Merge branch 'dump' of https://code-repo.d4science.org/miriam.baglioni/dnet-hadoop into resolve_conflicts_pr40_dump

dhp-common/pom.xml

@@ -87,6 +87,11 @@
 			<groupId>org.postgresql</groupId>
 			<artifactId>postgresql</artifactId>
 		</dependency>
+
+		<dependency>
+			<groupId>com.squareup.okhttp3</groupId>
+			<artifactId>okhttp</artifactId>
+		</dependency>
 	</dependencies>
 
 </project>

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

@@ -0,0 +1,53 @@
+
+package eu.dnetlib.dhp.common.api;
+
+import java.io.IOException;
+import java.io.InputStream;
+
+import okhttp3.MediaType;
+import okhttp3.RequestBody;
+import okhttp3.internal.Util;
+import okio.BufferedSink;
+import okio.Okio;
+import okio.Source;
+
+public class InputStreamRequestBody extends RequestBody {
+
+	private InputStream inputStream;
+	private MediaType mediaType;
+	private long lenght;
+
+	public static RequestBody create(final MediaType mediaType, final InputStream inputStream, final long len) {
+
+		return new InputStreamRequestBody(inputStream, mediaType, len);
+	}
+
+	private InputStreamRequestBody(InputStream inputStream, MediaType mediaType, long len) {
+		this.inputStream = inputStream;
+		this.mediaType = mediaType;
+		this.lenght = len;
+	}
+
+	@Override
+	public MediaType contentType() {
+		return mediaType;
+	}
+
+	@Override
+	public long contentLength() {
+
+		return lenght;
+
+	}
+
+	@Override
+	public void writeTo(BufferedSink sink) throws IOException {
+		Source source = null;
+		try {
+			source = Okio.source(inputStream);
+			sink.writeAll(source);
+		} finally {
+			Util.closeQuietly(source);
+		}
+	}
+}

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

@@ -0,0 +1,7 @@
+package eu.dnetlib.dhp.common.api;
+
+public class MissingConceptDoiException extends Throwable {
+    public MissingConceptDoiException(String message) {
+        super(message);
+    }
+}

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

@@ -0,0 +1,266 @@
+
+package eu.dnetlib.dhp.common.api;
+
+import java.io.*;
+import java.io.IOException;
+
+import com.google.gson.Gson;
+
+import eu.dnetlib.dhp.common.api.zenodo.ZenodoModel;
+import eu.dnetlib.dhp.common.api.zenodo.ZenodoModelList;
+import okhttp3.*;
+
+public class ZenodoAPIClient implements Serializable {
+
+
+	String urlString;
+	String bucket;
+
+	String deposition_id;
+	String access_token;
+
+
+	public static final MediaType MEDIA_TYPE_JSON = MediaType.parse("application/json; charset=utf-8");
+
+	private static final MediaType MEDIA_TYPE_ZIP = MediaType.parse("application/zip");
+
+	public String getUrlString() {
+		return urlString;
+	}
+
+	public void setUrlString(String urlString) {
+		this.urlString = urlString;
+	}
+
+	public String getBucket() {
+		return bucket;
+	}
+
+	public void setBucket(String bucket) {
+		this.bucket = bucket;
+	}
+
+	public void setDeposition_id(String deposition_id){this.deposition_id = deposition_id;}
+
+	public ZenodoAPIClient(String urlString, String access_token) throws IOException {
+
+		this.urlString = urlString;
+		this.access_token = access_token;
+	}
+
+	/**
+	 * Brand new deposition in Zenodo. It sets the deposition_id and the bucket where to store the files to upload
+	 * @return response code
+	 * @throws IOException
+	 */
+	public int newDeposition() throws IOException {
+		String json = "{}";
+		OkHttpClient httpClient = new OkHttpClient();
+
+		RequestBody body = RequestBody.create(MEDIA_TYPE_JSON, json);
+
+		Request request = new Request.Builder()
+			.url(urlString)
+			.addHeader("Content-Type", "application/json") // add request headers
+			.addHeader("Authorization", "Bearer " + access_token)
+			.post(body)
+			.build();
+
+		try (Response response = httpClient.newCall(request).execute()) {
+
+			if (!response.isSuccessful())
+				throw new IOException("Unexpected code " + response + response.body().string());
+
+			// Get response body
+			json = response.body().string();
+
+			ZenodoModel newSubmission = new Gson().fromJson(json, ZenodoModel.class);
+			this.bucket = newSubmission.getLinks().getBucket();
+			this.deposition_id = newSubmission.getId();
+
+			return response.code();
+
+		}
+
+	}
+
+	/**
+	 * Upload files in Zenodo.
+	 * @param is the inputStream for the file to upload
+	 * @param file_name the name of the file as it will appear on Zenodo
+	 * @param len the size of the file
+	 * @return the response code
+	 */
+	public int uploadIS(InputStream is, String file_name, long len) throws IOException {
+		OkHttpClient httpClient = new OkHttpClient();
+
+		Request request = new Request.Builder()
+			.url(bucket + "/" + file_name)
+			.addHeader("Content-Type", "application/zip") // add request headers
+			.addHeader("Authorization", "Bearer " + access_token)
+			.put(InputStreamRequestBody.create(MEDIA_TYPE_ZIP, is, len))
+			.build();
+
+		try (Response response = httpClient.newCall(request).execute()) {
+			if (!response.isSuccessful())
+				throw new IOException("Unexpected code " + response + response.body().string());
+			return response.code();
+		}
+	}
+
+	/**
+	 * Associates metadata information to the current deposition
+	 * @param metadata the metadata
+	 * @return response code
+	 * @throws IOException
+	 */
+	public int sendMretadata(String metadata) throws IOException {
+
+		OkHttpClient httpClient = new OkHttpClient();
+
+		RequestBody body = RequestBody.create(MEDIA_TYPE_JSON, metadata);
+
+		Request request = new Request.Builder()
+			.url(urlString + "/" + deposition_id)
+			.addHeader("Content-Type", "application/json") // add request headers
+			.addHeader("Authorization", "Bearer " + access_token)
+			.put(body)
+			.build();
+
+		try (Response response = httpClient.newCall(request).execute()) {
+
+			if (!response.isSuccessful())
+				throw new IOException("Unexpected code " + response + response.body().string());
+
+			return response.code();
+
+		}
+
+	}
+
+	/**
+	 * To publish the current deposition. It works for both new deposition or new version of an old deposition
+	 * @return response code
+	 * @throws IOException
+	 */
+	public int publish() throws IOException {
+
+		String json = "{}";
+
+		OkHttpClient httpClient = new OkHttpClient();
+
+		Request request = new Request.Builder()
+			.url(urlString + "/" + deposition_id + "/actions/publish")
+			.addHeader("Authorization", "Bearer " + access_token)
+			.post(RequestBody.create(MEDIA_TYPE_JSON, json))
+			.build();
+
+		try (Response response = httpClient.newCall(request).execute()) {
+
+			if (!response.isSuccessful())
+				throw new IOException("Unexpected code " + response + response.body().string());
+
+			return response.code();
+
+		}
+	}
+
+	/**
+	 * To create a new version of an already published deposition.
+	 * It sets the deposition_id and the bucket to be used for the new version.
+	 * @param concept_rec_id the concept record id of the deposition for which to create a new version. It is
+	 *                       the last part of the url for the DOI Zenodo suggests to use to cite all versions:
+	 *                       DOI: 10.xxx/zenodo.656930 concept_rec_id = 656930
+	 * @return response code
+	 * @throws IOException
+	 * @throws MissingConceptDoiException
+	 */
+	public int newVersion(String concept_rec_id) throws IOException, MissingConceptDoiException {
+		setDepositionId(concept_rec_id);
+		String json = "{}";
+
+		OkHttpClient httpClient = new OkHttpClient();
+
+		Request request = new Request.Builder()
+				.url(urlString + "/" + deposition_id + "/actions/newversion")
+				.addHeader("Authorization", "Bearer " + access_token)
+				.post(RequestBody.create(MEDIA_TYPE_JSON, json))
+				.build();
+
+		try (Response response = httpClient.newCall(request).execute()) {
+
+			if (!response.isSuccessful())
+				throw new IOException("Unexpected code " + response + response.body().string());
+
+			ZenodoModel zenodoModel = new Gson().fromJson(response.body().string(), ZenodoModel.class);
+			String latest_draft = zenodoModel.getLinks().getLatest_draft();
+			deposition_id = latest_draft.substring(latest_draft.lastIndexOf("/") + 1);
+			bucket = getBucket(latest_draft);
+			return response.code();
+
+		}
+	}
+
+	private void setDepositionId(String concept_rec_id) throws IOException, MissingConceptDoiException {
+
+		ZenodoModelList zenodoModelList = new Gson().fromJson(getPrevDepositions(), ZenodoModelList.class);
+
+		for(ZenodoModel zm : zenodoModelList){
+			if (zm.getConceptrecid().equals(concept_rec_id)){
+				deposition_id =  zm.getId();
+				return;
+			}
+		}
+
+		throw new MissingConceptDoiException("The concept record id specified was missing in the list of depositions");
+
+	}
+
+	private String getPrevDepositions() throws IOException {
+		OkHttpClient httpClient = new OkHttpClient();
+
+		Request request = new Request.Builder()
+				.url(urlString)
+				.addHeader("Content-Type", "application/json") // add request headers
+				.addHeader("Authorization", "Bearer " + access_token)
+				.get()
+				.build();
+
+		try (Response response = httpClient.newCall(request).execute()) {
+
+			if (!response.isSuccessful())
+				throw new IOException("Unexpected code " + response + response.body().string());
+
+			return response.body().string();
+
+		}
+
+	}
+
+	private String getBucket(String url) throws IOException {
+		OkHttpClient httpClient = new OkHttpClient();
+
+		Request request = new Request.Builder()
+				.url(url)
+				.addHeader("Content-Type", "application/json") // add request headers
+				.addHeader("Authorization", "Bearer " + access_token)
+				.get()
+				.build();
+
+		try (Response response = httpClient.newCall(request).execute()) {
+
+			if (!response.isSuccessful())
+				throw new IOException("Unexpected code " + response + response.body().string());
+
+			// Get response body
+			ZenodoModel zenodoModel = new Gson().fromJson(response.body().string(), ZenodoModel.class);
+
+
+			return zenodoModel.getLinks().getBucket();
+
+		}
+
+	}
+
+
+}

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

@@ -0,0 +1,14 @@
+
+package eu.dnetlib.dhp.common.api.zenodo;
+
+public class Community {
+	private String identifier;
+
+	public String getIdentifier() {
+		return identifier;
+	}
+
+	public void setIdentifier(String identifier) {
+		this.identifier = identifier;
+	}
+}

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

@@ -0,0 +1,47 @@
+
+package eu.dnetlib.dhp.common.api.zenodo;
+
+public class Creator {
+	private String affiliation;
+	private String name;
+	private String orcid;
+
+	public String getAffiliation() {
+		return affiliation;
+	}
+
+	public void setAffiliation(String affiliation) {
+		this.affiliation = affiliation;
+	}
+
+	public String getName() {
+		return name;
+	}
+
+	public void setName(String name) {
+		this.name = name;
+	}
+
+	public String getOrcid() {
+		return orcid;
+	}
+
+	public void setOrcid(String orcid) {
+		this.orcid = orcid;
+	}
+
+	public static Creator newInstance(String name, String affiliation, String orcid) {
+		Creator c = new Creator();
+		if (!(name == null)) {
+			c.name = name;
+		}
+		if (!(affiliation == null)) {
+			c.affiliation = affiliation;
+		}
+		if (!(orcid == null)) {
+			c.orcid = orcid;
+		}
+
+		return c;
+	}
+}

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

@@ -0,0 +1,58 @@
+
+package eu.dnetlib.dhp.common.api.zenodo;
+
+import java.io.Serializable;
+
+import net.minidev.json.annotate.JsonIgnore;
+
+public class File implements Serializable {
+	private String checksum;
+	private String filename;
+	private long filesize;
+	private String id;
+
+	@JsonIgnore
+	// private Links links;
+
+	public String getChecksum() {
+		return checksum;
+	}
+
+	public void setChecksum(String checksum) {
+		this.checksum = checksum;
+	}
+
+	public String getFilename() {
+		return filename;
+	}
+
+	public void setFilename(String filename) {
+		this.filename = filename;
+	}
+
+	public long getFilesize() {
+		return filesize;
+	}
+
+	public void setFilesize(long filesize) {
+		this.filesize = filesize;
+	}
+
+	public String getId() {
+		return id;
+	}
+
+	public void setId(String id) {
+		this.id = id;
+	}
+
+//    @JsonIgnore
+//    public Links getLinks() {
+//        return links;
+//    }
+//
+//    @JsonIgnore
+//    public void setLinks(Links links) {
+//        this.links = links;
+//    }
+}

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

@@ -0,0 +1,23 @@
+
+package eu.dnetlib.dhp.common.api.zenodo;
+
+import java.io.Serializable;
+
+public class Grant implements Serializable {
+	private String id;
+
+	public String getId() {
+		return id;
+	}
+
+	public void setId(String id) {
+		this.id = id;
+	}
+
+	public static Grant newInstance(String id) {
+		Grant g = new Grant();
+		g.id = id;
+
+		return g;
+	}
+}

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

@@ -0,0 +1,92 @@
+
+package eu.dnetlib.dhp.common.api.zenodo;
+
+import java.io.Serializable;
+
+public class Links implements Serializable {
+
+	private String bucket;
+
+	private String discard;
+
+	private String edit;
+	private String files;
+	private String html;
+	private String latest_draft;
+	private String latest_draft_html;
+	private String publish;
+
+	private String self;
+
+	public String getBucket() {
+		return bucket;
+	}
+
+	public void setBucket(String bucket) {
+		this.bucket = bucket;
+	}
+
+	public String getDiscard() {
+		return discard;
+	}
+
+	public void setDiscard(String discard) {
+		this.discard = discard;
+	}
+
+	public String getEdit() {
+		return edit;
+	}
+
+	public void setEdit(String edit) {
+		this.edit = edit;
+	}
+
+	public String getFiles() {
+		return files;
+	}
+
+	public void setFiles(String files) {
+		this.files = files;
+	}
+
+	public String getHtml() {
+		return html;
+	}
+
+	public void setHtml(String html) {
+		this.html = html;
+	}
+
+	public String getLatest_draft() {
+		return latest_draft;
+	}
+
+	public void setLatest_draft(String latest_draft) {
+		this.latest_draft = latest_draft;
+	}
+
+	public String getLatest_draft_html() {
+		return latest_draft_html;
+	}
+
+	public void setLatest_draft_html(String latest_draft_html) {
+		this.latest_draft_html = latest_draft_html;
+	}
+
+	public String getPublish() {
+		return publish;
+	}
+
+	public void setPublish(String publish) {
+		this.publish = publish;
+	}
+
+	public String getSelf() {
+		return self;
+	}
+
+	public void setSelf(String self) {
+		this.self = self;
+	}
+}

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

@@ -0,0 +1,153 @@
+
+package eu.dnetlib.dhp.common.api.zenodo;
+
+import java.io.Serializable;
+import java.util.List;
+
+public class Metadata implements Serializable {
+
+	private String access_right;
+	private List<Community> communities;
+	private List<Creator> creators;
+	private String description;
+	private String doi;
+	private List<Grant> grants;
+	private List<String> keywords;
+	private String language;
+	private String license;
+	private PrereserveDoi prereserve_doi;
+	private String publication_date;
+	private List<String> references;
+	private List<RelatedIdentifier> related_identifiers;
+	private String title;
+	private String upload_type;
+	private String version;
+
+	public String getUpload_type() {
+		return upload_type;
+	}
+
+	public void setUpload_type(String upload_type) {
+		this.upload_type = upload_type;
+	}
+
+	public String getVersion() {
+		return version;
+	}
+
+	public void setVersion(String version) {
+		this.version = version;
+	}
+
+	public String getAccess_right() {
+		return access_right;
+	}
+
+	public void setAccess_right(String access_right) {
+		this.access_right = access_right;
+	}
+
+	public List<Community> getCommunities() {
+		return communities;
+	}
+
+	public void setCommunities(List<Community> communities) {
+		this.communities = communities;
+	}
+
+	public List<Creator> getCreators() {
+		return creators;
+	}
+
+	public void setCreators(List<Creator> creators) {
+		this.creators = creators;
+	}
+
+	public String getDescription() {
+		return description;
+	}
+
+	public void setDescription(String description) {
+		this.description = description;
+	}
+
+	public String getDoi() {
+		return doi;
+	}
+
+	public void setDoi(String doi) {
+		this.doi = doi;
+	}
+
+	public List<Grant> getGrants() {
+		return grants;
+	}
+
+	public void setGrants(List<Grant> grants) {
+		this.grants = grants;
+	}
+
+	public List<String> getKeywords() {
+		return keywords;
+	}
+
+	public void setKeywords(List<String> keywords) {
+		this.keywords = keywords;
+	}
+
+	public String getLanguage() {
+		return language;
+	}
+
+	public void setLanguage(String language) {
+		this.language = language;
+	}
+
+	public String getLicense() {
+		return license;
+	}
+
+	public void setLicense(String license) {
+		this.license = license;
+	}
+
+	public PrereserveDoi getPrereserve_doi() {
+		return prereserve_doi;
+	}
+
+	public void setPrereserve_doi(PrereserveDoi prereserve_doi) {
+		this.prereserve_doi = prereserve_doi;
+	}
+
+	public String getPublication_date() {
+		return publication_date;
+	}
+
+	public void setPublication_date(String publication_date) {
+		this.publication_date = publication_date;
+	}
+
+	public List<String> getReferences() {
+		return references;
+	}
+
+	public void setReferences(List<String> references) {
+		this.references = references;
+	}
+
+	public List<RelatedIdentifier> getRelated_identifiers() {
+		return related_identifiers;
+	}
+
+	public void setRelated_identifiers(List<RelatedIdentifier> related_identifiers) {
+		this.related_identifiers = related_identifiers;
+	}
+
+	public String getTitle() {
+		return title;
+	}
+
+	public void setTitle(String title) {
+		this.title = title;
+	}
+}

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

@@ -0,0 +1,25 @@
+
+package eu.dnetlib.dhp.common.api.zenodo;
+
+import java.io.Serializable;
+
+public class PrereserveDoi implements Serializable {
+	private String doi;
+	private String recid;
+
+	public String getDoi() {
+		return doi;
+	}
+
+	public void setDoi(String doi) {
+		this.doi = doi;
+	}
+
+	public String getRecid() {
+		return recid;
+	}
+
+	public void setRecid(String recid) {
+		this.recid = recid;
+	}
+}

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

@@ -0,0 +1,43 @@
+
+package eu.dnetlib.dhp.common.api.zenodo;
+
+import java.io.Serializable;
+
+public class RelatedIdentifier implements Serializable {
+	private String identifier;
+	private String relation;
+	private String resource_type;
+	private String scheme;
+
+	public String getIdentifier() {
+		return identifier;
+	}
+
+	public void setIdentifier(String identifier) {
+		this.identifier = identifier;
+	}
+
+	public String getRelation() {
+		return relation;
+	}
+
+	public void setRelation(String relation) {
+		this.relation = relation;
+	}
+
+	public String getResource_type() {
+		return resource_type;
+	}
+
+	public void setResource_type(String resource_type) {
+		this.resource_type = resource_type;
+	}
+
+	public String getScheme() {
+		return scheme;
+	}
+
+	public void setScheme(String scheme) {
+		this.scheme = scheme;
+	}
+}

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

@@ -0,0 +1,118 @@
+
+package eu.dnetlib.dhp.common.api.zenodo;
+
+import java.io.Serializable;
+import java.util.List;
+
+public class ZenodoModel implements Serializable {
+
+	private String conceptrecid;
+	private String created;
+
+	private List<File> files;
+	private String id;
+	private Links links;
+	private Metadata metadata;
+	private String modified;
+	private String owner;
+	private String record_id;
+	private String state;
+	private boolean submitted;
+	private String title;
+
+	public String getConceptrecid() {
+		return conceptrecid;
+	}
+
+	public void setConceptrecid(String conceptrecid) {
+		this.conceptrecid = conceptrecid;
+	}
+
+	public String getCreated() {
+		return created;
+	}
+
+	public void setCreated(String created) {
+		this.created = created;
+	}
+
+	public List<File> getFiles() {
+		return files;
+	}
+
+	public void setFiles(List<File> files) {
+		this.files = files;
+	}
+
+	public String getId() {
+		return id;
+	}
+
+	public void setId(String id) {
+		this.id = id;
+	}
+
+	public Links getLinks() {
+		return links;
+	}
+
+	public void setLinks(Links links) {
+		this.links = links;
+	}
+
+	public Metadata getMetadata() {
+		return metadata;
+	}
+
+	public void setMetadata(Metadata metadata) {
+		this.metadata = metadata;
+	}
+
+	public String getModified() {
+		return modified;
+	}
+
+	public void setModified(String modified) {
+		this.modified = modified;
+	}
+
+	public String getOwner() {
+		return owner;
+	}
+
+	public void setOwner(String owner) {
+		this.owner = owner;
+	}
+
+	public String getRecord_id() {
+		return record_id;
+	}
+
+	public void setRecord_id(String record_id) {
+		this.record_id = record_id;
+	}
+
+	public String getState() {
+		return state;
+	}
+
+	public void setState(String state) {
+		this.state = state;
+	}
+
+	public boolean isSubmitted() {
+		return submitted;
+	}
+
+	public void setSubmitted(boolean submitted) {
+		this.submitted = submitted;
+	}
+
+	public String getTitle() {
+		return title;
+	}
+
+	public void setTitle(String title) {
+		this.title = title;
+	}
+}

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

@@ -0,0 +1,6 @@
+package eu.dnetlib.dhp.common.api.zenodo;
+
+import java.util.ArrayList;
+
+public class ZenodoModelList extends ArrayList<ZenodoModel> {
+}

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

@@ -0,0 +1,85 @@
+
+package eu.dnetlib.dhp.common.api;
+
+import java.io.File;
+import java.io.FileInputStream;
+import java.io.IOException;
+import java.io.InputStream;
+
+import org.apache.commons.io.IOUtils;
+import org.junit.jupiter.api.Assertions;
+import org.junit.jupiter.api.Disabled;
+import org.junit.jupiter.api.Test;
+
+@Disabled
+public class ZenodoAPIClientTest {
+
+	private final String URL_STRING = "https://sandbox.zenodo.org/api/deposit/depositions";
+	private final String ACCESS_TOKEN = "";
+
+	private final String CONCEPT_REC_ID = "657113";
+
+	@Test
+	public void testNewDeposition() throws IOException {
+
+		ZenodoAPIClient client = new ZenodoAPIClient(URL_STRING,
+			ACCESS_TOKEN);
+		Assertions.assertEquals(201, client.newDeposition());
+
+		File file = new File(getClass()
+			.getResource("/eu/dnetlib/dhp/common/api/COVID-19.json.gz")
+			.getPath());
+
+		InputStream is = new FileInputStream(file);
+
+		Assertions.assertEquals(200, client.uploadIS(is, "COVID-19.json.gz", file.length()));
+
+		String metadata = IOUtils.toString(getClass().getResourceAsStream("/eu/dnetlib/dhp/common/api/metadata.json"));
+
+		Assertions.assertEquals(200, client.sendMretadata(metadata));
+
+		Assertions.assertEquals(202, client.publish());
+
+	}
+
+	@Test
+	public void testNewVersionNewName() throws IOException, MissingConceptDoiException {
+
+		ZenodoAPIClient client = new ZenodoAPIClient(URL_STRING,
+			ACCESS_TOKEN);
+
+		Assertions.assertEquals(201, client.newVersion(CONCEPT_REC_ID));
+
+		File file = new File(getClass()
+			.getResource("/eu/dnetlib/dhp/common/api/newVersion")
+			.getPath());
+
+		InputStream is = new FileInputStream(file);
+
+		Assertions.assertEquals(200, client.uploadIS(is, "newVersion_deposition", file.length()));
+
+		Assertions.assertEquals(202, client.publish());
+
+	}
+
+	@Test
+	public void testNewVersionOldName() throws IOException, MissingConceptDoiException {
+
+		ZenodoAPIClient client = new ZenodoAPIClient(URL_STRING,
+			ACCESS_TOKEN);
+
+		Assertions.assertEquals(201, client.newVersion(CONCEPT_REC_ID));
+
+		File file = new File(getClass()
+			.getResource("/eu/dnetlib/dhp/common/api/newVersion2")
+			.getPath());
+
+		InputStream is = new FileInputStream(file);
+
+		Assertions.assertEquals(200, client.uploadIS(is, "newVersion_deposition", file.length()));
+
+		Assertions.assertEquals(202, client.publish());
+
+	}
+
+}

dhp-common/src/test/resources/eu/dnetlib/dhp/common/api/metadata.json

@@ -0,0 +1 @@
+{"metadata":{"access_right":"open","communities":[{"identifier":"openaire-research-graph"}],"creators":[{"affiliation":"ISTI - CNR","name":"Bardi, Alessia","orcid":"0000-0002-1112-1292"},{"affiliation":"eifl", "name":"Kuchma, Iryna"},{"affiliation":"BIH", "name":"Brobov, Evgeny"},{"affiliation":"GIDIF RBM", "name":"Truccolo, Ivana"},{"affiliation":"unesp", "name":"Monteiro, Elizabete"},{"affiliation":"und", "name":"Casalegno, Carlotta"},{"affiliation":"CARL ABRC", "name":"Clary, Erin"},{"affiliation":"The University of Edimburgh", "name":"Romanowski, Andrew"},{"affiliation":"ISTI - CNR", "name":"Pavone, Gina"},{"affiliation":"ISTI - CNR", "name":"Artini, Michele"},{"affiliation":"ISTI - CNR","name":"Atzori, Claudio","orcid":"0000-0001-9613-6639"},{"affiliation":"University of Bielefeld","name":"Bäcker, Amelie","orcid":"0000-0001-6015-2063"},{"affiliation":"ISTI - CNR","name":"Baglioni, Miriam","orcid":"0000-0002-2273-9004"},{"affiliation":"University of Bielefeld","name":"Czerniak, Andreas","orcid":"0000-0003-3883-4169"},{"affiliation":"ISTI - CNR","name":"De Bonis, Michele"},{"affiliation":"Athena Research and Innovation Centre","name":"Dimitropoulos, Harry"},{"affiliation":"Athena Research and Innovation Centre","name":"Foufoulas, Ioannis"},{"affiliation":"University of Warsaw","name":"Horst, Marek"},{"affiliation":"Athena Research and Innovation Centre","name":"Iatropoulou, Katerina"},{"affiliation":"University of Warsaw","name":"Jacewicz, Przemyslaw"},{"affiliation":"Athena Research and Innovation Centre","name":"Kokogiannaki, Argiro", "orcid":"0000-0002-3880-0244"},{"affiliation":"ISTI - CNR","name":"La Bruzzo, Sandro","orcid":"0000-0003-2855-1245"},{"affiliation":"ISTI - CNR","name":"Lazzeri, Emma"},{"affiliation":"University of Bielefeld","name":"Löhden, Aenne"},{"affiliation":"ISTI - CNR","name":"Manghi, Paolo","orcid":"0000-0001-7291-3210"},{"affiliation":"ISTI - CNR","name":"Mannocci, Andrea","orcid":"0000-0002-5193-7851"},{"affiliation":"Athena Research and Innovation Center","name":"Manola, Natalia"},{"affiliation":"ISTI - CNR","name":"Ottonello, Enrico"},{"affiliation":"University of Bielefeld","name":"Shirrwagen, Jochen"}],"description":"\\u003cp\\u003eThis dump provides access to the metadata records of publications, research data, software and projects that may be relevant to the Corona Virus Disease (COVID-19) fight. The dump contains records of the OpenAIRE COVID-19 Gateway (https://covid-19.openaire.eu/), identified via full-text mining and inference techniques applied to the OpenAIRE Research Graph (https://explore.openaire.eu/). The Graph is one of the largest Open Access collections of metadata records and links between publications, datasets, software, projects, funders, and organizations, aggregating 12,000+ scientific data sources world-wide, among which the Covid-19 data sources Zenodo COVID-19 Community, WHO (World Health Organization), BIP! FInder for COVID-19, Protein Data Bank, Dimensions, scienceOpen, and RSNA. \\u003cp\\u003eThe dump consists of a gzip file containing one json per line. Each json is compliant to the schema available at https://doi.org/10.5281/zenodo.3974226\\u003c/p\\u003e ","title":"OpenAIRE Covid-19 publications, datasets, software and projects metadata.","upload_type":"dataset","version":"1.0"}}

dhp-common/src/test/resources/eu/dnetlib/dhp/common/api/newDeposition

@@ -0,0 +1 @@
+This is a test for a new deposition

dhp-common/src/test/resources/eu/dnetlib/dhp/common/api/newVersion

@@ -0,0 +1 @@
+This is a test for a new version of an old deposition

dhp-common/src/test/resources/eu/dnetlib/dhp/common/api/newVersion2

@@ -0,0 +1,2 @@
+This is a test for a new version of an old deposition. This should replace the other new version. I expect to have only two
+files in the deposition

dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/common/ModelSupport.java

@@ -79,6 +79,15 @@ public class ModelSupport {
 		entityIdPrefix.put("result", "50");
 	}
 
+	public static final Map<String, String> idPrefixEntity = Maps.newHashMap();
+
+	static {
+		idPrefixEntity.put("10", "datasource");
+		idPrefixEntity.put("20", "organization");
+		idPrefixEntity.put("40", "project");
+		idPrefixEntity.put("50", "result");
+	}
+
 	public static final Map<String, RelationInverse> relationInverseMap = Maps.newHashMap();
 
 	static {

dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/dump/oaf/APC.java

@@ -0,0 +1,29 @@
+
+package eu.dnetlib.dhp.schema.dump.oaf;
+
+import java.io.Serializable;
+
+/**
+ * Used to refer to the Article Processing Charge information. Not dumped in this release. It contains two parameters: -
+ * currency of type String to store the currency of the APC - amount of type String to stores the charged amount
+ */
+public class APC implements Serializable {
+	private String currency;
+	private String amount;
+
+	public String getCurrency() {
+		return currency;
+	}
+
+	public void setCurrency(String currency) {
+		this.currency = currency;
+	}
+
+	public String getAmount() {
+		return amount;
+	}
+
+	public void setAmount(String amount) {
+		this.amount = amount;
+	}
+}

dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/dump/oaf/AccessRight.java

@@ -0,0 +1,31 @@
+
+package eu.dnetlib.dhp.schema.dump.oaf;
+
+/**
+ * AccessRight. Used to represent the result access rights. It extends the eu.dnet.lib.dhp.schema.dump.oaf.Qualifier
+ * element with a parameter scheme of type String to store the scheme. Values for this element are found against the
+ * COAR access right scheme. The classid of the element accessright in eu.dnetlib.dhp.schema.oaf.Result is used to get
+ * the COAR corresponding code whose value will be used to set the code parameter. The COAR label corresponding to the
+ * COAR code will be used to set the label parameter. The scheme value will always be the one referring to the COAR
+ * access right scheme
+ */
+public class AccessRight extends Qualifier {
+
+	private String scheme;
+
+	public String getScheme() {
+		return scheme;
+	}
+
+	public void setScheme(String scheme) {
+		this.scheme = scheme;
+	}
+
+	public static AccessRight newInstance(String code, String label, String scheme) {
+		AccessRight ar = new AccessRight();
+		ar.setCode(code);
+		ar.setLabel(label);
+		ar.setScheme(scheme);
+		return ar;
+	}
+}

dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/dump/oaf/Author.java

@@ -0,0 +1,73 @@
+
+package eu.dnetlib.dhp.schema.dump.oaf;
+
+import java.io.Serializable;
+import java.util.List;
+
+/**
+ * Used to represent the generic author of the result. It has six parameters: - name of type String to store the given
+ * name of the author. The value for this parameter corresponds to eu.dnetlib.dhp.schema.oaf.Author name - surname of
+ * type String to store the family name of the author. The value for this parameter corresponds to
+ * eu.dnetlib.dhp.schema.oaf.Author surname - fullname of type String to store the fullname of the author. The value for
+ * this parameter corresponds to eu.dnetlib.dhp.schema.oaf.Author fullname - rank of type Integer to store the rank on
+ * the author in the result's authors list. The value for this parameter corresponds to eu.dnetlib.dhp.schema.oaf.Author
+ * rank - pid of type eu.dnetlib.dhp.schema.dump.oaf.Pid to store the persistent identifier for the author. For the
+ * moment only ORCID identifiers will be dumped. - The id element is instantiated by using the following values in the
+ * eu.dnetlib.dhp.schema.oaf.Result pid: * Qualifier.classid for scheme * value for value - The provenance element is
+ * instantiated only if the dataInfo is set for the pid in the result to be dumped. The provenance element is
+ * instantiated by using the following values in the eu.dnetlib.dhp.schema.oaf.Result pid: *
+ * dataInfo.provenanceaction.classname for provenance * dataInfo.trust for trust
+ */
+public class Author implements Serializable {
+
+	private String fullname;
+
+	private String name;
+
+	private String surname;
+
+	private Integer rank;
+
+	private Pid pid;
+
+	public String getFullname() {
+		return fullname;
+	}
+
+	public void setFullname(String fullname) {
+		this.fullname = fullname;
+	}
+
+	public String getName() {
+		return name;
+	}
+
+	public void setName(String name) {
+		this.name = name;
+	}
+
+	public String getSurname() {
+		return surname;
+	}
+
+	public void setSurname(String surname) {
+		this.surname = surname;
+	}
+
+	public Integer getRank() {
+		return rank;
+	}
+
+	public void setRank(Integer rank) {
+		this.rank = rank;
+	}
+
+	public Pid getPid() {
+		return pid;
+	}
+
+	public void setPid(Pid pid) {
+		this.pid = pid;
+	}
+
+}

dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/dump/oaf/Container.java

@@ -0,0 +1,136 @@
+
+package eu.dnetlib.dhp.schema.dump.oaf;
+
+import java.io.Serializable;
+import java.util.Objects;
+
+/**
+ * To store information about the conference or journal where the result has been presented or published. It contains
+ * eleven parameters: - name of type String to store the name of the journal or conference. It corresponds to the
+ * parameter name of eu.dnetlib.dhp.schema.oaf.Journal - issnPrinted ot type String to store the journal printed issn.
+ * It corresponds to the parameter issnPrinted of eu.dnetlib.dhp.schema.oaf.Journal - issnOnline of type String to store
+ * the journal online issn. It corresponds to the parameter issnOnline of eu.dnetlib.dhp.schema.oaf.Journal -
+ * issnLinking of type String to store the journal linking issn. It corresponds to the parameter issnLinking of
+ * eu.dnetlib.dhp.schema.oaf.Journal - ep of type String to store the end page. It corresponds to the parameter ep of
+ * eu.dnetlib.dhp.schema.oaf.Journal - iss of type String to store the journal issue. It corresponds to the parameter
+ * iss of eu.dnetlib.dhp.schema.oaf.Journal - sp of type String to store the start page. It corresponds to the parameter
+ * sp of eu.dnetlib.dhp.schema.oaf.Journal - vol of type String to store the Volume. It corresponds to the parameter vol
+ * of eu.dnetlib.dhp.schema.oaf.Journal - edition of type String to store the edition of the journal or conference
+ * proceeding. It corresponds to the parameter edition of eu.dnetlib.dhp.schema.oaf.Journal - conferenceplace of type
+ * String to store the place of the conference. It corresponds to the parameter conferenceplace of
+ * eu.dnetlib.dhp.schema.oaf.Journal - conferencedate of type String to store the date of the conference. It corresponds
+ * to the parameter conferencedate of eu.dnetlib.dhp.schema.oaf.Journal
+ */
+public class Container implements Serializable {
+
+	private String name;
+
+	private String issnPrinted;
+
+	private String issnOnline;
+
+	private String issnLinking;
+
+	private String ep;
+
+	private String iss;
+
+	private String sp;
+
+	private String vol;
+
+	private String edition;
+
+	private String conferenceplace;
+
+	private String conferencedate;
+
+	public String getName() {
+		return name;
+	}
+
+	public void setName(String name) {
+		this.name = name;
+	}
+
+	public String getIssnPrinted() {
+		return issnPrinted;
+	}
+
+	public void setIssnPrinted(String issnPrinted) {
+		this.issnPrinted = issnPrinted;
+	}
+
+	public String getIssnOnline() {
+		return issnOnline;
+	}
+
+	public void setIssnOnline(String issnOnline) {
+		this.issnOnline = issnOnline;
+	}
+
+	public String getIssnLinking() {
+		return issnLinking;
+	}
+
+	public void setIssnLinking(String issnLinking) {
+		this.issnLinking = issnLinking;
+	}
+
+	public String getEp() {
+		return ep;
+	}
+
+	public void setEp(String ep) {
+		this.ep = ep;
+	}
+
+	public String getIss() {
+		return iss;
+	}
+
+	public void setIss(String iss) {
+		this.iss = iss;
+	}
+
+	public String getSp() {
+		return sp;
+	}
+
+	public void setSp(String sp) {
+		this.sp = sp;
+	}
+
+	public String getVol() {
+		return vol;
+	}
+
+	public void setVol(String vol) {
+		this.vol = vol;
+	}
+
+	public String getEdition() {
+		return edition;
+	}
+
+	public void setEdition(String edition) {
+		this.edition = edition;
+	}
+
+	public String getConferenceplace() {
+		return conferenceplace;
+	}
+
+	public void setConferenceplace(String conferenceplace) {
+		this.conferenceplace = conferenceplace;
+	}
+
+	public String getConferencedate() {
+		return conferencedate;
+	}
+
+	public void setConferencedate(String conferencedate) {
+		this.conferencedate = conferencedate;
+	}
+
+}

dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/dump/oaf/ControlledField.java

@@ -0,0 +1,38 @@
+
+package eu.dnetlib.dhp.schema.dump.oaf;
+
+import java.io.Serializable;
+
+/**
+ * To represent the information described by a scheme and a value in that scheme (i.e. pid). It has two parameters: -
+ * scheme of type String to store the scheme - value of type String to store the value in that scheme
+ */
+public class ControlledField implements Serializable {
+	private String scheme;
+	private String value;
+
+	public String getScheme() {
+		return scheme;
+	}
+
+	public void setScheme(String scheme) {
+		this.scheme = scheme;
+	}
+
+	public String getValue() {
+		return value;
+	}
+
+	public void setValue(String value) {
+		this.value = value;
+	}
+
+	public static ControlledField newInstance(String scheme, String value) {
+		ControlledField cf = new ControlledField();
+
+		cf.setScheme(scheme);
+		cf.setValue(value);
+
+		return cf;
+	}
+}

dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/dump/oaf/Country.java

@@ -0,0 +1,37 @@
+
+package eu.dnetlib.dhp.schema.dump.oaf;
+
+/**
+ * Represents the country associated to this result. It extends eu.dnetlib.dhp.schema.dump.oaf.Qualifier with a
+ * provenance parameter of type eu.dnetlib.dhp.schema.dumo.oaf.Provenance. The country in not mapped if its value in the
+ * result reprensented in the internal format is Unknown. The value for this element correspond to: - code corresponds
+ * to the classid of eu.dnetlib.dhp.schema.oaf.Country - label corresponds to the classname of
+ * eu.dnetlib.dhp.schema.oaf.Country - provenance set only if the dataInfo associated to the Country of the result to be
+ * dumped is not null. In this case : - provenance corresponds to dataInfo.provenanceaction.classid (to be modified with
+ * datainfo.provenanceaction.classname) - trust corresponds to dataInfo.trust
+ */
+public class Country extends Qualifier {
+
+	private Provenance provenance;
+
+	public Provenance getProvenance() {
+		return provenance;
+	}
+
+	public void setProvenance(Provenance provenance) {
+		this.provenance = provenance;
+	}
+
+	public static Country newInstance(String code, String label, Provenance provenance) {
+		Country c = new Country();
+		c.setProvenance(provenance);
+		c.setCode(code);
+		c.setLabel(label);
+		return c;
+	}
+
+	public static Country newInstance(String code, String label, String provenance, String trust) {
+		return newInstance(code, label, Provenance.newInstance(provenance, trust));
+	}
+
+}

dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/dump/oaf/Funder.java

@@ -0,0 +1,35 @@
+package eu.dnetlib.dhp.schema.dump.oaf;
+
+import java.io.Serializable;
+
+public class Funder implements Serializable {
+    private String shortName;
+
+    private String name;
+
+    private String jurisdiction;
+
+    public String getJurisdiction() {
+        return jurisdiction;
+    }
+
+    public void setJurisdiction(String jurisdiction) {
+        this.jurisdiction = jurisdiction;
+    }
+
+    public String getShortName() {
+        return shortName;
+    }
+
+    public void setShortName(String shortName) {
+        this.shortName = shortName;
+    }
+
+    public String getName() {
+        return name;
+    }
+
+    public void setName(String name) {
+        this.name = name;
+    }
+}

dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/dump/oaf/GeoLocation.java

@@ -0,0 +1,53 @@
+
+package eu.dnetlib.dhp.schema.dump.oaf;
+
+import java.io.Serializable;
+
+import org.apache.commons.lang3.StringUtils;
+
+import com.fasterxml.jackson.annotation.JsonIgnore;
+
+/**
+ * Represents the geolocation information. It has three parameters: - point of type String to store the point
+ * information. It corresponds to eu.dnetlib.dhp.schema.oaf.GeoLocation point - box ot type String to store the box
+ * information. It corresponds to eu.dnetlib.dhp.schema.oaf.GeoLocation box - place of type String to store the place
+ * information. It corresponds to eu.dnetlib.dhp.schema.oaf.GeoLocation place
+ */
+public class GeoLocation implements Serializable {
+
+	private String point;
+
+	private String box;
+
+	private String place;
+
+	public String getPoint() {
+		return point;
+	}
+
+	public void setPoint(String point) {
+		this.point = point;
+	}
+
+	public String getBox() {
+		return box;
+	}
+
+	public void setBox(String box) {
+		this.box = box;
+	}
+
+	public String getPlace() {
+		return place;
+	}
+
+	public void setPlace(String place) {
+		this.place = place;
+	}
+
+	@JsonIgnore
+	public boolean isBlank() {
+		return StringUtils.isBlank(point) && StringUtils.isBlank(box) && StringUtils.isBlank(place);
+	}
+
+}

dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/dump/oaf/Instance.java

@@ -0,0 +1,107 @@
+
+package eu.dnetlib.dhp.schema.dump.oaf;
+
+import java.io.Serializable;
+import java.util.List;
+
+/**
+ * Represents the manifestations (i.e. different versions) of the result. For example: the pre-print and the published
+ * versions are two manifestations of the same research result. It has the following parameters: - license of type
+ * String to store the license applied to the instance. It corresponds to the value of the licence in the instance to be
+ * dumped - accessright of type eu.dnetlib.dhp.schema.dump.oaf.AccessRight to store the accessright of the instance. -
+ * type of type String to store the type of the instance as defined in the corresponding dnet vocabulary
+ * (dnet:pubication_resource). It corresponds to the instancetype.classname of the instance to be mapped - hostedby of
+ * type eu.dnetlib.dhp.schema.dump.oaf.KeyValue to store the information about the source from which the instance can be
+ * viewed or downloaded. It is mapped against the hostedby parameter of the instance to be dumped and - key corresponds
+ * to hostedby.key - value corresponds to hostedby.value - url of type List<String> list of locations where the instance
+ * is accessible. It corresponds to url of the instance to be dumped - collectedfrom of type
+ * eu.dnetlib.dhp.schema.dump.oaf.KeyValue to store the information about the source from which the instance has been
+ * collected. It is mapped against the collectedfrom parameter of the instance to be dumped and - key corresponds to
+ * collectedfrom.key - value corresponds to collectedfrom.value - publicationdate of type String to store the
+ * publication date of the instance ;// dateofacceptance; - refereed of type String to store information abour tthe
+ * review status of the instance. Possible values are 'Unknown', 'nonPeerReviewed', 'peerReviewed'. It corresponds to
+ * refereed.classname of the instance to be dumped
+ */
+public class Instance implements Serializable {
+
+	private String license;
+
+	private AccessRight accessright;
+
+	private String type;
+
+	 private KeyValue hostedby;
+
+	private List<String> url;
+
+	 private KeyValue collectedfrom;
+
+	private String publicationdate;// dateofacceptance;
+
+	private String refereed; // peer-review status
+
+	public String getLicense() {
+		return license;
+	}
+
+	public void setLicense(String license) {
+		this.license = license;
+	}
+
+	public AccessRight getAccessright() {
+		return accessright;
+	}
+
+	public void setAccessright(AccessRight accessright) {
+		this.accessright = accessright;
+	}
+
+	public String getType() {
+		return type;
+	}
+
+	public void setType(String type) {
+		this.type = type;
+	}
+
+	public KeyValue getHostedby() {
+		return hostedby;
+	}
+
+	public void setHostedby(KeyValue hostedby) {
+		this.hostedby = hostedby;
+	}
+
+	public List<String> getUrl() {
+		return url;
+	}
+
+	public void setUrl(List<String> url) {
+		this.url = url;
+	}
+
+	public KeyValue getCollectedfrom() {
+		return collectedfrom;
+	}
+
+	public void setCollectedfrom(KeyValue collectedfrom) {
+		this.collectedfrom = collectedfrom;
+	}
+
+	public String getPublicationdate() {
+		return publicationdate;
+	}
+
+	public void setPublicationdate(String publicationdate) {
+		this.publicationdate = publicationdate;
+	}
+
+	public String getRefereed() {
+		return refereed;
+	}
+
+	public void setRefereed(String refereed) {
+		this.refereed = refereed;
+	}
+
+}

dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/dump/oaf/KeyValue.java

@@ -0,0 +1,48 @@
+
+package eu.dnetlib.dhp.schema.dump.oaf;
+
+import java.io.Serializable;
+
+import org.apache.commons.lang3.StringUtils;
+
+import com.fasterxml.jackson.annotation.JsonIgnore;
+
+/**
+ * To represent the information described by a key and a value. It has two parameters: - key to store the key (generally
+ * the OpenAIRE id for some entity) - value to store the value (generally the OpenAIRE name for the key)
+ */
+public class KeyValue implements Serializable {
+
+	private String key;
+
+	private String value;
+
+	public String getKey() {
+		return key;
+	}
+
+	public void setKey(String key) {
+		this.key = key;
+	}
+
+	public String getValue() {
+		return value;
+	}
+
+	public void setValue(String value) {
+		this.value = value;
+	}
+
+	public static KeyValue newInstance(String key, String value) {
+		KeyValue inst = new KeyValue();
+		inst.key = key;
+		inst.value = value;
+		return inst;
+	}
+
+	@JsonIgnore
+	public boolean isBlank() {
+		return StringUtils.isBlank(key) && StringUtils.isBlank(value);
+	}
+
+}

dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/dump/oaf/Pid.java

@@ -0,0 +1,45 @@
+
+package eu.dnetlib.dhp.schema.dump.oaf;
+
+import java.io.Serializable;
+
+/**
+ * To represent the generic persistent identifier. It has two parameters: - id of type
+ * eu.dnetlib.dhp.schema.dump.oaf.ControlledField to store the scheme and value of the Persistent Identifier. -
+ * provenance of type eu.dnetlib.dhp.schema.dump.oaf.Provenance to store the provenance and trust of the information
+ */
+public class Pid implements Serializable {
+	private ControlledField id;
+	private Provenance provenance;
+
+	public ControlledField getId() {
+		return id;
+	}
+
+	public void setId(ControlledField pid) {
+		this.id = pid;
+	}
+
+	public Provenance getProvenance() {
+		return provenance;
+	}
+
+	public void setProvenance(Provenance provenance) {
+		this.provenance = provenance;
+	}
+
+	public static Pid newInstance(ControlledField pid, Provenance provenance) {
+		Pid p = new Pid();
+		p.id = pid;
+		p.provenance = provenance;
+
+		return p;
+	}
+
+	public static Pid newInstance(ControlledField pid) {
+		Pid p = new Pid();
+		p.id = pid;
+
+		return p;
+	}
+}

dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/dump/oaf/Project.java

@@ -0,0 +1,44 @@
+package eu.dnetlib.dhp.schema.dump.oaf;
+
+import java.io.Serializable;
+
+public class Project implements Serializable {
+    protected String id;// OpenAIRE id
+    protected String code;
+
+    protected String acronym;
+
+    protected String title;
+
+    public String getId() {
+        return id;
+    }
+
+    public void setId(String id) {
+        this.id = id;
+    }
+
+    public String getCode() {
+        return code;
+    }
+
+    public void setCode(String code) {
+        this.code = code;
+    }
+
+    public String getAcronym() {
+        return acronym;
+    }
+
+    public void setAcronym(String acronym) {
+        this.acronym = acronym;
+    }
+
+    public String getTitle() {
+        return title;
+    }
+
+    public void setTitle(String title) {
+        this.title = title;
+    }
+}

dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/dump/oaf/Provenance.java

@@ -0,0 +1,41 @@
+
+package eu.dnetlib.dhp.schema.dump.oaf;
+
+import java.io.Serializable;
+
+/**
+ * Indicates the process that produced (or provided) the information, and the trust associated to the information. It
+ * has two parameters: - provenance of type String to store the provenance of the information, - trust of type String to
+ * store the trust associated to the information
+ */
+public class Provenance implements Serializable {
+	private String provenance;
+	private String trust;
+
+	public String getProvenance() {
+		return provenance;
+	}
+
+	public void setProvenance(String provenance) {
+		this.provenance = provenance;
+	}
+
+	public String getTrust() {
+		return trust;
+	}
+
+	public void setTrust(String trust) {
+		this.trust = trust;
+	}
+
+	public static Provenance newInstance(String provenance, String trust) {
+		Provenance p = new Provenance();
+		p.provenance = provenance;
+		p.trust = trust;
+		return p;
+	}
+
+	public String toString() {
+		return provenance + trust;
+	}
+}

dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/dump/oaf/Qualifier.java

@@ -0,0 +1,42 @@
+
+package eu.dnetlib.dhp.schema.dump.oaf;
+
+import java.io.Serializable;
+
+import org.apache.commons.lang3.StringUtils;
+
+import com.fasterxml.jackson.annotation.JsonIgnore;
+
+/**
+ * To represent the information described by a code and a value It has two parameters: - code to store the code
+ * (generally the classid of the eu.dnetlib.dhp.schema.oaf.Qualifier element) - label to store the label (generally the
+ * classname of the eu.dnetlib.dhp.schema.oaf.Qualifier element
+ */
+public class Qualifier implements Serializable {
+
+	private String code; // the classid in the Qualifier
+	private String label; // the classname in the Qualifier
+
+	public String getCode() {
+		return code;
+	}
+
+	public void setCode(String code) {
+		this.code = code;
+	}
+
+	public String getLabel() {
+		return label;
+	}
+
+	public void setLabel(String label) {
+		this.label = label;
+	}
+
+	public static Qualifier newInstance(String code, String value) {
+		Qualifier qualifier = new Qualifier();
+		qualifier.setCode(code);
+		qualifier.setLabel(value);
+		return qualifier;
+	}
+}

dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/dump/oaf/Result.java

@@ -0,0 +1,391 @@
+
+package eu.dnetlib.dhp.schema.dump.oaf;
+
+import java.io.Serializable;
+import java.util.List;
+
+import eu.dnetlib.dhp.schema.dump.oaf.community.Project;
+
+/**
+ * To represent the dumped result. It will be extended in the dump for Research Communities - Research
+ * Initiative/Infrastructures. It has the following parameters: - author of type
+ * List<eu.dnetlib.dhpschema.dump.oaf.Author> to describe the authors of a result. For each author in the result
+ * represented in the internal model one author in the esternal model is produced. - type of type String to represent
+ * the category of the result. Possible values are publication, dataset, software, other. It corresponds to
+ * resulttype.classname of the dumped result - language of type eu.dnetlib.dhp.schema.dump.oaf.Qualifier to store
+ * information about the language of the result. It is dumped as - code corresponds to language.classid - value
+ * corresponds to language.classname - country of type List<eu.dnetlib.dhp.schema.dump.oaf.Country> to store the country
+ * list to which the result is associated. For each country in the result respresented in the internal model one country
+ * in the external model is produces - subjects of type List<eu.dnetlib.dhp.dump.oaf.Subject> to store the subjects for
+ * the result. For each subject in the result represented in the internal model one subject in the external model is
+ * produced - maintitle of type String to store the main title of the result. It corresponds to the value of the first
+ * title in the resul to be dumped having classid equals to "main title" - subtitle of type String to store the subtitle
+ * of the result. It corresponds to the value of the first title in the resul to be dumped having classid equals to
+ * "subtitle" - description of type List<String> to store the description of the result. It corresponds to the list of
+ * description.value in the result represented in the internal model - publicationdate of type String to store the
+ * pubblication date. It corresponds to dateofacceptance.value in the result represented in the internal model -
+ * publisher of type String to store information about the publisher. It corresponds to publisher.value of the result
+ * represented in the intrenal model - embargoenddate of type String to store the embargo end date. It corresponds to
+ * embargoenddate.value of the result represented in the internal model - source of type List<String> See definition of
+ * Dublin Core field dc:source. It corresponds to the list of source.value in the result represented in the internal
+ * model - format of type List<String> It corresponds to the list of format.value in the result represented in the
+ * internal model - contributor of type List<String> to represent contributors for this result. It corresponds to the
+ * list of contributor.value in the result represented in the internal model - coverage of type String. It corresponds
+ * to the list of coverage.value in the result represented in the internal model - bestaccessright of type
+ * eu.dnetlib.dhp.schema.dump.oaf.AccessRight to store informatin about the openest access right associated to the
+ * manifestations of this research results. It corresponds to the same parameter in the result represented in the
+ * internal model - instance of type List<eu.dnetlib.dhp.schema.dump.oaf.Instance> to store all the instances associated
+ * to the result. It corresponds to the same parameter in the result represented in the internal model - container of
+ * type eu.dnetlib.dhp.schema/dump.oaf.Container (only for result of type publication). It corresponds to the parameter
+ * journal of the result represented in the internal model - documentationUrl of type List<String> (only for results of
+ * type software) to store the URLs to the software documentation. It corresponds to the list of documentationUrl.value
+ * of the result represented in the internal model - codeRepositoryUrl of type String (only for results of type
+ * software) to store the URL to the repository with the source code. It corresponds to codeRepositoryUrl.value of the
+ * result represented in the internal model - programmingLanguage of type String (only for results of type software) to
+ * store the programming language. It corresponds to programmingLanguaga.classid of the result represented in the
+ * internal model - contactperson of type List<String> (only for results of type other) to store the contact person for
+ * this result. It corresponds to the list of contactperson.value of the result represented in the internal model -
+ * contactgroup of type List<String> (only for results of type other) to store the information for the contact group. It
+ * corresponds to the list of contactgroup.value of the result represented in the internal model - tool of type
+ * List<String> (only fro results of type other) to store information about tool useful for the interpretation and/or
+ * re-used of the research product. It corresponds to the list of tool.value in the result represented in the internal
+ * modelt - size of type String (only for results of type dataset) to store the size of the dataset. It corresponds to
+ * size.value in the result represented in the internal model - version of type String (only for results of type
+ * dataset) to store the version. It corresponds to version.value of the result represented in the internal model -
+ * geolocation fo type List<eu.dnetlib.dhp.schema.dump.oaf.GeoLocation> (only for results of type dataset) to store
+ * geolocation information. For each geolocation element in the result represented in the internal model a GeoLocation
+ * in the external model il produced - id of type String to store the OpenAIRE id of the result. It corresponds to the
+ * id of the result represented in the internal model - originalId of type List<String> to store the original ids of the
+ * result. It corresponds to the originalId of the result represented in the internal model - pid of type
+ * List<eu.dnetlib.dhp.schema.dump.oaf.ControlledField> to store the persistent identifiers for the result. For each pid
+ * in the results represented in the internal model one pid in the external model is produced. The value correspondence
+ * is: - scheme corresponds to pid.qualifier.classid of the result represented in the internal model - value corresponds
+ * to the pid.value of the result represented in the internal model - dateofcollection of type String to store
+ * information about the time OpenAIRE collected the record. It corresponds to dateofcollection of the result
+ * represented in the internal model - lasteupdatetimestamp of type String to store the timestamp of the last update of
+ * the record. It corresponds to lastupdatetimestamp of the resord represented in the internal model
+ */
+public class Result implements Serializable {
+
+	private List<Author> author;
+
+	// resulttype allows subclassing results into publications | datasets | software
+	private String type; // resulttype
+
+	// common fields
+	private Qualifier language;
+
+	private List<Country> country;
+
+	private List<Subject> subjects;
+
+	private String maintitle;
+
+	private String subtitle;
+
+	private List<String> description;
+
+	private String publicationdate; // dateofacceptance;
+
+	private String publisher;
+
+	private String embargoenddate;
+
+	private List<String> source;
+
+	private List<String> format;
+
+	private List<String> contributor;
+
+	private List<String> coverage;
+
+	private AccessRight bestaccessright;
+
+	private List<Instance> instance;
+
+	private Container container;// Journal
+
+	private List<String> documentationUrl; // software
+
+	private String codeRepositoryUrl; // software
+
+	private String programmingLanguage; // software
+
+	private List<String> contactperson; // orp
+
+	private List<String> contactgroup; // orp
+
+	private List<String> tool; // orp
+
+	private String size; // dataset
+
+	private String version; // dataset
+
+	private List<GeoLocation> geolocation; // dataset
+
+	private String id;
+
+	private List<String> originalId;
+
+	private List<ControlledField> pid;
+
+	private String dateofcollection;
+
+	private Long lastupdatetimestamp;
+
+	public Long getLastupdatetimestamp() {
+		return lastupdatetimestamp;
+	}
+
+	public void setLastupdatetimestamp(Long lastupdatetimestamp) {
+		this.lastupdatetimestamp = lastupdatetimestamp;
+	}
+
+	public String getId() {
+		return id;
+	}
+
+	public void setId(String id) {
+		this.id = id;
+	}
+
+	public List<String> getOriginalId() {
+		return originalId;
+	}
+
+	public void setOriginalId(List<String> originalId) {
+		this.originalId = originalId;
+	}
+
+	public List<ControlledField> getPid() {
+		return pid;
+	}
+
+	public void setPid(List<ControlledField> pid) {
+		this.pid = pid;
+	}
+
+	public String getDateofcollection() {
+		return dateofcollection;
+	}
+
+	public void setDateofcollection(String dateofcollection) {
+		this.dateofcollection = dateofcollection;
+	}
+
+	public List<Author> getAuthor() {
+		return author;
+	}
+
+	public String getType() {
+		return type;
+	}
+
+	public void setType(String type) {
+		this.type = type;
+	}
+
+	public Container getContainer() {
+		return container;
+	}
+
+	public void setContainer(Container container) {
+		this.container = container;
+	}
+
+	public void setAuthor(List<Author> author) {
+		this.author = author;
+	}
+
+	public Qualifier getLanguage() {
+		return language;
+	}
+
+	public void setLanguage(Qualifier language) {
+		this.language = language;
+	}
+
+	public List<Country> getCountry() {
+		return country;
+	}
+
+	public void setCountry(List<Country> country) {
+		this.country = country;
+	}
+
+	public List<Subject> getSubjects() {
+		return subjects;
+	}
+
+	public void setSubjects(List<Subject> subjects) {
+		this.subjects = subjects;
+	}
+
+	public String getMaintitle() {
+		return maintitle;
+	}
+
+	public void setMaintitle(String maintitle) {
+		this.maintitle = maintitle;
+	}
+
+	public String getSubtitle() {
+		return subtitle;
+	}
+
+	public void setSubtitle(String subtitle) {
+		this.subtitle = subtitle;
+	}
+
+	public List<String> getDescription() {
+		return description;
+	}
+
+	public void setDescription(List<String> description) {
+		this.description = description;
+	}
+
+	public String getPublicationdate() {
+		return publicationdate;
+	}
+
+	public void setPublicationdate(String publicationdate) {
+		this.publicationdate = publicationdate;
+	}
+
+	public String getPublisher() {
+		return publisher;
+	}
+
+	public void setPublisher(String publisher) {
+		this.publisher = publisher;
+	}
+
+	public String getEmbargoenddate() {
+		return embargoenddate;
+	}
+
+	public void setEmbargoenddate(String embargoenddate) {
+		this.embargoenddate = embargoenddate;
+	}
+
+	public List<String> getSource() {
+		return source;
+	}
+
+	public void setSource(List<String> source) {
+		this.source = source;
+	}
+
+	public List<String> getFormat() {
+		return format;
+	}
+
+	public void setFormat(List<String> format) {
+		this.format = format;
+	}
+
+	public List<String> getContributor() {
+		return contributor;
+	}
+
+	public void setContributor(List<String> contributor) {
+		this.contributor = contributor;
+	}
+
+	public List<String> getCoverage() {
+		return coverage;
+	}
+
+	public void setCoverage(List<String> coverage) {
+		this.coverage = coverage;
+	}
+
+	public AccessRight getBestaccessright() {
+		return bestaccessright;
+	}
+
+	public void setBestaccessright(AccessRight bestaccessright) {
+		this.bestaccessright = bestaccessright;
+	}
+
+	public List<Instance> getInstance() {
+		return instance;
+	}
+
+	public void setInstance(List<Instance> instance) {
+		this.instance = instance;
+	}
+
+	public List<String> getDocumentationUrl() {
+		return documentationUrl;
+	}
+
+	public void setDocumentationUrl(List<String> documentationUrl) {
+		this.documentationUrl = documentationUrl;
+	}
+
+	public String getCodeRepositoryUrl() {
+		return codeRepositoryUrl;
+	}
+
+	public void setCodeRepositoryUrl(String codeRepositoryUrl) {
+		this.codeRepositoryUrl = codeRepositoryUrl;
+	}
+
+	public String getProgrammingLanguage() {
+		return programmingLanguage;
+	}
+
+	public void setProgrammingLanguage(String programmingLanguage) {
+		this.programmingLanguage = programmingLanguage;
+	}
+
+	public List<String> getContactperson() {
+		return contactperson;
+	}
+
+	public void setContactperson(List<String> contactperson) {
+		this.contactperson = contactperson;
+	}
+
+	public List<String> getContactgroup() {
+		return contactgroup;
+	}
+
+	public void setContactgroup(List<String> contactgroup) {
+		this.contactgroup = contactgroup;
+	}
+
+	public List<String> getTool() {
+		return tool;
+	}
+
+	public void setTool(List<String> tool) {
+		this.tool = tool;
+	}
+
+	public String getSize() {
+		return size;
+	}
+
+	public void setSize(String size) {
+		this.size = size;
+	}
+
+	public String getVersion() {
+		return version;
+	}
+
+	public void setVersion(String version) {
+		this.version = version;
+	}
+
+	public List<GeoLocation> getGeolocation() {
+		return geolocation;
+	}
+
+	public void setGeolocation(List<GeoLocation> geolocation) {
+		this.geolocation = geolocation;
+	}
+}

dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/dump/oaf/Subject.java

@@ -0,0 +1,34 @@
+
+package eu.dnetlib.dhp.schema.dump.oaf;
+
+import java.io.Serializable;
+
+/**
+ * To represent keywords associated to the result. It has two parameters: - subject of type
+ * eu.dnetlib.dhp.schema.dump.oaf.ControlledField to describe the subject. It mapped as: - schema it corresponds to
+ * qualifier.classid of the dumped subject - value it corresponds to the subject value - provenance of type
+ * eu.dnetlib.dhp.schema.dump.oaf.Provenance to represent the provenance of the subject. It is dumped only if dataInfo
+ * is not null. In this case: - provenance corresponds to dataInfo.provenanceaction.classname - trust corresponds to
+ * dataInfo.trust
+ */
+public class Subject implements Serializable {
+	private ControlledField subject;
+	private Provenance provenance;
+
+	public ControlledField getSubject() {
+		return subject;
+	}
+
+	public void setSubject(ControlledField subject) {
+		this.subject = subject;
+	}
+
+	public Provenance getProvenance() {
+		return provenance;
+	}
+
+	public void setProvenance(Provenance provenance) {
+		this.provenance = provenance;
+	}
+
+}

dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/dump/oaf/community/CommunityResult.java

@@ -0,0 +1,51 @@
+
+package eu.dnetlib.dhp.schema.dump.oaf.community;
+
+import java.util.List;
+
+import eu.dnetlib.dhp.schema.dump.oaf.KeyValue;
+import eu.dnetlib.dhp.schema.dump.oaf.Result;
+
+/**
+ * extends eu.dnetlib.dhp.schema.dump.oaf.Result with the following parameters: - projects of type
+ * List<eu.dnetlib.dhp.schema.dump.oaf.community.Project> to store the list of projects related to the result. The
+ * information is added after the result is mapped to the external model - context of type
+ * List<eu.dnetlib.dhp.schema/dump.oaf.community.Context> to store information about the RC RI related to the result.
+ * For each context in the result represented in the internal model one context in the external model is produced -
+ * collectedfrom of type List<eu.dnetliv.dhp.schema.dump.oaf.KeyValue> to store information about the sources from which
+ * the record has been collected. For each collectedfrom in the result represented in the internal model one
+ * collectedfrom in the external model is produced
+ */
+public class CommunityResult extends Result {
+
+	private List<Project> projects;
+
+	private List<Context> context;
+
+	protected List<KeyValue> collectedfrom;
+
+	public List<KeyValue> getCollectedfrom() {
+		return collectedfrom;
+	}
+
+	public void setCollectedfrom(List<KeyValue> collectedfrom) {
+		this.collectedfrom = collectedfrom;
+	}
+
+	public List<Project> getProjects() {
+		return projects;
+	}
+
+	public void setProjects(List<Project> projects) {
+		this.projects = projects;
+	}
+
+	public List<Context> getContext() {
+		return context;
+	}
+
+	public void setContext(List<Context> context) {
+		this.context = context;
+	}
+
+}

dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/dump/oaf/community/Context.java

@@ -0,0 +1,40 @@
+
+package eu.dnetlib.dhp.schema.dump.oaf.community;
+
+import java.util.List;
+import java.util.Objects;
+
+import eu.dnetlib.dhp.schema.dump.oaf.Provenance;
+import eu.dnetlib.dhp.schema.dump.oaf.Qualifier;
+
+/**
+ * Reference to a relevant research infrastructure, initiative or community (RI/RC) among those collaborating with
+ * OpenAIRE. It extend eu.dnetlib.dhp.shema.dump.oaf.Qualifier with a parameter provenance of type
+ * List<eu.dnetlib.dhp.schema.dump.oaf.Provenance> to store the provenances of the association between the result and
+ * the RC/RI. The values for this element correspond to: - code: it corresponds to the id of the context in the result
+ * to be mapped. If the context id refers to a RC/RI and contains '::' only the part of the id before the first "::"
+ * will be used as value for code - label it corresponds to the label associated to the id. The information id taken
+ * from the profile of the RC/RI - provenance it is set only if the dataInfo associated to the contenxt element of the
+ * result to be dumped is not null. For each dataInfo one instance of type eu.dnetlib.dhp.schema.dump.oaf.Provenance is
+ * instantiated if the element datainfo.provenanceaction is not null. In this case - provenance corresponds to
+ * dataInfo.provenanceaction.classname - trust corresponds to dataInfo.trust
+ */
+public class Context extends Qualifier {
+	private List<Provenance> provenance;
+
+	public List<Provenance> getProvenance() {
+		return provenance;
+	}
+
+	public void setProvenance(List<Provenance> provenance) {
+		this.provenance = provenance;
+	}
+
+	@Override
+	public int hashCode() {
+		String provenance = new String();
+		this.provenance.forEach(p -> provenance.concat(p.toString()));
+		return Objects.hash(getCode(), getLabel(), provenance);
+	}
+
+}

dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/dump/oaf/community/Funder.java

@@ -0,0 +1,52 @@
+
+package eu.dnetlib.dhp.schema.dump.oaf.community;
+
+import java.io.Serializable;
+
+/**
+ * To store information about the funder funding the project related to the result. It has the following parameters: -
+ * shortName of type String to store the funder short name (e.c. AKA). - name of type String to store the funder name
+ * (e.c. Akademy of Finland) - fundingStream of type String to store the funding stream - jurisdiction of type String to
+ * store the jurisdiction of the funder
+ */
+public class Funder implements Serializable {
+	private String shortName;
+
+	private String name;
+
+	private String fundingStream;
+
+	private String jurisdiction;
+
+	public String getJurisdiction() {
+		return jurisdiction;
+	}
+
+	public void setJurisdiction(String jurisdiction) {
+		this.jurisdiction = jurisdiction;
+	}
+
+	public String getShortName() {
+		return shortName;
+	}
+
+	public void setShortName(String shortName) {
+		this.shortName = shortName;
+	}
+
+	public String getName() {
+		return name;
+	}
+
+	public void setName(String name) {
+		this.name = name;
+	}
+
+	public String getFundingStream() {
+		return fundingStream;
+	}
+
+	public void setFundingStream(String fundingStream) {
+		this.fundingStream = fundingStream;
+	}
+}

dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/dump/oaf/community/Project.java

@@ -0,0 +1,88 @@
+
+package eu.dnetlib.dhp.schema.dump.oaf.community;
+
+import java.io.Serializable;
+
+import eu.dnetlib.dhp.schema.dump.oaf.Provenance;
+
+/**
+ * To store information about the project related to the result. This information is not directly mapped from the result
+ * represented in the internal model because it is not there. The mapped result will be enriched with project
+ * information derived by relation between results and projects. Project class has the following parameters: - id of
+ * type String to store the OpenAIRE id for the Project - code of type String to store the grant agreement - acronym of
+ * type String to store the acronym for the project - title of type String to store the title of the project - funder of
+ * type eu.dnetlib.dhp.schema.dump.oaf.community.Funder to store information about the funder funding the project -
+ * provenance of type eu.dnetlib.dhp.schema.dump.oaf.Provenance to store information about the. provenance of the
+ * association between the result and the project
+ */
+public class Project implements Serializable {
+
+	private String id;// OpenAIRE id
+	private String code;
+
+	private String acronym;
+
+	private String title;
+
+	private Funder funder;
+
+	private Provenance provenance;
+
+	public Provenance getProvenance() {
+		return provenance;
+	}
+
+	public void setProvenance(Provenance provenance) {
+		this.provenance = provenance;
+	}
+
+	public String getId() {
+		return id;
+	}
+
+	public void setId(String id) {
+		this.id = id;
+	}
+
+	public String getCode() {
+		return code;
+	}
+
+	public void setCode(String code) {
+		this.code = code;
+	}
+
+	public String getAcronym() {
+		return acronym;
+	}
+
+	public void setAcronym(String acronym) {
+		this.acronym = acronym;
+	}
+
+	public String getTitle() {
+		return title;
+	}
+
+	public void setTitle(String title) {
+		this.title = title;
+	}
+
+	public Funder getFunder() {
+		return funder;
+	}
+
+	public void setFunder(Funder funders) {
+		this.funder = funders;
+	}
+
+	public static Project newInstance(String id, String code, String acronym, String title, Funder funder) {
+		Project project = new Project();
+		project.setAcronym(acronym);
+		project.setCode(code);
+		project.setFunder(funder);
+		project.setId(id);
+		project.setTitle(title);
+		return project;
+	}
+}

dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/dump/oaf/graph/Constants.java

@@ -0,0 +1,21 @@
+
+package eu.dnetlib.dhp.schema.dump.oaf.graph;
+
+import java.io.Serializable;
+
+public class Constants implements Serializable {
+	// collectedFrom va con isProvidedBy -> becco da ModelSupport
+
+	public static final String HOSTED_BY = "isHostedBy";
+	public static final String HOSTS = "hosts";
+
+	// community result uso isrelatedto
+
+	public static final String RESULT_ENTITY = "result";
+	public static final String DATASOURCE_ENTITY = "datasource";
+	public static final String CONTEXT_ENTITY = "context";
+
+	public static final String CONTEXT_ID = "60";
+	public static final String CONTEXT_NS_PREFIX = "context____";
+
+}

dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/dump/oaf/graph/Datasource.java

@@ -0,0 +1,316 @@
+
+package eu.dnetlib.dhp.schema.dump.oaf.graph;
+
+import java.io.Serializable;
+import java.util.List;
+
+import eu.dnetlib.dhp.schema.dump.oaf.Container;
+import eu.dnetlib.dhp.schema.dump.oaf.ControlledField;
+import eu.dnetlib.dhp.schema.dump.oaf.KeyValue;
+
+/**
+ * To store information about the datasource OpenAIRE collects information from. It contains the following parameters: -
+ * id of type String to store the OpenAIRE id for the datasource. It corresponds to the parameter id of the datasource
+ * represented in the internal model - originalId of type List<String> to store the list of original ids associated to
+ * the datasource. It corresponds to the parameter originalId of the datasource represented in the internal model. The
+ * null values are filtered out - pid of type List<eu.dnetlib.shp.schema.dump.oaf.ControlledField> to store the
+ * persistent identifiers for the datasource. For each pid in the datasource represented in the internal model one pid
+ * in the external model is produced as : - schema corresponds to pid.qualifier.classid of the datasource represented in
+ * the internal model - value corresponds to pid.value of the datasource represented in the internal model -
+ * datasourceType of type eu.dnetlib.dhp.schema.dump.oaf.ControlledField to store the datasource type (e.g.
+ * pubsrepository::institutional, Institutional Repository) as in the dnet vocabulary dnet:datasource_typologies. It
+ * corresponds to datasourcetype of the datasource represented in the internal model and : - code corresponds to
+ * datasourcetype.classid - value corresponds to datasourcetype.classname - openairecompatibility of type String to
+ * store information about the OpenAIRE compatibility of the ingested results (which guidelines they are compliant to).
+ * It corresponds to openairecompatibility.classname of the datasource represented in the internal model - officialname
+ * of type Sgtring to store the official name of the datasource. It correspond to officialname.value of the datasource
+ * represented in the internal model - englishname of type String to store the English name of the datasource. It
+ * corresponds to englishname.value of the datasource represented in the internal model - websiteurl of type String to
+ * store the URL of the website of the datasource. It corresponds to websiteurl.value of the datasource represented in
+ * the internal model - logourl of type String to store the URL of the logo for the datasource. It corresponds to
+ * logourl.value of the datasource represented in the internal model - dateofvalidation of type String to store the data
+ * of validation against the guidelines for the datasource records. It corresponds to dateofvalidation.value of the
+ * datasource represented in the internal model - description of type String to store the description for the
+ * datasource. It corresponds to description.value of the datasource represented in the internal model
+ */
+public class Datasource implements Serializable {
+
+	private String id; // string
+
+	private List<String> originalId; // list string
+
+	private List<ControlledField> pid; // list<String>
+
+	private ControlledField datasourcetype; // value
+
+	private String openairecompatibility; // value
+
+	private String officialname; // string
+
+	private String englishname; // string
+
+	private String websiteurl; // string
+
+	private String logourl; // string
+
+	private String dateofvalidation; // string
+
+	private String description; // description
+
+	private List<String> subjects; // List<String>
+
+	// opendoar specific fields (od*)
+
+	private List<String> languages; // odlanguages List<String>
+
+	private List<String> contenttypes; // odcontent types List<String>
+
+	// re3data fields
+	private String releasestartdate; // string
+
+	private String releaseenddate; // string
+
+	private String missionstatementurl; // string
+
+	// {open, restricted or closed}
+	private String accessrights; // databaseaccesstype string
+
+	// {open, restricted or closed}
+	private String uploadrights; // datauploadtype string
+
+	// {feeRequired, registration, other}
+	private String databaseaccessrestriction; // string
+
+	// {feeRequired, registration, other}
+	private String datauploadrestriction; // string
+
+	private Boolean versioning; // boolean
+
+	private String citationguidelineurl; // string
+
+	// {yes, no, uknown}
+
+	private String pidsystems; // string
+
+	private String certificates; // string
+
+	private List<Object> policies; //
+
+	private Container journal; // issn etc del Journal
+
+	public String getId() {
+		return id;
+	}
+
+	public void setId(String id) {
+		this.id = id;
+	}
+
+	public List<String> getOriginalId() {
+		return originalId;
+	}
+
+	public void setOriginalId(List<String> originalId) {
+		this.originalId = originalId;
+	}
+
+	public List<ControlledField> getPid() {
+		return pid;
+	}
+
+	public void setPid(List<ControlledField> pid) {
+		this.pid = pid;
+	}
+
+	public ControlledField getDatasourcetype() {
+		return datasourcetype;
+	}
+
+	public void setDatasourcetype(ControlledField datasourcetype) {
+		this.datasourcetype = datasourcetype;
+	}
+
+	public String getOpenairecompatibility() {
+		return openairecompatibility;
+	}
+
+	public void setOpenairecompatibility(String openairecompatibility) {
+		this.openairecompatibility = openairecompatibility;
+	}
+
+	public String getOfficialname() {
+		return officialname;
+	}
+
+	public void setOfficialname(String officialname) {
+		this.officialname = officialname;
+	}
+
+	public String getEnglishname() {
+		return englishname;
+	}
+
+	public void setEnglishname(String englishname) {
+		this.englishname = englishname;
+	}
+
+	public String getWebsiteurl() {
+		return websiteurl;
+	}
+
+	public void setWebsiteurl(String websiteurl) {
+		this.websiteurl = websiteurl;
+	}
+
+	public String getLogourl() {
+		return logourl;
+	}
+
+	public void setLogourl(String logourl) {
+		this.logourl = logourl;
+	}
+
+	public String getDateofvalidation() {
+		return dateofvalidation;
+	}
+
+	public void setDateofvalidation(String dateofvalidation) {
+		this.dateofvalidation = dateofvalidation;
+	}
+
+	public String getDescription() {
+		return description;
+	}
+
+	public void setDescription(String description) {
+		this.description = description;
+	}
+
+	public List<String> getSubjects() {
+		return subjects;
+	}
+
+	public void setSubjects(List<String> subjects) {
+		this.subjects = subjects;
+	}
+
+	public List<String> getLanguages() {
+		return languages;
+	}
+
+	public void setLanguages(List<String> languages) {
+		this.languages = languages;
+	}
+
+	public List<String> getContenttypes() {
+		return contenttypes;
+	}
+
+	public void setContenttypes(List<String> contenttypes) {
+		this.contenttypes = contenttypes;
+	}
+
+	public String getReleasestartdate() {
+		return releasestartdate;
+	}
+
+	public void setReleasestartdate(String releasestartdate) {
+		this.releasestartdate = releasestartdate;
+	}
+
+	public String getReleaseenddate() {
+		return releaseenddate;
+	}
+
+	public void setReleaseenddate(String releaseenddate) {
+		this.releaseenddate = releaseenddate;
+	}
+
+	public String getMissionstatementurl() {
+		return missionstatementurl;
+	}
+
+	public void setMissionstatementurl(String missionstatementurl) {
+		this.missionstatementurl = missionstatementurl;
+	}
+
+	public String getAccessrights() {
+		return accessrights;
+	}
+
+	public void setAccessrights(String accessrights) {
+		this.accessrights = accessrights;
+	}
+
+	public String getUploadrights() {
+		return uploadrights;
+	}
+
+	public void setUploadrights(String uploadrights) {
+		this.uploadrights = uploadrights;
+	}
+
+	public String getDatabaseaccessrestriction() {
+		return databaseaccessrestriction;
+	}
+
+	public void setDatabaseaccessrestriction(String databaseaccessrestriction) {
+		this.databaseaccessrestriction = databaseaccessrestriction;
+	}
+
+	public String getDatauploadrestriction() {
+		return datauploadrestriction;
+	}
+
+	public void setDatauploadrestriction(String datauploadrestriction) {
+		this.datauploadrestriction = datauploadrestriction;
+	}
+
+	public Boolean getVersioning() {
+		return versioning;
+	}
+
+	public void setVersioning(Boolean versioning) {
+		this.versioning = versioning;
+	}
+
+	public String getCitationguidelineurl() {
+		return citationguidelineurl;
+	}
+
+	public void setCitationguidelineurl(String citationguidelineurl) {
+		this.citationguidelineurl = citationguidelineurl;
+	}
+
+	public String getPidsystems() {
+		return pidsystems;
+	}
+
+	public void setPidsystems(String pidsystems) {
+		this.pidsystems = pidsystems;
+	}
+
+	public String getCertificates() {
+		return certificates;
+	}
+
+	public void setCertificates(String certificates) {
+		this.certificates = certificates;
+	}
+
+	public List<Object> getPolicies() {
+		return policies;
+	}
+
+	public void setPolicies(List<Object> policiesr3) {
+		this.policies = policiesr3;
+	}
+
+	public Container getJournal() {
+		return journal;
+	}
+
+	public void setJournal(Container journal) {
+		this.journal = journal;
+	}
+}

dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/dump/oaf/graph/Funder.java

@@ -0,0 +1,54 @@
+
+package eu.dnetlib.dhp.schema.dump.oaf.graph;
+
+import java.io.Serializable;
+
+/**
+ * To store information about the funder funding the project related to the result. It has the following parameters:
+ * - private String shortName to store the short name of the funder (e.g. AKA)
+ * - private String name to store information about the name of the funder (e.g. Akademy of Finland)
+ * - private Fundings funding_stream to store the fundingstream
+ * - private String jurisdiction to store information about the jurisdiction of the funder
+ */
+public class Funder implements Serializable {
+
+	private String shortName;
+
+	private String name;
+
+	private Fundings funding_stream;
+
+	private String jurisdiction;
+
+	public String getShortName() {
+		return shortName;
+	}
+
+	public void setShortName(String shortName) {
+		this.shortName = shortName;
+	}
+
+	public String getName() {
+		return name;
+	}
+
+	public void setName(String name) {
+		this.name = name;
+	}
+
+	public String getJurisdiction() {
+		return jurisdiction;
+	}
+
+	public void setJurisdiction(String jurisdiction) {
+		this.jurisdiction = jurisdiction;
+	}
+
+	public Fundings getFunding_stream() {
+		return funding_stream;
+	}
+
+	public void setFunding_stream(Fundings funding_stream) {
+		this.funding_stream = funding_stream;
+	}
+}

dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/dump/oaf/graph/Fundings.java

@@ -0,0 +1,35 @@
+
+package eu.dnetlib.dhp.schema.dump.oaf.graph;
+
+import java.io.Serializable;
+
+/**
+ * To store inforamtion about the funding stream. It has two parameters:
+ * - private String id to store the id of the fundings stream. The id is created by appending the shortname of the
+ *   funder to the name of each level in the xml representing the fundng stream. For example: if the funder is the
+ *   European Commission, the funding level 0 name is FP7, the funding level 1 name is SP3 and the funding level 2 name is
+ *   PEOPLE then the id will be: EC::FP7::SP3::PEOPLE
+ * - private String description to describe the funding stream. It is created by concatenating the description of each funding
+ * 	 level so for the example above the description would be: SEVENTH FRAMEWORK PROGRAMME - SP3-People - Marie-Curie Actions
+ */
+public class Fundings implements Serializable {
+
+	private String id;
+	private String description;
+
+	public String getId() {
+		return id;
+	}
+
+	public void setId(String id) {
+		this.id = id;
+	}
+
+	public String getDescription() {
+		return description;
+	}
+
+	public void setDescription(String description) {
+		this.description = description;
+	}
+}

dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/dump/oaf/graph/Granted.java

@@ -0,0 +1,56 @@
+
+package eu.dnetlib.dhp.schema.dump.oaf.graph;
+
+import java.io.Serializable;
+import java.util.Optional;
+
+/**
+ * To describe the funded amount. It has the following parameters:
+ * - private String currency to store the currency of the fund
+ * - private float totalcost to store the total cost of the project
+ * - private float fundedamount to store the funded amount by the funder
+ */
+public class Granted implements Serializable {
+	private String currency;
+	private float totalcost;
+	private float fundedamount;
+
+	public String getCurrency() {
+		return currency;
+	}
+
+	public void setCurrency(String currency) {
+		this.currency = currency;
+	}
+
+	public float getTotalcost() {
+		return totalcost;
+	}
+
+	public void setTotalcost(float totalcost) {
+		this.totalcost = totalcost;
+	}
+
+	public float getFundedamount() {
+		return fundedamount;
+	}
+
+	public void setFundedamount(float fundedamount) {
+		this.fundedamount = fundedamount;
+	}
+
+	public static Granted newInstance(String currency, float totalcost, float fundedamount) {
+		Granted granted = new Granted();
+		granted.currency = currency;
+		granted.totalcost = totalcost;
+		granted.fundedamount = fundedamount;
+		return granted;
+	}
+
+	public static Granted newInstance(String currency, float fundedamount) {
+		Granted granted = new Granted();
+		granted.currency = currency;
+		granted.fundedamount = fundedamount;
+		return granted;
+	}
+}

dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/dump/oaf/graph/Node.java

@@ -0,0 +1,41 @@
+
+package eu.dnetlib.dhp.schema.dump.oaf.graph;
+
+import java.io.Serializable;
+
+/**
+ * To represent the generic node in a relation. It has the following parameters:
+ * - private String id the openaire id of the entity in the relation
+ * - private String type the type of the entity in the relation.
+ *
+ * Consider the generic relation between a Result R and a Project P, the node representing R will have
+ * as id the id of R and as type result, while the node representing the project will have as id the id of the project
+ * and as type project
+ */
+public class Node implements Serializable {
+	private String id;
+	private String type;
+
+	public String getId() {
+		return id;
+	}
+
+	public void setId(String id) {
+		this.id = id;
+	}
+
+	public String getType() {
+		return type;
+	}
+
+	public void setType(String type) {
+		this.type = type;
+	}
+
+	public static Node newInstance(String id, String type) {
+		Node node = new Node();
+		node.id = id;
+		node.type = type;
+		return node;
+	}
+}

dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/dump/oaf/graph/Organization.java

@@ -0,0 +1,89 @@
+
+package eu.dnetlib.dhp.schema.dump.oaf.graph;
+
+import java.io.Serializable;
+import java.util.List;
+
+import eu.dnetlib.dhp.schema.dump.oaf.ControlledField;
+import eu.dnetlib.dhp.schema.dump.oaf.Country;
+import eu.dnetlib.dhp.schema.dump.oaf.KeyValue;
+import eu.dnetlib.dhp.schema.dump.oaf.Qualifier;
+import eu.dnetlib.dhp.schema.dump.oaf.community.Project;
+
+
+/**
+ * To represent the generic organizaiton. It has the following parameters:
+ * - private String legalshortname to store the legalshortname of the organizaiton
+ * - private String legalname to store the legal name of the organization
+ * - private String websiteurl to store the websiteurl of the organization
+ * - private List<String> alternativenames to store the alternative names of the organization
+ * - private Qualifier country to store the country of the organization
+ * - private String id to store the id of the organization
+ * - private List<ControlledField> pid to store the list of pids for the organization
+ */
+public class Organization implements Serializable {
+	private String legalshortname;
+	private String legalname;
+	private String websiteurl;
+	private List<String> alternativenames;
+	private Qualifier country;
+	private String id;
+	private List<ControlledField> pid;
+
+	public String getLegalshortname() {
+		return legalshortname;
+	}
+
+	public void setLegalshortname(String legalshortname) {
+		this.legalshortname = legalshortname;
+	}
+
+	public String getLegalname() {
+		return legalname;
+	}
+
+	public void setLegalname(String legalname) {
+		this.legalname = legalname;
+	}
+
+	public String getWebsiteurl() {
+		return websiteurl;
+	}
+
+	public void setWebsiteurl(String websiteurl) {
+		this.websiteurl = websiteurl;
+	}
+
+	public List<String> getAlternativenames() {
+		return alternativenames;
+	}
+
+	public void setAlternativenames(List<String> alternativenames) {
+		this.alternativenames = alternativenames;
+	}
+
+	public Qualifier getCountry() {
+		return country;
+	}
+
+	public void setCountry(Qualifier country) {
+		this.country = country;
+	}
+
+	public String getId() {
+		return id;
+	}
+
+	public void setId(String id) {
+		this.id = id;
+	}
+
+	public List<ControlledField> getPid() {
+		return pid;
+	}
+
+	public void setPid(List<ControlledField> pid) {
+		this.pid = pid;
+	}
+
+}

dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/dump/oaf/graph/Programme.java

@@ -0,0 +1,37 @@
+
+package eu.dnetlib.dhp.schema.dump.oaf.graph;
+
+import java.io.Serializable;
+
+/**
+ * To store information about the ec programme for the project. It has the following parameters:
+ * - private String code to store the code of the programme
+ * - private String description to store the description of the programme
+ */
+public class Programme implements Serializable {
+	private String code;
+	private String description;
+
+	public String getCode() {
+		return code;
+	}
+
+	public void setCode(String code) {
+		this.code = code;
+	}
+
+	public String getDescription() {
+		return description;
+	}
+
+	public void setDescription(String description) {
+		this.description = description;
+	}
+
+	public static Programme newInstance(String code, String description) {
+		Programme p = new Programme();
+		p.code = code;
+		p.description = description;
+		return p;
+	}
+}

dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/dump/oaf/graph/Project.java

@@ -0,0 +1,195 @@
+
+package eu.dnetlib.dhp.schema.dump.oaf.graph;
+
+import java.io.Serializable;
+import java.util.List;
+
+import eu.dnetlib.dhp.schema.dump.oaf.KeyValue;
+
+/**
+ * This is the class representing the Project in the model used for the dumps of the whole graph. At the moment the dump
+ * of the Projects differs from the other dumps because we do not create relations between Funders (Organization) and
+ * Projects but we put the information about the Funder within the Project representation. We also removed the
+ * collected from element from the Project. No relation between the Project and the Datasource entity from which it is
+ * collected will be created. We will never create relations between Project and Datasource. In case some relation will
+ * be extracted from the Project they will refer the Funder and will be of type ( organization -> funds -> project,
+ * project -> isFundedBy -> organization) We also removed the duration parameter because the most of times it is set to
+ * 0. It has the following parameters:
+ * - private String id to store the id of the project (OpenAIRE id)
+ * - private String websiteurl to store the websiteurl of the project
+ * - private String code to store the grant agreement of the project
+ * - private String acronym to store the acronym of the project
+ * - private String title to store the tile of the project
+ * - private String startdate to store the start date
+ * - private String enddate to store the end date
+ * - private String callidentifier to store the call indentifier
+ * - private String keywords to store the keywords
+ * - private boolean openaccessmandateforpublications to store if the project must accomplish to the open access mandate
+ *   for publications. This value will be set to true if one of the field in the project represented in the internal model
+ *   is set to true
+ * - private boolean openaccessmandatefordataset to store if the project must accomplish to the open access mandate for
+ * 	 dataset. It is set to the value in the corresponding filed of the project represented in the internal model
+ * - private List<String> subject to store the list of subjects of the project
+ * - private List<Funder> funding to store the list of funder of the project
+ * - private String summary to store the summary of the project
+ * - private Granted granted to store the granted amount
+ * - private List<Programme> programme to store the list of programmes the project is related to
+ */
+
+public class Project implements Serializable {
+	private String id;
+
+	private String websiteurl;
+	private String code;
+	private String acronym;
+	private String title;
+	private String startdate;
+
+	private String enddate;
+
+	private String callidentifier;
+
+	private String keywords;
+
+	private boolean openaccessmandateforpublications;
+
+	private boolean openaccessmandatefordataset;
+	private List<String> subject;
+
+	private List<Funder> funding;
+
+	private String summary;
+
+	private Granted granted;
+
+	private List<Programme> programme;
+
+	public String getId() {
+		return id;
+	}
+
+	public void setId(String id) {
+		this.id = id;
+	}
+
+	public String getWebsiteurl() {
+		return websiteurl;
+	}
+
+	public void setWebsiteurl(String websiteurl) {
+		this.websiteurl = websiteurl;
+	}
+
+	public String getCode() {
+		return code;
+	}
+
+	public void setCode(String code) {
+		this.code = code;
+	}
+
+	public String getAcronym() {
+		return acronym;
+	}
+
+	public void setAcronym(String acronym) {
+		this.acronym = acronym;
+	}
+
+	public String getTitle() {
+		return title;
+	}
+
+	public void setTitle(String title) {
+		this.title = title;
+	}
+
+	public String getStartdate() {
+		return startdate;
+	}
+
+	public void setStartdate(String startdate) {
+		this.startdate = startdate;
+	}
+
+	public String getEnddate() {
+		return enddate;
+	}
+
+	public void setEnddate(String enddate) {
+		this.enddate = enddate;
+	}
+
+	public String getCallidentifier() {
+		return callidentifier;
+	}
+
+	public void setCallidentifier(String callidentifier) {
+		this.callidentifier = callidentifier;
+	}
+
+	public String getKeywords() {
+		return keywords;
+	}
+
+	public void setKeywords(String keywords) {
+		this.keywords = keywords;
+	}
+
+	public boolean isOpenaccessmandateforpublications() {
+		return openaccessmandateforpublications;
+	}
+
+	public void setOpenaccessmandateforpublications(boolean openaccessmandateforpublications) {
+		this.openaccessmandateforpublications = openaccessmandateforpublications;
+	}
+
+	public boolean isOpenaccessmandatefordataset() {
+		return openaccessmandatefordataset;
+	}
+
+	public void setOpenaccessmandatefordataset(boolean openaccessmandatefordataset) {
+		this.openaccessmandatefordataset = openaccessmandatefordataset;
+	}
+
+	public List<String> getSubject() {
+		return subject;
+	}
+
+	public void setSubject(List<String> subject) {
+		this.subject = subject;
+	}
+
+	public List<Funder> getFunding() {
+		return funding;
+	}
+
+	public void setFunding(List<Funder> funding) {
+		this.funding = funding;
+	}
+
+	public String getSummary() {
+		return summary;
+	}
+
+	public void setSummary(String summary) {
+		this.summary = summary;
+	}
+
+	public Granted getGranted() {
+		return granted;
+	}
+
+	public void setGranted(Granted granted) {
+		this.granted = granted;
+	}
+
+	public List<Programme> getProgramme() {
+		return programme;
+	}
+
+	public void setProgramme(List<Programme> programme) {
+		this.programme = programme;
+	}
+
+}

dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/dump/oaf/graph/RelType.java

@@ -0,0 +1,40 @@
+
+package eu.dnetlib.dhp.schema.dump.oaf.graph;
+
+import java.io.Serializable;
+
+/**
+ * To represent the semantics of the generic relation between two entities. It has the following parameters:
+ * - private String name to store the semantics of the relation (i.e. isAuthorInstitutionOf). It corresponds to the
+ *   relclass parameter in the relation represented in the internal model
+ *   represented in the internal model
+ * - private String type to store the type of the relation (i.e. affiliation). It corresponds to the subreltype parameter
+ *   of the relation represented in theinternal model
+ */
+public class RelType implements Serializable {
+	private String name; // relclass
+	private String type; // subreltype
+
+	public String getName() {
+		return name;
+	}
+
+	public void setName(String name) {
+		this.name = name;
+	}
+
+	public String getType() {
+		return type;
+	}
+
+	public void setType(String type) {
+		this.type = type;
+	}
+
+	public static RelType newInstance(String name, String type) {
+		RelType rel = new RelType();
+		rel.name = name;
+		rel.type = type;
+		return rel;
+	}
+}

dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/dump/oaf/graph/Relation.java

@@ -0,0 +1,68 @@
+
+package eu.dnetlib.dhp.schema.dump.oaf.graph;
+
+import java.io.Serializable;
+import java.util.Objects;
+
+import eu.dnetlib.dhp.schema.dump.oaf.Provenance;
+
+/**
+ * To represent the gereric relation between two entities. It has the following parameters:
+ * - private Node source to represent the entity source of the relation
+ * - private Node target to represent the entity target of the relation
+ * - private RelType reltype to represent the semantics of the relation
+ * - private Provenance provenance to represent the provenance of the relation
+ */
+public class Relation implements Serializable {
+	private Node source;
+	private Node target;
+	private RelType reltype;
+	private Provenance provenance;
+
+	public Node getSource() {
+		return source;
+	}
+
+	public void setSource(Node source) {
+		this.source = source;
+	}
+
+	public Node getTarget() {
+		return target;
+	}
+
+	public void setTarget(Node target) {
+		this.target = target;
+	}
+
+	public RelType getReltype() {
+		return reltype;
+	}
+
+	public void setReltype(RelType reltype) {
+		this.reltype = reltype;
+	}
+
+	public Provenance getProvenance() {
+		return provenance;
+	}
+
+	public void setProvenance(Provenance provenance) {
+		this.provenance = provenance;
+	}
+
+	@Override
+	public int hashCode() {
+
+		return Objects.hash(source.getId(), target.getId(), reltype.getType() + ":" + reltype.getName());
+	}
+
+	public static Relation newInstance(Node source, Node target, RelType reltype, Provenance provenance) {
+		Relation relation = new Relation();
+		relation.source = source;
+		relation.target = target;
+		relation.reltype = reltype;
+		relation.provenance = provenance;
+		return relation;
+	}
+}

dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/dump/oaf/graph/ResearchCommunity.java

@@ -0,0 +1,20 @@
+
+package eu.dnetlib.dhp.schema.dump.oaf.graph;
+
+import java.util.List;
+
+/**
+ * To represent RC entities. It extends eu.dnetlib.dhp.dump.oaf.grap.ResearchInitiative by adding the parameter subject
+ * to store the list of subjects related to the community
+ */
+public class ResearchCommunity extends ResearchInitiative {
+	private List<String> subject;
+
+	public List<String> getSubject() {
+		return subject;
+	}
+
+	public void setSubject(List<String> subject) {
+		this.subject = subject;
+	}
+}

dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/dump/oaf/graph/ResearchInitiative.java

@@ -0,0 +1,71 @@
+
+package eu.dnetlib.dhp.schema.dump.oaf.graph;
+
+import java.io.Serializable;
+
+/**
+ * To represent entity of type RC/RI. It has the following parameters, which are mostly derived by the profile
+ * - private String id to store the openaire id for the entity. Is has as code 00 and will be created as
+ *   00|context_____::md5(originalId)
+ * 	private String originalId to store the id of the context as provided in the profile (i.e. mes)
+ * 	private String name to store the name of the context (got from the label attribute in the context definition)
+ * 	private String type to store the type of the context (i.e.: research initiative or research community)
+ * 	private String description to store the description of the context as given in the profile
+ * 	private String zenodo_community to store the zenodo community associated to the context (main zenodo community)
+ */
+public class ResearchInitiative implements Serializable {
+	private String id; // openaireId
+	private String originalId; // context id
+	private String name; // context name
+	private String type; // context type: research initiative or research community
+	private String description;
+	private String zenodo_community;
+
+	public String getZenodo_community() {
+		return zenodo_community;
+	}
+
+	public void setZenodo_community(String zenodo_community) {
+		this.zenodo_community = zenodo_community;
+	}
+
+	public String getType() {
+		return type;
+	}
+
+	public void setType(String type) {
+		this.type = type;
+	}
+
+	public String getId() {
+		return id;
+	}
+
+	public void setId(String id) {
+		this.id = id;
+	}
+
+	public String getName() {
+		return name;
+	}
+
+	public void setName(String label) {
+		this.name = label;
+	}
+
+	public String getOriginalId() {
+		return originalId;
+	}
+
+	public void setOriginalId(String originalId) {
+		this.originalId = originalId;
+	}
+
+	public String getDescription() {
+		return description;
+	}
+
+	public void setDescription(String description) {
+		this.description = description;
+	}
+}

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

@@ -110,13 +110,6 @@ public class CommunityConfigurationFactory {
 	}
 
 	private static List<ZenodoCommunity> parseZenodoCommunities(final Node node) {
-//		final Node oacommunitynode = node.selectSingleNode("./oacommunity");
-//		String oacommunity = null;
-//		if (oacommunitynode != null) {
-//			String tmp = oacommunitynode.getText();
-//			if (StringUtils.isNotBlank(tmp))
-//				oacommunity = tmp;
-//		}
 
 		final List<Node> list = node.selectNodes("./zenodocommunities/zenodocommunity");
 		final List<ZenodoCommunity> zenodoCommunityList = new ArrayList<>();
@@ -127,11 +120,7 @@ public class CommunityConfigurationFactory {
 
 			zenodoCommunityList.add(zc);
 		}
-//		if (oacommunity != null) {
-//			ZenodoCommunity zc = new ZenodoCommunity();
-//			zc.setZenodoCommunityId(oacommunity);
-//			zenodoCommunityList.add(zc);
-//		}
+
 		log.info("size of the zenodo community list " + zenodoCommunityList.size());
 		return zenodoCommunityList;
 	}

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

@@ -20,8 +20,6 @@ import eu.dnetlib.dhp.schema.oaf.*;
 /** Created by miriam on 02/08/2018. */
 public class ResultTagger implements Serializable {
 
-	private String trust = "0.8";
-
 	private boolean clearContext(Result result) {
 		int tmp = result.getContext().size();
 		List<Context> clist = result
@@ -73,7 +71,8 @@ public class ResultTagger implements Serializable {
 		final Set<String> subjects = new HashSet<>();
 
 		if (Objects.nonNull(result.getSubject())) {
-			result.getSubject()
+			result
+				.getSubject()
 				.stream()
 				.map(subject -> subject.getValue())
 				.filter(StringUtils::isNotBlank)
@@ -170,21 +169,24 @@ public class ResultTagger implements Serializable {
 									getDataInfo(
 										BULKTAG_DATA_INFO_TYPE,
 										CLASS_ID_SUBJECT,
-										CLASS_NAME_BULKTAG_SUBJECT));
+										CLASS_NAME_BULKTAG_SUBJECT,
+										TAGGING_TRUST));
 						if (datasources.contains(c.getId()))
 							dataInfoList
 								.add(
 									getDataInfo(
 										BULKTAG_DATA_INFO_TYPE,
 										CLASS_ID_DATASOURCE,
-										CLASS_NAME_BULKTAG_DATASOURCE));
+										CLASS_NAME_BULKTAG_DATASOURCE,
+										TAGGING_TRUST));
 						if (czenodo.contains(c.getId()))
 							dataInfoList
 								.add(
 									getDataInfo(
 										BULKTAG_DATA_INFO_TYPE,
 										CLASS_ID_CZENODO,
-										CLASS_NAME_BULKTAG_ZENODO));
+										CLASS_NAME_BULKTAG_ZENODO,
+										TAGGING_TRUST));
 					}
 					return c;
 				})
@@ -210,21 +212,24 @@ public class ResultTagger implements Serializable {
 								getDataInfo(
 									BULKTAG_DATA_INFO_TYPE,
 									CLASS_ID_SUBJECT,
-									CLASS_NAME_BULKTAG_SUBJECT));
+									CLASS_NAME_BULKTAG_SUBJECT,
+									TAGGING_TRUST));
 					if (datasources.contains(c))
 						dataInfoList
 							.add(
 								getDataInfo(
 									BULKTAG_DATA_INFO_TYPE,
 									CLASS_ID_DATASOURCE,
-									CLASS_NAME_BULKTAG_DATASOURCE));
+									CLASS_NAME_BULKTAG_DATASOURCE,
+									TAGGING_TRUST));
 					if (czenodo.contains(c))
 						dataInfoList
 							.add(
 								getDataInfo(
 									BULKTAG_DATA_INFO_TYPE,
 									CLASS_ID_CZENODO,
-									CLASS_NAME_BULKTAG_ZENODO));
+									CLASS_NAME_BULKTAG_ZENODO,
+									TAGGING_TRUST));
 					context.setDataInfo(dataInfoList);
 					return context;
 				})
@@ -235,11 +240,12 @@ public class ResultTagger implements Serializable {
 	}
 
 	public static DataInfo getDataInfo(
-		String inference_provenance, String inference_class_id, String inference_class_name) {
+		String inference_provenance, String inference_class_id, String inference_class_name, String trust) {
 		DataInfo di = new DataInfo();
 		di.setInferred(true);
 		di.setInferenceprovenance(inference_provenance);
 		di.setProvenanceaction(getQualifier(inference_class_id, inference_class_name));
+		di.setTrust(trust);
 		return di;
 	}
 

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

@@ -14,4 +14,6 @@ public class TaggingConstants {
 	public static final String CLASS_NAME_BULKTAG_SUBJECT = "Bulktagging for Community - Subject";
 	public static final String CLASS_NAME_BULKTAG_DATASOURCE = "Bulktagging for Community - Datasource";
 	public static final String CLASS_NAME_BULKTAG_ZENODO = "Bulktagging for Community - Zenodo";
+
+	public static final String TAGGING_TRUST = "0.8";
 }

dhp-workflows/dhp-enrichment/src/test/resources/eu/dnetlib/dhp/bulktag/communityconfiguration/community_configuration.xml

@@ -106,12 +106,6 @@
             <subject>aqua</subject>
             <subject>sea</subject>
         </subjects>
-        <providers>
-            <datasource>
-                <openaireId>re3data_____::9633d1e8c4309c833c2c442abeb0cfeb</openaireId>
-                <selcriteria/>
-            </datasource>
-        </providers>
         <zenodocommunities/>
     </community>
     <community id="aginfra">

dhp-workflows/dhp-graph-mapper/pom.xml

@@ -42,6 +42,12 @@
 
     <dependencies>
 
+        <!-- https://mvnrepository.com/artifact/org.apache.commons/commons-compress -->
+        <dependency>
+            <groupId>org.apache.commons</groupId>
+            <artifactId>commons-compress</artifactId>
+        </dependency>
+
         <dependency>
             <groupId>commons-io</groupId>
             <artifactId>commons-io</artifactId>
@@ -59,6 +65,12 @@
             <groupId>org.apache.spark</groupId>
             <artifactId>spark-hive_2.11</artifactId>
             <scope>test</scope>
+            <exclusions>
+                <exclusion>
+                <groupId>org.apache.httpcomponents</groupId>
+                    <artifactId>httpclient</artifactId>
+                </exclusion>
+            </exclusions>
         </dependency>
 
         <dependency>
@@ -92,14 +104,21 @@
             <groupId>org.postgresql</groupId>
             <artifactId>postgresql</artifactId>
         </dependency>
+        <dependency>
+
+            <groupId>org.apache.httpcomponents</groupId>
+            <artifactId>httpmime</artifactId>
+        </dependency>
+        <dependency>
+            <groupId>com.github.victools</groupId>
+            <artifactId>jsonschema-generator</artifactId>
+            <scope>test</scope>
+        </dependency>
         <dependency>
             <groupId>org.json4s</groupId>
             <artifactId>json4s-jackson_2.11</artifactId>
-            <version>3.5.3</version>
         </dependency>
 
-
-
     </dependencies>
 
 

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

@@ -0,0 +1,43 @@
+
+package eu.dnetlib.dhp.oa.graph.dump;
+
+import java.util.Map;
+
+import com.google.common.collect.Maps;
+
+public class Constants {
+
+	public static final Map<String, String> accessRightsCoarMap = Maps.newHashMap();
+	public static final Map<String, String> coarCodeLabelMap = Maps.newHashMap();
+
+	public static final String INFERRED = "Inferred by OpenAIRE";
+
+	public static final String HARVESTED = "Harvested";
+	public static final String DEFAULT_TRUST = "0.9";
+	public static final String USER_CLAIM = "Linked by user";;
+
+	public static String COAR_ACCESS_RIGHT_SCHEMA = "http://vocabularies.coar-repositories.org/documentation/access_rights/";
+
+	public static String ZENODO_COMMUNITY_PREFIX = "https://zenodo.org/communities/";
+
+	public static String RESEARCH_COMMUNITY = "Research Community";
+
+	public static String RESEARCH_INFRASTRUCTURE = "Research Infrastructure/Initiative";
+
+	public static String ORCID = "orcid";
+
+	static {
+		accessRightsCoarMap.put("OPEN", "c_abf2");
+		accessRightsCoarMap.put("RESTRICTED", "c_16ec");
+		accessRightsCoarMap.put("OPEN SOURCE", "c_abf2");
+		accessRightsCoarMap.put("CLOSED", "c_14cb");
+		accessRightsCoarMap.put("EMBARGO", "c_f1cf");
+	}
+
+	static {
+		coarCodeLabelMap.put("c_abf2", "OPEN");
+		coarCodeLabelMap.put("c_16ec", "RESTRICTED");
+		coarCodeLabelMap.put("c_14cb", "CLOSED");
+		coarCodeLabelMap.put("c_f1cf", "EMBARGO");
+	}
+}

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

@@ -0,0 +1,106 @@
+
+package eu.dnetlib.dhp.oa.graph.dump;
+
+import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
+
+import java.io.Serializable;
+import java.util.List;
+import java.util.Objects;
+import java.util.Optional;
+import java.util.Set;
+import java.util.stream.Collectors;
+
+import org.apache.spark.SparkConf;
+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 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.schema.dump.oaf.graph.ResearchInitiative;
+import eu.dnetlib.dhp.schema.oaf.*;
+
+/**
+ * It fires the execution of the actual dump for result entities. If the dump is for RC/RI products its checks for each
+ * result its belongingess to at least one RC/RI before "asking" for its mapping.
+ */
+public class DumpProducts implements Serializable {
+
+	public void run(Boolean isSparkSessionManaged, String inputPath, String outputPath, String communityMapPath,
+		Class<? extends OafEntity> inputClazz,
+		Class<? extends eu.dnetlib.dhp.schema.dump.oaf.Result> outputClazz,
+		boolean graph) {
+
+		SparkConf conf = new SparkConf();
+
+		runWithSparkSession(
+			conf,
+			isSparkSessionManaged,
+			spark -> {
+				Utils.removeOutputDir(spark, outputPath);
+				execDump(spark, inputPath, outputPath, communityMapPath, inputClazz, outputClazz, graph);
+			});
+	}
+
+	public static <I extends OafEntity, O extends eu.dnetlib.dhp.schema.dump.oaf.Result> void execDump(
+		SparkSession spark,
+		String inputPath,
+		String outputPath,
+		String communityMapPath,
+		Class<I> inputClazz,
+		Class<O> outputClazz,
+		boolean graph) {
+
+		CommunityMap communityMap = Utils.getCommunityMap(spark, communityMapPath);
+
+		Utils
+			.readPath(spark, inputPath, inputClazz)
+			.map(value -> execMap(value, communityMap, graph), Encoders.bean(outputClazz))
+			.filter(Objects::nonNull)
+			.write()
+			.mode(SaveMode.Overwrite)
+			.option("compression", "gzip")
+			.json(outputPath);
+
+	}
+
+	private static <I extends OafEntity, O extends eu.dnetlib.dhp.schema.dump.oaf.Result> O execMap(I value,
+		CommunityMap communityMap,
+		boolean graph) {
+
+		Optional<DataInfo> odInfo = Optional.ofNullable(value.getDataInfo());
+		if (odInfo.isPresent()) {
+			if (odInfo.get().getDeletedbyinference()) {
+				return null;
+			}
+		} else {
+			return null;
+		}
+
+		if (!graph) {
+			Set<String> communities = communityMap.keySet();
+
+			Optional<List<Context>> inputContext = Optional
+				.ofNullable(((eu.dnetlib.dhp.schema.oaf.Result) value).getContext());
+			if (!inputContext.isPresent()) {
+				return null;
+			}
+			List<String> toDumpFor = inputContext.get().stream().map(c -> {
+				if (communities.contains(c.getId())) {
+					return c.getId();
+				}
+				if (c.getId().contains("::") && communities.contains(c.getId().substring(0, c.getId().indexOf("::")))) {
+					return c.getId().substring(0, 3);
+				}
+				return null;
+			}).filter(Objects::nonNull).collect(Collectors.toList());
+			if (toDumpFor.size() == 0) {
+				return null;
+			}
+		}
+		return (O) ResultMapper.map(value, communityMap, graph);
+
+	}
+}

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

@@ -0,0 +1,114 @@
+
+package eu.dnetlib.dhp.oa.graph.dump;
+
+import java.io.*;
+
+import org.apache.commons.compress.archivers.ar.ArArchiveEntry;
+import org.apache.commons.compress.archivers.ar.ArArchiveOutputStream;
+import org.apache.commons.compress.archivers.tar.TarArchiveEntry;
+import org.apache.commons.compress.archivers.tar.TarArchiveOutputStream;
+import org.apache.commons.io.IOUtils;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.*;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import eu.dnetlib.dhp.application.ArgumentApplicationParser;
+import eu.dnetlib.dhp.oa.graph.dump.community.CommunityMap;
+
+public class MakeTar implements Serializable {
+
+	private static final Logger log = LoggerFactory.getLogger(MakeTar.class);
+
+	public static void main(String[] args) throws Exception {
+		String jsonConfiguration = IOUtils
+			.toString(
+				MakeTar.class
+					.getResourceAsStream(
+						"/eu/dnetlib/dhp/oa/graph/dump/input_maketar_parameters.json"));
+
+		final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
+		parser.parseArgument(args);
+
+		final String outputPath = parser.get("hdfsPath");
+		log.info("hdfsPath: {}", outputPath);
+
+		final String hdfsNameNode = parser.get("nameNode");
+		log.info("nameNode: {}", hdfsNameNode);
+
+		final String inputPath = parser.get("sourcePath");
+		log.info("input path : {}", inputPath);
+
+		Configuration conf = new Configuration();
+		conf.set("fs.defaultFS", hdfsNameNode);
+
+		FileSystem fileSystem = FileSystem.get(conf);
+
+		makeTArArchive(fileSystem, inputPath, outputPath);
+
+	}
+
+	public static void makeTArArchive(FileSystem fileSystem, String inputPath, String outputPath) throws IOException {
+
+		RemoteIterator<LocatedFileStatus> dir_iterator = fileSystem.listLocatedStatus(new Path(inputPath));
+
+		while (dir_iterator.hasNext()) {
+			LocatedFileStatus fileStatus = dir_iterator.next();
+
+			Path p = fileStatus.getPath();
+			String p_string = p.toString();
+			String entity = p_string.substring(p_string.lastIndexOf("/") + 1);
+
+			write(fileSystem, p_string, outputPath + "/" + entity + ".tar", entity);
+		}
+
+	}
+
+	private static void write(FileSystem fileSystem, String inputPath, String outputPath, String dir_name)
+		throws IOException {
+
+		Path hdfsWritePath = new Path(outputPath);
+		FSDataOutputStream fsDataOutputStream = null;
+		if (fileSystem.exists(hdfsWritePath)) {
+			fileSystem.delete(hdfsWritePath, true);
+
+		}
+		fsDataOutputStream = fileSystem.create(hdfsWritePath);
+
+		TarArchiveOutputStream ar = new TarArchiveOutputStream(fsDataOutputStream.getWrappedStream());
+
+		RemoteIterator<LocatedFileStatus> fileStatusListIterator = fileSystem
+			.listFiles(
+				new Path(inputPath), true);
+
+		while (fileStatusListIterator.hasNext()) {
+			LocatedFileStatus fileStatus = fileStatusListIterator.next();
+
+			Path p = fileStatus.getPath();
+			String p_string = p.toString();
+			if (!p_string.endsWith("_SUCCESS")) {
+				String name = p_string.substring(p_string.lastIndexOf("/") + 1);
+				TarArchiveEntry entry = new TarArchiveEntry(dir_name + "/" + name + ".json.gz");
+				entry.setSize(fileStatus.getLen());
+				ar.putArchiveEntry(entry);
+
+				InputStream is = fileSystem.open(fileStatus.getPath());
+
+				BufferedInputStream bis = new BufferedInputStream(is);
+
+				int count;
+				byte data[] = new byte[1024];
+				while ((count = bis.read(data, 0, data.length)) != -1) {
+					ar.write(data, 0, count);
+				}
+				bis.close();
+				ar.closeArchiveEntry();
+
+			}
+
+		}
+
+		ar.close();
+	}
+
+}

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

@@ -0,0 +1,58 @@
+
+package eu.dnetlib.dhp.oa.graph.dump;
+
+import java.io.StringReader;
+import java.util.List;
+
+import org.dom4j.Document;
+import org.dom4j.DocumentException;
+import org.dom4j.Element;
+import org.dom4j.io.SAXReader;
+
+import eu.dnetlib.dhp.oa.graph.dump.community.CommunityMap;
+import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpException;
+import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
+
+public class QueryInformationSystem {
+
+	private ISLookUpService isLookUp;
+
+	private static final String XQUERY = "for $x in collection('/db/DRIVER/ContextDSResources/ContextDSResourceType') "
+		+
+		"  where $x//CONFIGURATION/context[./@type='community' or ./@type='ri'] " +
+		" and ($x//context/param[./@name = 'status']/text() = 'manager'  or $x//context/param[./@name = 'status']/text() = 'all') "
+		+
+		"  return " +
+		"<community> " +
+		"{$x//CONFIGURATION/context/@id}" +
+		"{$x//CONFIGURATION/context/@label}" +
+		"</community>";
+
+	public CommunityMap getCommunityMap()
+		throws ISLookUpException, DocumentException {
+		return getMap(isLookUp.quickSearchProfile(XQUERY));
+
+	}
+
+	public ISLookUpService getIsLookUp() {
+		return isLookUp;
+	}
+
+	public void setIsLookUp(ISLookUpService isLookUpService) {
+		this.isLookUp = isLookUpService;
+	}
+
+	private CommunityMap getMap(List<String> communityMap) throws DocumentException {
+		final CommunityMap map = new CommunityMap();
+
+		for (String xml : communityMap) {
+			final Document doc;
+			doc = new SAXReader().read(new StringReader(xml));
+			Element root = doc.getRootElement();
+			map.put(root.attribute("id").getValue(), root.attribute("label").getValue());
+		}
+
+		return map;
+	}
+
+}

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

@@ -0,0 +1,523 @@
+
+package eu.dnetlib.dhp.oa.graph.dump;
+
+import java.io.Serializable;
+import java.util.*;
+import java.util.stream.Collectors;
+
+import org.apache.commons.lang3.StringUtils;
+
+import eu.dnetlib.dhp.schema.common.ModelConstants;
+import eu.dnetlib.dhp.schema.dump.oaf.*;
+import eu.dnetlib.dhp.schema.dump.oaf.community.CommunityResult;
+import eu.dnetlib.dhp.schema.dump.oaf.community.Context;
+import eu.dnetlib.dhp.schema.oaf.DataInfo;
+import eu.dnetlib.dhp.schema.oaf.Field;
+import eu.dnetlib.dhp.schema.oaf.Journal;
+import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
+
+public class ResultMapper implements Serializable {
+
+	public static <I extends eu.dnetlib.dhp.schema.oaf.OafEntity> Result map(
+		I in, Map<String, String> communityMap, boolean graph) {
+
+		Result out;
+		if (graph) {
+			out = new Result();
+		} else {
+			out = new CommunityResult();
+		}
+
+		eu.dnetlib.dhp.schema.oaf.Result input = (eu.dnetlib.dhp.schema.oaf.Result) in;
+		Optional<eu.dnetlib.dhp.schema.oaf.Qualifier> ort = Optional.ofNullable(input.getResulttype());
+		if (ort.isPresent()) {
+			switch (ort.get().getClassid()) {
+				case "publication":
+					Optional<Journal> journal = Optional
+						.ofNullable(((eu.dnetlib.dhp.schema.oaf.Publication) input).getJournal());
+					if (journal.isPresent()) {
+						Journal j = journal.get();
+						Container c = new Container();
+						c.setConferencedate(j.getConferencedate());
+						c.setConferenceplace(j.getConferenceplace());
+						c.setEdition(j.getEdition());
+						c.setEp(j.getEp());
+						c.setIss(j.getIss());
+						c.setIssnLinking(j.getIssnLinking());
+						c.setIssnOnline(j.getIssnOnline());
+						c.setIssnPrinted(j.getIssnPrinted());
+						c.setName(j.getName());
+						c.setSp(j.getSp());
+						c.setVol(j.getVol());
+						out.setContainer(c);
+						out.setType(ModelConstants.PUBLICATION_DEFAULT_RESULTTYPE.getClassname());
+					}
+					break;
+				case "dataset":
+					eu.dnetlib.dhp.schema.oaf.Dataset id = (eu.dnetlib.dhp.schema.oaf.Dataset) input;
+					Optional.ofNullable(id.getSize()).ifPresent(v -> out.setSize(v.getValue()));
+					Optional.ofNullable(id.getVersion()).ifPresent(v -> out.setVersion(v.getValue()));
+
+					out
+						.setGeolocation(
+							Optional
+								.ofNullable(id.getGeolocation())
+								.map(
+									igl -> igl
+										.stream()
+										.filter(Objects::nonNull)
+										.map(gli -> {
+											GeoLocation gl = new GeoLocation();
+											gl.setBox(gli.getBox());
+											gl.setPlace(gli.getPlace());
+											gl.setPoint(gli.getPoint());
+											return gl;
+										})
+										.collect(Collectors.toList()))
+								.orElse(null));
+
+					out.setType(ModelConstants.DATASET_DEFAULT_RESULTTYPE.getClassname());
+					break;
+				case "software":
+
+					eu.dnetlib.dhp.schema.oaf.Software is = (eu.dnetlib.dhp.schema.oaf.Software) input;
+					Optional
+						.ofNullable(is.getCodeRepositoryUrl())
+						.ifPresent(value -> out.setCodeRepositoryUrl(value.getValue()));
+					Optional
+						.ofNullable(is.getDocumentationUrl())
+						.ifPresent(
+							value -> out
+								.setDocumentationUrl(
+									value
+										.stream()
+										.map(v -> v.getValue())
+										.collect(Collectors.toList())));
+
+					Optional
+						.ofNullable(is.getProgrammingLanguage())
+						.ifPresent(value -> out.setProgrammingLanguage(value.getClassid()));
+
+					out.setType(ModelConstants.SOFTWARE_DEFAULT_RESULTTYPE.getClassname());
+					break;
+				case "other":
+
+					eu.dnetlib.dhp.schema.oaf.OtherResearchProduct ir = (eu.dnetlib.dhp.schema.oaf.OtherResearchProduct) input;
+					out
+						.setContactgroup(
+							Optional
+								.ofNullable(ir.getContactgroup())
+								.map(value -> value.stream().map(cg -> cg.getValue()).collect(Collectors.toList()))
+								.orElse(null));
+
+					out
+						.setContactperson(
+							Optional
+								.ofNullable(ir.getContactperson())
+								.map(value -> value.stream().map(cp -> cp.getValue()).collect(Collectors.toList()))
+								.orElse(null));
+					out
+						.setTool(
+							Optional
+								.ofNullable(ir.getTool())
+								.map(value -> value.stream().map(t -> t.getValue()).collect(Collectors.toList()))
+								.orElse(null));
+
+					out.setType(ModelConstants.ORP_DEFAULT_RESULTTYPE.getClassname());
+
+					break;
+			}
+
+			Optional
+				.ofNullable(input.getAuthor())
+				.ifPresent(ats -> out.setAuthor(ats.stream().map(at -> getAuthor(at)).collect(Collectors.toList())));
+
+			// I do not map Access Right UNKNOWN or OTHER
+
+			Optional<eu.dnetlib.dhp.schema.oaf.Qualifier> oar = Optional.ofNullable(input.getBestaccessright());
+			if (oar.isPresent()) {
+				if (Constants.accessRightsCoarMap.containsKey(oar.get().getClassid())) {
+					String code = Constants.accessRightsCoarMap.get(oar.get().getClassid());
+					out
+						.setBestaccessright(
+							AccessRight
+								.newInstance(
+									code,
+									Constants.coarCodeLabelMap.get(code),
+									Constants.COAR_ACCESS_RIGHT_SCHEMA));
+				}
+			}
+
+			final List<String> contributorList = new ArrayList<>();
+			Optional
+				.ofNullable(input.getContributor())
+				.ifPresent(value -> value.stream().forEach(c -> contributorList.add(c.getValue())));
+			out.setContributor(contributorList);
+
+			// List<Country> countryList = new ArrayList<>();
+			Optional
+				.ofNullable(input.getCountry())
+				.ifPresent(
+					value -> out
+						.setCountry(
+							value
+								.stream()
+								.map(
+									c -> {
+										if (c.getClassid().equals((ModelConstants.UNKNOWN))) {
+											return null;
+										}
+										Country country = new Country();
+										country.setCode(c.getClassid());
+										country.setLabel(c.getClassname());
+										Optional
+											.ofNullable(c.getDataInfo())
+											.ifPresent(
+												provenance -> country
+													.setProvenance(
+														Provenance
+															.newInstance(
+																provenance
+																	.getProvenanceaction()
+																	.getClassname(),
+																c.getDataInfo().getTrust())));
+										return country;
+									})
+								.filter(Objects::nonNull)
+								.collect(Collectors.toList())));
+
+			// out.setCountry(countryList);
+
+			final List<String> coverageList = new ArrayList<>();
+			Optional
+				.ofNullable(input.getCoverage())
+				.ifPresent(value -> value.stream().forEach(c -> coverageList.add(c.getValue())));
+			out.setCoverage(coverageList);
+
+			out.setDateofcollection(input.getDateofcollection());
+
+			final List<String> descriptionList = new ArrayList<>();
+			Optional
+				.ofNullable(input.getDescription())
+				.ifPresent(value -> value.forEach(d -> descriptionList.add(d.getValue())));
+			out.setDescription(descriptionList);
+			Optional<Field<String>> oStr = Optional.ofNullable(input.getEmbargoenddate());
+			if (oStr.isPresent()) {
+				out.setEmbargoenddate(oStr.get().getValue());
+			}
+
+			final List<String> formatList = new ArrayList<>();
+			Optional
+				.ofNullable(input.getFormat())
+				.ifPresent(value -> value.stream().forEach(f -> formatList.add(f.getValue())));
+			out.setFormat(formatList);
+			out.setId(input.getId());
+			out.setOriginalId(input.getOriginalId());
+
+			final List<Instance> instanceList = new ArrayList<>();
+			Optional
+				.ofNullable(input.getInstance())
+				.ifPresent(
+					inst -> inst
+						.stream()
+						.forEach(i -> instanceList.add(getInstance(i, graph))));
+			out
+				.setInstance(instanceList);
+
+			Optional<eu.dnetlib.dhp.schema.oaf.Qualifier> oL = Optional.ofNullable(input.getLanguage());
+			if (oL.isPresent()) {
+				eu.dnetlib.dhp.schema.oaf.Qualifier language = oL.get();
+				out.setLanguage(Qualifier.newInstance(language.getClassid(), language.getClassname()));
+			}
+			Optional<Long> oLong = Optional.ofNullable(input.getLastupdatetimestamp());
+			if (oLong.isPresent()) {
+				out.setLastupdatetimestamp(oLong.get());
+			}
+			Optional<List<StructuredProperty>> otitle = Optional.ofNullable(input.getTitle());
+			if (otitle.isPresent()) {
+				List<StructuredProperty> iTitle = otitle
+					.get()
+					.stream()
+					.filter(t -> t.getQualifier().getClassid().equalsIgnoreCase("main title"))
+					.collect(Collectors.toList());
+				if (iTitle.size() > 0) {
+					out.setMaintitle(iTitle.get(0).getValue());
+				}
+
+				iTitle = otitle
+					.get()
+					.stream()
+					.filter(t -> t.getQualifier().getClassid().equalsIgnoreCase("subtitle"))
+					.collect(Collectors.toList());
+				if (iTitle.size() > 0) {
+					out.setSubtitle(iTitle.get(0).getValue());
+				}
+
+			}
+
+			List<ControlledField> pids = new ArrayList<>();
+			Optional
+				.ofNullable(input.getPid())
+				.ifPresent(
+					value -> value
+						.stream()
+						.forEach(
+							p -> pids
+								.add(
+									ControlledField
+										.newInstance(p.getQualifier().getClassid(), p.getValue()))));
+			out.setPid(pids);
+			oStr = Optional.ofNullable(input.getDateofacceptance());
+			if (oStr.isPresent()) {
+				out.setPublicationdate(oStr.get().getValue());
+			}
+			oStr = Optional.ofNullable(input.getPublisher());
+			if (oStr.isPresent()) {
+				out.setPublisher(oStr.get().getValue());
+			}
+
+			List<String> sourceList = new ArrayList<>();
+			Optional
+				.ofNullable(input.getSource())
+				.ifPresent(value -> value.stream().forEach(s -> sourceList.add(s.getValue())));
+			// out.setSource(input.getSource().stream().map(s -> s.getValue()).collect(Collectors.toList()));
+			List<Subject> subjectList = new ArrayList<>();
+			Optional
+				.ofNullable(input.getSubject())
+				.ifPresent(
+					value -> value
+						.forEach(s -> subjectList.add(getSubject(s))));
+
+			out.setSubjects(subjectList);
+
+			out.setType(input.getResulttype().getClassid());
+		}
+
+		if (!graph) {
+			((CommunityResult) out)
+				.setCollectedfrom(
+					input
+						.getCollectedfrom()
+						.stream()
+						.map(cf -> KeyValue.newInstance(cf.getKey(), cf.getValue()))
+						.collect(Collectors.toList()));
+
+			Set<String> communities = communityMap.keySet();
+			List<Context> contextList = Optional
+				.ofNullable(
+					input
+						.getContext())
+				.map(
+					value -> value
+						.stream()
+						.map(c -> {
+							String community_id = c.getId();
+							if (community_id.indexOf("::") > 0) {
+								community_id = community_id.substring(0, community_id.indexOf("::"));
+							}
+							if (communities.contains(community_id)) {
+								Context context = new Context();
+								context.setCode(community_id);
+								context.setLabel(communityMap.get(community_id));
+								Optional<List<DataInfo>> dataInfo = Optional.ofNullable(c.getDataInfo());
+								if (dataInfo.isPresent()) {
+									List<Provenance> provenance = new ArrayList<>();
+									provenance
+										.addAll(
+											dataInfo
+												.get()
+												.stream()
+												.map(
+													di -> Optional
+														.ofNullable(di.getProvenanceaction())
+														.map(
+															provenanceaction -> Provenance
+																.newInstance(
+																	provenanceaction.getClassname(), di.getTrust()))
+														.orElse(null))
+												.filter(Objects::nonNull)
+												.collect(Collectors.toSet()));
+
+									context.setProvenance(getUniqueProvenance(provenance));
+								}
+								return context;
+							}
+							return null;
+						})
+						.filter(Objects::nonNull)
+						.collect(Collectors.toList()))
+				.orElse(new ArrayList<>());
+
+			if (contextList.size() > 0) {
+				Set<Integer> hashValue = new HashSet<>();
+				List<Context> remainigContext = new ArrayList<>();
+				contextList.forEach(c -> {
+					if (!hashValue.contains(c.hashCode())) {
+						remainigContext.add(c);
+						hashValue.add(c.hashCode());
+					}
+				});
+				((CommunityResult) out).setContext(remainigContext);
+			}
+		}
+		return out;
+
+	}
+
+	private static Instance getInstance(eu.dnetlib.dhp.schema.oaf.Instance i, boolean graph) {
+
+			Instance instance = new Instance();
+
+			if(!graph){
+				instance
+						.setCollectedfrom(
+								KeyValue
+										.newInstance(i.getCollectedfrom().getKey(), i.getCollectedfrom().getValue()));
+				instance
+						.setHostedby(
+								KeyValue.newInstance(i.getHostedby().getKey(), i.getHostedby().getValue()));
+			}
+
+			Optional<eu.dnetlib.dhp.schema.oaf.Qualifier> opAr = Optional
+					.ofNullable(i.getAccessright());
+			if (opAr.isPresent()) {
+				if (Constants.accessRightsCoarMap.containsKey(opAr.get().getClassid())) {
+					String code = Constants.accessRightsCoarMap.get(opAr.get().getClassid());
+					instance
+							.setAccessright(
+									AccessRight
+											.newInstance(
+													code,
+													Constants.coarCodeLabelMap.get(code),
+													Constants.COAR_ACCESS_RIGHT_SCHEMA));
+				}
+			}
+
+
+			Optional
+					.ofNullable(i.getLicense())
+					.ifPresent(value -> instance.setLicense(value.getValue()));
+			Optional
+					.ofNullable(i.getDateofacceptance())
+					.ifPresent(value -> instance.setPublicationdate(value.getValue()));
+			Optional
+					.ofNullable(i.getRefereed())
+					.ifPresent(value -> instance.setRefereed(value.getClassname()));
+			// .ifPresent(value -> instance.setRefereed(value.getValue()));
+			Optional
+					.ofNullable(i.getInstancetype())
+					.ifPresent(value -> instance.setType(value.getClassname()));
+			Optional.ofNullable(i.getUrl()).ifPresent(value -> instance.setUrl(value));
+
+		return instance;
+	}
+
+	private static List<Provenance> getUniqueProvenance(List<Provenance> provenance) {
+		Provenance iProv = new Provenance();
+		// iProv.setProvenance(Constants.INFERRED);
+
+		Provenance hProv = new Provenance();
+		// hProv.setProvenance(Constants.HARVESTED);
+		Provenance lProv = new Provenance();
+
+		for (Provenance p : provenance) {
+			switch (p.getProvenance()) {
+				case Constants.HARVESTED:
+					hProv = getHighestTrust(hProv, p);
+					break;
+				case Constants.INFERRED:
+					iProv = getHighestTrust(iProv, p);
+					// To be removed as soon as the new beta run has been done
+					// this fixex issue of not set trust during bulktagging
+					if (StringUtils.isEmpty(iProv.getTrust())) {
+						iProv.setTrust(Constants.DEFAULT_TRUST);
+					}
+					break;
+				case Constants.USER_CLAIM:
+					lProv = getHighestTrust(lProv, p);
+					break;
+			}
+
+		}
+
+		return Arrays
+			.asList(iProv, hProv, lProv)
+			.stream()
+			.filter(p -> !StringUtils.isEmpty(p.getProvenance()))
+			.collect(Collectors.toList());
+
+	}
+
+	private static Provenance getHighestTrust(Provenance hProv, Provenance p) {
+		if (StringUtils.isNoneEmpty(hProv.getTrust(), p.getTrust()))
+			return hProv.getTrust().compareTo(p.getTrust()) > 0 ? hProv : p;
+
+		return (StringUtils.isEmpty(p.getTrust()) && !StringUtils.isEmpty(hProv.getTrust())) ? hProv : p;
+
+	}
+
+	private static Subject getSubject(StructuredProperty s) {
+		Subject subject = new Subject();
+		subject.setSubject(ControlledField.newInstance(s.getQualifier().getClassid(), s.getValue()));
+		Optional<DataInfo> di = Optional.ofNullable(s.getDataInfo());
+		if (di.isPresent()) {
+			Provenance p = new Provenance();
+			p.setProvenance(di.get().getProvenanceaction().getClassname());
+			p.setTrust(di.get().getTrust());
+			subject.setProvenance(p);
+		}
+
+		return subject;
+	}
+
+	private static Author getAuthor(eu.dnetlib.dhp.schema.oaf.Author oa) {
+		Author a = new Author();
+		a.setFullname(oa.getFullname());
+		a.setName(oa.getName());
+		a.setSurname(oa.getSurname());
+		a.setRank(oa.getRank());
+
+		Optional<List<StructuredProperty>> oPids = Optional
+			.ofNullable(oa.getPid());
+		if (oPids.isPresent()) {
+			Pid pid = getOrcid(oPids.get());
+			if (pid != null) {
+				a.setPid(pid);
+			}
+		}
+
+		return a;
+	}
+
+	private static Pid getOrcid(List<StructuredProperty> p) {
+		for (StructuredProperty pid : p) {
+			if (pid.getQualifier().getClassid().equals(Constants.ORCID)) {
+				Optional<DataInfo> di = Optional.ofNullable(pid.getDataInfo());
+				if (di.isPresent()) {
+					return Pid
+						.newInstance(
+							ControlledField
+								.newInstance(
+									pid.getQualifier().getClassid(),
+									pid.getValue()),
+							Provenance
+								.newInstance(
+									di.get().getProvenanceaction().getClassname(),
+									di.get().getTrust()));
+				} else {
+					return Pid
+						.newInstance(
+							ControlledField
+								.newInstance(
+									pid.getQualifier().getClassid(),
+									pid.getValue())
+
+						);
+				}
+
+			}
+		}
+		return null;
+	}
+
+}

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

@@ -0,0 +1,84 @@
+
+package eu.dnetlib.dhp.oa.graph.dump;
+
+import java.io.BufferedWriter;
+import java.io.IOException;
+import java.io.OutputStreamWriter;
+import java.io.Serializable;
+import java.nio.charset.StandardCharsets;
+
+import org.apache.commons.io.IOUtils;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.FSDataOutputStream;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.dom4j.DocumentException;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import eu.dnetlib.dhp.application.ArgumentApplicationParser;
+import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpException;
+
+/**
+ * This class connects with the IS related to the isLookUpUrl got as parameter. It saves the information about the
+ * context that will guide the dump of the results. The information saved is a HashMap. The key is the id of a community
+ * - research infrastructure/initiative , the value is the label of the research community - research
+ * infrastructure/initiative.
+ */
+
+public class SaveCommunityMap implements Serializable {
+
+	private static final Logger log = LoggerFactory.getLogger(SaveCommunityMap.class);
+	private final QueryInformationSystem queryInformationSystem;
+
+	private final Configuration conf;
+	private final BufferedWriter writer;
+
+	public SaveCommunityMap(String hdfsPath, String hdfsNameNode, String isLookUpUrl) throws IOException {
+		conf = new Configuration();
+		conf.set("fs.defaultFS", hdfsNameNode);
+		FileSystem fileSystem = FileSystem.get(conf);
+		Path hdfsWritePath = new Path(hdfsPath);
+		FSDataOutputStream fsDataOutputStream = null;
+		if (fileSystem.exists(hdfsWritePath)) {
+			fileSystem.delete(hdfsWritePath);
+		}
+		fsDataOutputStream = fileSystem.create(hdfsWritePath);
+
+		queryInformationSystem = new QueryInformationSystem();
+		queryInformationSystem.setIsLookUp(Utils.getIsLookUpService(isLookUpUrl));
+
+		writer = new BufferedWriter(new OutputStreamWriter(fsDataOutputStream, StandardCharsets.UTF_8));
+
+	}
+
+	public static void main(String[] args) throws Exception {
+		String jsonConfiguration = IOUtils
+			.toString(
+				SaveCommunityMap.class
+					.getResourceAsStream(
+						"/eu/dnetlib/dhp/oa/graph/dump/input_cm_parameters.json"));
+
+		final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
+		parser.parseArgument(args);
+
+		final String nameNode = parser.get("nameNode");
+		log.info("nameNode: {}", nameNode);
+
+		final String outputPath = parser.get("outputPath");
+		log.info("outputPath: {}", outputPath);
+
+		final String isLookUpUrl = parser.get("isLookUpUrl");
+		log.info("isLookUpUrl: {}", isLookUpUrl);
+
+		final SaveCommunityMap scm = new SaveCommunityMap(outputPath, nameNode, isLookUpUrl);
+
+		scm.saveCommunityMap();
+
+	}
+
+	private void saveCommunityMap() throws ISLookUpException, IOException, DocumentException {
+		writer.write(Utils.OBJECT_MAPPER.writeValueAsString(queryInformationSystem.getCommunityMap()));
+		writer.close();
+	}
+}

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

@@ -0,0 +1,86 @@
+
+package eu.dnetlib.dhp.oa.graph.dump;
+
+import java.io.Serializable;
+import java.util.Optional;
+import org.apache.commons.io.IOUtils;
+import org.apache.commons.logging.Log;
+import org.apache.commons.logging.LogFactory;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.*;
+import eu.dnetlib.dhp.application.ArgumentApplicationParser;
+import eu.dnetlib.dhp.common.api.MissingConceptDoiException;
+import eu.dnetlib.dhp.common.api.ZenodoAPIClient;
+import eu.dnetlib.dhp.oa.graph.dump.community.CommunityMap;
+
+public class SendToZenodoHDFS implements Serializable {
+
+	private static final Log log = LogFactory.getLog(SendToZenodoHDFS.class);
+
+	public static void main(final String[] args) throws Exception, MissingConceptDoiException {
+		final ArgumentApplicationParser parser = new ArgumentApplicationParser(
+			IOUtils
+				.toString(
+					SendToZenodoHDFS.class
+						.getResourceAsStream(
+							"/eu/dnetlib/dhp/oa/graph/dump/upload_zenodo.json")));
+
+		parser.parseArgument(args);
+
+		final String hdfsPath = parser.get("hdfsPath");
+		final String hdfsNameNode = parser.get("nameNode");
+		final String access_token = parser.get("accessToken");
+		final String connection_url = parser.get("connectionUrl");
+		final String metadata = parser.get("metadata");
+		final Boolean newDeposition = Boolean.valueOf(parser.get("newDeposition"));
+		final String concept_rec_id = Optional
+			.ofNullable(parser.get("conceptRecordId"))
+			.orElse(null);
+		final String communityMapPath = parser.get("communityMapPath");
+
+		Configuration conf = new Configuration();
+		conf.set("fs.defaultFS", hdfsNameNode);
+
+		FileSystem fileSystem = FileSystem.get(conf);
+
+		CommunityMap communityMap = Utils.readCommunityMap(fileSystem, communityMapPath);
+
+		RemoteIterator<LocatedFileStatus> fileStatusListIterator = fileSystem
+			.listFiles(
+				new Path(hdfsPath), true);
+		ZenodoAPIClient zenodoApiClient = new ZenodoAPIClient(connection_url, access_token);
+		if (newDeposition) {
+			zenodoApiClient.newDeposition();
+		} else {
+			if (concept_rec_id == null) {
+				throw new MissingConceptDoiException("No concept record id has been provided");
+			}
+			zenodoApiClient.newVersion(concept_rec_id);
+		}
+
+		while (fileStatusListIterator.hasNext()) {
+			LocatedFileStatus fileStatus = fileStatusListIterator.next();
+
+			Path p = fileStatus.getPath();
+			String p_string = p.toString();
+			if (!p_string.endsWith("_SUCCESS")) {
+				// String tmp = p_string.substring(0, p_string.lastIndexOf("/"));
+				String name = p_string.substring(p_string.lastIndexOf("/") + 1);
+				log.info("Sending information for community: " + name);
+				if (communityMap.containsKey(name.substring(0, name.lastIndexOf(".")))) {
+					name = communityMap.get(name.substring(0, name.lastIndexOf("."))).replace(" ", "_") + ".tar";
+				}
+
+				FSDataInputStream inputStream = fileSystem.open(p);
+				zenodoApiClient.uploadIS(inputStream, name, fileStatus.getLen());
+
+			}
+
+		}
+
+		zenodoApiClient.sendMretadata(metadata);
+		zenodoApiClient.publish();
+
+	}
+
+}

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

@@ -0,0 +1,73 @@
+
+package eu.dnetlib.dhp.oa.graph.dump;
+
+import java.io.BufferedReader;
+import java.io.IOException;
+import java.io.InputStreamReader;
+
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.apache.spark.api.java.function.MapFunction;
+import org.apache.spark.sql.Dataset;
+import org.apache.spark.sql.Encoders;
+import org.apache.spark.sql.SparkSession;
+
+import com.fasterxml.jackson.databind.ObjectMapper;
+import com.google.gson.Gson;
+
+import eu.dnetlib.dhp.common.HdfsSupport;
+import eu.dnetlib.dhp.oa.graph.dump.community.CommunityMap;
+import eu.dnetlib.dhp.oa.graph.dump.graph.Constants;
+import eu.dnetlib.dhp.utils.DHPUtils;
+import eu.dnetlib.dhp.utils.ISLookupClientFactory;
+import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
+
+public class Utils {
+	public static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
+
+	public static void removeOutputDir(SparkSession spark, String path) {
+		HdfsSupport.remove(path, spark.sparkContext().hadoopConfiguration());
+	}
+
+	public static <R> Dataset<R> readPath(
+		SparkSession spark, String inputPath, Class<R> clazz) {
+		return spark
+			.read()
+			.textFile(inputPath)
+			.map((MapFunction<String, R>) value -> OBJECT_MAPPER.readValue(value, clazz), Encoders.bean(clazz));
+	}
+
+	public static ISLookUpService getIsLookUpService(String isLookUpUrl) {
+		return ISLookupClientFactory.getLookUpService(isLookUpUrl);
+	}
+
+	public static String getContextId(String id) {
+
+		return String
+			.format(
+				"%s|%s::%s", Constants.CONTEXT_ID, Constants.CONTEXT_NS_PREFIX,
+				DHPUtils.md5(id));
+	}
+
+	public static CommunityMap getCommunityMap(SparkSession spark, String communityMapPath) {
+
+		return new Gson().fromJson(spark.read().textFile(communityMapPath).collectAsList().get(0), CommunityMap.class);
+
+	}
+
+	public static CommunityMap readCommunityMap(FileSystem fileSystem, String communityMapPath) throws IOException {
+		BufferedReader br = new BufferedReader(new InputStreamReader(fileSystem.open(new Path(communityMapPath))));
+		StringBuffer sb = new StringBuffer();
+		try {
+			String line;
+			while ((line = br.readLine()) != null) {
+				sb.append(line);
+			}
+		} finally {
+			br.close();
+
+		}
+
+		return new Gson().fromJson(sb.toString(), CommunityMap.class);
+	}
+}

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

@@ -0,0 +1,8 @@
+
+package eu.dnetlib.dhp.oa.graph.dump.community;
+
+import java.io.Serializable;
+import java.util.HashMap;
+
+public class CommunityMap extends HashMap<String, String> implements Serializable {
+}

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

@@ -0,0 +1,83 @@
+
+package eu.dnetlib.dhp.oa.graph.dump.community;
+
+import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
+
+import java.io.Serializable;
+import java.util.Optional;
+import java.util.Set;
+import java.util.stream.Collectors;
+
+import org.apache.spark.SparkConf;
+import org.apache.spark.sql.Dataset;
+import org.apache.spark.sql.SaveMode;
+import org.apache.spark.sql.SparkSession;
+
+import eu.dnetlib.dhp.oa.graph.dump.Utils;
+import eu.dnetlib.dhp.schema.dump.oaf.community.CommunityResult;
+
+/**
+ * This class splits the dumped results according to the research community - research initiative/infrastructure they
+ * are related to. The information about the community is found in the element "context.id" in the result. Since the
+ * context that can be found in the result can be associated not only to communities, a community Map is provided. It
+ * will guide the splitting process. Note: the repartition(1) just before writing the results related to a community.
+ * This is a choice due to uploading constraints (just one file for each community) As soon as a better solution will be
+ * in place remove the repartition
+ */
+public class CommunitySplit implements Serializable {
+
+	public void run(Boolean isSparkSessionManaged, String inputPath, String outputPath, String communityMapPath) {
+		SparkConf conf = new SparkConf();
+		runWithSparkSession(
+			conf,
+			isSparkSessionManaged,
+			spark -> {
+				Utils.removeOutputDir(spark, outputPath);
+				execSplit(spark, inputPath, outputPath, Utils.getCommunityMap(spark, communityMapPath).keySet());
+			});
+	}
+
+	private static void execSplit(SparkSession spark, String inputPath, String outputPath,
+		Set<String> communities) {
+
+		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 + "/software", CommunityResult.class));
+
+		communities
+			.stream()
+			.forEach(c -> printResult(c, result, outputPath));
+
+	}
+
+	private static void printResult(String c, Dataset<CommunityResult> result, String outputPath) {
+		Dataset<CommunityResult> community_products = result
+			.filter(r -> containsCommunity(r, c));
+
+		try {
+			community_products.first();
+			community_products
+				.write()
+				.option("compression", "gzip")
+				.mode(SaveMode.Overwrite)
+				.json(outputPath + "/" + c);
+		} catch (Exception e) {
+
+		}
+
+	}
+
+	private static boolean containsCommunity(CommunityResult r, String c) {
+		if (Optional.ofNullable(r.getContext()).isPresent()) {
+			return r
+				.getContext()
+				.stream()
+				.filter(con -> con.getCode().equals(c))
+				.collect(Collectors.toList())
+				.size() > 0;
+		}
+		return false;
+	}
+}

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

@@ -0,0 +1,28 @@
+
+package eu.dnetlib.dhp.oa.graph.dump.community;
+
+import java.io.Serializable;
+import java.util.List;
+
+import eu.dnetlib.dhp.schema.dump.oaf.community.Project;
+
+public class ResultProject implements Serializable {
+	private String resultId;
+	private List<Project> projectsList;
+
+	public String getResultId() {
+		return resultId;
+	}
+
+	public void setResultId(String resultId) {
+		this.resultId = resultId;
+	}
+
+	public List<Project> getProjectsList() {
+		return projectsList;
+	}
+
+	public void setProjectsList(List<Project> projectsList) {
+		this.projectsList = projectsList;
+	}
+}

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

@@ -0,0 +1,62 @@
+
+package eu.dnetlib.dhp.oa.graph.dump.community;
+
+import java.io.Serializable;
+import java.util.*;
+
+import org.apache.commons.io.IOUtils;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import eu.dnetlib.dhp.application.ArgumentApplicationParser;
+import eu.dnetlib.dhp.oa.graph.dump.DumpProducts;
+import eu.dnetlib.dhp.schema.dump.oaf.community.CommunityResult;
+import eu.dnetlib.dhp.schema.oaf.Result;
+
+/**
+ * Spark action to trigger the dump of results associated to research community - reseach initiative/infrasctructure The
+ * actual dump if performed via the class DumpProducts that is used also for the entire graph dump
+ */
+public class SparkDumpCommunityProducts implements Serializable {
+
+	private static final Logger log = LoggerFactory.getLogger(SparkDumpCommunityProducts.class);
+
+	public static void main(String[] args) throws Exception {
+		String jsonConfiguration = IOUtils
+			.toString(
+				SparkDumpCommunityProducts.class
+					.getResourceAsStream(
+						"/eu/dnetlib/dhp/oa/graph/dump/input_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 resultClassName = parser.get("resultTableName");
+		log.info("resultTableName: {}", resultClassName);
+
+		String communityMapPath = parser.get("communityMapPath");
+
+		Class<? extends Result> inputClazz = (Class<? extends Result>) Class.forName(resultClassName);
+
+		DumpProducts dump = new DumpProducts();
+
+		dump
+			.run(
+				isSparkSessionManaged, inputPath, outputPath, communityMapPath, inputClazz, CommunityResult.class,
+				false);
+
+	}
+
+}

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

@@ -0,0 +1,185 @@
+
+package eu.dnetlib.dhp.oa.graph.dump.community;
+
+import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
+
+import java.io.Serializable;
+import java.io.StringReader;
+import java.util.*;
+import java.util.stream.Collectors;
+
+import org.apache.commons.io.IOUtils;
+import org.apache.spark.SparkConf;
+import org.apache.spark.api.java.function.MapFunction;
+import org.apache.spark.api.java.function.MapGroupsFunction;
+import org.apache.spark.sql.Dataset;
+import org.apache.spark.sql.Encoders;
+import org.apache.spark.sql.SaveMode;
+import org.apache.spark.sql.SparkSession;
+import org.dom4j.Document;
+import org.dom4j.DocumentException;
+import org.dom4j.Node;
+import org.dom4j.io.SAXReader;
+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.Provenance;
+import eu.dnetlib.dhp.schema.dump.oaf.community.Funder;
+import eu.dnetlib.dhp.schema.dump.oaf.community.Project;
+import eu.dnetlib.dhp.schema.oaf.DataInfo;
+import eu.dnetlib.dhp.schema.oaf.Relation;
+import scala.Tuple2;
+
+/**
+ * Preparation of the Project information to be added to the dumped results. For each result associated to at least one
+ * Project, a serialization of an instance af ResultProject closs is done. ResultProject contains the resultId, and the
+ * list of Projects (as in eu.dnetlib.dhp.schema.dump.oaf.community.Project) it is associated to
+ */
+public class SparkPrepareResultProject implements Serializable {
+	private static final Logger log = LoggerFactory.getLogger(SparkPrepareResultProject.class);
+
+	public static void main(String[] args) throws Exception {
+		String jsonConfiguration = IOUtils
+			.toString(
+				SparkPrepareResultProject.class
+					.getResourceAsStream(
+						"/eu/dnetlib/dhp/oa/graph/dump/project_prep_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);
+
+		SparkConf conf = new SparkConf();
+
+		runWithSparkSession(
+			conf,
+			isSparkSessionManaged,
+			spark -> {
+				Utils.removeOutputDir(spark, outputPath);
+				prepareResultProjectList(spark, inputPath, outputPath);
+			});
+	}
+
+	private static void prepareResultProjectList(SparkSession spark, String inputPath, String outputPath) {
+		Dataset<Relation> relation = Utils
+			.readPath(spark, inputPath + "/relation", Relation.class)
+			.filter("dataInfo.deletedbyinference = false and relClass = 'produces'");
+		Dataset<eu.dnetlib.dhp.schema.oaf.Project> projects = Utils
+			.readPath(spark, inputPath + "/project", eu.dnetlib.dhp.schema.oaf.Project.class);
+
+		projects
+			.joinWith(relation, projects.col("id").equalTo(relation.col("source")))
+			.groupByKey(
+				(MapFunction<Tuple2<eu.dnetlib.dhp.schema.oaf.Project, Relation>, String>) value -> value
+					._2()
+					.getTarget(),
+				Encoders.STRING())
+			.mapGroups(
+				(MapGroupsFunction<String, Tuple2<eu.dnetlib.dhp.schema.oaf.Project, Relation>, ResultProject>) (s,
+					it) -> {
+					Set<String> projectSet = new HashSet<>();
+					Tuple2<eu.dnetlib.dhp.schema.oaf.Project, Relation> first = it.next();
+					ResultProject rp = new ResultProject();
+					rp.setResultId(first._2().getTarget());
+					eu.dnetlib.dhp.schema.oaf.Project p = first._1();
+					projectSet.add(p.getId());
+					Project ps = getProject(p);
+
+					List<Project> projList = new ArrayList<>();
+					projList.add(ps);
+					rp.setProjectsList(projList);
+					it.forEachRemaining(c -> {
+						eu.dnetlib.dhp.schema.oaf.Project op = c._1();
+						if (!projectSet.contains(op.getId())) {
+							projList
+								.add(getProject(op));
+
+							projectSet.add(op.getId());
+
+						}
+
+					});
+					return rp;
+				}, Encoders.bean(ResultProject.class))
+			.write()
+			.mode(SaveMode.Overwrite)
+			.option("compression", "gzip")
+			.json(outputPath);
+	}
+
+	private static Project getProject(eu.dnetlib.dhp.schema.oaf.Project op) {
+		Project p = Project
+			.newInstance(
+				op.getId(),
+				op.getCode().getValue(),
+				Optional
+					.ofNullable(op.getAcronym())
+					.map(a -> a.getValue())
+					.orElse(null),
+				Optional
+					.ofNullable(op.getTitle())
+					.map(v -> v.getValue())
+					.orElse(null),
+				Optional
+					.ofNullable(op.getFundingtree())
+					.map(
+						value -> value
+							.stream()
+							.map(ft -> getFunder(ft.getValue()))
+							.collect(Collectors.toList())
+							.get(0))
+					.orElse(null));
+
+		Optional<DataInfo> di = Optional.ofNullable(op.getDataInfo());
+		Provenance provenance = new Provenance();
+		if (di.isPresent()) {
+			provenance.setProvenance(di.get().getProvenanceaction().getClassname());
+			provenance.setTrust(di.get().getTrust());
+			p.setProvenance(provenance);
+		}
+
+		return p;
+
+	}
+
+	private static Funder getFunder(String fundingtree) {
+		// ["<fundingtree><funder><id>nsf_________::NSF</id><shortname>NSF</shortname><name>National Science
+		// Foundation</name><jurisdiction>US</jurisdiction></funder><funding_level_1><id>nsf_________::NSF::CISE/OAD::CISE/CCF</id><description>Division
+		// of Computing and Communication Foundations</description><name>Division of Computing and Communication
+		// Foundations</name><parent><funding_level_0><id>nsf_________::NSF::CISE/OAD</id><description>Directorate for
+		// Computer &amp; Information Science &amp; Engineering</description><name>Directorate for Computer &amp;
+		// Information Science &amp;
+		// Engineering</name><parent/><class>nsf:fundingStream</class></funding_level_0></parent></funding_level_1></fundingtree>"]
+		Funder f = new Funder();
+		final Document doc;
+		try {
+			doc = new SAXReader().read(new StringReader(fundingtree));
+			f.setShortName(((Node) (doc.selectNodes("//funder/shortname").get(0))).getText());
+			f.setName(((Node) (doc.selectNodes("//funder/name").get(0))).getText());
+			f.setJurisdiction(((Node) (doc.selectNodes("//funder/jurisdiction").get(0))).getText());
+			for (Object o : doc.selectNodes("//funding_level_0")) {
+				List node = ((Node) o).selectNodes("./name");
+				f.setFundingStream(((Node) node.get(0)).getText());
+
+			}
+
+			return f;
+		} catch (DocumentException e) {
+			e.printStackTrace();
+		}
+		return f;
+	}
+}

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

@@ -0,0 +1,50 @@
+
+package eu.dnetlib.dhp.oa.graph.dump.community;
+
+import java.io.Serializable;
+import java.util.Optional;
+
+import org.apache.commons.io.IOUtils;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import eu.dnetlib.dhp.application.ArgumentApplicationParser;
+
+/**
+ * Spark job to trigger the split of results associated to research community - reseach initiative/infrasctructure. The
+ * actual split is performed by the class CommunitySplit
+ */
+public class SparkSplitForCommunity implements Serializable {
+
+	private static final Logger log = LoggerFactory.getLogger(SparkSplitForCommunity.class);
+
+	public static void main(String[] args) throws Exception {
+		String jsonConfiguration = IOUtils
+			.toString(
+				SparkSplitForCommunity.class
+					.getResourceAsStream(
+						"/eu/dnetlib/dhp/oa/graph/dump/split_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 communityMapPath = parser.get("communityMapPath");
+
+		CommunitySplit split = new CommunitySplit();
+		split.run(isSparkSessionManaged, inputPath, outputPath, communityMapPath);
+
+	}
+
+}

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

@@ -0,0 +1,90 @@
+
+package eu.dnetlib.dhp.oa.graph.dump.community;
+
+import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
+
+import java.io.Serializable;
+import java.util.Optional;
+
+import org.apache.commons.io.IOUtils;
+import org.apache.spark.SparkConf;
+import org.apache.spark.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 com.fasterxml.jackson.databind.ObjectMapper;
+
+import eu.dnetlib.dhp.application.ArgumentApplicationParser;
+import eu.dnetlib.dhp.oa.graph.dump.Utils;
+import eu.dnetlib.dhp.schema.dump.oaf.community.CommunityResult;
+
+public class SparkUpdateProjectInfo implements Serializable {
+
+	private static final Logger log = LoggerFactory.getLogger(SparkUpdateProjectInfo.class);
+	public static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
+
+	public static void main(String[] args) throws Exception {
+		String jsonConfiguration = IOUtils
+			.toString(
+				SparkUpdateProjectInfo.class
+					.getResourceAsStream(
+						"/eu/dnetlib/dhp/oa/graph/dump/project_input_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 preparedInfoPath = parser.get("preparedInfoPath");
+		log.info("preparedInfoPath: {}", preparedInfoPath);
+
+		SparkConf conf = new SparkConf();
+
+		runWithSparkSession(
+			conf,
+			isSparkSessionManaged,
+			spark -> {
+				Utils.removeOutputDir(spark, outputPath);
+				extend(spark, inputPath, outputPath, preparedInfoPath);// , inputClazz);
+			});
+	}
+
+	private static void extend(
+		SparkSession spark,
+		String inputPath,
+		String outputPath,
+		String preparedInfoPath) {
+		Dataset<CommunityResult> result = Utils.readPath(spark, inputPath, CommunityResult.class);
+		Dataset<ResultProject> resultProject = Utils.readPath(spark, preparedInfoPath, ResultProject.class);
+		result
+			.joinWith(
+				resultProject, result.col("id").equalTo(resultProject.col("resultId")),
+				"left")
+			.map(value -> {
+				CommunityResult r = value._1();
+				Optional.ofNullable(value._2()).ifPresent(rp -> {
+					r.setProjects(rp.getProjectsList());
+				});
+				return r;
+			}, Encoders.bean(CommunityResult.class))
+			.write()
+			.option("compression", "gzip")
+			.mode(SaveMode.Append)
+			.json(outputPath);
+
+	}
+
+}

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

@@ -0,0 +1,26 @@
+
+package eu.dnetlib.dhp.oa.graph.dump.graph;
+
+import java.io.Serializable;
+
+public class Constants implements Serializable {
+
+	public static final String IS_HOSTED_BY = "isHostedBy";
+	public static final String HOSTS = "hosts";
+
+	public static final String IS_FUNDED_BY = "isFundedBy";
+	public static final String FUNDS = "funds";
+
+	public static final String FUNDINGS = "fundings";
+
+	public static final String RESULT_ENTITY = "result";
+	public static final String DATASOURCE_ENTITY = "datasource";
+	public static final String CONTEXT_ENTITY = "context";
+	public static final String ORGANIZATION_ENTITY = "organization";
+	public static final String PROJECT_ENTITY = "project";
+
+	public static final String CONTEXT_ID = "00";
+	public static final String CONTEXT_NS_PREFIX = "context_____";
+
+	// public static final String FUNDER_DS = "entityregistry::projects";
+}

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

@@ -0,0 +1,84 @@
+
+package eu.dnetlib.dhp.oa.graph.dump.graph;
+
+import java.io.Serializable;
+import java.util.List;
+
+/**
+ * Deserialization of the information in the context needed to create Context Entities, and relations between context
+ * entities and datasources and projects
+ */
+public class ContextInfo implements Serializable {
+	private String id;
+	private String description;
+	private String type;
+	private String zenodocommunity;
+	private String name;
+	private List<String> projectList;
+	private List<String> datasourceList;
+	private List<String> subject;
+
+	public List<String> getSubject() {
+		return subject;
+	}
+
+	public void setSubject(List<String> subject) {
+		this.subject = subject;
+	}
+
+	public String getName() {
+		return name;
+	}
+
+	public void setName(String name) {
+		this.name = name;
+	}
+
+	public String getId() {
+		return id;
+	}
+
+	public void setId(String id) {
+		this.id = id;
+	}
+
+	public String getDescription() {
+		return description;
+	}
+
+	public void setDescription(String description) {
+		this.description = description;
+	}
+
+	public String getType() {
+		return type;
+	}
+
+	public void setType(String type) {
+		this.type = type;
+	}
+
+	public String getZenodocommunity() {
+		return zenodocommunity;
+	}
+
+	public void setZenodocommunity(String zenodocommunity) {
+		this.zenodocommunity = zenodocommunity;
+	}
+
+	public List<String> getProjectList() {
+		return projectList;
+	}
+
+	public void setProjectList(List<String> projectList) {
+		this.projectList = projectList;
+	}
+
+	public List<String> getDatasourceList() {
+		return datasourceList;
+	}
+
+	public void setDatasourceList(List<String> datasourceList) {
+		this.datasourceList = datasourceList;
+	}
+}

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

@@ -0,0 +1,105 @@
+
+package eu.dnetlib.dhp.oa.graph.dump.graph;
+
+import java.io.BufferedWriter;
+import java.io.IOException;
+import java.io.OutputStreamWriter;
+import java.io.Serializable;
+import java.nio.charset.StandardCharsets;
+import java.util.function.Consumer;
+import java.util.function.Function;
+
+import org.apache.commons.io.IOUtils;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.FSDataOutputStream;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.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.ResearchInitiative;
+
+/**
+ * Writes on HDFS Context entities. It queries the Information System at the lookup url provided as parameter and
+ * collects the general information for contexes of type community or ri. The general information is the id of the
+ * context, its label, the subjects associated to the context, its zenodo community, description and type. This
+ * information is used to create a new Context Entity
+ */
+public class CreateContextEntities implements Serializable {
+
+	private static final Logger log = LoggerFactory.getLogger(CreateContextEntities.class);
+	private final Configuration conf;
+	private final BufferedWriter writer;
+
+	public static void main(String[] args) throws Exception {
+		String jsonConfiguration = IOUtils
+			.toString(
+				CreateContextEntities.class
+					.getResourceAsStream(
+						"/eu/dnetlib/dhp/oa/graph/dump_whole/input_entity_parameter.json"));
+
+		final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
+		parser.parseArgument(args);
+
+		final String hdfsPath = parser.get("hdfsPath");
+		log.info("hdfsPath: {}", hdfsPath);
+
+		final String hdfsNameNode = parser.get("nameNode");
+		log.info("nameNode: {}", hdfsNameNode);
+
+		final String isLookUpUrl = parser.get("isLookUpUrl");
+		log.info("isLookUpUrl: {}", isLookUpUrl);
+
+		final CreateContextEntities cce = new CreateContextEntities(hdfsPath, hdfsNameNode);
+
+		log.info("Processing contexts...");
+		cce.execute(Process::getEntity, isLookUpUrl);
+
+		cce.close();
+
+	}
+
+	private void close() throws IOException {
+		writer.close();
+	}
+
+	public CreateContextEntities(String hdfsPath, String hdfsNameNode) throws IOException {
+		this.conf = new Configuration();
+		this.conf.set("fs.defaultFS", hdfsNameNode);
+		FileSystem fileSystem = FileSystem.get(this.conf);
+		Path hdfsWritePath = new Path(hdfsPath);
+		FSDataOutputStream fsDataOutputStream = null;
+		if (fileSystem.exists(hdfsWritePath)) {
+			fsDataOutputStream = fileSystem.append(hdfsWritePath);
+		} else {
+			fsDataOutputStream = fileSystem.create(hdfsWritePath);
+		}
+
+		this.writer = new BufferedWriter(new OutputStreamWriter(fsDataOutputStream, StandardCharsets.UTF_8));
+
+	}
+
+	public <R extends ResearchInitiative> void execute(final Function<ContextInfo, R> producer, String isLookUpUrl)
+		throws Exception {
+
+		QueryInformationSystem queryInformationSystem = new QueryInformationSystem();
+		queryInformationSystem.setIsLookUp(Utils.getIsLookUpService(isLookUpUrl));
+
+		final Consumer<ContextInfo> consumer = ci -> writeEntity(producer.apply(ci));
+
+		queryInformationSystem.getContextInformation(consumer);
+	}
+
+	protected <R extends ResearchInitiative> void writeEntity(final R r) {
+		try {
+			writer.write(Utils.OBJECT_MAPPER.writeValueAsString(r));
+			// log.info("writing context : {}", new Gson().toJson(r));
+			writer.newLine();
+		} catch (final Exception e) {
+			throw new RuntimeException(e);
+		}
+	}
+
+}

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

@@ -0,0 +1,124 @@
+
+package eu.dnetlib.dhp.oa.graph.dump.graph;
+
+import java.io.BufferedWriter;
+import java.io.IOException;
+import java.io.OutputStreamWriter;
+import java.io.Serializable;
+import java.nio.charset.StandardCharsets;
+import java.util.List;
+import java.util.Optional;
+import java.util.function.Consumer;
+import java.util.function.Function;
+
+import org.apache.commons.io.IOUtils;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.FSDataOutputStream;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.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.common.ModelSupport;
+import eu.dnetlib.dhp.schema.dump.oaf.graph.*;
+import eu.dnetlib.dhp.schema.oaf.Datasource;
+import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpException;
+
+/**
+ * Writes the set of new Relation between the context and datasources. At the moment the relation between the context
+ * and the project is not created because of a low coverage in the profiles of openaire ids related to projects
+ */
+public class CreateContextRelation implements Serializable {
+	private static final Logger log = LoggerFactory.getLogger(CreateContextEntities.class);
+	private final Configuration conf;
+	private final BufferedWriter writer;
+	private final QueryInformationSystem queryInformationSystem;
+
+	private static final String CONTEX_RELATION_DATASOURCE = "contentproviders";
+	private static final String CONTEX_RELATION_PROJECT = "projects";
+
+	public static void main(String[] args) throws Exception {
+		String jsonConfiguration = IOUtils
+			.toString(
+				CreateContextRelation.class
+					.getResourceAsStream(
+						"/eu/dnetlib/dhp/oa/graph/dump_whole/input_entity_parameter.json"));
+
+		final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
+		parser.parseArgument(args);
+
+		Boolean isSparkSessionManaged = Optional
+			.ofNullable(parser.get("isSparkSessionManaged"))
+			.map(Boolean::valueOf)
+			.orElse(Boolean.TRUE);
+		log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
+
+		final String hdfsPath = parser.get("hdfsPath");
+		log.info("hdfsPath: {}", hdfsPath);
+
+		final String hdfsNameNode = parser.get("nameNode");
+		log.info("nameNode: {}", hdfsNameNode);
+
+		final String isLookUpUrl = parser.get("isLookUpUrl");
+		log.info("isLookUpUrl: {}", isLookUpUrl);
+
+		final CreateContextRelation cce = new CreateContextRelation(hdfsPath, hdfsNameNode, isLookUpUrl);
+
+		log.info("Creating relation for datasource...");
+		cce.execute(Process::getRelation, CONTEX_RELATION_DATASOURCE, ModelSupport.getIdPrefix(Datasource.class));
+
+		log.info("Creating relations for projects... ");
+//		cce
+//			.execute(
+//				Process::getRelation, CONTEX_RELATION_PROJECT,
+//				ModelSupport.getIdPrefix(eu.dnetlib.dhp.schema.oaf.Project.class));
+
+		cce.close();
+
+	}
+
+	private void close() throws IOException {
+		writer.close();
+	}
+
+	public CreateContextRelation(String hdfsPath, String hdfsNameNode, String isLookUpUrl)
+		throws IOException, ISLookUpException {
+		this.conf = new Configuration();
+		this.conf.set("fs.defaultFS", hdfsNameNode);
+
+		queryInformationSystem = new QueryInformationSystem();
+		queryInformationSystem.setIsLookUp(Utils.getIsLookUpService(isLookUpUrl));
+		queryInformationSystem.execContextRelationQuery();
+
+		FileSystem fileSystem = FileSystem.get(this.conf);
+		Path hdfsWritePath = new Path(hdfsPath);
+		FSDataOutputStream fsDataOutputStream = null;
+		if (fileSystem.exists(hdfsWritePath)) {
+			fsDataOutputStream = fileSystem.append(hdfsWritePath);
+		} else {
+			fsDataOutputStream = fileSystem.create(hdfsWritePath);
+		}
+
+		this.writer = new BufferedWriter(new OutputStreamWriter(fsDataOutputStream, StandardCharsets.UTF_8));
+
+	}
+
+	public void execute(final Function<ContextInfo, List<Relation>> producer, String category, String prefix) {
+
+		final Consumer<ContextInfo> consumer = ci -> producer.apply(ci).forEach(c -> writeEntity(c));
+
+		queryInformationSystem.getContextRelation(consumer, category, prefix);
+	}
+
+	protected void writeEntity(final Relation r) {
+		try {
+			writer.write(Utils.OBJECT_MAPPER.writeValueAsString(r));
+			writer.newLine();
+		} catch (final Exception e) {
+			throw new RuntimeException(e);
+		}
+	}
+
+}

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

@@ -0,0 +1,496 @@
+
+package eu.dnetlib.dhp.oa.graph.dump.graph;
+
+import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
+
+import java.io.Serializable;
+import java.io.StringReader;
+import java.util.*;
+import java.util.stream.Collectors;
+
+import org.apache.spark.SparkConf;
+import org.apache.spark.sql.Encoders;
+import org.apache.spark.sql.SaveMode;
+import org.apache.spark.sql.SparkSession;
+import org.dom4j.Document;
+import org.dom4j.DocumentException;
+import org.dom4j.Node;
+import org.dom4j.io.SAXReader;
+
+import eu.dnetlib.dhp.oa.graph.dump.DumpProducts;
+import eu.dnetlib.dhp.oa.graph.dump.Utils;
+import eu.dnetlib.dhp.schema.common.ModelSupport;
+import eu.dnetlib.dhp.schema.dump.oaf.*;
+import eu.dnetlib.dhp.schema.dump.oaf.graph.*;
+import eu.dnetlib.dhp.schema.oaf.Field;
+import eu.dnetlib.dhp.schema.oaf.Journal;
+import eu.dnetlib.dhp.schema.oaf.OafEntity;
+
+/**
+ * Dumps of entities in the model defined in eu.dnetlib.dhp.schema.dump.oaf.graph. Results are dumped using the same
+ * Mapper as for eu.dnetlib.dhp.schema.dump.oaf.community, while for the other entities the mapping is defined below
+ */
+public class DumpGraphEntities implements Serializable {
+
+	public void run(Boolean isSparkSessionManaged,
+		String inputPath,
+		String outputPath,
+		Class<? extends OafEntity> inputClazz,
+		String communityMapPath) {
+
+		SparkConf conf = new SparkConf();
+
+		switch (ModelSupport.idPrefixMap.get(inputClazz)) {
+			case "50":
+				DumpProducts d = new DumpProducts();
+				d
+					.run(
+						isSparkSessionManaged, inputPath, outputPath, communityMapPath, inputClazz, Result.class,
+						true);
+				break;
+			case "40":
+				runWithSparkSession(
+					conf,
+					isSparkSessionManaged,
+					spark -> {
+						Utils.removeOutputDir(spark, outputPath);
+						projectMap(spark, inputPath, outputPath, inputClazz);
+
+					});
+				break;
+			case "20":
+				runWithSparkSession(
+					conf,
+					isSparkSessionManaged,
+					spark -> {
+						Utils.removeOutputDir(spark, outputPath);
+						organizationMap(spark, inputPath, outputPath, inputClazz);
+
+					});
+				break;
+			case "10":
+				runWithSparkSession(
+					conf,
+					isSparkSessionManaged,
+					spark -> {
+						Utils.removeOutputDir(spark, outputPath);
+						datasourceMap(spark, inputPath, outputPath, inputClazz);
+
+					});
+				break;
+		}
+
+	}
+
+	private static <E extends OafEntity> void datasourceMap(SparkSession spark, String inputPath, String outputPath,
+		Class<E> inputClazz) {
+		Utils
+			.readPath(spark, inputPath, inputClazz)
+			.map(d -> mapDatasource((eu.dnetlib.dhp.schema.oaf.Datasource) d), Encoders.bean(Datasource.class))
+			.filter(Objects::nonNull)
+			.write()
+			.mode(SaveMode.Overwrite)
+			.option("compression", "gzip")
+			.json(outputPath);
+	}
+
+	private static <E extends OafEntity> void projectMap(SparkSession spark, String inputPath, String outputPath,
+		Class<E> inputClazz) {
+		Utils
+			.readPath(spark, inputPath, inputClazz)
+			.map(p -> mapProject((eu.dnetlib.dhp.schema.oaf.Project) p), Encoders.bean(Project.class))
+			.write()
+			.mode(SaveMode.Overwrite)
+			.option("compression", "gzip")
+			.json(outputPath);
+	}
+
+	private static Datasource mapDatasource(eu.dnetlib.dhp.schema.oaf.Datasource d) {
+		Datasource datasource = new Datasource();
+
+		datasource.setId(d.getId());
+
+		Optional
+			.ofNullable(d.getOriginalId())
+			.ifPresent(
+				oId -> datasource.setOriginalId(oId.stream().filter(Objects::nonNull).collect(Collectors.toList())));
+
+		Optional
+			.ofNullable(d.getPid())
+			.ifPresent(
+				pids -> pids
+					.stream()
+					.map(p -> ControlledField.newInstance(p.getQualifier().getClassid(), p.getValue()))
+					.collect(Collectors.toList()));
+
+		Optional
+			.ofNullable(d.getDatasourcetype())
+			.ifPresent(
+				dsType -> datasource
+					.setDatasourcetype(ControlledField.newInstance(dsType.getClassid(), dsType.getClassname())));
+
+		Optional
+			.ofNullable(d.getOpenairecompatibility())
+			.ifPresent(v -> datasource.setOpenairecompatibility(v.getClassname()));
+
+		Optional
+			.ofNullable(d.getOfficialname())
+			.ifPresent(oname -> datasource.setOfficialname(oname.getValue()));
+
+		Optional
+			.ofNullable(d.getEnglishname())
+			.ifPresent(ename -> datasource.setEnglishname(ename.getValue()));
+
+		Optional
+			.ofNullable(d.getWebsiteurl())
+			.ifPresent(wsite -> datasource.setWebsiteurl(wsite.getValue()));
+
+		Optional
+			.ofNullable(d.getLogourl())
+			.ifPresent(lurl -> datasource.setLogourl(lurl.getValue()));
+
+		Optional
+			.ofNullable(d.getDateofvalidation())
+			.ifPresent(dval -> datasource.setDateofvalidation(dval.getValue()));
+
+		Optional
+			.ofNullable(d.getDescription())
+			.ifPresent(dex -> datasource.setDescription(dex.getValue()));
+
+		Optional
+			.ofNullable(d.getSubjects())
+			.ifPresent(
+				sbjs -> datasource.setSubjects(sbjs.stream().map(sbj -> sbj.getValue()).collect(Collectors.toList())));
+
+		Optional
+			.ofNullable(d.getOdpolicies())
+			.ifPresent(odp -> datasource.setPolicies(Arrays.asList(odp.getValue())));
+
+		Optional
+			.ofNullable(d.getOdlanguages())
+			.ifPresent(
+				langs -> datasource
+					.setLanguages(langs.stream().map(lang -> lang.getValue()).collect(Collectors.toList())));
+
+		Optional
+			.ofNullable(d.getOdcontenttypes())
+			.ifPresent(
+				ctypes -> datasource
+					.setContenttypes(ctypes.stream().map(ctype -> ctype.getValue()).collect(Collectors.toList())));
+
+		Optional
+			.ofNullable(d.getReleasestartdate())
+			.ifPresent(rd -> datasource.setReleasestartdate(rd.getValue()));
+
+		Optional
+			.ofNullable(d.getReleaseenddate())
+			.ifPresent(ed -> datasource.setReleaseenddate(ed.getValue()));
+
+		Optional
+			.ofNullable(d.getMissionstatementurl())
+			.ifPresent(ms -> datasource.setMissionstatementurl(ms.getValue()));
+
+		Optional
+			.ofNullable(d.getDatabaseaccesstype())
+			.ifPresent(ar -> datasource.setAccessrights(ar.getValue()));
+
+		Optional
+			.ofNullable(d.getDatauploadtype())
+			.ifPresent(dut -> datasource.setUploadrights(dut.getValue()));
+
+		Optional
+			.ofNullable(d.getDatabaseaccessrestriction())
+			.ifPresent(dar -> datasource.setDatabaseaccessrestriction(dar.getValue()));
+
+		Optional
+			.ofNullable(d.getDatauploadrestriction())
+			.ifPresent(dur -> datasource.setDatauploadrestriction(dur.getValue()));
+
+		Optional
+			.ofNullable(d.getVersioning())
+			.ifPresent(v -> datasource.setVersioning(v.getValue()));
+
+		Optional
+			.ofNullable(d.getCitationguidelineurl())
+			.ifPresent(cu -> datasource.setCitationguidelineurl(cu.getValue()));
+
+		Optional
+			.ofNullable(d.getPidsystems())
+			.ifPresent(ps -> datasource.setPidsystems(ps.getValue()));
+
+		Optional
+			.ofNullable(d.getCertificates())
+			.ifPresent(c -> datasource.setCertificates(c.getValue()));
+
+		Optional
+			.ofNullable(d.getPolicies())
+			.ifPresent(ps -> datasource.setPolicies(ps.stream().map(p -> p.getValue()).collect(Collectors.toList())));
+
+		Optional
+			.ofNullable(d.getJournal())
+			.ifPresent(j -> datasource.setJournal(getContainer(j)));
+
+		return datasource;
+
+	}
+
+	private static Container getContainer(Journal j) {
+		Container c = new Container();
+
+		Optional
+			.ofNullable(j.getName())
+			.ifPresent(n -> c.setName(n));
+
+		Optional
+			.ofNullable(j.getIssnPrinted())
+			.ifPresent(issnp -> c.setIssnPrinted(issnp));
+
+		Optional
+			.ofNullable(j.getIssnOnline())
+			.ifPresent(issno -> c.setIssnOnline(issno));
+
+		Optional
+			.ofNullable(j.getIssnLinking())
+			.ifPresent(isnl -> c.setIssnLinking(isnl));
+
+		Optional
+			.ofNullable(j.getEp())
+			.ifPresent(ep -> c.setEp(ep));
+
+		Optional
+			.ofNullable(j.getIss())
+			.ifPresent(iss -> c.setIss(iss));
+
+		Optional
+			.ofNullable(j.getSp())
+			.ifPresent(sp -> c.setSp(sp));
+
+		Optional
+			.ofNullable(j.getVol())
+			.ifPresent(vol -> c.setVol(vol));
+
+		Optional
+			.ofNullable(j.getEdition())
+			.ifPresent(edition -> c.setEdition(edition));
+
+		Optional
+			.ofNullable(j.getConferencedate())
+			.ifPresent(cdate -> c.setConferencedate(cdate));
+
+		Optional
+			.ofNullable(j.getConferenceplace())
+			.ifPresent(cplace -> c.setConferenceplace(cplace));
+
+		return c;
+	}
+
+	private static Project mapProject(eu.dnetlib.dhp.schema.oaf.Project p) throws DocumentException {
+		Project project = new Project();
+
+		Optional
+			.ofNullable(p.getId())
+			.ifPresent(id -> project.setId(id));
+
+		Optional
+			.ofNullable(p.getWebsiteurl())
+			.ifPresent(w -> project.setWebsiteurl(w.getValue()));
+
+		Optional
+			.ofNullable(p.getCode())
+			.ifPresent(code -> project.setCode(code.getValue()));
+
+		Optional
+			.ofNullable(p.getAcronym())
+			.ifPresent(acronynim -> project.setAcronym(acronynim.getValue()));
+
+		Optional
+			.ofNullable(p.getTitle())
+			.ifPresent(title -> project.setTitle(title.getValue()));
+
+		Optional
+			.ofNullable(p.getStartdate())
+			.ifPresent(sdate -> project.setStartdate(sdate.getValue()));
+
+		Optional
+			.ofNullable(p.getEnddate())
+			.ifPresent(edate -> project.setEnddate(edate.getValue()));
+
+		Optional
+			.ofNullable(p.getCallidentifier())
+			.ifPresent(cide -> project.setCallidentifier(cide.getValue()));
+
+		Optional
+			.ofNullable(p.getKeywords())
+			.ifPresent(key -> project.setKeywords(key.getValue()));
+
+		Optional<Field<String>> omandate = Optional.ofNullable(p.getOamandatepublications());
+		Optional<Field<String>> oecsc39 = Optional.ofNullable(p.getEcsc39());
+		boolean mandate = false;
+		if (omandate.isPresent()) {
+			if (omandate.get().getValue().equals("true")) {
+				mandate = true;
+			}
+		}
+		if (oecsc39.isPresent()) {
+			if (oecsc39.get().getValue().equals("true")) {
+				mandate = true;
+			}
+		}
+
+		project.setOpenaccessmandateforpublications(mandate);
+		project.setOpenaccessmandatefordataset(false);
+
+		Optional
+			.ofNullable(p.getEcarticle29_3())
+			.ifPresent(oamandate -> project.setOpenaccessmandatefordataset(oamandate.getValue().equals("true")));
+
+		project
+			.setSubject(
+				Optional
+					.ofNullable(p.getSubjects())
+					.map(subjs -> subjs.stream().map(s -> s.getValue()).collect(Collectors.toList()))
+					.orElse(new ArrayList<>()));
+
+		Optional
+			.ofNullable(p.getSummary())
+			.ifPresent(summary -> project.setSummary(summary.getValue()));
+
+		Optional<Float> ofundedamount = Optional.ofNullable(p.getFundedamount());
+		Optional<Field<String>> ocurrency = Optional.ofNullable(p.getCurrency());
+		Optional<Float> ototalcost = Optional.ofNullable(p.getTotalcost());
+
+		if (ocurrency.isPresent()) {
+			if (ofundedamount.isPresent()) {
+				if (ototalcost.isPresent()) {
+					project
+						.setGranted(
+							Granted.newInstance(ocurrency.get().getValue(), ototalcost.get(), ofundedamount.get()));
+				} else {
+					project.setGranted(Granted.newInstance(ocurrency.get().getValue(), ofundedamount.get()));
+				}
+			}
+		}
+
+		project
+			.setProgramme(
+				Optional
+					.ofNullable(p.getProgramme())
+					.map(
+						programme -> programme
+							.stream()
+							.map(pg -> Programme.newInstance(pg.getCode(), pg.getDescription()))
+							.collect(Collectors.toList()))
+					.orElse(new ArrayList<>()));
+
+		Optional<List<Field<String>>> ofundTree = Optional
+			.ofNullable(p.getFundingtree());
+		List<Funder> funList = new ArrayList<>();
+		if (ofundTree.isPresent()) {
+			for (Field<String> fundingtree : ofundTree.get()) {
+				funList.add(getFunder(fundingtree.getValue()));
+			}
+		}
+		project.setFunding(funList);
+
+		return project;
+	}
+
+	public static Funder getFunder(String fundingtree) throws DocumentException {
+		Funder f = new Funder();
+		final Document doc;
+
+		doc = new SAXReader().read(new StringReader(fundingtree));
+		f.setShortName(((org.dom4j.Node) (doc.selectNodes("//funder/shortname").get(0))).getText());
+		f.setName(((org.dom4j.Node) (doc.selectNodes("//funder/name").get(0))).getText());
+		f.setJurisdiction(((org.dom4j.Node) (doc.selectNodes("//funder/jurisdiction").get(0))).getText());
+		// f.setId(((org.dom4j.Node) (doc.selectNodes("//funder/id").get(0))).getText());
+
+		String id = "";
+		String description = "";
+		// List<Levels> fundings = new ArrayList<>();
+		int level = 0;
+		List<org.dom4j.Node> nodes = doc.selectNodes("//funding_level_" + level);
+		while (nodes.size() > 0) {
+			for (org.dom4j.Node n : nodes) {
+
+				List node = n.selectNodes("./id");
+				id = ((org.dom4j.Node) node.get(0)).getText();
+				id = id.substring(id.indexOf("::") + 2);
+
+				node = n.selectNodes("./description");
+				description += ((Node) node.get(0)).getText() + " - ";
+
+			}
+			level += 1;
+			nodes = doc.selectNodes("//funding_level_" + level);
+		}
+
+		if (!id.equals("")) {
+			Fundings fundings = new Fundings();
+			fundings.setId(id);
+			fundings.setDescription(description.substring(0, description.length() - 3).trim());
+			f.setFunding_stream(fundings);
+		}
+
+		return f;
+
+	}
+
+	private static <E extends OafEntity> void organizationMap(SparkSession spark, String inputPath, String outputPath,
+		Class<E> inputClazz) {
+		Utils
+			.readPath(spark, inputPath, inputClazz)
+			.map(o -> mapOrganization((eu.dnetlib.dhp.schema.oaf.Organization) o), Encoders.bean(Organization.class))
+			.write()
+			.mode(SaveMode.Overwrite)
+			.option("compression", "gzip")
+			.json(outputPath);
+	}
+
+	private static Organization mapOrganization(eu.dnetlib.dhp.schema.oaf.Organization org) {
+		Organization organization = new Organization();
+
+		Optional
+			.ofNullable(org.getLegalshortname())
+			.ifPresent(value -> organization.setLegalshortname(value.getValue()));
+
+		Optional
+			.ofNullable(org.getLegalname())
+			.ifPresent(value -> organization.setLegalname(value.getValue()));
+
+		Optional
+			.ofNullable(org.getWebsiteurl())
+			.ifPresent(value -> organization.setWebsiteurl(value.getValue()));
+
+		Optional
+			.ofNullable(org.getAlternativeNames())
+			.ifPresent(
+				value -> organization
+					.setAlternativenames(
+						value
+							.stream()
+							.map(v -> v.getValue())
+							.collect(Collectors.toList())));
+
+		Optional
+			.ofNullable(org.getCountry())
+			.ifPresent(
+				value -> organization.setCountry(Qualifier.newInstance(value.getClassid(), value.getClassname())));
+
+		Optional
+			.ofNullable(org.getId())
+			.ifPresent(value -> organization.setId(value));
+
+		Optional
+			.ofNullable(org.getPid())
+			.ifPresent(
+				value -> organization
+					.setPid(
+						value
+							.stream()
+							.map(p -> ControlledField.newInstance(p.getQualifier().getClassid(), p.getValue()))
+							.collect(Collectors.toList())));
+
+		return organization;
+	}
+}

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

@@ -0,0 +1,197 @@
+
+package eu.dnetlib.dhp.oa.graph.dump.graph;
+
+import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
+
+import java.io.Serializable;
+import java.util.*;
+
+import org.apache.spark.SparkConf;
+import org.apache.spark.api.java.function.FlatMapFunction;
+import org.apache.spark.sql.Encoders;
+import org.apache.spark.sql.SaveMode;
+import org.apache.spark.sql.SparkSession;
+
+import eu.dnetlib.dhp.oa.graph.dump.Utils;
+import eu.dnetlib.dhp.oa.graph.dump.community.CommunityMap;
+import eu.dnetlib.dhp.schema.common.ModelConstants;
+import eu.dnetlib.dhp.schema.dump.oaf.Provenance;
+import eu.dnetlib.dhp.schema.dump.oaf.graph.Node;
+import eu.dnetlib.dhp.schema.dump.oaf.graph.RelType;
+import eu.dnetlib.dhp.schema.dump.oaf.graph.Relation;
+import eu.dnetlib.dhp.schema.oaf.KeyValue;
+import eu.dnetlib.dhp.schema.oaf.Result;
+
+/**
+ * Creates new Relations (as in eu.dnetlib.dhp.schema.dump.oaf.graph.Relation) from the information in the Entity.
+ * The new Relations are created for the datasource in the collectedfrom and hostedby elements and for the context
+ * related to communities and research initiative/infrastructures.
+ *
+ * For collectedfrom elements it creates: datasource -> provides -> result and result -> isProvidedBy -> datasource
+ * For hostedby elements it creates: datasource -> hosts -> result and result -> isHostedBy -> datasource
+ * For context elements it creates: context <-> isRelatedTo <-> result
+ */
+public class Extractor implements Serializable {
+
+	public void run(Boolean isSparkSessionManaged,
+		String inputPath,
+		String outputPath,
+		Class<? extends Result> inputClazz,
+		String communityMapPath) {
+
+		SparkConf conf = new SparkConf();
+
+		runWithSparkSession(
+			conf,
+			isSparkSessionManaged,
+			spark -> {
+				Utils.removeOutputDir(spark, outputPath);
+				extractRelationResult(
+					spark, inputPath, outputPath, inputClazz, Utils.getCommunityMap(spark, communityMapPath));
+			});
+	}
+
+	private <R extends Result> void extractRelationResult(SparkSession spark,
+		String inputPath,
+		String outputPath,
+		Class<R> inputClazz,
+		CommunityMap communityMap) {
+
+		Set<Integer> hashCodes = new HashSet<>();
+
+		Utils
+			.readPath(spark, inputPath, inputClazz)
+			.flatMap((FlatMapFunction<R, Relation>) value -> {
+				List<Relation> relationList = new ArrayList<>();
+				Optional
+					.ofNullable(value.getInstance())
+					.ifPresent(inst -> inst.forEach(instance -> {
+						Optional
+							.ofNullable(instance.getCollectedfrom())
+							.ifPresent(
+								cf -> getRelatioPair(
+									value, relationList, cf,
+									ModelConstants.IS_PROVIDED_BY, ModelConstants.PROVIDES, hashCodes));
+						Optional
+							.ofNullable(instance.getHostedby())
+							.ifPresent(
+								hb -> getRelatioPair(
+									value, relationList, hb,
+									Constants.IS_HOSTED_BY, Constants.HOSTS, hashCodes));
+					}));
+				Set<String> communities = communityMap.keySet();
+				Optional
+					.ofNullable(value.getContext())
+					.ifPresent(contexts -> contexts.forEach(context -> {
+						String id = context.getId();
+						if (id.contains(":")) {
+							id = id.substring(0, id.indexOf(":"));
+						}
+						if (communities.contains(id)) {
+							String contextId = Utils.getContextId(id);
+							Provenance provenance = Optional
+								.ofNullable(context.getDataInfo())
+								.map(
+									dinfo -> Optional
+										.ofNullable(dinfo.get(0).getProvenanceaction())
+										.map(
+											paction -> Provenance
+												.newInstance(
+													paction.getClassid(),
+													dinfo.get(0).getTrust()))
+										.orElse(null))
+								.orElse(null);
+							Relation r = getRelation(
+								value.getId(), contextId,
+								Constants.RESULT_ENTITY,
+								Constants.CONTEXT_ENTITY,
+								ModelConstants.RELATIONSHIP, ModelConstants.IS_RELATED_TO, provenance);
+							if (!hashCodes.contains(r.hashCode())) {
+								relationList
+									.add(r);
+								hashCodes.add(r.hashCode());
+							}
+							r = getRelation(
+								contextId, value.getId(),
+								Constants.CONTEXT_ENTITY,
+								Constants.RESULT_ENTITY,
+								ModelConstants.RELATIONSHIP,
+								ModelConstants.IS_RELATED_TO, provenance);
+							if (!hashCodes.contains(r.hashCode())) {
+								relationList
+									.add(
+										r);
+								hashCodes.add(r.hashCode());
+							}
+
+						}
+
+					}));
+
+				return relationList.iterator();
+			}, Encoders.bean(Relation.class))
+			.write()
+			.option("compression", "gzip")
+			.mode(SaveMode.Overwrite)
+			.json(outputPath);
+
+	}
+
+	private static <R extends Result> void getRelatioPair(R value, List<Relation> relationList, KeyValue cf,
+		String result_dtasource, String datasource_result,
+		Set<Integer> hashCodes) {
+		Provenance provenance = Optional
+			.ofNullable(cf.getDataInfo())
+			.map(
+				dinfo -> Optional
+					.ofNullable(dinfo.getProvenanceaction())
+					.map(
+						paction -> Provenance
+							.newInstance(
+								paction.getClassid(),
+								dinfo.getTrust()))
+					.orElse(
+						Provenance
+							.newInstance(
+								eu.dnetlib.dhp.oa.graph.dump.Constants.HARVESTED,
+								eu.dnetlib.dhp.oa.graph.dump.Constants.DEFAULT_TRUST)))
+			.orElse(
+				Provenance
+					.newInstance(
+						eu.dnetlib.dhp.oa.graph.dump.Constants.HARVESTED,
+						eu.dnetlib.dhp.oa.graph.dump.Constants.DEFAULT_TRUST));
+		Relation r = getRelation(
+			value.getId(),
+			cf.getKey(), Constants.RESULT_ENTITY, Constants.DATASOURCE_ENTITY,
+			result_dtasource, ModelConstants.PROVISION,
+			provenance);
+		if (!hashCodes.contains(r.hashCode())) {
+			relationList
+				.add(r);
+			hashCodes.add(r.hashCode());
+		}
+
+		r = getRelation(
+			cf.getKey(), value.getId(),
+			Constants.DATASOURCE_ENTITY, Constants.RESULT_ENTITY,
+			datasource_result, ModelConstants.PROVISION,
+			provenance);
+
+		if (!hashCodes.contains(r.hashCode())) {
+			relationList
+				.add(r);
+			hashCodes.add(r.hashCode());
+		}
+
+	}
+
+	private static Relation getRelation(String source, String target, String sourceType, String targetType,
+		String relName, String relType, Provenance provenance) {
+		Relation r = new Relation();
+		r.setSource(Node.newInstance(source, sourceType));
+		r.setTarget(Node.newInstance(target, targetType));
+		r.setReltype(RelType.newInstance(relName, relType));
+		r.setProvenance(provenance);
+		return r;
+	}
+}

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

@@ -0,0 +1,25 @@
+
+package eu.dnetlib.dhp.oa.graph.dump.graph;
+
+import java.io.Serializable;
+
+public class MergedRels implements Serializable {
+	private String organizationId;
+	private String representativeId;
+
+	public String getOrganizationId() {
+		return organizationId;
+	}
+
+	public void setOrganizationId(String organizationId) {
+		this.organizationId = organizationId;
+	}
+
+	public String getRepresentativeId() {
+		return representativeId;
+	}
+
+	public void setRepresentativeId(String representativeId) {
+		this.representativeId = representativeId;
+	}
+}

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

@@ -0,0 +1,21 @@
+
+package eu.dnetlib.dhp.oa.graph.dump.graph;
+
+import java.util.ArrayList;
+import java.util.HashMap;
+import java.util.List;
+
+public class OrganizationMap extends HashMap<String, List<String>> {
+
+	public OrganizationMap() {
+		super();
+	}
+
+	public List<String> get(String key) {
+
+		if (super.get(key) == null) {
+			return new ArrayList<>();
+		}
+		return super.get(key);
+	}
+}

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

@@ -0,0 +1,98 @@
+
+package eu.dnetlib.dhp.oa.graph.dump.graph;
+
+import java.io.Serializable;
+import java.util.ArrayList;
+import java.util.List;
+
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import eu.dnetlib.dhp.oa.graph.dump.Constants;
+import eu.dnetlib.dhp.oa.graph.dump.Utils;
+import eu.dnetlib.dhp.schema.common.ModelConstants;
+import eu.dnetlib.dhp.schema.common.ModelSupport;
+import eu.dnetlib.dhp.schema.dump.oaf.Provenance;
+import eu.dnetlib.dhp.schema.dump.oaf.graph.*;
+
+/**
+ * It process the ContextInfo information to produce a new Context Entity or a set of Relations between the
+ * generic context entity and datasource/projects related to the context.
+ *
+ */
+public class Process implements Serializable {
+	private static final Logger log = LoggerFactory.getLogger(Process.class);
+
+	public static <R extends ResearchInitiative> R getEntity(ContextInfo ci) {
+		try {
+			ResearchInitiative ri;
+			if (ci.getType().equals("community")) {
+				ri = new ResearchCommunity();
+				((ResearchCommunity) ri).setSubject(ci.getSubject());
+				ri.setType(Constants.RESEARCH_COMMUNITY);
+			} else {
+				ri = new ResearchInitiative();
+				ri.setType(Constants.RESEARCH_INFRASTRUCTURE);
+			}
+			ri.setId(Utils.getContextId(ci.getId()));
+			ri.setOriginalId(ci.getId());
+
+			ri.setDescription(ci.getDescription());
+			ri.setName(ci.getName());
+			ri.setZenodo_community(Constants.ZENODO_COMMUNITY_PREFIX + ci.getZenodocommunity());
+			return (R) ri;
+
+		} catch (final Exception e) {
+			throw new RuntimeException(e);
+		}
+	}
+
+	public static List<Relation> getRelation(ContextInfo ci) {
+		try {
+
+			List<Relation> relationList = new ArrayList<>();
+			ci
+				.getDatasourceList()
+				.forEach(ds -> {
+
+					String nodeType = ModelSupport.idPrefixEntity.get(ds.substring(0, 2));
+
+					String contextId = Utils.getContextId(ci.getId());
+					relationList
+						.add(
+							Relation
+								.newInstance(
+									Node
+										.newInstance(
+											contextId, eu.dnetlib.dhp.schema.dump.oaf.graph.Constants.CONTEXT_ENTITY),
+									Node.newInstance(ds, nodeType),
+									RelType.newInstance(ModelConstants.IS_RELATED_TO, ModelConstants.RELATIONSHIP),
+									Provenance
+										.newInstance(
+											Constants.USER_CLAIM,
+											Constants.DEFAULT_TRUST)));
+
+					relationList
+						.add(
+							Relation
+								.newInstance(
+									Node.newInstance(ds, nodeType),
+									Node
+										.newInstance(
+											contextId, eu.dnetlib.dhp.schema.dump.oaf.graph.Constants.CONTEXT_ENTITY),
+									RelType.newInstance(ModelConstants.IS_RELATED_TO, ModelConstants.RELATIONSHIP),
+									Provenance
+										.newInstance(
+											Constants.USER_CLAIM,
+											Constants.DEFAULT_TRUST)));
+
+				});
+
+			return relationList;
+
+		} catch (final Exception e) {
+			throw new RuntimeException(e);
+		}
+	}
+
+}

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

@@ -0,0 +1,132 @@
+
+package eu.dnetlib.dhp.oa.graph.dump.graph;
+
+import java.io.StringReader;
+import java.sql.ResultSet;
+import java.sql.SQLException;
+import java.sql.Statement;
+import java.util.*;
+import java.util.function.Consumer;
+import java.util.stream.Collectors;
+
+import org.dom4j.Document;
+import org.dom4j.DocumentException;
+import org.dom4j.Element;
+import org.dom4j.Node;
+import org.dom4j.io.SAXReader;
+import org.jetbrains.annotations.NotNull;
+
+import eu.dnetlib.dhp.schema.common.ModelSupport;
+import eu.dnetlib.dhp.schema.dump.oaf.graph.ResearchInitiative;
+import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpException;
+import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
+
+public class QueryInformationSystem {
+
+	private ISLookUpService isLookUp;
+	private List<String> contextRelationResult;
+
+	private static final String XQUERY = "for $x in collection('/db/DRIVER/ContextDSResources/ContextDSResourceType') "
+		+
+		"  where $x//CONFIGURATION/context[./@type='community' or ./@type='ri'] " +
+		" and $x//context/param[./@name = 'status']/text() = 'all' " +
+		"  return " +
+		"$x//context";
+
+	private static final String XQUERY_ENTITY = "for $x in collection('/db/DRIVER/ContextDSResources/ContextDSResourceType') "
+		+
+		"where $x//context[./@type='community' or ./@type = 'ri'] and $x//context/param[./@name = 'status']/text() = 'all' return "
+		+
+		"concat(data($x//context/@id) , '@@', $x//context/param[./@name =\"name\"]/text(), '@@', " +
+		"$x//context/param[./@name=\"description\"]/text(), '@@', $x//context/param[./@name = \"subject\"]/text(), '@@', "
+		+
+		"$x//context/param[./@name = \"zenodoCommunity\"]/text(), '@@', $x//context/@type)";
+
+	public void getContextInformation(final Consumer<ContextInfo> consumer) throws ISLookUpException {
+
+		isLookUp
+			.quickSearchProfile(XQUERY_ENTITY)
+			.forEach(c -> {
+				ContextInfo cinfo = new ContextInfo();
+				String[] cSplit = c.split("@@");
+				cinfo.setId(cSplit[0]);
+				cinfo.setName(cSplit[1]);
+				cinfo.setDescription(cSplit[2]);
+				if (!cSplit[3].trim().equals("")) {
+					cinfo.setSubject(Arrays.asList(cSplit[3].split(",")));
+				}
+				cinfo.setZenodocommunity(cSplit[4]);
+				cinfo.setType(cSplit[5]);
+				consumer.accept(cinfo);
+			});
+
+	}
+
+	public List<String> getContextRelationResult() {
+		return contextRelationResult;
+	}
+
+	public void setContextRelationResult(List<String> contextRelationResult) {
+		this.contextRelationResult = contextRelationResult;
+	}
+
+	public ISLookUpService getIsLookUp() {
+		return isLookUp;
+	}
+
+	public void setIsLookUp(ISLookUpService isLookUpService) {
+		this.isLookUp = isLookUpService;
+	}
+
+	public void execContextRelationQuery() throws ISLookUpException {
+		contextRelationResult = isLookUp.quickSearchProfile(XQUERY);
+
+	}
+
+	public void getContextRelation(final Consumer<ContextInfo> consumer, String category, String prefix) {
+
+		contextRelationResult.forEach(xml -> {
+			ContextInfo cinfo = new ContextInfo();
+			final Document doc;
+
+			try {
+
+				doc = new SAXReader().read(new StringReader(xml));
+				Element root = doc.getRootElement();
+				cinfo.setId(root.attributeValue("id"));
+
+				Iterator it = root.elementIterator();
+				while (it.hasNext()) {
+					Element el = (Element) it.next();
+					if (el.getName().equals("category")) {
+						String categoryId = el.attributeValue("id");
+						categoryId = categoryId.substring(categoryId.lastIndexOf("::") + 2);
+						if (categoryId.equals(category)) {
+							cinfo.setDatasourceList(getCategoryList(el, prefix));
+						}
+					}
+
+				}
+				consumer.accept(cinfo);
+			} catch (DocumentException e) {
+				e.printStackTrace();
+			}
+
+		});
+
+	}
+
+	@NotNull
+	private List<String> getCategoryList(Element el, String prefix) {
+		List<String> datasourceList = new ArrayList<>();
+		for (Object node : el.selectNodes(".//param")) {
+			Node n = (Node) node;
+			if (n.valueOf("./@name").equals("openaireId")) {
+				datasourceList.add(prefix + "|" + n.getText());
+			}
+		}
+
+		return datasourceList;
+	}
+
+}

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

@@ -0,0 +1,89 @@
+
+package eu.dnetlib.dhp.oa.graph.dump.graph;
+
+import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
+
+import java.io.Serializable;
+import java.util.Optional;
+
+import org.apache.commons.io.IOUtils;
+import org.apache.spark.SparkConf;
+import org.apache.spark.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.Result;
+import eu.dnetlib.dhp.schema.dump.oaf.graph.Relation;
+
+/**
+ * Reads all the entities of the same type (Relation / Results) and saves them in the same folder
+ *
+ */
+public class SparkCollectAndSave implements Serializable {
+
+	private static final Logger log = LoggerFactory.getLogger(SparkCollectAndSave.class);
+
+	public static void main(String[] args) throws Exception {
+		String jsonConfiguration = IOUtils
+			.toString(
+				SparkCollectAndSave.class
+					.getResourceAsStream(
+						"/eu/dnetlib/dhp/oa/graph/dump_whole/input_collect_and_save.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);
+
+		SparkConf conf = new SparkConf();
+
+		runWithSparkSession(
+			conf,
+			isSparkSessionManaged,
+			spark -> {
+				Utils.removeOutputDir(spark, outputPath + "/result");
+				run(spark, inputPath, outputPath);
+
+			});
+
+	}
+
+	private static void run(SparkSession spark, String inputPath, String outputPath) {
+		Utils
+			.readPath(spark, inputPath + "/result/publication", Result.class)
+			.union(Utils.readPath(spark, inputPath + "/result/dataset", Result.class))
+			.union(Utils.readPath(spark, inputPath + "/result/otherresearchproduct", Result.class))
+			.union(Utils.readPath(spark, inputPath + "/result/software", Result.class))
+			.write()
+			.option("compression", "gzip")
+			.mode(SaveMode.Overwrite)
+			.json(outputPath + "/result");
+
+		Utils
+			.readPath(spark, inputPath + "/relation/publication", Relation.class)
+			.union(Utils.readPath(spark, inputPath + "/relation/dataset", Relation.class))
+			.union(Utils.readPath(spark, inputPath + "/relation/orp", Relation.class))
+			.union(Utils.readPath(spark, inputPath + "/relation/software", Relation.class))
+			.union(Utils.readPath(spark, inputPath + "/relation/contextOrg", Relation.class))
+			.union(Utils.readPath(spark, inputPath + "/relation/context", Relation.class))
+			.union(Utils.readPath(spark, inputPath + "/relation/relation", Relation.class))
+			.write()
+			.mode(SaveMode.Overwrite)
+			.option("compression", "gzip")
+			.json(outputPath + "/relation");
+
+	}
+}

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

@@ -0,0 +1,54 @@
+
+package eu.dnetlib.dhp.oa.graph.dump.graph;
+
+import java.io.Serializable;
+import java.util.Optional;
+
+import org.apache.commons.io.IOUtils;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import eu.dnetlib.dhp.application.ArgumentApplicationParser;
+import eu.dnetlib.dhp.schema.oaf.OafEntity;
+
+/**
+ * Spark Job that fires the dump for the entites
+ */
+public class SparkDumpEntitiesJob implements Serializable {
+	private static final Logger log = LoggerFactory.getLogger(SparkDumpEntitiesJob.class);
+
+	public static void main(String[] args) throws Exception {
+		String jsonConfiguration = IOUtils
+			.toString(
+				SparkDumpEntitiesJob.class
+					.getResourceAsStream(
+						"/eu/dnetlib/dhp/oa/graph/dump_whole/input_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 resultClassName = parser.get("resultTableName");
+		log.info("resultTableName: {}", resultClassName);
+
+		final String communityMapPath = parser.get("communityMapPath");
+
+		Class<? extends OafEntity> inputClazz = (Class<? extends OafEntity>) Class.forName(resultClassName);
+
+		DumpGraphEntities dg = new DumpGraphEntities();
+		dg.run(isSparkSessionManaged, inputPath, outputPath, inputClazz, communityMapPath);
+
+	}
+
+}

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

@@ -0,0 +1,111 @@
+
+package eu.dnetlib.dhp.oa.graph.dump.graph;
+
+import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
+
+import java.io.Serializable;
+import java.util.Optional;
+
+import org.apache.commons.io.IOUtils;
+import org.apache.spark.SparkConf;
+import org.apache.spark.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.common.ModelSupport;
+import eu.dnetlib.dhp.schema.dump.oaf.Provenance;
+import eu.dnetlib.dhp.schema.dump.oaf.graph.Node;
+import eu.dnetlib.dhp.schema.dump.oaf.graph.RelType;
+import eu.dnetlib.dhp.schema.oaf.Relation;
+
+/**
+ * Dumps eu.dnetlib.dhp.schema.oaf.Relation in eu.dnetlib.dhp.schema.dump.oaf.graph.Relation
+ */
+public class SparkDumpRelationJob implements Serializable {
+
+	private static final Logger log = LoggerFactory.getLogger(SparkDumpRelationJob.class);
+
+	public static void main(String[] args) throws Exception {
+		String jsonConfiguration = IOUtils
+			.toString(
+				SparkDumpRelationJob.class
+					.getResourceAsStream(
+						"/eu/dnetlib/dhp/oa/graph/dump_whole/input_relationdump_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);
+
+		SparkConf conf = new SparkConf();
+
+		runWithSparkSession(
+			conf,
+			isSparkSessionManaged,
+			spark -> {
+				Utils.removeOutputDir(spark, outputPath);
+				dumpRelation(spark, inputPath, outputPath);
+
+			});
+
+	}
+
+	private static void dumpRelation(SparkSession spark, String inputPath, String outputPath) {
+		Utils
+			.readPath(spark, inputPath, Relation.class)
+			.map(relation -> {
+				eu.dnetlib.dhp.schema.dump.oaf.graph.Relation rel = new eu.dnetlib.dhp.schema.dump.oaf.graph.Relation();
+				rel
+					.setSource(
+						Node
+							.newInstance(
+								relation.getSource(),
+								ModelSupport.idPrefixEntity.get(relation.getSource().substring(0, 2))));
+
+				rel
+					.setTarget(
+						Node
+							.newInstance(
+								relation.getTarget(),
+								ModelSupport.idPrefixEntity.get(relation.getTarget().substring(0, 2))));
+
+				rel
+					.setReltype(
+						RelType
+							.newInstance(
+								relation.getRelClass(),
+								relation.getSubRelType()));
+
+				Optional
+					.ofNullable(relation.getDataInfo())
+					.ifPresent(
+						datainfo -> rel
+							.setProvenance(
+								Provenance
+									.newInstance(datainfo.getProvenanceaction().getClassname(), datainfo.getTrust())));
+
+				return rel;
+
+			}, Encoders.bean(eu.dnetlib.dhp.schema.dump.oaf.graph.Relation.class))
+			.write()
+			.option("compression", "gzip")
+			.mode(SaveMode.Overwrite)
+			.json(outputPath);
+
+	}
+
+}

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

@@ -0,0 +1,57 @@
+
+package eu.dnetlib.dhp.oa.graph.dump.graph;
+
+import java.io.Serializable;
+import java.util.*;
+
+import org.apache.commons.io.IOUtils;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import eu.dnetlib.dhp.application.ArgumentApplicationParser;
+import eu.dnetlib.dhp.oa.graph.dump.QueryInformationSystem;
+import eu.dnetlib.dhp.oa.graph.dump.Utils;
+import eu.dnetlib.dhp.oa.graph.dump.community.CommunityMap;
+import eu.dnetlib.dhp.schema.oaf.Result;
+
+/**
+ * Spark job that fires the extraction of relations from entities
+ */
+public class SparkExtractRelationFromEntities implements Serializable {
+	private static final Logger log = LoggerFactory.getLogger(SparkExtractRelationFromEntities.class);
+
+	public static void main(String[] args) throws Exception {
+		String jsonConfiguration = IOUtils
+			.toString(
+				SparkExtractRelationFromEntities.class
+					.getResourceAsStream(
+						"/eu/dnetlib/dhp/oa/graph/dump/input_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 resultClassName = parser.get("resultTableName");
+		log.info("resultTableName: {}", resultClassName);
+
+		final String communityMapPath = parser.get("communityMapPath");
+
+		Class<? extends Result> inputClazz = (Class<? extends Result>) Class.forName(resultClassName);
+
+		Extractor extractor = new Extractor();
+		extractor.run(isSparkSessionManaged, inputPath, outputPath, inputClazz, communityMapPath);
+
+	}
+
+}

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

@@ -0,0 +1,161 @@
+
+
+package eu.dnetlib.dhp.oa.graph.dump.graph;
+
+import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
+
+import java.io.Serializable;
+import java.util.*;
+import java.util.function.Consumer;
+
+import org.apache.commons.io.IOUtils;
+import org.apache.spark.SparkConf;
+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 com.google.gson.Gson;
+
+import eu.dnetlib.dhp.application.ArgumentApplicationParser;
+import eu.dnetlib.dhp.oa.graph.dump.Utils;
+import eu.dnetlib.dhp.schema.common.ModelConstants;
+import eu.dnetlib.dhp.schema.common.ModelSupport;
+import eu.dnetlib.dhp.schema.dump.oaf.Provenance;
+import eu.dnetlib.dhp.schema.dump.oaf.graph.Node;
+import eu.dnetlib.dhp.schema.dump.oaf.graph.RelType;
+import eu.dnetlib.dhp.schema.oaf.Relation;
+
+/**
+ * Create new Relations between Context Entities and Organizations whose products are associated to the context.
+ * It produces relation such as: organization <-> isRelatedTo <-> context
+ */
+public class SparkOrganizationRelation implements Serializable {
+	private static final Logger log = LoggerFactory.getLogger(SparkOrganizationRelation.class);
+
+	public static void main(String[] args) throws Exception {
+		String jsonConfiguration = IOUtils
+			.toString(
+				SparkOrganizationRelation.class
+					.getResourceAsStream(
+						"/eu/dnetlib/dhp/oa/graph/dump_whole/input_organization_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 OrganizationMap organizationMap = new Gson()
+			.fromJson(parser.get("organizationCommunityMap"), OrganizationMap.class);
+		log.info("organization map : {}", new Gson().toJson(organizationMap));
+
+		SparkConf conf = new SparkConf();
+
+		runWithSparkSession(
+			conf,
+			isSparkSessionManaged,
+			spark -> {
+				Utils.removeOutputDir(spark, outputPath);
+				extractRelation(spark, inputPath, organizationMap, outputPath);
+
+			});
+
+	}
+
+	private static void extractRelation(SparkSession spark, String inputPath, OrganizationMap organizationMap,
+		String outputPath) {
+		Dataset<Relation> relationDataset = Utils.readPath(spark, inputPath, Relation.class);
+
+		relationDataset.createOrReplaceTempView("relation");
+
+		List<eu.dnetlib.dhp.schema.dump.oaf.graph.Relation> relList = new ArrayList<>();
+
+		Dataset<MergedRels> mergedRelsDataset = spark
+			.sql(
+				"SELECT target organizationId, source representativeId " +
+					"FROM relation " +
+					"WHERE datainfo.deletedbyinference = false " +
+					"AND relclass = 'merges' " +
+					"AND substr(source, 1, 2) = '20'")
+			.as(Encoders.bean(MergedRels.class));
+
+		mergedRelsDataset.map((MapFunction<MergedRels, MergedRels>) mergedRels -> {
+			if (organizationMap.containsKey(mergedRels.getOrganizationId())) {
+				return mergedRels;
+			}
+			return null;
+		}, Encoders.bean(MergedRels.class))
+			.filter(Objects::nonNull)
+			.collectAsList()
+			.forEach(getMergedRelsConsumer(organizationMap, relList));
+
+		organizationMap
+			.keySet()
+			.forEach(
+				oId -> organizationMap
+					.get(oId)
+					.forEach(community -> addRelations(relList, community, oId)));
+
+		spark
+			.createDataset(relList, Encoders.bean(eu.dnetlib.dhp.schema.dump.oaf.graph.Relation.class))
+			.write()
+			.mode(SaveMode.Overwrite)
+			.option("compression", "gzip")
+			.json(outputPath);
+
+	}
+
+	@NotNull
+	private static Consumer<MergedRels> getMergedRelsConsumer(OrganizationMap organizationMap,
+		List<eu.dnetlib.dhp.schema.dump.oaf.graph.Relation> relList) {
+		return mergedRels -> {
+			String oId = mergedRels.getOrganizationId();
+			organizationMap
+				.get(oId)
+				.forEach(community -> addRelations(relList, community, mergedRels.getRepresentativeId()));
+			organizationMap.remove(oId);
+		};
+	}
+
+	private static void addRelations(List<eu.dnetlib.dhp.schema.dump.oaf.graph.Relation> relList, String community,
+		String organization) {
+
+		String id = Utils.getContextId(community);
+		log.info("create relation for organization: {}", organization);
+		relList
+			.add(
+				eu.dnetlib.dhp.schema.dump.oaf.graph.Relation
+					.newInstance(
+						Node.newInstance(id, Constants.CONTEXT_ENTITY),
+						Node.newInstance(organization, ModelSupport.idPrefixEntity.get(organization.substring(0, 2))),
+						RelType.newInstance(ModelConstants.IS_RELATED_TO, ModelConstants.RELATIONSHIP),
+						Provenance
+							.newInstance(
+								eu.dnetlib.dhp.oa.graph.dump.Constants.USER_CLAIM,
+								eu.dnetlib.dhp.oa.graph.dump.Constants.DEFAULT_TRUST)));
+
+		relList
+			.add(
+				eu.dnetlib.dhp.schema.dump.oaf.graph.Relation
+					.newInstance(
+						Node.newInstance(organization, ModelSupport.idPrefixEntity.get(organization.substring(0, 2))),
+						Node.newInstance(id, Constants.CONTEXT_ENTITY),
+						RelType.newInstance(ModelConstants.IS_RELATED_TO, ModelConstants.RELATIONSHIP),
+						Provenance
+							.newInstance(
+								eu.dnetlib.dhp.oa.graph.dump.Constants.USER_CLAIM,
+								eu.dnetlib.dhp.oa.graph.dump.Constants.DEFAULT_TRUST)));
+	}
+
+}

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

@@ -0,0 +1,25 @@
+
+[
+
+	{
+		"paramName":"is",
+		"paramLongName":"isLookUpUrl",
+		"paramDescription": "URL of the isLookUp Service",
+		"paramRequired": true
+	},
+	{
+		"paramName":"nn",
+		"paramLongName":"nameNode",
+		"paramDescription": "the name node",
+		"paramRequired": true
+	},
+	{
+		"paramName": "out",
+		"paramLongName": "outputPath",
+		"paramDescription": "the path used to store temporary output files",
+		"paramRequired": true
+	}
+]
+
+
+

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

@@ -0,0 +1,24 @@
+[
+
+	{
+		"paramName":"s",
+		"paramLongName":"sourcePath",
+		"paramDescription": "the path of the sequencial file to read",
+		"paramRequired": true
+	},
+	{
+		"paramName": "hdp",
+		"paramLongName": "hdfsPath",
+		"paramDescription": "the path used to store the output archive",
+		"paramRequired": true
+	},
+	{
+		"paramName":"nn",
+		"paramLongName":"nameNode",
+		"paramDescription": "the name node",
+		"paramRequired": true
+	}
+]
+
+
+

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

@@ -0,0 +1,36 @@
+[
+
+	{
+		"paramName":"cmp",
+		"paramLongName":"communityMapPath",
+		"paramDescription": "the path to the serialization of the community map",
+		"paramRequired": true
+	},
+	{
+		"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":"tn",
+		"paramLongName":"resultTableName",
+		"paramDescription": "the name of the result table we are currently working on",
+		"paramRequired": true
+	}
+]
+
+
+

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

@@ -0,0 +1,30 @@
+<configuration>
+    <property>
+        <name>jobTracker</name>
+        <value>yarnRM</value>
+    </property>
+    <property>
+        <name>nameNode</name>
+        <value>hdfs://nameservice1</value>
+    </property>
+    <property>
+        <name>oozie.use.system.libpath</name>
+        <value>true</value>
+    </property>
+    <property>
+        <name>hiveMetastoreUris</name>
+        <value>thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083</value>
+    </property>
+    <property>
+        <name>hiveJdbcUrl</name>
+        <value>jdbc:hive2://iis-cdh5-test-m3.ocean.icm.edu.pl:10000</value>
+    </property>
+    <property>
+        <name>hiveDbName</name>
+        <value>openaire</value>
+    </property>
+    <property>
+        <name>oozie.launcher.mapreduce.user.classpath.first</name>
+        <value>true</value>
+    </property>
+</configuration>

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

@@ -0,0 +1,431 @@
+<workflow-app name="dump_community_products" xmlns="uri:oozie:workflow:0.5">
+
+    <parameters>
+            <property>
+                <name>sourcePath</name>
+                <description>the source path</description>
+            </property>
+            <property>
+                <name>isLookUpUrl</name>
+                <description>the isLookup service endpoint</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>newDeposition</name>
+            <description>true if it is a brand new depositon. false for new version of an old deposition</description>
+        </property>
+        <property>
+            <name>conceptRecordId</name>
+            <description>for new version, the id of the record for the old deposition</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>${oozieActionShareLibForSpark2}</value>
+            </property>
+
+        </configuration>
+    </global>
+
+    <start to="reset_outputpath"/>
+
+    <kill name="Kill">
+        <message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
+    </kill>
+
+    <action name="reset_outputpath">
+        <fs>
+            <delete path="${outputPath}"/>
+            <mkdir path="${outputPath}"/>
+        </fs>
+        <ok to="save_community_map"/>
+        <error to="Kill"/>
+    </action>
+
+    <action name="save_community_map">
+        <java>
+            <main-class>eu.dnetlib.dhp.oa.graph.dump.SaveCommunityMap</main-class>
+            <arg>--outputPath</arg><arg>${workingDir}/communityMap</arg>
+            <arg>--nameNode</arg><arg>${nameNode}</arg>
+            <arg>--isLookUpUrl</arg><arg>${isLookUpUrl}</arg>
+        </java>
+        <ok to="fork_dump"/>
+        <error to="Kill"/>
+    </action>
+
+    <fork name="fork_dump">
+        <path start="dump_publication"/>
+        <path start="dump_dataset"/>
+        <path start="dump_orp"/>
+        <path start="dump_software"/>
+    </fork>
+
+    <action name="dump_publication">
+        <spark xmlns="uri:oozie:spark-action:0.2">
+            <master>yarn</master>
+            <mode>cluster</mode>
+            <name>Dump table publication for community related products</name>
+            <class>eu.dnetlib.dhp.oa.graph.dump.community.SparkDumpCommunityProducts</class>
+            <jar>dhp-graph-mapper-${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}/publication</arg>
+            <arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
+            <arg>--outputPath</arg><arg>${workingDir}/publication</arg>
+            <arg>--communityMapPath</arg><arg>${workingDir}/communityMap</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 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}/dataset</arg>
+            <arg>--communityMapPath</arg><arg>${workingDir}/communityMap</arg>
+        </spark>
+        <ok to="join_dump"/>
+        <error to="Kill"/>
+    </action>
+
+    <action name="dump_orp">
+        <spark xmlns="uri:oozie:spark-action:0.2">
+            <master>yarn</master>
+            <mode>cluster</mode>
+            <name>Dump table ORP for community related products</name>
+            <class>eu.dnetlib.dhp.oa.graph.dump.community.SparkDumpCommunityProducts</class>
+            <jar>dhp-graph-mapper-${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>${workingDir}/otherresearchproduct</arg>
+            <arg>--communityMapPath</arg><arg>${workingDir}/communityMap</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}/software</arg>
+            <arg>--communityMapPath</arg><arg>${workingDir}/communityMap</arg>
+        </spark>
+        <ok to="join_dump"/>
+        <error to="Kill"/>
+    </action>
+
+    <join name="join_dump" to="prepareResultProject"/>
+
+    <action name="prepareResultProject">
+        <spark xmlns="uri:oozie:spark-action:0.2">
+            <master>yarn</master>
+            <mode>cluster</mode>
+            <name>Prepare association result subset of project info</name>
+            <class>eu.dnetlib.dhp.oa.graph.dump.community.SparkPrepareResultProject</class>
+            <jar>dhp-graph-mapper-${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}/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>${workingDir}/dataset</arg>
+            <arg>--outputPath</arg><arg>${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}/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>${workingDir}/software</arg>
+            <arg>--outputPath</arg><arg>${workingDir}/ext/software</arg>
+            <arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo</arg>
+        </spark>
+        <ok to="join_extend"/>
+        <error to="Kill"/>
+    </action>
+
+    <join name="join_extend" to="splitForCommunities"/>
+
+        <action name="splitForCommunities">
+            <spark xmlns="uri:oozie:spark-action:0.2">
+                <master>yarn</master>
+                <mode>cluster</mode>
+                <name>Split dumped result for community</name>
+                <class>eu.dnetlib.dhp.oa.graph.dump.community.SparkSplitForCommunity</class>
+                <jar>dhp-graph-mapper-${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}/ext</arg>
+                <arg>--outputPath</arg><arg>${workingDir}/split</arg>
+                <arg>--communityMapPath</arg><arg>${workingDir}/communityMap</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>${workingDir}/split</arg>
+        </java>
+        <ok to="send_zenodo"/>
+        <error to="Kill"/>
+    </action>
+
+
+    <action name="send_zenodo">
+        <java>
+            <main-class>eu.dnetlib.dhp.oa.graph.dump.SendToZenodoHDFS</main-class>
+            <arg>--hdfsPath</arg><arg>${outputPath}</arg>
+            <arg>--hdfsNameNode</arg><arg>${nameNode}</arg>
+            <arg>--accessToken</arg><arg>${accessToken}</arg>
+            <arg>--connectionUrl</arg><arg>${connectionUrl}</arg>
+            <arg>--metadata</arg><arg>${metadata}</arg>
+            <arg>--communityMapPath</arg><arg>${workingDir}/communityMap</arg>
+            <arg>--conceptRecordId</arg><arg>${conceptRecordId}</arg>
+            <arg>--newDeposition</arg><arg>${newDeposition}</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/project_input_parameters.json

@@ -0,0 +1,29 @@
+[
+
+	{
+		"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": "pip",
+		"paramLongName": "preparedInfoPath",
+		"paramDescription": "the path of the association result projectlist",
+		"paramRequired": true
+	}
+]
+
+

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

@@ -0,0 +1,542 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "definitions": {
+    "AccessRight": {
+      "type": "object",
+      "properties": {
+        "code": {
+          "type": "string",
+          "description": "COAR access mode code: http://vocabularies.coar-repositories.org/documentation/access_rights/"
+        },
+        "label": {
+          "type": "string",
+          "description": "Label for the access mode"
+        },
+        "scheme": {
+          "type": "string",
+          "description": "Scheme of reference for access right code. Always set to COAR access rights vocabulary: http://vocabularies.coar-repositories.org/documentation/access_rights/"
+        }
+      }
+    },
+    "ControlledField": {
+      "type": "object",
+      "properties": {
+        "scheme": {
+          "type": "string",
+          "description": "The scheme for the resource"
+        },
+        "value": {
+          "type": "string",
+          "description": "the value in the scheme"
+        }
+      }
+    },
+    "KeyValue": {
+      "type": "object",
+      "properties": {
+        "key": {
+          "type": "string",
+          "description": "Description of key"
+        },
+        "value": {
+          "type": "string",
+          "description": "Description of value"
+        }
+      }
+    },
+    "Provenance": {
+      "type": "object",
+      "properties": {
+        "provenance": {
+          "type": "string",
+          "description": "The provenance of the information"
+        },
+        "trust": {
+          "type": "string",
+          "description": "The trust associated to the information"
+        }
+      }
+    }
+  },
+  "type": "object",
+  "properties": {
+    "author": {
+      "description": "List of authors of the research results",
+      "type": "array",
+      "items": {
+        "type": "object",
+        "properties": {
+          "affiliation": {
+            "description": "Affiliations of the author",
+            "type": "array",
+            "items": {
+              "type": "string",
+              "description": "One of the affiliation of the author"
+            }
+          },
+          "fullname": {
+            "type": "string",
+            "description": "Fullname of the author"
+          },
+          "name": {
+            "type": "string",
+            "description": "First name of the author"
+          },
+          "pid": {
+            "type": "object",
+            "properties": {
+              "id": {
+                "allOf": [
+                  {"$ref": "#/definitions/ControlledField"},
+                  {"description": "The author's id and scheme. OpenAIRE currently supports 'ORCID'"}
+                ]
+              },
+              "provenance": {
+                "allOf": [
+                  {"$ref": "#/definitions/Provenance"},
+                  {"description": "The provenance of the author's pid"}
+                ]
+              }
+            },
+            "description": "Persistent identifier of the author (e.g. ORCID)"
+          },
+          "rank": {
+            "type": "integer",
+            "description": "Order in which the author appears in the authors list"
+          },
+          "surname": {
+            "type": "string",
+            "description": "Surname of the author"
+          }
+        },
+        "description": "One of the author of the research result"
+      }
+    },
+    "bestaccessright": {
+      "allOf": [
+        {"$ref": "#/definitions/AccessRight"},
+        {"description": "The openest access right associated to the manifestations of this research results"}
+      ]
+    },
+    "codeRepositoryUrl": {
+      "type": "string",
+      "description": "Only for results with type 'software': the URL to the repository with the source code"
+    },
+    "collectedfrom": {
+      "description": "Information about the sources from which the record has been collected",
+      "type": "array",
+      "items": {
+        "allOf": [
+          {"$ref": "#/definitions/KeyValue"},
+          {"description": "Key is the OpenAIRE identifier of the data source, value is its name"}
+        ]
+      }
+    },
+    "contactgroup": {
+      "description": "Only for results with type 'software': Information on the group responsible for providing further information regarding the resource",
+      "type": "array",
+      "items": {
+        "type": "string"
+      }
+    },
+    "contactperson": {
+      "description": "Only for results with type 'software': Information on the person responsible for providing further information regarding the resource",
+      "type": "array",
+      "items": {
+        "type": "string"
+      }
+    },
+    "container": {
+      "type": "object",
+      "properties": {
+        "conferencedate": {
+          "type": "string",
+          "description": "Date of the conference"
+        },
+        "conferenceplace": {
+          "type": "string",
+          "description": "Place of the conference"
+        },
+        "edition": {
+          "type": "string",
+          "description": "Edition of the journal or conference proceeding"
+        },
+        "ep": {
+          "type": "string",
+          "description": "End page"
+        },
+        "iss": {
+          "type": "string",
+          "description": "Journal issue"
+        },
+        "issnLinking": {
+          "type": "string",
+          "description": "Journal linking iisn"
+        },
+        "issnOnline": {
+          "type": "string",
+          "description": "Journal online issn"
+        },
+        "issnPrinted": {
+          "type": "string",
+          "description": "Journal printed issn"
+        },
+        "name": {
+          "type": "string",
+          "description": "Name of the journal or conference"
+        },
+        "sp": {
+          "type": "string",
+          "description": "Start page"
+        },
+        "vol": {
+          "type": "string",
+          "description": "Volume"
+        }
+      },
+      "description": "Container has information about the conference or journal where the result has been presented or published"
+    },
+    "context": {
+      "description": "Reference to a relevant research infrastructure, initiative or community (RI/RC) among those collaborating with OpenAIRE. Please see https://connect.openaire.eu",
+      "type": "array",
+      "items": {
+        "type": "object",
+        "properties": {
+          "code": {
+            "type": "string",
+            "description": "Code identifying the RI/RC"
+          },
+          "label": {
+            "type": "string",
+            "description": "Label of the RI/RC"
+          },
+          "provenance": {
+            "description": "Why this result is associated to the RI/RC.",
+            "type": "array",
+            "items": {
+              "allOf": [
+                {"$ref": "#/definitions/Provenance"}
+
+              ]
+            }
+          }
+        }
+      }
+    },
+    "contributor": {
+      "description": "Contributors of this result",
+      "type": "array",
+      "items": {
+        "type": "string"
+      }
+    },
+    "country": {
+      "description": "Country associated to this result",
+      "type": "array",
+      "items": {
+        "type": "object",
+        "properties": {
+          "code": {
+            "type": "string",
+            "description": "ISO 3166-1 alpha-2 country code"
+          },
+          "label": {
+            "type": "string",
+            "description": "English label of the country"
+          },
+          "provenance": {
+            "allOf": [
+              {"$ref": "#/definitions/Provenance"},
+              {"description": "Why this result is associated to the country."}
+            ]
+          }
+        }
+      }
+    },
+    "coverage": {
+      "type": "array",
+      "items": {
+        "type": "string"
+      }
+    },
+    "dateofcollection": {
+      "type": "string",
+      "description": "When OpenAIRE collected the record the last time"
+    },
+    "description": {
+      "type": "array",
+      "items": {
+        "type": "string"
+      }
+    },
+    "documentationUrl": {
+      "description": "Only for results with type 'software': URL to the software documentation",
+      "type": "array",
+      "items": {
+        "type": "string"
+
+      }
+    },
+    "embargoenddate": {
+      "type": "string",
+      "description": "Date when the embargo ends and this result turns Open Access"
+    },
+    "externalReference": {
+      "description": "Links to external resources like entries from thematic databases (e.g. Protein Data Bank)",
+      "type": "array",
+      "items": {
+        "type": "object",
+        "properties": {
+          "name": {
+            "type": "string"
+          },
+          "provenance": {
+            "allOf": [
+              {"$ref": "#/definitions/Provenance"},
+              {"description": "Why this result is linked to the external resource"}
+            ]
+          },
+          "typology": {
+            "type": "string"
+          },
+          "value": {
+            "type": "string"
+          }
+        }
+      }
+    },
+    "format": {
+
+      "type": "array",
+      "items": {
+        "type": "string"
+      }
+    },
+    "geolocation": {
+      "description": "Geolocation information",
+      "type": "array",
+      "items": {
+        "type": "object",
+        "properties": {
+          "box": {
+            "type": "string"
+          },
+          "place": {
+            "type": "string"
+          },
+          "point": {
+            "type": "string"
+          }
+        }
+      }
+    },
+    "id": {
+      "type": "string",
+      "description": "OpenAIRE identifier"
+    },
+    "instance": {
+      "description": "Manifestations (i.e. different versions) of the result. For example: the pre-print and the published versions are two manifestations of the same research result",
+      "type": "array",
+      "items": {
+        "type": "object",
+        "properties": {
+          "accessright": {
+            "allOf": [
+              {"$ref": "#/definitions/AccessRight"},
+              {"description": "Access right of this instance"}
+            ]
+          },
+          "collectedfrom": {
+            "allOf": [
+              {"$ref": "#/definitions/KeyValue"},
+              {"description": "Information about the source from which the instance has been collected. Key is the OpenAIRE identifier of the data source, value is its name"}
+            ]
+          },
+          "hostedby": {
+            "allOf": [
+              {"$ref": "#/definitions/KeyValue"},
+              {"description": "Information about the source from which the instance can be viewed or downloaded. Key is the OpenAIRE identifier of the data source, value is its name"}
+            ]
+          },
+          "license": {
+            "type": "string",
+            "description": "License applied to the instance"
+          },
+          "publicationdate": {
+            "type": "string",
+            "description": "Publication date of the instance"
+          },
+          "refereed": {
+            "type": "string",
+            "description": "Was the instance subject to peer-review? Possible values are 'Unknown', 'nonPeerReviewed', 'peerReviewed' (see also https://api.openaire.eu/vocabularies/dnet:review_levels)"
+          },
+          "type": {
+            "type": "string",
+            "description": "Type of the instance. Possible values are listed at https://api.openaire.eu/vocabularies/dnet:publication_resource"
+          },
+          "url": {
+            "description":"Location where the instance is accessible",
+            "type": "array",
+            "items": {
+              "type": "string"
+            }
+          }
+        }
+      }
+    },
+    "language": {
+      "type": "object",
+      "properties": {
+        "code": {
+          "type": "string",
+          "description": "alpha-3/ISO 639-2 code of the language"
+        },
+        "label": {
+          "type": "string",
+          "description": "English label"
+        }
+      }
+    },
+    "lastupdatetimestamp": {
+      "type": "integer",
+      "description": "Timestamp of last update of the record in OpenAIRE"
+    },
+    "maintitle": {
+      "type": "string",
+      "description": "Title"
+    },
+    "originalId": {
+      "description": "Identifiers of the record at the original sources",
+      "type": "array",
+      "items": {
+        "type": "string"
+      }
+    },
+    "pid": {
+      "description": "Persistent identifiers of the result",
+      "type": "array",
+      "items": {
+        "allOf": [
+          {"$ref": "#/definitions/ControlledField"},
+          {"description": "scheme: list of available schemes are at https://api.openaire.eu/vocabularies/dnet:pid_types, value: the PID of the result "}
+        ]
+      }
+    },
+    "programmingLanguage": {
+      "type": "string",
+      "description": "Only for results with type 'software': the programming language"
+    },
+    "projects": {
+      "description": "List of projects (i.e. grants) that (co-)funded the production ofn the research results",
+      "type": "array",
+      "items": {
+        "type": "object",
+        "properties": {
+          "acronym": {
+            "type": "string",
+            "description": "Project acronym"
+          },
+          "code": {
+            "type": "string",
+            "description": "Grant code"
+          },
+          "funder": {
+            "type": "object",
+            "properties": {
+              "fundingStream": {
+                "type": "string",
+                "description": "Stream of funding (e.g. for European Commission can be H2020 or FP7)"
+              },
+              "jurisdiction": {
+                "type": "string",
+                "description": "Geographical jurisdiction (e.g. for European Commission is EU, for Croatian Science Foundation is HR)"
+              },
+              "name": {
+                "type": "string",
+                "description": "Name of the funder"
+              },
+              "shortName": {
+                "type": "string",
+                "description": "Short name or acronym of the funder"
+              }
+            },
+            "description": "Information about the funder funding the project"
+          },
+          "id": {
+            "type": "string",
+            "description": "OpenAIRE identifier of the project"
+          },
+          "provenance": {
+            "allOf": [
+              {"$ref": "#/definitions/Provenance"},
+              {"description": "Why this project is associated to the result"}
+            ]
+          },
+          "title": {
+            "type": "string",
+            "description": "Title of the project"
+          }
+        }
+      }
+    },
+    "publicationdate": {
+      "type": "string",
+      "description": "Date of publication"
+    },
+    "publisher": {
+      "type": "string",
+      "description": "Publisher"
+    },
+    "size": {
+      "type": "string",
+      "description": "Only for results with type 'dataset': the declared size of the dataset"
+    },
+    "source": {
+      "description": "See definition of Dublin Core field dc:source",
+      "type": "array",
+      "items": {
+        "type": "string"
+      }
+    },
+    "subjects": {
+      "description": "Keywords associated to the result",
+      "type": "array",
+      "items": {
+        "type": "object",
+        "properties": {
+          "provenance": {
+            "allOf": [
+              {"$ref": "#/definitions/Provenance"},
+              {"description": "Why this subject is associated to the result"}
+            ]
+          },
+          "subject": {
+            "allOf": [
+              {"$ref": "#/definitions/ControlledField"},
+              {"description": "OpenAIRE subject classification scheme (https://api.openaire.eu/vocabularies/dnet:subject_classification_typologies) and value. When the scheme is 'keyword', it means that the subject is free-text (i.e. not a term from a controlled vocabulary). "}
+            ]
+          }
+        }
+      }
+    },
+    "subtitle": {
+      "type": "string",
+      "description": "Sub-title of the result"
+    },
+    "tool": {
+      "description": "Only for results with type 'other': tool useful for the interpretation and/or re-used of the research product",
+      "type": "array",
+      "items": {
+        "type": "string"
+      }
+    },
+    "type": {
+      "type": "string",
+      "description": "Type of the result: one of 'publication', 'dataset', 'software', 'other' (see also https://api.openaire.eu/vocabularies/dnet:result_typologies)"
+    },
+    "version": {
+      "type": "string",
+      "description": "Version of the result"
+    }
+  }
+}

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

@@ -0,0 +1,32 @@
+
+[
+
+	{
+		"paramName":"cmp",
+		"paramLongName":"communityMapPath",
+		"paramDescription": "the path to the serialization of the community map",
+		"paramRequired": false
+	},
+
+	{
+		"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/upload_zenodo.json

@@ -0,0 +1,51 @@
+
+[
+  {
+    "paramName":"nd",
+    "paramLongName":"newDeposition",
+    "paramDescription": "if it is a new deposition (true) or a new versione (false)",
+    "paramRequired": true
+  },
+  {
+    "paramName":"cri",
+    "paramLongName":"conceptRecordId",
+    "paramDescription": "The id of the concept record for a new version",
+    "paramRequired": false
+  },
+  {
+    "paramName":"cmp",
+    "paramLongName":"communityMapPath",
+    "paramDescription": "the path to the serialization of the community map",
+    "paramRequired": false
+  },
+{
+"paramName":"hdfsp",
+"paramLongName":"hdfsPath",
+"paramDescription": "the path of the folder tofind files to send to Zenodo",
+"paramRequired": true
+},
+{
+"paramName": "hdfsnn",
+"paramLongName": "hdfsNameNode",
+"paramDescription": "the name node",
+"paramRequired": true
+},
+{
+"paramName": "at",
+"paramLongName": "accessToken",
+"paramDescription": "the access token for the deposition",
+"paramRequired": false
+},
+{
+"paramName":"cu",
+"paramLongName":"connectionUrl",
+"paramDescription": "the url to connect to deposit",
+"paramRequired": false
+},
+{
+"paramName":"m",
+"paramLongName":"metadata",
+"paramDescription": "metadata associated to the deposition",
+"paramRequired": false
+}
+]

dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/dump_whole/input_collect_and_save.json

@@ -0,0 +1,24 @@
+[
+
+	{
+		"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_whole/input_entity_parameter.json

@@ -0,0 +1,24 @@
+[
+
+	{
+		"paramName":"is",
+		"paramLongName":"isLookUpUrl",
+		"paramDescription": "URL of the isLookUp Service",
+		"paramRequired": false
+	},
+	{
+		"paramName": "hdfs",
+		"paramLongName": "hdfsPath",
+		"paramDescription": "the path used to store temporary output files",
+		"paramRequired": true
+	},
+	{
+		"paramName": "nn",
+		"paramLongName": "hdfsNameNode",
+		"paramDescription": "the name node",
+		"paramRequired": true
+	}
+]
+
+
+