Merge branch 'master' into beta

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

@@ -191,7 +191,7 @@ public class ZenodoAPIClient implements Serializable {
 	 * @throws MissingConceptDoiException
 	 */
 	public int newVersion(String concept_rec_id) throws IOException, MissingConceptDoiException {
-		setDepositionId(concept_rec_id);
+		setDepositionId(concept_rec_id, 1);
 		String json = "{}";
 
 		OkHttpClient httpClient = new OkHttpClient.Builder().connectTimeout(600, TimeUnit.SECONDS).build();
@@ -253,9 +253,10 @@ public class ZenodoAPIClient implements Serializable {
 
 	}
 
-	private void setDepositionId(String concept_rec_id) throws IOException, MissingConceptDoiException {
+	private void setDepositionId(String concept_rec_id, Integer page) throws IOException, MissingConceptDoiException {
 
-		ZenodoModelList zenodoModelList = new Gson().fromJson(getPrevDepositions(), ZenodoModelList.class);
+		ZenodoModelList zenodoModelList = new Gson()
+			.fromJson(getPrevDepositions(String.valueOf(page)), ZenodoModelList.class);
 
 		for (ZenodoModel zm : zenodoModelList) {
 			if (zm.getConceptrecid().equals(concept_rec_id)) {
@@ -263,16 +264,23 @@ public class ZenodoAPIClient implements Serializable {
 				return;
 			}
 		}
-
+		if (zenodoModelList.size() == 0)
-		throw new MissingConceptDoiException("The concept record id specified was missing in the list of depositions");
+			throw new MissingConceptDoiException(
+				"The concept record id specified was missing in the list of depositions");
+		setDepositionId(concept_rec_id, page + 1);
 
 	}
 
-	private String getPrevDepositions() throws IOException {
+	private String getPrevDepositions(String page) throws IOException {
+
 		OkHttpClient httpClient = new OkHttpClient.Builder().connectTimeout(600, TimeUnit.SECONDS).build();
 
+		HttpUrl.Builder urlBuilder = HttpUrl.parse(urlString).newBuilder();
+		urlBuilder.addQueryParameter("page", page);
+		String url = urlBuilder.build().toString();
+
 		Request request = new Request.Builder()
-			.url(urlString)
+			.url(url)
 			.addHeader(HttpHeaders.CONTENT_TYPE, ContentType.APPLICATION_JSON.toString()) // add request headers
 			.addHeader(HttpHeaders.AUTHORIZATION, "Bearer " + access_token)
 			.get()

dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/transformation/TransformationJobTest.java

@@ -19,7 +19,9 @@ import org.apache.spark.sql.Encoder;
 import org.apache.spark.sql.Encoders;
 import org.apache.spark.sql.SparkSession;
 import org.apache.spark.util.LongAccumulator;
-import org.junit.jupiter.api.*;
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.DisplayName;
+import org.junit.jupiter.api.Test;
 import org.junit.jupiter.api.extension.ExtendWith;
 import org.junit.jupiter.api.io.TempDir;
 import org.mockito.junit.jupiter.MockitoExtension;
@@ -50,7 +52,7 @@ class TransformationJobTest extends AbstractVocabularyTest {
 	@Test
 	@DisplayName("Test Date cleaner")
 	void testDateCleaner() throws Exception {
-		DateCleaner dc = new DateCleaner();
+		final DateCleaner dc = new DateCleaner();
 		assertEquals("1982-09-20", dc.clean("20/09/1982"));
 		assertEquals("2002-09-20", dc.clean("20-09-2002"));
 		assertEquals("2002-09-20", dc.clean("2002-09-20"));
@@ -68,9 +70,9 @@ class TransformationJobTest extends AbstractVocabularyTest {
 		mr.setProvenance(new Provenance("DSID", "DSNAME", "PREFIX"));
 		mr.setBody(IOUtils.toString(getClass().getResourceAsStream("/eu/dnetlib/dhp/transform/input_zenodo.xml")));
 		// We Load the XSLT transformation Rule from the classpath
-		XSLTTransformationFunction tr = loadTransformationRule("/eu/dnetlib/dhp/transform/zenodo_tr.xslt");
+		final XSLTTransformationFunction tr = loadTransformationRule("/eu/dnetlib/dhp/transform/zenodo_tr.xslt");
 
-		MetadataRecord result = tr.call(mr);
+		final MetadataRecord result = tr.call(mr);
 
 		// Print the record
 		System.out.println(result.getBody());
@@ -86,9 +88,9 @@ class TransformationJobTest extends AbstractVocabularyTest {
 		mr.setProvenance(new Provenance("DSID", "DSNAME", "PREFIX"));
 		mr.setBody(IOUtils.toString(getClass().getResourceAsStream("/eu/dnetlib/dhp/transform/input_itgv4.xml")));
 		// We Load the XSLT transformation Rule from the classpath
-		XSLTTransformationFunction tr = loadTransformationRule("/eu/dnetlib/dhp/transform/zenodo_tr.xslt");
+		final XSLTTransformationFunction tr = loadTransformationRule("/eu/dnetlib/dhp/transform/zenodo_tr.xslt");
 
-		MetadataRecord result = tr.call(mr);
+		final MetadataRecord result = tr.call(mr);
 
 		// Print the record
 		System.out.println(result.getBody());
@@ -108,9 +110,9 @@ class TransformationJobTest extends AbstractVocabularyTest {
 		mr.setProvenance(new Provenance("DSID", "DSNAME", "PREFIX"));
 		mr.setBody(IOUtils.toString(getClass().getResourceAsStream("/eu/dnetlib/dhp/transform/input_itgv4.xml")));
 		// We Load the XSLT transformation Rule from the classpath
-		XSLTTransformationFunction tr = loadTransformationRule(xslTransformationScript);
+		final XSLTTransformationFunction tr = loadTransformationRule(xslTransformationScript);
 
-		MetadataRecord result = tr.call(mr);
+		final MetadataRecord result = tr.call(mr);
 
 		// Print the record
 		System.out.println(result.getBody());
@@ -129,9 +131,9 @@ class TransformationJobTest extends AbstractVocabularyTest {
 		mr.setProvenance(new Provenance("DSID", "DSNAME", "PREFIX"));
 		mr.setBody(IOUtils.toString(getClass().getResourceAsStream("/eu/dnetlib/dhp/transform/input_omicsdi.xml")));
 		// We Load the XSLT transformation Rule from the classpath
-		XSLTTransformationFunction tr = loadTransformationRule(xslTransformationScript);
+		final XSLTTransformationFunction tr = loadTransformationRule(xslTransformationScript);
 
-		MetadataRecord result = tr.call(mr);
+		final MetadataRecord result = tr.call(mr);
 
 		// Print the record
 		System.out.println(result.getBody());
@@ -140,7 +142,8 @@ class TransformationJobTest extends AbstractVocabularyTest {
 
 	@Test
 	@DisplayName("Test TransformSparkJobNode.main with oaiOpenaire_datacite (v4)")
-	void transformTestITGv4OAIdatacite(@TempDir Path testDir) throws Exception {
+	void transformTestITGv4OAIdatacite(@TempDir
+	final Path testDir) throws Exception {
 
 		try (SparkSession spark = SparkSession.builder().config(sparkConf).getOrCreate()) {
 
@@ -203,7 +206,8 @@ class TransformationJobTest extends AbstractVocabularyTest {
 
 	@Test
 	@DisplayName("Test TransformSparkJobNode.main")
-	void transformTest(@TempDir Path testDir) throws Exception {
+	void transformTest(@TempDir
+	final Path testDir) throws Exception {
 
 		try (SparkSession spark = SparkSession.builder().config(sparkConf).getOrCreate()) {
 
@@ -256,6 +260,25 @@ class TransformationJobTest extends AbstractVocabularyTest {
 		}
 	}
 
+	@Test
+	@DisplayName("Test Transform Single XML using cnr_explora_tr XSLTTransformator")
+	void testCnrExploraTransformSaxonHE() throws Exception {
+
+		// We Set the input Record getting the XML from the classpath
+		final MetadataRecord mr = new MetadataRecord();
+
+		mr.setProvenance(new Provenance("openaire____::cnr_explora", "CNR ExploRA", "cnr_________"));
+		mr.setBody(IOUtils.toString(getClass().getResourceAsStream("/eu/dnetlib/dhp/transform/input_cnr_explora.xml")));
+		// We Load the XSLT transformation Rule from the classpath
+		final XSLTTransformationFunction tr = loadTransformationRule("/eu/dnetlib/dhp/transform/cnr_explora_tr.xslt");
+
+		final MetadataRecord result = tr.call(mr);
+
+		// Print the record
+		System.out.println(result.getBody());
+		// TODO Create significant Assert
+	}
+
 	private XSLTTransformationFunction loadTransformationRule(final String path) throws Exception {
 		final String trValue = IOUtils.toString(this.getClass().getResourceAsStream(path));
 		final LongAccumulator la = new LongAccumulator();

dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/cnr_explora_tr.xslt

@@ -0,0 +1,214 @@
+<xsl:stylesheet
+	xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+	xmlns:oaire="http://namespace.openaire.eu/schema/oaire/"
+	xmlns:vocabulary="http://eu/dnetlib/transform/clean"
+	xmlns:dateCleaner="http://eu/dnetlib/transform/dateISO"
+	xmlns:oaf="http://namespace.openaire.eu/oaf"
+	xmlns:oai="http://www.openarchives.org/OAI/2.0/"
+	xmlns:datacite="http://datacite.org/schema/kernel-4"
+	xmlns:dri="http://www.driver-repository.eu/namespace/dri"
+	xmlns:xs="http://www.w3.org/2001/XMLSchema"
+	xmlns:dr="http://www.driver-repository.eu/namespace/dr"
+	xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+	xmlns:dc="http://purl.org/dc/elements/1.1/"
+	exclude-result-prefixes="xsl vocabulary dateCleaner" version="2.0">
+	<xsl:param name="varOfficialName" />
+	<xsl:param name="varDataSourceId" />
+	<xsl:param name="varFP7" select="'corda_______::'" />
+	<xsl:param name="varH2020" select="'corda__h2020::'" />
+	<xsl:param name="repoCode"
+		select="substring-before(//*[local-name() = 'header']/*[local-name()='recordIdentifier'], ':')" />
+	<xsl:param name="index" select="0" />
+	<xsl:param name="transDate" select="current-dateTime()" />
+
+	<xsl:template match="/">
+		<record>
+			<xsl:apply-templates select="//*[local-name() = 'header']" />
+			<metadata>
+				<xsl:call-template name="allElements">
+					<xsl:with-param name="sourceElement" select="//dc:title" />
+					<xsl:with-param name="targetElement" select="'dc:title'" />
+				</xsl:call-template>
+				<xsl:call-template name="allElements">
+					<xsl:with-param name="sourceElement" select="//dc:creator/replace(., '^(.*)\|.*$', '$1')" />
+					<xsl:with-param name="targetElement" select="'dc:creator'" />
+				</xsl:call-template>
+				<xsl:call-template name="allElements">
+					<xsl:with-param name="sourceElement" select="//dc:contributor" />
+					<xsl:with-param name="targetElement" select="'dc:contributor'" />
+				</xsl:call-template>
+				<xsl:call-template name="allElements">
+					<xsl:with-param name="sourceElement" select="//dc:description" />
+					<xsl:with-param name="targetElement" select="'dc:description'" />
+				</xsl:call-template>
+				<xsl:call-template name="allElements">
+					<xsl:with-param name="sourceElement" select="//dc:subject" />
+					<xsl:with-param name="targetElement" select="'dc:subject'" />
+				</xsl:call-template>
+				<xsl:call-template name="allElements">
+					<xsl:with-param name="sourceElement" select="//dc:publisher" />
+					<xsl:with-param name="targetElement" select="'dc:publisher'" />
+				</xsl:call-template>
+				<xsl:call-template name="allElements">
+					<xsl:with-param name="sourceElement" select="//dc:format" />
+					<xsl:with-param name="targetElement" select="'dc:format'" />
+				</xsl:call-template>
+				<xsl:call-template name="allElements">
+					<xsl:with-param name="sourceElement" select="//dc:type" />
+					<xsl:with-param name="targetElement" select="'dc:type'" />
+				</xsl:call-template>
+				<xsl:call-template name="allElements">
+					<xsl:with-param name="sourceElement" select="//dc:source" />
+					<xsl:with-param name="targetElement" select="'dc:source'" />
+				</xsl:call-template>
+				<dc:language>
+					<xsl:value-of select="vocabulary:clean( //dc:language, 'dnet:languages')" />
+				</dc:language>
+				<xsl:call-template name="allElements">
+					<xsl:with-param name="sourceElement" select="//dc:rights" />
+					<xsl:with-param name="targetElement" select="'dc:rights'" />
+				</xsl:call-template>
+				<xsl:call-template name="allElements">
+					<xsl:with-param name="sourceElement" select="//dc:relation[not(starts-with(.,'info:cnr-pdr'))]" />
+					<xsl:with-param name="targetElement" select="'dc:relation'" />
+				</xsl:call-template>
+				
+				<xsl:call-template name="allElements">
+					<xsl:with-param name="sourceElement" select="//dc:identifier[starts-with(., 'http')]" />
+					<xsl:with-param name="targetElement" select="'dc:identifier'" />
+				</xsl:call-template>
+				<xsl:for-each select="//dc:relation">
+					<xsl:if	test="matches(normalize-space(.), '(info:eu-repo/grantagreement/ec/fp7/)(\d\d\d\d\d\d)(.*)', 'i')">
+						<oaf:projectid>
+							<xsl:value-of select="concat($varFP7, replace(normalize-space(.), '(info:eu-repo/grantagreement/ec/fp7/)(\d\d\d\d\d\d)(.*)', '$2', 'i'))" />
+						</oaf:projectid>
+					</xsl:if>
+					<xsl:if test="matches(normalize-space(.), '(info:eu-repo/grantagreement/ec/h2020/)(\d\d\d\d\d\d)(.*)', 'i')">
+						<oaf:projectid>
+							<xsl:value-of select="concat($varH2020, replace(normalize-space(.), '(info:eu-repo/grantagreement/ec/h2020/)(\d\d\d\d\d\d)(.*)', '$2', 'i'))" />
+						</oaf:projectid>
+					</xsl:if>
+				</xsl:for-each>
+				
+				<oaf:accessrights>
+					<xsl:value-of select="vocabulary:clean( //dc:rights, 'dnet:access_modes')" />
+				</oaf:accessrights>
+				
+				<xsl:variable name="varCobjCategory" select="vocabulary:clean( //dc:type, 'dnet:publication_resource')" />
+				<xsl:variable name="varSuperType" select="vocabulary:clean( $varCobjCategory, 'dnet:result_typologies')" />				
+				<dr:CobjCategory type="{$varSuperType}"><xsl:value-of select="$varCobjCategory" /></dr:CobjCategory>
+				
+				
+				<xsl:variable name="varRefereedConvt" select="for $i in (//dc:type, //dc:description, //oai:setSpec) return vocabulary:clean( normalize-space($i), 'dnet:review_levels')" />
+				<xsl:variable name="varRefereedIdntf" select="(//*[string(node-name(.)) = 'dc:identifier' and matches(lower-case(.), '(^|.*[\.\-_/\s\(\)%\d#])pre[\.\-_/\s\(\)%\d#]?prints?([\.\-_/\s\(\)%\d#].*)?$')][count(//dc:identifier) = 1]/'0002', //*[string(node-name(.)) = 'dc:identifier' and matches(lower-case(.), '(^|.*[\.\-_/\s\(\)%\d#])refereed([\.\-_/\s\(\)\d%\d#].*)?$')]/'0001', //*[string(node-name(.)) = 'dc:identifier' and matches(lower-case(.), '.*-peer-reviewed-(fulltext-)?article-.*')]/'0001')" />
+				<xsl:variable name="varRefereedSourc" select="//*[string(node-name(.)) = ('dc:source', 'dc:publisher') and matches(lower-case(.), '^(.*\s)?pre[\s\-_]*prints?([\s\.,].*)?$')]/'0002'" />
+				<xsl:variable name="varRefereedDescr" select="(//dc:description[matches(lower-case(.), '.*(this\s*book|this\s*volume|it)\s*constitutes\s*the\s*(thoroughly\s*)?refereed') or matches(lower-case(.), '.*peer[\.\-_/\s\(\)]?review\s*under\s*responsibility\s*of.*') or matches(lower-case(.), '(this|a)\s*(article|preprint)\s*(has\s*been\s*)?(peer[\-\s]*)?reviewed\s*and\s*recommended\s*by\s*peer[\-\s]*community')]/'0001', //dc:description[matches(., '^version\s*(préliminaire.*|preliminary.*|0$)')]/'0002')" />
+				<xsl:variable name="varRefereedTitle" select="(//dc:title[matches(lower-case(.), '.*\[.*peer[\s\-\._]*review\s*:.*\]\s*$')]/'0001', //dc:title[matches(lower-case(.), '.*\(\s*pre[\s\-\._]*prints?\s*\)\s*$')]/'0002')" />
+				<xsl:variable name="varRefereedSubjt" select="(//dc:subject[matches(lower-case(.), '^\s*refereed\s*$')][//oaf:datasourceprefix = 'narcis______']/'0001', //dc:subject[matches(lower-case(.), '^\s*no[nt].{0,3}refereed\s*$')][//oaf:datasourceprefix = 'narcis______']/'0002')" />
+				<xsl:variable name="varRefereed" select="($varRefereedConvt, $varRefereedIdntf, $varRefereedSourc, $varRefereedDescr, $varRefereedTitle, $varRefereedSubjt)" />
+				<xsl:choose>
+					<xsl:when test="count($varRefereed[. = '0001']) &gt; 0">
+						<oaf:refereed>
+							<xsl:value-of select="'0001'" />
+						</oaf:refereed>
+					</xsl:when>
+					<xsl:when test="count($varRefereed[. = '0002']) &gt; 0">
+						<oaf:refereed>
+							<xsl:value-of select="'0002'" />
+						</oaf:refereed>
+					</xsl:when>
+				</xsl:choose>
+				
+				<oaf:dateAccepted>
+					<xsl:value-of select="dateCleaner:dateISO( //dc:date[1] )" />
+				</oaf:dateAccepted>
+				
+				<xsl:if test="//dc:relation[starts-with(., 'http')] and //dc:rights[.='info:eu-repo/semantics/openAccess']">
+					<oaf:fulltext>
+						<xsl:value-of select="//dc:relation[starts-with(., 'http')]" />
+					</oaf:fulltext>
+				</xsl:if>
+				
+				<oaf:hostedBy name="{$varOfficialName}" id="{$varDataSourceId}" />
+				<oaf:collectedFrom name="{$varOfficialName}" id="{$varDataSourceId}ß" />
+
+				<xsl:variable name="varKnownFileEndings" select="('.bmp', '.doc', '.docx', '.epub', '.flv', '.jpeg', '.jpg', '.m4v', '.mp4', '.mpg', '.odp', '.pdf', '.png', '.ppt', '.tiv', '.txt', '.xls', '.xlsx', '.zip')" />
+				<xsl:variable name="varIdDoi" select="distinct-values((//dc:identifier[starts-with(., '10.')][matches(., '(10[.][0-9]{4,}[^\s/&gt;]*/[^\s&gt;]+)')], //dc:identifier[starts-with(., 'http') and (contains(., '://dx.doi.org/10.') or contains(., '://doi.org/10.'))]/substring-after(., 'doi.org/'), //dc:identifier[starts-with(lower-case(.), 'doi:10.')]/substring-after(lower-case(.), 'doi:')))" />
+				<xsl:for-each select="$varIdDoi">
+					<oaf:identifier identifierType="doi">
+						<xsl:value-of select="." />
+					</oaf:identifier>
+				</xsl:for-each>
+				
+				<xsl:variable name="varIdHdl" select="distinct-values(//dc:identifier[starts-with(., 'http') and contains(., '://hdl.handle.net/')]/substring-after(., 'hdl.handle.net/'))" />
+				<xsl:for-each select="$varIdHdl" >
+					<oaf:identifier identifierType="handle">
+						<xsl:value-of select="." />
+					</oaf:identifier>
+				</xsl:for-each>
+				
+				<xsl:variable name="varIdUrn" select="distinct-values(//dc:identifier[starts-with(., 'urn:nbn:nl:') or starts-with(., 'URN:NBN:NL:')])" />
+				<xsl:for-each select="$varIdUrn">
+					<oaf:identifier identifierType="urn">
+						<xsl:value-of select="." />
+					</oaf:identifier>
+				</xsl:for-each>
+				
+				<xsl:variable name="varOrigBaseUrl" select="//*[local-name() = 'about']/*[local-name() = 'provenance']//*[local-name() = 'originDescription' and not(./*[local-name() = 'originDescription'])]/*[local-name() = 'baseURL']" />
+				<xsl:variable name="varIdLdpg" select="distinct-values(//dc:identifier[(contains(substring-after(., '://'), '/') and contains($varOrigBaseUrl, substring-before(substring-after(., '://'), '/'))) or (contains(substring-after(., '://'), ':') and contains($varOrigBaseUrl, substring-before(substring-after(., '://'), ':')))][not(replace(lower-case(.), '.*(\.[a-z]*)$', '$1') = $varKnownFileEndings)])" />
+				<xsl:for-each select="$varIdLdpg">
+					<oaf:identifier identifierType="landingPage">
+						<xsl:value-of select="." />
+					</oaf:identifier>
+				</xsl:for-each>
+				
+				<xsl:variable name="varIdUrl" select="distinct-values(//dc:identifier[starts-with(., 'http')][not(contains(., '://dx.doi.org/') or contains(., '://doi.org/') or contains(., '://hdl.handle.net/'))][count(index-of($varIdLdpg, .)) = 0])" />
+				<xsl:for-each select="$varIdUrl">
+					<oaf:identifier identifierType="url">
+						<xsl:value-of select="." />
+					</oaf:identifier>
+				</xsl:for-each>
+				
+				<xsl:for-each select="//oai:setSpec">
+					<xsl:variable name="rorDsId" select="vocabulary:clean(., 'cnr:institutes')" />
+					<xsl:if test="contains($rorDsId, '/ror.org/')">
+						<oaf:relation relType="resultOrganization" subRelType="affiliation" relClass="hasAuthorInstitution">
+							<xsl:value-of select="concat('ror_________::', $rorDsId)" />
+						</oaf:relation>
+					</xsl:if>
+				</xsl:for-each>
+				
+			</metadata>
+			
+			<xsl:copy-of select="//*[local-name() = 'about']" />
+		</record>
+	</xsl:template>
+	
+	
+	<xsl:template name="allElements">
+		<xsl:param name="sourceElement" />
+		<xsl:param name="targetElement" />
+	
+		<xsl:for-each select="$sourceElement">
+			<xsl:element name="{$targetElement}">
+				<xsl:value-of select="normalize-space(.)" />
+			</xsl:element>
+		</xsl:for-each>
+	</xsl:template>
+	
+	<xsl:template match="//*[local-name() = 'header']">
+		<xsl:copy>
+			<xsl:apply-templates select="node()|@*" />
+			<xsl:element name="dr:dateOfTransformation">
+				<xsl:value-of select="$transDate" />
+			</xsl:element>
+		</xsl:copy>
+	</xsl:template>
+	
+	<xsl:template match="node()|@*">
+		<xsl:copy>
+			<xsl:apply-templates select="node()|@*" />
+		</xsl:copy>
+	</xsl:template>
+	
+</xsl:stylesheet>

dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/input_cnr_explora.xml

@@ -0,0 +1,57 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<record xmlns="http://www.openarchives.org/OAI/2.0/"> 
+  <header> 
+    <identifier><![CDATA[oai:it.cnr:prodotti:433382]]></identifier>  
+    <datestamp><![CDATA[2020-11-30T15:32:03Z]]></datestamp>  
+    <setSpec><![CDATA[openaire]]></setSpec>  
+    <setSpec><![CDATA[CDS027]]></setSpec>  
+    <setSpec><![CDATA[CDS080]]></setSpec> 
+  </header>  
+  <metadata> 
+    <oai_dc:dc xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">  
+      <dc:type><![CDATA[info:eu-repo/semantics/conferenceObject]]></dc:type>  
+      <dc:type><![CDATA[Presentazione]]></dc:type>  
+      <dc:title><![CDATA[A multiscale observing approach for understanding acidification process in a marginal sea (northern Adriatic)]]></dc:title>  
+      <dc:creator><![CDATA[Cantoni C.]]></dc:creator>  
+      <dc:creator><![CDATA[Barba L.]]></dc:creator>  
+      <dc:creator><![CDATA[Bastianini M.]]></dc:creator>  
+      <dc:creator><![CDATA[Bortoluzzi G.]]></dc:creator>  
+      <dc:creator><![CDATA[Celio M.]]></dc:creator>  
+      <dc:creator><![CDATA[Chiggiato J.]]></dc:creator>  
+      <dc:creator><![CDATA[Cozzi S.]]></dc:creator>  
+      <dc:creator><![CDATA[Luchetta A.]]></dc:creator>  
+      <dc:creator><![CDATA[Ravaioli M.]]></dc:creator>  
+      <dc:creator><![CDATA[Sparnocchia S.]]></dc:creator>  
+      <dc:language><![CDATA[eng]]></dc:language>  
+      <dc:description><![CDATA[The Northern Adriatic is a shallow, semi-enclosed industrialized sub-basin of the Mediterranean affected by significant ecosystem
+changes, which are studied through several research activities including the long-term monitoring of ILTER international network.
+Changes of pHT (-0.06) and TA (+74 ?mol/kg) in dense winter waters over the last 25 years already showed that this area is prone to
+acidification process under a complex inorganic carbon chemistry variability. To understand these changes, monthly sampling of the
+main biogeochemical and biological parameters has been carrying out since 2008 by a fixed station (PALOMA, Gulf of Trieste). In 2013
+the site has been implemented with continuous pCO2 measurements at 3 m depth and has been regularly visiting during basin wide
+surveys for the last two years. The combination of automated in situ measurements, monthly samplings and basin scale
+oceanographic cruises is used to better understand the processes controlling air-sea CO2 fluxes and inorganic carbon chemistry under
+three different scenarios: an extreme event of dense water formation, the phytoplankton blooms associated with riverine inputs and
+the late-summer marked oxygen under saturation in the deeper waters.]]></dc:description>  
+      <dc:source><![CDATA[ASLO - Aquatic Sciences Meeting, Granada, Spagna, 22-27/02/2015]]></dc:source>  
+      <dc:source><![CDATA[info:cnr-pdr/source/autori:Cantoni C., Barba L., Bastianini M., Bortoluzzi G., Celio M., Chiggiato J., Cozzi S., Luchetta A., Ravaioli M., Sparnocchia S./congresso_nome:ASLO - Aquatic Sciences Meeting/congresso_luogo:Granada, Spagna/congresso_data:22-27%2F02%2F2015/anno:2015/pagina_da:/pagina_a:/intervallo_pagine:]]></dc:source>  
+      <dc:date><![CDATA[2015]]></dc:date>  
+      <dc:identifier><![CDATA[http://www.cnr.it/prodotto/i/433382]]></dc:identifier>  
+      <dc:identifier><![CDATA[https://publications.cnr.it/doc/433382]]></dc:identifier>  
+      <dc:identifier><![CDATA[http://sgmeet.com/aslo/granada2015/]]></dc:identifier>  
+      <dc:relation><![CDATA[info:eu-repo/grantAgreement/EC/FP7/211574//Integrated Carbon Observation System/ICOS]]></dc:relation>  
+      <dc:relation><![CDATA[info:cnr-pdr/author/matricola:502/SPARNOCCHIA/STEFANIA]]></dc:relation>  
+      <dc:relation><![CDATA[info:cnr-pdr/author/matricola:990/BASTIANINI/MAURO]]></dc:relation>  
+      <dc:relation><![CDATA[info:cnr-pdr/author/matricola:5185/BARBA/LUISA]]></dc:relation>  
+      <dc:relation><![CDATA[info:cnr-pdr/author/matricola:5453/COZZI/STEFANO]]></dc:relation>  
+      <dc:relation><![CDATA[info:cnr-pdr/author/matricola:12491/LUCHETTA/ANNA]]></dc:relation>  
+      <dc:relation><![CDATA[info:cnr-pdr/author/matricola:12837/CANTONI/CAROLINA]]></dc:relation>  
+      <dc:relation><![CDATA[info:cnr-pdr/author/matricola:18161/RAVAIOLI/MARIANGELA]]></dc:relation>  
+      <dc:rights><![CDATA[info:eu-repo/semantics/openAccess]]></dc:rights>  
+      <dc:subject><![CDATA[ocean acidification]]></dc:subject>  
+      <dc:subject><![CDATA[Northern Adriatic Sea]]></dc:subject>  
+      <dc:subject><![CDATA[inorganic carbon system]]></dc:subject>  
+      <dc:subject><![CDATA[PALOMA]]></dc:subject> 
+    </oai_dc:dc> 
+  </metadata> 
+</record>

dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/synonyms.txt

@@ -1232,4 +1232,268 @@ dnet:review_levels @=@ 0001 @=@ 印刷物/電子媒体-学術雑誌論文（査
 dnet:review_levels @=@ 0001 @=@ 印刷物/電子媒体-紀要論文（査読有り）
 dnet:review_levels @=@ 0001 @=@ 印刷物/電子媒体-雑誌記事（査読有り）
 dnet:review_levels @=@ 0001 @=@ 原著論文（査読有り）
-dnet:review_levels @=@ 0001 @=@ 査読論文
+dnet:review_levels @=@ 0001 @=@ 査読論文
+cnr:institutes @=@ https://ror.org/00brf2d87 @=@ CDS001
+cnr:institutes @=@ https://ror.org/00brf2d87 @=@ IDASC - Istituto di Acustica e Sensoristica \"Orso Mario Corbino\"
+cnr:institutes @=@ https://ror.org/006qkqr45 @=@ CDS002
+cnr:institutes @=@ https://ror.org/006qkqr45 @=@ IAMC - Istituto per l'ambiente marino costiero
+cnr:institutes @=@ https://ror.org/054ye0e45 @=@ CDS003
+cnr:institutes @=@ https://ror.org/054ye0e45 @=@ IASI - Istituto di analisi dei sistemi ed informatica \"Antonio Ruberti\"
+cnr:institutes @=@ https://ror.org/00ygy3d85 @=@ CDS004
+cnr:institutes @=@ https://ror.org/00ygy3d85 @=@ IAC - Istituto per le applicazioni del calcolo \"Mauro Picone\"
+cnr:institutes @=@ https://ror.org/000sy1f36 @=@ CDS005
+cnr:institutes @=@ https://ror.org/000sy1f36 @=@ IASF - Istituto di astrofisica spaziale e fisica cosmica
+cnr:institutes @=@ https://ror.org/00x5wpm25 @=@ CDS006
+cnr:institutes @=@ https://ror.org/00x5wpm25 @=@ IBAM - Istituto per i beni archeologici e monumentali
+cnr:institutes @=@ https://ror.org/03eqeqg74 @=@ CDS007
+cnr:institutes @=@ https://ror.org/03eqeqg74 @=@ IBP - Istituto di biochimica delle proteine
+cnr:institutes @=@ https://ror.org/041xzk838 @=@ CDS008
+cnr:institutes @=@ https://ror.org/041xzk838 @=@ IBF - Istituto di biofisica
+cnr:institutes @=@ https://ror.org/00s2j5046 @=@ CDS009
+cnr:institutes @=@ https://ror.org/00s2j5046 @=@ IBFM - Istituto di bioimmagini e fisiologia molecolare
+cnr:institutes @=@ __CDS010__ @=@ CDS010
+cnr:institutes @=@ __CDS010__ @=@ IBAF - Istituto di biologia agro-ambientale e forestale
+cnr:institutes @=@ __CDS011__ @=@ CDS011
+cnr:institutes @=@ __CDS011__ @=@ IBC - Istituto di biologia cellulare
+cnr:institutes @=@ https://ror.org/02e5sbe24 @=@ CDS012
+cnr:institutes @=@ https://ror.org/02e5sbe24 @=@ IBBA - Istituto di biologia e biotecnologia agraria
+cnr:institutes @=@ https://ror.org/01nyatq71 @=@ CDS013
+cnr:institutes @=@ https://ror.org/01nyatq71 @=@ IBPM - Istituto di biologia e patologia molecolari
+cnr:institutes @=@ https://ror.org/01dy2q607 @=@ CDS014
+cnr:institutes @=@ https://ror.org/01dy2q607 @=@ IBIM - Istituto di biomedicina e di immunologia molecolare \"Alberto Monroy\"
+cnr:institutes @=@ https://ror.org/05nzf7q96 @=@ CDS015
+cnr:institutes @=@ https://ror.org/05nzf7q96 @=@ IBIOM - Istituto di Biomembrane, Bioenergetica e Biotecnologie Molecolari
+cnr:institutes @=@ https://ror.org/05m1yqp60 @=@ CDS016
+cnr:institutes @=@ https://ror.org/05m1yqp60 @=@ IBIMET - Istituto di biometeorologia
+cnr:institutes @=@ https://ror.org/03rqtqb02 @=@ CDS017
+cnr:institutes @=@ https://ror.org/03rqtqb02 @=@ IBB - Istituto di biostrutture e bioimmagini
+cnr:institutes @=@ https://ror.org/04r5fge26 @=@ CDS018
+cnr:institutes @=@ https://ror.org/04r5fge26 @=@ ICAR - Istituto di calcolo e reti ad alte prestazioni
+cnr:institutes @=@ https://ror.org/03wyf0g15 @=@ CDS019
+cnr:institutes @=@ https://ror.org/03wyf0g15 @=@ ICB - Istituto di chimica biomolecolare
+cnr:institutes @=@ https://ror.org/02fkw1114 @=@ CDS020
+cnr:institutes @=@ https://ror.org/02fkw1114 @=@ ICCOM - Istituto di chimica dei composti organo metallici
+cnr:institutes @=@ https://ror.org/0141vn777 @=@ CDS021
+cnr:institutes @=@ https://ror.org/0141vn777 @=@ ICRM - Istituto di chimica del riconoscimento molecolare
+cnr:institutes @=@ __CDS022__ @=@ CDS022
+cnr:institutes @=@ __CDS022__ @=@ ICTP - Istituto di chimica e tecnologia dei polimeri
+cnr:institutes @=@ __CDS023__ @=@ CDS023
+cnr:institutes @=@ __CDS023__ @=@ ICIS - Istituto di chimica inorganica e delle superfici
+cnr:institutes @=@ https://ror.org/00be3zh53 @=@ CDS024
+cnr:institutes @=@ https://ror.org/00be3zh53 @=@ ISASI - Istituto di Scienze Applicate e Sistemi Intelligenti \"Eduardo Caianiello\"
+cnr:institutes @=@ __CDS025__ @=@ CDS025
+cnr:institutes @=@ __CDS025__ @=@ ICEVO - Istituto di Studi sulle Civiltà dell'Egeo e del Vicino Oriente
+cnr:institutes @=@ https://ror.org/02ynrme92 @=@ CDS026
+cnr:institutes @=@ https://ror.org/02ynrme92 @=@ ICVBC - Istituto per la conservazione e valorizzazione dei beni culturali
+cnr:institutes @=@ https://ror.org/05wba8r86 @=@ CDS027
+cnr:institutes @=@ https://ror.org/05wba8r86 @=@ IC - Istituto di cristallografia
+cnr:institutes @=@ https://ror.org/03z58xd74 @=@ CDS028
+cnr:institutes @=@ https://ror.org/03z58xd74 @=@ IDPA - Istituto per la dinamica dei processi ambientali
+cnr:institutes @=@ https://ror.org/00n4jbh84 @=@ CDS029
+cnr:institutes @=@ https://ror.org/00n4jbh84 @=@ IEIIT - Istituto di elettronica e di ingegneria dell'informazione e delle telecomunicazioni
+cnr:institutes @=@ https://ror.org/04sn06036 @=@ CDS030
+cnr:institutes @=@ https://ror.org/04sn06036 @=@ IEOS - Istituto per l'endocrinologia e l'oncologia \"Gaetano Salvatore\"
+cnr:institutes @=@ https://ror.org/01rg40y89 @=@ CDS031
+cnr:institutes @=@ https://ror.org/01rg40y89 @=@ ICMATE - Istituto di Chimica della Materia Condensata e di Tecnologie per l'Energia
+cnr:institutes @=@ https://ror.org/00dqega85 @=@ CDS032
+cnr:institutes @=@ https://ror.org/00dqega85 @=@ IFAC - Istituto di fisica applicata \"Nello Carrara\"
+cnr:institutes @=@ https://ror.org/02n2bgz18 @=@ CDS033
+cnr:institutes @=@ https://ror.org/02n2bgz18 @=@ IFP - Istituto di fisica del plasma \"Piero Caldirola\"
+cnr:institutes @=@ __CDS034__ @=@ CDS034
+cnr:institutes @=@ __CDS034__ @=@ IFSI - Istituto di fisica dello spazio interplanetario
+cnr:institutes @=@ https://ror.org/01kdj2848 @=@ CDS035
+cnr:institutes @=@ https://ror.org/01kdj2848 @=@ IFC - Istituto di fisiologia clinica
+cnr:institutes @=@ https://ror.org/049ebw417 @=@ CDS036
+cnr:institutes @=@ https://ror.org/049ebw417 @=@ IFN - Istituto di fotonica e nanotecnologie
+cnr:institutes @=@ https://ror.org/01f5tnx94 @=@ CDS037
+cnr:institutes @=@ https://ror.org/01f5tnx94 @=@ IGI - Istituto gas ionizzati
+cnr:institutes @=@ __CDS038__ @=@ CDS038
+cnr:institutes @=@ __CDS038__ @=@ IGP - Istituto di genetica delle popolazioni
+cnr:institutes @=@ https://ror.org/04hadk112 @=@ CDS039
+cnr:institutes @=@ https://ror.org/04hadk112 @=@ IGB - Istituto di genetica e biofisica \"Adriano Buzzati Traverso\"
+cnr:institutes @=@ https://ror.org/03qpd8w66 @=@ CDS040
+cnr:institutes @=@ https://ror.org/03qpd8w66 @=@ IGM - Istituto di genetica molecolare \"Luigi Luca Cavalli Sforza\"
+cnr:institutes @=@ https://ror.org/01gtsa866 @=@ CDS041
+cnr:institutes @=@ https://ror.org/01gtsa866 @=@ IBBR - Istituto di Bioscienze e Biorisorse
+cnr:institutes @=@ https://ror.org/00ytw6m58 @=@ CDS042
+cnr:institutes @=@ https://ror.org/00ytw6m58 @=@ IGAG - Istituto di geologia ambientale e geoingegneria
+cnr:institutes @=@ https://ror.org/015bmra78 @=@ CDS043
+cnr:institutes @=@ https://ror.org/015bmra78 @=@ IGG - Istituto di geoscienze e georisorse
+cnr:institutes @=@ https://ror.org/02gdcn153 @=@ CDS044
+cnr:institutes @=@ https://ror.org/02gdcn153 @=@ IIT - Istituto di informatica e telematica
+cnr:institutes @=@ __CDS045__ @=@ CDS045
+cnr:institutes @=@ __CDS045__ @=@ ISIB - Istituto di ingegneria biomedica
+cnr:institutes @=@ https://ror.org/05hky6p02 @=@ CDS046
+cnr:institutes @=@ https://ror.org/05hky6p02 @=@ IIA - Istituto sull'inquinamento atmosferico
+cnr:institutes @=@ https://ror.org/011n2hw53 @=@ CDS047
+cnr:institutes @=@ https://ror.org/011n2hw53 @=@ ILIESI - Istituto per il lessico intellettuale europeo e storia delle idee
+cnr:institutes @=@ https://ror.org/028g3pe33 @=@ CDS048
+cnr:institutes @=@ https://ror.org/028g3pe33 @=@ ILC - Istituto di linguistica computazionale \"Antonio Zampolli\"
+cnr:institutes @=@ __CDS049__ @=@ CDS049
+cnr:institutes @=@ __CDS049__ @=@ IMAMOTER - Istituto per le macchine agricole e movimento terra
+cnr:institutes @=@ https://ror.org/03m0n3c07 @=@ CDS050
+cnr:institutes @=@ https://ror.org/03m0n3c07 @=@ IMATI - Istituto di matematica applicata e tecnologie informatiche \"Enrico Magenes\"
+cnr:institutes @=@ __CDS051__ @=@ CDS051
+cnr:institutes @=@ __CDS051__ @=@ IMCB - Istituto per i materiali compositi e biomedici
+cnr:institutes @=@ https://ror.org/00z8ws214 @=@ CDS052
+cnr:institutes @=@ https://ror.org/00z8ws214 @=@ IMEM - Istituto dei materiali per l'elettronica ed il magnetismo
+cnr:institutes @=@ __CDS053__ @=@ CDS053
+cnr:institutes @=@ __CDS053__ @=@ ISB - Istituto per i Sistemi Biologici
+cnr:institutes @=@ https://ror.org/00bc51d88 @=@ CDS054
+cnr:institutes @=@ https://ror.org/00bc51d88 @=@ NANOTEC - Istituto di Nanotecnologia
+cnr:institutes @=@ https://ror.org/024ye7w89 @=@ CDS055
+cnr:institutes @=@ https://ror.org/024ye7w89 @=@ IMAA - Istituto di metodologie per l'analisi ambientale
+cnr:institutes @=@ __CDS056__ @=@ CDS056
+cnr:institutes @=@ __CDS056__ @=@ IMGC - Istituto di metrologia \"Gustavo Colonnetti\"
+cnr:institutes @=@ https://ror.org/05vk2g845 @=@ CDS057
+cnr:institutes @=@ https://ror.org/05vk2g845 @=@ IMM - Istituto per la microelettronica e microsistemi
+cnr:institutes @=@ https://ror.org/02qwy8e97 @=@ CDS058
+cnr:institutes @=@ https://ror.org/02qwy8e97 @=@ IM - Istituto motori
+cnr:institutes @=@ __CDS059__ @=@ CDS059
+cnr:institutes @=@ __CDS059__ @=@ INMM - Istituto di neurobiologia e medicina molecolare
+cnr:institutes @=@ https://ror.org/02dr63s31 @=@ CDS060
+cnr:institutes @=@ https://ror.org/02dr63s31 @=@ IRGB - Istituto di Ricerca Genetica e Biomedica
+cnr:institutes @=@ https://ror.org/0240rwx68 @=@ CDS061
+cnr:institutes @=@ https://ror.org/0240rwx68 @=@ IN - Istituto di neuroscienze
+cnr:institutes @=@ https://ror.org/02rzxrg25 @=@ CDS062
+cnr:institutes @=@ https://ror.org/02rzxrg25 @=@ OVI - Istituto opera del vocabolario italiano
+cnr:institutes @=@ https://ror.org/05patmk97 @=@ CDS063
+cnr:institutes @=@ https://ror.org/05patmk97 @=@ IPCF - Istituto per i processi chimico-fisici
+cnr:institutes @=@ __CDS064__ @=@ CDS064
+cnr:institutes @=@ __CDS064__ @=@ IPP - Istituto per la protezione delle piante
+cnr:institutes @=@ https://ror.org/029st3z03 @=@ CDS065
+cnr:institutes @=@ https://ror.org/029st3z03 @=@ IRA - Istituto di radioastronomia
+cnr:institutes @=@ https://ror.org/0040zx077 @=@ CDS066
+cnr:institutes @=@ https://ror.org/0040zx077 @=@ IRPI - Istituto di ricerca per la protezione idrogeologica
+cnr:institutes @=@ https://ror.org/044bfsy89 @=@ CDS067
+cnr:institutes @=@ https://ror.org/044bfsy89 @=@ IRCRES - Istituto di Ricerca sulla Crescita Economica Sostenibile
+cnr:institutes @=@ https://ror.org/01n1ayq61 @=@ CDS068
+cnr:institutes @=@ https://ror.org/01n1ayq61 @=@ IRPPS - Istituto di ricerche sulla popolazione e le politiche sociali
+cnr:institutes @=@ https://ror.org/02db0kh50 @=@ CDS069
+cnr:institutes @=@ https://ror.org/02db0kh50 @=@ IRSA - Istituto di ricerca sulle acque
+cnr:institutes @=@ https://ror.org/05813wx75 @=@ CDS070
+cnr:institutes @=@ https://ror.org/05813wx75 @=@ IRC - Istituto di ricerche sulla combustione
+cnr:institutes @=@ https://ror.org/04vnwke91 @=@ CDS071
+cnr:institutes @=@ https://ror.org/04vnwke91 @=@ IRISS - Istituto di Ricerca su Innovazione e Servizi per lo Sviluppo
+cnr:institutes @=@ https://ror.org/02wxw4x45 @=@ CDS072
+cnr:institutes @=@ https://ror.org/02wxw4x45 @=@ IREA - Istituto per il rilevamento elettromagnetico dell'ambiente
+cnr:institutes @=@ https://ror.org/01j6drw72 @=@ CDS073
+cnr:institutes @=@ https://ror.org/01j6drw72 @=@ ISTEC - Istituto di scienza e tecnologia dei materiali ceramici
+cnr:institutes @=@ https://ror.org/05kacka20 @=@ CDS074
+cnr:institutes @=@ https://ror.org/05kacka20 @=@ ISTI - Istituto di scienza e tecnologie dell'informazione \"Alessandro Faedo\"
+cnr:institutes @=@ https://ror.org/00n8ttd98 @=@ CDS075
+cnr:institutes @=@ https://ror.org/00n8ttd98 @=@ ISAC - Istituto di scienze dell'atmosfera e del clima
+cnr:institutes @=@ https://ror.org/0013zhk30 @=@ CDS076
+cnr:institutes @=@ https://ror.org/0013zhk30 @=@ ISA - Istituto di Scienze dell'Alimentazione
+cnr:institutes @=@ https://ror.org/03x7xkr71 @=@ CDS077
+cnr:institutes @=@ https://ror.org/03x7xkr71 @=@ ISPA - Istituto di scienze delle produzioni alimentari
+cnr:institutes @=@ https://ror.org/05w9g2j85 @=@ CDS078
+cnr:institutes @=@ https://ror.org/05w9g2j85 @=@ ISTC - Istituto di scienze e tecnologie della cognizione
+cnr:institutes @=@ https://ror.org/032tyv240 @=@ CDS079
+cnr:institutes @=@ https://ror.org/032tyv240 @=@ ISTM - Istituto di scienze e tecnologie molecolari
+cnr:institutes @=@ https://ror.org/02hdf6119 @=@ CDS080
+cnr:institutes @=@ https://ror.org/02hdf6119 @=@ ISMAR - Istituto di scienze marine
+cnr:institutes @=@ https://ror.org/01yg57d71 @=@ CDS081
+cnr:institutes @=@ https://ror.org/01yg57d71 @=@ ISN - Istituto di scienze neurologiche
+cnr:institutes @=@ https://ror.org/021z1mz76 @=@ CDS082
+cnr:institutes @=@ https://ror.org/021z1mz76 @=@ ISOF - Istituto per la sintesi organica e la fotoreattività
+cnr:institutes @=@ https://ror.org/01wqae691 @=@ CDS083
+cnr:institutes @=@ https://ror.org/01wqae691 @=@ ISPAAM - Istituto per il sistema produzione animale in ambiente Mediterraneo
+cnr:institutes @=@ __CDS084__ @=@ CDS084
+cnr:institutes @=@ __CDS084__ @=@ ISAFoM - Istituto per i sistemi agricoli e forestali del mediterraneo
+cnr:institutes @=@ https://ror.org/00awwz417 @=@ CDS085
+cnr:institutes @=@ https://ror.org/00awwz417 @=@ ISPF - Istituto per la storia del pensiero filosofico e scientifico moderno
+cnr:institutes @=@ https://ror.org/03a111314 @=@ CDS086
+cnr:institutes @=@ https://ror.org/03a111314 @=@ ISEM - Istituto di storia dell'Europa mediterranea
+cnr:institutes @=@ https://ror.org/01zz9wh30 @=@ CDS087
+cnr:institutes @=@ https://ror.org/01zz9wh30 @=@ ISM - Istituto di struttura della materia
+cnr:institutes @=@ https://ror.org/035y5td47 @=@ CDS088
+cnr:institutes @=@ https://ror.org/035y5td47 @=@ ISGI - Istituto di studi giuridici internazionali
+cnr:institutes @=@ __CDS089__ @=@ CDS089
+cnr:institutes @=@ __CDS089__ @=@ ISPRI - Istituto sperimentale di studi socio - economici sull'innovazione e le politiche della ricerca
+cnr:institutes @=@ https://ror.org/051t1q308 @=@ CDS090
+cnr:institutes @=@ https://ror.org/051t1q308 @=@ ISSIA - Istituto di studi sui sistemi intelligenti per l'automazione
+cnr:institutes @=@ https://ror.org/05k3cs357 @=@ CDS091
+cnr:institutes @=@ https://ror.org/05k3cs357 @=@ ISSIRFA - Istituto di studi sui sistemi regionali federali e sulle autonomie \"Massimo Severo Giannini\"
+cnr:institutes @=@ https://ror.org/02gcxw165 @=@ CDS092
+cnr:institutes @=@ https://ror.org/02gcxw165 @=@ ISMA - Istituto di Studi sul Mediterraneo Antico
+cnr:institutes @=@ https://ror.org/05db0es39 @=@ CDS093
+cnr:institutes @=@ https://ror.org/05db0es39 @=@ ISMed - Istituto di studi sul Mediterraneo
+cnr:institutes @=@ https://ror.org/029k6t707 @=@ CDS094
+cnr:institutes @=@ https://ror.org/029k6t707 @=@ ISE - Istituto per lo studio degli ecosistemi
+cnr:institutes @=@ https://ror.org/00w6r1881 @=@ CDS095
+cnr:institutes @=@ https://ror.org/00w6r1881 @=@ ISMN - Istituto per lo studio dei materiali nanostrutturati
+cnr:institutes @=@ https://ror.org/01mfmr054 @=@ CDS096
+cnr:institutes @=@ https://ror.org/01mfmr054 @=@ ISMAC - Istituto per lo studio delle macromolecole
+cnr:institutes @=@ https://ror.org/058nrs650 @=@ CDS097
+cnr:institutes @=@ https://ror.org/058nrs650 @=@ ITM - Istituto per la tecnologia delle membrane
+cnr:institutes @=@ https://ror.org/0331xj092 @=@ CDS098
+cnr:institutes @=@ https://ror.org/0331xj092 @=@ ITABC - Istituto per le tecnologie applicate ai beni culturali
+cnr:institutes @=@ https://ror.org/052q58629 @=@ CDS099
+cnr:institutes @=@ https://ror.org/052q58629 @=@ ITAE - Istituto di tecnologie avanzate per l'energia \"Nicola Giordano\"
+cnr:institutes @=@ https://ror.org/04ehykb85 @=@ CDS100
+cnr:institutes @=@ https://ror.org/04ehykb85 @=@ ITB - Istituto di tecnologie biomediche
+cnr:institutes @=@ https://ror.org/0221agg28 @=@ CDS101
+cnr:institutes @=@ https://ror.org/0221agg28 @=@ ITC - Istituto per le tecnologie della costruzione
+cnr:institutes @=@ https://ror.org/02xz4xc25 @=@ CDS102
+cnr:institutes @=@ https://ror.org/02xz4xc25 @=@ ITD - Istituto per le tecnologie didattiche
+cnr:institutes @=@ __CDS103__ @=@ CDS103
+cnr:institutes @=@ __CDS103__ @=@ STIIMA - Istituto di Sistemi e Tecnologie Industriali Intelligenti per il Manifatturiero Avanzato
+cnr:institutes @=@ https://ror.org/01as2bh37 @=@ CDS104
+cnr:institutes @=@ https://ror.org/01as2bh37 @=@ ITTIG - Istituto di teoria e tecniche dell'informazione giuridica
+cnr:institutes @=@ https://ror.org/01y5w6t76 @=@ CDS105
+cnr:institutes @=@ https://ror.org/01y5w6t76 @=@ ITOI - Istituto per i trapianti d'organo e immunocitologia
+cnr:institutes @=@ https://ror.org/04xy2mq71 @=@ CDS106
+cnr:institutes @=@ https://ror.org/04xy2mq71 @=@ IVALSA - Istituto per la valorizzazione del legno e delle specie arboree
+cnr:institutes @=@ __CDS107__ @=@ CDS107
+cnr:institutes @=@ __CDS107__ @=@ IVV - Istituto di virologia vegetale
+cnr:institutes @=@ https://ror.org/013nxtf56 @=@ CDS108
+cnr:institutes @=@ https://ror.org/013nxtf56 @=@ IRSIG - Istituto di ricerca sui sistemi giudiziari
+cnr:institutes @=@ https://ror.org/05rcgef49 @=@ CDS109
+cnr:institutes @=@ https://ror.org/05rcgef49 @=@ ISC - Istituto dei sistemi complessi
+cnr:institutes @=@ __CDS110__ @=@ CDS110
+cnr:institutes @=@ __CDS110__ @=@ INFM - Centro di responsabilità scientifica INFM
+cnr:institutes @=@ https://ror.org/02dp3a879 @=@ CDS111
+cnr:institutes @=@ https://ror.org/02dp3a879 @=@ INO - Istituto nazionale di ottica
+cnr:institutes @=@ __CDS112__ @=@ CDS112
+cnr:institutes @=@ __CDS112__ @=@ IDAIC - Centro di responsabilità di attività scientifica IDAIC
+cnr:institutes @=@ https://ror.org/00p03yg71 @=@ CDS113
+cnr:institutes @=@ https://ror.org/00p03yg71 @=@ SPIN - Istituto superconduttori, materiali innovativi e dispositivi
+cnr:institutes @=@ https://ror.org/00yfw2296 @=@ CDS114
+cnr:institutes @=@ https://ror.org/00yfw2296 @=@ IOM - Istituto officina dei materiali
+cnr:institutes @=@ https://ror.org/0042e5975 @=@ CDS115
+cnr:institutes @=@ https://ror.org/0042e5975 @=@ NANO - Istituto Nanoscienze
+cnr:institutes @=@ https://ror.org/03ta8pf33 @=@ CDS116
+cnr:institutes @=@ https://ror.org/03ta8pf33 @=@ IFT - Istituto di Farmacologia Traslazionale
+cnr:institutes @=@ https://ror.org/040xhth73 @=@ CDS117
+cnr:institutes @=@ https://ror.org/040xhth73 @=@ IBCN - Istituto di Biologia Cellulare e Neurobiologia
+cnr:institutes @=@ https://ror.org/02qnx8e75 @=@ CDS118
+cnr:institutes @=@ https://ror.org/02qnx8e75 @=@ INM - Istituto di iNgegneria del Mare
+cnr:institutes @=@ https://ror.org/05nr7xa08 @=@ CDS119
+cnr:institutes @=@ https://ror.org/05nr7xa08 @=@ IPCB - Istituto per i Polimeri, Compositi e Biomateriali
+cnr:institutes @=@ https://ror.org/008fjbg42 @=@ CDS121
+cnr:institutes @=@ https://ror.org/008fjbg42 @=@ IPSP - Istituto per la Protezione Sostenibile delle Piante
+cnr:institutes @=@ __CDS122__ @=@ CDS122
+cnr:institutes @=@ __CDS122__ @=@ IRBIM - Istituto per le Risorse Biologiche e le Biotecnologie Marine
+cnr:institutes @=@ __CDS123__ @=@ CDS123
+cnr:institutes @=@ __CDS123__ @=@ ISPC - Istituto di Scienze del Patrimonio Culturale
+cnr:institutes @=@ __CDS124__ @=@ CDS124
+cnr:institutes @=@ __CDS124__ @=@ IAS - Istituto per lo studio degli impatti Antropici e Sostenibilità in ambiente marino
+cnr:institutes @=@ __CDS125__ @=@ CDS125
+cnr:institutes @=@ __CDS125__ @=@ IRET - Istituto di Ricerca sugli Ecosistemi Terrestri
+cnr:institutes @=@ https://ror.org/03a0vt050 @=@ CDS126
+cnr:institutes @=@ https://ror.org/03a0vt050 @=@ ISTP - Istituto per la Scienza e Tecnologia dei Plasmi
+cnr:institutes @=@ __CDS127__ @=@ CDS127
+cnr:institutes @=@ __CDS127__ @=@ ISP - Istituto di Scienze Polari
+cnr:institutes @=@ https://ror.org/03byxpq91 @=@ CDS128
+cnr:institutes @=@ https://ror.org/03byxpq91 @=@ IRIB - Istituto per la Ricerca e l'Innovazione Biomedica
+cnr:institutes @=@ __CDS129__ @=@ CDS129
+cnr:institutes @=@ __CDS129__ @=@ IGSG - Istituto di Informatica Giuridica e Sistemi Giudiziari
+cnr:institutes @=@ __CDS130__ @=@ CDS130
+cnr:institutes @=@ __CDS130__ @=@ IBBC - Istituto di Biochimica e Biologia Cellulare
+cnr:institutes @=@ __CDS131__ @=@ CDS131
+cnr:institutes @=@ __CDS131__ @=@ IBE - Istituto per la BioEconomia
+cnr:institutes @=@ https://ror.org/0263zy895 @=@ CDS132
+cnr:institutes @=@ https://ror.org/0263zy895 @=@ SCITEC - Istituto di Scienze e Tecnologie Chimiche \"Giulio Natta\"
+cnr:institutes @=@ __CDS133__ @=@ CDS133
+cnr:institutes @=@ __CDS133__ @=@ STEMS - Istituto di Scienze e Tecnologie per l'Energia e la Mobilità Sostenibili

dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/terms.txt

@@ -1077,4 +1077,137 @@ dnet:topic_types @=@ dnet:topic_types @=@ ENRICH/MISSING/DATASET/IS_SUPPLEMENTED
 dnet:topic_types @=@ dnet:topic_types @=@ ENRICH/MISSING/AUTHOR/ORCID @=@ An Open Researcher and Contributor ID (ORCID) that can be associated to an author of your publications
 dnet:review_levels @=@ dnet:review_levels @=@ 0000 @=@ Unknown
 dnet:review_levels @=@ dnet:review_levels @=@ 0002 @=@ nonPeerReviewed
-dnet:review_levels @=@ dnet:review_levels @=@ 0001 @=@ peerReviewed
+dnet:review_levels @=@ dnet:review_levels @=@ 0001 @=@ peerReviewed
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/00brf2d87 @=@ https://ror.org/00brf2d87
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/006qkqr45 @=@ https://ror.org/006qkqr45
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/054ye0e45 @=@ https://ror.org/054ye0e45
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/00ygy3d85 @=@ https://ror.org/00ygy3d85
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/000sy1f36 @=@ https://ror.org/000sy1f36
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/00x5wpm25 @=@ https://ror.org/00x5wpm25
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/03eqeqg74 @=@ https://ror.org/03eqeqg74
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/041xzk838 @=@ https://ror.org/041xzk838
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/00s2j5046 @=@ https://ror.org/00s2j5046
+cnr:institutes @=@ cnr:institutes @=@ __CDS010__ @=@ __CDS010__
+cnr:institutes @=@ cnr:institutes @=@ __CDS011__ @=@ __CDS011__
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/02e5sbe24 @=@ https://ror.org/02e5sbe24
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/01nyatq71 @=@ https://ror.org/01nyatq71
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/01dy2q607 @=@ https://ror.org/01dy2q607
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/05nzf7q96 @=@ https://ror.org/05nzf7q96
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/05m1yqp60 @=@ https://ror.org/05m1yqp60
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/03rqtqb02 @=@ https://ror.org/03rqtqb02
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/04r5fge26 @=@ https://ror.org/04r5fge26
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/03wyf0g15 @=@ https://ror.org/03wyf0g15
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/02fkw1114 @=@ https://ror.org/02fkw1114
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/0141vn777 @=@ https://ror.org/0141vn777
+cnr:institutes @=@ cnr:institutes @=@ __CDS022__ @=@ __CDS022__
+cnr:institutes @=@ cnr:institutes @=@ __CDS023__ @=@ __CDS023__
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/00be3zh53 @=@ https://ror.org/00be3zh53
+cnr:institutes @=@ cnr:institutes @=@ __CDS025__ @=@ __CDS025__
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/02ynrme92 @=@ https://ror.org/02ynrme92
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/05wba8r86 @=@ https://ror.org/05wba8r86
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/03z58xd74 @=@ https://ror.org/03z58xd74
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/00n4jbh84 @=@ https://ror.org/00n4jbh84
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/04sn06036 @=@ https://ror.org/04sn06036
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/01rg40y89 @=@ https://ror.org/01rg40y89
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/00dqega85 @=@ https://ror.org/00dqega85
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/02n2bgz18 @=@ https://ror.org/02n2bgz18
+cnr:institutes @=@ cnr:institutes @=@ __CDS034__ @=@ __CDS034__
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/01kdj2848 @=@ https://ror.org/01kdj2848
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/049ebw417 @=@ https://ror.org/049ebw417
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/01f5tnx94 @=@ https://ror.org/01f5tnx94
+cnr:institutes @=@ cnr:institutes @=@ __CDS038__ @=@ __CDS038__
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/04hadk112 @=@ https://ror.org/04hadk112
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/03qpd8w66 @=@ https://ror.org/03qpd8w66
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/01gtsa866 @=@ https://ror.org/01gtsa866
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/00ytw6m58 @=@ https://ror.org/00ytw6m58
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/015bmra78 @=@ https://ror.org/015bmra78
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/02gdcn153 @=@ https://ror.org/02gdcn153
+cnr:institutes @=@ cnr:institutes @=@ __CDS045__ @=@ __CDS045__
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/05hky6p02 @=@ https://ror.org/05hky6p02
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/011n2hw53 @=@ https://ror.org/011n2hw53
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/028g3pe33 @=@ https://ror.org/028g3pe33
+cnr:institutes @=@ cnr:institutes @=@ __CDS049__ @=@ __CDS049__
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/03m0n3c07 @=@ https://ror.org/03m0n3c07
+cnr:institutes @=@ cnr:institutes @=@ __CDS051__ @=@ __CDS051__
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/00z8ws214 @=@ https://ror.org/00z8ws214
+cnr:institutes @=@ cnr:institutes @=@ __CDS053__ @=@ __CDS053__
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/00bc51d88 @=@ https://ror.org/00bc51d88
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/024ye7w89 @=@ https://ror.org/024ye7w89
+cnr:institutes @=@ cnr:institutes @=@ __CDS056__ @=@ __CDS056__
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/05vk2g845 @=@ https://ror.org/05vk2g845
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/02qwy8e97 @=@ https://ror.org/02qwy8e97
+cnr:institutes @=@ cnr:institutes @=@ __CDS059__ @=@ __CDS059__
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/02dr63s31 @=@ https://ror.org/02dr63s31
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/0240rwx68 @=@ https://ror.org/0240rwx68
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/02rzxrg25 @=@ https://ror.org/02rzxrg25
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/05patmk97 @=@ https://ror.org/05patmk97
+cnr:institutes @=@ cnr:institutes @=@ __CDS064__ @=@ __CDS064__
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/029st3z03 @=@ https://ror.org/029st3z03
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/0040zx077 @=@ https://ror.org/0040zx077
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/044bfsy89 @=@ https://ror.org/044bfsy89
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/01n1ayq61 @=@ https://ror.org/01n1ayq61
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/02db0kh50 @=@ https://ror.org/02db0kh50
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/05813wx75 @=@ https://ror.org/05813wx75
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/04vnwke91 @=@ https://ror.org/04vnwke91
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/02wxw4x45 @=@ https://ror.org/02wxw4x45
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/01j6drw72 @=@ https://ror.org/01j6drw72
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/05kacka20 @=@ https://ror.org/05kacka20
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/00n8ttd98 @=@ https://ror.org/00n8ttd98
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/0013zhk30 @=@ https://ror.org/0013zhk30
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/03x7xkr71 @=@ https://ror.org/03x7xkr71
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/05w9g2j85 @=@ https://ror.org/05w9g2j85
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/032tyv240 @=@ https://ror.org/032tyv240
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/02hdf6119 @=@ https://ror.org/02hdf6119
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/01yg57d71 @=@ https://ror.org/01yg57d71
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/021z1mz76 @=@ https://ror.org/021z1mz76
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/01wqae691 @=@ https://ror.org/01wqae691
+cnr:institutes @=@ cnr:institutes @=@ __CDS084__ @=@ __CDS084__
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/00awwz417 @=@ https://ror.org/00awwz417
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/03a111314 @=@ https://ror.org/03a111314
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/01zz9wh30 @=@ https://ror.org/01zz9wh30
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/035y5td47 @=@ https://ror.org/035y5td47
+cnr:institutes @=@ cnr:institutes @=@ __CDS089__ @=@ __CDS089__
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/051t1q308 @=@ https://ror.org/051t1q308
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/05k3cs357 @=@ https://ror.org/05k3cs357
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/02gcxw165 @=@ https://ror.org/02gcxw165
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/05db0es39 @=@ https://ror.org/05db0es39
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/029k6t707 @=@ https://ror.org/029k6t707
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/00w6r1881 @=@ https://ror.org/00w6r1881
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/01mfmr054 @=@ https://ror.org/01mfmr054
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/058nrs650 @=@ https://ror.org/058nrs650
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/0331xj092 @=@ https://ror.org/0331xj092
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/052q58629 @=@ https://ror.org/052q58629
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/04ehykb85 @=@ https://ror.org/04ehykb85
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/0221agg28 @=@ https://ror.org/0221agg28
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/02xz4xc25 @=@ https://ror.org/02xz4xc25
+cnr:institutes @=@ cnr:institutes @=@ __CDS103__ @=@ __CDS103__
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/01as2bh37 @=@ https://ror.org/01as2bh37
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/01y5w6t76 @=@ https://ror.org/01y5w6t76
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/04xy2mq71 @=@ https://ror.org/04xy2mq71
+cnr:institutes @=@ cnr:institutes @=@ __CDS107__ @=@ __CDS107__
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/013nxtf56 @=@ https://ror.org/013nxtf56
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/05rcgef49 @=@ https://ror.org/05rcgef49
+cnr:institutes @=@ cnr:institutes @=@ __CDS110__ @=@ __CDS110__
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/02dp3a879 @=@ https://ror.org/02dp3a879
+cnr:institutes @=@ cnr:institutes @=@ __CDS112__ @=@ __CDS112__
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/00p03yg71 @=@ https://ror.org/00p03yg71
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/00yfw2296 @=@ https://ror.org/00yfw2296
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/0042e5975 @=@ https://ror.org/0042e5975
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/03ta8pf33 @=@ https://ror.org/03ta8pf33
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/040xhth73 @=@ https://ror.org/040xhth73
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/02qnx8e75 @=@ https://ror.org/02qnx8e75
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/05nr7xa08 @=@ https://ror.org/05nr7xa08
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/008fjbg42 @=@ https://ror.org/008fjbg42
+cnr:institutes @=@ cnr:institutes @=@ __CDS122__ @=@ __CDS122__
+cnr:institutes @=@ cnr:institutes @=@ __CDS123__ @=@ __CDS123__
+cnr:institutes @=@ cnr:institutes @=@ __CDS124__ @=@ __CDS124__
+cnr:institutes @=@ cnr:institutes @=@ __CDS125__ @=@ __CDS125__
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/03a0vt050 @=@ https://ror.org/03a0vt050
+cnr:institutes @=@ cnr:institutes @=@ __CDS127__ @=@ __CDS127__
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/03byxpq91 @=@ https://ror.org/03byxpq91
+cnr:institutes @=@ cnr:institutes @=@ __CDS129__ @=@ __CDS129__
+cnr:institutes @=@ cnr:institutes @=@ __CDS130__ @=@ __CDS130__
+cnr:institutes @=@ cnr:institutes @=@ __CDS131__ @=@ __CDS131__
+cnr:institutes @=@ cnr:institutes @=@ https://ror.org/0263zy895 @=@ https://ror.org/0263zy895
+cnr:institutes @=@ cnr:institutes @=@ __CDS133__ @=@ __CDS133__
+

dhp-workflows/dhp-doiboost/src/test/scala/eu/dnetlib/dhp/doiboost/crossref/CrossrefMappingTest.scala

@@ -498,9 +498,6 @@ class CrossrefMappingTest {
     assertNotNull(pub.getJournal.getIssnOnline)
     assertNotNull(pub.getJournal.getName)
 
-
-
-
   }
 
   @Test

dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/SparkBulkTagJob.java

@@ -5,6 +5,7 @@ import static eu.dnetlib.dhp.PropagationConstant.removeOutputDir;
 import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
 
 import java.util.ArrayList;
+import java.util.Objects;
 import java.util.Optional;
 
 import org.apache.commons.io.IOUtils;
@@ -102,6 +103,7 @@ public class SparkBulkTagJob {
 		ResultTagger resultTagger = new ResultTagger();
 		readPath(spark, inputPath, resultClazz)
 			.map(patchResult(), Encoders.bean(resultClazz))
+			.filter(Objects::nonNull)
 			.map(
 				(MapFunction<R, R>) value -> resultTagger
 					.enrichContextCriteria(

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

@@ -10,6 +10,7 @@ import java.util.stream.Collectors;
 
 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.api.java.function.MapGroupsFunction;
 import org.apache.spark.sql.Dataset;
@@ -81,8 +82,9 @@ public class SparkPrepareResultProject implements Serializable {
 		Dataset<Relation> relation = Utils
 			.readPath(spark, inputPath + "/relation", Relation.class)
 			.filter(
-				"dataInfo.deletedbyinference = false and lower(relClass) = '"
+				(FilterFunction<Relation>) r -> !r.getDataInfo().getDeletedbyinference() &&
-					+ ModelConstants.IS_PRODUCED_BY.toLowerCase() + "'");
+					r.getRelClass().equalsIgnoreCase(ModelConstants.IS_PRODUCED_BY));
+
 		Dataset<eu.dnetlib.dhp.schema.oaf.Project> projects = Utils
 			.readPath(spark, inputPath + "/project", eu.dnetlib.dhp.schema.oaf.Project.class);
 

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

@@ -7,17 +7,22 @@ import java.io.Serializable;
 import java.util.List;
 import java.util.Objects;
 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.function.FlatMapFunction;
+import org.apache.spark.api.java.function.ForeachFunction;
 import org.apache.spark.api.java.function.MapFunction;
 import org.apache.spark.sql.*;
+import org.jetbrains.annotations.NotNull;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 
 import eu.dnetlib.dhp.application.ArgumentApplicationParser;
 import eu.dnetlib.dhp.oa.graph.dump.Utils;
 import eu.dnetlib.dhp.schema.dump.oaf.community.CommunityResult;
+import eu.dnetlib.dhp.schema.dump.oaf.community.Funder;
 import eu.dnetlib.dhp.schema.dump.oaf.community.Project;
 
 /**
@@ -33,87 +38,83 @@ public class SparkDumpFunderResults implements Serializable {
 				SparkDumpFunderResults.class
 					.getResourceAsStream(
 						"/eu/dnetlib/dhp/oa/graph/dump/funder_result_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 inputPath = parser.get("sourcePath");
 		log.info("inputPath: {}", inputPath);
-
 		final String outputPath = parser.get("outputPath");
 		log.info("outputPath: {}", outputPath);
-
-		final String graphPath = parser.get("graphPath");
-		log.info("relationPath: {}", graphPath);
-
 		SparkConf conf = new SparkConf();
-
 		runWithSparkSession(
 			conf,
 			isSparkSessionManaged,
 			spark -> {
 				Utils.removeOutputDir(spark, outputPath);
-				writeResultProjectList(spark, inputPath, outputPath, graphPath);
+				writeResultProjectList(spark, inputPath, outputPath);
 			});
 	}
 
-	private static void writeResultProjectList(SparkSession spark, String inputPath, String outputPath,
+	private static void writeResultProjectList(SparkSession spark, String inputPath, String outputPath) {
-		String graphPath) {
-
-		Dataset<eu.dnetlib.dhp.schema.oaf.Project> project = Utils
-			.readPath(spark, graphPath + "/project", eu.dnetlib.dhp.schema.oaf.Project.class);
-
 		Dataset<CommunityResult> result = Utils
 			.readPath(spark, inputPath + "/publication", CommunityResult.class)
 			.union(Utils.readPath(spark, inputPath + "/dataset", CommunityResult.class))
-			.union(Utils.readPath(spark, inputPath + "/orp", CommunityResult.class))
+			.union(Utils.readPath(spark, inputPath + "/otherresearchproduct", CommunityResult.class))
 			.union(Utils.readPath(spark, inputPath + "/software", CommunityResult.class));
-
+		log.info("Number of result {}", result.count());
-		List<String> funderList = project
+		Dataset<String> tmp = result
-			.select("id")
+			.flatMap((FlatMapFunction<CommunityResult, String>) cr -> cr.getProjects().stream().map(p -> {
-			.map((MapFunction<Row, String>) value -> value.getString(0).substring(0, 15), Encoders.STRING())
+				return getFunderName(p);
-			.distinct()
+			}).collect(Collectors.toList()).iterator(), Encoders.STRING())
-			.collectAsList();
+			.distinct();
-
+		List<String> funderList = tmp.collectAsList();
 		funderList.forEach(funder -> {
-			String fundernsp = funder.substring(3);
+			dumpResults(funder, result, outputPath);
-			String funderdump;
-			if (fundernsp.startsWith("corda")) {
-				funderdump = "EC_";
-				if (fundernsp.endsWith("h2020")) {
-					funderdump += "H2020";
-				} else {
-					funderdump += "FP7";
-				}
-			} else {
-				funderdump = fundernsp.substring(0, fundernsp.indexOf("_")).toUpperCase();
-			}
-			writeFunderResult(funder, result, outputPath, funderdump);
 		});
-
 	}
 
-	private static void dumpResults(String nsp, Dataset<CommunityResult> results, String outputPath,
+	@NotNull
-		String funderName) {
+	private static String getFunderName(Project p) {
+		Optional<Funder> ofunder = Optional.ofNullable(p.getFunder());
+		if (ofunder.isPresent()) {
+			String fName = ofunder.get().getShortName();
+			if (fName.equalsIgnoreCase("ec")) {
+				fName += "_" + ofunder.get().getFundingStream();
+			}
+			return fName;
+		} else {
+			String fName = p.getId().substring(3, p.getId().indexOf("_")).toUpperCase();
+			if (fName.equalsIgnoreCase("ec")) {
+				if (p.getId().contains("h2020")) {
+					fName += "_H2020";
+				} else {
+					fName += "_FP7";
+				}
+			} else if (fName.equalsIgnoreCase("conicytf")) {
+				fName = "CONICYT";
+			} else if (fName.equalsIgnoreCase("dfgf")) {
+				fName = "DFG";
+			} else if (fName.equalsIgnoreCase("tubitakf")) {
+				fName = "TUBITAK";
+			} else if (fName.equalsIgnoreCase("euenvagency")) {
+				fName = "EEA";
+			}
+			return fName;
+		}
+	}
 
+	private static void dumpResults(String funder, Dataset<CommunityResult> results, String outputPath) {
 		results.map((MapFunction<CommunityResult, CommunityResult>) r -> {
 			if (!Optional.ofNullable(r.getProjects()).isPresent()) {
 				return null;
 			}
 			for (Project p : r.getProjects()) {
-				if (p.getId().startsWith(nsp)) {
+				String fName = getFunderName(p);
-					if (nsp.startsWith("40|irb")) {
+				if (fName.equalsIgnoreCase(funder)) {
-						if (p.getFunder().getShortName().equals(funderName))
-							return r;
-						else
-							return null;
-					}
 					return r;
 				}
 			}
@@ -123,18 +124,6 @@ public class SparkDumpFunderResults implements Serializable {
 			.write()
 			.mode(SaveMode.Overwrite)
 			.option("compression", "gzip")
-			.json(outputPath + "/" + funderName);
+			.json(outputPath + "/" + funder);
 	}
-
-	private static void writeFunderResult(String funder, Dataset<CommunityResult> results, String outputPath,
-		String funderDump) {
-
-		if (funder.startsWith("40|irb")) {
-			dumpResults(funder, results, outputPath, "HRZZ");
-			dumpResults(funder, results, outputPath, "MZOS");
-		} else
-			dumpResults(funder, results, outputPath, funderDump);
-
-	}
-
 }

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

@@ -5,9 +5,12 @@ import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
 
 import java.io.Serializable;
 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.function.FilterFunction;
+import org.apache.spark.api.java.function.FlatMapFunction;
 import org.apache.spark.api.java.function.MapFunction;
 import org.apache.spark.api.java.function.MapGroupsFunction;
 import org.apache.spark.sql.Dataset;
@@ -18,11 +21,18 @@ import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 
 import eu.dnetlib.dhp.application.ArgumentApplicationParser;
+import eu.dnetlib.dhp.oa.graph.dump.Constants;
+import eu.dnetlib.dhp.oa.graph.dump.DumpProducts;
+import eu.dnetlib.dhp.oa.graph.dump.ResultMapper;
 import eu.dnetlib.dhp.oa.graph.dump.Utils;
+import eu.dnetlib.dhp.oa.graph.dump.community.CommunityMap;
+import eu.dnetlib.dhp.oa.graph.dump.community.ResultProject;
 import eu.dnetlib.dhp.schema.common.ModelConstants;
+import eu.dnetlib.dhp.schema.dump.oaf.community.CommunityResult;
 import eu.dnetlib.dhp.schema.oaf.Project;
 import eu.dnetlib.dhp.schema.oaf.Relation;
 import eu.dnetlib.dhp.schema.oaf.Result;
+import scala.Tuple2;
 
 /**
  * Selects the results linked to projects. Only for these results the dump will be performed.
@@ -58,8 +68,10 @@ public class SparkResultLinkedToProject implements Serializable {
 		final String resultClassName = parser.get("resultTableName");
 		log.info("resultTableName: {}", resultClassName);
 
-		final String graphPath = parser.get("graphPath");
+		final String resultProjectsPath = parser.get("graphPath");
-		log.info("graphPath: {}", graphPath);
+		log.info("graphPath: {}", resultProjectsPath);
+
+		String communityMapPath = parser.get("communityMapPath");
 
 		@SuppressWarnings("unchecked")
 		Class<? extends Result> inputClazz = (Class<? extends Result>) Class.forName(resultClassName);
@@ -70,43 +82,33 @@ public class SparkResultLinkedToProject implements Serializable {
 			isSparkSessionManaged,
 			spark -> {
 				Utils.removeOutputDir(spark, outputPath);
-				writeResultsLinkedToProjects(spark, inputClazz, inputPath, outputPath, graphPath);
+				writeResultsLinkedToProjects(
+					communityMapPath, spark, inputClazz, inputPath, outputPath, resultProjectsPath);
 			});
 	}
 
-	private static <R extends Result> void writeResultsLinkedToProjects(SparkSession spark, Class<R> inputClazz,
+	private static <R extends Result> void writeResultsLinkedToProjects(String communityMapPath, SparkSession spark,
-		String inputPath, String outputPath, String graphPath) {
+		Class<R> inputClazz,
+		String inputPath, String outputPath, String resultProjectsPath) {
 
 		Dataset<R> results = Utils
 			.readPath(spark, inputPath, inputClazz)
-			.filter("dataInfo.deletedbyinference = false and datainfo.invisible = false");
-		Dataset<Relation> relations = Utils
-			.readPath(spark, graphPath + "/relation", Relation.class)
 			.filter(
-				"dataInfo.deletedbyinference = false and lower(relClass) = '"
+				(FilterFunction<R>) r -> !r.getDataInfo().getDeletedbyinference() &&
-					+ ModelConstants.IS_PRODUCED_BY.toLowerCase() + "'");
+					!r.getDataInfo().getInvisible());
-		Dataset<Project> project = Utils.readPath(spark, graphPath + "/project", Project.class);
+		Dataset<ResultProject> resultProjectDataset = Utils
-
+			.readPath(spark, resultProjectsPath, ResultProject.class);
-		results.createOrReplaceTempView("result");
+		CommunityMap communityMap = Utils.getCommunityMap(spark, communityMapPath);
-		relations.createOrReplaceTempView("relation");
+		results
-		project.createOrReplaceTempView("project");
+			.joinWith(resultProjectDataset, results.col("id").equalTo(resultProjectDataset.col("resultId")))
-
+			.map((MapFunction<Tuple2<R, ResultProject>, CommunityResult>) t2 -> {
-		Dataset<R> tmp = spark
+				CommunityResult cr = (CommunityResult) ResultMapper
-			.sql(
+					.map(
-				"Select res.* " +
+						t2._1(),
-					"from relation rel " +
+						communityMap, Constants.DUMPTYPE.FUNDER.getType());
-					"join result res " +
+				cr.setProjects(t2._2().getProjectsList());
-					"on rel.source = res.id " +
+				return cr;
-					"join project p " +
+			}, Encoders.bean(CommunityResult.class))
-					"on rel.target = p.id " +
-					"")
-			.as(Encoders.bean(inputClazz));
-		tmp
-			.groupByKey(
-				(MapFunction<R, String>) value -> value
-					.getId(),
-				Encoders.STRING())
-			.mapGroups((MapGroupsFunction<String, R, R>) (k, it) -> it.next(), Encoders.bean(inputClazz))
 			.write()
 			.mode(SaveMode.Overwrite)
 			.option("compression", "gzip")

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

@@ -0,0 +1,82 @@
+
+package eu.dnetlib.dhp.oa.graph.dump.projectssubset;
+
+import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
+
+import java.io.Serializable;
+import java.util.Objects;
+import java.util.Optional;
+
+import org.apache.commons.io.IOUtils;
+import org.apache.spark.SparkConf;
+import org.apache.spark.api.java.function.MapFunction;
+import org.apache.spark.sql.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.application.ArgumentApplicationParser;
+import eu.dnetlib.dhp.oa.graph.dump.Utils;
+import eu.dnetlib.dhp.schema.dump.oaf.graph.Project;
+import scala.Tuple2;
+
+public class ProjectsSubsetSparkJob implements Serializable {
+	private static final Logger log = LoggerFactory.getLogger(ProjectsSubsetSparkJob.class);
+
+	public static void main(String[] args) throws Exception {
+		String jsonConfiguration = IOUtils
+			.toString(
+				ProjectsSubsetSparkJob.class
+					.getResourceAsStream(
+						"/eu/dnetlib/dhp/oa/graph/dump/project_subset_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 inputPath = parser.get("sourcePath");
+		log.info("inputPath: {}", inputPath);
+		final String outputPath = parser.get("outputPath");
+		log.info("outputPath: {}", outputPath);
+		final String projectListPath = parser.get("projectListPath");
+		log.info("projectListPath: {}", projectListPath);
+		SparkConf conf = new SparkConf();
+		runWithSparkSession(
+			conf,
+			isSparkSessionManaged,
+			spark -> {
+				Utils.removeOutputDir(spark, outputPath);
+				getNewProjectList(spark, inputPath, outputPath, projectListPath);
+			});
+	}
+
+	private static void getNewProjectList(SparkSession spark, String inputPath, String outputPath,
+		String projectListPath) {
+		Dataset<String> projectList = spark.read().textFile(projectListPath);
+		Dataset<Project> projects;
+		projects = Utils.readPath(spark, inputPath, Project.class);
+		projects
+			.joinWith(projectList, projects.col("id").equalTo(projectList.col("value")), "left")
+			.map((MapFunction<Tuple2<Project, String>, Project>) t2 -> {
+				if (Optional.ofNullable(t2._2()).isPresent())
+					return null;
+				return t2._1();
+			}, Encoders.bean(Project.class))
+			.filter(Objects::nonNull)
+			.write()
+			.mode(SaveMode.Overwrite)
+			.option("compression", "gzip")
+			.json(outputPath);
+		Utils
+			.readPath(spark, outputPath, Project.class)
+			.map((MapFunction<Project, String>) p -> p.getId(), Encoders.STRING())
+			.write()
+			.mode(SaveMode.Append)
+			.option("compression", "gzip")
+			.text(projectListPath);
+	}
+}

dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/dump/funder_result_parameters.json

@@ -17,10 +17,10 @@
 		"paramDescription": "true if the spark session is managed, false otherwise",
 		"paramRequired": false
 	},
-{
+	{
-	"paramName": "gp",
+		"paramName": "gp",
-	"paramLongName": "graphPath",
+		"paramLongName": "graphPath",
-	"paramDescription": "the relationPath",
+		"paramDescription": "the relationPath",
-	"paramRequired": true
+		"paramRequired": false
-}
+	}
 ]

dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/dump/input_parameter_select_relation.json

@@ -0,0 +1,20 @@
+[
+  {
+    "paramName":"s",
+    "paramLongName":"sourcePath",
+    "paramDescription": "the path of the sequencial file to read",
+    "paramRequired": true
+  },
+  {
+    "paramName": "out",
+    "paramLongName": "outputPath",
+    "paramDescription": "the path used to store temporary output files",
+    "paramRequired": true
+  },
+  {
+    "paramName": "ssm",
+    "paramLongName": "isSparkSessionManaged",
+    "paramDescription": "true if the spark session is managed, false otherwise",
+    "paramRequired": false
+  }
+]

dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/dump/input_parameters_link_prj.json

@@ -28,6 +28,12 @@
 		"paramLongName":"graphPath",
 		"paramDescription": "the path to the relations",
 		"paramRequired": true
+	},
+	{
+		"paramName":"cmp",
+		"paramLongName":"communityMapPath",
+		"paramDescription": "the path to the relations",
+		"paramRequired": true
 	}
 ]
 

dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/dump/project_subset_parameters.json

@@ -0,0 +1,27 @@
+[
+  {
+    "paramName":"s",
+    "paramLongName":"sourcePath",
+    "paramDescription": "the path of the sequencial file to read",
+    "paramRequired": true
+  },
+  {
+    "paramName": "out",
+    "paramLongName": "outputPath",
+    "paramDescription": "the path used to store temporary output files",
+    "paramRequired": true
+  },
+  {
+    "paramName": "ssm",
+    "paramLongName": "isSparkSessionManaged",
+    "paramDescription": "true if the spark session is managed, false otherwise",
+    "paramRequired": false
+  },
+  {
+    "paramName": "pl",
+    "paramLongName": "projectListPath",
+    "paramDescription": "the path of the association result projectlist",
+    "paramRequired": true
+  }
+]
+

dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/dump/projectsubset/oozie_app/config-default.xml

@@ -27,4 +27,4 @@
         <name>oozie.launcher.mapreduce.user.classpath.first</name>
         <value>true</value>
     </property>
-</configuration>
+</configuration>

dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/dump/projectsubset/oozie_app/workflow.xml

@@ -0,0 +1,171 @@
+<workflow-app name="dump_graph" xmlns="uri:oozie:workflow:0.5">
+    <parameters>
+        <property>
+            <name>sourcePath</name>
+            <description>the source path</description>
+        </property>
+        <property>
+            <name>projectListPath</name>
+            <description>the path to the project list</description>
+        </property>
+        <property>
+            <name>outputPath</name>
+            <description>the output path</description>
+        </property>
+        <property>
+            <name>accessToken</name>
+            <description>the access token used for the deposition in Zenodo</description>
+        </property>
+        <property>
+            <name>connectionUrl</name>
+            <description>the connection url for Zenodo</description>
+        </property>
+        <property>
+            <name>metadata</name>
+            <description> the metadata associated to the deposition</description>
+        </property>
+        <property>
+            <name>depositionType</name>
+            <description>the type of deposition we want to perform. "new" for brand new deposition, "version" for a new version of a published deposition (in this case the concept record id must be provided), "upload" to upload content to an open deposition for which we already have the deposition id (in this case the deposition id should be provided)</description>
+        </property>
+        <property>
+            <name>conceptRecordId</name>
+            <description>for new version, the id of the record for the old deposition</description>
+        </property>
+        <property>
+            <name>depositionId</name>
+            <description>the depositionId of a deposition open that has to be added content</description>
+        </property>
+        <property>
+            <name>sparkDriverMemory</name>
+            <description>memory for driver process</description>
+        </property>
+        <property>
+            <name>sparkExecutorMemory</name>
+            <description>memory for individual executor</description>
+        </property>
+        <property>
+            <name>sparkExecutorCores</name>
+            <description>number of cores used by single executor</description>
+        </property>
+        <property>
+            <name>oozieActionShareLibForSpark2</name>
+            <description>oozie action sharelib for spark 2.*</description>
+        </property>
+        <property>
+            <name>spark2ExtraListeners</name>
+            <value>com.cloudera.spark.lineage.NavigatorAppListener</value>
+            <description>spark 2.* extra listeners classname</description>
+        </property>
+        <property>
+            <name>spark2SqlQueryExecutionListeners</name>
+            <value>com.cloudera.spark.lineage.NavigatorQueryListener</value>
+            <description>spark 2.* sql query execution listeners classname</description>
+        </property>
+        <property>
+            <name>spark2YarnHistoryServerAddress</name>
+            <description>spark 2.* yarn history server address</description>
+        </property>
+        <property>
+            <name>spark2EventLogDir</name>
+            <description>spark 2.* event log dir location</description>
+        </property>
+    </parameters>
+    <global>
+        <job-tracker>${jobTracker}</job-tracker>
+        <name-node>${nameNode}</name-node>
+        <configuration>
+            <property>
+                <name>mapreduce.job.queuename</name>
+                <value>${queueName}</value>
+            </property>
+            <property>
+                <name>oozie.launcher.mapred.job.queue.name</name>
+                <value>${oozieLauncherQueueName}</value>
+            </property>
+            <property>
+                <name>oozie.action.sharelib.for.spark</name>
+                <value>${oozieActionShareLibForSpark2}</value>
+            </property>
+        </configuration>
+    </global>
+    <start to="dump_project"/>
+    <kill name="Kill">
+        <message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
+    </kill>
+    <action name="dump_project">
+        <spark xmlns="uri:oozie:spark-action:0.2">
+            <master>yarn</master>
+            <mode>cluster</mode>
+            <name>Dump table project </name>
+            <class>eu.dnetlib.dhp.oa.graph.dump.complete.SparkDumpEntitiesJob</class>
+            <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
+            <spark-opts>
+                --executor-memory=${sparkExecutorMemory}
+                --executor-cores=${sparkExecutorCores}
+                --driver-memory=${sparkDriverMemory}
+                --conf spark.extraListeners=${spark2ExtraListeners}
+                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
+                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
+                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
+                --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
+            </spark-opts>
+            <arg>--sourcePath</arg><arg>${sourcePath}/project</arg>
+            <arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Project</arg>
+            <arg>--outputPath</arg><arg>${workingDir}/project</arg>
+            <arg>--communityMapPath</arg><arg>noneed</arg>
+        </spark>
+        <ok to="get_new_projects"/>
+        <error to="Kill"/>
+    </action>
+    <action name="get_new_projects">
+        <spark xmlns="uri:oozie:spark-action:0.2">
+            <master>yarn</master>
+            <mode>cluster</mode>
+            <name>Dump table project </name>
+            <class>eu.dnetlib.dhp.oa.graph.dump.projectssubset.ProjectsSubsetSparkJob</class>
+            <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
+            <spark-opts>
+                --executor-memory=${sparkExecutorMemory}
+                --executor-cores=${sparkExecutorCores}
+                --driver-memory=${sparkDriverMemory}
+                --conf spark.extraListeners=${spark2ExtraListeners}
+                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
+                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
+                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
+                --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
+            </spark-opts>
+            <arg>--sourcePath</arg><arg>${workingDir}/project</arg>
+            <arg>--outputPath</arg><arg>${workingDir}/tar/project</arg>
+            <arg>--projectListPath</arg><arg>${projectListPath}</arg>
+        </spark>
+        <ok to="make_archive"/>
+        <error to="Kill"/>
+    </action>
+    <action name="make_archive">
+        <java>
+            <main-class>eu.dnetlib.dhp.oa.graph.dump.MakeTar</main-class>
+            <arg>--hdfsPath</arg><arg>${outputPath}</arg>
+            <arg>--nameNode</arg><arg>${nameNode}</arg>
+            <arg>--sourcePath</arg><arg>${workingDir}/tar</arg>
+        </java>
+        <ok to="send_zenodo"/>
+        <error to="Kill"/>
+    </action>
+    <action name="send_zenodo">
+        <java>
+            <main-class>eu.dnetlib.dhp.oa.graph.dump.SendToZenodoHDFS</main-class>
+            <arg>--hdfsPath</arg><arg>${outputPath}</arg>
+            <arg>--nameNode</arg><arg>${nameNode}</arg>
+            <arg>--accessToken</arg><arg>${accessToken}</arg>
+            <arg>--connectionUrl</arg><arg>${connectionUrl}</arg>
+            <arg>--metadata</arg><arg>${metadata}</arg>
+            <arg>--conceptRecordId</arg><arg>${conceptRecordId}</arg>
+            <arg>--depositionType</arg><arg>${depositionType}</arg>
+            <arg>--depositionId</arg><arg>${depositionId}</arg>
+        </java>
+        <ok to="End"/>
+        <error to="Kill"/>
+    </action>
+    <end name="End"/>
+</workflow-app>

dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/dump/wf/subworkflows/commoncommunityfunder/oozie_app/workflow.xml

@@ -1,347 +0,0 @@
-<workflow-app name="sub_dump_community_funder_results" xmlns="uri:oozie:workflow:0.5">
-    <parameters>
-
-        <property>
-            <name>sourcePath</name>
-            <description>the source path</description>
-        </property>
-        <property>
-            <name>outputPath</name>
-            <description>the output path</description>
-        </property>
-        <property>
-            <name>communityMapPath</name>
-            <description>the path to the community map</description>
-        </property>
-        <property>
-            <name>selectedResults</name>
-            <description>the path the the possible subset ot results to be dumped</description>
-        </property>
-        <property>
-            <name>hiveDbName</name>
-            <description>the target hive database name</description>
-        </property>
-        <property>
-            <name>hiveJdbcUrl</name>
-            <description>hive server jdbc url</description>
-        </property>
-        <property>
-            <name>hiveMetastoreUris</name>
-            <description>hive server metastore URIs</description>
-        </property>
-        <property>
-            <name>sparkDriverMemory</name>
-            <description>memory for driver process</description>
-        </property>
-        <property>
-            <name>sparkExecutorMemory</name>
-            <description>memory for individual executor</description>
-        </property>
-        <property>
-            <name>sparkExecutorCores</name>
-            <description>number of cores used by single executor</description>
-        </property>
-        <property>
-            <name>oozieActionShareLibForSpark2</name>
-            <description>oozie action sharelib for spark 2.*</description>
-        </property>
-        <property>
-            <name>spark2ExtraListeners</name>
-            <value>com.cloudera.spark.lineage.NavigatorAppListener</value>
-            <description>spark 2.* extra listeners classname</description>
-        </property>
-        <property>
-            <name>spark2SqlQueryExecutionListeners</name>
-            <value>com.cloudera.spark.lineage.NavigatorQueryListener</value>
-            <description>spark 2.* sql query execution listeners classname</description>
-        </property>
-        <property>
-            <name>spark2YarnHistoryServerAddress</name>
-            <description>spark 2.* yarn history server address</description>
-        </property>
-        <property>
-            <name>spark2EventLogDir</name>
-            <description>spark 2.* event log dir location</description>
-        </property>
-    </parameters>
-
-    <global>
-        <job-tracker>${jobTracker}</job-tracker>
-        <name-node>${nameNode}</name-node>
-        <configuration>
-            <property>
-                <name>mapreduce.job.queuename</name>
-                <value>${queueName}</value>
-            </property>
-            <property>
-                <name>oozie.launcher.mapred.job.queue.name</name>
-                <value>${oozieLauncherQueueName}</value>
-            </property>
-            <property>
-                <name>oozie.action.sharelib.for.spark</name>
-                <value>${oozieActionShareLibForSpark2}</value>
-            </property>
-
-        </configuration>
-    </global>
-
-    <start to="fork_dump"/>
-
-    <kill name="Kill">
-        <message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
-    </kill>
-
-
-
-
-    <fork name="fork_dump">
-        <path start="dump_publication"/>
-        <path start="dump_dataset"/>
-        <path start="dump_orp"/>
-        <path start="dump_software"/>
-    </fork>
-
-    <action name="dump_publication">
-        <spark xmlns="uri:oozie:spark-action:0.2">
-            <master>yarn</master>
-            <mode>cluster</mode>
-            <name>Dump table publication for community/funder related products</name>
-            <class>eu.dnetlib.dhp.oa.graph.dump.community.SparkDumpCommunityProducts</class>
-            <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
-            <spark-opts>
-                --executor-memory=${sparkExecutorMemory}
-                --executor-cores=${sparkExecutorCores}
-                --driver-memory=${sparkDriverMemory}
-                --conf spark.extraListeners=${spark2ExtraListeners}
-                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
-                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
-                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-                --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
-            </spark-opts>
-            <arg>--sourcePath</arg><arg>${selectedResults}/publication</arg>
-            <arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
-            <arg>--outputPath</arg><arg>${workingDir}/dump/publication</arg>
-            <arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
-            <arg>--dumpType</arg><arg>${dumpType}</arg>
-        </spark>
-        <ok to="join_dump"/>
-        <error to="Kill"/>
-    </action>
-
-    <action name="dump_dataset">
-        <spark xmlns="uri:oozie:spark-action:0.2">
-            <master>yarn</master>
-            <mode>cluster</mode>
-            <name>Dump table dataset for community/funder related products</name>
-            <class>eu.dnetlib.dhp.oa.graph.dump.community.SparkDumpCommunityProducts</class>
-            <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
-            <spark-opts>
-                --executor-memory=${sparkExecutorMemory}
-                --executor-cores=${sparkExecutorCores}
-                --driver-memory=${sparkDriverMemory}
-                --conf spark.extraListeners=${spark2ExtraListeners}
-                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
-                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
-                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-                --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
-            </spark-opts>
-            <arg>--sourcePath</arg><arg>${selectedResults}/dataset</arg>
-            <arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
-            <arg>--outputPath</arg><arg>${workingDir}/dump/dataset</arg>
-            <arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
-        </spark>
-        <ok to="join_dump"/>
-        <error to="Kill"/>
-    </action>
-
-    <action name="dump_orp">
-        <spark xmlns="uri:oozie:spark-action:0.2">
-            <master>yarn</master>
-            <mode>cluster</mode>
-            <name>Dump table ORP for community related products</name>
-            <class>eu.dnetlib.dhp.oa.graph.dump.community.SparkDumpCommunityProducts</class>
-            <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
-            <spark-opts>
-                --executor-memory=${sparkExecutorMemory}
-                --executor-cores=${sparkExecutorCores}
-                --driver-memory=${sparkDriverMemory}
-                --conf spark.extraListeners=${spark2ExtraListeners}
-                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
-                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
-                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-                --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
-            </spark-opts>
-            <arg>--sourcePath</arg><arg>${selectedResults}/otherresearchproduct</arg>
-            <arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
-            <arg>--outputPath</arg><arg>${workingDir}/dump/otherresearchproduct</arg>
-            <arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
-        </spark>
-        <ok to="join_dump"/>
-        <error to="Kill"/>
-    </action>
-
-    <action name="dump_software">
-        <spark xmlns="uri:oozie:spark-action:0.2">
-            <master>yarn</master>
-            <mode>cluster</mode>
-            <name>Dump table software for community related products</name>
-            <class>eu.dnetlib.dhp.oa.graph.dump.community.SparkDumpCommunityProducts</class>
-            <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
-            <spark-opts>
-                --executor-memory=${sparkExecutorMemory}
-                --executor-cores=${sparkExecutorCores}
-                --driver-memory=${sparkDriverMemory}
-                --conf spark.extraListeners=${spark2ExtraListeners}
-                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
-                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
-                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-                --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
-            </spark-opts>
-            <arg>--sourcePath</arg><arg>${selectedResults}/software</arg>
-            <arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
-            <arg>--outputPath</arg><arg>${workingDir}/dump/software</arg>
-            <arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
-        </spark>
-        <ok to="join_dump"/>
-        <error to="Kill"/>
-    </action>
-
-    <join name="join_dump" to="prepareResultProject"/>
-
-    <action name="prepareResultProject">
-        <spark xmlns="uri:oozie:spark-action:0.2">
-            <master>yarn</master>
-            <mode>cluster</mode>
-            <name>Prepare association result subset of project info</name>
-            <class>eu.dnetlib.dhp.oa.graph.dump.community.SparkPrepareResultProject</class>
-            <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
-            <spark-opts>
-                --executor-memory=${sparkExecutorMemory}
-                --executor-cores=${sparkExecutorCores}
-                --driver-memory=${sparkDriverMemory}
-                --conf spark.extraListeners=${spark2ExtraListeners}
-                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
-                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
-                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-                --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
-            </spark-opts>
-            <arg>--sourcePath</arg><arg>${sourcePath}</arg>
-            <arg>--outputPath</arg><arg>${workingDir}/preparedInfo</arg>
-        </spark>
-        <ok to="fork_extendWithProject"/>
-        <error to="Kill"/>
-    </action>
-
-    <fork name="fork_extendWithProject">
-        <path start="extend_publication"/>
-        <path start="extend_dataset"/>
-        <path start="extend_orp"/>
-        <path start="extend_software"/>
-    </fork>
-
-    <action name="extend_publication">
-        <spark xmlns="uri:oozie:spark-action:0.2">
-            <master>yarn</master>
-            <mode>cluster</mode>
-            <name>Extend dumped publications with information about project</name>
-            <class>eu.dnetlib.dhp.oa.graph.dump.community.SparkUpdateProjectInfo</class>
-            <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
-            <spark-opts>
-                --executor-memory=${sparkExecutorMemory}
-                --executor-cores=${sparkExecutorCores}
-                --driver-memory=${sparkDriverMemory}
-                --conf spark.extraListeners=${spark2ExtraListeners}
-                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
-                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
-                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-                --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
-            </spark-opts>
-            <arg>--sourcePath</arg><arg>${workingDir}/dump/publication</arg>
-            <arg>--outputPath</arg><arg>${outputPath}/ext/publication</arg>
-            <arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo</arg>
-        </spark>
-        <ok to="join_extend"/>
-        <error to="Kill"/>
-    </action>
-
-    <action name="extend_dataset">
-        <spark xmlns="uri:oozie:spark-action:0.2">
-            <master>yarn</master>
-            <mode>cluster</mode>
-            <name>Extend dumped dataset with information about project</name>
-            <class>eu.dnetlib.dhp.oa.graph.dump.community.SparkUpdateProjectInfo</class>
-            <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
-            <spark-opts>
-                --executor-memory=${sparkExecutorMemory}
-                --executor-cores=${sparkExecutorCores}
-                --driver-memory=${sparkDriverMemory}
-                --conf spark.extraListeners=${spark2ExtraListeners}
-                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
-                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
-                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-                --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
-            </spark-opts>
-            <arg>--sourcePath</arg><arg>${workingDir}/dump/dataset</arg>
-            <arg>--outputPath</arg><arg>${outputPath}/ext/dataset</arg>
-            <arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo</arg>
-        </spark>
-        <ok to="join_extend"/>
-        <error to="Kill"/>
-    </action>
-
-    <action name="extend_orp">
-        <spark xmlns="uri:oozie:spark-action:0.2">
-            <master>yarn</master>
-            <mode>cluster</mode>
-            <name>Extend dumped ORP with information about project</name>
-            <class>eu.dnetlib.dhp.oa.graph.dump.community.SparkUpdateProjectInfo</class>
-            <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
-            <spark-opts>
-                --executor-memory=${sparkExecutorMemory}
-                --executor-cores=${sparkExecutorCores}
-                --driver-memory=${sparkDriverMemory}
-                --conf spark.extraListeners=${spark2ExtraListeners}
-                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
-                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
-                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-                --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
-            </spark-opts>
-            <arg>--sourcePath</arg><arg>${workingDir}/dump/otherresearchproduct</arg>
-            <arg>--outputPath</arg><arg>${outputPath}/ext/orp</arg>
-            <arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo</arg>
-        </spark>
-        <ok to="join_extend"/>
-        <error to="Kill"/>
-    </action>
-
-    <action name="extend_software">
-        <spark xmlns="uri:oozie:spark-action:0.2">
-            <master>yarn</master>
-            <mode>cluster</mode>
-            <name>Extend dumped software with information about project</name>
-            <class>eu.dnetlib.dhp.oa.graph.dump.community.SparkUpdateProjectInfo</class>
-            <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
-            <spark-opts>
-                --executor-memory=${sparkExecutorMemory}
-                --executor-cores=${sparkExecutorCores}
-                --driver-memory=${sparkDriverMemory}
-                --conf spark.extraListeners=${spark2ExtraListeners}
-                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
-                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
-                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-                --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
-            </spark-opts>
-            <arg>--sourcePath</arg><arg>${workingDir}/dump/software</arg>
-            <arg>--outputPath</arg><arg>${outputPath}/ext/software</arg>
-            <arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo</arg>
-        </spark>
-        <ok to="join_extend"/>
-        <error to="Kill"/>
-    </action>
-    <join name="join_extend" to="End"/>
-
-    <end name="End"/>
-
-</workflow-app>
-
-

dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/dump/wf/subworkflows/community/oozie_app/import.txt

@@ -1,2 +0,0 @@
-## This is a classpath-based import file (this header is required)
-dump_common classpath eu/dnetlib/dhp/oa/graph/dump/wf/subworkflows/commoncommunityfunder/oozie_app

dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/dump/wf/subworkflows/community/oozie_app/workflow.xml

@@ -77,42 +77,259 @@
         </configuration>
     </global>
 
-    <start to="common_action_community_funder"/>
+    <start to="fork_dump"/>
 
     <kill name="Kill">
         <message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
     </kill>
 
-    <action name="common_action_community_funder">
+    <fork name="fork_dump">
-        <sub-workflow>
+        <path start="dump_publication"/>
-            <app-path>${wf:appPath()}/dump_common
+        <path start="dump_dataset"/>
-            </app-path>
+        <path start="dump_orp"/>
-            <propagate-configuration/>
+        <path start="dump_software"/>
-            <configuration>
+    </fork>
-                <property>
+
-                    <name>sourcePath</name>
+    <action name="dump_publication">
-                    <value>${sourcePath}</value>
+        <spark xmlns="uri:oozie:spark-action:0.2">
-                </property>
+            <master>yarn</master>
-                <property>
+            <mode>cluster</mode>
-                    <name>selectedResults</name>
+            <name>Dump table publication for community/funder related products</name>
-                    <value>${sourcePath}</value>
+            <class>eu.dnetlib.dhp.oa.graph.dump.community.SparkDumpCommunityProducts</class>
-                </property>
+            <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
-                <property>
+            <spark-opts>
-                    <name>communityMapPath</name>
+                --executor-memory=${sparkExecutorMemory}
-                    <value>${workingDir}/communityMap</value>
+                --executor-cores=${sparkExecutorCores}
-                </property>
+                --driver-memory=${sparkDriverMemory}
-                <property>
+                --conf spark.extraListeners=${spark2ExtraListeners}
-                    <name>outputPath</name>
+                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
-                    <value>${workingDir}</value>
+                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
-                </property>
+                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-            </configuration>
+                --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
-        </sub-workflow>
+            </spark-opts>
-        <ok to="splitForCommunities" />
+            <arg>--sourcePath</arg><arg>${sourcePath}/publication</arg>
-        <error to="Kill" />
+            <arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
+            <arg>--outputPath</arg><arg>${workingDir}/dump/publication</arg>
+            <arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
+            <arg>--dumpType</arg><arg>${dumpType}</arg>
+        </spark>
+        <ok to="join_dump"/>
+        <error to="Kill"/>
+    </action>
+
+    <action name="dump_dataset">
+        <spark xmlns="uri:oozie:spark-action:0.2">
+            <master>yarn</master>
+            <mode>cluster</mode>
+            <name>Dump table dataset for community/funder related products</name>
+            <class>eu.dnetlib.dhp.oa.graph.dump.community.SparkDumpCommunityProducts</class>
+            <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
+            <spark-opts>
+                --executor-memory=${sparkExecutorMemory}
+                --executor-cores=${sparkExecutorCores}
+                --driver-memory=${sparkDriverMemory}
+                --conf spark.extraListeners=${spark2ExtraListeners}
+                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
+                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
+                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
+                --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
+            </spark-opts>
+            <arg>--sourcePath</arg><arg>${sourcePath}/dataset</arg>
+            <arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
+            <arg>--outputPath</arg><arg>${workingDir}/dump/dataset</arg>
+            <arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
+        </spark>
+        <ok to="join_dump"/>
+        <error to="Kill"/>
+    </action>
+
+    <action name="dump_orp">
+        <spark xmlns="uri:oozie:spark-action:0.2">
+            <master>yarn</master>
+            <mode>cluster</mode>
+            <name>Dump table ORP for community related products</name>
+            <class>eu.dnetlib.dhp.oa.graph.dump.community.SparkDumpCommunityProducts</class>
+            <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
+            <spark-opts>
+                --executor-memory=${sparkExecutorMemory}
+                --executor-cores=${sparkExecutorCores}
+                --driver-memory=${sparkDriverMemory}
+                --conf spark.extraListeners=${spark2ExtraListeners}
+                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
+                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
+                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
+                --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
+            </spark-opts>
+            <arg>--sourcePath</arg><arg>${sourcePath}/otherresearchproduct</arg>
+            <arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
+            <arg>--outputPath</arg><arg>${workingDir}/dump/otherresearchproduct</arg>
+            <arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
+        </spark>
+        <ok to="join_dump"/>
+        <error to="Kill"/>
+    </action>
+
+    <action name="dump_software">
+        <spark xmlns="uri:oozie:spark-action:0.2">
+            <master>yarn</master>
+            <mode>cluster</mode>
+            <name>Dump table software for community related products</name>
+            <class>eu.dnetlib.dhp.oa.graph.dump.community.SparkDumpCommunityProducts</class>
+            <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
+            <spark-opts>
+                --executor-memory=${sparkExecutorMemory}
+                --executor-cores=${sparkExecutorCores}
+                --driver-memory=${sparkDriverMemory}
+                --conf spark.extraListeners=${spark2ExtraListeners}
+                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
+                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
+                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
+                --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
+            </spark-opts>
+            <arg>--sourcePath</arg><arg>${sourcePath}/software</arg>
+            <arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
+            <arg>--outputPath</arg><arg>${workingDir}/dump/software</arg>
+            <arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
+        </spark>
+        <ok to="join_dump"/>
+        <error to="Kill"/>
+    </action>
+
+    <join name="join_dump" to="prepareResultProject"/>
+
+    <action name="prepareResultProject">
+        <spark xmlns="uri:oozie:spark-action:0.2">
+            <master>yarn</master>
+            <mode>cluster</mode>
+            <name>Prepare association result subset of project info</name>
+            <class>eu.dnetlib.dhp.oa.graph.dump.community.SparkPrepareResultProject</class>
+            <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
+            <spark-opts>
+                --executor-memory=${sparkExecutorMemory}
+                --executor-cores=${sparkExecutorCores}
+                --driver-memory=${sparkDriverMemory}
+                --conf spark.extraListeners=${spark2ExtraListeners}
+                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
+                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
+                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
+                --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
+            </spark-opts>
+            <arg>--sourcePath</arg><arg>${sourcePath}</arg>
+            <arg>--outputPath</arg><arg>${workingDir}/preparedInfo</arg>
+        </spark>
+        <ok to="fork_extendWithProject"/>
+        <error to="Kill"/>
+    </action>
+
+    <fork name="fork_extendWithProject">
+        <path start="extend_publication"/>
+        <path start="extend_dataset"/>
+        <path start="extend_orp"/>
+        <path start="extend_software"/>
+    </fork>
+
+    <action name="extend_publication">
+        <spark xmlns="uri:oozie:spark-action:0.2">
+            <master>yarn</master>
+            <mode>cluster</mode>
+            <name>Extend dumped publications with information about project</name>
+            <class>eu.dnetlib.dhp.oa.graph.dump.community.SparkUpdateProjectInfo</class>
+            <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
+            <spark-opts>
+                --executor-memory=${sparkExecutorMemory}
+                --executor-cores=${sparkExecutorCores}
+                --driver-memory=${sparkDriverMemory}
+                --conf spark.extraListeners=${spark2ExtraListeners}
+                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
+                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
+                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
+                --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
+            </spark-opts>
+            <arg>--sourcePath</arg><arg>${workingDir}/dump/publication</arg>
+            <arg>--outputPath</arg><arg>${workingDir}/ext/publication</arg>
+            <arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo</arg>
+        </spark>
+        <ok to="join_extend"/>
+        <error to="Kill"/>
+    </action>
+
+    <action name="extend_dataset">
+        <spark xmlns="uri:oozie:spark-action:0.2">
+            <master>yarn</master>
+            <mode>cluster</mode>
+            <name>Extend dumped dataset with information about project</name>
+            <class>eu.dnetlib.dhp.oa.graph.dump.community.SparkUpdateProjectInfo</class>
+            <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
+            <spark-opts>
+                --executor-memory=${sparkExecutorMemory}
+                --executor-cores=${sparkExecutorCores}
+                --driver-memory=${sparkDriverMemory}
+                --conf spark.extraListeners=${spark2ExtraListeners}
+                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
+                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
+                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
+                --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
+            </spark-opts>
+            <arg>--sourcePath</arg><arg>${workingDir}/dump/dataset</arg>
+            <arg>--outputPath</arg><arg>${workingDir}/ext/dataset</arg>
+            <arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo</arg>
+        </spark>
+        <ok to="join_extend"/>
+        <error to="Kill"/>
+    </action>
+
+    <action name="extend_orp">
+        <spark xmlns="uri:oozie:spark-action:0.2">
+            <master>yarn</master>
+            <mode>cluster</mode>
+            <name>Extend dumped ORP with information about project</name>
+            <class>eu.dnetlib.dhp.oa.graph.dump.community.SparkUpdateProjectInfo</class>
+            <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
+            <spark-opts>
+                --executor-memory=${sparkExecutorMemory}
+                --executor-cores=${sparkExecutorCores}
+                --driver-memory=${sparkDriverMemory}
+                --conf spark.extraListeners=${spark2ExtraListeners}
+                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
+                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
+                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
+                --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
+            </spark-opts>
+            <arg>--sourcePath</arg><arg>${workingDir}/dump/otherresearchproduct</arg>
+            <arg>--outputPath</arg><arg>${workingDir}/ext/orp</arg>
+            <arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo</arg>
+        </spark>
+        <ok to="join_extend"/>
+        <error to="Kill"/>
+    </action>
+
+    <action name="extend_software">
+        <spark xmlns="uri:oozie:spark-action:0.2">
+            <master>yarn</master>
+            <mode>cluster</mode>
+            <name>Extend dumped software with information about project</name>
+            <class>eu.dnetlib.dhp.oa.graph.dump.community.SparkUpdateProjectInfo</class>
+            <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
+            <spark-opts>
+                --executor-memory=${sparkExecutorMemory}
+                --executor-cores=${sparkExecutorCores}
+                --driver-memory=${sparkDriverMemory}
+                --conf spark.extraListeners=${spark2ExtraListeners}
+                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
+                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
+                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
+                --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
+            </spark-opts>
+            <arg>--sourcePath</arg><arg>${workingDir}/dump/software</arg>
+            <arg>--outputPath</arg><arg>${workingDir}/ext/software</arg>
+            <arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo</arg>
+        </spark>
+        <ok to="join_extend"/>
+        <error to="Kill"/>
     </action>
 
 
-
+    <join name="join_extend" to="splitForCommunities"/>
     <action name="splitForCommunities">
         <spark xmlns="uri:oozie:spark-action:0.2">
             <master>yarn</master>

dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/dump/wf/subworkflows/complete/oozie_app/workflow.xml

@@ -298,6 +298,7 @@
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
                 --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
                 --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
+                --conf spark.sql.shuffle.partitions=3840
             </spark-opts>
             <arg>--sourcePath</arg><arg>${sourcePath}</arg>
             <arg>--outputPath</arg><arg>${workingDir}/validrelation</arg>

dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/dump/wf/subworkflows/funder/oozie_app/import.txt

@@ -1,2 +0,0 @@
-## This is a classpath-based import file (this header is required)
-dump_common classpath eu/dnetlib/dhp/oa/graph/dump/wf/subworkflows/commoncommunityfunder/oozie_app

dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/dump/wf/subworkflows/funder/oozie_app/workflow.xml

@@ -77,12 +77,36 @@
         </configuration>
     </global>
 
-    <start to="fork_result_linked_to_projects"/>
+    <start to="prepareResultProject"/>
 
     <kill name="Kill">
         <message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
     </kill>
 
+    <action name="prepareResultProject">
+        <spark xmlns="uri:oozie:spark-action:0.2">
+            <master>yarn</master>
+            <mode>cluster</mode>
+            <name>Prepare association result subset of project info</name>
+            <class>eu.dnetlib.dhp.oa.graph.dump.community.SparkPrepareResultProject</class>
+            <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
+            <spark-opts>
+                --executor-memory=${sparkExecutorMemory}
+                --executor-cores=${sparkExecutorCores}
+                --driver-memory=${sparkDriverMemory}
+                --conf spark.extraListeners=${spark2ExtraListeners}
+                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
+                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
+                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
+                --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
+            </spark-opts>
+            <arg>--sourcePath</arg><arg>${sourcePath}</arg>
+            <arg>--outputPath</arg><arg>${workingDir}/preparedInfo</arg>
+        </spark>
+        <ok to="fork_result_linked_to_projects"/>
+        <error to="Kill"/>
+    </action>
+
 
     <fork name="fork_result_linked_to_projects">
         <path start="select_publication_linked_to_projects"/>
@@ -111,7 +135,8 @@
             <arg>--sourcePath</arg><arg>${sourcePath}/publication</arg>
             <arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
             <arg>--outputPath</arg><arg>${workingDir}/result/publication</arg>
-            <arg>--graphPath</arg><arg>${sourcePath}</arg>
+            <arg>--graphPath</arg><arg>${workingDir}/preparedInfo</arg>
+            <arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
         </spark>
         <ok to="join_link"/>
         <error to="Kill"/>
@@ -137,7 +162,8 @@
             <arg>--sourcePath</arg><arg>${sourcePath}/dataset</arg>
             <arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
             <arg>--outputPath</arg><arg>${workingDir}/result/dataset</arg>
-            <arg>--graphPath</arg><arg>${sourcePath}</arg>
+            <arg>--graphPath</arg><arg>${workingDir}/preparedInfo</arg>
+            <arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
         </spark>
         <ok to="join_link"/>
         <error to="Kill"/>
@@ -163,7 +189,8 @@
             <arg>--sourcePath</arg><arg>${sourcePath}/otherresearchproduct</arg>
             <arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
             <arg>--outputPath</arg><arg>${workingDir}/result/otherresearchproduct</arg>
-            <arg>--graphPath</arg><arg>${sourcePath}</arg>
+            <arg>--graphPath</arg><arg>${workingDir}/preparedInfo</arg>
+            <arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
         </spark>
         <ok to="join_link"/>
         <error to="Kill"/>
@@ -189,41 +216,14 @@
             <arg>--sourcePath</arg><arg>${sourcePath}/software</arg>
             <arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
             <arg>--outputPath</arg><arg>${workingDir}/result/software</arg>
-            <arg>--graphPath</arg><arg>${sourcePath}</arg>
+            <arg>--graphPath</arg><arg>${workingDir}/preparedInfo</arg>
+            <arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
         </spark>
         <ok to="join_link"/>
         <error to="Kill"/>
     </action>
 
-    <join name="join_link" to="common_action_community_funder"/>
+    <join name="join_link" to="dump_funder_results"/>
-
-    <action name="common_action_community_funder">
-        <sub-workflow>
-            <app-path>${wf:appPath()}/dump_common
-            </app-path>
-            <propagate-configuration/>
-            <configuration>
-                <property>
-                    <name>sourcePath</name>
-                    <value>${sourcePath}</value>
-                </property>
-                <property>
-                    <name>selectedResults</name>
-                    <value>${workingDir}/result</value>
-                </property>
-                <property>
-                    <name>communityMapPath</name>
-                    <value>${workingDir}/communityMap</value>
-                </property>
-                <property>
-                    <name>outputPath</name>
-                    <value>${workingDir}</value>
-                </property>
-            </configuration>
-        </sub-workflow>
-        <ok to="dump_funder_results" />
-        <error to="Kill" />
-    </action>
 
     <action name="dump_funder_results">
         <spark xmlns="uri:oozie:spark-action:0.2">
@@ -242,9 +242,8 @@
                 --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
                 --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
             </spark-opts>
-            <arg>--sourcePath</arg><arg>${workingDir}/ext</arg>
+            <arg>--sourcePath</arg><arg>${workingDir}/result</arg>
             <arg>--outputPath</arg><arg>${outputPath}</arg>
-            <arg>--graphPath</arg><arg>${sourcePath}</arg>
         </spark>
         <ok to="End"/>
         <error to="Kill"/>

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

@@ -321,4 +321,27 @@ public class PrepareResultProjectJobTest {
 			3, resultExplodedProvenance.filter("provenance = 'sysimport:crosswalk:entityregistry'").count());
 
 	}
+
+	@Test
+	void testMatchx() throws Exception {
+
+		final String sourcePath = getClass()
+			.getResource("/eu/dnetlib/dhp/oa/graph/dump/funderresource/match")
+			.getPath();
+
+		SparkPrepareResultProject.main(new String[] {
+			"-isSparkSessionManaged", Boolean.FALSE.toString(),
+			"-outputPath", workingDir.toString() + "/preparedInfo",
+			"-sourcePath", sourcePath
+		});
+
+		final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
+
+		JavaRDD<ResultProject> tmp = sc
+			.textFile(workingDir.toString() + "/preparedInfo")
+			.map(item -> OBJECT_MAPPER.readValue(item, ResultProject.class));
+
+		tmp.foreach(r -> System.out.println(OBJECT_MAPPER.writeValueAsString(r)));
+	}
+
 }

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

@@ -22,6 +22,7 @@ import org.slf4j.LoggerFactory;
 import com.fasterxml.jackson.databind.ObjectMapper;
 
 import eu.dnetlib.dhp.oa.graph.dump.funderresults.SparkResultLinkedToProject;
+import eu.dnetlib.dhp.schema.dump.oaf.community.CommunityResult;
 import eu.dnetlib.dhp.schema.oaf.Publication;
 import eu.dnetlib.dhp.schema.oaf.Result;
 
@@ -76,7 +77,11 @@ public class ResultLinkedToProjectTest {
 			.getPath();
 
 		final String graphPath = getClass()
-			.getResource("/eu/dnetlib/dhp/oa/graph/dump/funderresource/nomatch")
+			.getResource("/eu/dnetlib/dhp/oa/graph/dump/funderresource/preparedInfo")
+			.getPath();
+
+		final String communityMapPath = getClass()
+			.getResource("/eu/dnetlib/dhp/oa/graph/dump/funderresource/communityMapPath")
 			.getPath();
 
 		SparkResultLinkedToProject.main(new String[] {
@@ -84,20 +89,18 @@ public class ResultLinkedToProjectTest {
 			"-outputPath", workingDir.toString() + "/preparedInfo",
 			"-sourcePath", sourcePath,
 			"-resultTableName", "eu.dnetlib.dhp.schema.oaf.Publication",
-			"-graphPath", graphPath
+			"-graphPath", graphPath,
+			"-communityMapPath", communityMapPath
 
 		});
 
 		final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
 
-		JavaRDD<Result> tmp = sc
+		JavaRDD<CommunityResult> tmp = sc
 			.textFile(workingDir.toString() + "/preparedInfo")
-			.map(item -> OBJECT_MAPPER.readValue(item, Result.class));
+			.map(item -> OBJECT_MAPPER.readValue(item, CommunityResult.class));
 
-		org.apache.spark.sql.Dataset<Result> verificationDataset = spark
+		Assertions.assertEquals(0, tmp.count());
-			.createDataset(tmp.rdd(), Encoders.bean(Result.class));
-
-		Assertions.assertEquals(0, verificationDataset.count());
 
 	}
 
@@ -108,8 +111,12 @@ public class ResultLinkedToProjectTest {
 			.getResource("/eu/dnetlib/dhp/oa/graph/dump/funderresource/match/papers.json")
 			.getPath();
 
-		final String relationPath = getClass()
+		final String graphPath = getClass()
-			.getResource("/eu/dnetlib/dhp/oa/graph/dump/funderresource/match")
+			.getResource("/eu/dnetlib/dhp/oa/graph/dump/funderresource/preparedInfo")
+			.getPath();
+
+		final String communityMapPath = getClass()
+			.getResource("/eu/dnetlib/dhp/oa/graph/dump/funderresource/communityMapPath")
 			.getPath();
 
 		SparkResultLinkedToProject.main(new String[] {
@@ -117,20 +124,18 @@ public class ResultLinkedToProjectTest {
 			"-outputPath", workingDir.toString() + "/preparedInfo",
 			"-sourcePath", sourcePath,
 			"-resultTableName", "eu.dnetlib.dhp.schema.oaf.Publication",
-			"-graphPath", relationPath
+			"-graphPath", graphPath,
+			"-communityMapPath", communityMapPath
 
 		});
 
 		final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
 
-		JavaRDD<Publication> tmp = sc
+		JavaRDD<CommunityResult> tmp = sc
 			.textFile(workingDir.toString() + "/preparedInfo")
-			.map(item -> OBJECT_MAPPER.readValue(item, Publication.class));
+			.map(item -> OBJECT_MAPPER.readValue(item, CommunityResult.class));
 
-		org.apache.spark.sql.Dataset<Publication> verificationDataset = spark
+		Assertions.assertEquals(1, tmp.count());
-			.createDataset(tmp.rdd(), Encoders.bean(Publication.class));
-
-		Assertions.assertEquals(1, verificationDataset.count());
 
 	}
 

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

@@ -5,10 +5,14 @@ import java.io.IOException;
 import java.nio.file.Files;
 import java.nio.file.Path;
 
+// import eu.dnetlib.dhp.oa.graph.dump.funderresults.SparkDumpFunderResults2;
+// import eu.dnetlib.dhp.oa.graph.dump.funderresults.SparkGetFunderList;
 import org.apache.commons.io.FileUtils;
 import org.apache.spark.SparkConf;
 import org.apache.spark.api.java.JavaRDD;
 import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.api.java.function.ForeachFunction;
+import org.apache.spark.sql.Dataset;
 import org.apache.spark.sql.Encoders;
 import org.apache.spark.sql.SparkSession;
 import org.junit.jupiter.api.AfterAll;
@@ -68,20 +72,19 @@ public class SplitPerFunderTest {
 	void test1() throws Exception {
 
 		final String sourcePath = getClass()
-			.getResource("/eu/dnetlib/dhp/oa/graph/dump/funderresource/extendeddump")
+			.getResource("/eu/dnetlib/dhp/oa/graph/dump/funderresource/ext")
 			.getPath();
 
 		SparkDumpFunderResults.main(new String[] {
 			"-isSparkSessionManaged", Boolean.FALSE.toString(),
 			"-outputPath", workingDir.toString() + "/split",
-			"-sourcePath", sourcePath,
+			"-sourcePath", sourcePath
-			"-graphPath", sourcePath
 
 		});
 
 		final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
 
-		// FP7 3
+		// FP7 3 and H2020 3
 		JavaRDD<CommunityResult> tmp = sc
 			.textFile(workingDir.toString() + "/split/EC_FP7")
 			.map(item -> OBJECT_MAPPER.readValue(item, CommunityResult.class));
@@ -143,11 +146,6 @@ public class SplitPerFunderTest {
 			.map(item -> OBJECT_MAPPER.readValue(item, CommunityResult.class));
 		Assertions.assertEquals(1, tmp.count());
 
-		// CONICYT 0
-		tmp = sc
-			.textFile(workingDir.toString() + "/split/CONICYTF")
-			.map(item -> OBJECT_MAPPER.readValue(item, CommunityResult.class));
-		Assertions.assertEquals(0, tmp.count());
-
 	}
+
 }

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

@@ -0,0 +1,125 @@
+
+package eu.dnetlib.dhp.oa.graph.dump.projectssubset;
+
+import java.io.IOException;
+import java.nio.file.Files;
+import java.nio.file.Path;
+import java.util.HashMap;
+
+import org.apache.commons.io.FileUtils;
+import org.apache.spark.SparkConf;
+import org.apache.spark.api.java.JavaRDD;
+import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.sql.SaveMode;
+import org.apache.spark.sql.SparkSession;
+import org.junit.jupiter.api.AfterAll;
+import org.junit.jupiter.api.Assertions;
+import org.junit.jupiter.api.BeforeAll;
+import org.junit.jupiter.api.Test;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import com.fasterxml.jackson.databind.ObjectMapper;
+
+import eu.dnetlib.dhp.schema.dump.oaf.graph.Project;
+
+public class ProjectSubsetTest {
+	private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
+	private static SparkSession spark;
+	private static Path workingDir;
+	private static final Logger log = LoggerFactory
+		.getLogger(eu.dnetlib.dhp.oa.graph.dump.projectssubset.ProjectSubsetTest.class);
+
+	@BeforeAll
+	public static void beforeAll() throws IOException {
+		workingDir = Files
+			.createTempDirectory(
+				eu.dnetlib.dhp.oa.graph.dump.projectssubset.ProjectSubsetTest.class.getSimpleName());
+		log.info("using work dir {}", workingDir);
+		SparkConf conf = new SparkConf();
+		conf.setAppName(eu.dnetlib.dhp.oa.graph.dump.projectssubset.ProjectSubsetTest.class.getSimpleName());
+		conf.setMaster("local[*]");
+		conf.set("spark.driver.host", "localhost");
+		conf.set("hive.metastore.local", "true");
+		conf.set("spark.ui.enabled", "false");
+		conf.set("spark.sql.warehouse.dir", workingDir.toString());
+		conf.set("hive.metastore.warehouse.dir", workingDir.resolve("warehouse").toString());
+		spark = SparkSession
+			.builder()
+			.appName(eu.dnetlib.dhp.oa.graph.dump.projectssubset.ProjectSubsetTest.class.getSimpleName())
+			.config(conf)
+			.getOrCreate();
+	}
+
+	@AfterAll
+	public static void afterAll() throws IOException {
+		FileUtils.deleteDirectory(workingDir.toFile());
+		spark.stop();
+	}
+
+	@Test
+	void testAllNew() throws Exception {
+		final String projectListPath = getClass()
+			.getResource("/eu/dnetlib/dhp/oa/graph/dump/projectsubset/projectId")
+			.getPath();
+		final String sourcePath = getClass()
+			.getResource("/eu/dnetlib/dhp/oa/graph/dump/projectsubset/allnew/projects")
+			.getPath();
+		spark
+			.read()
+			.textFile(projectListPath)
+			.write()
+			.mode(SaveMode.Overwrite)
+			.text(workingDir.toString() + "/projectIds");
+		ProjectsSubsetSparkJob.main(new String[] {
+			"-isSparkSessionManaged", Boolean.FALSE.toString(),
+			"-outputPath", workingDir.toString() + "/projects",
+			"-sourcePath", sourcePath,
+			"-projectListPath", workingDir.toString() + "/projectIds"
+		});
+		final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
+		JavaRDD<Project> tmp = sc
+			.textFile(workingDir.toString() + "/projects")
+			.map(item -> OBJECT_MAPPER.readValue(item, Project.class));
+		Assertions.assertEquals(12, tmp.count());
+		Assertions.assertEquals(2, tmp.filter(p -> p.getId().substring(3, 15).equals("aka_________")).count());
+		Assertions.assertEquals(2, tmp.filter(p -> p.getId().substring(3, 15).equals("anr_________")).count());
+		Assertions.assertEquals(4, tmp.filter(p -> p.getId().substring(3, 15).equals("arc_________")).count());
+		Assertions.assertEquals(3, tmp.filter(p -> p.getId().substring(3, 15).equals("conicytf____")).count());
+		Assertions.assertEquals(1, tmp.filter(p -> p.getId().substring(3, 15).equals("corda_______")).count());
+		Assertions.assertEquals(40, sc.textFile(workingDir.toString() + "/projectIds").count());
+	}
+
+	@Test
+	void testMatchOne() throws Exception {
+		final String projectListPath = getClass()
+			.getResource("/eu/dnetlib/dhp/oa/graph/dump/projectsubset/projectId")
+			.getPath();
+		final String sourcePath = getClass()
+			.getResource("/eu/dnetlib/dhp/oa/graph/dump/projectsubset/matchOne/projects")
+			.getPath();
+		spark
+			.read()
+			.textFile(projectListPath)
+			.write()
+			.mode(SaveMode.Overwrite)
+			.text(workingDir.toString() + "/projectIds");
+		ProjectsSubsetSparkJob.main(new String[] {
+			"-isSparkSessionManaged", Boolean.FALSE.toString(),
+			"-outputPath", workingDir.toString() + "/projects",
+			"-sourcePath", sourcePath,
+			"-projectListPath", workingDir.toString() + "/projectIds"
+		});
+		final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
+		JavaRDD<Project> tmp = sc
+			.textFile(workingDir.toString() + "/projects")
+			.map(item -> OBJECT_MAPPER.readValue(item, Project.class));
+		Assertions.assertEquals(11, tmp.count());
+		Assertions.assertEquals(2, tmp.filter(p -> p.getId().substring(3, 15).equals("aka_________")).count());
+		Assertions.assertEquals(2, tmp.filter(p -> p.getId().substring(3, 15).equals("anr_________")).count());
+		Assertions.assertEquals(4, tmp.filter(p -> p.getId().substring(3, 15).equals("arc_________")).count());
+		Assertions.assertEquals(3, tmp.filter(p -> p.getId().substring(3, 15).equals("conicytf____")).count());
+		Assertions.assertEquals(0, tmp.filter(p -> p.getId().substring(3, 15).equals("corda__h2020")).count());
+		Assertions.assertEquals(39, sc.textFile(workingDir.toString() + "/projectIds").count());
+	}
+}

dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/dump/funderresource/communityMapPath/communityMap

@@ -0,0 +1 @@
+{"ee":"SDSN - Greece","epos":"EPOS","enrmaps":"Energy Research","fet-h2020":"FET H2020","instruct":"Instruct-Eric","egi":"EGI Federation","euromarine":"Euromarine","covid-19":"COVID-19","dariah":"DARIAH EU","rda":"Research Data Alliance","clarin":"CLARIN","aginfra":"Agricultural and Food Sciences","risis":"RISI","fam":"Fisheries and Aquaculture Management","beopen":"Transport Research","elixir-gr":"ELIXIR GR","fet-fp7":"FET FP7","ifremer":"Ifremer","science-innovation-policy":"Science and Innovation Policy Studies","mes":"European Marine Scinece","oa-pg":"EC Post-Grant Open Access Pilot","ni":"Neuroinformatics","dh-ch":"Digital Humanities and Cultural Heritage"}

dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/dump/funderresource/fundersList/list

@@ -0,0 +1,8 @@
+NSF
+CIHR
+NWO
+NHMRC
+NIH
+MZOS
+SNSF
+EC

dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/dump/funderresource/preparedInfo/resultProject

@@ -0,0 +1 @@
+{"resultId":"50|a89337edbe55::43e8b61e5e8d682545cb867be8118585","projectsList":[{"id":"40|aka_________::01bb7b48e29d732a1c7bc5150b9195c4","code":"135027","acronym":null,"title":"Dynamic 3D resolution-enhanced low-coherence interferometric imaging / Consortium: Hi-Lo","funder":{"shortName":"AKA","name":"Academy of Finland","jurisdiction":"FI","fundingStream":null},"provenance":{"provenance":"Harvested","trust":"0.900000000000000022"},"validated":null},{"id":"40|aka_________::9d1af21dbd0f5bc719f71553d19a6b3a","code":"316061","acronym":null,"title":"Finnish Imaging of Degenerative Shoulder Study (FIMAGE): A study on the prevalence of degenerative imaging changes of the shoulder and their relevance to clinical symptoms in the general population.","funder":{"shortName":"AKA","name":"Academy of Finland","jurisdiction":"FI","fundingStream":null},"provenance":{"provenance":"Harvested","trust":"0.900000000000000022"},"validated":null}]}

dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/dump/projectsubset/allnew/projects

@@ -0,0 +1,12 @@
+{"id":"40|aka_________::01bb7b48e29d732a1c7bc5150b9195c4","websiteurl":null,"code":"135027","acronym":null,"title":"Dynamic 3D resolution-enhanced low-coherence interferometric imaging / Consortium: Hi-Lo","startdate":null,"enddate":null,"callidentifier":"Fotoniikka ja modernit kuvantamismenetelmät LT","keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"AKA","name":"Academy of Finland","jurisdiction":"FI","funding_stream":null}],"summary":null,"granted":null,"h2020programme":[]}
+{"id":"40|aka_________::9d1af21dbd0f5bc719f71553d19a6b3a","websiteurl":null,"code":"316061","acronym":null,"title":"Finnish Imaging of Degenerative Shoulder Study (FIMAGE): A study on the prevalence of degenerative imaging changes of the shoulder and their relevance to clinical symptoms in the general population.","startdate":null,"enddate":null,"callidentifier":"Academy Project Funding TT","keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"AKA","name":"Academy of Finland","jurisdiction":"FI","funding_stream":null}],"summary":null,"granted":null,"h2020programme":[]}
+{"id":"40|anr_________::1f21edc5c902be305ee47148955c6e50","websiteurl":null,"code":"ANR-17-CE05-0033","acronym":"MOISE","title":"METAL OXIDES AS LOW LOADED NANO-IRIDIUM SUPPORT FOR COMPETITIVE WATER ELECTROLYSIS","startdate":null,"enddate":null,"callidentifier":null,"keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"ANR","name":"French National Research Agency (ANR)","jurisdiction":"FR","funding_stream":null}],"summary":null,"granted":null,"h2020programme":[]}
+{"id":"40|anr_________::547e78ffdcb7d72a1ef31058dede3a33","websiteurl":null,"code":"ANR-09-SEGI-0005","acronym":"GALAXY","title":"DEVELOPPEMENT COLLABORATIF DE SYSTEMES COMPLEXES SELON UNE APPROCHE GUIDEE  PAR LES MODELES","startdate":null,"enddate":null,"callidentifier":null,"keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"ANR","name":"French National Research Agency (ANR)","jurisdiction":"FR","funding_stream":null}],"summary":null,"granted":null,"h2020programme":[]}
+{"id":"40|arc_________::838e781a8d479e27a11101421fd8b296","websiteurl":"http://purl.org/au-research/grants/arc/LE0347462","code":"LE0347462","acronym":null,"title":"Femtosecond laser micromachining facility","startdate":"2003-01-01","enddate":"2003-12-31","callidentifier":null,"keywords":"biomedical nanostructures,femtosecond laser machining,laser manufacturing,laser micromachining,microphotonics,photonic bandgap structures","openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"ARC","name":"Australian Research Council (ARC)","jurisdiction":"AU","funding_stream":{"id":"ARC::Linkage Infrastructure, Equipment and Facilities","description":"Linkage Infrastructure, Equipment and Facilities"}}],"summary":null,"granted":null,"h2020programme":[]}
+{"id":"40|arc_________::a461f180f7b6700c0499d4d3d53e58c7","websiteurl":"http://purl.org/au-research/grants/arc/LP140100567","code":"LP140100567","acronym":null,"title":"Linkage Projects - Grant ID: LP140100567","startdate":"2014-01-01","enddate":"2017-12-31","callidentifier":null,"keywords":"EDUCATIONAL MEASUREMENT; EDUCATIONAL MEASUREMENT; HIGH-STAKES TESTING; HIGH-STAKES TESTING; PERFORMANCE ASSESSMENT; PERFORMANCE ASSESSMENT; PERFORMANCE ASSESSMENT","openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"ARC","name":"Australian Research Council (ARC)","jurisdiction":"AU","funding_stream":{"id":"ARC::Linkage Projects","description":"Linkage Projects"}}],"summary":null,"granted":null,"h2020programme":[]}
+{"id":"40|arc_________::b46b9e07d4cea67ccf497520a75ad0c8","websiteurl":"http://purl.org/au-research/grants/arc/DP180101235","code":"DP180101235","acronym":null,"title":"Discovery Projects - Grant ID: DP180101235","startdate":"2018-01-01","enddate":"2023-12-31","callidentifier":null,"keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"ARC","name":"Australian Research Council (ARC)","jurisdiction":"AU","funding_stream":{"id":"ARC::Discovery Projects","description":"Discovery Projects"}}],"summary":null,"granted":null,"h2020programme":[]}
+{"id":"40|arc_________::c5f86314ce288f91a7f31c219b128fab","websiteurl":"http://purl.org/au-research/grants/arc/LE0989831","code":"LE0989831","acronym":null,"title":"The Australian Music Navigator: research infrastructure for discovering, accessing and analysing Australia's musical landscape","startdate":"2009-01-01","enddate":"2009-12-31","callidentifier":null,"keywords":"database metadata,digital sound,electroacoustic music,film music,music,music information retrieval","openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"ARC","name":"Australian Research Council (ARC)","jurisdiction":"AU","funding_stream":{"id":"ARC::Linkage Infrastructure, Equipment and Facilities","description":"Linkage Infrastructure, Equipment and Facilities"}}],"summary":null,"granted":null,"h2020programme":[]}
+{"id":"40|conicytf____::05539f3427ad605d7c1de0168f3e337f","websiteurl":"http://repositorio.conicyt.cl/handle/10533/183109","code":"3120023","acronym":null,"title":"SYNTHESIS AND STRUCTURE-ACTIVITY RELATIONSHIPS OF HETEROARYLISOQUINOLINE- AND PHENANTHRIDINEQUINONES AS ANTITUMOR AGENTS","startdate":"2011-01-01","enddate":"2014-01-28","callidentifier":null,"keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"CONICYT","name":"Comisión Nacional de Investigación Científica y Tecnológica","jurisdiction":"CL","funding_stream":{"id":"CONICYT::FONDECYT::POSTDOCTORADO","description":"Fondecyt fundings - Fondecyt stream, POSTDOCTORADO"}}],"summary":null,"granted":null,"h2020programme":[]}
+{"id":"40|conicytf____::96b47b91a6c061e31f626612b1650c03","websiteurl":"http://repositorio.conicyt.cl/handle/10533/163340","code":"1040240","acronym":null,"title":"ESTUDIO TEORICO-EXPERIMENTAL DE LA PERMEACION DE FLUIDOS SUPERCRITICOS Y LA SEPARACION DE MEZCLAS A ALTA PRESION A TRAVES DE MEMBRANAS MICROPOROSAS.","startdate":"2004-01-15","enddate":"2007-01-15","callidentifier":null,"keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"CONICYT","name":"Comisión Nacional de Investigación Científica y Tecnológica","jurisdiction":"CL","funding_stream":{"id":"CONICYT::FONDECYT::REGULAR","description":"Fondecyt fundings - Fondecyt stream, REGULAR"}}],"summary":null,"granted":null,"h2020programme":[]}
+{"id":"40|conicytf____::b122147e0a13f34cdb6311a9d714f9a5","websiteurl":"http://repositorio.conicyt.cl/handle/10533/162452","code":"1020683","acronym":null,"title":"SINTESIS Y CARACTERIZACION DE SALES CUATERNARIAS CON EL ANION CALCOFOSFATO [P2Qy]4- (Q=S,Se;y=6,7) PROPIEDADES FISICAS Y REACCIONES DE INCLUSION.","startdate":"2002-01-15","enddate":"2006-01-15","callidentifier":null,"keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"CONICYT","name":"Comisión Nacional de Investigación Científica y Tecnológica","jurisdiction":"CL","funding_stream":{"id":"CONICYT::FONDECYT::REGULAR","description":"Fondecyt fundings - Fondecyt stream, REGULAR"}}],"summary":null,"granted":null,"h2020programme":[]}
+{"id":"40|corda_______::132bac68f17bb81c451d9071be6e4d6d","websiteurl":null,"code":"628405","acronym":"ANIM","title":"Precisely Defined, Surface-Engineered Nanostructures via Crystallization-Driven Self-Assembly of Linear-Dendritic Block Copolymers","startdate":"2014-05-01","enddate":"2016-04-30","callidentifier":"FP7-PEOPLE-2013-IIF","keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"EC","name":"European Commission","jurisdiction":"EU","funding_stream":{"id":"EC::FP7::SP3::PEOPLE","description":"SEVENTH FRAMEWORK PROGRAMME - SP3-People - Marie-Curie Actions"}}],"summary":null,"granted":null,"h2020programme":[]}

dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/dump/projectsubset/matchOne/projects

@@ -0,0 +1,12 @@
+{"id":"40|aka_________::01bb7b48e29d732a1c7bc5150b9195c4","websiteurl":null,"code":"135027","acronym":null,"title":"Dynamic 3D resolution-enhanced low-coherence interferometric imaging / Consortium: Hi-Lo","startdate":null,"enddate":null,"callidentifier":"Fotoniikka ja modernit kuvantamismenetelmät LT","keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"AKA","name":"Academy of Finland","jurisdiction":"FI","funding_stream":null}],"summary":null,"granted":null,"h2020programme":[]}
+{"id":"40|aka_________::9d1af21dbd0f5bc719f71553d19a6b3a","websiteurl":null,"code":"316061","acronym":null,"title":"Finnish Imaging of Degenerative Shoulder Study (FIMAGE): A study on the prevalence of degenerative imaging changes of the shoulder and their relevance to clinical symptoms in the general population.","startdate":null,"enddate":null,"callidentifier":"Academy Project Funding TT","keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"AKA","name":"Academy of Finland","jurisdiction":"FI","funding_stream":null}],"summary":null,"granted":null,"h2020programme":[]}
+{"id":"40|anr_________::1f21edc5c902be305ee47148955c6e50","websiteurl":null,"code":"ANR-17-CE05-0033","acronym":"MOISE","title":"METAL OXIDES AS LOW LOADED NANO-IRIDIUM SUPPORT FOR COMPETITIVE WATER ELECTROLYSIS","startdate":null,"enddate":null,"callidentifier":null,"keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"ANR","name":"French National Research Agency (ANR)","jurisdiction":"FR","funding_stream":null}],"summary":null,"granted":null,"h2020programme":[]}
+{"id":"40|anr_________::547e78ffdcb7d72a1ef31058dede3a33","websiteurl":null,"code":"ANR-09-SEGI-0005","acronym":"GALAXY","title":"DEVELOPPEMENT COLLABORATIF DE SYSTEMES COMPLEXES SELON UNE APPROCHE GUIDEE  PAR LES MODELES","startdate":null,"enddate":null,"callidentifier":null,"keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"ANR","name":"French National Research Agency (ANR)","jurisdiction":"FR","funding_stream":null}],"summary":null,"granted":null,"h2020programme":[]}
+{"id":"40|arc_________::838e781a8d479e27a11101421fd8b296","websiteurl":"http://purl.org/au-research/grants/arc/LE0347462","code":"LE0347462","acronym":null,"title":"Femtosecond laser micromachining facility","startdate":"2003-01-01","enddate":"2003-12-31","callidentifier":null,"keywords":"biomedical nanostructures,femtosecond laser machining,laser manufacturing,laser micromachining,microphotonics,photonic bandgap structures","openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"ARC","name":"Australian Research Council (ARC)","jurisdiction":"AU","funding_stream":{"id":"ARC::Linkage Infrastructure, Equipment and Facilities","description":"Linkage Infrastructure, Equipment and Facilities"}}],"summary":null,"granted":null,"h2020programme":[]}
+{"id":"40|arc_________::a461f180f7b6700c0499d4d3d53e58c7","websiteurl":"http://purl.org/au-research/grants/arc/LP140100567","code":"LP140100567","acronym":null,"title":"Linkage Projects - Grant ID: LP140100567","startdate":"2014-01-01","enddate":"2017-12-31","callidentifier":null,"keywords":"EDUCATIONAL MEASUREMENT; EDUCATIONAL MEASUREMENT; HIGH-STAKES TESTING; HIGH-STAKES TESTING; PERFORMANCE ASSESSMENT; PERFORMANCE ASSESSMENT; PERFORMANCE ASSESSMENT","openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"ARC","name":"Australian Research Council (ARC)","jurisdiction":"AU","funding_stream":{"id":"ARC::Linkage Projects","description":"Linkage Projects"}}],"summary":null,"granted":null,"h2020programme":[]}
+{"id":"40|arc_________::b46b9e07d4cea67ccf497520a75ad0c8","websiteurl":"http://purl.org/au-research/grants/arc/DP180101235","code":"DP180101235","acronym":null,"title":"Discovery Projects - Grant ID: DP180101235","startdate":"2018-01-01","enddate":"2023-12-31","callidentifier":null,"keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"ARC","name":"Australian Research Council (ARC)","jurisdiction":"AU","funding_stream":{"id":"ARC::Discovery Projects","description":"Discovery Projects"}}],"summary":null,"granted":null,"h2020programme":[]}
+{"id":"40|arc_________::c5f86314ce288f91a7f31c219b128fab","websiteurl":"http://purl.org/au-research/grants/arc/LE0989831","code":"LE0989831","acronym":null,"title":"The Australian Music Navigator: research infrastructure for discovering, accessing and analysing Australia's musical landscape","startdate":"2009-01-01","enddate":"2009-12-31","callidentifier":null,"keywords":"database metadata,digital sound,electroacoustic music,film music,music,music information retrieval","openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"ARC","name":"Australian Research Council (ARC)","jurisdiction":"AU","funding_stream":{"id":"ARC::Linkage Infrastructure, Equipment and Facilities","description":"Linkage Infrastructure, Equipment and Facilities"}}],"summary":null,"granted":null,"h2020programme":[]}
+{"id":"40|conicytf____::05539f3427ad605d7c1de0168f3e337f","websiteurl":"http://repositorio.conicyt.cl/handle/10533/183109","code":"3120023","acronym":null,"title":"SYNTHESIS AND STRUCTURE-ACTIVITY RELATIONSHIPS OF HETEROARYLISOQUINOLINE- AND PHENANTHRIDINEQUINONES AS ANTITUMOR AGENTS","startdate":"2011-01-01","enddate":"2014-01-28","callidentifier":null,"keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"CONICYT","name":"Comisión Nacional de Investigación Científica y Tecnológica","jurisdiction":"CL","funding_stream":{"id":"CONICYT::FONDECYT::POSTDOCTORADO","description":"Fondecyt fundings - Fondecyt stream, POSTDOCTORADO"}}],"summary":null,"granted":null,"h2020programme":[]}
+{"id":"40|conicytf____::96b47b91a6c061e31f626612b1650c03","websiteurl":"http://repositorio.conicyt.cl/handle/10533/163340","code":"1040240","acronym":null,"title":"ESTUDIO TEORICO-EXPERIMENTAL DE LA PERMEACION DE FLUIDOS SUPERCRITICOS Y LA SEPARACION DE MEZCLAS A ALTA PRESION A TRAVES DE MEMBRANAS MICROPOROSAS.","startdate":"2004-01-15","enddate":"2007-01-15","callidentifier":null,"keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"CONICYT","name":"Comisión Nacional de Investigación Científica y Tecnológica","jurisdiction":"CL","funding_stream":{"id":"CONICYT::FONDECYT::REGULAR","description":"Fondecyt fundings - Fondecyt stream, REGULAR"}}],"summary":null,"granted":null,"h2020programme":[]}
+{"id":"40|conicytf____::b122147e0a13f34cdb6311a9d714f9a5","websiteurl":"http://repositorio.conicyt.cl/handle/10533/162452","code":"1020683","acronym":null,"title":"SINTESIS Y CARACTERIZACION DE SALES CUATERNARIAS CON EL ANION CALCOFOSFATO [P2Qy]4- (Q=S,Se;y=6,7) PROPIEDADES FISICAS Y REACCIONES DE INCLUSION.","startdate":"2002-01-15","enddate":"2006-01-15","callidentifier":null,"keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"CONICYT","name":"Comisión Nacional de Investigación Científica y Tecnológica","jurisdiction":"CL","funding_stream":{"id":"CONICYT::FONDECYT::REGULAR","description":"Fondecyt fundings - Fondecyt stream, REGULAR"}}],"summary":null,"granted":null,"h2020programme":[]}
+{"id":"40|corda__h2020::bf5d35ec8d24ae4abfb4a1c6a0af3856","websiteurl":null,"code":"628405","acronym":"ANIM","title":"Precisely Defined, Surface-Engineered Nanostructures via Crystallization-Driven Self-Assembly of Linear-Dendritic Block Copolymers","startdate":"2014-05-01","enddate":"2016-04-30","callidentifier":"FP7-PEOPLE-2013-IIF","keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"EC","name":"European Commission","jurisdiction":"EU","funding_stream":{"id":"EC::FP7::SP3::PEOPLE","description":"SEVENTH FRAMEWORK PROGRAMME - SP3-People - Marie-Curie Actions"}}],"summary":null,"granted":null,"h2020programme":[]}

dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/dump/projectsubset/projectId

@@ -0,0 +1,28 @@
+40|nih_________::4c32cdbc4c9949853f02219fc4780a30
+40|nih_________::b485512ef116af73bee79d50c8f9ca01
+40|nih_________::b44d9bc8e99d9a0477ac06897e3e9c19
+40|nih_________::7d2d2b7d1644a722a6bbcb031d82fec6
+40|nsf_________::6b2674b0341e07b818a56c6f0daa2633
+40|nih_________::96bb39aecc8f7b9f3b02ed36ef09538b
+40|nsf_________::88d92bdf20ec2fac3ed9740f962b4fad
+40|nih_________::4bb8c14729a0082378bb04db8321ce14
+40|nih_________::08a8eed6c17c6d8e427afcfd29f87c7b
+40|nsf_________::c314f3d35af1990121bf5b803937e112
+40|nih_________::3ad6a2e6ebd561206f0da69468337f50
+40|nih_________::d02c60c65a59629e69a30abcf2ceaed1
+40|nih_________::d5a241cc94253feb72181cde15f51e96
+40|nih_________::b5df718bbca69af50d4b7213e26af3f0
+40|nih_________::bc90893c1be80503578e48f6ef6b7061
+40|rcuk________::2c39b38c26c260b14a9816b88c91c132
+40|nih_________::ab103ad117cd0579df66f7592a7d4adf
+40|nih_________::147aa6ad8bd201e2a02c7b6cc3f68348
+40|corda__h2020::bf5d35ec8d24ae4abfb4a1c6a0af3856
+40|nih_________::b8083208156f2764d07c736ba9b49dd2
+40|nih_________::f4d1e0aece0e6a9eff8d054c28e082db
+40|nsf_________::56297da8b472a4be8ac3f09af813c9f6
+40|nsf_________::6b6dc3398eeebb3de1ab66e6eb8c5cb3
+40|nih_________::93289a36ebffb0bee3d6b01c6fc0a3d6
+40|nih_________::6c3b00dd4ae9d43d6630ff18f189ebae
+40|nih_________::1d983a87768f13bc8377b1b7d17290a2
+40|nih_________::c3b56e91859b114644c1403e892eb80f
+40|rcuk________::c1e15330fc7956063652f9c06e584548