}
+
 		if (value instanceof Datasource) {
 			// nothing to evaluate here
 		} else if (value instanceof Project) {
@@ -112,7 +133,7 @@ public class GraphCleaningFunctions extends CleaningFunctions {
 		return true;
 	}
 
-	public static <T extends Oaf> T cleanup(T value) {
+	public static <T extends Oaf> T cleanup(T value, VocabularyGroup vocs) {
 		if (value instanceof Datasource) {
 			// nothing to clean here
 		} else if (value instanceof Project) {
@@ -195,14 +216,29 @@ public class GraphCleaningFunctions extends CleaningFunctions {
 									final String title = sp
 										.getValue()
 										.toLowerCase();
-									final String residual = Unidecode
-										.decode(title)
-										.replaceAll(TITLE_FILTER_REGEX, "");
-									return residual.length() > TITLE_FILTER_RESIDUAL_LENGTH;
+									final String decoded = Unidecode.decode(title);
+
+									if (StringUtils.contains(decoded, TITLE_TEST)) {
+										return decoded
+											.replaceAll(TITLE_FILTER_REGEX, "")
+											.length() > TITLE_FILTER_RESIDUAL_LENGTH;
+									}
+									return !decoded
+										.replaceAll("\\W|\\d", "")
+										.isEmpty();
 								})
 							.map(GraphCleaningFunctions::cleanValue)
 							.collect(Collectors.toList()));
 			}
+			if (Objects.nonNull(r.getFormat())) {
+				r
+					.setFormat(
+						r
+							.getFormat()
+							.stream()
+							.map(GraphCleaningFunctions::cleanValue)
+							.collect(Collectors.toList()));
+			}
 			if (Objects.nonNull(r.getDescription())) {
 				r
 					.setDescription(
@@ -225,6 +261,38 @@ public class GraphCleaningFunctions extends CleaningFunctions {
 			if (Objects.nonNull(r.getInstance())) {
 
 				for (Instance i : r.getInstance()) {
+					if (!vocs.termExists(ModelConstants.DNET_PUBLICATION_RESOURCE, i.getInstancetype().getClassid())) {
+						if (r instanceof Publication) {
+							i
+								.setInstancetype(
+									OafMapperUtils
+										.qualifier(
+											"0038", "Other literature type", ModelConstants.DNET_PUBLICATION_RESOURCE,
+											ModelConstants.DNET_PUBLICATION_RESOURCE));
+						} else if (r instanceof Dataset) {
+							i
+								.setInstancetype(
+									OafMapperUtils
+										.qualifier(
+											"0039", "Other dataset type", ModelConstants.DNET_PUBLICATION_RESOURCE,
+											ModelConstants.DNET_PUBLICATION_RESOURCE));
+						} else if (r instanceof Software) {
+							i
+								.setInstancetype(
+									OafMapperUtils
+										.qualifier(
+											"0040", "Other software type", ModelConstants.DNET_PUBLICATION_RESOURCE,
+											ModelConstants.DNET_PUBLICATION_RESOURCE));
+						} else if (r instanceof OtherResearchProduct) {
+							i
+								.setInstancetype(
+									OafMapperUtils
+										.qualifier(
+											"0020", "Other ORP type", ModelConstants.DNET_PUBLICATION_RESOURCE,
+											ModelConstants.DNET_PUBLICATION_RESOURCE));
+						}
+					}
+
 					if (Objects.nonNull(i.getPid())) {
 						i.setPid(processPidCleaning(i.getPid()));
 					}
@@ -284,7 +352,7 @@ public class GraphCleaningFunctions extends CleaningFunctions {
 						r
 							.getAuthor()
 							.stream()
-							.filter(a -> Objects.nonNull(a))
+							.filter(Objects::nonNull)
 							.filter(a -> StringUtils.isNotBlank(a.getFullname()))
 							.filter(a -> StringUtils.isNotBlank(a.getFullname().replaceAll("[\\W]", "")))
 							.collect(Collectors.toList()));

dhp-common/src/main/java/eu/dnetlib/dhp/schema/oaf/utils/OafMapperUtils.java

@@ -17,13 +17,16 @@ import eu.dnetlib.dhp.schema.oaf.*;
 
 public class OafMapperUtils {
 
+	private OafMapperUtils() {
+	}
+
 	public static Oaf merge(final Oaf left, final Oaf right) {
 		if (ModelSupport.isSubClass(left, OafEntity.class)) {
 			return mergeEntities((OafEntity) left, (OafEntity) right);
 		} else if (ModelSupport.isSubClass(left, Relation.class)) {
 			((Relation) left).mergeFrom((Relation) right);
 		} else {
-			throw new RuntimeException("invalid Oaf type:" + left.getClass().getCanonicalName());
+			throw new IllegalArgumentException("invalid Oaf type:" + left.getClass().getCanonicalName());
 		}
 		return left;
 	}
@@ -38,7 +41,7 @@ public class OafMapperUtils {
 		} else if (ModelSupport.isSubClass(left, Project.class)) {
 			left.mergeFrom(right);
 		} else {
-			throw new RuntimeException("invalid OafEntity subtype:" + left.getClass().getCanonicalName());
+			throw new IllegalArgumentException("invalid OafEntity subtype:" + left.getClass().getCanonicalName());
 		}
 		return left;
 	}
@@ -62,7 +65,7 @@ public class OafMapperUtils {
 
 	public static List<KeyValue> listKeyValues(final String... s) {
 		if (s.length % 2 > 0) {
-			throw new RuntimeException("Invalid number of parameters (k,v,k,v,....)");
+			throw new IllegalArgumentException("Invalid number of parameters (k,v,k,v,....)");
 		}
 
 		final List<KeyValue> list = new ArrayList<>();
@@ -88,7 +91,7 @@ public class OafMapperUtils {
 			.stream(values)
 			.map(v -> field(v, info))
 			.filter(Objects::nonNull)
-			.filter(distinctByKey(f -> f.getValue()))
+			.filter(distinctByKey(Field::getValue))
 			.collect(Collectors.toList());
 	}
 
@@ -97,7 +100,7 @@ public class OafMapperUtils {
 			.stream()
 			.map(v -> field(v, info))
 			.filter(Objects::nonNull)
-			.filter(distinctByKey(f -> f.getValue()))
+			.filter(distinctByKey(Field::getValue))
 			.collect(Collectors.toList());
 	}
 
@@ -342,10 +345,10 @@ public class OafMapperUtils {
 		if (instanceList != null) {
 			final Optional<AccessRight> min = instanceList
 				.stream()
-				.map(i -> i.getAccessright())
+				.map(Instance::getAccessright)
 				.min(new AccessRightComparator<>());
 
-			final Qualifier rights = min.isPresent() ? qualifier(min.get()) : new Qualifier();
+			final Qualifier rights = min.map(OafMapperUtils::qualifier).orElseGet(Qualifier::new);
 
 			if (StringUtils.isBlank(rights.getClassid())) {
 				rights.setClassid(UNKNOWN);

dhp-common/src/main/java/eu/dnetlib/dhp/utils/DHPUtils.java

@@ -4,19 +4,19 @@ package eu.dnetlib.dhp.utils;
 import java.io.*;
 import java.nio.charset.StandardCharsets;
 import java.security.MessageDigest;
-import java.util.List;
-import java.util.Map;
-import java.util.Properties;
-import java.util.zip.GZIPInputStream;
-import java.util.zip.GZIPOutputStream;
+import java.util.*;
+import java.util.stream.Collectors;
 
-import org.apache.commons.codec.binary.Base64;
-import org.apache.commons.codec.binary.Base64OutputStream;
 import org.apache.commons.codec.binary.Hex;
 import org.apache.commons.io.IOUtils;
+import org.apache.commons.lang3.StringUtils;
 import org.apache.hadoop.conf.Configuration;
 import org.apache.hadoop.fs.FileSystem;
 import org.apache.hadoop.fs.Path;
+import org.apache.http.client.methods.CloseableHttpResponse;
+import org.apache.http.client.methods.HttpGet;
+import org.apache.http.impl.client.CloseableHttpClient;
+import org.apache.http.impl.client.HttpClients;
 import org.apache.spark.sql.Dataset;
 import org.apache.spark.sql.SaveMode;
 import org.slf4j.Logger;
@@ -26,6 +26,8 @@ import com.fasterxml.jackson.databind.ObjectMapper;
 import com.google.common.collect.Maps;
 import com.jayway.jsonpath.JsonPath;
 
+import eu.dnetlib.dhp.schema.mdstore.MDStoreWithInfo;
+import eu.dnetlib.dhp.schema.oaf.utils.CleaningFunctions;
 import net.minidev.json.JSONArray;
 import scala.collection.JavaConverters;
 import scala.collection.Seq;
@@ -34,6 +36,9 @@ public class DHPUtils {
 
 	private static final Logger log = LoggerFactory.getLogger(DHPUtils.class);
 
+	private DHPUtils() {
+	}
+
 	public static Seq<String> toSeq(List<String> list) {
 		return JavaConverters.asScalaIteratorConverter(list.iterator()).asScala().toSeq();
 	}
@@ -44,40 +49,59 @@ public class DHPUtils {
 			md.update(s.getBytes(StandardCharsets.UTF_8));
 			return new String(Hex.encodeHex(md.digest()));
 		} catch (final Exception e) {
-			System.err.println("Error creating id");
+			log.error("Error creating id from {}", s);
 			return null;
 		}
 	}
 
+	/**
+	 * Retrieves from the metadata store manager application the list of paths associated with mdstores characterized
+	 * by he given format, layout, interpretation
+	 * @param mdstoreManagerUrl the URL of the mdstore manager service
+	 * @param format the mdstore format
+	 * @param layout the mdstore layout
+	 * @param interpretation the mdstore interpretation
+	 * @param includeEmpty include Empty mdstores
+	 * @return the set of hdfs paths
+	 * @throws IOException in case of HTTP communication issues
+	 */
+	public static Set<String> mdstorePaths(final String mdstoreManagerUrl,
+		final String format,
+		final String layout,
+		final String interpretation,
+		boolean includeEmpty) throws IOException {
+		final String url = mdstoreManagerUrl + "/mdstores/";
+		final ObjectMapper objectMapper = new ObjectMapper();
+
+		final HttpGet req = new HttpGet(url);
+
+		try (final CloseableHttpClient client = HttpClients.createDefault()) {
+			try (final CloseableHttpResponse response = client.execute(req)) {
+				final String json = IOUtils.toString(response.getEntity().getContent());
+				final MDStoreWithInfo[] mdstores = objectMapper.readValue(json, MDStoreWithInfo[].class);
+				return Arrays
+					.stream(mdstores)
+					.filter(md -> md.getFormat().equalsIgnoreCase(format))
+					.filter(md -> md.getLayout().equalsIgnoreCase(layout))
+					.filter(md -> md.getInterpretation().equalsIgnoreCase(interpretation))
+					.filter(md -> StringUtils.isNotBlank(md.getHdfsPath()))
+					.filter(md -> StringUtils.isNotBlank(md.getCurrentVersion()))
+					.filter(md -> includeEmpty || md.getSize() > 0)
+					.map(md -> md.getHdfsPath() + "/" + md.getCurrentVersion() + "/store")
+					.collect(Collectors.toSet());
+			}
+		}
+	}
+
 	public static String generateIdentifier(final String originalId, final String nsPrefix) {
 		return String.format("%s::%s", nsPrefix, DHPUtils.md5(originalId));
 	}
 
-	public static String compressString(final String input) {
-		try (ByteArrayOutputStream out = new ByteArrayOutputStream();
-			Base64OutputStream b64os = new Base64OutputStream(out)) {
-			GZIPOutputStream gzip = new GZIPOutputStream(b64os);
-			gzip.write(input.getBytes(StandardCharsets.UTF_8));
-			gzip.close();
-			return out.toString();
-		} catch (Throwable e) {
-			return null;
-		}
-	}
+	public static String generateUnresolvedIdentifier(final String pid, final String pidType) {
 
-	public static String decompressString(final String input) {
-		byte[] byteArray = Base64.decodeBase64(input.getBytes());
-		int len;
-		try (GZIPInputStream gis = new GZIPInputStream(new ByteArrayInputStream((byteArray)));
-			ByteArrayOutputStream bos = new ByteArrayOutputStream(byteArray.length)) {
-			byte[] buffer = new byte[1024];
-			while ((len = gis.read(buffer)) != -1) {
-				bos.write(buffer, 0, len);
-			}
-			return bos.toString();
-		} catch (Exception e) {
-			return null;
-		}
+		final String cleanedPid = CleaningFunctions.normalizePidValue(pidType, pid);
+
+		return String.format("unresolved::%s::%s", cleanedPid, pidType.toLowerCase().trim());
 	}
 
 	public static String getJPathString(final String jsonPath, final String json) {

dhp-common/src/main/java/eu/dnetlib/dhp/utils/ISLookupClientFactory.java

@@ -18,13 +18,16 @@ public class ISLookupClientFactory {
 	private static final int requestTimeout = 60000 * 10;
 	private static final int connectTimeout = 60000 * 10;
 
+	private ISLookupClientFactory() {
+	}
+
 	public static ISLookUpService getLookUpService(final String isLookupUrl) {
 		return getServiceStub(ISLookUpService.class, isLookupUrl);
 	}
 
 	@SuppressWarnings("unchecked")
 	private static <T> T getServiceStub(final Class<T> clazz, final String endpoint) {
-		log.info(String.format("creating %s stub from %s", clazz.getName(), endpoint));
+		log.info("creating {} stub from {}", clazz.getName(), endpoint);
 		final JaxWsProxyFactoryBean jaxWsProxyFactory = new JaxWsProxyFactoryBean();
 		jaxWsProxyFactory.setServiceClass(clazz);
 		jaxWsProxyFactory.setAddress(endpoint);
@@ -38,12 +41,10 @@ public class ISLookupClientFactory {
 
 			log
 				.info(
-					String
-						.format(
-							"setting connectTimeout to %s, requestTimeout to %s for service %s",
-							connectTimeout,
-							requestTimeout,
-							clazz.getCanonicalName()));
+					"setting connectTimeout to {}, requestTimeout to {} for service {}",
+					connectTimeout,
+					requestTimeout,
+					clazz.getCanonicalName());
 
 			policy.setConnectionTimeout(connectTimeout);
 			policy.setReceiveTimeout(requestTimeout);

dhp-common/src/main/java/eu/dnetlib/dhp/utils/saxon/AbstractExtensionFunction.java

@@ -10,7 +10,7 @@ import net.sf.saxon.trans.XPathException;
 
 public abstract class AbstractExtensionFunction extends ExtensionFunctionDefinition {
 
-	public static String DEFAULT_SAXON_EXT_NS_URI = "http://www.d-net.research-infrastructures.eu/saxon-extension";
+	public static final String DEFAULT_SAXON_EXT_NS_URI = "http://www.d-net.research-infrastructures.eu/saxon-extension";
 
 	public abstract String getName();
 

dhp-common/src/main/java/eu/dnetlib/dhp/utils/saxon/ExtractYear.java

@@ -26,7 +26,7 @@ public class ExtractYear extends AbstractExtensionFunction {
 
 	@Override
 	public Sequence doCall(XPathContext context, Sequence[] arguments) throws XPathException {
-		if (arguments == null | arguments.length == 0) {
+		if (arguments == null || arguments.length == 0) {
 			return new StringValue("");
 		}
 		final Item item = arguments[0].head();
@@ -63,8 +63,7 @@ public class ExtractYear extends AbstractExtensionFunction {
 		for (String format : dateFormats) {
 			try {
 				c.setTime(new SimpleDateFormat(format).parse(s));
-				String year = String.valueOf(c.get(Calendar.YEAR));
-				return year;
+				return String.valueOf(c.get(Calendar.YEAR));
 			} catch (ParseException e) {
 			}
 		}

dhp-common/src/main/java/eu/dnetlib/dhp/utils/saxon/NormalizeDate.java

@@ -30,7 +30,7 @@ public class NormalizeDate extends AbstractExtensionFunction {
 
 	@Override
 	public Sequence doCall(XPathContext context, Sequence[] arguments) throws XPathException {
-		if (arguments == null | arguments.length == 0) {
+		if (arguments == null || arguments.length == 0) {
 			return new StringValue(BLANK);
 		}
 		String s = arguments[0].head().getStringValue();

dhp-common/src/main/java/eu/dnetlib/dhp/utils/saxon/PickFirst.java

@@ -1,6 +1,8 @@
 
 package eu.dnetlib.dhp.utils.saxon;
 
+import static org.apache.commons.lang3.StringUtils.isNotBlank;
+
 import org.apache.commons.lang3.StringUtils;
 
 import net.sf.saxon.expr.XPathContext;
@@ -26,7 +28,8 @@ public class PickFirst extends AbstractExtensionFunction {
 		final String s1 = getValue(arguments[0]);
 		final String s2 = getValue(arguments[1]);
 
-		return new StringValue(StringUtils.isNotBlank(s1) ? s1 : StringUtils.isNotBlank(s2) ? s2 : "");
+		final String value = isNotBlank(s1) ? s1 : isNotBlank(s2) ? s2 : "";
+		return new StringValue(value);
 	}
 
 	private String getValue(final Sequence arg) throws XPathException {

dhp-common/src/main/java/eu/dnetlib/dhp/utils/saxon/SaxonTransformerFactory.java

@@ -12,6 +12,9 @@ import net.sf.saxon.TransformerFactoryImpl;
 
 public class SaxonTransformerFactory {
 
+	private SaxonTransformerFactory() {
+	}
+
 	/**
 	 * Creates the index record transformer from the given XSLT
 	 *

dhp-common/src/main/scala/eu/dnetlib/dhp/application/SparkScalaApplication.scala

@@ -0,0 +1,73 @@
+package eu.dnetlib.dhp.application
+
+import scala.io.Source
+
+/** This is the main Interface SparkApplication
+  * where all the Spark Scala class should inherit
+  */
+trait SparkScalaApplication {
+
+  /** This is the path in the classpath of the json
+    * describes all the argument needed to run
+    */
+  val propertyPath: String
+
+  /** Utility to parse the arguments using the
+    * property json in the classpath identified from
+    * the variable propertyPath
+    *
+    * @param args the list of arguments
+    */
+  def parseArguments(args: Array[String]): ArgumentApplicationParser = {
+    val parser = new ArgumentApplicationParser(
+      Source.fromInputStream(getClass.getResourceAsStream(propertyPath)).mkString
+    )
+    parser.parseArgument(args)
+    parser
+  }
+
+  /** Here all the spark applications runs this method
+    * where the whole logic of the spark node is defined
+    */
+  def run(): Unit
+}
+
+import org.apache.spark.SparkConf
+import org.apache.spark.sql.SparkSession
+import org.slf4j.Logger
+
+abstract class AbstractScalaApplication(
+  val propertyPath: String,
+  val args: Array[String],
+  log: Logger
+) extends SparkScalaApplication {
+
+  var parser: ArgumentApplicationParser = null
+
+  var spark: SparkSession = null
+
+  def initialize(): SparkScalaApplication = {
+    parser = parseArguments(args)
+    spark = createSparkSession()
+    this
+  }
+
+  /** Utility for creating a spark session starting from parser
+    *
+    * @return a spark Session
+    */
+  private def createSparkSession(): SparkSession = {
+    require(parser != null)
+
+    val conf: SparkConf = new SparkConf()
+    val master = parser.get("master")
+    log.info(s"Creating Spark session: Master: $master")
+    SparkSession
+      .builder()
+      .config(conf)
+      .appName(getClass.getSimpleName)
+      .master(master)
+      .getOrCreate()
+  }
+
+}

dhp-common/src/main/scala/eu/dnetlib/dhp/sx/graph/scholix/ScholixUtils.scala

@@ -0,0 +1,442 @@
+package eu.dnetlib.dhp.sx.graph.scholix
+
+import eu.dnetlib.dhp.schema.oaf.{Publication, Relation, Result, StructuredProperty}
+import eu.dnetlib.dhp.schema.sx.scholix._
+import eu.dnetlib.dhp.schema.sx.summary.{CollectedFromType, SchemeValue, ScholixSummary, Typology}
+import eu.dnetlib.dhp.utils.DHPUtils
+import org.apache.spark.sql.expressions.Aggregator
+import org.apache.spark.sql.{Encoder, Encoders}
+import org.json4s
+import org.json4s.DefaultFormats
+import org.json4s.jackson.JsonMethods.parse
+import scala.collection.JavaConverters._
+import scala.io.Source
+
+object ScholixUtils extends Serializable {
+
+  val DNET_IDENTIFIER_SCHEMA: String = "DNET Identifier"
+
+  val DATE_RELATION_KEY: String = "RelationDate"
+
+  case class RelationVocabulary(original: String, inverse: String) {}
+
+  case class RelatedEntities(id: String, relatedDataset: Long, relatedPublication: Long) {}
+
+  val relations: Map[String, RelationVocabulary] = {
+    val input = Source
+      .fromInputStream(
+        getClass.getResourceAsStream("/eu/dnetlib/scholexplorer/relation/relations.json")
+      )
+      .mkString
+    implicit lazy val formats: DefaultFormats.type = org.json4s.DefaultFormats
+
+    lazy val json: json4s.JValue = parse(input)
+
+    json.extract[Map[String, RelationVocabulary]]
+  }
+
+  def extractRelationDate(relation: Relation): String = {
+
+    if (relation.getProperties == null || !relation.getProperties.isEmpty)
+      null
+    else {
+      val date = relation.getProperties.asScala
+        .find(p => DATE_RELATION_KEY.equalsIgnoreCase(p.getKey))
+        .map(p => p.getValue)
+      if (date.isDefined)
+        date.get
+      else
+        null
+    }
+  }
+
+  def extractRelationDate(summary: ScholixSummary): String = {
+
+    if (summary.getDate == null || summary.getDate.isEmpty)
+      null
+    else {
+      summary.getDate.get(0)
+    }
+  }
+
+  def inverseRelationShip(rel: ScholixRelationship): ScholixRelationship = {
+    new ScholixRelationship(rel.getInverse, rel.getSchema, rel.getName)
+
+  }
+
+  def generateScholixResourceFromResult(r: Result): ScholixResource = {
+    generateScholixResourceFromSummary(ScholixUtils.resultToSummary(r))
+  }
+
+  val statsAggregator: Aggregator[(String, String, Long), RelatedEntities, RelatedEntities] =
+    new Aggregator[(String, String, Long), RelatedEntities, RelatedEntities] with Serializable {
+      override def zero: RelatedEntities = null
+
+      override def reduce(b: RelatedEntities, a: (String, String, Long)): RelatedEntities = {
+        val relatedDataset = if ("dataset".equalsIgnoreCase(a._2)) a._3 else 0
+        val relatedPublication = if ("publication".equalsIgnoreCase(a._2)) a._3 else 0
+
+        if (b == null)
+          RelatedEntities(a._1, relatedDataset, relatedPublication)
+        else
+          RelatedEntities(
+            a._1,
+            b.relatedDataset + relatedDataset,
+            b.relatedPublication + relatedPublication
+          )
+      }
+
+      override def merge(b1: RelatedEntities, b2: RelatedEntities): RelatedEntities = {
+        if (b1 != null && b2 != null)
+          RelatedEntities(
+            b1.id,
+            b1.relatedDataset + b2.relatedDataset,
+            b1.relatedPublication + b2.relatedPublication
+          )
+        else if (b1 != null)
+          b1
+        else
+          b2
+      }
+
+      override def finish(reduction: RelatedEntities): RelatedEntities = reduction
+
+      override def bufferEncoder: Encoder[RelatedEntities] = Encoders.bean(classOf[RelatedEntities])
+
+      override def outputEncoder: Encoder[RelatedEntities] = Encoders.bean(classOf[RelatedEntities])
+    }
+
+  val scholixAggregator: Aggregator[(String, Scholix), Scholix, Scholix] =
+    new Aggregator[(String, Scholix), Scholix, Scholix] with Serializable {
+      override def zero: Scholix = null
+
+      def scholix_complete(s: Scholix): Boolean = {
+        if (s == null || s.getIdentifier == null) {
+          false
+        } else if (s.getSource == null || s.getTarget == null) {
+          false
+        } else if (s.getLinkprovider == null || s.getLinkprovider.isEmpty)
+          false
+        else
+          true
+      }
+
+      override def reduce(b: Scholix, a: (String, Scholix)): Scholix = {
+        if (scholix_complete(b)) b else a._2
+      }
+
+      override def merge(b1: Scholix, b2: Scholix): Scholix = {
+        if (scholix_complete(b1)) b1 else b2
+      }
+
+      override def finish(reduction: Scholix): Scholix = reduction
+
+      override def bufferEncoder: Encoder[Scholix] = Encoders.kryo[Scholix]
+
+      override def outputEncoder: Encoder[Scholix] = Encoders.kryo[Scholix]
+    }
+
+  def createInverseScholixRelation(scholix: Scholix): Scholix = {
+    val s = new Scholix
+    s.setPublicationDate(scholix.getPublicationDate)
+    s.setPublisher(scholix.getPublisher)
+    s.setLinkprovider(scholix.getLinkprovider)
+    s.setRelationship(inverseRelationShip(scholix.getRelationship))
+    s.setSource(scholix.getTarget)
+    s.setTarget(scholix.getSource)
+    s.setIdentifier(
+      DHPUtils.md5(
+        s"${s.getSource.getIdentifier}::${s.getRelationship.getName}::${s.getTarget.getIdentifier}"
+      )
+    )
+    s
+
+  }
+
+  def extractCollectedFrom(summary: ScholixResource): List[ScholixEntityId] = {
+    if (summary.getCollectedFrom != null && !summary.getCollectedFrom.isEmpty) {
+      val l: List[ScholixEntityId] = summary.getCollectedFrom.asScala.map { d =>
+        new ScholixEntityId(d.getProvider.getName, d.getProvider.getIdentifiers)
+      }(collection.breakOut)
+      l
+    } else List()
+  }
+
+  def extractCollectedFrom(summary: ScholixSummary): List[ScholixEntityId] = {
+    if (summary.getDatasources != null && !summary.getDatasources.isEmpty) {
+      val l: List[ScholixEntityId] = summary.getDatasources.asScala.map { d =>
+        new ScholixEntityId(
+          d.getDatasourceName,
+          List(new ScholixIdentifier(d.getDatasourceId, "DNET Identifier", null)).asJava
+        )
+      }(collection.breakOut)
+      l
+    } else List()
+  }
+
+  def extractCollectedFrom(relation: Relation): List[ScholixEntityId] = {
+    if (relation.getCollectedfrom != null && !relation.getCollectedfrom.isEmpty) {
+
+      val l: List[ScholixEntityId] = relation.getCollectedfrom.asScala.map { c =>
+        new ScholixEntityId(
+          c.getValue,
+          List(new ScholixIdentifier(c.getKey, DNET_IDENTIFIER_SCHEMA, null)).asJava
+        )
+      }.toList
+      l
+    } else List()
+  }
+
+  def generateCompleteScholix(scholix: Scholix, target: ScholixSummary): Scholix = {
+    val s = new Scholix
+    s.setPublicationDate(scholix.getPublicationDate)
+    s.setPublisher(scholix.getPublisher)
+    s.setLinkprovider(scholix.getLinkprovider)
+    s.setRelationship(scholix.getRelationship)
+    s.setSource(scholix.getSource)
+    s.setTarget(generateScholixResourceFromSummary(target))
+    s.setIdentifier(
+      DHPUtils.md5(
+        s"${s.getSource.getIdentifier}::${s.getRelationship.getName}::${s.getTarget.getIdentifier}"
+      )
+    )
+    s
+  }
+
+  def generateCompleteScholix(scholix: Scholix, target: ScholixResource): Scholix = {
+    val s = new Scholix
+    s.setPublicationDate(scholix.getPublicationDate)
+    s.setPublisher(scholix.getPublisher)
+    s.setLinkprovider(scholix.getLinkprovider)
+    s.setRelationship(scholix.getRelationship)
+    s.setSource(scholix.getSource)
+    s.setTarget(target)
+    s.setIdentifier(
+      DHPUtils.md5(
+        s"${s.getSource.getIdentifier}::${s.getRelationship.getName}::${s.getTarget.getIdentifier}"
+      )
+    )
+    s
+  }
+
+  def generateScholixResourceFromSummary(summaryObject: ScholixSummary): ScholixResource = {
+    val r = new ScholixResource
+    r.setIdentifier(summaryObject.getLocalIdentifier)
+    r.setDnetIdentifier(summaryObject.getId)
+
+    r.setObjectType(summaryObject.getTypology.toString)
+    r.setObjectSubType(summaryObject.getSubType)
+
+    if (summaryObject.getTitle != null && !summaryObject.getTitle.isEmpty)
+      r.setTitle(summaryObject.getTitle.get(0))
+
+    if (summaryObject.getAuthor != null && !summaryObject.getAuthor.isEmpty) {
+      val l: List[ScholixEntityId] =
+        summaryObject.getAuthor.asScala.map(a => new ScholixEntityId(a, null)).toList
+      if (l.nonEmpty)
+        r.setCreator(l.asJava)
+    }
+
+    if (summaryObject.getDate != null && !summaryObject.getDate.isEmpty)
+      r.setPublicationDate(summaryObject.getDate.get(0))
+    if (summaryObject.getPublisher != null && !summaryObject.getPublisher.isEmpty) {
+      val plist: List[ScholixEntityId] =
+        summaryObject.getPublisher.asScala.map(p => new ScholixEntityId(p, null)).toList
+
+      if (plist.nonEmpty)
+        r.setPublisher(plist.asJava)
+    }
+
+    if (summaryObject.getDatasources != null && !summaryObject.getDatasources.isEmpty) {
+
+      val l: List[ScholixCollectedFrom] = summaryObject.getDatasources.asScala
+        .map(c =>
+          new ScholixCollectedFrom(
+            new ScholixEntityId(
+              c.getDatasourceName,
+              List(new ScholixIdentifier(c.getDatasourceId, DNET_IDENTIFIER_SCHEMA, null)).asJava
+            ),
+            "collected",
+            "complete"
+          )
+        )
+        .toList
+
+      if (l.nonEmpty)
+        r.setCollectedFrom(l.asJava)
+
+    }
+    r
+  }
+
+  def scholixFromSource(relation: Relation, source: ScholixResource): Scholix = {
+    if (relation == null || source == null)
+      return null
+    val s = new Scholix
+    var l: List[ScholixEntityId] = extractCollectedFrom(relation)
+    if (l.isEmpty)
+      l = extractCollectedFrom(source)
+    if (l.isEmpty)
+      return null
+    s.setLinkprovider(l.asJava)
+    var d = extractRelationDate(relation)
+    if (d == null)
+      d = source.getPublicationDate
+
+    s.setPublicationDate(d)
+
+    if (source.getPublisher != null && !source.getPublisher.isEmpty) {
+      s.setPublisher(source.getPublisher)
+    }
+
+    val semanticRelation = relations.getOrElse(relation.getRelClass.toLowerCase, null)
+    if (semanticRelation == null)
+      return null
+    s.setRelationship(
+      new ScholixRelationship(semanticRelation.original, "datacite", semanticRelation.inverse)
+    )
+    s.setSource(source)
+
+    s
+  }
+
+  def scholixFromSource(relation: Relation, source: ScholixSummary): Scholix = {
+
+    if (relation == null || source == null)
+      return null
+
+    val s = new Scholix
+
+    var l: List[ScholixEntityId] = extractCollectedFrom(relation)
+    if (l.isEmpty)
+      l = extractCollectedFrom(source)
+    if (l.isEmpty)
+      return null
+
+    s.setLinkprovider(l.asJava)
+
+    var d = extractRelationDate(relation)
+    if (d == null)
+      d = extractRelationDate(source)
+
+    s.setPublicationDate(d)
+
+    if (source.getPublisher != null && !source.getPublisher.isEmpty) {
+      val l: List[ScholixEntityId] = source.getPublisher.asScala
+        .map { p =>
+          new ScholixEntityId(p, null)
+        }(collection.breakOut)
+
+      if (l.nonEmpty)
+        s.setPublisher(l.asJava)
+    }
+
+    val semanticRelation = relations.getOrElse(relation.getRelClass.toLowerCase, null)
+    if (semanticRelation == null)
+      return null
+    s.setRelationship(
+      new ScholixRelationship(semanticRelation.original, "datacite", semanticRelation.inverse)
+    )
+    s.setSource(generateScholixResourceFromSummary(source))
+
+    s
+  }
+
+  def findURLForPID(
+    pidValue: List[StructuredProperty],
+    urls: List[String]
+  ): List[(StructuredProperty, String)] = {
+    pidValue.map { p =>
+      val pv = p.getValue
+
+      val r = urls.find(u => u.toLowerCase.contains(pv.toLowerCase))
+      (p, r.orNull)
+    }
+  }
+
+  def extractTypedIdentifierFromInstance(r: Result): List[ScholixIdentifier] = {
+    if (r.getInstance() == null || r.getInstance().isEmpty)
+      return List()
+    r.getInstance()
+      .asScala
+      .filter(i => i.getUrl != null && !i.getUrl.isEmpty)
+      .filter(i => i.getPid != null && i.getUrl != null)
+      .flatMap(i => findURLForPID(i.getPid.asScala.toList, i.getUrl.asScala.toList))
+      .map(i => new ScholixIdentifier(i._1.getValue, i._1.getQualifier.getClassid, i._2))
+      .distinct
+      .toList
+  }
+
+  def resultToSummary(r: Result): ScholixSummary = {
+    val s = new ScholixSummary
+    s.setId(r.getId)
+    if (r.getPid == null || r.getPid.isEmpty)
+      return null
+
+    val persistentIdentifiers: List[ScholixIdentifier] = extractTypedIdentifierFromInstance(r)
+    if (persistentIdentifiers.isEmpty)
+      return null
+    s.setLocalIdentifier(persistentIdentifiers.asJava)
+    if (r.isInstanceOf[Publication])
+      s.setTypology(Typology.publication)
+    else
+      s.setTypology(Typology.dataset)
+
+    s.setSubType(r.getInstance().get(0).getInstancetype.getClassname)
+
+    if (r.getTitle != null && r.getTitle.asScala.nonEmpty) {
+      val titles: List[String] = r.getTitle.asScala.map(t => t.getValue).toList
+      if (titles.nonEmpty)
+        s.setTitle(titles.asJava)
+      else
+        return null
+    }
+
+    if (r.getAuthor != null && !r.getAuthor.isEmpty) {
+      val authors: List[String] = r.getAuthor.asScala.map(a => a.getFullname).toList
+      if (authors.nonEmpty)
+        s.setAuthor(authors.asJava)
+    }
+    if (r.getInstance() != null) {
+      val dt: List[String] = r
+        .getInstance()
+        .asScala
+        .filter(i => i.getDateofacceptance != null)
+        .map(i => i.getDateofacceptance.getValue)
+        .toList
+      if (dt.nonEmpty)
+        s.setDate(dt.distinct.asJava)
+    }
+    if (r.getDescription != null && !r.getDescription.isEmpty) {
+      val d = r.getDescription.asScala.find(f => f != null && f.getValue != null)
+      if (d.isDefined)
+        s.setDescription(d.get.getValue)
+    }
+
+    if (r.getSubject != null && !r.getSubject.isEmpty) {
+      val subjects: List[SchemeValue] = r.getSubject.asScala
+        .map(s => new SchemeValue(s.getQualifier.getClassname, s.getValue))
+        .toList
+      if (subjects.nonEmpty)
+        s.setSubject(subjects.asJava)
+    }
+
+    if (r.getPublisher != null)
+      s.setPublisher(List(r.getPublisher.getValue).asJava)
+
+    if (r.getCollectedfrom != null && !r.getCollectedfrom.isEmpty) {
+      val cf: List[CollectedFromType] = r.getCollectedfrom.asScala
+        .map(c => new CollectedFromType(c.getValue, c.getKey, "complete"))
+        .toList
+      if (cf.nonEmpty)
+        s.setDatasources(cf.distinct.asJava)
+    }
+
+    s.setRelatedDatasets(0)
+    s.setRelatedPublications(0)
+    s.setRelatedUnknown(0)
+
+    s
+  }
+
+}

dhp-common/src/test/java/eu/dnetlib/dhp/application/ArgumentApplicationParserTest.java

@@ -7,10 +7,10 @@ import static org.junit.jupiter.api.Assertions.assertNotNull;
 import org.apache.commons.io.IOUtils;
 import org.junit.jupiter.api.Test;
 
-public class ArgumentApplicationParserTest {
+class ArgumentApplicationParserTest {
 
 	@Test
-	public void testParseParameter() throws Exception {
+	void testParseParameter() throws Exception {
 		final String jsonConfiguration = IOUtils
 			.toString(
 				this.getClass().getResourceAsStream("/eu/dnetlib/application/parameters.json"));

dhp-common/src/test/java/eu/dnetlib/dhp/common/HdfsSupportTest.java

@@ -21,13 +21,13 @@ public class HdfsSupportTest {
 	class Remove {
 
 		@Test
-		public void shouldThrowARuntimeExceptionOnError() {
+		void shouldThrowARuntimeExceptionOnError() {
 			// when
 			assertThrows(RuntimeException.class, () -> HdfsSupport.remove(null, new Configuration()));
 		}
 
 		@Test
-		public void shouldRemoveADirFromHDFS(@TempDir Path tempDir) {
+		void shouldRemoveADirFromHDFS(@TempDir Path tempDir) {
 			// when
 			HdfsSupport.remove(tempDir.toString(), new Configuration());
 
@@ -36,7 +36,7 @@ public class HdfsSupportTest {
 		}
 
 		@Test
-		public void shouldRemoveAFileFromHDFS(@TempDir Path tempDir) throws IOException {
+		void shouldRemoveAFileFromHDFS(@TempDir Path tempDir) throws IOException {
 			// given
 			Path file = Files.createTempFile(tempDir, "p", "s");
 
@@ -52,13 +52,13 @@ public class HdfsSupportTest {
 	class ListFiles {
 
 		@Test
-		public void shouldThrowARuntimeExceptionOnError() {
+		void shouldThrowARuntimeExceptionOnError() {
 			// when
 			assertThrows(RuntimeException.class, () -> HdfsSupport.listFiles(null, new Configuration()));
 		}
 
 		@Test
-		public void shouldListFilesLocatedInPath(@TempDir Path tempDir) throws IOException {
+		void shouldListFilesLocatedInPath(@TempDir Path tempDir) throws IOException {
 			Path subDir1 = Files.createTempDirectory(tempDir, "list_me");
 			Path subDir2 = Files.createTempDirectory(tempDir, "list_me");
 

dhp-common/src/test/java/eu/dnetlib/dhp/common/PacePersonTest.java

@@ -5,10 +5,10 @@ import static org.junit.jupiter.api.Assertions.*;
 
 import org.junit.jupiter.api.Test;
 
-public class PacePersonTest {
+class PacePersonTest {
 
 	@Test
-	public void pacePersonTest1() {
+	void pacePersonTest1() {
 
 		PacePerson p = new PacePerson("Artini, Michele", false);
 		assertEquals("Artini", p.getSurnameString());
@@ -17,7 +17,7 @@ public class PacePersonTest {
 	}
 
 	@Test
-	public void pacePersonTest2() {
+	void pacePersonTest2() {
 		PacePerson p = new PacePerson("Michele G. Artini", false);
 		assertEquals("Artini, Michele G.", p.getNormalisedFullname());
 		assertEquals("Michele G", p.getNameString());

dhp-common/src/test/java/eu/dnetlib/dhp/common/SparkSessionSupportTest.java

@@ -18,7 +18,8 @@ public class SparkSessionSupportTest {
 	class RunWithSparkSession {
 
 		@Test
-		public void shouldExecuteFunctionAndNotStopSparkSessionWhenSparkSessionIsNotManaged()
+		@SuppressWarnings("unchecked")
+		void shouldExecuteFunctionAndNotStopSparkSessionWhenSparkSessionIsNotManaged()
 			throws Exception {
 			// given
 			SparkSession spark = mock(SparkSession.class);
@@ -37,7 +38,8 @@ public class SparkSessionSupportTest {
 		}
 
 		@Test
-		public void shouldExecuteFunctionAndStopSparkSessionWhenSparkSessionIsManaged()
+		@SuppressWarnings("unchecked")
+		void shouldExecuteFunctionAndStopSparkSessionWhenSparkSessionIsManaged()
 			throws Exception {
 			// given
 			SparkSession spark = mock(SparkSession.class);

dhp-common/src/test/java/eu/dnetlib/dhp/common/api/ZenodoAPIClientTest.java

@@ -12,7 +12,7 @@ import org.junit.jupiter.api.Disabled;
 import org.junit.jupiter.api.Test;
 
 @Disabled
-public class ZenodoAPIClientTest {
+class ZenodoAPIClientTest {
 
 	private final String URL_STRING = "https://sandbox.zenodo.org/api/deposit/depositions";
 	private final String ACCESS_TOKEN = "";
@@ -22,7 +22,7 @@ public class ZenodoAPIClientTest {
 	private final String depositionId = "674915";
 
 	@Test
-	public void testUploadOldDeposition() throws IOException, MissingConceptDoiException {
+	void testUploadOldDeposition() throws IOException, MissingConceptDoiException {
 		ZenodoAPIClient client = new ZenodoAPIClient(URL_STRING,
 			ACCESS_TOKEN);
 		Assertions.assertEquals(200, client.uploadOpenDeposition(depositionId));
@@ -44,7 +44,7 @@ public class ZenodoAPIClientTest {
 	}
 
 	@Test
-	public void testNewDeposition() throws IOException {
+	void testNewDeposition() throws IOException {
 
 		ZenodoAPIClient client = new ZenodoAPIClient(URL_STRING,
 			ACCESS_TOKEN);
@@ -67,7 +67,7 @@ public class ZenodoAPIClientTest {
 	}
 
 	@Test
-	public void testNewVersionNewName() throws IOException, MissingConceptDoiException {
+	void testNewVersionNewName() throws IOException, MissingConceptDoiException {
 
 		ZenodoAPIClient client = new ZenodoAPIClient(URL_STRING,
 			ACCESS_TOKEN);
@@ -87,7 +87,7 @@ public class ZenodoAPIClientTest {
 	}
 
 	@Test
-	public void testNewVersionOldName() throws IOException, MissingConceptDoiException {
+	void testNewVersionOldName() throws IOException, MissingConceptDoiException {
 
 		ZenodoAPIClient client = new ZenodoAPIClient(URL_STRING,
 			ACCESS_TOKEN);

dhp-common/src/test/java/eu/dnetlib/dhp/oa/merge/AuthorMergerTest.java

@@ -21,7 +21,7 @@ import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
 import eu.dnetlib.pace.util.MapDocumentUtil;
 import scala.Tuple2;
 
-public class AuthorMergerTest {
+class AuthorMergerTest {
 
 	private String publicationsBasePath;
 
@@ -43,7 +43,7 @@ public class AuthorMergerTest {
 	}
 
 	@Test
-	public void mergeTest() { // used in the dedup: threshold set to 0.95
+	void mergeTest() { // used in the dedup: threshold set to 0.95
 
 		for (List<Author> authors1 : authors) {
 			System.out.println("List " + (authors.indexOf(authors1) + 1));

dhp-common/src/test/java/eu/dnetlib/dhp/schema/oaf/utils/OafMapperUtilsTest.java

@@ -21,7 +21,7 @@ import eu.dnetlib.dhp.schema.oaf.Publication;
 import eu.dnetlib.dhp.schema.oaf.Result;
 import me.xuender.unidecode.Unidecode;
 
-public class OafMapperUtilsTest {
+class OafMapperUtilsTest {
 
 	private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper()
 		.configure(DeserializationFeature.FAIL_ON_UNKNOWN_PROPERTIES, false);
@@ -42,7 +42,7 @@ public class OafMapperUtilsTest {
 	}
 
 	@Test
-	public void testDateValidation() {
+	void testDateValidation() {
 
 		assertTrue(GraphCleaningFunctions.doCleanDate("2016-05-07T12:41:19.202Z  ").isPresent());
 		assertTrue(GraphCleaningFunctions.doCleanDate("2020-09-10 11:08:52 ").isPresent());
@@ -107,7 +107,7 @@ public class OafMapperUtilsTest {
 		assertEquals("2006-01-02", GraphCleaningFunctions.doCleanDate("2006-01-02T15:04:05+0000").get());
 		assertEquals("2009-08-13", GraphCleaningFunctions.doCleanDate("2009-08-12T22:15:09-07:00").get());
 		assertEquals("2009-08-12", GraphCleaningFunctions.doCleanDate("2009-08-12T22:15:09").get());
-		assertEquals("2009-08-12", GraphCleaningFunctions.doCleanDate("2009-08-12T22:15:09Z").get());
+		assertEquals("2009-08-13", GraphCleaningFunctions.doCleanDate("2009-08-12T22:15:09Z").get());
 		assertEquals("2014-04-26", GraphCleaningFunctions.doCleanDate("2014-04-26 17:24:37.3186369").get());
 		assertEquals("2012-08-03", GraphCleaningFunctions.doCleanDate("2012-08-03 18:31:59.257000000").get());
 		assertEquals("2014-04-26", GraphCleaningFunctions.doCleanDate("2014-04-26 17:24:37.123").get());
@@ -147,44 +147,46 @@ public class OafMapperUtilsTest {
 	}
 
 	@Test
-	public void testDate() {
-		System.out.println(GraphCleaningFunctions.cleanDate("23-FEB-1998"));
+	void testDate() {
+		final String date = GraphCleaningFunctions.cleanDate("23-FEB-1998");
+		assertNotNull(date);
+		System.out.println(date);
 	}
 
 	@Test
-	public void testMergePubs() throws IOException {
+	void testMergePubs() throws IOException {
 		Publication p1 = read("publication_1.json", Publication.class);
 		Publication p2 = read("publication_2.json", Publication.class);
 		Dataset d1 = read("dataset_1.json", Dataset.class);
 		Dataset d2 = read("dataset_2.json", Dataset.class);
 
-		assertEquals(p1.getCollectedfrom().size(), 1);
-		assertEquals(p1.getCollectedfrom().get(0).getKey(), ModelConstants.CROSSREF_ID);
-		assertEquals(d2.getCollectedfrom().size(), 1);
+		assertEquals(1, p1.getCollectedfrom().size());
+		assertEquals(ModelConstants.CROSSREF_ID, p1.getCollectedfrom().get(0).getKey());
+		assertEquals(1, d2.getCollectedfrom().size());
 		assertFalse(cfId(d2.getCollectedfrom()).contains(ModelConstants.CROSSREF_ID));
 
-		assertTrue(
+		assertEquals(
+			ModelConstants.PUBLICATION_RESULTTYPE_CLASSID,
 			OafMapperUtils
 				.mergeResults(p1, d2)
 				.getResulttype()
-				.getClassid()
-				.equals(ModelConstants.PUBLICATION_RESULTTYPE_CLASSID));
+				.getClassid());
 
-		assertEquals(p2.getCollectedfrom().size(), 1);
+		assertEquals(1, p2.getCollectedfrom().size());
 		assertFalse(cfId(p2.getCollectedfrom()).contains(ModelConstants.CROSSREF_ID));
-		assertEquals(d1.getCollectedfrom().size(), 1);
+		assertEquals(1, d1.getCollectedfrom().size());
 		assertTrue(cfId(d1.getCollectedfrom()).contains(ModelConstants.CROSSREF_ID));
 
-		assertTrue(
+		assertEquals(
+			ModelConstants.DATASET_RESULTTYPE_CLASSID,
 			OafMapperUtils
 				.mergeResults(p2, d1)
 				.getResulttype()
-				.getClassid()
-				.equals(ModelConstants.DATASET_RESULTTYPE_CLASSID));
+				.getClassid());
 	}
 
 	protected HashSet<String> cfId(List<KeyValue> collectedfrom) {
-		return collectedfrom.stream().map(c -> c.getKey()).collect(Collectors.toCollection(HashSet::new));
+		return collectedfrom.stream().map(KeyValue::getKey).collect(Collectors.toCollection(HashSet::new));
 	}
 
 	protected <T extends Result> T read(String filename, Class<T> clazz) throws IOException {

dhp-common/src/test/java/eu/dnetlib/scholexplorer/relation/RelationMapperTest.java

@@ -3,10 +3,10 @@ package eu.dnetlib.scholexplorer.relation;
 
 import org.junit.jupiter.api.Test;
 
-public class RelationMapperTest {
+class RelationMapperTest {
 
 	@Test
-	public void testLoadRels() throws Exception {
+	void testLoadRels() throws Exception {
 
 		RelationMapper relationMapper = RelationMapper.load();
 		relationMapper.keySet().forEach(System.out::println);

dhp-workflows/dhp-actionmanager/src/main/java/eu/dnetlib/dhp/actionmanager/ISClient.java

@@ -3,40 +3,37 @@ package eu.dnetlib.dhp.actionmanager;
 
 import java.io.Serializable;
 import java.io.StringReader;
-import java.util.*;
+import java.util.List;
+import java.util.NoSuchElementException;
+import java.util.Optional;
+import java.util.Set;
 import java.util.stream.Collectors;
 
 import org.apache.commons.lang3.tuple.Triple;
 import org.dom4j.Document;
 import org.dom4j.DocumentException;
-import org.dom4j.Element;
 import org.dom4j.io.SAXReader;
-import org.jetbrains.annotations.NotNull;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
+import org.xml.sax.SAXException;
 
 import com.google.common.base.Joiner;
 import com.google.common.base.Splitter;
 import com.google.common.collect.Iterables;
-import com.google.common.collect.Lists;
 import com.google.common.collect.Sets;
 
 import eu.dnetlib.actionmanager.rmi.ActionManagerException;
-import eu.dnetlib.actionmanager.set.ActionManagerSet;
-import eu.dnetlib.actionmanager.set.ActionManagerSet.ImpactTypes;
-import eu.dnetlib.dhp.actionmanager.partition.PartitionActionSetsByPayloadTypeJob;
 import eu.dnetlib.dhp.utils.ISLookupClientFactory;
 import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpException;
 import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
-import scala.Tuple2;
 
 public class ISClient implements Serializable {
 
-	private static final Logger log = LoggerFactory.getLogger(PartitionActionSetsByPayloadTypeJob.class);
+	private static final Logger log = LoggerFactory.getLogger(ISClient.class);
 
 	private static final String INPUT_ACTION_SET_ID_SEPARATOR = ",";
 
-	private final ISLookUpService isLookup;
+	private final transient ISLookUpService isLookup;
 
 	public ISClient(String isLookupUrl) {
 		isLookup = ISLookupClientFactory.getLookUpService(isLookupUrl);
@@ -63,7 +60,7 @@ public class ISClient implements Serializable {
 				.map(
 					sets -> sets
 						.stream()
-						.map(set -> parseSetInfo(set))
+						.map(ISClient::parseSetInfo)
 						.filter(t -> ids.contains(t.getLeft()))
 						.map(t -> buildDirectory(basePath, t))
 						.collect(Collectors.toList()))
@@ -73,15 +70,17 @@ public class ISClient implements Serializable {
 		}
 	}
 
-	private Triple<String, String, String> parseSetInfo(String set) {
+	private static Triple<String, String, String> parseSetInfo(String set) {
 		try {
-			Document doc = new SAXReader().read(new StringReader(set));
+			final SAXReader reader = new SAXReader();
+			reader.setFeature("http://apache.org/xml/features/disallow-doctype-decl", true);
+			Document doc = reader.read(new StringReader(set));
 			return Triple
 				.of(
 					doc.valueOf("//SET/@id"),
 					doc.valueOf("//SET/@directory"),
 					doc.valueOf("//SET/@latest"));
-		} catch (DocumentException e) {
+		} catch (DocumentException | SAXException e) {
 			throw new IllegalStateException(e);
 		}
 	}
@@ -99,7 +98,7 @@ public class ISClient implements Serializable {
 		final String q = "for $x in /RESOURCE_PROFILE[.//RESOURCE_TYPE/@value='ActionManagerServiceResourceType'] return $x//SERVICE_PROPERTIES/PROPERTY[./@ key='"
 			+ propertyName
 			+ "']/@value/string()";
-		log.debug("quering for service property: " + q);
+		log.debug("quering for service property: {}", q);
 		try {
 			final List<String> value = isLookup.quickSearchProfile(q);
 			return Iterables.getOnlyElement(value);

dhp-workflows/dhp-actionmanager/src/main/java/eu/dnetlib/dhp/actionmanager/promote/MergeAndGet.java

@@ -62,6 +62,7 @@ public class MergeAndGet {
 					x.getClass().getCanonicalName(), y.getClass().getCanonicalName()));
 	}
 
+	@SuppressWarnings("unchecked")
 	private static <G extends Oaf, A extends Oaf> G selectNewerAndGet(G x, A y) {
 		if (x.getClass().equals(y.getClass())
 			&& x.getLastupdatetimestamp() > y.getLastupdatetimestamp()) {

dhp-workflows/dhp-actionmanager/src/main/java/eu/dnetlib/dhp/actionmanager/promote/PromoteActionPayloadForGraphTableJob.java

@@ -74,7 +74,9 @@ public class PromoteActionPayloadForGraphTableJob {
 			.orElse(true);
 		logger.info("shouldGroupById: {}", shouldGroupById);
 
+		@SuppressWarnings("unchecked")
 		Class<? extends Oaf> rowClazz = (Class<? extends Oaf>) Class.forName(graphTableClassName);
+		@SuppressWarnings("unchecked")
 		Class<? extends Oaf> actionPayloadClazz = (Class<? extends Oaf>) Class.forName(actionPayloadClassName);
 
 		throwIfGraphTableClassIsNotSubClassOfActionPayloadClass(rowClazz, actionPayloadClazz);
@@ -152,7 +154,7 @@ public class PromoteActionPayloadForGraphTableJob {
 		return spark
 			.read()
 			.parquet(path)
-			.map((MapFunction<Row, String>) value -> extractPayload(value), Encoders.STRING())
+			.map((MapFunction<Row, String>) PromoteActionPayloadForGraphTableJob::extractPayload, Encoders.STRING())
 			.map(
 				(MapFunction<String, A>) value -> decodePayload(actionPayloadClazz, value),
 				Encoders.bean(actionPayloadClazz));

dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/publication/oozie_app/workflow.xml

@@ -107,7 +107,7 @@
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
                 --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-                --conf spark.sql.shuffle.partitions=2560
+                --conf spark.sql.shuffle.partitions=5000
             </spark-opts>
             <arg>--inputGraphTablePath</arg><arg>${inputGraphRootPath}/publication</arg>
             <arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
@@ -159,7 +159,7 @@
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
                 --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-                --conf spark.sql.shuffle.partitions=2560
+                --conf spark.sql.shuffle.partitions=5000
             </spark-opts>
             <arg>--inputGraphTablePath</arg><arg>${workingDir}/publication</arg>
             <arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>

dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/relation/oozie_app/workflow.xml

@@ -99,7 +99,7 @@
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
                 --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-                --conf spark.sql.shuffle.partitions=2560
+                --conf spark.sql.shuffle.partitions=5000
             </spark-opts>
             <arg>--inputGraphTablePath</arg><arg>${inputGraphRootPath}/relation</arg>
             <arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Relation</arg>

dhp-workflows/dhp-actionmanager/src/test/java/eu/dnetlib/dhp/actionmanager/partition/PartitionActionSetsByPayloadTypeJobTest.java

@@ -80,7 +80,7 @@ public class PartitionActionSetsByPayloadTypeJobTest {
 		private ISClient isClient;
 
 		@Test
-		public void shouldPartitionActionSetsByPayloadType(@TempDir Path workingDir) throws Exception {
+		void shouldPartitionActionSetsByPayloadType(@TempDir Path workingDir) throws Exception {
 			// given
 			Path inputActionSetsBaseDir = workingDir.resolve("input").resolve("action_sets");
 			Path outputDir = workingDir.resolve("output");

dhp-workflows/dhp-actionmanager/src/test/java/eu/dnetlib/dhp/actionmanager/promote/MergeAndGetTest.java

@@ -20,7 +20,7 @@ public class MergeAndGetTest {
 	class MergeFromAndGetStrategy {
 
 		@Test
-		public void shouldThrowForOafAndOaf() {
+		void shouldThrowForOafAndOaf() {
 			// given
 			Oaf a = mock(Oaf.class);
 			Oaf b = mock(Oaf.class);
@@ -33,7 +33,7 @@ public class MergeAndGetTest {
 		}
 
 		@Test
-		public void shouldThrowForOafAndRelation() {
+		void shouldThrowForOafAndRelation() {
 			// given
 			Oaf a = mock(Oaf.class);
 			Relation b = mock(Relation.class);
@@ -46,7 +46,7 @@ public class MergeAndGetTest {
 		}
 
 		@Test
-		public void shouldThrowForOafAndOafEntity() {
+		void shouldThrowForOafAndOafEntity() {
 			// given
 			Oaf a = mock(Oaf.class);
 			OafEntity b = mock(OafEntity.class);
@@ -59,7 +59,7 @@ public class MergeAndGetTest {
 		}
 
 		@Test
-		public void shouldThrowForRelationAndOaf() {
+		void shouldThrowForRelationAndOaf() {
 			// given
 			Relation a = mock(Relation.class);
 			Oaf b = mock(Oaf.class);
@@ -72,7 +72,7 @@ public class MergeAndGetTest {
 		}
 
 		@Test
-		public void shouldThrowForRelationAndOafEntity() {
+		void shouldThrowForRelationAndOafEntity() {
 			// given
 			Relation a = mock(Relation.class);
 			OafEntity b = mock(OafEntity.class);
@@ -85,7 +85,7 @@ public class MergeAndGetTest {
 		}
 
 		@Test
-		public void shouldBehaveProperlyForRelationAndRelation() {
+		void shouldBehaveProperlyForRelationAndRelation() {
 			// given
 			Relation a = mock(Relation.class);
 			Relation b = mock(Relation.class);
@@ -101,7 +101,7 @@ public class MergeAndGetTest {
 		}
 
 		@Test
-		public void shouldThrowForOafEntityAndOaf() {
+		void shouldThrowForOafEntityAndOaf() {
 			// given
 			OafEntity a = mock(OafEntity.class);
 			Oaf b = mock(Oaf.class);
@@ -114,7 +114,7 @@ public class MergeAndGetTest {
 		}
 
 		@Test
-		public void shouldThrowForOafEntityAndRelation() {
+		void shouldThrowForOafEntityAndRelation() {
 			// given
 			OafEntity a = mock(OafEntity.class);
 			Relation b = mock(Relation.class);
@@ -127,7 +127,7 @@ public class MergeAndGetTest {
 		}
 
 		@Test
-		public void shouldThrowForOafEntityAndOafEntityButNotSubclasses() {
+		void shouldThrowForOafEntityAndOafEntityButNotSubclasses() {
 			// given
 			class OafEntitySub1 extends OafEntity {
 			}
@@ -145,7 +145,7 @@ public class MergeAndGetTest {
 		}
 
 		@Test
-		public void shouldBehaveProperlyForOafEntityAndOafEntity() {
+		void shouldBehaveProperlyForOafEntityAndOafEntity() {
 			// given
 			OafEntity a = mock(OafEntity.class);
 			OafEntity b = mock(OafEntity.class);
@@ -165,7 +165,7 @@ public class MergeAndGetTest {
 	class SelectNewerAndGetStrategy {
 
 		@Test
-		public void shouldThrowForOafEntityAndRelation() {
+		void shouldThrowForOafEntityAndRelation() {
 			// given
 			OafEntity a = mock(OafEntity.class);
 			Relation b = mock(Relation.class);
@@ -178,7 +178,7 @@ public class MergeAndGetTest {
 		}
 
 		@Test
-		public void shouldThrowForRelationAndOafEntity() {
+		void shouldThrowForRelationAndOafEntity() {
 			// given
 			Relation a = mock(Relation.class);
 			OafEntity b = mock(OafEntity.class);
@@ -191,7 +191,7 @@ public class MergeAndGetTest {
 		}
 
 		@Test
-		public void shouldThrowForOafEntityAndResult() {
+		void shouldThrowForOafEntityAndResult() {
 			// given
 			OafEntity a = mock(OafEntity.class);
 			Result b = mock(Result.class);
@@ -204,7 +204,7 @@ public class MergeAndGetTest {
 		}
 
 		@Test
-		public void shouldThrowWhenSuperTypeIsNewerForResultAndOafEntity() {
+		void shouldThrowWhenSuperTypeIsNewerForResultAndOafEntity() {
 			// given
 			// real types must be used because subclass-superclass resolution does not work for
 			// mocks
@@ -221,7 +221,7 @@ public class MergeAndGetTest {
 		}
 
 		@Test
-		public void shouldShouldReturnLeftForOafEntityAndOafEntity() {
+		void shouldShouldReturnLeftForOafEntityAndOafEntity() {
 			// given
 			OafEntity a = mock(OafEntity.class);
 			when(a.getLastupdatetimestamp()).thenReturn(1L);
@@ -238,7 +238,7 @@ public class MergeAndGetTest {
 		}
 
 		@Test
-		public void shouldShouldReturnRightForOafEntityAndOafEntity() {
+		void shouldShouldReturnRightForOafEntityAndOafEntity() {
 			// given
 			OafEntity a = mock(OafEntity.class);
 			when(a.getLastupdatetimestamp()).thenReturn(2L);

dhp-workflows/dhp-actionmanager/src/test/java/eu/dnetlib/dhp/actionmanager/promote/PromoteActionPayloadForGraphTableJobTest.java

@@ -77,7 +77,7 @@ public class PromoteActionPayloadForGraphTableJobTest {
 	class Main {
 
 		@Test
-		public void shouldThrowWhenGraphTableClassIsNotASubClassOfActionPayloadClass() {
+		void shouldThrowWhenGraphTableClassIsNotASubClassOfActionPayloadClass() {
 			// given
 			Class<Relation> rowClazz = Relation.class;
 			Class<OafEntity> actionPayloadClazz = OafEntity.class;
@@ -116,7 +116,7 @@ public class PromoteActionPayloadForGraphTableJobTest {
 
 		@ParameterizedTest(name = "strategy: {0}, graph table: {1}, action payload: {2}")
 		@MethodSource("eu.dnetlib.dhp.actionmanager.promote.PromoteActionPayloadForGraphTableJobTest#promoteJobTestParams")
-		public void shouldPromoteActionPayloadForGraphTable(
+		void shouldPromoteActionPayloadForGraphTable(
 			MergeAndGet.Strategy strategy,
 			Class<? extends Oaf> rowClazz,
 			Class<? extends Oaf> actionPayloadClazz)

dhp-workflows/dhp-actionmanager/src/test/java/eu/dnetlib/dhp/actionmanager/promote/PromoteActionPayloadFunctionsTest.java

@@ -44,7 +44,7 @@ public class PromoteActionPayloadFunctionsTest {
 	class JoinTableWithActionPayloadAndMerge {
 
 		@Test
-		public void shouldThrowWhenTableTypeIsNotSubtypeOfActionPayloadType() {
+		void shouldThrowWhenTableTypeIsNotSubtypeOfActionPayloadType() {
 			// given
 			class OafImpl extends Oaf {
 			}
@@ -58,7 +58,7 @@ public class PromoteActionPayloadFunctionsTest {
 		}
 
 		@Test
-		public void shouldRunProperlyWhenActionPayloadTypeAndTableTypeAreTheSame() {
+		void shouldRunProperlyWhenActionPayloadTypeAndTableTypeAreTheSame() {
 			// given
 			String id0 = "id0";
 			String id1 = "id1";
@@ -138,7 +138,7 @@ public class PromoteActionPayloadFunctionsTest {
 		}
 
 		@Test
-		public void shouldRunProperlyWhenActionPayloadTypeIsSuperTypeOfTableType() {
+		void shouldRunProperlyWhenActionPayloadTypeIsSuperTypeOfTableType() {
 			// given
 			String id0 = "id0";
 			String id1 = "id1";
@@ -218,7 +218,7 @@ public class PromoteActionPayloadFunctionsTest {
 	class GroupTableByIdAndMerge {
 
 		@Test
-		public void shouldRunProperly() {
+		void shouldRunProperly() {
 			// given
 			String id1 = "id1";
 			String id2 = "id2";

dhp-workflows/dhp-aggregation/pom.xml

@@ -29,6 +29,13 @@
                             <goal>testCompile</goal>
                         </goals>
                     </execution>
+                    <execution>
+                        <id>scala-doc</id>
+                        <phase>process-resources</phase> <!-- or wherever -->
+                        <goals>
+                            <goal>doc</goal>
+                        </goals>
+                    </execution>
                 </executions>
                 <configuration>
                     <scalaVersion>${scala.version}</scalaVersion>
@@ -84,14 +91,6 @@
             <artifactId>json</artifactId>
         </dependency>
 
-        <!-- https://mvnrepository.com/artifact/org.apache.commons/commons-csv -->
-        <dependency>
-            <groupId>org.apache.commons</groupId>
-            <artifactId>commons-csv</artifactId>
-            <version>1.8</version>
-        </dependency>
-
-
         <!-- https://mvnrepository.com/artifact/org.apache.poi/poi-ooxml -->
         <dependency>
             <groupId>org.apache.poi</groupId>

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/Constants.java

@@ -0,0 +1,92 @@
+
+package eu.dnetlib.dhp.actionmanager;
+
+import java.util.Optional;
+
+import org.apache.spark.api.java.function.MapFunction;
+import org.apache.spark.sql.Dataset;
+import org.apache.spark.sql.Encoders;
+import org.apache.spark.sql.SparkSession;
+
+import com.fasterxml.jackson.databind.ObjectMapper;
+
+import eu.dnetlib.dhp.application.ArgumentApplicationParser;
+import eu.dnetlib.dhp.schema.common.ModelConstants;
+import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
+import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
+
+public class Constants {
+
+	public static final String DOI = "doi";
+	public static final String DOI_CLASSNAME = "Digital Object Identifier";
+
+	public static final String DEFAULT_DELIMITER = ",";
+
+	public static final String UPDATE_DATA_INFO_TYPE = "update";
+	public static final String UPDATE_SUBJECT_FOS_CLASS_ID = "subject:fos";
+	public static final String UPDATE_CLASS_NAME = "Inferred by OpenAIRE";
+	public static final String UPDATE_MEASURE_BIP_CLASS_ID = "measure:bip";
+	public static final String UPDATE_SUBJECT_SDG_CLASS_ID = "subject:sdg";
+
+	public static final String FOS_CLASS_ID = "FOS";
+	public static final String FOS_CLASS_NAME = "Fields of Science and Technology classification";
+
+	public static final String SDG_CLASS_ID = "SDG";
+	public static final String SDG_CLASS_NAME = "Sustainable Development Goals";
+
+	public static final String NULL = "NULL";
+
+	public static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
+
+	private Constants() {
+	}
+
+	public static Boolean isSparkSessionManaged(ArgumentApplicationParser parser) {
+		return Optional
+			.ofNullable(parser.get("isSparkSessionManaged"))
+			.map(Boolean::valueOf)
+			.orElse(Boolean.TRUE);
+	}
+
+	public static <R> Dataset<R> readPath(
+		SparkSession spark, String inputPath, Class<R> clazz) {
+		return spark
+			.read()
+			.textFile(inputPath)
+			.map((MapFunction<String, R>) value -> OBJECT_MAPPER.readValue(value, clazz), Encoders.bean(clazz));
+	}
+
+	public static StructuredProperty getSubject(String sbj, String classid, String classname,
+		String diqualifierclassid) {
+		if (sbj.equals(NULL))
+			return null;
+		StructuredProperty sp = new StructuredProperty();
+		sp.setValue(sbj);
+		sp
+			.setQualifier(
+				OafMapperUtils
+					.qualifier(
+						classid,
+						classname,
+						ModelConstants.DNET_SUBJECT_TYPOLOGIES,
+						ModelConstants.DNET_SUBJECT_TYPOLOGIES));
+		sp
+			.setDataInfo(
+				OafMapperUtils
+					.dataInfo(
+						false,
+						UPDATE_DATA_INFO_TYPE,
+						true,
+						false,
+						OafMapperUtils
+							.qualifier(
+								diqualifierclassid,
+								UPDATE_CLASS_NAME,
+								ModelConstants.DNET_PROVENANCE_ACTIONS,
+								ModelConstants.DNET_PROVENANCE_ACTIONS),
+						""));
+
+		return sp;
+
+	}
+}

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/bipfinder/CollectAndSave.java

@@ -1,84 +0,0 @@
-
-package eu.dnetlib.dhp.actionmanager.bipfinder;
-
-import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
-
-import java.io.Serializable;
-import java.util.Optional;
-
-import org.apache.commons.io.IOUtils;
-import org.apache.hadoop.io.Text;
-import org.apache.hadoop.mapred.SequenceFileOutputFormat;
-import org.apache.spark.SparkConf;
-import org.apache.spark.api.java.JavaSparkContext;
-import org.apache.spark.sql.SparkSession;
-import org.slf4j.Logger;
-import org.slf4j.LoggerFactory;
-
-import com.fasterxml.jackson.databind.ObjectMapper;
-
-import eu.dnetlib.dhp.application.ArgumentApplicationParser;
-import eu.dnetlib.dhp.common.HdfsSupport;
-import eu.dnetlib.dhp.schema.oaf.Result;
-
-/**
- * Just collects all the atomic actions produced for the different results and saves them in
- * outputpath for the ActionSet
- */
-public class CollectAndSave implements Serializable {
-
-	private static final Logger log = LoggerFactory.getLogger(CollectAndSave.class);
-	private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
-
-	public static <I extends Result> void main(String[] args) throws Exception {
-
-		String jsonConfiguration = IOUtils
-			.toString(
-				CollectAndSave.class
-					.getResourceAsStream(
-						"/eu/dnetlib/dhp/actionmanager/bipfinder/input_actionset_parameter.json"));
-
-		final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
-
-		parser.parseArgument(args);
-
-		Boolean isSparkSessionManaged = Optional
-			.ofNullable(parser.get("isSparkSessionManaged"))
-			.map(Boolean::valueOf)
-			.orElse(Boolean.TRUE);
-
-		log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
-
-		final String inputPath = parser.get("inputPath");
-		log.info("inputPath {}: ", inputPath);
-
-		final String outputPath = parser.get("outputPath");
-		log.info("outputPath {}: ", outputPath);
-
-		SparkConf conf = new SparkConf();
-
-		runWithSparkSession(
-			conf,
-			isSparkSessionManaged,
-			spark -> {
-				removeOutputDir(spark, outputPath);
-				collectAndSave(spark, inputPath, outputPath);
-			});
-	}
-
-	private static void collectAndSave(SparkSession spark, String inputPath, String outputPath) {
-		JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
-
-		sc
-			.sequenceFile(inputPath + "/publication", Text.class, Text.class)
-			.union(sc.sequenceFile(inputPath + "/dataset", Text.class, Text.class))
-			.union(sc.sequenceFile(inputPath + "/otherresearchproduct", Text.class, Text.class))
-			.union(sc.sequenceFile(inputPath + "/software", Text.class, Text.class))
-			.saveAsHadoopFile(outputPath, Text.class, Text.class, SequenceFileOutputFormat.class);
-	}
-
-	private static void removeOutputDir(SparkSession spark, String path) {
-		HdfsSupport.remove(path, spark.sparkContext().hadoopConfiguration());
-	}
-
-}

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/bipfinder/PreparedResult.java

@@ -1,28 +0,0 @@
-
-package eu.dnetlib.dhp.actionmanager.bipfinder;
-
-import java.io.Serializable;
-
-/**
- * Subset of the information of the generic results that are needed to create the atomic action
- */
-public class PreparedResult implements Serializable {
-	private String id; // openaire id
-	private String value; // doi
-
-	public String getId() {
-		return id;
-	}
-
-	public void setId(String id) {
-		this.id = id;
-	}
-
-	public String getValue() {
-		return value;
-	}
-
-	public void setValue(String value) {
-		this.value = value;
-	}
-}

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/bipfinder/SparkAtomicActionScoreJob.java

@@ -1,6 +1,7 @@
 
 package eu.dnetlib.dhp.actionmanager.bipfinder;
 
+import static eu.dnetlib.dhp.actionmanager.Constants.*;
 import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
 
 import java.io.Serializable;
@@ -15,7 +16,6 @@ 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.MapFunction;
-import org.apache.spark.api.java.function.MapGroupsFunction;
 import org.apache.spark.sql.Dataset;
 import org.apache.spark.sql.Encoders;
 import org.apache.spark.sql.SparkSession;
@@ -24,11 +24,15 @@ import org.slf4j.LoggerFactory;
 
 import com.fasterxml.jackson.databind.ObjectMapper;
 
+import eu.dnetlib.dhp.actionmanager.bipmodel.BipDeserialize;
+import eu.dnetlib.dhp.actionmanager.bipmodel.BipScore;
 import eu.dnetlib.dhp.application.ArgumentApplicationParser;
 import eu.dnetlib.dhp.common.HdfsSupport;
 import eu.dnetlib.dhp.schema.action.AtomicAction;
+import eu.dnetlib.dhp.schema.common.ModelConstants;
 import eu.dnetlib.dhp.schema.oaf.*;
 import eu.dnetlib.dhp.schema.oaf.KeyValue;
+import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
 import scala.Tuple2;
 
 /**
@@ -46,7 +50,7 @@ public class SparkAtomicActionScoreJob implements Serializable {
 			.toString(
 				SparkAtomicActionScoreJob.class
 					.getResourceAsStream(
-						"/eu/dnetlib/dhp/actionmanager/bipfinder/input_parameters.json"));
+						"/eu/dnetlib/dhp/actionmanager/bipfinder/input_actionset_parameter.json"));
 
 		final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
 
@@ -65,14 +69,6 @@ public class SparkAtomicActionScoreJob implements Serializable {
 		final String outputPath = parser.get("outputPath");
 		log.info("outputPath {}: ", outputPath);
 
-		final String bipScorePath = parser.get("bipScorePath");
-		log.info("bipScorePath: {}", bipScorePath);
-
-		final String resultClassName = parser.get("resultTableName");
-		log.info("resultTableName: {}", resultClassName);
-
-		Class<I> inputClazz = (Class<I>) Class.forName(resultClassName);
-
 		SparkConf conf = new SparkConf();
 
 		runWithSparkSession(
@@ -80,14 +76,13 @@ public class SparkAtomicActionScoreJob implements Serializable {
 			isSparkSessionManaged,
 			spark -> {
 				removeOutputDir(spark, outputPath);
-				prepareResults(spark, inputPath, outputPath, bipScorePath, inputClazz);
+				prepareResults(spark, inputPath, outputPath);
 			});
 	}
 
-	private static <I extends Result> void prepareResults(SparkSession spark, String inputPath, String outputPath,
-		String bipScorePath, Class<I> inputClazz) {
+	private static <I extends Result> void prepareResults(SparkSession spark, String bipScorePath, String outputPath) {
 
-		final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
+		final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
 
 		JavaRDD<BipDeserialize> bipDeserializeJavaRDD = sc
 			.textFile(bipScorePath)
@@ -101,43 +96,19 @@ public class SparkAtomicActionScoreJob implements Serializable {
 				return bs;
 			}).collect(Collectors.toList()).iterator()).rdd(), Encoders.bean(BipScore.class));
 
-		System.out.println(bipScores.count());
-
-		Dataset<I> results = readPath(spark, inputPath, inputClazz);
-
-		results.createOrReplaceTempView("result");
-
-		Dataset<PreparedResult> preparedResult = spark
-			.sql(
-				"select pIde.value value, id " +
-					"from result " +
-					"lateral view explode (pid) p as pIde " +
-					"where dataInfo.deletedbyinference = false and pIde.qualifier.classid = '" + DOI + "'")
-			.as(Encoders.bean(PreparedResult.class));
-
 		bipScores
-			.joinWith(
-				preparedResult, bipScores.col("id").equalTo(preparedResult.col("value")),
-				"inner")
-			.map((MapFunction<Tuple2<BipScore, PreparedResult>, BipScore>) value -> {
-				BipScore ret = value._1();
-				ret.setId(value._2().getId());
-				return ret;
-			}, Encoders.bean(BipScore.class))
-			.groupByKey((MapFunction<BipScore, String>) value -> value.getId(), Encoders.STRING())
-			.mapGroups((MapGroupsFunction<String, BipScore, Result>) (k, it) -> {
-				Result ret = new Result();
-				ret.setDataInfo(getDataInfo());
-				BipScore first = it.next();
-				ret.setId(first.getId());
 
-				ret.setMeasures(getMeasure(first));
-				it.forEachRemaining(value -> ret.getMeasures().addAll(getMeasure(value)));
+			.map((MapFunction<BipScore, Result>) bs -> {
+				Result ret = new Result();
+
+				ret.setId(bs.getId());
+
+				ret.setMeasures(getMeasure(bs));
 
 				return ret;
 			}, Encoders.bean(Result.class))
 			.toJavaRDD()
-			.map(p -> new AtomicAction(inputClazz, p))
+			.map(p -> new AtomicAction(Result.class, p))
 			.mapToPair(
 				aa -> new Tuple2<>(new Text(aa.getClazz().getCanonicalName()),
 					new Text(OBJECT_MAPPER.writeValueAsString(aa))))
@@ -161,7 +132,21 @@ public class SparkAtomicActionScoreJob implements Serializable {
 								KeyValue kv = new KeyValue();
 								kv.setValue(unit.getValue());
 								kv.setKey(unit.getKey());
-								kv.setDataInfo(getDataInfo());
+								kv
+									.setDataInfo(
+										OafMapperUtils
+											.dataInfo(
+												false,
+												UPDATE_DATA_INFO_TYPE,
+												true,
+												false,
+												OafMapperUtils
+													.qualifier(
+														UPDATE_MEASURE_BIP_CLASS_ID,
+														UPDATE_CLASS_NAME,
+														ModelConstants.DNET_PROVENANCE_ACTIONS,
+														ModelConstants.DNET_PROVENANCE_ACTIONS),
+												""));
 								return kv;
 							})
 							.collect(Collectors.toList()));
@@ -170,21 +155,6 @@ public class SparkAtomicActionScoreJob implements Serializable {
 			.collect(Collectors.toList());
 	}
 
-	private static DataInfo getDataInfo() {
-		DataInfo di = new DataInfo();
-		di.setInferred(false);
-		di.setInvisible(false);
-		di.setDeletedbyinference(false);
-		di.setTrust("");
-		Qualifier qualifier = new Qualifier();
-		qualifier.setClassid("sysimport:actionset");
-		qualifier.setClassname("Harvested");
-		qualifier.setSchemename("dnet:provenanceActions");
-		qualifier.setSchemeid("dnet:provenanceActions");
-		di.setProvenanceaction(qualifier);
-		return di;
-	}
-
 	private static void removeOutputDir(SparkSession spark, String path) {
 		HdfsSupport.remove(path, spark.sparkContext().hadoopConfiguration());
 	}

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/bipmodel/BipDeserialize.java

@@ -1,5 +1,5 @@
 
-package eu.dnetlib.dhp.actionmanager.bipfinder;
+package eu.dnetlib.dhp.actionmanager.bipmodel;
 
 import java.io.Serializable;
 import java.util.ArrayList;

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/bipmodel/BipScore.java

@@ -1,5 +1,5 @@
 
-package eu.dnetlib.dhp.actionmanager.bipfinder;
+package eu.dnetlib.dhp.actionmanager.bipmodel;
 
 import java.io.Serializable;
 import java.util.List;

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/bipmodel/KeyValue.java

@@ -1,5 +1,5 @@
 
-package eu.dnetlib.dhp.actionmanager.bipfinder;
+package eu.dnetlib.dhp.actionmanager.bipmodel;
 
 import java.io.Serializable;
 

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/bipmodel/Score.java

@@ -1,5 +1,5 @@
 
-package eu.dnetlib.dhp.actionmanager.bipfinder;
+package eu.dnetlib.dhp.actionmanager.bipmodel;
 
 import java.io.Serializable;
 import java.util.List;

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/createunresolvedentities/GetFOSSparkJob.java

@@ -0,0 +1,91 @@
+
+package eu.dnetlib.dhp.actionmanager.createunresolvedentities;
+
+import static eu.dnetlib.dhp.actionmanager.Constants.DEFAULT_DELIMITER;
+import static eu.dnetlib.dhp.actionmanager.Constants.isSparkSessionManaged;
+import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
+
+import java.io.Serializable;
+import java.util.Optional;
+
+import org.apache.commons.io.IOUtils;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.spark.SparkConf;
+import org.apache.spark.api.java.function.MapFunction;
+import org.apache.spark.sql.*;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import eu.dnetlib.dhp.actionmanager.createunresolvedentities.model.FOSDataModel;
+import eu.dnetlib.dhp.application.ArgumentApplicationParser;
+
+public class GetFOSSparkJob implements Serializable {
+
+	private static final Logger log = LoggerFactory.getLogger(GetFOSSparkJob.class);
+
+	public static void main(String[] args) throws Exception {
+
+		String jsonConfiguration = IOUtils
+			.toString(
+				GetFOSSparkJob.class
+					.getResourceAsStream(
+						"/eu/dnetlib/dhp/actionmanager/createunresolvedentities/get_input_parameters.json"));
+
+		final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
+
+		parser.parseArgument(args);
+
+		Boolean isSparkSessionManaged = isSparkSessionManaged(parser);
+		log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
+
+		// the path where the original fos csv file is stored
+		final String sourcePath = parser.get("sourcePath");
+		log.info("sourcePath {}", sourcePath);
+
+		// the path where to put the file as json
+		final String outputPath = parser.get("outputPath");
+		log.info("outputPath {}", outputPath);
+
+		final String delimiter = Optional
+			.ofNullable(parser.get("delimiter"))
+			.orElse(DEFAULT_DELIMITER);
+
+		SparkConf sconf = new SparkConf();
+		runWithSparkSession(
+			sconf,
+			isSparkSessionManaged,
+			spark -> {
+				getFOS(
+					spark,
+					sourcePath,
+					outputPath,
+					delimiter);
+			});
+	}
+
+	private static void getFOS(SparkSession spark, String sourcePath, String outputPath, String delimiter) {
+		Dataset<Row> fosData = spark
+			.read()
+			.format("csv")
+			.option("sep", delimiter)
+			.option("inferSchema", "true")
+			.option("header", "true")
+			.option("quotes", "\"")
+			.load(sourcePath);
+
+		fosData.map((MapFunction<Row, FOSDataModel>) r -> {
+			FOSDataModel fosDataModel = new FOSDataModel();
+			fosDataModel.setDoi(r.getString(0).toLowerCase());
+			fosDataModel.setLevel1(r.getString(1));
+			fosDataModel.setLevel2(r.getString(2));
+			fosDataModel.setLevel3(r.getString(3));
+			return fosDataModel;
+		}, Encoders.bean(FOSDataModel.class))
+			.write()
+			.mode(SaveMode.Overwrite)
+			.json(outputPath);
+
+	}
+
+}

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/createunresolvedentities/GetSDGSparkJob.java

@@ -0,0 +1,91 @@
+
+package eu.dnetlib.dhp.actionmanager.createunresolvedentities;
+
+import static eu.dnetlib.dhp.actionmanager.Constants.DEFAULT_DELIMITER;
+import static eu.dnetlib.dhp.actionmanager.Constants.isSparkSessionManaged;
+import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
+
+import java.io.Serializable;
+import java.util.Optional;
+
+import org.apache.commons.io.IOUtils;
+import org.apache.spark.SparkConf;
+import org.apache.spark.api.java.function.FilterFunction;
+import org.apache.spark.api.java.function.MapFunction;
+import org.apache.spark.sql.*;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import eu.dnetlib.dhp.actionmanager.createunresolvedentities.model.FOSDataModel;
+import eu.dnetlib.dhp.actionmanager.createunresolvedentities.model.SDGDataModel;
+import eu.dnetlib.dhp.application.ArgumentApplicationParser;
+
+public class GetSDGSparkJob implements Serializable {
+
+	private static final Logger log = LoggerFactory.getLogger(GetSDGSparkJob.class);
+
+	public static void main(String[] args) throws Exception {
+
+		String jsonConfiguration = IOUtils
+			.toString(
+				GetSDGSparkJob.class
+					.getResourceAsStream(
+						"/eu/dnetlib/dhp/actionmanager/createunresolvedentities/get_input_parameters.json"));
+
+		final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
+
+		parser.parseArgument(args);
+
+		Boolean isSparkSessionManaged = isSparkSessionManaged(parser);
+		log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
+
+		// the path where the original fos csv file is stored
+		final String sourcePath = parser.get("sourcePath");
+		log.info("sourcePath {}", sourcePath);
+
+		// the path where to put the file as json
+		final String outputPath = parser.get("outputPath");
+		log.info("outputPath {}", outputPath);
+
+		final String delimiter = Optional
+			.ofNullable(parser.get("delimiter"))
+			.orElse(DEFAULT_DELIMITER);
+
+		SparkConf sconf = new SparkConf();
+		runWithSparkSession(
+			sconf,
+			isSparkSessionManaged,
+			spark -> {
+				getSDG(
+					spark,
+					sourcePath,
+					outputPath,
+					delimiter);
+			});
+	}
+
+	private static void getSDG(SparkSession spark, String sourcePath, String outputPath, String delimiter) {
+		Dataset<Row> sdgData = spark
+			.read()
+			.format("csv")
+			.option("sep", delimiter)
+			.option("inferSchema", "true")
+			.option("header", "true")
+			.option("quotes", "\"")
+			.load(sourcePath);
+
+		sdgData.map((MapFunction<Row, SDGDataModel>) r -> {
+			SDGDataModel sdgDataModel = new SDGDataModel();
+			sdgDataModel.setDoi(r.getString(0).toLowerCase());
+			sdgDataModel.setSbj(r.getString(1));
+
+			return sdgDataModel;
+		}, Encoders.bean(SDGDataModel.class))
+			.filter((FilterFunction<SDGDataModel>) sdg -> sdg.getSbj() != null)
+			.write()
+			.mode(SaveMode.Overwrite)
+			.json(outputPath);
+
+	}
+
+}

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/createunresolvedentities/PrepareBipFinder.java

@@ -0,0 +1,178 @@
+
+package eu.dnetlib.dhp.actionmanager.createunresolvedentities;
+
+import static eu.dnetlib.dhp.actionmanager.Constants.*;
+import static eu.dnetlib.dhp.actionmanager.Constants.UPDATE_CLASS_NAME;
+import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
+
+import java.io.Serializable;
+import java.util.Arrays;
+import java.util.List;
+import java.util.Optional;
+import java.util.stream.Collectors;
+
+import org.apache.commons.io.IOUtils;
+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.MapFunction;
+import org.apache.spark.sql.Encoders;
+import org.apache.spark.sql.SaveMode;
+import org.apache.spark.sql.SparkSession;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import com.fasterxml.jackson.databind.ObjectMapper;
+
+import eu.dnetlib.dhp.actionmanager.bipmodel.BipDeserialize;
+import eu.dnetlib.dhp.actionmanager.bipmodel.BipScore;
+import eu.dnetlib.dhp.application.ArgumentApplicationParser;
+import eu.dnetlib.dhp.common.HdfsSupport;
+import eu.dnetlib.dhp.schema.common.ModelConstants;
+import eu.dnetlib.dhp.schema.oaf.Instance;
+import eu.dnetlib.dhp.schema.oaf.KeyValue;
+import eu.dnetlib.dhp.schema.oaf.Measure;
+import eu.dnetlib.dhp.schema.oaf.Result;
+import eu.dnetlib.dhp.schema.oaf.utils.CleaningFunctions;
+import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
+import eu.dnetlib.dhp.utils.DHPUtils;
+
+public class PrepareBipFinder implements Serializable {
+
+	private static final Logger log = LoggerFactory.getLogger(PrepareBipFinder.class);
+	private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
+
+	public static void main(String[] args) throws Exception {
+
+		String jsonConfiguration = IOUtils
+			.toString(
+				PrepareBipFinder.class
+					.getResourceAsStream(
+						"/eu/dnetlib/dhp/actionmanager/createunresolvedentities/prepare_parameters.json"));
+
+		final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
+
+		parser.parseArgument(args);
+
+		Boolean isSparkSessionManaged = Optional
+			.ofNullable(parser.get("isSparkSessionManaged"))
+			.map(Boolean::valueOf)
+			.orElse(Boolean.TRUE);
+
+		log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
+
+		final String sourcePath = parser.get("sourcePath");
+		log.info("sourcePath {}: ", sourcePath);
+
+		final String outputPath = parser.get("outputPath");
+		log.info("outputPath {}: ", outputPath);
+
+		SparkConf conf = new SparkConf();
+
+		runWithSparkSession(
+			conf,
+			isSparkSessionManaged,
+			spark -> {
+				HdfsSupport.remove(outputPath, spark.sparkContext().hadoopConfiguration());
+				prepareResults(spark, sourcePath, outputPath);
+			});
+	}
+
+	private static void prepareResults(SparkSession spark, String inputPath, String outputPath) {
+
+		final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
+
+		JavaRDD<BipDeserialize> bipDeserializeJavaRDD = sc
+			.textFile(inputPath)
+			.map(item -> OBJECT_MAPPER.readValue(item, BipDeserialize.class));
+
+		spark
+			.createDataset(bipDeserializeJavaRDD.flatMap(entry -> entry.keySet().stream().map(key -> {
+				BipScore bs = new BipScore();
+				bs.setId(key);
+				bs.setScoreList(entry.get(key));
+
+				return bs;
+			}).collect(Collectors.toList()).iterator()).rdd(), Encoders.bean(BipScore.class))
+			.map((MapFunction<BipScore, Result>) v -> {
+				Result r = new Result();
+				final String cleanedPid = CleaningFunctions.normalizePidValue(DOI, v.getId());
+
+				r.setId(DHPUtils.generateUnresolvedIdentifier(v.getId(), DOI));
+				Instance inst = new Instance();
+				inst.setMeasures(getMeasure(v));
+
+				inst
+					.setPid(
+						Arrays
+							.asList(
+								OafMapperUtils
+									.structuredProperty(
+										cleanedPid,
+										OafMapperUtils
+											.qualifier(
+												DOI, DOI_CLASSNAME,
+												ModelConstants.DNET_PID_TYPES,
+												ModelConstants.DNET_PID_TYPES),
+										null)));
+				r.setInstance(Arrays.asList(inst));
+				r
+					.setDataInfo(
+						OafMapperUtils
+							.dataInfo(
+								false, null, true,
+								false,
+								OafMapperUtils
+									.qualifier(
+										ModelConstants.PROVENANCE_ENRICH,
+										null,
+										ModelConstants.DNET_PROVENANCE_ACTIONS,
+										ModelConstants.DNET_PROVENANCE_ACTIONS),
+								null));
+				return r;
+			}, Encoders.bean(Result.class))
+			.write()
+			.mode(SaveMode.Overwrite)
+			.option("compression", "gzip")
+			.json(outputPath + "/bip");
+	}
+
+	private static List<Measure> getMeasure(BipScore value) {
+		return value
+			.getScoreList()
+			.stream()
+			.map(score -> {
+				Measure m = new Measure();
+				m.setId(score.getId());
+				m
+					.setUnit(
+						score
+							.getUnit()
+							.stream()
+							.map(unit -> {
+								KeyValue kv = new KeyValue();
+								kv.setValue(unit.getValue());
+								kv.setKey(unit.getKey());
+								kv
+									.setDataInfo(
+										OafMapperUtils
+											.dataInfo(
+												false,
+												UPDATE_DATA_INFO_TYPE,
+												true,
+												false,
+												OafMapperUtils
+													.qualifier(
+														UPDATE_MEASURE_BIP_CLASS_ID,
+														UPDATE_CLASS_NAME,
+														ModelConstants.DNET_PROVENANCE_ACTIONS,
+														ModelConstants.DNET_PROVENANCE_ACTIONS),
+												""));
+								return kv;
+							})
+							.collect(Collectors.toList()));
+				return m;
+			})
+			.collect(Collectors.toList());
+	}
+}

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/createunresolvedentities/PrepareFOSSparkJob.java

@@ -0,0 +1,99 @@
+
+package eu.dnetlib.dhp.actionmanager.createunresolvedentities;
+
+import static eu.dnetlib.dhp.actionmanager.Constants.*;
+import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
+
+import java.io.Serializable;
+import java.util.*;
+import java.util.stream.Collectors;
+
+import org.apache.commons.io.IOUtils;
+import org.apache.spark.SparkConf;
+import org.apache.spark.api.java.function.MapFunction;
+import org.apache.spark.api.java.function.MapGroupsFunction;
+import org.apache.spark.sql.Dataset;
+import org.apache.spark.sql.Encoders;
+import org.apache.spark.sql.SaveMode;
+import org.apache.spark.sql.SparkSession;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import eu.dnetlib.dhp.actionmanager.createunresolvedentities.model.FOSDataModel;
+import eu.dnetlib.dhp.application.ArgumentApplicationParser;
+import eu.dnetlib.dhp.schema.oaf.Result;
+import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
+import eu.dnetlib.dhp.utils.DHPUtils;
+
+public class PrepareFOSSparkJob implements Serializable {
+	private static final Logger log = LoggerFactory.getLogger(PrepareFOSSparkJob.class);
+
+	public static void main(String[] args) throws Exception {
+
+		String jsonConfiguration = IOUtils
+			.toString(
+				PrepareFOSSparkJob.class
+					.getResourceAsStream(
+						"/eu/dnetlib/dhp/actionmanager/createunresolvedentities/prepare_parameters.json"));
+
+		final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
+
+		parser.parseArgument(args);
+
+		Boolean isSparkSessionManaged = isSparkSessionManaged(parser);
+		log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
+
+		String sourcePath = parser.get("sourcePath");
+		log.info("sourcePath: {}", sourcePath);
+
+		final String outputPath = parser.get("outputPath");
+		log.info("outputPath: {}", outputPath);
+
+		SparkConf conf = new SparkConf();
+		runWithSparkSession(
+			conf,
+			isSparkSessionManaged,
+			spark -> {
+				distributeFOSdois(
+					spark,
+					sourcePath,
+
+					outputPath);
+			});
+	}
+
+	private static void distributeFOSdois(SparkSession spark, String sourcePath, String outputPath) {
+		Dataset<FOSDataModel> fosDataset = readPath(spark, sourcePath, FOSDataModel.class);
+
+		fosDataset
+			.groupByKey((MapFunction<FOSDataModel, String>) v -> v.getDoi().toLowerCase(), Encoders.STRING())
+			.mapGroups((MapGroupsFunction<String, FOSDataModel, Result>) (k, it) -> {
+				Result r = new Result();
+				FOSDataModel first = it.next();
+				r.setId(DHPUtils.generateUnresolvedIdentifier(k, DOI));
+				HashSet<String> level1 = new HashSet<>();
+				HashSet<String> level2 = new HashSet<>();
+				HashSet<String> level3 = new HashSet<>();
+				addLevels(level1, level2, level3, first);
+				it.forEachRemaining(v -> addLevels(level1, level2, level3, v));
+				List<StructuredProperty> sbjs = new ArrayList<>();
+				level1.forEach(l -> sbjs.add(getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID)));
+				level2.forEach(l -> sbjs.add(getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID)));
+				level3.forEach(l -> sbjs.add(getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID)));
+				r.setSubject(sbjs);
+				return r;
+			}, Encoders.bean(Result.class))
+			.write()
+			.mode(SaveMode.Overwrite)
+			.option("compression", "gzip")
+			.json(outputPath + "/fos");
+	}
+
+	private static void addLevels(HashSet<String> level1, HashSet<String> level2, HashSet<String> level3,
+		FOSDataModel first) {
+		level1.add(first.getLevel1());
+		level2.add(first.getLevel2());
+		level3.add(first.getLevel3());
+	}
+
+}

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/createunresolvedentities/PrepareSDGSparkJob.java

@@ -0,0 +1,89 @@
+
+package eu.dnetlib.dhp.actionmanager.createunresolvedentities;
+
+import static eu.dnetlib.dhp.actionmanager.Constants.*;
+import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
+
+import java.io.Serializable;
+import java.util.ArrayList;
+import java.util.List;
+
+import org.apache.commons.io.IOUtils;
+import org.apache.spark.SparkConf;
+import org.apache.spark.api.java.function.MapFunction;
+import org.apache.spark.api.java.function.MapGroupsFunction;
+import org.apache.spark.sql.Dataset;
+import org.apache.spark.sql.Encoders;
+import org.apache.spark.sql.SaveMode;
+import org.apache.spark.sql.SparkSession;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import eu.dnetlib.dhp.actionmanager.createunresolvedentities.model.SDGDataModel;
+import eu.dnetlib.dhp.application.ArgumentApplicationParser;
+import eu.dnetlib.dhp.schema.oaf.Result;
+import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
+import eu.dnetlib.dhp.utils.DHPUtils;
+
+public class PrepareSDGSparkJob implements Serializable {
+	private static final Logger log = LoggerFactory.getLogger(PrepareSDGSparkJob.class);
+
+	public static void main(String[] args) throws Exception {
+
+		String jsonConfiguration = IOUtils
+			.toString(
+				PrepareSDGSparkJob.class
+					.getResourceAsStream(
+						"/eu/dnetlib/dhp/actionmanager/createunresolvedentities/prepare_parameters.json"));
+
+		final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
+
+		parser.parseArgument(args);
+
+		Boolean isSparkSessionManaged = isSparkSessionManaged(parser);
+		log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
+
+		String sourcePath = parser.get("sourcePath");
+		log.info("sourcePath: {}", sourcePath);
+
+		final String outputPath = parser.get("outputPath");
+		log.info("outputPath: {}", outputPath);
+
+		SparkConf conf = new SparkConf();
+		runWithSparkSession(
+			conf,
+			isSparkSessionManaged,
+			spark -> {
+				doPrepare(
+					spark,
+					sourcePath,
+
+					outputPath);
+			});
+	}
+
+	private static void doPrepare(SparkSession spark, String sourcePath, String outputPath) {
+		Dataset<SDGDataModel> sdgDataset = readPath(spark, sourcePath, SDGDataModel.class);
+
+		sdgDataset
+			.groupByKey((MapFunction<SDGDataModel, String>) r -> r.getDoi().toLowerCase(), Encoders.STRING())
+			.mapGroups((MapGroupsFunction<String, SDGDataModel, Result>) (k, it) -> {
+				Result r = new Result();
+				r.setId(DHPUtils.generateUnresolvedIdentifier(k, DOI));
+				SDGDataModel first = it.next();
+				List<StructuredProperty> sbjs = new ArrayList<>();
+				sbjs.add(getSubject(first.getSbj(), SDG_CLASS_ID, SDG_CLASS_NAME, UPDATE_SUBJECT_SDG_CLASS_ID));
+				it
+					.forEachRemaining(
+						s -> sbjs
+							.add(getSubject(s.getSbj(), SDG_CLASS_ID, SDG_CLASS_NAME, UPDATE_SUBJECT_SDG_CLASS_ID)));
+				r.setSubject(sbjs);
+				return r;
+			}, Encoders.bean(Result.class))
+			.write()
+			.mode(SaveMode.Overwrite)
+			.option("compression", "gzip")
+			.json(outputPath + "/sdg");
+	}
+
+}

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/createunresolvedentities/SparkSaveUnresolved.java

@@ -0,0 +1,79 @@
+
+package eu.dnetlib.dhp.actionmanager.createunresolvedentities;
+
+import static eu.dnetlib.dhp.actionmanager.Constants.*;
+import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
+
+import java.io.Serializable;
+
+import org.apache.commons.io.IOUtils;
+import org.apache.spark.SparkConf;
+import org.apache.spark.api.java.function.MapFunction;
+import org.apache.spark.api.java.function.MapGroupsFunction;
+import org.apache.spark.sql.Encoders;
+import org.apache.spark.sql.SaveMode;
+import org.apache.spark.sql.SparkSession;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import eu.dnetlib.dhp.application.ArgumentApplicationParser;
+import eu.dnetlib.dhp.schema.oaf.Result;
+
+public class SparkSaveUnresolved implements Serializable {
+	private static final Logger log = LoggerFactory.getLogger(SparkSaveUnresolved.class);
+
+	public static void main(String[] args) throws Exception {
+
+		String jsonConfiguration = IOUtils
+			.toString(
+				PrepareFOSSparkJob.class
+					.getResourceAsStream(
+						"/eu/dnetlib/dhp/actionmanager/createunresolvedentities/produce_unresolved_parameters.json"));
+
+		final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
+
+		parser.parseArgument(args);
+
+		Boolean isSparkSessionManaged = isSparkSessionManaged(parser);
+		log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
+
+		String sourcePath = parser.get("sourcePath");
+		log.info("sourcePath: {}", sourcePath);
+
+		final String outputPath = parser.get("outputPath");
+		log.info("outputPath: {}", outputPath);
+
+		SparkConf conf = new SparkConf();
+		runWithSparkSession(
+			conf,
+			isSparkSessionManaged,
+			spark -> {
+				saveUnresolved(
+					spark,
+					sourcePath,
+
+					outputPath);
+			});
+	}
+
+	private static void saveUnresolved(SparkSession spark, String sourcePath, String outputPath) {
+
+		spark
+			.read()
+			.textFile(sourcePath + "/*")
+			.map(
+				(MapFunction<String, Result>) l -> OBJECT_MAPPER.readValue(l, Result.class),
+				Encoders.bean(Result.class))
+			.groupByKey((MapFunction<Result, String>) Result::getId, Encoders.STRING())
+			.mapGroups((MapGroupsFunction<String, Result, Result>) (k, it) -> {
+				Result ret = it.next();
+				it.forEachRemaining(r -> ret.mergeFrom(r));
+				return ret;
+			}, Encoders.bean(Result.class))
+			.write()
+			.mode(SaveMode.Overwrite)
+			.option("compression", "gzip")
+			.json(outputPath);
+	}
+
+}

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/createunresolvedentities/model/FOSDataModel.java

@@ -0,0 +1,71 @@
+
+package eu.dnetlib.dhp.actionmanager.createunresolvedentities.model;
+
+import java.io.Serializable;
+
+import com.opencsv.bean.CsvBindByPosition;
+
+public class FOSDataModel implements Serializable {
+	@CsvBindByPosition(position = 0)
+//    @CsvBindByName(column = "doi")
+	private String doi;
+
+	@CsvBindByPosition(position = 1)
+//    @CsvBindByName(column = "level1")
+	private String level1;
+
+	@CsvBindByPosition(position = 2)
+//    @CsvBindByName(column = "level2")
+	private String level2;
+
+	@CsvBindByPosition(position = 3)
+//    @CsvBindByName(column = "level3")
+	private String level3;
+
+	public FOSDataModel() {
+
+	}
+
+	public FOSDataModel(String doi, String level1, String level2, String level3) {
+		this.doi = doi;
+		this.level1 = level1;
+		this.level2 = level2;
+		this.level3 = level3;
+	}
+
+	public static FOSDataModel newInstance(String d, String level1, String level2, String level3) {
+		return new FOSDataModel(d, level1, level2, level3);
+	}
+
+	public String getDoi() {
+		return doi;
+	}
+
+	public void setDoi(String doi) {
+		this.doi = doi;
+	}
+
+	public String getLevel1() {
+		return level1;
+	}
+
+	public void setLevel1(String level1) {
+		this.level1 = level1;
+	}
+
+	public String getLevel2() {
+		return level2;
+	}
+
+	public void setLevel2(String level2) {
+		this.level2 = level2;
+	}
+
+	public String getLevel3() {
+		return level3;
+	}
+
+	public void setLevel3(String level3) {
+		this.level3 = level3;
+	}
+}

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/createunresolvedentities/model/SDGDataModel.java

@@ -0,0 +1,47 @@
+
+package eu.dnetlib.dhp.actionmanager.createunresolvedentities.model;
+
+import java.io.Serializable;
+
+import com.opencsv.bean.CsvBindByPosition;
+
+public class SDGDataModel implements Serializable {
+
+	@CsvBindByPosition(position = 0)
+//    @CsvBindByName(column = "doi")
+	private String doi;
+
+	@CsvBindByPosition(position = 1)
+//    @CsvBindByName(column = "sdg")
+	private String sbj;
+
+	public SDGDataModel() {
+
+	}
+
+	public SDGDataModel(String doi, String sbj) {
+		this.doi = doi;
+		this.sbj = sbj;
+
+	}
+
+	public static SDGDataModel newInstance(String d, String sbj) {
+		return new SDGDataModel(d, sbj);
+	}
+
+	public String getDoi() {
+		return doi;
+	}
+
+	public void setDoi(String doi) {
+		this.doi = doi;
+	}
+
+	public String getSbj() {
+		return sbj;
+	}
+
+	public void setSbj(String sbj) {
+		this.sbj = sbj;
+	}
+}

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/datacite/DataciteToOAFTransformation.scala

@@ -1,607 +0,0 @@
-package eu.dnetlib.dhp.actionmanager.datacite
-
-import com.fasterxml.jackson.databind.ObjectMapper
-import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup
-import eu.dnetlib.dhp.schema.action.AtomicAction
-import eu.dnetlib.dhp.schema.common.ModelConstants
-import eu.dnetlib.dhp.schema.oaf.utils.{IdentifierFactory, OafMapperUtils}
-import eu.dnetlib.dhp.schema.oaf.{AccessRight, Author, DataInfo, Instance, KeyValue, Oaf, OtherResearchProduct, Publication, Qualifier, Relation, Result, Software, StructuredProperty, Dataset => OafDataset}
-import eu.dnetlib.dhp.utils.DHPUtils
-import org.apache.commons.lang3.StringUtils
-import org.json4s.DefaultFormats
-import org.json4s.JsonAST.{JField, JObject, JString}
-import org.json4s.jackson.JsonMethods.parse
-
-import java.nio.charset.CodingErrorAction
-import java.text.SimpleDateFormat
-import java.time.LocalDate
-import java.time.chrono.ThaiBuddhistDate
-import java.time.format.DateTimeFormatter
-import java.util.regex.Pattern
-import java.util.{Date, Locale}
-import scala.collection.JavaConverters._
-import scala.io.{Codec, Source}
-import scala.language.postfixOps
-
-case class DataciteType(doi: String, timestamp: Long, isActive: Boolean, json: String) {}
-
-case class RelatedIdentifierType(relationType: String, relatedIdentifier: String, relatedIdentifierType: String) {}
-
-case class NameIdentifiersType(nameIdentifierScheme: Option[String], schemeUri: Option[String], nameIdentifier: Option[String]) {}
-
-case class CreatorType(nameType: Option[String], nameIdentifiers: Option[List[NameIdentifiersType]], name: Option[String], familyName: Option[String], givenName: Option[String], affiliation: Option[List[String]]) {}
-
-case class TitleType(title: Option[String], titleType: Option[String], lang: Option[String]) {}
-
-case class SubjectType(subject: Option[String], subjectScheme: Option[String]) {}
-
-case class DescriptionType(descriptionType: Option[String], description: Option[String]) {}
-
-case class FundingReferenceType(funderIdentifierType: Option[String], awardTitle: Option[String], awardUri: Option[String], funderName: Option[String], funderIdentifier: Option[String], awardNumber: Option[String]) {}
-
-case class DateType(date: Option[String], dateType: Option[String]) {}
-
-case class HostedByMapType(openaire_id: String, datacite_name: String, official_name: String, similarity: Option[Float]) {}
-
-object DataciteToOAFTransformation {
-
-  val REL_TYPE_VALUE:String = "resultResult"
-  val DATE_RELATION_KEY = "RelationDate"
-
-  val subRelTypeMapping: Map[String,(String,String)] = Map(
-    "References" ->("IsReferencedBy","relationship"),
-    "IsSupplementTo" ->("IsSupplementedBy","supplement"),
-    "IsPartOf" ->("HasPart","part"),
-    "HasPart" ->("IsPartOf","part"),
-    "IsVersionOf" ->("HasVersion","version"),
-    "HasVersion" ->("IsVersionOf","version"),
-    "IsIdenticalTo" ->("IsIdenticalTo","relationship"),
-    "IsPreviousVersionOf" ->("IsNewVersionOf","version"),
-    "IsContinuedBy" ->("Continues","relationship"),
-    "Continues" ->("IsContinuedBy","relationship"),
-    "IsNewVersionOf" ->("IsPreviousVersionOf","version"),
-    "IsSupplementedBy" ->("IsSupplementTo","supplement"),
-    "IsDocumentedBy" ->("Documents","relationship"),
-    "IsSourceOf" ->("IsDerivedFrom","relationship"),
-    "Cites" ->("IsCitedBy","citation"),
-    "IsCitedBy" ->("Cites","citation"),
-    "IsDerivedFrom" ->("IsSourceOf","relationship"),
-    "IsVariantFormOf" ->("IsDerivedFrom","version"),
-    "IsReferencedBy" ->("References","relationship"),
-    "IsObsoletedBy" ->("IsNewVersionOf","version"),
-    "Reviews" ->("IsReviewedBy","review"),
-    "Documents" ->("IsDocumentedBy","relationship"),
-    "IsCompiledBy" ->("Compiles","relationship"),
-    "Compiles" ->("IsCompiledBy","relationship"),
-    "IsReviewedBy" ->("Reviews","review")
-  )
-
-  implicit val codec: Codec = Codec("UTF-8")
-  codec.onMalformedInput(CodingErrorAction.REPLACE)
-  codec.onUnmappableCharacter(CodingErrorAction.REPLACE)
-
-  val DOI_CLASS = "doi"
-  val SUBJ_CLASS = "keywords"
-
-
-  val j_filter: List[String] = {
-    val s = Source.fromInputStream(getClass.getResourceAsStream("datacite_filter")).mkString
-    s.lines.toList
-  }
-
-  val mapper = new ObjectMapper()
-  val unknown_repository: HostedByMapType = HostedByMapType(ModelConstants.UNKNOWN_REPOSITORY_ORIGINALID, ModelConstants.UNKNOWN_REPOSITORY.getValue, ModelConstants.UNKNOWN_REPOSITORY.getValue, Some(1.0F))
-
-  val dataInfo: DataInfo = generateDataInfo("0.9")
-  val DATACITE_COLLECTED_FROM: KeyValue = OafMapperUtils.keyValue(ModelConstants.DATACITE_ID, "Datacite")
-
-  val hostedByMap: Map[String, HostedByMapType] = {
-    val s = Source.fromInputStream(getClass.getResourceAsStream("hostedBy_map.json")).mkString
-    implicit lazy val formats: DefaultFormats.type = org.json4s.DefaultFormats
-    lazy val json: org.json4s.JValue = parse(s)
-    json.extract[Map[String, HostedByMapType]]
-  }
-
-  val df_en: DateTimeFormatter = DateTimeFormatter.ofPattern("[MM-dd-yyyy][MM/dd/yyyy][dd-MM-yy][dd-MMM-yyyy][dd/MMM/yyyy][dd-MMM-yy][dd/MMM/yy][dd-MM-yy][dd/MM/yy][dd-MM-yyyy][dd/MM/yyyy][yyyy-MM-dd][yyyy/MM/dd]", Locale.ENGLISH)
-  val df_it: DateTimeFormatter = DateTimeFormatter.ofPattern("[dd-MM-yyyy][dd/MM/yyyy]", Locale.ITALIAN)
-
-  val funder_regex: List[(Pattern, String)] = List(
-    (Pattern.compile("(info:eu-repo/grantagreement/ec/h2020/)(\\d\\d\\d\\d\\d\\d)(.*)", Pattern.MULTILINE | Pattern.CASE_INSENSITIVE), "40|corda__h2020::"),
-    (Pattern.compile("(info:eu-repo/grantagreement/ec/fp7/)(\\d\\d\\d\\d\\d\\d)(.*)", Pattern.MULTILINE | Pattern.CASE_INSENSITIVE), "40|corda_______::")
-
-  )
-
-  val Date_regex: List[Pattern] = List(
-    //Y-M-D
-    Pattern.compile("(18|19|20)\\d\\d([- /.])(0[1-9]|1[012])\\2(0[1-9]|[12][0-9]|3[01])", Pattern.MULTILINE),
-    //M-D-Y
-    Pattern.compile("((0[1-9]|1[012])|([1-9]))([- /.])(0[1-9]|[12][0-9]|3[01])([- /.])(18|19|20)?\\d\\d", Pattern.MULTILINE),
-    //D-M-Y
-    Pattern.compile("(?:(?:31(/|-|\\.)(?:0?[13578]|1[02]|(?:Jan|Mar|May|Jul|Aug|Oct|Dec)))\\1|(?:(?:29|30)(/|-|\\.)(?:0?[1,3-9]|1[0-2]|(?:Jan|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec))\\2))(?:(?:1[6-9]|[2-9]\\d)?\\d{2})|(?:29(/|-|\\.)(?:0?2|(?:Feb))\\3(?:(?:(?:1[6-9]|[2-9]\\d)?(?:0[48]|[2468][048]|[13579][26])|(?:(?:16|[2468][048]|[3579][26])00))))|(?:0?[1-9]|1\\d|2[0-8])(/|-|\\.)(?:(?:0?[1-9]|(?:Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep))|(?:1[0-2]|(?:Oct|Nov|Dec)))\\4(?:(?:1[6-9]|[2-9]\\d)?\\d{2})", Pattern.MULTILINE),
-    //Y
-    Pattern.compile("(19|20)\\d\\d", Pattern.MULTILINE)
-  )
-
-
-  def filter_json(json: String): Boolean = {
-    j_filter.exists(f => json.contains(f))
-  }
-
-  def toActionSet(item: Oaf): (String, String) = {
-    val mapper = new ObjectMapper()
-
-    item match {
-      case dataset: OafDataset =>
-        val a: AtomicAction[OafDataset] = new AtomicAction[OafDataset]
-        a.setClazz(classOf[OafDataset])
-        a.setPayload(dataset)
-        (dataset.getClass.getCanonicalName, mapper.writeValueAsString(a))
-      case publication: Publication =>
-        val a: AtomicAction[Publication] = new AtomicAction[Publication]
-        a.setClazz(classOf[Publication])
-        a.setPayload(publication)
-        (publication.getClass.getCanonicalName, mapper.writeValueAsString(a))
-      case software: Software =>
-        val a: AtomicAction[Software] = new AtomicAction[Software]
-        a.setClazz(classOf[Software])
-        a.setPayload(software)
-        (software.getClass.getCanonicalName, mapper.writeValueAsString(a))
-      case orp: OtherResearchProduct =>
-        val a: AtomicAction[OtherResearchProduct] = new AtomicAction[OtherResearchProduct]
-        a.setClazz(classOf[OtherResearchProduct])
-        a.setPayload(orp)
-        (orp.getClass.getCanonicalName, mapper.writeValueAsString(a))
-
-      case relation: Relation =>
-        val a: AtomicAction[Relation] = new AtomicAction[Relation]
-        a.setClazz(classOf[Relation])
-        a.setPayload(relation)
-        (relation.getClass.getCanonicalName, mapper.writeValueAsString(a))
-      case _ =>
-        null
-    }
-
-  }
-
-
-  def embargo_end(embargo_end_date: String): Boolean = {
-    val dt = LocalDate.parse(embargo_end_date, DateTimeFormatter.ofPattern("[yyyy-MM-dd]"))
-    val td = LocalDate.now()
-    td.isAfter(dt)
-  }
-
-
-  def extract_date(input: String): Option[String] = {
-    val d = Date_regex.map(pattern => {
-      val matcher = pattern.matcher(input)
-      if (matcher.find())
-        matcher.group(0)
-      else
-        null
-    }
-    ).find(s => s != null)
-
-    if (d.isDefined) {
-      val a_date = if (d.get.length == 4) s"01-01-${d.get}" else d.get
-      try {
-        return Some(LocalDate.parse(a_date, df_en).toString)
-      } catch {
-        case _: Throwable => try {
-          return Some(LocalDate.parse(a_date, df_it).toString)
-        } catch {
-          case _: Throwable =>
-            return None
-        }
-      }
-    }
-    d
-  }
-
-  def fix_thai_date(input:String, format:String) :String = {
-    try {
-      val a_date = LocalDate.parse(input,DateTimeFormatter.ofPattern(format))
-      val d = ThaiBuddhistDate.of(a_date.getYear, a_date.getMonth.getValue, a_date.getDayOfMonth)
-      LocalDate.from(d).toString
-    } catch {
-      case _: Throwable => ""
-    }
-  }
-  def getTypeQualifier(resourceType: String, resourceTypeGeneral: String, schemaOrg: String, vocabularies: VocabularyGroup): (Qualifier, Qualifier) = {
-    if (resourceType != null && resourceType.nonEmpty) {
-      val typeQualifier = vocabularies.getSynonymAsQualifier(ModelConstants.DNET_PUBLICATION_RESOURCE, resourceType)
-      if (typeQualifier != null)
-        return (typeQualifier, vocabularies.getSynonymAsQualifier(ModelConstants.DNET_RESULT_TYPOLOGIES, typeQualifier.getClassid))
-    }
-    if (schemaOrg != null && schemaOrg.nonEmpty) {
-      val typeQualifier = vocabularies.getSynonymAsQualifier(ModelConstants.DNET_PUBLICATION_RESOURCE, schemaOrg)
-      if (typeQualifier != null)
-        return (typeQualifier, vocabularies.getSynonymAsQualifier(ModelConstants.DNET_RESULT_TYPOLOGIES, typeQualifier.getClassid))
-
-    }
-    if (resourceTypeGeneral != null && resourceTypeGeneral.nonEmpty) {
-      val typeQualifier = vocabularies.getSynonymAsQualifier(ModelConstants.DNET_PUBLICATION_RESOURCE, resourceTypeGeneral)
-      if (typeQualifier != null)
-        return (typeQualifier, vocabularies.getSynonymAsQualifier(ModelConstants.DNET_RESULT_TYPOLOGIES, typeQualifier.getClassid))
-
-    }
-    null
-  }
-
-
-  def getResult(resourceType: String, resourceTypeGeneral: String, schemaOrg: String, vocabularies: VocabularyGroup): Result = {
-    val typeQualifiers: (Qualifier, Qualifier) = getTypeQualifier(resourceType, resourceTypeGeneral, schemaOrg, vocabularies)
-    if (typeQualifiers == null)
-      return null
-    val i = new Instance
-    i.setInstancetype(typeQualifiers._1)
-    typeQualifiers._2.getClassname match {
-      case "dataset" =>
-        val r = new OafDataset
-        r.setInstance(List(i).asJava)
-        return r
-      case "publication" =>
-        val r = new Publication
-        r.setInstance(List(i).asJava)
-        return r
-      case "software" =>
-        val r = new Software
-        r.setInstance(List(i).asJava)
-        return r
-      case "other" =>
-        val r = new OtherResearchProduct
-        r.setInstance(List(i).asJava)
-        return r
-    }
-    null
-  }
-
-
-  def available_date(input: String): Boolean = {
-
-    implicit lazy val formats: DefaultFormats.type = org.json4s.DefaultFormats
-    lazy val json: org.json4s.JValue = parse(input)
-    val l: List[String] = for {
-      JObject(dates) <- json \\ "dates"
-      JField("dateType", JString(dateTypes)) <- dates
-    } yield dateTypes
-
-    l.exists(p => p.equalsIgnoreCase("available"))
-
-  }
-
-
-  /**
-   * As describe in ticket #6377
-   * when the result come from figshare we need to remove subject
-   * and set Access rights OPEN.
-   *
-   * @param r
-   */
-  def fix_figshare(r: Result): Unit = {
-
-    if (r.getInstance() != null) {
-      val hosted_by_figshare = r.getInstance().asScala.exists(i => i.getHostedby != null && "figshare".equalsIgnoreCase(i.getHostedby.getValue))
-      if (hosted_by_figshare) {
-        r.getInstance().asScala.foreach(i => i.setAccessright(ModelConstants.OPEN_ACCESS_RIGHT()))
-        val l: List[StructuredProperty] = List()
-        r.setSubject(l.asJava)
-      }
-    }
-
-
-  }
-
-
-  def createDNetTargetIdentifier(pid: String, pidType: String, idPrefix: String): String = {
-    val f_part = s"$idPrefix|${pidType.toLowerCase}".padTo(15, '_')
-    s"$f_part::${IdentifierFactory.md5(pid.toLowerCase)}"
-  }
-
-  def generateOAFDate(dt: String, q: Qualifier): StructuredProperty = {
-    OafMapperUtils.structuredProperty(dt, q, null)
-  }
-
-  def generateRelation(sourceId: String, targetId: String, relClass: String, cf: KeyValue, di: DataInfo): Relation = {
-
-    val r = new Relation
-    r.setSource(sourceId)
-    r.setTarget(targetId)
-    r.setRelType(ModelConstants.RESULT_PROJECT)
-    r.setRelClass(relClass)
-    r.setSubRelType(ModelConstants.OUTCOME)
-    r.setCollectedfrom(List(cf).asJava)
-    r.setDataInfo(di)
-    r
-
-
-  }
-
-  def get_projectRelation(awardUri: String, sourceId: String): List[Relation] = {
-    val match_pattern = funder_regex.find(s => s._1.matcher(awardUri).find())
-
-    if (match_pattern.isDefined) {
-      val m = match_pattern.get._1
-      val p = match_pattern.get._2
-      val grantId = m.matcher(awardUri).replaceAll("$2")
-      val targetId = s"$p${DHPUtils.md5(grantId)}"
-      List(
-        generateRelation(sourceId, targetId, "isProducedBy", DATACITE_COLLECTED_FROM, dataInfo),
-        generateRelation(targetId, sourceId, "produces", DATACITE_COLLECTED_FROM, dataInfo)
-      )
-    }
-    else
-      List()
-
-  }
-
-
-  def generateOAF(input: String, ts: Long, dateOfCollection: Long, vocabularies: VocabularyGroup, exportLinks: Boolean): List[Oaf] = {
-    if (filter_json(input))
-      return List()
-
-    implicit lazy val formats: DefaultFormats.type = org.json4s.DefaultFormats
-    lazy val json = parse(input)
-
-    val resourceType = (json \ "attributes" \ "types" \ "resourceType").extractOrElse[String](null)
-    val resourceTypeGeneral = (json \ "attributes" \ "types" \ "resourceTypeGeneral").extractOrElse[String](null)
-    val schemaOrg = (json \ "attributes" \ "types" \ "schemaOrg").extractOrElse[String](null)
-
-    val doi = (json \ "attributes" \ "doi").extract[String]
-    if (doi.isEmpty)
-      return List()
-
-    //Mapping type based on vocabularies dnet:publication_resource and dnet:result_typologies
-    val result = getResult(resourceType, resourceTypeGeneral, schemaOrg, vocabularies)
-    if (result == null)
-      return List()
-
-
-    val doi_q = OafMapperUtils.qualifier("doi", "doi", ModelConstants.DNET_PID_TYPES, ModelConstants.DNET_PID_TYPES)
-    val pid = OafMapperUtils.structuredProperty(doi, doi_q, dataInfo)
-    result.setPid(List(pid).asJava)
-    result.setId(OafMapperUtils.createOpenaireId(50, s"datacite____::$doi", true))
-    result.setOriginalId(List(doi).asJava)
-
-    val d = new Date(dateOfCollection * 1000)
-    val ISO8601FORMAT = new SimpleDateFormat("yyyy-MM-dd'T'HH:mm:ssZ", Locale.US)
-
-
-    result.setDateofcollection(ISO8601FORMAT.format(d))
-    result.setDateoftransformation(ISO8601FORMAT.format(d))
-    result.setDataInfo(dataInfo)
-
-    val creators = (json \\ "creators").extractOrElse[List[CreatorType]](List())
-
-
-    val authors = creators.zipWithIndex.map { case (c, idx) =>
-      val a = new Author
-      a.setFullname(c.name.orNull)
-      a.setName(c.givenName.orNull)
-      a.setSurname(c.familyName.orNull)
-      if (c.nameIdentifiers != null && c.nameIdentifiers.isDefined && c.nameIdentifiers.get != null) {
-        a.setPid(c.nameIdentifiers.get.map(ni => {
-          val q = if (ni.nameIdentifierScheme.isDefined) vocabularies.getTermAsQualifier(ModelConstants.DNET_PID_TYPES, ni.nameIdentifierScheme.get.toLowerCase()) else null
-          if (ni.nameIdentifier != null && ni.nameIdentifier.isDefined) {
-            OafMapperUtils.structuredProperty(ni.nameIdentifier.get, q, dataInfo)
-          }
-          else
-            null
-
-        }
-        )
-          .asJava)
-      }
-      if (c.affiliation.isDefined)
-        a.setAffiliation(c.affiliation.get.filter(af => af.nonEmpty).map(af => OafMapperUtils.field(af, dataInfo)).asJava)
-      a.setRank(idx + 1)
-      a
-    }
-
-
-    val titles: List[TitleType] = (json \\ "titles").extractOrElse[List[TitleType]](List())
-
-    result.setTitle(titles.filter(t => t.title.nonEmpty).map(t => {
-      if (t.titleType.isEmpty) {
-        OafMapperUtils.structuredProperty(t.title.get, ModelConstants.MAIN_TITLE_QUALIFIER, null)
-      } else {
-        OafMapperUtils.structuredProperty(t.title.get, t.titleType.get, t.titleType.get, ModelConstants.DNET_DATACITE_TITLE, ModelConstants.DNET_DATACITE_TITLE, null)
-      }
-    }).asJava)
-
-    if (authors == null || authors.isEmpty || !authors.exists(a => a != null))
-      return List()
-    result.setAuthor(authors.asJava)
-
-    val dates = (json \\ "dates").extract[List[DateType]]
-    val publication_year = (json \\ "publicationYear").extractOrElse[String](null)
-
-    val i_date = dates
-      .filter(d => d.date.isDefined && d.dateType.isDefined)
-      .find(d => d.dateType.get.equalsIgnoreCase("issued"))
-      .map(d => extract_date(d.date.get))
-    val a_date: Option[String] = dates
-      .filter(d => d.date.isDefined && d.dateType.isDefined && d.dateType.get.equalsIgnoreCase("available"))
-      .map(d => extract_date(d.date.get))
-      .find(d => d != null && d.isDefined)
-      .map(d => d.get)
-
-    if (a_date.isDefined) {
-      if(doi.startsWith("10.14457"))
-        result.setEmbargoenddate(OafMapperUtils.field(fix_thai_date(a_date.get,"[yyyy-MM-dd]"), null))
-      else
-        result.setEmbargoenddate(OafMapperUtils.field(a_date.get, null))
-    }
-    if (i_date.isDefined && i_date.get.isDefined) {
-      if(doi.startsWith("10.14457")) {
-        result.setDateofacceptance(OafMapperUtils.field(fix_thai_date(i_date.get.get,"[yyyy-MM-dd]"), null))
-        result.getInstance().get(0).setDateofacceptance(OafMapperUtils.field(fix_thai_date(i_date.get.get,"[yyyy-MM-dd]"), null))
-      }
-      else {
-        result.setDateofacceptance(OafMapperUtils.field(i_date.get.get, null))
-        result.getInstance().get(0).setDateofacceptance(OafMapperUtils.field(i_date.get.get, null))
-      }
-    }
-    else if (publication_year != null) {
-      if(doi.startsWith("10.14457")) {
-        result.setDateofacceptance(OafMapperUtils.field(fix_thai_date(s"01-01-$publication_year","[dd-MM-yyyy]"), null))
-        result.getInstance().get(0).setDateofacceptance(OafMapperUtils.field(fix_thai_date(s"01-01-$publication_year","[dd-MM-yyyy]"), null))
-
-      } else {
-        result.setDateofacceptance(OafMapperUtils.field(s"01-01-$publication_year", null))
-        result.getInstance().get(0).setDateofacceptance(OafMapperUtils.field(s"01-01-$publication_year", null))
-      }
-    }
-
-
-    result.setRelevantdate(dates.filter(d => d.date.isDefined && d.dateType.isDefined)
-      .map(d => (extract_date(d.date.get), d.dateType.get))
-      .filter(d => d._1.isDefined)
-      .map(d => (d._1.get, vocabularies.getTermAsQualifier(ModelConstants.DNET_DATACITE_DATE, d._2.toLowerCase())))
-      .filter(d => d._2 != null)
-      .map(d => generateOAFDate(d._1, d._2)).asJava)
-
-    val subjects = (json \\ "subjects").extract[List[SubjectType]]
-
-    result.setSubject(subjects.filter(s => s.subject.nonEmpty)
-      .map(s =>
-        OafMapperUtils.structuredProperty(s.subject.get, SUBJ_CLASS, SUBJ_CLASS, ModelConstants.DNET_SUBJECT_TYPOLOGIES, ModelConstants.DNET_SUBJECT_TYPOLOGIES, null)
-      ).asJava)
-
-
-    result.setCollectedfrom(List(DATACITE_COLLECTED_FROM).asJava)
-
-    val descriptions = (json \\ "descriptions").extract[List[DescriptionType]]
-
-    result.setDescription(
-      descriptions
-        .filter(d => d.description.isDefined).
-        map(d =>
-          OafMapperUtils.field(d.description.get, null)
-        ).filter(s => s != null).asJava)
-
-
-    val publisher = (json \\ "publisher").extractOrElse[String](null)
-    if (publisher != null)
-      result.setPublisher(OafMapperUtils.field(publisher, null))
-
-
-    val language: String = (json \\ "language").extractOrElse[String](null)
-
-    if (language != null)
-      result.setLanguage(vocabularies.getSynonymAsQualifier(ModelConstants.DNET_LANGUAGES, language))
-
-
-    val instance = result.getInstance().get(0)
-
-    val client = (json \ "relationships" \ "client" \\ "id").extractOpt[String]
-
-    val accessRights: List[String] = for {
-      JObject(rightsList) <- json \\ "rightsList"
-      JField("rightsUri", JString(rightsUri)) <- rightsList
-    } yield rightsUri
-
-    val aRights: Option[AccessRight] = accessRights.map(r => {
-      vocabularies.getSynonymAsQualifier(ModelConstants.DNET_ACCESS_MODES, r)
-    }).find(q => q != null).map(q => {
-      val a = new AccessRight
-      a.setClassid(q.getClassid)
-      a.setClassname(q.getClassname)
-      a.setSchemeid(q.getSchemeid)
-      a.setSchemename(q.getSchemename)
-      a
-    })
-
-
-    val access_rights_qualifier = if (aRights.isDefined) aRights.get else OafMapperUtils.accessRight(ModelConstants.UNKNOWN, ModelConstants.NOT_AVAILABLE, ModelConstants.DNET_ACCESS_MODES, ModelConstants.DNET_ACCESS_MODES)
-
-    if (client.isDefined) {
-      val hb = hostedByMap.getOrElse(client.get.toUpperCase(), unknown_repository)
-      instance.setHostedby(OafMapperUtils.keyValue(generateDSId(hb.openaire_id), hb.official_name))
-      instance.setCollectedfrom(DATACITE_COLLECTED_FROM)
-      instance.setUrl(List(s"https://dx.doi.org/$doi").asJava)
-      instance.setAccessright(access_rights_qualifier)
-      instance.setPid(result.getPid)
-      val license = accessRights
-        .find(r => r.startsWith("http") && r.matches(".*(/licenses|/publicdomain|unlicense\\.org/|/legal-and-data-protection-notices|/download/license|/open-government-licence).*"))
-      if (license.isDefined)
-        instance.setLicense(OafMapperUtils.field(license.get, null))
-    }
-
-    val awardUris: List[String] = for {
-      JObject(fundingReferences) <- json \\ "fundingReferences"
-      JField("awardUri", JString(awardUri)) <- fundingReferences
-    } yield awardUri
-
-    result.setId(IdentifierFactory.createIdentifier(result))
-    var relations: List[Relation] = awardUris.flatMap(a => get_projectRelation(a, result.getId)).filter(r => r != null)
-
-    fix_figshare(result)
-
-    if (result.getId == null)
-      return List()
-
-    if (exportLinks) {
-      val rels: List[RelatedIdentifierType] = for {
-        JObject(relIdentifier) <- json \\ "relatedIdentifiers"
-        JField("relationType", JString(relationType)) <- relIdentifier
-        JField("relatedIdentifierType", JString(relatedIdentifierType)) <- relIdentifier
-        JField("relatedIdentifier", JString(relatedIdentifier)) <- relIdentifier
-      } yield RelatedIdentifierType(relationType, relatedIdentifier, relatedIdentifierType)
-
-      relations = relations ::: generateRelations(rels,result.getId, if (i_date.isDefined && i_date.get.isDefined) i_date.get.get else null)
-    }
-    if (relations != null && relations.nonEmpty) {
-      List(result) ::: relations
-    }
-    else
-      List(result)
-  }
-
-  private def generateRelations(rels: List[RelatedIdentifierType], id:String, date:String):List[Relation] = {
-    rels
-      .filter(r =>
-        subRelTypeMapping.contains(r.relationType) && (
-          r.relatedIdentifierType.equalsIgnoreCase("doi") ||
-            r.relatedIdentifierType.equalsIgnoreCase("pmid") ||
-            r.relatedIdentifierType.equalsIgnoreCase("arxiv"))
-      )
-      .map(r => {
-        val rel = new Relation
-        rel.setCollectedfrom(List(DATACITE_COLLECTED_FROM).asJava)
-        rel.setDataInfo(dataInfo)
-
-        val subRelType = subRelTypeMapping(r.relationType)._2
-        rel.setRelType(REL_TYPE_VALUE)
-        rel.setSubRelType(subRelType)
-        rel.setRelClass(r.relationType)
-
-        val dateProps:KeyValue = OafMapperUtils.keyValue(DATE_RELATION_KEY, date)
-
-        rel.setProperties(List(dateProps).asJava)
-
-        rel.setSource(id)
-        rel.setTarget(s"unresolved::${r.relatedIdentifier}::${r.relatedIdentifierType}")
-        rel.setCollectedfrom(List(DATACITE_COLLECTED_FROM).asJava)
-        rel.getCollectedfrom.asScala.map(c => c.getValue)(collection.breakOut)
-        rel
-      })(collection breakOut)
-  }
-
-  def generateDataInfo(trust: String): DataInfo = {
-    val di = new DataInfo
-    di.setDeletedbyinference(false)
-    di.setInferred(false)
-    di.setInvisible(false)
-    di.setTrust(trust)
-    di.setProvenanceaction(ModelConstants.PROVENANCE_ACTION_SET_QUALIFIER)
-    di
-  }
-
-  def generateDSId(input: String): String = {
-    val b = StringUtils.substringBefore(input, "::")
-    val a = StringUtils.substringAfter(input, "::")
-    s"10|$b::${DHPUtils.md5(a)}"
-  }
-
-
-}

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/datacite/ExportActionSetJobNode.scala

@@ -1,41 +0,0 @@
-package eu.dnetlib.dhp.actionmanager.datacite
-
-import eu.dnetlib.dhp.application.ArgumentApplicationParser
-import eu.dnetlib.dhp.schema.oaf.Oaf
-import org.apache.hadoop.io.Text
-import org.apache.hadoop.io.compress.GzipCodec
-import org.apache.hadoop.mapred.SequenceFileOutputFormat
-import org.apache.spark.SparkConf
-import org.apache.spark.sql.{Dataset, Encoder, Encoders, SaveMode, SparkSession}
-import org.slf4j.{Logger, LoggerFactory}
-
-import scala.io.Source
-
-object ExportActionSetJobNode {
-
-  val log: Logger = LoggerFactory.getLogger(ExportActionSetJobNode.getClass)
-
-  def main(args: Array[String]): Unit = {
-    val conf = new SparkConf
-    val parser = new ArgumentApplicationParser(Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/dhp/actionmanager/datacite/exportDataset_parameters.json")).mkString)
-    parser.parseArgument(args)
-    val master = parser.get("master")
-    val sourcePath = parser.get("sourcePath")
-    val targetPath = parser.get("targetPath")
-
-    val spark: SparkSession = SparkSession.builder().config(conf)
-      .appName(ExportActionSetJobNode.getClass.getSimpleName)
-      .master(master)
-      .getOrCreate()
-    implicit val resEncoder: Encoder[Oaf] = Encoders.kryo[Oaf]
-    implicit val tEncoder:Encoder[(String,String)] = Encoders.tuple(Encoders.STRING,Encoders.STRING)
-
-    spark.read.load(sourcePath).as[Oaf]
-      .map(o =>DataciteToOAFTransformation.toActionSet(o))
-      .filter(o => o!= null)
-      .rdd.map(s => (new Text(s._1), new Text(s._2))).saveAsHadoopFile(s"$targetPath", classOf[Text], classOf[Text], classOf[SequenceFileOutputFormat[Text,Text]], classOf[GzipCodec])
-
-
-  }
-
-}

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/datacite/FilterCrossrefEntitiesSpark.scala

@@ -1,46 +0,0 @@
-package eu.dnetlib.dhp.actionmanager.datacite
-
-import eu.dnetlib.dhp.application.ArgumentApplicationParser
-import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup
-import eu.dnetlib.dhp.schema.mdstore.MetadataRecord
-import eu.dnetlib.dhp.schema.oaf.{Oaf, Result}
-import eu.dnetlib.dhp.utils.ISLookupClientFactory
-import org.apache.spark.SparkConf
-import org.apache.spark.sql.{Dataset, Encoder, Encoders, SaveMode, SparkSession}
-import org.slf4j.{Logger, LoggerFactory}
-
-import scala.io.Source
-
-object FilterCrossrefEntitiesSpark {
-
-  val log: Logger = LoggerFactory.getLogger(getClass.getClass)
-
-  def main(args: Array[String]): Unit = {
-    val conf = new SparkConf
-    val parser = new ArgumentApplicationParser(Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/dhp/actionmanager/datacite/filter_crossref_param.json")).mkString)
-    parser.parseArgument(args)
-    val master = parser.get("master")
-    val sourcePath = parser.get("sourcePath")
-    log.info("sourcePath: {}", sourcePath)
-    val targetPath = parser.get("targetPath")
-    log.info("targetPath: {}", targetPath)
-
-
-
-    val spark: SparkSession = SparkSession.builder().config(conf)
-      .appName(getClass.getSimpleName)
-      .master(master)
-      .getOrCreate()
-
-
-
-    implicit val oafEncoder: Encoder[Oaf] = Encoders.kryo[Oaf]
-    implicit val resEncoder: Encoder[Result] = Encoders.kryo[Result]
-
-    val d:Dataset[Oaf]= spark.read.load(sourcePath).as[Oaf]
-
-    d.filter(r => r.isInstanceOf[Result]).map(r => r.asInstanceOf[Result]).write.mode(SaveMode.Overwrite).save(targetPath)
-
-  }
-
-}

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/datacite/GenerateDataciteDatasetSpark.scala

@@ -1,48 +0,0 @@
-package eu.dnetlib.dhp.actionmanager.datacite
-
-import eu.dnetlib.dhp.application.ArgumentApplicationParser
-import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup
-import eu.dnetlib.dhp.schema.mdstore.MetadataRecord
-import eu.dnetlib.dhp.schema.oaf.Oaf
-import eu.dnetlib.dhp.utils.ISLookupClientFactory
-import org.apache.spark.SparkConf
-import org.apache.spark.sql.{Encoder, Encoders, SaveMode, SparkSession}
-import org.slf4j.{Logger, LoggerFactory}
-
-import scala.io.Source
-
-object GenerateDataciteDatasetSpark {
-
-  val log: Logger = LoggerFactory.getLogger(GenerateDataciteDatasetSpark.getClass)
-
-  def main(args: Array[String]): Unit = {
-    val conf = new SparkConf
-    val parser = new ArgumentApplicationParser(Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/dhp/actionmanager/datacite/generate_dataset_params.json")).mkString)
-    parser.parseArgument(args)
-    val master = parser.get("master")
-    val sourcePath = parser.get("sourcePath")
-    val targetPath = parser.get("targetPath")
-    val exportLinks = "true".equalsIgnoreCase(parser.get("exportLinks"))
-    val isLookupUrl: String = parser.get("isLookupUrl")
-    log.info("isLookupUrl: {}", isLookupUrl)
-
-    val isLookupService = ISLookupClientFactory.getLookUpService(isLookupUrl)
-    val vocabularies = VocabularyGroup.loadVocsFromIS(isLookupService)
-    val spark: SparkSession = SparkSession.builder().config(conf)
-      .appName(GenerateDataciteDatasetSpark.getClass.getSimpleName)
-      .master(master)
-      .getOrCreate()
-
-    implicit val mrEncoder: Encoder[MetadataRecord] = Encoders.kryo[MetadataRecord]
-
-    implicit val resEncoder: Encoder[Oaf] = Encoders.kryo[Oaf]
-
-    import spark.implicits._
-
-    spark.read.load(sourcePath).as[DataciteType]
-      .filter(d => d.isActive)
-      .flatMap(d => DataciteToOAFTransformation.generateOAF(d.json, d.timestamp, d.timestamp, vocabularies, exportLinks))
-      .filter(d => d != null)
-      .write.mode(SaveMode.Overwrite).save(targetPath)
-  }
-}

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/opencitations/CreateActionSetSparkJob.java

@@ -0,0 +1,181 @@
+
+package eu.dnetlib.dhp.actionmanager.opencitations;
+
+import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
+
+import java.io.IOException;
+import java.io.Serializable;
+import java.util.*;
+
+import org.apache.commons.cli.ParseException;
+import org.apache.commons.io.IOUtils;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.mapred.SequenceFileOutputFormat;
+import org.apache.spark.SparkConf;
+import org.apache.spark.api.java.function.FilterFunction;
+import org.apache.spark.api.java.function.FlatMapFunction;
+import org.apache.spark.sql.Encoders;
+import org.apache.spark.sql.SparkSession;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import com.fasterxml.jackson.databind.ObjectMapper;
+
+import eu.dnetlib.dhp.application.ArgumentApplicationParser;
+import eu.dnetlib.dhp.schema.action.AtomicAction;
+import eu.dnetlib.dhp.schema.common.ModelConstants;
+import eu.dnetlib.dhp.schema.common.ModelSupport;
+import eu.dnetlib.dhp.schema.oaf.*;
+import eu.dnetlib.dhp.schema.oaf.utils.CleaningFunctions;
+import eu.dnetlib.dhp.schema.oaf.utils.IdentifierFactory;
+import scala.Tuple2;
+
+public class CreateActionSetSparkJob implements Serializable {
+	public static final String OPENCITATIONS_CLASSID = "sysimport:crosswalk:opencitations";
+	public static final String OPENCITATIONS_CLASSNAME = "Imported from OpenCitations";
+	private static final String ID_PREFIX = "50|doi_________::";
+	private static final String TRUST = "0.91";
+
+	private static final Logger log = LoggerFactory.getLogger(CreateActionSetSparkJob.class);
+	private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
+
+	public static void main(final String[] args) throws IOException, ParseException {
+
+		final ArgumentApplicationParser parser = new ArgumentApplicationParser(
+			IOUtils
+				.toString(
+					Objects
+						.requireNonNull(
+							CreateActionSetSparkJob.class
+								.getResourceAsStream(
+									"/eu/dnetlib/dhp/actionmanager/opencitations/as_parameters.json"))));
+
+		parser.parseArgument(args);
+
+		Boolean isSparkSessionManaged = Optional
+			.ofNullable(parser.get("isSparkSessionManaged"))
+			.map(Boolean::valueOf)
+			.orElse(Boolean.TRUE);
+
+		log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
+
+		final String inputPath = parser.get("inputPath");
+		log.info("inputPath {}", inputPath.toString());
+
+		final String outputPath = parser.get("outputPath");
+		log.info("outputPath {}", outputPath);
+
+		final boolean shouldDuplicateRels = Optional
+			.ofNullable(parser.get("shouldDuplicateRels"))
+			.map(Boolean::valueOf)
+			.orElse(Boolean.FALSE);
+
+		SparkConf conf = new SparkConf();
+		runWithSparkSession(
+			conf,
+			isSparkSessionManaged,
+			spark -> {
+				extractContent(spark, inputPath, outputPath, shouldDuplicateRels);
+			});
+
+	}
+
+	private static void extractContent(SparkSession spark, String inputPath, String outputPath,
+		boolean shouldDuplicateRels) {
+		spark
+			.sqlContext()
+			.createDataset(spark.sparkContext().textFile(inputPath + "/*", 6000), Encoders.STRING())
+			.flatMap(
+				(FlatMapFunction<String, Relation>) value -> createRelation(value, shouldDuplicateRels).iterator(),
+				Encoders.bean(Relation.class))
+			.filter((FilterFunction<Relation>) value -> value != null)
+			.toJavaRDD()
+			.map(p -> new AtomicAction(p.getClass(), p))
+			.mapToPair(
+				aa -> new Tuple2<>(new Text(aa.getClazz().getCanonicalName()),
+					new Text(OBJECT_MAPPER.writeValueAsString(aa))))
+			.saveAsHadoopFile(outputPath, Text.class, Text.class, SequenceFileOutputFormat.class);
+
+	}
+
+	private static List<Relation> createRelation(String value, boolean duplicate) {
+		String[] line = value.split(",");
+		if (!line[1].startsWith("10.")) {
+			return new ArrayList<>();
+		}
+		List<Relation> relationList = new ArrayList<>();
+
+		String citing = ID_PREFIX + IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", line[1]));
+		final String cited = ID_PREFIX + IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", line[2]));
+
+		relationList
+			.addAll(
+				getRelations(
+					citing,
+					cited));
+
+		if (duplicate && line[1].endsWith(".refs")) {
+			citing = ID_PREFIX + IdentifierFactory
+				.md5(CleaningFunctions.normalizePidValue("doi", line[1].substring(0, line[1].indexOf(".refs"))));
+			relationList.addAll(getRelations(citing, cited));
+		}
+
+		return relationList;
+	}
+
+	private static Collection<Relation> getRelations(String citing, String cited) {
+
+		return Arrays
+			.asList(
+				getRelation(citing, cited, ModelConstants.CITES),
+				getRelation(cited, citing, ModelConstants.IS_CITED_BY));
+	}
+
+	public static Relation getRelation(
+		String source,
+		String target,
+		String relclass) {
+		Relation r = new Relation();
+		r.setCollectedfrom(getCollectedFrom());
+		r.setSource(source);
+		r.setTarget(target);
+		r.setRelClass(relclass);
+		r.setRelType(ModelConstants.RESULT_RESULT);
+		r.setSubRelType(ModelConstants.CITATION);
+		r
+			.setDataInfo(
+				getDataInfo());
+		return r;
+	}
+
+	public static List<KeyValue> getCollectedFrom() {
+		KeyValue kv = new KeyValue();
+		kv.setKey(ModelConstants.OPENOCITATIONS_ID);
+		kv.setValue(ModelConstants.OPENOCITATIONS_NAME);
+
+		return Arrays.asList(kv);
+	}
+
+	public static DataInfo getDataInfo() {
+		DataInfo di = new DataInfo();
+		di.setInferred(false);
+		di.setDeletedbyinference(false);
+		di.setTrust(TRUST);
+
+		di
+			.setProvenanceaction(
+				getQualifier(OPENCITATIONS_CLASSID, OPENCITATIONS_CLASSNAME, ModelConstants.DNET_PROVENANCE_ACTIONS));
+		return di;
+	}
+
+	public static Qualifier getQualifier(String class_id, String class_name,
+		String qualifierSchema) {
+		Qualifier pa = new Qualifier();
+		pa.setClassid(class_id);
+		pa.setClassname(class_name);
+		pa.setSchemeid(qualifierSchema);
+		pa.setSchemename(qualifierSchema);
+		return pa;
+	}
+
+}

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/opencitations/GetOpenCitationsRefs.java

@@ -0,0 +1,93 @@
+
+package eu.dnetlib.dhp.actionmanager.opencitations;
+
+import java.io.*;
+import java.io.Serializable;
+import java.util.Objects;
+import java.util.zip.GZIPOutputStream;
+import java.util.zip.ZipEntry;
+import java.util.zip.ZipInputStream;
+
+import org.apache.commons.cli.ParseException;
+import org.apache.commons.io.IOUtils;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.FSDataInputStream;
+import org.apache.hadoop.fs.FSDataOutputStream;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import eu.dnetlib.dhp.application.ArgumentApplicationParser;
+
+public class GetOpenCitationsRefs implements Serializable {
+	private static final Logger log = LoggerFactory.getLogger(GetOpenCitationsRefs.class);
+
+	public static void main(final String[] args) throws IOException, ParseException {
+
+		final ArgumentApplicationParser parser = new ArgumentApplicationParser(
+			IOUtils
+				.toString(
+					Objects
+						.requireNonNull(
+							GetOpenCitationsRefs.class
+								.getResourceAsStream(
+									"/eu/dnetlib/dhp/actionmanager/opencitations/input_parameters.json"))));
+
+		parser.parseArgument(args);
+
+		final String[] inputFile = parser.get("inputFile").split(";");
+		log.info("inputFile {}", inputFile.toString());
+
+		final String workingPath = parser.get("workingPath");
+		log.info("workingPath {}", workingPath);
+
+		final String hdfsNameNode = parser.get("hdfsNameNode");
+		log.info("hdfsNameNode {}", hdfsNameNode);
+
+		Configuration conf = new Configuration();
+		conf.set("fs.defaultFS", hdfsNameNode);
+
+		FileSystem fileSystem = FileSystem.get(conf);
+
+		GetOpenCitationsRefs ocr = new GetOpenCitationsRefs();
+
+		for (String file : inputFile) {
+			ocr.doExtract(workingPath + "/Original/" + file, workingPath, fileSystem);
+		}
+
+	}
+
+	private void doExtract(String inputFile, String workingPath, FileSystem fileSystem)
+		throws IOException {
+
+		final Path path = new Path(inputFile);
+
+		FSDataInputStream oc_zip = fileSystem.open(path);
+
+		int count = 1;
+		try (ZipInputStream zis = new ZipInputStream(oc_zip)) {
+			ZipEntry entry = null;
+			while ((entry = zis.getNextEntry()) != null) {
+
+				if (!entry.isDirectory()) {
+					String fileName = entry.getName();
+					fileName = fileName.substring(0, fileName.indexOf("T")) + "_" + count;
+					count++;
+					try (
+						FSDataOutputStream out = fileSystem
+							.create(new Path(workingPath + "/COCI/" + fileName + ".gz"));
+						GZIPOutputStream gzipOs = new GZIPOutputStream(new BufferedOutputStream(out))) {
+
+						IOUtils.copy(zis, gzipOs);
+
+					}
+				}
+
+			}
+
+		}
+
+	}
+
+}

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/project/PrepareProgramme.java

@@ -20,7 +20,7 @@ import org.slf4j.LoggerFactory;
 
 import com.fasterxml.jackson.databind.ObjectMapper;
 
-import eu.dnetlib.dhp.actionmanager.project.utils.CSVProgramme;
+import eu.dnetlib.dhp.actionmanager.project.utils.model.CSVProgramme;
 import eu.dnetlib.dhp.application.ArgumentApplicationParser;
 import eu.dnetlib.dhp.common.HdfsSupport;
 import scala.Tuple2;
@@ -171,26 +171,23 @@ public class PrepareProgramme {
 	}
 
 	private static CSVProgramme groupProgrammeByCode(CSVProgramme a, CSVProgramme b) {
-		if (!a.getLanguage().equals("en")) {
-			if (b.getLanguage().equalsIgnoreCase("en")) {
-				a.setTitle(b.getTitle());
-				a.setLanguage(b.getLanguage());
-			}
+		if (!a.getLanguage().equals("en") && b.getLanguage().equalsIgnoreCase("en")) {
+			a.setTitle(b.getTitle());
+			a.setLanguage(b.getLanguage());
 		}
-		if (StringUtils.isEmpty(a.getShortTitle())) {
-			if (!StringUtils.isEmpty(b.getShortTitle())) {
-				a.setShortTitle(b.getShortTitle());
-			}
+		if (StringUtils.isEmpty(a.getShortTitle()) && !StringUtils.isEmpty(b.getShortTitle())) {
+			a.setShortTitle(b.getShortTitle());
 		}
 
 		return a;
 	}
 
+	@SuppressWarnings("unchecked")
 	private static List<CSVProgramme> prepareClassification(JavaRDD<CSVProgramme> h2020Programmes) {
 		Object[] codedescription = h2020Programmes
 			.map(
 				value -> new Tuple2<>(value.getCode(),
-					new Tuple2<String, String>(value.getTitle(), value.getShortTitle())))
+					new Tuple2<>(value.getTitle(), value.getShortTitle())))
 			.collect()
 			.toArray();
 
@@ -216,7 +213,7 @@ public class PrepareProgramme {
 			String[] tmp = ent.split("\\.");
 			if (tmp.length <= 2) {
 				if (StringUtils.isEmpty(entry._2()._2())) {
-					map.put(entry._1(), new Tuple2<String, String>(entry._2()._1(), entry._2()._1()));
+					map.put(entry._1(), new Tuple2<>(entry._2()._1(), entry._2()._1()));
 				} else {
 					map.put(entry._1(), entry._2());
 				}

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/project/PrepareProjects.java

@@ -18,7 +18,7 @@ import org.slf4j.LoggerFactory;
 
 import com.fasterxml.jackson.databind.ObjectMapper;
 
-import eu.dnetlib.dhp.actionmanager.project.utils.CSVProject;
+import eu.dnetlib.dhp.actionmanager.project.utils.model.CSVProject;
 import eu.dnetlib.dhp.application.ArgumentApplicationParser;
 import eu.dnetlib.dhp.common.HdfsSupport;
 import scala.Tuple2;
@@ -29,7 +29,7 @@ import scala.Tuple2;
  */
 public class PrepareProjects {
 
-	private static final Logger log = LoggerFactory.getLogger(PrepareProgramme.class);
+	private static final Logger log = LoggerFactory.getLogger(PrepareProjects.class);
 	private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
 
 	public static void main(String[] args) throws Exception {

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/project/ReadProjectsFromDB.java

@@ -31,15 +31,16 @@ import eu.dnetlib.dhp.common.DbClient;
  */
 public class ReadProjectsFromDB implements Closeable {
 
-	private final DbClient dbClient;
 	private static final Log log = LogFactory.getLog(ReadProjectsFromDB.class);
+
+	private static final String query = "SELECT code  " +
+		"from projects where id like 'corda__h2020%' ";
+
+	private final DbClient dbClient;
 	private final Configuration conf;
 	private final BufferedWriter writer;
 	private final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
 
-	private final static String query = "SELECT code  " +
-		"from projects where id like 'corda__h2020%' ";
-
 	public static void main(final String[] args) throws Exception {
 		final ArgumentApplicationParser parser = new ArgumentApplicationParser(
 			IOUtils
@@ -65,9 +66,9 @@ public class ReadProjectsFromDB implements Closeable {
 		}
 	}
 
-	public void execute(final String sql, final Function<ResultSet, List<ProjectSubset>> producer) throws Exception {
+	public void execute(final String sql, final Function<ResultSet, List<ProjectSubset>> producer) {
 
-		final Consumer<ResultSet> consumer = rs -> producer.apply(rs).forEach(r -> writeProject(r));
+		final Consumer<ResultSet> consumer = rs -> producer.apply(rs).forEach(this::writeProject);
 
 		dbClient.processResults(sql, consumer);
 	}
@@ -94,20 +95,20 @@ public class ReadProjectsFromDB implements Closeable {
 
 	public ReadProjectsFromDB(
 		final String hdfsPath, String hdfsNameNode, final String dbUrl, final String dbUser, final String dbPassword)
-		throws Exception {
+		throws IOException {
 
 		this.dbClient = new DbClient(dbUrl, dbUser, dbPassword);
 		this.conf = new Configuration();
 		this.conf.set("fs.defaultFS", hdfsNameNode);
 		FileSystem fileSystem = FileSystem.get(this.conf);
 		Path hdfsWritePath = new Path(hdfsPath);
-		FSDataOutputStream fsDataOutputStream = null;
+
 		if (fileSystem.exists(hdfsWritePath)) {
 			fileSystem.delete(hdfsWritePath, false);
 		}
-		fsDataOutputStream = fileSystem.create(hdfsWritePath);
+		FSDataOutputStream fos = fileSystem.create(hdfsWritePath);
 
-		this.writer = new BufferedWriter(new OutputStreamWriter(fsDataOutputStream, StandardCharsets.UTF_8));
+		this.writer = new BufferedWriter(new OutputStreamWriter(fos, StandardCharsets.UTF_8));
 	}
 
 	@Override

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/project/SparkAtomicActionJob.java

@@ -4,7 +4,6 @@ package eu.dnetlib.dhp.actionmanager.project;
 import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
 
 import java.util.Arrays;
-import java.util.HashMap;
 import java.util.Objects;
 import java.util.Optional;
 
@@ -22,15 +21,16 @@ import org.slf4j.LoggerFactory;
 
 import com.fasterxml.jackson.databind.ObjectMapper;
 
-import eu.dnetlib.dhp.actionmanager.project.utils.CSVProgramme;
-import eu.dnetlib.dhp.actionmanager.project.utils.CSVProject;
-import eu.dnetlib.dhp.actionmanager.project.utils.EXCELTopic;
+import eu.dnetlib.dhp.actionmanager.project.utils.model.CSVProgramme;
+import eu.dnetlib.dhp.actionmanager.project.utils.model.CSVProject;
+import eu.dnetlib.dhp.actionmanager.project.utils.model.EXCELTopic;
 import eu.dnetlib.dhp.application.ArgumentApplicationParser;
 import eu.dnetlib.dhp.common.HdfsSupport;
 import eu.dnetlib.dhp.schema.action.AtomicAction;
 import eu.dnetlib.dhp.schema.common.ModelSupport;
 import eu.dnetlib.dhp.schema.oaf.H2020Classification;
 import eu.dnetlib.dhp.schema.oaf.H2020Programme;
+import eu.dnetlib.dhp.schema.oaf.OafEntity;
 import eu.dnetlib.dhp.schema.oaf.Project;
 import eu.dnetlib.dhp.utils.DHPUtils;
 import scala.Tuple2;
@@ -47,13 +47,10 @@ import scala.Tuple2;
  *
  * To produce one single entry for each project code a step of groupoing is needed: each project can be associated to more
  * than one programme.
- *
- *
  */
 public class SparkAtomicActionJob {
 	private static final Logger log = LoggerFactory.getLogger(SparkAtomicActionJob.class);
 	private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
-	private static final HashMap<String, String> programmeMap = new HashMap<>();
 
 	public static void main(String[] args) throws Exception {
 
@@ -137,7 +134,6 @@ public class SparkAtomicActionJob {
 						h2020classification.setClassification(csvProgramme.getClassification());
 						h2020classification.setH2020Programme(pm);
 						setLevelsandProgramme(h2020classification, csvProgramme.getClassification_short());
-						// setProgramme(h2020classification, ocsvProgramme.get().getClassification());
 						pp.setH2020classification(Arrays.asList(h2020classification));
 
 						return pp;
@@ -152,20 +148,16 @@ public class SparkAtomicActionJob {
 			.map((MapFunction<Tuple2<Project, EXCELTopic>, Project>) p -> {
 				Optional<EXCELTopic> op = Optional.ofNullable(p._2());
 				Project rp = p._1();
-				if (op.isPresent()) {
-					rp.setH2020topicdescription(op.get().getTitle());
-				}
+				op.ifPresent(excelTopic -> rp.setH2020topicdescription(excelTopic.getTitle()));
 				return rp;
 			}, Encoders.bean(Project.class))
 			.filter(Objects::nonNull)
 			.groupByKey(
-				(MapFunction<Project, String>) p -> p.getId(),
+				(MapFunction<Project, String>) OafEntity::getId,
 				Encoders.STRING())
 			.mapGroups((MapGroupsFunction<String, Project, Project>) (s, it) -> {
 				Project first = it.next();
-				it.forEachRemaining(p -> {
-					first.mergeFrom(p);
-				});
+				it.forEachRemaining(first::mergeFrom);
 				return first;
 			}, Encoders.bean(Project.class))
 			.toJavaRDD()
@@ -189,12 +181,6 @@ public class SparkAtomicActionJob {
 		h2020Classification.getH2020Programme().setDescription(tmp[tmp.length - 1]);
 	}
 
-//	private static void setProgramme(H2020Classification h2020Classification, String classification) {
-//		String[] tmp = classification.split(" \\| ");
-//
-//		h2020Classification.getH2020Programme().setDescription(tmp[tmp.length - 1]);
-//	}
-
 	public static <R> Dataset<R> readPath(
 		SparkSession spark, String inputPath, Class<R> clazz) {
 		return spark

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/project/utils/CSVParser.java

@@ -1,40 +0,0 @@
-
-package eu.dnetlib.dhp.actionmanager.project.utils;
-
-import java.io.IOException;
-import java.util.ArrayList;
-import java.util.List;
-import java.util.Set;
-
-import org.apache.commons.csv.CSVFormat;
-import org.apache.commons.csv.CSVRecord;
-import org.apache.commons.lang.reflect.FieldUtils;
-
-/**
- * Reads a generic csv and maps it into classes that mirror its schema
- */
-public class CSVParser {
-
-	public <R> List<R> parse(String csvFile, String classForName)
-		throws ClassNotFoundException, IOException, IllegalAccessException, InstantiationException {
-		final CSVFormat format = CSVFormat.EXCEL
-			.withHeader()
-			.withDelimiter(';')
-			.withQuote('"')
-			.withTrim();
-		List<R> ret = new ArrayList<>();
-		final org.apache.commons.csv.CSVParser parser = org.apache.commons.csv.CSVParser.parse(csvFile, format);
-		final Set<String> headers = parser.getHeaderMap().keySet();
-		Class<?> clazz = Class.forName(classForName);
-		for (CSVRecord csvRecord : parser.getRecords()) {
-			final Object cc = clazz.newInstance();
-			for (String header : headers) {
-				FieldUtils.writeField(cc, header, csvRecord.get(header), true);
-
-			}
-			ret.add((R) cc);
-		}
-
-		return ret;
-	}
-}

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/project/utils/CSVProject.java

@@ -1,200 +0,0 @@
-
-package eu.dnetlib.dhp.actionmanager.project.utils;
-
-import java.io.Serializable;
-
-/**
- * the mmodel for the projects csv file
- */
-public class CSVProject implements Serializable {
-	private String rcn;
-	private String id;
-	private String acronym;
-	private String status;
-	private String programme;
-	private String topics;
-	private String frameworkProgramme;
-	private String title;
-	private String startDate;
-	private String endDate;
-	private String projectUrl;
-	private String objective;
-	private String totalCost;
-	private String ecMaxContribution;
-	private String call;
-	private String fundingScheme;
-	private String coordinator;
-	private String coordinatorCountry;
-	private String participants;
-	private String participantCountries;
-	private String subjects;
-
-	public String getRcn() {
-		return rcn;
-	}
-
-	public void setRcn(String rcn) {
-		this.rcn = rcn;
-	}
-
-	public String getId() {
-		return id;
-	}
-
-	public void setId(String id) {
-		this.id = id;
-	}
-
-	public String getAcronym() {
-		return acronym;
-	}
-
-	public void setAcronym(String acronym) {
-		this.acronym = acronym;
-	}
-
-	public String getStatus() {
-		return status;
-	}
-
-	public void setStatus(String status) {
-		this.status = status;
-	}
-
-	public String getProgramme() {
-		return programme;
-	}
-
-	public void setProgramme(String programme) {
-		this.programme = programme;
-	}
-
-	public String getTopics() {
-		return topics;
-	}
-
-	public void setTopics(String topics) {
-		this.topics = topics;
-	}
-
-	public String getFrameworkProgramme() {
-		return frameworkProgramme;
-	}
-
-	public void setFrameworkProgramme(String frameworkProgramme) {
-		this.frameworkProgramme = frameworkProgramme;
-	}
-
-	public String getTitle() {
-		return title;
-	}
-
-	public void setTitle(String title) {
-		this.title = title;
-	}
-
-	public String getStartDate() {
-		return startDate;
-	}
-
-	public void setStartDate(String startDate) {
-		this.startDate = startDate;
-	}
-
-	public String getEndDate() {
-		return endDate;
-	}
-
-	public void setEndDate(String endDate) {
-		this.endDate = endDate;
-	}
-
-	public String getProjectUrl() {
-		return projectUrl;
-	}
-
-	public void setProjectUrl(String projectUrl) {
-		this.projectUrl = projectUrl;
-	}
-
-	public String getObjective() {
-		return objective;
-	}
-
-	public void setObjective(String objective) {
-		this.objective = objective;
-	}
-
-	public String getTotalCost() {
-		return totalCost;
-	}
-
-	public void setTotalCost(String totalCost) {
-		this.totalCost = totalCost;
-	}
-
-	public String getEcMaxContribution() {
-		return ecMaxContribution;
-	}
-
-	public void setEcMaxContribution(String ecMaxContribution) {
-		this.ecMaxContribution = ecMaxContribution;
-	}
-
-	public String getCall() {
-		return call;
-	}
-
-	public void setCall(String call) {
-		this.call = call;
-	}
-
-	public String getFundingScheme() {
-		return fundingScheme;
-	}
-
-	public void setFundingScheme(String fundingScheme) {
-		this.fundingScheme = fundingScheme;
-	}
-
-	public String getCoordinator() {
-		return coordinator;
-	}
-
-	public void setCoordinator(String coordinator) {
-		this.coordinator = coordinator;
-	}
-
-	public String getCoordinatorCountry() {
-		return coordinatorCountry;
-	}
-
-	public void setCoordinatorCountry(String coordinatorCountry) {
-		this.coordinatorCountry = coordinatorCountry;
-	}
-
-	public String getParticipants() {
-		return participants;
-	}
-
-	public void setParticipants(String participants) {
-		this.participants = participants;
-	}
-
-	public String getParticipantCountries() {
-		return participantCountries;
-	}
-
-	public void setParticipantCountries(String participantCountries) {
-		this.participantCountries = participantCountries;
-	}
-
-	public String getSubjects() {
-		return subjects;
-	}
-
-	public void setSubjects(String subjects) {
-		this.subjects = subjects;
-	}
-
-}

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/project/utils/EXCELParser.java

@@ -17,6 +17,8 @@ import org.apache.poi.ss.usermodel.Row;
 import org.apache.poi.xssf.usermodel.XSSFSheet;
 import org.apache.poi.xssf.usermodel.XSSFWorkbook;
 
+import eu.dnetlib.dhp.actionmanager.project.utils.model.EXCELTopic;
+
 /**
  * Reads a generic excel file and maps it into classes that mirror its schema
  */
@@ -26,52 +28,52 @@ public class EXCELParser {
 		throws ClassNotFoundException, IOException, IllegalAccessException, InstantiationException,
 		InvalidFormatException {
 
-		OPCPackage pkg = OPCPackage.open(file);
-		XSSFWorkbook wb = new XSSFWorkbook(pkg);
+		try (OPCPackage pkg = OPCPackage.open(file); XSSFWorkbook wb = new XSSFWorkbook(pkg)) {
 
-		XSSFSheet sheet = wb.getSheet(sheetName);
-
-		if (sheetName == null) {
-			throw new RuntimeException("Sheet name " + sheetName + " not present in current file");
-		}
-
-		List<R> ret = new ArrayList<>();
-
-		DataFormatter dataFormatter = new DataFormatter();
-		Iterator<Row> rowIterator = sheet.rowIterator();
-		List<String> headers = new ArrayList<>();
-		int count = 0;
-		while (rowIterator.hasNext()) {
-			Row row = rowIterator.next();
-
-			if (count == 0) {
-				Iterator<Cell> cellIterator = row.cellIterator();
-
-				while (cellIterator.hasNext()) {
-					Cell cell = cellIterator.next();
-					headers.add(dataFormatter.formatCellValue(cell));
-				}
-			} else {
-				Class<?> clazz = Class.forName(classForName);
-				final Object cc = clazz.newInstance();
-
-				for (int i = 0; i < headers.size(); i++) {
-					Cell cell = row.getCell(i);
-					FieldUtils.writeField(cc, headers.get(i), dataFormatter.formatCellValue(cell), true);
-
-				}
-
-				EXCELTopic et = (EXCELTopic) cc;
-				if (StringUtils.isNotBlank(et.getRcn())) {
-					ret.add((R) cc);
-				}
+			XSSFSheet sheet = wb.getSheet(sheetName);
 
+			if (sheet == null) {
+				throw new IllegalArgumentException("Sheet name " + sheetName + " not present in current file");
 			}
 
-			count += 1;
-		}
+			List<R> ret = new ArrayList<>();
 
-		return ret;
+			DataFormatter dataFormatter = new DataFormatter();
+			Iterator<Row> rowIterator = sheet.rowIterator();
+			List<String> headers = new ArrayList<>();
+			int count = 0;
+			while (rowIterator.hasNext()) {
+				Row row = rowIterator.next();
+
+				if (count == 0) {
+					Iterator<Cell> cellIterator = row.cellIterator();
+
+					while (cellIterator.hasNext()) {
+						Cell cell = cellIterator.next();
+						headers.add(dataFormatter.formatCellValue(cell));
+					}
+				} else {
+					Class<?> clazz = Class.forName(classForName);
+					final Object cc = clazz.newInstance();
+
+					for (int i = 0; i < headers.size(); i++) {
+						Cell cell = row.getCell(i);
+						FieldUtils.writeField(cc, headers.get(i), dataFormatter.formatCellValue(cell), true);
+
+					}
+
+					EXCELTopic et = (EXCELTopic) cc;
+					if (StringUtils.isNotBlank(et.getRcn())) {
+						ret.add((R) cc);
+					}
+
+				}
+
+				count += 1;
+			}
+
+			return ret;
+		}
 	}
 
 }

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/project/utils/ReadCSV.java

@@ -1,34 +1,21 @@
 
 package eu.dnetlib.dhp.actionmanager.project.utils;
 
-import java.io.BufferedWriter;
-import java.io.Closeable;
-import java.io.IOException;
-import java.io.OutputStreamWriter;
-import java.nio.charset.StandardCharsets;
+import java.io.*;
+import java.util.Optional;
 
 import org.apache.commons.io.IOUtils;
-import org.apache.commons.logging.Log;
-import org.apache.commons.logging.LogFactory;
 import org.apache.hadoop.conf.Configuration;
-import org.apache.hadoop.fs.FSDataOutputStream;
 import org.apache.hadoop.fs.FileSystem;
-import org.apache.hadoop.fs.Path;
-
-import com.fasterxml.jackson.databind.ObjectMapper;
 
 import eu.dnetlib.dhp.application.ArgumentApplicationParser;
-import eu.dnetlib.dhp.collection.HttpConnector2;
+import eu.dnetlib.dhp.common.collection.GetCSV;
+import eu.dnetlib.dhp.common.collection.HttpConnector2;
 
 /**
  * Applies the parsing of a csv file and writes the Serialization of it in hdfs
  */
-public class ReadCSV implements Closeable {
-	private static final Log log = LogFactory.getLog(ReadCSV.class);
-	private final Configuration conf;
-	private final BufferedWriter writer;
-	private final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
-	private final String csvFile;
+public class ReadCSV {
 
 	public static void main(final String[] args) throws Exception {
 		final ArgumentApplicationParser parser = new ArgumentApplicationParser(
@@ -44,56 +31,22 @@ public class ReadCSV implements Closeable {
 		final String hdfsPath = parser.get("hdfsPath");
 		final String hdfsNameNode = parser.get("hdfsNameNode");
 		final String classForName = parser.get("classForName");
+		Optional<String> delimiter = Optional.ofNullable(parser.get("delimiter"));
+		char del = ';';
+		if (delimiter.isPresent())
+			del = delimiter.get().charAt(0);
 
-		try (final ReadCSV readCSV = new ReadCSV(hdfsPath, hdfsNameNode, fileURL)) {
+		Configuration conf = new Configuration();
+		conf.set("fs.defaultFS", hdfsNameNode);
 
-			log.info("Getting CSV file...");
-			readCSV.execute(classForName);
+		FileSystem fileSystem = FileSystem.get(conf);
+		BufferedReader reader = new BufferedReader(
+			new InputStreamReader(new HttpConnector2().getInputSourceAsStream(fileURL)));
 
-		}
-	}
+		GetCSV.getCsv(fileSystem, reader, hdfsPath, classForName, del);
 
-	public void execute(final String classForName) throws Exception {
-		CSVParser csvParser = new CSVParser();
-		csvParser
-			.parse(csvFile, classForName)
-			.stream()
-			.forEach(p -> write(p));
+		reader.close();
 
 	}
 
-	@Override
-	public void close() throws IOException {
-		writer.close();
-	}
-
-	public ReadCSV(
-		final String hdfsPath,
-		final String hdfsNameNode,
-		final String fileURL)
-		throws Exception {
-		this.conf = new Configuration();
-		this.conf.set("fs.defaultFS", hdfsNameNode);
-		HttpConnector2 httpConnector = new HttpConnector2();
-		FileSystem fileSystem = FileSystem.get(this.conf);
-		Path hdfsWritePath = new Path(hdfsPath);
-		FSDataOutputStream fsDataOutputStream = null;
-		if (fileSystem.exists(hdfsWritePath)) {
-			fileSystem.delete(hdfsWritePath, false);
-		}
-		fsDataOutputStream = fileSystem.create(hdfsWritePath);
-
-		this.writer = new BufferedWriter(new OutputStreamWriter(fsDataOutputStream, StandardCharsets.UTF_8));
-		this.csvFile = httpConnector.getInputSource(fileURL);
-	}
-
-	protected void write(final Object p) {
-		try {
-			writer.write(OBJECT_MAPPER.writeValueAsString(p));
-			writer.newLine();
-		} catch (final Exception e) {
-			throw new RuntimeException(e);
-		}
-	}
-
 }

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/project/utils/ReadExcel.java

@@ -11,18 +11,20 @@ import org.apache.hadoop.conf.Configuration;
 import org.apache.hadoop.fs.FSDataOutputStream;
 import org.apache.hadoop.fs.FileSystem;
 import org.apache.hadoop.fs.Path;
+import org.apache.poi.openxml4j.exceptions.InvalidFormatException;
 
 import com.fasterxml.jackson.databind.ObjectMapper;
 
 import eu.dnetlib.dhp.application.ArgumentApplicationParser;
-import eu.dnetlib.dhp.collection.HttpConnector2;
+import eu.dnetlib.dhp.common.collection.CollectorException;
+import eu.dnetlib.dhp.common.collection.HttpConnector2;
 
 /**
  * Applies the parsing of an excel file and writes the Serialization of it in hdfs
  */
 public class ReadExcel implements Closeable {
-	private static final Log log = LogFactory.getLog(ReadCSV.class);
-	private final Configuration conf;
+	private static final Log log = LogFactory.getLog(ReadExcel.class);
+
 	private final BufferedWriter writer;
 	private final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
 	private final InputStream excelFile;
@@ -31,7 +33,7 @@ public class ReadExcel implements Closeable {
 		final ArgumentApplicationParser parser = new ArgumentApplicationParser(
 			IOUtils
 				.toString(
-					ReadCSV.class
+					ReadExcel.class
 						.getResourceAsStream(
 							"/eu/dnetlib/dhp/actionmanager/project/parameters.json")));
 
@@ -51,13 +53,15 @@ public class ReadExcel implements Closeable {
 		}
 	}
 
-	public void execute(final String classForName, final String sheetName) throws Exception {
+	public void execute(final String classForName, final String sheetName)
+		throws IOException, ClassNotFoundException, InvalidFormatException, IllegalAccessException,
+		InstantiationException {
+
 		EXCELParser excelParser = new EXCELParser();
 		excelParser
 			.parse(excelFile, classForName, sheetName)
 			.stream()
-			.forEach(p -> write(p));
-
+			.forEach(this::write);
 	}
 
 	@Override
@@ -68,20 +72,20 @@ public class ReadExcel implements Closeable {
 	public ReadExcel(
 		final String hdfsPath,
 		final String hdfsNameNode,
-		final String fileURL)
-		throws Exception {
-		this.conf = new Configuration();
-		this.conf.set("fs.defaultFS", hdfsNameNode);
+		final String fileURL) throws CollectorException, IOException {
+
+		final Configuration conf = new Configuration();
+		conf.set("fs.defaultFS", hdfsNameNode);
 		HttpConnector2 httpConnector = new HttpConnector2();
-		FileSystem fileSystem = FileSystem.get(this.conf);
+		FileSystem fileSystem = FileSystem.get(conf);
 		Path hdfsWritePath = new Path(hdfsPath);
-		FSDataOutputStream fsDataOutputStream = null;
+
 		if (fileSystem.exists(hdfsWritePath)) {
 			fileSystem.delete(hdfsWritePath, false);
 		}
-		fsDataOutputStream = fileSystem.create(hdfsWritePath);
+		FSDataOutputStream fos = fileSystem.create(hdfsWritePath);
 
-		this.writer = new BufferedWriter(new OutputStreamWriter(fsDataOutputStream, StandardCharsets.UTF_8));
+		this.writer = new BufferedWriter(new OutputStreamWriter(fos, StandardCharsets.UTF_8));
 		this.excelFile = httpConnector.getInputSourceAsStream(fileURL);
 	}
 

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/project/utils/model/CSVProgramme.java

@@ -1,20 +1,32 @@
 
-package eu.dnetlib.dhp.actionmanager.project.utils;
+package eu.dnetlib.dhp.actionmanager.project.utils.model;
 
 import java.io.Serializable;
 
+import com.opencsv.bean.CsvBindByName;
+import com.opencsv.bean.CsvIgnore;
+
 /**
  * The model for the programme csv file
  */
 public class CSVProgramme implements Serializable {
 
-	private String rcn;
+	@CsvBindByName(column = "code")
 	private String code;
 
+	@CsvBindByName(column = "title")
 	private String title;
+
+	@CsvBindByName(column = "shortTitle")
 	private String shortTitle;
+
+	@CsvBindByName(column = "language")
 	private String language;
+
+	@CsvIgnore
 	private String classification;
+
+	@CsvIgnore
 	private String classification_short;
 
 	public String getClassification_short() {
@@ -33,14 +45,6 @@ public class CSVProgramme implements Serializable {
 		this.classification = classification;
 	}
 
-	public String getRcn() {
-		return rcn;
-	}
-
-	public void setRcn(String rcn) {
-		this.rcn = rcn;
-	}
-
 	public String getCode() {
 		return code;
 	}
@@ -73,5 +77,4 @@ public class CSVProgramme implements Serializable {
 		this.language = language;
 	}
 
-//
 }

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/project/utils/model/CSVProject.java

@@ -0,0 +1,46 @@
+
+package eu.dnetlib.dhp.actionmanager.project.utils.model;
+
+import java.io.Serializable;
+
+import com.opencsv.bean.CsvBindByName;
+
+/**
+ * the mmodel for the projects csv file
+ */
+public class CSVProject implements Serializable {
+
+	@CsvBindByName(column = "id")
+	private String id;
+
+	@CsvBindByName(column = "programme")
+	private String programme;
+
+	@CsvBindByName(column = "topics")
+	private String topics;
+
+	public String getId() {
+		return id;
+	}
+
+	public void setId(String id) {
+		this.id = id;
+	}
+
+	public String getProgramme() {
+		return programme;
+	}
+
+	public void setProgramme(String programme) {
+		this.programme = programme;
+	}
+
+	public String getTopics() {
+		return topics;
+	}
+
+	public void setTopics(String topics) {
+		this.topics = topics;
+	}
+
+}

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/project/utils/model/EXCELTopic.java

@@ -1,5 +1,5 @@
 
-package eu.dnetlib.dhp.actionmanager.project.utils;
+package eu.dnetlib.dhp.actionmanager.project.utils.model;
 
 import java.io.Serializable;
 

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/ror/GenerateRorActionSetJob.java

@@ -9,6 +9,7 @@ import static eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils.listKeyValues;
 import static eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils.qualifier;
 import static eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils.structuredProperty;
 
+import java.io.IOException;
 import java.io.InputStream;
 import java.util.ArrayList;
 import java.util.Arrays;
@@ -74,7 +75,7 @@ public class GenerateRorActionSetJob {
 
 		final String jsonConfiguration = IOUtils
 			.toString(
-				SparkAtomicActionJob.class
+				GenerateRorActionSetJob.class
 					.getResourceAsStream("/eu/dnetlib/dhp/actionmanager/ror/action_set_parameters.json"));
 
 		final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
@@ -108,7 +109,7 @@ public class GenerateRorActionSetJob {
 
 	private static void processRorOrganizations(final SparkSession spark,
 		final String inputPath,
-		final String outputPath) throws Exception {
+		final String outputPath) throws IOException {
 
 		readInputPath(spark, inputPath)
 			.map(
@@ -203,7 +204,7 @@ public class GenerateRorActionSetJob {
 
 	private static Dataset<RorOrganization> readInputPath(
 		final SparkSession spark,
-		final String path) throws Exception {
+		final String path) throws IOException {
 
 		try (final FileSystem fileSystem = FileSystem.get(new Configuration());
 			final InputStream is = fileSystem.open(new Path(path))) {

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/ror/model/Address.java

@@ -7,6 +7,8 @@ import com.fasterxml.jackson.annotation.JsonProperty;
 
 public class Address implements Serializable {
 
+	private static final long serialVersionUID = 2444635485253443195L;
+
 	@JsonProperty("lat")
 	private Float lat;
 
@@ -37,8 +39,6 @@ public class Address implements Serializable {
 	@JsonProperty("line")
 	private String line;
 
-	private final static long serialVersionUID = 2444635485253443195L;
-
 	public Float getLat() {
 		return lat;
 	}