implemented methods to extract fulltext link from an API call

Reviewed-on: D-Net/dnet-hadoop#458

dhp-common/pom.xml

@@ -63,11 +63,13 @@
 
 	<dependencies>
 		<dependency>
-			<groupId>eu.dnetlib.dhp</groupId>
-			<artifactId>dhp-pace-core</artifactId>
-			<version>${project.version}</version>
+			<groupId>edu.cmu</groupId>
+			<artifactId>secondstring</artifactId>
+		</dependency>
+		<dependency>
+			<groupId>com.ibm.icu</groupId>
+			<artifactId>icu4j</artifactId>
 		</dependency>
-
 		<dependency>
 			<groupId>org.apache.hadoop</groupId>
 			<artifactId>hadoop-common</artifactId>

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

@@ -7,12 +7,12 @@ import java.sql.*;
 import java.util.function.Consumer;
 
 import org.apache.commons.lang3.StringUtils;
-import org.apache.commons.logging.Log;
-import org.apache.commons.logging.LogFactory;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
 
 public class DbClient implements Closeable {
 
-	private static final Log log = LogFactory.getLog(DbClient.class);
+	private static final Logger log = LoggerFactory.getLogger(DbClient.class);
 
 	private final Connection connection;
 
@@ -37,6 +37,8 @@ public class DbClient implements Closeable {
 		try (final Statement stmt = connection.createStatement()) {
 			stmt.setFetchSize(100);
 
+			log.info("running SQL:\n\n{}\n\n", sql);
+
 			try (final ResultSet rs = stmt.executeQuery(sql)) {
 				while (rs.next()) {
 					consumer.accept(rs);

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

@@ -1,53 +0,0 @@
-
-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 final InputStream inputStream;
-	private final MediaType mediaType;
-	private final 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

@@ -1,8 +0,0 @@
-
-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

@@ -1,365 +0,0 @@
-
-package eu.dnetlib.dhp.common.api;
-
-import java.io.*;
-import java.io.IOException;
-import java.net.HttpURLConnection;
-import java.net.URL;
-import java.util.concurrent.TimeUnit;
-
-import org.apache.http.HttpHeaders;
-import org.apache.http.entity.ContentType;
-import org.jetbrains.annotations.NotNull;
-
-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) {
-
-		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 = "{}";
-
-		URL url = new URL(urlString);
-		HttpURLConnection conn = (HttpURLConnection) url.openConnection();
-		conn.setRequestProperty(HttpHeaders.CONTENT_TYPE, ContentType.APPLICATION_JSON.toString());
-		conn.setRequestProperty(HttpHeaders.AUTHORIZATION, "Bearer " + access_token);
-		conn.setRequestMethod("POST");
-		conn.setDoOutput(true);
-		try (OutputStream os = conn.getOutputStream()) {
-			byte[] input = json.getBytes("utf-8");
-			os.write(input, 0, input.length);
-		}
-
-		String body = getBody(conn);
-
-		int responseCode = conn.getResponseCode();
-		conn.disconnect();
-
-		if (!checkOKStatus(responseCode))
-			throw new IOException("Unexpected code " + responseCode + body);
-
-		ZenodoModel newSubmission = new Gson().fromJson(body, ZenodoModel.class);
-		this.bucket = newSubmission.getLinks().getBucket();
-		this.deposition_id = newSubmission.getId();
-
-		return responseCode;
-	}
-
-	/**
-	 * 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
-	 * @return the response code
-	 */
-	public int uploadIS(InputStream is, String file_name) throws IOException {
-
-		URL url = new URL(bucket + "/" + file_name);
-		HttpURLConnection conn = (HttpURLConnection) url.openConnection();
-		conn.setRequestProperty(HttpHeaders.CONTENT_TYPE, "application/zip");
-		conn.setRequestProperty(HttpHeaders.AUTHORIZATION, "Bearer " + access_token);
-		conn.setDoOutput(true);
-		conn.setRequestMethod("PUT");
-
-		byte[] buf = new byte[8192];
-		int length;
-		try (OutputStream os = conn.getOutputStream()) {
-			while ((length = is.read(buf)) != -1) {
-				os.write(buf, 0, length);
-			}
-
-		}
-		int responseCode = conn.getResponseCode();
-		if (!checkOKStatus(responseCode)) {
-			throw new IOException("Unexpected code " + responseCode + getBody(conn));
-		}
-
-		return responseCode;
-	}
-
-	@NotNull
-	private String getBody(HttpURLConnection conn) throws IOException {
-		String body = "{}";
-		try (BufferedReader br = new BufferedReader(
-			new InputStreamReader(conn.getInputStream(), "utf-8"))) {
-			StringBuilder response = new StringBuilder();
-			String responseLine = null;
-			while ((responseLine = br.readLine()) != null) {
-				response.append(responseLine.trim());
-			}
-
-			body = response.toString();
-
-		}
-		return body;
-	}
-
-	/**
-	 * Associates metadata information to the current deposition
-	 *
-	 * @param metadata the metadata
-	 * @return response code
-	 * @throws IOException
-	 */
-	public int sendMretadata(String metadata) throws IOException {
-
-		URL url = new URL(urlString + "/" + deposition_id);
-		HttpURLConnection conn = (HttpURLConnection) url.openConnection();
-		conn.setRequestProperty(HttpHeaders.CONTENT_TYPE, ContentType.APPLICATION_JSON.toString());
-		conn.setRequestProperty(HttpHeaders.AUTHORIZATION, "Bearer " + access_token);
-		conn.setDoOutput(true);
-		conn.setRequestMethod("PUT");
-
-		try (OutputStream os = conn.getOutputStream()) {
-			byte[] input = metadata.getBytes("utf-8");
-			os.write(input, 0, input.length);
-
-		}
-
-		final int responseCode = conn.getResponseCode();
-		conn.disconnect();
-		if (!checkOKStatus(responseCode))
-			throw new IOException("Unexpected code " + responseCode + getBody(conn));
-
-		return responseCode;
-
-	}
-
-	private boolean checkOKStatus(int responseCode) {
-
-		if (HttpURLConnection.HTTP_OK != responseCode ||
-			HttpURLConnection.HTTP_CREATED != responseCode)
-			return true;
-		return false;
-	}
-
-	/**
-	 * To publish the current deposition. It works for both new deposition or new version of an old deposition
-	 *
-	 * @return response code
-	 * @throws IOException
-	 */
-	@Deprecated
-	public int publish() throws IOException {
-
-		String json = "{}";
-
-		OkHttpClient httpClient = new OkHttpClient.Builder().connectTimeout(600, TimeUnit.SECONDS).build();
-
-		RequestBody body = RequestBody.create(json, MEDIA_TYPE_JSON);
-
-		Request request = new Request.Builder()
-			.url(urlString + "/" + deposition_id + "/actions/publish")
-			.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());
-
-			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, 1);
-		String json = "{}";
-
-		URL url = new URL(urlString + "/" + deposition_id + "/actions/newversion");
-		HttpURLConnection conn = (HttpURLConnection) url.openConnection();
-
-		conn.setRequestProperty(HttpHeaders.AUTHORIZATION, "Bearer " + access_token);
-		conn.setDoOutput(true);
-		conn.setRequestMethod("POST");
-
-		try (OutputStream os = conn.getOutputStream()) {
-			byte[] input = json.getBytes("utf-8");
-			os.write(input, 0, input.length);
-
-		}
-
-		String body = getBody(conn);
-
-		int responseCode = conn.getResponseCode();
-
-		conn.disconnect();
-		if (!checkOKStatus(responseCode))
-			throw new IOException("Unexpected code " + responseCode + body);
-
-		ZenodoModel zenodoModel = new Gson().fromJson(body, ZenodoModel.class);
-		String latest_draft = zenodoModel.getLinks().getLatest_draft();
-		deposition_id = latest_draft.substring(latest_draft.lastIndexOf("/") + 1);
-		bucket = getBucket(latest_draft);
-
-		return responseCode;
-
-	}
-
-	/**
-	 * To finish uploading a version or new deposition not published
-	 * It sets the deposition_id and the bucket to be used
-	 *
-	 *
-	 * @param deposition_id the deposition id of the not yet published upload
-	 *            concept_rec_id = 656930
-	 * @return response code
-	 * @throws IOException
-	 * @throws MissingConceptDoiException
-	 */
-	public int uploadOpenDeposition(String deposition_id) throws IOException, MissingConceptDoiException {
-
-		this.deposition_id = deposition_id;
-
-		String json = "{}";
-
-		URL url = new URL(urlString + "/" + deposition_id);
-		HttpURLConnection conn = (HttpURLConnection) url.openConnection();
-
-		conn.setRequestProperty(HttpHeaders.AUTHORIZATION, "Bearer " + access_token);
-		conn.setRequestMethod("POST");
-		conn.setDoOutput(true);
-		try (OutputStream os = conn.getOutputStream()) {
-			byte[] input = json.getBytes("utf-8");
-			os.write(input, 0, input.length);
-		}
-
-		String body = getBody(conn);
-
-		int responseCode = conn.getResponseCode();
-		conn.disconnect();
-
-		if (!checkOKStatus(responseCode))
-			throw new IOException("Unexpected code " + responseCode + body);
-
-		ZenodoModel zenodoModel = new Gson().fromJson(body, ZenodoModel.class);
-		bucket = zenodoModel.getLinks().getBucket();
-
-		return responseCode;
-
-	}
-
-	private void setDepositionId(String concept_rec_id, Integer page) throws IOException, MissingConceptDoiException {
-
-		ZenodoModelList zenodoModelList = new Gson()
-			.fromJson(getPrevDepositions(String.valueOf(page)), ZenodoModelList.class);
-
-		for (ZenodoModel zm : zenodoModelList) {
-			if (zm.getConceptrecid().equals(concept_rec_id)) {
-				deposition_id = zm.getId();
-				return;
-			}
-		}
-		if (zenodoModelList.size() == 0)
-			throw new MissingConceptDoiException(
-				"The concept record id specified was missing in the list of depositions");
-		setDepositionId(concept_rec_id, page + 1);
-
-	}
-
-	private String getPrevDepositions(String page) throws IOException {
-
-		HttpUrl.Builder urlBuilder = HttpUrl.parse(urlString).newBuilder();
-		urlBuilder.addQueryParameter("page", page);
-
-		URL url = new URL(urlBuilder.build().toString());
-		HttpURLConnection conn = (HttpURLConnection) url.openConnection();
-		conn.setRequestProperty(HttpHeaders.CONTENT_TYPE, ContentType.APPLICATION_JSON.toString());
-		conn.setRequestProperty(HttpHeaders.AUTHORIZATION, "Bearer " + access_token);
-		conn.setDoOutput(true);
-		conn.setRequestMethod("GET");
-
-		String body = getBody(conn);
-
-		int responseCode = conn.getResponseCode();
-
-		conn.disconnect();
-		if (!checkOKStatus(responseCode))
-			throw new IOException("Unexpected code " + responseCode + body);
-
-		return body;
-
-	}
-
-	private String getBucket(String inputUurl) throws IOException {
-
-		URL url = new URL(inputUurl);
-		HttpURLConnection conn = (HttpURLConnection) url.openConnection();
-		conn.setRequestProperty(HttpHeaders.CONTENT_TYPE, ContentType.APPLICATION_JSON.toString());
-		conn.setRequestProperty(HttpHeaders.AUTHORIZATION, "Bearer " + access_token);
-		conn.setDoOutput(true);
-		conn.setRequestMethod("GET");
-
-		String body = getBody(conn);
-
-		int responseCode = conn.getResponseCode();
-
-		conn.disconnect();
-		if (!checkOKStatus(responseCode))
-			throw new IOException("Unexpected code " + responseCode + body);
-
-		ZenodoModel zenodoModel = new Gson().fromJson(body, ZenodoModel.class);
-
-		return zenodoModel.getLinks().getBucket();
-
-	}
-
-}

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

@@ -1,14 +0,0 @@
-
-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

@@ -1,47 +0,0 @@
-
-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

@@ -1,44 +0,0 @@
-
-package eu.dnetlib.dhp.common.api.zenodo;
-
-import java.io.Serializable;
-
-public class File implements Serializable {
-	private String checksum;
-	private String filename;
-	private long filesize;
-	private String id;
-
-	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;
-	}
-
-}

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

@@ -1,23 +0,0 @@
-
-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

@@ -1,92 +0,0 @@
-
-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

@@ -1,153 +0,0 @@
-
-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

@@ -1,25 +0,0 @@
-
-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

@@ -1,43 +0,0 @@
-
-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

@@ -1,118 +0,0 @@
-
-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

@@ -1,7 +0,0 @@
-
-package eu.dnetlib.dhp.common.api.zenodo;
-
-import java.util.ArrayList;
-
-public class ZenodoModelList extends ArrayList<ZenodoModel> {
-}

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

@@ -10,6 +10,7 @@ import org.apache.commons.lang3.StringUtils;
 import com.wcohen.ss.JaroWinkler;
 
 import eu.dnetlib.dhp.schema.oaf.Author;
+import eu.dnetlib.dhp.schema.oaf.Qualifier;
 import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
 import eu.dnetlib.pace.model.Person;
 import scala.Tuple2;
@@ -146,10 +147,20 @@ public class AuthorMerger {
 	}
 
 	public static String pidToComparableString(StructuredProperty pid) {
-		final String classid = pid.getQualifier().getClassid() != null ? pid.getQualifier().getClassid().toLowerCase()
-			: "";
-		return (pid.getQualifier() != null ? classid : "")
-			+ (pid.getValue() != null ? pid.getValue().toLowerCase() : "");
+		final String classId = Optional
+			.ofNullable(pid)
+			.map(
+				p -> Optional
+					.ofNullable(p.getQualifier())
+					.map(Qualifier::getClassid)
+					.map(String::toLowerCase)
+					.orElse(""))
+			.orElse("");
+		return Optional
+			.ofNullable(pid)
+			.map(StructuredProperty::getValue)
+			.map(v -> String.join("|", v, classId))
+			.orElse("");
 	}
 
 	public static int countAuthorsPids(List<Author> authors) {

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

@@ -135,7 +135,7 @@ public class GroupEntitiesSparkJob {
 					.applyCoarVocabularies(entity, vocs),
 				OAFENTITY_KRYO_ENC)
 			.groupByKey((MapFunction<OafEntity, String>) OafEntity::getId, Encoders.STRING())
-			.mapGroups((MapGroupsFunction<String, OafEntity, OafEntity>) MergeUtils::mergeGroup, OAFENTITY_KRYO_ENC)
+			.mapGroups((MapGroupsFunction<String, OafEntity, OafEntity>) MergeUtils::mergeById, OAFENTITY_KRYO_ENC)
 			.map(
 				(MapFunction<OafEntity, Tuple2<String, OafEntity>>) t -> new Tuple2<>(
 					t.getClass().getName(), t),

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

@@ -119,7 +119,7 @@ public class GraphCleaningFunctions extends CleaningFunctions {
 							.getContext()
 							.stream()
 							.filter(c -> !StringUtils.startsWith(c.getId().toLowerCase(), contextId))
-							.collect(Collectors.toList()));
+							.collect(Collectors.toCollection(ArrayList::new)));
 			}
 			return (T) res;
 		} else {
@@ -1003,4 +1003,41 @@ public class GraphCleaningFunctions extends CleaningFunctions {
 			.orElse(null);
 	}
 
+	/**
+	 * Implements bad and ugly things that we should get rid of ASAP.
+	 *
+	 * @param value
+	 * @return
+	 * @param <T>
+	 */
+	public static <T extends Oaf> T dedicatedUglyHacks(T value) {
+		if (value instanceof OafEntity) {
+			if (value instanceof Result) {
+				final Result r = (Result) value;
+
+				// Fix for AMS Acta
+				Optional
+					.ofNullable(r.getInstance())
+					.map(
+						instance -> instance
+							.stream()
+							.filter(
+								i -> Optional
+									.ofNullable(i.getHostedby())
+									.map(KeyValue::getKey)
+									.map(dsId -> dsId.equals("10|re3data_____::4cc76bed7ce2fb95fd8e7a2dfde16016"))
+									.orElse(false)))
+					.ifPresent(instance -> instance.forEach(i -> {
+						if (Optional
+							.ofNullable(i.getPid())
+							.map(pid -> pid.stream().noneMatch(p -> p.getValue().startsWith("10.6092/unibo/amsacta")))
+							.orElse(false)) {
+							i.setHostedby(UNKNOWN_REPOSITORY);
+						}
+					}));
+			}
+		}
+		return value;
+	}
+
 }

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

@@ -0,0 +1,106 @@
+
+package eu.dnetlib.dhp.schema.oaf.utils;
+
+import java.util.*;
+
+import eu.dnetlib.dhp.schema.common.ModelConstants;
+import eu.dnetlib.dhp.schema.oaf.Oaf;
+import eu.dnetlib.dhp.schema.oaf.OafEntity;
+import eu.dnetlib.dhp.schema.oaf.Result;
+
+public class MergeEntitiesComparator implements Comparator<Oaf> {
+	static final List<String> PID_AUTHORITIES = Arrays
+		.asList(
+			ModelConstants.ARXIV_ID,
+			ModelConstants.PUBMED_CENTRAL_ID,
+			ModelConstants.EUROPE_PUBMED_CENTRAL_ID,
+			ModelConstants.DATACITE_ID,
+			ModelConstants.CROSSREF_ID);
+
+	static final List<String> RESULT_TYPES = Arrays
+		.asList(
+			ModelConstants.ORP_RESULTTYPE_CLASSID,
+			ModelConstants.SOFTWARE_RESULTTYPE_CLASSID,
+			ModelConstants.DATASET_RESULTTYPE_CLASSID,
+			ModelConstants.PUBLICATION_RESULTTYPE_CLASSID);
+
+	public static final Comparator<Oaf> INSTANCE = new MergeEntitiesComparator();
+
+	@Override
+	public int compare(Oaf left, Oaf right) {
+		if (left == null && right == null)
+			return 0;
+		if (left == null)
+			return -1;
+		if (right == null)
+			return 1;
+
+		int res = 0;
+
+		// pid authority
+		int cfp1 = Optional
+			.ofNullable(left.getCollectedfrom())
+			.map(
+				cf -> cf
+					.stream()
+					.map(kv -> PID_AUTHORITIES.indexOf(kv.getKey()))
+					.max(Integer::compare)
+					.orElse(-1))
+			.orElse(-1);
+		int cfp2 = Optional
+			.ofNullable(right.getCollectedfrom())
+			.map(
+				cf -> cf
+					.stream()
+					.map(kv -> PID_AUTHORITIES.indexOf(kv.getKey()))
+					.max(Integer::compare)
+					.orElse(-1))
+			.orElse(-1);
+
+		if (cfp1 >= 0 && cfp1 > cfp2) {
+			return 1;
+		} else if (cfp2 >= 0 && cfp2 > cfp1) {
+			return -1;
+		}
+
+		// trust
+		if (left.getDataInfo() != null && right.getDataInfo() != null) {
+			res = left.getDataInfo().getTrust().compareTo(right.getDataInfo().getTrust());
+		}
+
+		// result type
+		if (res == 0) {
+			if (left instanceof Result && right instanceof Result) {
+				Result r1 = (Result) left;
+				Result r2 = (Result) right;
+
+				if (r1.getResulttype() == null || r1.getResulttype().getClassid() == null) {
+					if (r2.getResulttype() != null && r2.getResulttype().getClassid() != null) {
+						return -1;
+					}
+				} else if (r2.getResulttype() == null || r2.getResulttype().getClassid() == null) {
+					return 1;
+				}
+
+				int rt1 = RESULT_TYPES.indexOf(r1.getResulttype().getClassid());
+				int rt2 = RESULT_TYPES.indexOf(r2.getResulttype().getClassid());
+
+				if (rt1 >= 0 && rt1 > rt2) {
+					return 1;
+				} else if (rt2 >= 0 && rt2 > rt1) {
+					return -1;
+				}
+			}
+		}
+
+		// id
+		if (res == 0) {
+			if (left instanceof OafEntity && right instanceof OafEntity) {
+				res = ((OafEntity) left).getId().compareTo(((OafEntity) right).getId());
+			}
+		}
+
+		return res;
+	}
+
+}

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

@@ -30,40 +30,37 @@ import eu.dnetlib.dhp.schema.common.ModelSupport;
 import eu.dnetlib.dhp.schema.oaf.*;
 
 public class MergeUtils {
+	public static <T extends Oaf> T mergeById(String s, Iterator<T> oafEntityIterator) {
+		return mergeGroup(s, oafEntityIterator, true);
+	}
 
 	public static <T extends Oaf> T mergeGroup(String s, Iterator<T> oafEntityIterator) {
-		TreeSet<T> sortedEntities = new TreeSet<>((o1, o2) -> {
-			int res = 0;
+		return mergeGroup(s, oafEntityIterator, false);
+	}
 
-			if (o1.getDataInfo() != null && o2.getDataInfo() != null) {
-				res = o1.getDataInfo().getTrust().compareTo(o2.getDataInfo().getTrust());
-			}
+	public static <T extends Oaf> T mergeGroup(String s, Iterator<T> oafEntityIterator,
+		boolean checkDelegateAuthority) {
 
-			if (res == 0) {
-				if (o1 instanceof Result && o2 instanceof Result) {
-					return ResultTypeComparator.INSTANCE.compare((Result) o1, (Result) o2);
-				}
-			}
+		ArrayList<T> sortedEntities = new ArrayList<>();
+		oafEntityIterator.forEachRemaining(sortedEntities::add);
+		sortedEntities.sort(MergeEntitiesComparator.INSTANCE.reversed());
 
-			return res;
-		});
+		Iterator<T> it = sortedEntities.iterator();
+		T merged = it.next();
 
-		while (oafEntityIterator.hasNext()) {
-			sortedEntities.add(oafEntityIterator.next());
-		}
-
-		T merged = sortedEntities.descendingIterator().next();
-
-		Iterator<T> it = sortedEntities.descendingIterator();
 		while (it.hasNext()) {
-			merged = checkedMerge(merged, it.next());
+			merged = checkedMerge(merged, it.next(), checkDelegateAuthority);
 		}
 
 		return merged;
 	}
 
-	public static <T extends Oaf> T checkedMerge(final T left, final T right) {
-		return (T) merge(left, right, false);
+	public static <T extends Oaf> T checkedMerge(final T left, final T right, boolean checkDelegateAuthority) {
+		return (T) merge(left, right, checkDelegateAuthority);
+	}
+
+	public static <T extends Result, E extends Result> Result mergeResult(final T left, final E right) {
+		return (Result) merge(left, right, false);
 	}
 
 	public static Oaf merge(final Oaf left, final Oaf right) {
@@ -108,7 +105,7 @@ public class MergeUtils {
 				return mergeSoftware((Software) left, (Software) right);
 			}
 
-			return mergeResult((Result) left, (Result) right);
+			return mergeResultFields((Result) left, (Result) right);
 		} else if (sameClass(left, right, Datasource.class)) {
 			// TODO
 			final int trust = compareTrust(left, right);
@@ -131,7 +128,7 @@ public class MergeUtils {
 	 * https://graph.openaire.eu/docs/data-model/pids-and-identifiers#delegated-authorities and in that case it prefers
 	 * such version.
 	 * <p>
-	 * Otherwise, it considers a resulttype priority order implemented in {@link ResultTypeComparator}
+	 * Otherwise, it considers a resulttype priority order implemented in {@link MergeEntitiesComparator}
 	 * and proceeds with the canonical property merging.
 	 *
 	 * @param left
@@ -149,11 +146,12 @@ public class MergeUtils {
 		if (!leftFromDelegatedAuthority && rightFromDelegatedAuthority) {
 			return right;
 		}
+
 		// TODO: raise trust to have preferred fields from one or the other??
-		if (new ResultTypeComparator().compare(left, right) < 0) {
-			return mergeResult(left, right);
+		if (MergeEntitiesComparator.INSTANCE.compare(left, right) > 0) {
+			return mergeResultFields(left, right);
 		} else {
-			return mergeResult(right, left);
+			return mergeResultFields(right, left);
 		}
 	}
 
@@ -213,9 +211,9 @@ public class MergeUtils {
 
 	private static <T, K> List<T> mergeLists(final List<T> left, final List<T> right, int trust,
 		Function<T, K> keyExtractor, BinaryOperator<T> merger) {
-		if (left == null) {
-			return right;
-		} else if (right == null) {
+		if (left == null || left.isEmpty()) {
+			return right != null ? right : new ArrayList<>();
+		} else if (right == null || right.isEmpty()) {
 			return left;
 		}
 
@@ -263,6 +261,12 @@ public class MergeUtils {
 
 	// TODO review
 	private static List<KeyValue> mergeByKey(List<KeyValue> left, List<KeyValue> right, int trust) {
+		if (left == null) {
+			return right;
+		} else if (right == null) {
+			return left;
+		}
+
 		if (trust < 0) {
 			List<KeyValue> s = left;
 			left = right;
@@ -270,8 +274,9 @@ public class MergeUtils {
 		}
 
 		HashMap<String, KeyValue> values = new HashMap<>();
-		left.forEach(kv -> values.put(kv.getKey(), kv));
-		right.forEach(kv -> values.putIfAbsent(kv.getKey(), kv));
+
+		Optional.ofNullable(left).ifPresent(l -> l.forEach(kv -> values.put(kv.getKey(), kv)));
+		Optional.ofNullable(right).ifPresent(r -> r.forEach(kv -> values.putIfAbsent(kv.getKey(), kv)));
 
 		return new ArrayList<>(values.values());
 	}
@@ -323,7 +328,7 @@ public class MergeUtils {
 		final T merged = mergeOafFields(original, enrich, trust);
 
 		merged.setOriginalId(unionDistinctListOfString(merged.getOriginalId(), enrich.getOriginalId()));
-		merged.setPid(unionDistinctLists(merged.getPid(), enrich.getPid(), trust));
+		merged.setPid(mergeLists(merged.getPid(), enrich.getPid(), trust, MergeUtils::spKeyExtractor, (p1, p2) -> p1));
 		merged.setDateofcollection(LocalDateTime.now().toString());
 		merged
 			.setDateoftransformation(
@@ -367,7 +372,7 @@ public class MergeUtils {
 		return merge;
 	}
 
-	public static <T extends Result> T mergeResult(T original, T enrich) {
+	private static <T extends Result> T mergeResultFields(T original, T enrich) {
 		final int trust = compareTrust(original, enrich);
 		T merge = mergeOafEntityFields(original, enrich, trust);
 
@@ -386,7 +391,7 @@ public class MergeUtils {
 		}
 
 		// should be an instance attribute, get the first non-null value
-		merge.setLanguage(coalesce(merge.getLanguage(), enrich.getLanguage()));
+		merge.setLanguage(coalesceQualifier(merge.getLanguage(), enrich.getLanguage()));
 
 		// distinct countries, do not manage datainfo
 		merge.setCountry(mergeQualifiers(merge.getCountry(), enrich.getCountry(), trust));
@@ -427,7 +432,10 @@ public class MergeUtils {
 
 		// merge datainfo for same context id
 		merge.setContext(mergeLists(merge.getContext(), enrich.getContext(), trust, Context::getId, (r, l) -> {
-			r.getDataInfo().addAll(l.getDataInfo());
+			ArrayList<DataInfo> di = new ArrayList<>();
+			di.addAll(r.getDataInfo());
+			di.addAll(l.getDataInfo());
+			r.setDataInfo(di);
 			return r;
 		}));
 
@@ -556,6 +564,13 @@ public class MergeUtils {
 		return m != null ? m : e;
 	}
 
+	private static Qualifier coalesceQualifier(Qualifier m, Qualifier e) {
+		if (m == null || m.getClassid() == null || StringUtils.isBlank(m.getClassid())) {
+			return e;
+		}
+		return m;
+	}
+
 	private static List<Author> mergeAuthors(List<Author> author, List<Author> author1, int trust) {
 		List<List<Author>> authors = new ArrayList<>();
 		if (author != null) {
@@ -568,6 +583,10 @@ public class MergeUtils {
 	}
 
 	private static String instanceKeyExtractor(Instance i) {
+		// three levels of concatenating:
+		// 1. ::
+		// 2. @@
+		// 3. ||
 		return String
 			.join(
 				"::",
@@ -575,10 +594,10 @@ public class MergeUtils {
 				kvKeyExtractor(i.getCollectedfrom()),
 				qualifierKeyExtractor(i.getAccessright()),
 				qualifierKeyExtractor(i.getInstancetype()),
-				Optional.ofNullable(i.getUrl()).map(u -> String.join("::", u)).orElse(null),
+				Optional.ofNullable(i.getUrl()).map(u -> String.join("@@", u)).orElse(null),
 				Optional
 					.ofNullable(i.getPid())
-					.map(pp -> pp.stream().map(MergeUtils::spKeyExtractor).collect(Collectors.joining("::")))
+					.map(pp -> pp.stream().map(MergeUtils::spKeyExtractor).collect(Collectors.joining("@@")))
 					.orElse(null));
 	}
 
@@ -639,6 +658,13 @@ public class MergeUtils {
 			return d1;
 		}
 
+		if (StringUtils.contains(d1.getValue(), "null")) {
+			return d2;
+		}
+		if (StringUtils.contains(d2.getValue(), "null")) {
+			return d1;
+		}
+
 		return Stream
 			.of(d1, d2)
 			.min(
@@ -687,13 +713,13 @@ public class MergeUtils {
 	private static String spKeyExtractor(StructuredProperty sp) {
 		return Optional
 			.ofNullable(sp)
-			.map(s -> Joiner.on("::").join(s, qualifierKeyExtractor(s.getQualifier())))
+			.map(s -> Joiner.on("||").join(qualifierKeyExtractor(s.getQualifier()), s.getValue()))
 			.orElse(null);
 	}
 
 	private static <T extends OtherResearchProduct> T mergeORP(T original, T enrich) {
 		int trust = compareTrust(original, enrich);
-		final T merge = mergeResult(original, enrich);
+		final T merge = mergeResultFields(original, enrich);
 
 		merge.setContactperson(unionDistinctLists(merge.getContactperson(), enrich.getContactperson(), trust));
 		merge.setContactgroup(unionDistinctLists(merge.getContactgroup(), enrich.getContactgroup(), trust));
@@ -704,7 +730,7 @@ public class MergeUtils {
 
 	private static <T extends Software> T mergeSoftware(T original, T enrich) {
 		int trust = compareTrust(original, enrich);
-		final T merge = mergeResult(original, enrich);
+		final T merge = mergeResultFields(original, enrich);
 
 		merge.setDocumentationUrl(unionDistinctLists(merge.getDocumentationUrl(), enrich.getDocumentationUrl(), trust));
 		merge.setLicense(unionDistinctLists(merge.getLicense(), enrich.getLicense(), trust));
@@ -718,7 +744,7 @@ public class MergeUtils {
 
 	private static <T extends Dataset> T mergeDataset(T original, T enrich) {
 		int trust = compareTrust(original, enrich);
-		T merge = mergeResult(original, enrich);
+		T merge = mergeResultFields(original, enrich);
 
 		merge.setStoragedate(chooseReference(merge.getStoragedate(), enrich.getStoragedate(), trust));
 		merge.setDevice(chooseReference(merge.getDevice(), enrich.getDevice(), trust));
@@ -737,7 +763,7 @@ public class MergeUtils {
 
 	public static <T extends Publication> T mergePublication(T original, T enrich) {
 		final int trust = compareTrust(original, enrich);
-		T merged = mergeResult(original, enrich);
+		T merged = mergeResultFields(original, enrich);
 
 		merged.setJournal(chooseReference(merged.getJournal(), enrich.getJournal(), trust));
 
@@ -855,9 +881,11 @@ public class MergeUtils {
 		if (toEnrichInstances == null) {
 			return enrichmentResult;
 		}
-		if (enrichmentInstances == null) {
-			return enrichmentResult;
+
+		if (enrichmentInstances == null || enrichmentInstances.isEmpty()) {
+			return toEnrichInstances;
 		}
+
 		Map<String, Instance> ri = toInstanceMap(enrichmentInstances);
 
 		toEnrichInstances.forEach(i -> {

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

@@ -1,78 +0,0 @@
-
-package eu.dnetlib.dhp.schema.oaf.utils;
-
-import static eu.dnetlib.dhp.schema.common.ModelConstants.CROSSREF_ID;
-
-import java.util.Comparator;
-import java.util.HashSet;
-import java.util.Optional;
-import java.util.stream.Collectors;
-
-import eu.dnetlib.dhp.schema.common.ModelConstants;
-import eu.dnetlib.dhp.schema.oaf.KeyValue;
-import eu.dnetlib.dhp.schema.oaf.Result;
-
-public class ResultTypeComparator implements Comparator<Result> {
-
-	public static final ResultTypeComparator INSTANCE = new ResultTypeComparator();
-
-	@Override
-	public int compare(Result left, Result right) {
-
-		if (left == null && right == null)
-			return 0;
-		if (left == null)
-			return 1;
-		if (right == null)
-			return -1;
-
-		HashSet<String> lCf = getCollectedFromIds(left);
-		HashSet<String> rCf = getCollectedFromIds(right);
-
-		if (lCf.contains(CROSSREF_ID) && !rCf.contains(CROSSREF_ID)) {
-			return -1;
-		}
-		if (!lCf.contains(CROSSREF_ID) && rCf.contains(CROSSREF_ID)) {
-			return 1;
-		}
-
-		String lClass = left.getResulttype().getClassid();
-		String rClass = right.getResulttype().getClassid();
-
-		if (!lClass.equals(rClass)) {
-			if (lClass.equals(ModelConstants.PUBLICATION_RESULTTYPE_CLASSID))
-				return -1;
-			if (rClass.equals(ModelConstants.PUBLICATION_RESULTTYPE_CLASSID))
-				return 1;
-
-			if (lClass.equals(ModelConstants.DATASET_RESULTTYPE_CLASSID))
-				return -1;
-			if (rClass.equals(ModelConstants.DATASET_RESULTTYPE_CLASSID))
-				return 1;
-
-			if (lClass.equals(ModelConstants.SOFTWARE_RESULTTYPE_CLASSID))
-				return -1;
-			if (rClass.equals(ModelConstants.SOFTWARE_RESULTTYPE_CLASSID))
-				return 1;
-
-			if (lClass.equals(ModelConstants.ORP_RESULTTYPE_CLASSID))
-				return -1;
-			if (rClass.equals(ModelConstants.ORP_RESULTTYPE_CLASSID))
-				return 1;
-		}
-
-		// Else (but unlikely), lexicographical ordering will do.
-		return lClass.compareTo(rClass);
-	}
-
-	protected HashSet<String> getCollectedFromIds(Result left) {
-		return Optional
-			.ofNullable(left.getCollectedfrom())
-			.map(
-				cf -> cf
-					.stream()
-					.map(KeyValue::getKey)
-					.collect(Collectors.toCollection(HashSet::new)))
-			.orElse(new HashSet<>());
-	}
-}

dhp-common/src/main/java/eu/dnetlib/pace/common/PaceCommonUtils.java

@@ -0,0 +1,101 @@
+
+package eu.dnetlib.pace.common;
+
+import java.nio.charset.StandardCharsets;
+import java.text.Normalizer;
+import java.util.Set;
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
+
+import org.apache.commons.io.IOUtils;
+import org.apache.commons.lang3.StringUtils;
+
+import com.google.common.base.Splitter;
+import com.google.common.collect.Iterables;
+import com.google.common.collect.Sets;
+import com.ibm.icu.text.Transliterator;
+
+/**
+ * Set of common functions for the framework
+ *
+ * @author claudio
+ */
+public class PaceCommonUtils {
+
+	// transliterator
+	protected static Transliterator transliterator = Transliterator.getInstance("Any-Eng");
+
+	protected static final String aliases_from = "⁰¹²³⁴⁵⁶⁷⁸⁹⁺⁻⁼⁽⁾ⁿ₀₁₂₃₄₅₆₇₈₉₊₋₌₍₎àáâäæãåāèéêëēėęəîïíīįìôöòóœøōõûüùúūßśšłžźżçćčñń";
+	protected static final String aliases_to = "0123456789+-=()n0123456789+-=()aaaaaaaaeeeeeeeeiiiiiioooooooouuuuussslzzzcccnn";
+
+	protected static Pattern hexUnicodePattern = Pattern.compile("\\\\u(\\p{XDigit}{4})");
+
+	protected static String fixAliases(final String s) {
+		final StringBuilder sb = new StringBuilder();
+
+		s.chars().forEach(ch -> {
+			final int i = StringUtils.indexOf(aliases_from, ch);
+			sb.append(i >= 0 ? aliases_to.charAt(i) : (char) ch);
+		});
+
+		return sb.toString();
+	}
+
+	protected static String transliterate(final String s) {
+		try {
+			return transliterator.transliterate(s);
+		} catch (Exception e) {
+			return s;
+		}
+	}
+
+	public static String normalize(final String s) {
+		return fixAliases(transliterate(nfd(unicodeNormalization(s))))
+			.toLowerCase()
+			// do not compact the regexes in a single expression, would cause StackOverflowError in case of large input
+			// strings
+			.replaceAll("[^ \\w]+", "")
+			.replaceAll("(\\p{InCombiningDiacriticalMarks})+", "")
+			.replaceAll("(\\p{Punct})+", " ")
+			.replaceAll("(\\d)+", " ")
+			.replaceAll("(\\n)+", " ")
+			.trim();
+	}
+
+	public static String nfd(final String s) {
+		return Normalizer.normalize(s, Normalizer.Form.NFD);
+	}
+
+	public static String unicodeNormalization(final String s) {
+
+		Matcher m = hexUnicodePattern.matcher(s);
+		StringBuffer buf = new StringBuffer(s.length());
+		while (m.find()) {
+			String ch = String.valueOf((char) Integer.parseInt(m.group(1), 16));
+			m.appendReplacement(buf, Matcher.quoteReplacement(ch));
+		}
+		m.appendTail(buf);
+		return buf.toString();
+	}
+
+	public static Set<String> loadFromClasspath(final String classpath) {
+
+		Transliterator transliterator = Transliterator.getInstance("Any-Eng");
+
+		final Set<String> h = Sets.newHashSet();
+		try {
+			for (final String s : IOUtils
+				.readLines(PaceCommonUtils.class.getResourceAsStream(classpath), StandardCharsets.UTF_8)) {
+				h.add(fixAliases(transliterator.transliterate(s))); // transliteration of the stopwords
+			}
+		} catch (final Throwable e) {
+			return Sets.newHashSet();
+		}
+		return h;
+	}
+
+	protected static Iterable<String> tokens(final String s, final int maxTokens) {
+		return Iterables.limit(Splitter.on(" ").omitEmptyStrings().trimResults().split(s), maxTokens);
+	}
+
+}

dhp-common/src/main/java/eu/dnetlib/pace/model/Person.java

@@ -12,7 +12,7 @@ import com.google.common.collect.Iterables;
 import com.google.common.collect.Lists;
 import com.google.common.hash.Hashing;
 
-import eu.dnetlib.pace.common.AbstractPaceFunctions;
+import eu.dnetlib.pace.common.PaceCommonUtils;
 import eu.dnetlib.pace.util.Capitalise;
 import eu.dnetlib.pace.util.DotAbbreviations;
 
@@ -86,7 +86,7 @@ public class Person {
 
 	private List<String> splitTerms(final String s) {
 		if (particles == null) {
-			particles = AbstractPaceFunctions.loadFromClasspath("/eu/dnetlib/pace/config/name_particles.txt");
+			particles = PaceCommonUtils.loadFromClasspath("/eu/dnetlib/pace/config/name_particles.txt");
 		}
 
 		final List<String> list = Lists.newArrayList();

dhp-common/src/main/java/eu/dnetlib/pace/util/Capitalise.java

@@ -15,4 +15,4 @@ public class Capitalise implements Function<String, String> {
 	public String apply(final String s) {
 		return WordUtils.capitalize(s.toLowerCase(), DELIM);
 	}
-};
+}

dhp-common/src/main/java/eu/dnetlib/pace/util/DotAbbreviations.java

@@ -8,4 +8,4 @@ public class DotAbbreviations implements Function<String, String> {
 	public String apply(String s) {
 		return s.length() == 1 ? s + "." : s;
 	}
-};
+}

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

@@ -1,109 +0,0 @@
-
-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
-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";
-
-	private final String depositionId = "674915";
-
-	@Test
-	void testUploadOldDeposition() throws IOException, MissingConceptDoiException {
-		ZenodoAPIClient client = new ZenodoAPIClient(URL_STRING,
-			ACCESS_TOKEN);
-		Assertions.assertEquals(200, client.uploadOpenDeposition(depositionId));
-
-		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"));
-
-		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
-	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"));
-
-		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
-	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"));
-
-		Assertions.assertEquals(202, client.publish());
-
-	}
-
-	@Test
-	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"));
-
-		Assertions.assertEquals(202, client.publish());
-
-	}
-
-}

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

@@ -63,7 +63,7 @@ public class MergeUtilsTest {
 		assertEquals(1, d1.getCollectedfrom().size());
 		assertTrue(cfId(d1.getCollectedfrom()).contains(ModelConstants.CROSSREF_ID));
 
-		final Result p1d2 = MergeUtils.checkedMerge(p1, d2);
+		final Result p1d2 = MergeUtils.checkedMerge(p1, d2, true);
 		assertEquals(ModelConstants.PUBLICATION_RESULTTYPE_CLASSID, p1d2.getResulttype().getClassid());
 		assertTrue(p1d2 instanceof Publication);
 		assertEquals(p1.getId(), p1d2.getId());
@@ -74,7 +74,7 @@ public class MergeUtilsTest {
 		Publication p2 = read("publication_2.json", Publication.class);
 		Dataset d1 = read("dataset_1.json", Dataset.class);
 
-		final Result p2d1 = MergeUtils.checkedMerge(p2, d1);
+		final Result p2d1 = MergeUtils.checkedMerge(p2, d1, true);
 		assertEquals((ModelConstants.DATASET_RESULTTYPE_CLASSID), p2d1.getResulttype().getClassid());
 		assertTrue(p2d1 instanceof Dataset);
 		assertEquals(d1.getId(), p2d1.getId());
@@ -86,7 +86,7 @@ public class MergeUtilsTest {
 		Publication p1 = read("publication_1.json", Publication.class);
 		Publication p2 = read("publication_2.json", Publication.class);
 
-		Result p1p2 = MergeUtils.checkedMerge(p1, p2);
+		Result p1p2 = MergeUtils.checkedMerge(p1, p2, true);
 		assertTrue(p1p2 instanceof Publication);
 		assertEquals(p1.getId(), p1p2.getId());
 		assertEquals(2, p1p2.getCollectedfrom().size());

dhp-pace-core/pom.xml

@@ -49,6 +49,12 @@
 	</build>
 
 	<dependencies>
+		<dependency>
+			<groupId>eu.dnetlib.dhp</groupId>
+			<artifactId>dhp-common</artifactId>
+			<version>${project.version}</version>
+		</dependency>
+
 		<dependency>
 			<groupId>edu.cmu</groupId>
 			<artifactId>secondstring</artifactId>

dhp-pace-core/src/main/java/eu/dnetlib/pace/common/AbstractPaceFunctions.java

@@ -4,7 +4,6 @@ package eu.dnetlib.pace.common;
 import java.io.IOException;
 import java.io.StringWriter;
 import java.nio.charset.StandardCharsets;
-import java.text.Normalizer;
 import java.util.*;
 import java.util.regex.Matcher;
 import java.util.regex.Pattern;
@@ -14,19 +13,15 @@ import org.apache.commons.io.IOUtils;
 import org.apache.commons.lang3.StringUtils;
 
 import com.google.common.base.Joiner;
-import com.google.common.base.Splitter;
-import com.google.common.collect.Iterables;
 import com.google.common.collect.Sets;
 import com.ibm.icu.text.Transliterator;
 
-import eu.dnetlib.pace.clustering.NGramUtils;
-
 /**
  * Set of common functions for the framework
  *
  * @author claudio
  */
-public class AbstractPaceFunctions {
+public class AbstractPaceFunctions extends PaceCommonUtils {
 
 	// city map to be used when translating the city names into codes
 	private static Map<String, String> cityMap = AbstractPaceFunctions
@@ -41,9 +36,6 @@ public class AbstractPaceFunctions {
 	protected static Set<String> stopwords_it = loadFromClasspath("/eu/dnetlib/pace/config/stopwords_it.txt");
 	protected static Set<String> stopwords_pt = loadFromClasspath("/eu/dnetlib/pace/config/stopwords_pt.txt");
 
-	// transliterator
-	protected static Transliterator transliterator = Transliterator.getInstance("Any-Eng");
-
 	// blacklist of ngrams: to avoid generic keys
 	protected static Set<String> ngramBlacklist = loadFromClasspath("/eu/dnetlib/pace/config/ngram_blacklist.txt");
 
@@ -51,8 +43,6 @@ public class AbstractPaceFunctions {
 	public static final Pattern HTML_REGEX = Pattern.compile("<[^>]*>");
 
 	private static final String alpha = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789 ";
-	private static final String aliases_from = "⁰¹²³⁴⁵⁶⁷⁸⁹⁺⁻⁼⁽⁾ⁿ₀₁₂₃₄₅₆₇₈₉₊₋₌₍₎àáâäæãåāèéêëēėęəîïíīįìôöòóœøōõûüùúūßśšłžźżçćčñń";
-	private static final String aliases_to = "0123456789+-=()n0123456789+-=()aaaaaaaaeeeeeeeeiiiiiioooooooouuuuussslzzzcccnn";
 
 	// doi prefix for normalization
 	public static final Pattern DOI_PREFIX = Pattern.compile("(https?:\\/\\/dx\\.doi\\.org\\/)|(doi:)");
@@ -129,25 +119,6 @@ public class AbstractPaceFunctions {
 		return numberPattern.matcher(strNum).matches();
 	}
 
-	protected static String fixAliases(final String s) {
-		final StringBuilder sb = new StringBuilder();
-
-		s.chars().forEach(ch -> {
-			final int i = StringUtils.indexOf(aliases_from, ch);
-			sb.append(i >= 0 ? aliases_to.charAt(i) : (char) ch);
-		});
-
-		return sb.toString();
-	}
-
-	protected static String transliterate(final String s) {
-		try {
-			return transliterator.transliterate(s);
-		} catch (Exception e) {
-			return s;
-		}
-	}
-
 	protected static String removeSymbols(final String s) {
 		final StringBuilder sb = new StringBuilder();
 
@@ -162,23 +133,6 @@ public class AbstractPaceFunctions {
 		return s != null;
 	}
 
-	public static String normalize(final String s) {
-		return fixAliases(transliterate(nfd(unicodeNormalization(s))))
-			.toLowerCase()
-			// do not compact the regexes in a single expression, would cause StackOverflowError in case of large input
-			// strings
-			.replaceAll("[^ \\w]+", "")
-			.replaceAll("(\\p{InCombiningDiacriticalMarks})+", "")
-			.replaceAll("(\\p{Punct})+", " ")
-			.replaceAll("(\\d)+", " ")
-			.replaceAll("(\\n)+", " ")
-			.trim();
-	}
-
-	public static String nfd(final String s) {
-		return Normalizer.normalize(s, Normalizer.Form.NFD);
-	}
-
 	public static String utf8(final String s) {
 		byte[] bytes = s.getBytes(StandardCharsets.UTF_8);
 		return new String(bytes, StandardCharsets.UTF_8);
@@ -233,22 +187,6 @@ public class AbstractPaceFunctions {
 		return newset;
 	}
 
-	public static Set<String> loadFromClasspath(final String classpath) {
-
-		Transliterator transliterator = Transliterator.getInstance("Any-Eng");
-
-		final Set<String> h = Sets.newHashSet();
-		try {
-			for (final String s : IOUtils
-				.readLines(NGramUtils.class.getResourceAsStream(classpath), StandardCharsets.UTF_8)) {
-				h.add(fixAliases(transliterator.transliterate(s))); // transliteration of the stopwords
-			}
-		} catch (final Throwable e) {
-			return Sets.newHashSet();
-		}
-		return h;
-	}
-
 	public static Map<String, String> loadMapFromClasspath(final String classpath) {
 
 		Transliterator transliterator = Transliterator.getInstance("Any-Eng");
@@ -303,10 +241,6 @@ public class AbstractPaceFunctions {
 		return StringUtils.substring(s, 0, 1).toLowerCase();
 	}
 
-	protected static Iterable<String> tokens(final String s, final int maxTokens) {
-		return Iterables.limit(Splitter.on(" ").omitEmptyStrings().trimResults().split(s), maxTokens);
-	}
-
 	public static String normalizePid(String pid) {
 		return DOI_PREFIX.matcher(pid.toLowerCase()).replaceAll("");
 	}

dhp-pace-core/src/main/java/eu/dnetlib/pace/tree/AuthorsMatch.java

@@ -1,19 +1,20 @@
 
 package eu.dnetlib.pace.tree;
 
-import com.wcohen.ss.AbstractStringDistance;
-import eu.dnetlib.pace.config.Config;
-import eu.dnetlib.pace.model.Person;
-import eu.dnetlib.pace.tree.support.AbstractListComparator;
-import eu.dnetlib.pace.tree.support.ComparatorClass;
-import eu.dnetlib.pace.util.AuthorMatchers;
-
 import java.util.ArrayList;
 import java.util.List;
 import java.util.Map;
 import java.util.function.BiFunction;
 import java.util.stream.Collectors;
 
+import com.wcohen.ss.AbstractStringDistance;
+
+import eu.dnetlib.pace.config.Config;
+import eu.dnetlib.pace.model.Person;
+import eu.dnetlib.pace.tree.support.AbstractListComparator;
+import eu.dnetlib.pace.tree.support.ComparatorClass;
+import eu.dnetlib.pace.util.AuthorMatchers;
+
 @ComparatorClass("authorsMatch")
 public class AuthorsMatch extends AbstractListComparator {
 

dhp-pace-core/src/main/java/eu/dnetlib/pace/tree/CountryMatch.java

@@ -0,0 +1,48 @@
+
+package eu.dnetlib.pace.tree;
+
+import java.util.Map;
+
+import com.wcohen.ss.AbstractStringDistance;
+
+import eu.dnetlib.pace.config.Config;
+import eu.dnetlib.pace.tree.support.AbstractStringComparator;
+import eu.dnetlib.pace.tree.support.ComparatorClass;
+
+@ComparatorClass("countryMatch")
+public class CountryMatch extends AbstractStringComparator {
+
+	public CountryMatch(Map<String, String> params) {
+		super(params, new com.wcohen.ss.JaroWinkler());
+	}
+
+	public CountryMatch(final double weight) {
+		super(weight, new com.wcohen.ss.JaroWinkler());
+	}
+
+	protected CountryMatch(final double weight, final AbstractStringDistance ssalgo) {
+		super(weight, ssalgo);
+	}
+
+	@Override
+	public double distance(final String a, final String b, final Config conf) {
+		if (a.isEmpty() || b.isEmpty()) {
+			return -1.0; // return -1 if a field is missing
+		}
+		if (a.equalsIgnoreCase("unknown") || b.equalsIgnoreCase("unknown")) {
+			return -1.0; // return -1 if a country is UNKNOWN
+		}
+
+		return a.equals(b) ? 1.0 : 0;
+	}
+
+	@Override
+	public double getWeight() {
+		return super.weight;
+	}
+
+	@Override
+	protected double normalize(final double d) {
+		return d;
+	}
+}

dhp-pace-core/src/test/java/eu/dnetlib/pace/comparators/ComparatorTest.java

@@ -336,4 +336,23 @@ public class ComparatorTest extends AbstractPaceTest {
 		System.out.println("compare = " + compare);
 	}
 
+	@Test
+	public void countryMatch() {
+
+		CountryMatch countryMatch = new CountryMatch(params);
+
+		double result = countryMatch.distance("UNKNOWN", "UNKNOWN", conf);
+		assertEquals(-1.0, result);
+
+		result = countryMatch.distance("CHILE", "UNKNOWN", conf);
+		assertEquals(-1.0, result);
+
+		result = countryMatch.distance("CHILE", "ITALY", conf);
+		assertEquals(0.0, result);
+
+		result = countryMatch.distance("CHILE", "CHILE", conf);
+		assertEquals(1.0, result);
+
+	}
+
 }

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

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

dhp-shade-package/dependency-reduced-pom.xml

@@ -0,0 +1,113 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
+  <parent>
+    <artifactId>dhp</artifactId>
+    <groupId>eu.dnetlib.dhp</groupId>
+    <version>1.2.5-SNAPSHOT</version>
+  </parent>
+  <modelVersion>4.0.0</modelVersion>
+  <artifactId>dhp-shade-package</artifactId>
+  <description>This module create a jar of all module dependencies</description>
+  <build>
+    <plugins>
+      <plugin>
+        <artifactId>maven-shade-plugin</artifactId>
+        <executions>
+          <execution>
+            <phase>package</phase>
+            <goals>
+              <goal>shade</goal>
+            </goals>
+            <configuration>
+              <transformers>
+                <transformer>
+                  <mainClass>eu.dnetlib.dhp.oa.dedup.SparkCreateSimRels</mainClass>
+                </transformer>
+                <transformer />
+                <transformer>
+                  <resource>META-INF/cxf/bus-extensions.txt</resource>
+                </transformer>
+              </transformers>
+              <filters>
+                <filter>
+                  <artifact>*:*</artifact>
+                  <excludes>
+                    <exclude>META-INF/maven/**</exclude>
+                    <exclude>META-INF/*.SF</exclude>
+                    <exclude>META-INF/*.DSA</exclude>
+                    <exclude>META-INF/*.RSA</exclude>
+                  </excludes>
+                </filter>
+              </filters>
+              <relocations>
+                <relocation>
+                  <pattern>com</pattern>
+                  <shadedPattern>repackaged.com.google.common</shadedPattern>
+                  <includes>
+                    <include>com.google.common.**</include>
+                  </includes>
+                </relocation>
+              </relocations>
+            </configuration>
+          </execution>
+        </executions>
+      </plugin>
+    </plugins>
+  </build>
+  <dependencies>
+    <dependency>
+      <groupId>org.projectlombok</groupId>
+      <artifactId>lombok</artifactId>
+      <version>1.18.28</version>
+      <scope>provided</scope>
+    </dependency>
+    <dependency>
+      <groupId>org.junit.jupiter</groupId>
+      <artifactId>junit-jupiter</artifactId>
+      <version>5.6.1</version>
+      <scope>test</scope>
+      <exclusions>
+        <exclusion>
+          <artifactId>junit-jupiter-api</artifactId>
+          <groupId>org.junit.jupiter</groupId>
+        </exclusion>
+        <exclusion>
+          <artifactId>junit-jupiter-params</artifactId>
+          <groupId>org.junit.jupiter</groupId>
+        </exclusion>
+        <exclusion>
+          <artifactId>junit-jupiter-engine</artifactId>
+          <groupId>org.junit.jupiter</groupId>
+        </exclusion>
+      </exclusions>
+    </dependency>
+    <dependency>
+      <groupId>org.mockito</groupId>
+      <artifactId>mockito-core</artifactId>
+      <version>3.3.3</version>
+      <scope>test</scope>
+      <exclusions>
+        <exclusion>
+          <artifactId>byte-buddy</artifactId>
+          <groupId>net.bytebuddy</groupId>
+        </exclusion>
+        <exclusion>
+          <artifactId>byte-buddy-agent</artifactId>
+          <groupId>net.bytebuddy</groupId>
+        </exclusion>
+      </exclusions>
+    </dependency>
+    <dependency>
+      <groupId>org.mockito</groupId>
+      <artifactId>mockito-junit-jupiter</artifactId>
+      <version>3.3.3</version>
+      <scope>test</scope>
+    </dependency>
+  </dependencies>
+  <distributionManagement>
+    <site>
+      <id>DHPSite</id>
+      <url>${dhp.site.stage.path}/dhp-common</url>
+    </site>
+  </distributionManagement>
+</project>

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

@@ -103,6 +103,7 @@
                 --executor-memory=${sparkExecutorMemory}
                 --executor-cores=${sparkExecutorCores}
                 --driver-memory=${sparkDriverMemory}
+                --conf spark.executor.memoryOverhead=${sparkExecutorMemory}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
@@ -156,6 +157,7 @@
                 --executor-memory=${sparkExecutorMemory}
                 --executor-cores=${sparkExecutorCores}
                 --driver-memory=${sparkDriverMemory}
+                --conf spark.executor.memoryOverhead=${sparkExecutorMemory}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}

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

@@ -95,6 +95,7 @@
                 --executor-memory=${sparkExecutorMemory}
                 --executor-cores=${sparkExecutorCores}
                 --driver-memory=${sparkDriverMemory}
+                --conf spark.executor.memoryOverhead=${sparkExecutorMemory}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}

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

@@ -125,6 +125,7 @@
                 --executor-memory=${sparkExecutorMemory}
                 --executor-cores=${sparkExecutorCores}
                 --driver-memory=${sparkDriverMemory}
+                --conf spark.executor.memoryOverhead=${sparkExecutorMemory}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}

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

@@ -95,6 +95,7 @@
                 --executor-memory=${sparkExecutorMemory}
                 --executor-cores=${sparkExecutorCores}
                 --driver-memory=${sparkDriverMemory}
+                --conf spark.executor.memoryOverhead=${sparkExecutorMemory}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}

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

@@ -103,6 +103,7 @@
                 --executor-memory=${sparkExecutorMemory}
                 --executor-cores=${sparkExecutorCores}
                 --driver-memory=${sparkDriverMemory}
+                --conf spark.executor.memoryOverhead=${sparkExecutorMemory}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
@@ -155,11 +156,12 @@
                 --executor-memory=${sparkExecutorMemory}
                 --executor-cores=${sparkExecutorCores}
                 --driver-memory=${sparkDriverMemory}
+                --conf spark.executor.memoryOverhead=${sparkExecutorMemory}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
                 --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-                --conf spark.sql.shuffle.partitions=2560
+                --conf spark.sql.shuffle.partitions=8000
             </spark-opts>
             <arg>--inputGraphTablePath</arg><arg>${workingDir}/otherresearchproduct</arg>
             <arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>

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

@@ -95,6 +95,7 @@
                 --executor-memory=${sparkExecutorMemory}
                 --executor-cores=${sparkExecutorCores}
                 --driver-memory=${sparkDriverMemory}
+                --conf spark.executor.memoryOverhead=${sparkExecutorMemory}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}

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

@@ -103,11 +103,12 @@
                 --executor-memory=${sparkExecutorMemory}
                 --executor-cores=${sparkExecutorCores}
                 --driver-memory=${sparkDriverMemory}
+                --conf spark.executor.memoryOverhead=${sparkExecutorMemory}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
                 --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-                --conf spark.sql.shuffle.partitions=7000
+                --conf spark.sql.shuffle.partitions=15000
             </spark-opts>
             <arg>--inputGraphTablePath</arg><arg>${inputGraphRootPath}/publication</arg>
             <arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
@@ -156,11 +157,12 @@
                 --executor-memory=${sparkExecutorMemory}
                 --executor-cores=${sparkExecutorCores}
                 --driver-memory=${sparkDriverMemory}
+                --conf spark.executor.memoryOverhead=${sparkExecutorMemory}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
                 --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-                --conf spark.sql.shuffle.partitions=7000
+                --conf spark.sql.shuffle.partitions=15000
             </spark-opts>
             <arg>--inputGraphTablePath</arg><arg>${workingDir}/publication</arg>
             <arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>

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

@@ -95,11 +95,12 @@
                 --executor-memory=${sparkExecutorMemory}
                 --executor-cores=${sparkExecutorCores}
                 --driver-memory=${sparkDriverMemory}
+                --conf spark.executor.memoryOverhead=${sparkExecutorMemory}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
                 --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-                --conf spark.sql.shuffle.partitions=10000
+                --conf spark.sql.shuffle.partitions=15000
             </spark-opts>
             <arg>--inputGraphTablePath</arg><arg>${inputGraphRootPath}/relation</arg>
             <arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Relation</arg>

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

@@ -103,6 +103,7 @@
                 --executor-memory=${sparkExecutorMemory}
                 --executor-cores=${sparkExecutorCores}
                 --driver-memory=${sparkDriverMemory}
+                --conf spark.executor.memoryOverhead=${sparkExecutorMemory}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
@@ -155,11 +156,12 @@
                 --executor-memory=${sparkExecutorMemory}
                 --executor-cores=${sparkExecutorCores}
                 --driver-memory=${sparkDriverMemory}
+                --conf spark.executor.memoryOverhead=${sparkExecutorMemory}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
                 --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-                --conf spark.sql.shuffle.partitions=2560
+                --conf spark.sql.shuffle.partitions=4000
             </spark-opts>
             <arg>--inputGraphTablePath</arg><arg>${workingDir}/software</arg>
             <arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>

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

@@ -42,6 +42,9 @@ public class Constants {
 	public static final String NULL = "NULL";
 	public static final String NA = "N/A";
 
+	public static final String WEB_CRAWL_ID = "10|openaire____::fb98a192f6a055ba495ef414c330834b";
+	public static final String WEB_CRAWL_NAME = "Web Crawl";
+
 	public static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
 
 	private Constants() {

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

@@ -9,6 +9,7 @@ import java.util.List;
 
 import org.apache.commons.io.IOUtils;
 import org.apache.hadoop.io.Text;
+import org.apache.hadoop.io.compress.BZip2Codec;
 import org.apache.hadoop.io.compress.GzipCodec;
 import org.apache.hadoop.mapred.SequenceFileOutputFormat;
 import org.apache.spark.SparkConf;
@@ -40,9 +41,9 @@ public class PrepareAffiliationRelations implements Serializable {
 	private static final Logger log = LoggerFactory.getLogger(PrepareAffiliationRelations.class);
 	private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
 	private static final String ID_PREFIX = "50|doi_________::";
-	public static final String BIP_AFFILIATIONS_CLASSID = "result:organization:bipinference";
-	public static final String BIP_AFFILIATIONS_CLASSNAME = "Affiliation relation inferred by BIP!";
-	public static final String BIP_INFERENCE_PROVENANCE = "bip:affiliation:crossref";
+	public static final String BIP_AFFILIATIONS_CLASSID = "result:organization:openaireinference";
+	public static final String BIP_AFFILIATIONS_CLASSNAME = "Affiliation relation inferred by OpenAIRE";
+	public static final String BIP_INFERENCE_PROVENANCE = "openaire:affiliation";
 
 	public static <I extends Result> void main(String[] args) throws Exception {
 
@@ -70,6 +71,9 @@ public class PrepareAffiliationRelations implements Serializable {
 		final String dataciteInputPath = parser.get("dataciteInputPath");
 		log.info("dataciteInputPath: {}", dataciteInputPath);
 
+		final String webcrawlInputPath = parser.get("webCrawlInputPath");
+		log.info("webcrawlInputPath: {}", webcrawlInputPath);
+
 		final String outputPath = parser.get("outputPath");
 		log.info("outputPath: {}", outputPath);
 
@@ -101,12 +105,18 @@ public class PrepareAffiliationRelations implements Serializable {
 				JavaPairRDD<Text, Text> dataciteRelations = prepareAffiliationRelations(
 					spark, dataciteInputPath, collectedFromDatacite);
 
+				List<KeyValue> collectedFromWebCrawl = OafMapperUtils
+					.listKeyValues(Constants.WEB_CRAWL_ID, Constants.WEB_CRAWL_NAME);
+				JavaPairRDD<Text, Text> webCrawlRelations = prepareAffiliationRelations(
+					spark, webcrawlInputPath, collectedFromWebCrawl);
+
 				crossrefRelations
 					.union(pubmedRelations)
 					.union(openAPCRelations)
 					.union(dataciteRelations)
+					.union(webCrawlRelations)
 					.saveAsHadoopFile(
-						outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class);
+						outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, BZip2Codec.class);
 
 			});
 	}

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

@@ -80,9 +80,11 @@ public class PrepareFOSSparkJob implements Serializable {
 
 		fosDataset
 			.groupByKey((MapFunction<FOSDataModel, String>) v -> v.getOaid().toLowerCase(), Encoders.STRING())
-			.mapGroups((MapGroupsFunction<String, FOSDataModel, Result>) (k, it) -> {
-				return getResult(ModelSupport.getIdPrefix(Result.class) + "|" + k, it);
-			}, Encoders.bean(Result.class))
+			.mapGroups(
+				(MapGroupsFunction<String, FOSDataModel, Result>) (k,
+					it) -> getResult(
+						ModelSupport.entityIdPrefix.get(Result.class.getSimpleName().toLowerCase()) + "|" + k, it),
+				Encoders.bean(Result.class))
 			.write()
 			.mode(SaveMode.Overwrite)
 			.option("compression", "gzip")
@@ -113,19 +115,7 @@ public class PrepareFOSSparkJob implements Serializable {
 			.forEach(
 				l -> add(sbjs, getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID, true)));
 		r.setSubject(sbjs);
-		r
-			.setDataInfo(
-				OafMapperUtils
-					.dataInfo(
-						false, null, true,
-						false,
-						OafMapperUtils
-							.qualifier(
-								ModelConstants.PROVENANCE_ENRICH,
-								null,
-								ModelConstants.DNET_PROVENANCE_ACTIONS,
-								ModelConstants.DNET_PROVENANCE_ACTIONS),
-						null));
+
 		return r;
 	}
 

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

@@ -81,19 +81,7 @@ public class PrepareSDGSparkJob implements Serializable {
 						s -> sbjs
 							.add(getSubject(s.getSbj(), SDG_CLASS_ID, SDG_CLASS_NAME, UPDATE_SUBJECT_SDG_CLASS_ID)));
 				r.setSubject(sbjs);
-				r
-					.setDataInfo(
-						OafMapperUtils
-							.dataInfo(
-								false, null, true,
-								false,
-								OafMapperUtils
-									.qualifier(
-										ModelConstants.PROVENANCE_ENRICH,
-										null,
-										ModelConstants.DNET_PROVENANCE_ACTIONS,
-										ModelConstants.DNET_PROVENANCE_ACTIONS),
-								null));
+
 				return r;
 			}, Encoders.bean(Result.class))
 			.write()

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

@@ -93,7 +93,7 @@ public class CreateActionSetSparkJob implements Serializable {
 			.filter((FilterFunction<Relation>) Objects::nonNull)
 			.toJavaRDD()
 			.map(p -> new AtomicAction(p.getClass(), p));
-//TODO relations in stand-by waiting to know if we need to create them or not In case we need just make a union before saving the sequence file
+
 		spark
 			.read()
 			.textFile(inputPath)
@@ -108,6 +108,7 @@ public class CreateActionSetSparkJob implements Serializable {
 			.filter((FilterFunction<Result>) r -> r != null)
 			.toJavaRDD()
 			.map(p -> new AtomicAction(p.getClass(), p))
+			.union(relations)
 			.mapToPair(
 				aa -> new Tuple2<>(new Text(aa.getClazz().getCanonicalName()),
 					new Text(OBJECT_MAPPER.writeValueAsString(aa))))

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

@@ -0,0 +1,258 @@
+
+package eu.dnetlib.dhp.actionmanager.webcrawl;
+
+import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
+
+import java.io.Serializable;
+import java.util.*;
+import java.util.stream.Collectors;
+
+import org.apache.commons.io.IOUtils;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.io.compress.GzipCodec;
+import org.apache.hadoop.mapred.SequenceFileOutputFormat;
+import org.apache.spark.SparkConf;
+import org.apache.spark.api.java.function.FilterFunction;
+import org.apache.spark.api.java.function.FlatMapFunction;
+import org.apache.spark.sql.*;
+import org.apache.spark.sql.types.StructType;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import com.fasterxml.jackson.databind.ObjectMapper;
+
+import eu.dnetlib.dhp.actionmanager.Constants;
+import eu.dnetlib.dhp.application.ArgumentApplicationParser;
+import eu.dnetlib.dhp.schema.action.AtomicAction;
+import eu.dnetlib.dhp.schema.common.ModelConstants;
+import eu.dnetlib.dhp.schema.oaf.Relation;
+import eu.dnetlib.dhp.schema.oaf.utils.IdentifierFactory;
+import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
+import eu.dnetlib.dhp.schema.oaf.utils.PidCleaner;
+import eu.dnetlib.dhp.schema.oaf.utils.PidType;
+import io.netty.util.Constant;
+import scala.Tuple2;
+
+/**
+ * @author miriam.baglioni
+ * @Date 18/04/24
+ */
+public class CreateActionSetFromWebEntries implements Serializable {
+	private static final Logger log = LoggerFactory.getLogger(CreateActionSetFromWebEntries.class);
+	private static final String DOI_PREFIX = "50|doi_________::";
+
+	private static final String ROR_PREFIX = "20|ror_________::";
+
+	private static final String PMID_PREFIX = "50|pmid________::";
+
+	private static final String PMCID_PREFIX = "50|pmc_________::";
+
+	public static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
+
+	public static void main(String[] args) throws Exception {
+		String jsonConfiguration = IOUtils
+			.toString(
+				CreateActionSetFromWebEntries.class
+					.getResourceAsStream(
+						"/eu/dnetlib/dhp/actionmanager/webcrawl/as_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 blackListInputPath = parser.get("blackListPath");
+		log.info("blackListInputPath: {}", blackListInputPath);
+
+		SparkConf conf = new SparkConf();
+
+		runWithSparkSession(
+			conf,
+			isSparkSessionManaged,
+			spark -> {
+
+				createActionSet(spark, inputPath, outputPath, blackListInputPath);
+
+			});
+	}
+
+	public static void createActionSet(SparkSession spark, String inputPath,
+		String outputPath, String blackListInputPath) {
+
+		final Dataset<Row> dataset = readWebCrawl(spark, inputPath)
+			.filter("country_code=='IE'")
+			.drop("publication_year");
+
+		final Dataset<Row> blackList = readBlackList(spark, blackListInputPath);
+
+		dataset
+			.join(blackList, dataset.col("id").equalTo(blackList.col("OpenAlexId")), "left")
+			.filter((FilterFunction<Row>) r -> r.getAs("OpenAlexId") == null)
+			.drop("OpenAlexId")
+			.flatMap((FlatMapFunction<Row, Relation>) row -> {
+				List<Relation> ret = new ArrayList<>();
+				final String ror = ROR_PREFIX
+					+ IdentifierFactory.md5(PidCleaner.normalizePidValue("ROR", row.getAs("ror")));
+				ret.addAll(createAffiliationRelationPairDOI(row.getAs("doi"), ror));
+//				ret.addAll(createAffiliationRelationPairPMID(row.getAs("pmid"), ror));
+//				ret.addAll(createAffiliationRelationPairPMCID(row.getAs("pmcid"), ror));
+
+				return ret
+					.iterator();
+			}, Encoders.bean(Relation.class))
+			.toJavaRDD()
+			.map(p -> new AtomicAction(p.getClass(), p))
+			.mapToPair(
+				aa -> new Tuple2<>(new Text(aa.getClazz().getCanonicalName()),
+					new Text(OBJECT_MAPPER.writeValueAsString(aa))))
+			.saveAsHadoopFile(outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class);
+
+	}
+
+	private static Dataset<Row> readWebCrawl(SparkSession spark, String inputPath) {
+		StructType webInfo = StructType
+			.fromDDL(
+				"`id` STRING , `doi` STRING, `ids` STRUCT<`pmid` :STRING, `pmcid`: STRING >, `publication_year` STRING, "
+					+
+					"`authorships` ARRAY<STRUCT <`institutions`: ARRAY <STRUCT <`ror`: STRING, `country_code` :STRING>>>>");
+
+		return spark
+			.read()
+			.schema(webInfo)
+			.json(inputPath)
+			.withColumn(
+				"authors", functions
+					.explode(
+						functions.col("authorships")))
+			.selectExpr("id", "doi", "ids", "publication_year", "authors.institutions as institutions")
+			.withColumn(
+				"institution", functions
+					.explode(
+						functions.col("institutions")))
+
+			.selectExpr(
+				"id", "doi", "institution.ror as ror",
+				"institution.country_code as country_code", "publication_year")
+			.distinct();
+
+//			.selectExpr(
+//				"id", "doi", "ids.pmcid as pmcid", "ids.pmid as pmid", "institution.ror as ror",
+//				"institution.country_code as country_code", "publication_year")
+//			.distinct();
+
+	}
+
+	private static Dataset<Row> readBlackList(SparkSession spark, String inputPath) {
+
+		return spark
+			.read()
+			.option("header", true)
+			.csv(inputPath)
+			.select("OpenAlexId");
+	}
+
+	private static List<Relation> createAffiliationRelationPairPMCID(String pmcid, String ror) {
+		if (pmcid == null)
+			return new ArrayList<>();
+
+		return createAffiliatioRelationPair(
+			PMCID_PREFIX
+				+ IdentifierFactory
+					.md5(PidCleaner.normalizePidValue(PidType.pmc.toString(), removeResolver("PMC", pmcid))),
+			ror);
+	}
+
+	private static List<Relation> createAffiliationRelationPairPMID(String pmid, String ror) {
+		if (pmid == null)
+			return new ArrayList<>();
+
+		return createAffiliatioRelationPair(
+			PMID_PREFIX
+				+ IdentifierFactory
+					.md5(PidCleaner.normalizePidValue(PidType.pmid.toString(), removeResolver("PMID", pmid))),
+			ror);
+	}
+
+	private static String removeResolver(String pidType, String pid) {
+		switch (pidType) {
+			case "PMID":
+				return pid.substring(33);
+			case "PMC":
+				return "PMC" + pid.substring(43);
+			case "DOI":
+				return pid.substring(16);
+		}
+
+		throw new RuntimeException();
+
+	}
+
+	private static List<Relation> createAffiliationRelationPairDOI(String doi, String ror) {
+		if (doi == null)
+			return new ArrayList<>();
+
+		return createAffiliatioRelationPair(
+			DOI_PREFIX
+				+ IdentifierFactory
+					.md5(PidCleaner.normalizePidValue(PidType.doi.toString(), removeResolver("DOI", doi))),
+			ror);
+
+	}
+
+	private static List<Relation> createAffiliatioRelationPair(String resultId, String orgId) {
+		ArrayList<Relation> newRelations = new ArrayList();
+
+		newRelations
+			.add(
+				OafMapperUtils
+					.getRelation(
+						orgId, resultId, ModelConstants.RESULT_ORGANIZATION, ModelConstants.AFFILIATION,
+						ModelConstants.IS_AUTHOR_INSTITUTION_OF,
+						Arrays
+							.asList(
+								OafMapperUtils.keyValue(Constants.WEB_CRAWL_ID, Constants.WEB_CRAWL_NAME)),
+						OafMapperUtils
+							.dataInfo(
+								false, null, false, false,
+								OafMapperUtils
+									.qualifier(
+										"sysimport:crasswalk:webcrawl", "Imported from Webcrawl",
+										ModelConstants.DNET_PROVENANCE_ACTIONS, ModelConstants.DNET_PROVENANCE_ACTIONS),
+								"0.9"),
+						null));
+
+		newRelations
+			.add(
+				OafMapperUtils
+					.getRelation(
+						resultId, orgId, ModelConstants.RESULT_ORGANIZATION, ModelConstants.AFFILIATION,
+						ModelConstants.HAS_AUTHOR_INSTITUTION,
+						Arrays
+							.asList(
+								OafMapperUtils.keyValue(Constants.WEB_CRAWL_ID, Constants.WEB_CRAWL_NAME)),
+						OafMapperUtils
+							.dataInfo(
+								false, null, false, false,
+								OafMapperUtils
+									.qualifier(
+										"sysimport:crasswalk:webcrawl", "Imported from Webcrawl",
+										ModelConstants.DNET_PROVENANCE_ACTIONS, ModelConstants.DNET_PROVENANCE_ACTIONS),
+								"0.9"),
+						null));
+
+		return newRelations;
+
+	}
+
+}

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/collection/plugin/rest/RestIterator.java

@@ -18,7 +18,11 @@ import javax.xml.transform.TransformerConfigurationException;
 import javax.xml.transform.TransformerFactory;
 import javax.xml.transform.dom.DOMSource;
 import javax.xml.transform.stream.StreamResult;
-import javax.xml.xpath.*;
+import javax.xml.xpath.XPath;
+import javax.xml.xpath.XPathConstants;
+import javax.xml.xpath.XPathExpression;
+import javax.xml.xpath.XPathExpressionException;
+import javax.xml.xpath.XPathFactory;
 
 import org.apache.commons.io.IOUtils;
 import org.apache.commons.lang3.StringUtils;
@@ -35,7 +39,7 @@ import eu.dnetlib.dhp.common.collection.CollectorException;
 import eu.dnetlib.dhp.common.collection.HttpClientParams;
 
 /**
- * log.info(...) equal to  log.trace(...) in the application-logs
+ * log.info(...) equal to log.trace(...) in the application-logs
  * <p>
  * known bug: at resumptionType 'discover' if the (resultTotal % resultSizeValue) == 0 the collecting fails -> change the resultSizeValue
  *
@@ -47,6 +51,7 @@ public class RestIterator implements Iterator<String> {
 
 	private static final Logger log = LoggerFactory.getLogger(RestIterator.class);
 	public static final String UTF_8 = "UTF-8";
+	private static final int MAX_ATTEMPTS = 5;
 
 	private final HttpClientParams clientParams;
 
@@ -60,8 +65,9 @@ public class RestIterator implements Iterator<String> {
 	private final int resultSizeValue;
 	private int resumptionInt = 0; // integer resumption token (first record to harvest)
 	private int resultTotal = -1;
-	private String resumptionStr = Integer.toString(resumptionInt); // string resumption token (first record to harvest
-																	// or token scanned from results)
+	private String resumptionStr = Integer.toString(this.resumptionInt); // string resumption token (first record to
+																			// harvest
+	// or token scanned from results)
 	private InputStream resultStream;
 	private Transformer transformer;
 	private XPath xpath;
@@ -73,7 +79,7 @@ public class RestIterator implements Iterator<String> {
 	private final String querySize;
 	private final String authMethod;
 	private final String authToken;
-	private final Queue<String> recordQueue = new PriorityBlockingQueue<String>();
+	private final Queue<String> recordQueue = new PriorityBlockingQueue<>();
 	private int discoverResultSize = 0;
 	private int pagination = 1;
 	/*
@@ -83,8 +89,8 @@ public class RestIterator implements Iterator<String> {
 	 */
 	private final String resultOutputFormat;
 
-	/** RestIterator class
-	 *  compatible to version 1.3.33
+	/**
+	 * RestIterator class compatible to version 1.3.33
 	 */
 	public RestIterator(
 		final HttpClientParams clientParams,
@@ -108,40 +114,42 @@ public class RestIterator implements Iterator<String> {
 		this.resumptionType = resumptionType;
 		this.resumptionParam = resumptionParam;
 		this.resultFormatValue = resultFormatValue;
-		this.resultSizeValue = Integer.valueOf(resultSizeValueStr);
+		this.resultSizeValue = Integer.parseInt(resultSizeValueStr);
 		this.queryParams = queryParams;
 		this.authMethod = authMethod;
 		this.authToken = authToken;
 		this.resultOutputFormat = resultOutputFormat;
 
-		queryFormat = StringUtils.isNotBlank(resultFormatParam) ? "&" + resultFormatParam + "=" + resultFormatValue
+		this.queryFormat = StringUtils.isNotBlank(resultFormatParam) ? "&" + resultFormatParam + "=" + resultFormatValue
+			: "";
+		this.querySize = StringUtils.isNotBlank(resultSizeParam) ? "&" + resultSizeParam + "=" + resultSizeValueStr
 			: "";
-		querySize = StringUtils.isNotBlank(resultSizeParam) ? "&" + resultSizeParam + "=" + resultSizeValueStr : "";
 
 		try {
 			initXmlTransformation(resultTotalXpath, resumptionXpath, entityXpath);
-		} catch (Exception e) {
+		} catch (final Exception e) {
 			throw new IllegalStateException("xml transformation init failed: " + e.getMessage());
 		}
 
 		initQueue();
 	}
 
-	private void initXmlTransformation(String resultTotalXpath, String resumptionXpath, String entityXpath)
+	private void initXmlTransformation(final String resultTotalXpath, final String resumptionXpath,
+		final String entityXpath)
 		throws TransformerConfigurationException, XPathExpressionException {
 		final TransformerFactory factory = TransformerFactory.newInstance();
-		transformer = factory.newTransformer();
-		transformer.setOutputProperty(OutputKeys.INDENT, "yes");
-		transformer.setOutputProperty("{http://xml.apache.org/xslt}indent-amount", "3");
-		xpath = XPathFactory.newInstance().newXPath();
-		xprResultTotalPath = xpath.compile(resultTotalXpath);
-		xprResumptionPath = xpath.compile(StringUtils.isBlank(resumptionXpath) ? "/" : resumptionXpath);
-		xprEntity = xpath.compile(entityXpath);
+		this.transformer = factory.newTransformer();
+		this.transformer.setOutputProperty(OutputKeys.INDENT, "yes");
+		this.transformer.setOutputProperty("{http://xml.apache.org/xslt}indent-amount", "3");
+		this.xpath = XPathFactory.newInstance().newXPath();
+		this.xprResultTotalPath = this.xpath.compile(resultTotalXpath);
+		this.xprResumptionPath = this.xpath.compile(StringUtils.isBlank(resumptionXpath) ? "/" : resumptionXpath);
+		this.xprEntity = this.xpath.compile(entityXpath);
 	}
 
 	private void initQueue() {
-		query = baseUrl + "?" + queryParams + querySize + queryFormat;
-		log.info("REST calls starting with {}", query);
+		this.query = this.baseUrl + "?" + this.queryParams + this.querySize + this.queryFormat;
+		log.info("REST calls starting with {}", this.query);
 	}
 
 	private void disconnect() {
@@ -154,12 +162,11 @@ public class RestIterator implements Iterator<String> {
 	 */
 	@Override
 	public boolean hasNext() {
-		if (recordQueue.isEmpty() && query.isEmpty()) {
+		if (this.recordQueue.isEmpty() && this.query.isEmpty()) {
 			disconnect();
 			return false;
-		} else {
-			return true;
 		}
+		return true;
 	}
 
 	/*
@@ -168,214 +175,241 @@ public class RestIterator implements Iterator<String> {
 	 */
 	@Override
 	public String next() {
-		synchronized (recordQueue) {
-			while (recordQueue.isEmpty() && !query.isEmpty()) {
+		synchronized (this.recordQueue) {
+			while (this.recordQueue.isEmpty() && !this.query.isEmpty()) {
 				try {
-					query = downloadPage(query);
-				} catch (CollectorException e) {
+					this.query = downloadPage(this.query, 0);
+				} catch (final CollectorException e) {
 					log.debug("CollectorPlugin.next()-Exception: {}", e);
 					throw new RuntimeException(e);
 				}
 			}
-			return recordQueue.poll();
+			return this.recordQueue.poll();
 		}
 	}
 
 	/*
-	 * download page and return nextQuery
+	 * download page and return nextQuery (with number of attempt)
 	 */
-	private String downloadPage(String query) throws CollectorException {
-		String resultJson;
-		String resultXml = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>";
-		String nextQuery = "";
-		String emptyXml = resultXml + "<" + JsonUtils.XML_WRAP_TAG + "></" + JsonUtils.XML_WRAP_TAG + ">";
-		Node resultNode = null;
-		NodeList nodeList = null;
-		String qUrlArgument = "";
-		int urlOldResumptionSize = 0;
-		InputStream theHttpInputStream;
+	private String downloadPage(String query, final int attempt) throws CollectorException {
 
-		// check if cursor=* is initial set otherwise add it to the queryParam URL
-		if (resumptionType.equalsIgnoreCase("deep-cursor")) {
-			log.debug("check resumptionType deep-cursor and check cursor=*?{}", query);
-			if (!query.contains("&cursor=")) {
-				query += "&cursor=*";
+		if (attempt > MAX_ATTEMPTS) {
+			throw new CollectorException("Max Number of attempts reached, query:" + query);
+		}
+
+		if (attempt > 0) {
+			final int delay = (attempt * 5000);
+			log.debug("Attempt {} with delay {}", attempt, delay);
+			try {
+				Thread.sleep(delay);
+			} catch (final InterruptedException e) {
+				new CollectorException(e);
 			}
 		}
 
 		try {
-			log.info("requestig URL [{}]", query);
+			String resultJson;
+			String resultXml = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>";
+			String nextQuery = "";
+			final String emptyXml = resultXml + "<" + JsonUtils.XML_WRAP_TAG + "></" + JsonUtils.XML_WRAP_TAG + ">";
+			Node resultNode = null;
+			NodeList nodeList = null;
+			String qUrlArgument = "";
+			int urlOldResumptionSize = 0;
+			InputStream theHttpInputStream;
 
-			URL qUrl = new URL(query);
-			log.debug("authMethod: {}", authMethod);
-			if ("bearer".equalsIgnoreCase(this.authMethod)) {
-				log.trace("authMethod before inputStream: {}", resultXml);
-				HttpURLConnection conn = (HttpURLConnection) qUrl.openConnection();
-				conn.setRequestProperty(HttpHeaders.AUTHORIZATION, "Bearer " + authToken);
-				conn.setRequestProperty(HttpHeaders.CONTENT_TYPE, ContentType.APPLICATION_JSON.getMimeType());
-				conn.setRequestMethod("GET");
-				theHttpInputStream = conn.getInputStream();
-			} else if (BASIC.equalsIgnoreCase(this.authMethod)) {
-				log.trace("authMethod before inputStream: {}", resultXml);
-				HttpURLConnection conn = (HttpURLConnection) qUrl.openConnection();
-				conn.setRequestProperty(HttpHeaders.AUTHORIZATION, "Basic " + authToken);
-				conn.setRequestProperty(HttpHeaders.ACCEPT, ContentType.APPLICATION_XML.getMimeType());
-				conn.setRequestMethod("GET");
-				theHttpInputStream = conn.getInputStream();
-			} else {
-				theHttpInputStream = qUrl.openStream();
-			}
-
-			resultStream = theHttpInputStream;
-			if ("json".equals(resultOutputFormat)) {
-				resultJson = IOUtils.toString(resultStream, StandardCharsets.UTF_8);
-				resultXml = JsonUtils.convertToXML(resultJson);
-				resultStream = IOUtils.toInputStream(resultXml, UTF_8);
-			}
-
-			if (!(emptyXml).equalsIgnoreCase(resultXml)) {
-				resultNode = (Node) xpath.evaluate("/", new InputSource(resultStream), XPathConstants.NODE);
-				nodeList = (NodeList) xprEntity.evaluate(resultNode, XPathConstants.NODESET);
-				log.debug("nodeList.length: {}", nodeList.getLength());
-				for (int i = 0; i < nodeList.getLength(); i++) {
-					StringWriter sw = new StringWriter();
-					transformer.transform(new DOMSource(nodeList.item(i)), new StreamResult(sw));
-					String toEnqueue = sw.toString();
-					if (toEnqueue == null || StringUtils.isBlank(toEnqueue) || emptyXml.equalsIgnoreCase(toEnqueue)) {
-						log.warn("The following record resulted in empty item for the feeding queue: {}", resultXml);
-					} else {
-						recordQueue.add(sw.toString());
-					}
+			// check if cursor=* is initial set otherwise add it to the queryParam URL
+			if ("deep-cursor".equalsIgnoreCase(this.resumptionType)) {
+				log.debug("check resumptionType deep-cursor and check cursor=*?{}", query);
+				if (!query.contains("&cursor=")) {
+					query += "&cursor=*";
 				}
-			} else {
-				log.warn("resultXml is equal with emptyXml");
 			}
 
-			resumptionInt += resultSizeValue;
+			try {
+				log.info("requesting URL [{}]", query);
 
-			switch (resumptionType.toLowerCase()) {
-				case "scan": // read of resumptionToken , evaluate next results, e.g. OAI, iterate over items
-					resumptionStr = xprResumptionPath.evaluate(resultNode);
-					break;
+				final URL qUrl = new URL(query);
+				log.debug("authMethod: {}", this.authMethod);
+				if ("bearer".equalsIgnoreCase(this.authMethod)) {
+					log.trace("authMethod before inputStream: {}", resultXml);
+					final HttpURLConnection conn = (HttpURLConnection) qUrl.openConnection();
+					conn.setRequestProperty(HttpHeaders.AUTHORIZATION, "Bearer " + this.authToken);
+					conn.setRequestProperty(HttpHeaders.CONTENT_TYPE, ContentType.APPLICATION_JSON.getMimeType());
+					conn.setRequestMethod("GET");
+					theHttpInputStream = conn.getInputStream();
+				} else if (this.BASIC.equalsIgnoreCase(this.authMethod)) {
+					log.trace("authMethod before inputStream: {}", resultXml);
+					final HttpURLConnection conn = (HttpURLConnection) qUrl.openConnection();
+					conn.setRequestProperty(HttpHeaders.AUTHORIZATION, "Basic " + this.authToken);
+					conn.setRequestProperty(HttpHeaders.ACCEPT, ContentType.APPLICATION_XML.getMimeType());
+					conn.setRequestMethod("GET");
+					theHttpInputStream = conn.getInputStream();
+				} else {
+					theHttpInputStream = qUrl.openStream();
+				}
 
-				case "count": // begin at one step for all records, iterate over items
-					resumptionStr = Integer.toString(resumptionInt);
-					break;
+				this.resultStream = theHttpInputStream;
+				if ("json".equals(this.resultOutputFormat)) {
+					resultJson = IOUtils.toString(this.resultStream, StandardCharsets.UTF_8);
+					resultXml = JsonUtils.convertToXML(resultJson);
+					this.resultStream = IOUtils.toInputStream(resultXml, UTF_8);
+				}
 
-				case "discover": // size of result items unknown, iterate over items (for openDOAR - 201808)
-					if (resultSizeValue < 2) {
-						throw new CollectorException("Mode: discover, Param 'resultSizeValue' is less than 2");
+				if (!(emptyXml).equalsIgnoreCase(resultXml)) {
+					resultNode = (Node) this.xpath
+						.evaluate("/", new InputSource(this.resultStream), XPathConstants.NODE);
+					nodeList = (NodeList) this.xprEntity.evaluate(resultNode, XPathConstants.NODESET);
+					log.debug("nodeList.length: {}", nodeList.getLength());
+					for (int i = 0; i < nodeList.getLength(); i++) {
+						final StringWriter sw = new StringWriter();
+						this.transformer.transform(new DOMSource(nodeList.item(i)), new StreamResult(sw));
+						final String toEnqueue = sw.toString();
+						if ((toEnqueue == null) || StringUtils.isBlank(toEnqueue)
+							|| emptyXml.equalsIgnoreCase(toEnqueue)) {
+							log
+								.warn(
+									"The following record resulted in empty item for the feeding queue: {}", resultXml);
+						} else {
+							this.recordQueue.add(sw.toString());
+						}
 					}
-					qUrlArgument = qUrl.getQuery();
-					String[] arrayQUrlArgument = qUrlArgument.split("&");
-					for (String arrayUrlArgStr : arrayQUrlArgument) {
-						if (arrayUrlArgStr.startsWith(resumptionParam)) {
-							String[] resumptionKeyValue = arrayUrlArgStr.split("=");
-							if (isInteger(resumptionKeyValue[1])) {
-								urlOldResumptionSize = Integer.parseInt(resumptionKeyValue[1]);
-								log.debug("discover OldResumptionSize from Url (int): {}", urlOldResumptionSize);
-							} else {
-								log.debug("discover OldResumptionSize from Url (str): {}", resumptionKeyValue[1]);
+				} else {
+					log.warn("resultXml is equal with emptyXml");
+				}
+
+				this.resumptionInt += this.resultSizeValue;
+
+				switch (this.resumptionType.toLowerCase()) {
+					case "scan": // read of resumptionToken , evaluate next results, e.g. OAI, iterate over items
+						this.resumptionStr = this.xprResumptionPath.evaluate(resultNode);
+						break;
+
+					case "count": // begin at one step for all records, iterate over items
+						this.resumptionStr = Integer.toString(this.resumptionInt);
+						break;
+
+					case "discover": // size of result items unknown, iterate over items (for openDOAR - 201808)
+						if (this.resultSizeValue < 2) {
+							throw new CollectorException("Mode: discover, Param 'resultSizeValue' is less than 2");
+						}
+						qUrlArgument = qUrl.getQuery();
+						final String[] arrayQUrlArgument = qUrlArgument.split("&");
+						for (final String arrayUrlArgStr : arrayQUrlArgument) {
+							if (arrayUrlArgStr.startsWith(this.resumptionParam)) {
+								final String[] resumptionKeyValue = arrayUrlArgStr.split("=");
+								if (isInteger(resumptionKeyValue[1])) {
+									urlOldResumptionSize = Integer.parseInt(resumptionKeyValue[1]);
+									log.debug("discover OldResumptionSize from Url (int): {}", urlOldResumptionSize);
+								} else {
+									log.debug("discover OldResumptionSize from Url (str): {}", resumptionKeyValue[1]);
+								}
 							}
 						}
-					}
 
-					if (((emptyXml).equalsIgnoreCase(resultXml))
-						|| ((nodeList != null) && (nodeList.getLength() < resultSizeValue))) {
-						// resumptionStr = "";
-						if (nodeList != null) {
-							discoverResultSize += nodeList.getLength();
+						if (((emptyXml).equalsIgnoreCase(resultXml))
+							|| ((nodeList != null) && (nodeList.getLength() < this.resultSizeValue))) {
+							// resumptionStr = "";
+							if (nodeList != null) {
+								this.discoverResultSize += nodeList.getLength();
+							}
+							this.resultTotal = this.discoverResultSize;
+						} else {
+							this.resumptionStr = Integer.toString(this.resumptionInt);
+							this.resultTotal = this.resumptionInt + 1;
+							if (nodeList != null) {
+								this.discoverResultSize += nodeList.getLength();
+							}
 						}
-						resultTotal = discoverResultSize;
-					} else {
-						resumptionStr = Integer.toString(resumptionInt);
-						resultTotal = resumptionInt + 1;
+						log.info("discoverResultSize: {}", this.discoverResultSize);
+						break;
+
+					case "pagination":
+					case "page": // pagination, iterate over page numbers
+						this.pagination += 1;
 						if (nodeList != null) {
-							discoverResultSize += nodeList.getLength();
+							this.discoverResultSize += nodeList.getLength();
+						} else {
+							this.resultTotal = this.discoverResultSize;
+							this.pagination = this.discoverResultSize;
 						}
-					}
-					log.info("discoverResultSize: {}", discoverResultSize);
-					break;
+						this.resumptionInt = this.pagination;
+						this.resumptionStr = Integer.toString(this.resumptionInt);
+						break;
 
-				case "pagination":
-				case "page": // pagination, iterate over page numbers
-					pagination += 1;
-					if (nodeList != null) {
-						discoverResultSize += nodeList.getLength();
-					} else {
-						resultTotal = discoverResultSize;
-						pagination = discoverResultSize;
-					}
-					resumptionInt = pagination;
-					resumptionStr = Integer.toString(resumptionInt);
-					break;
+					case "deep-cursor": // size of result items unknown, iterate over items (for supporting deep cursor
+										// in
+										// solr)
+						// isn't relevant -- if (resultSizeValue < 2) {throw new CollectorServiceException("Mode:
+						// deep-cursor, Param 'resultSizeValue' is less than 2");}
 
-				case "deep-cursor": // size of result items unknown, iterate over items (for supporting deep cursor in
-									// solr)
-					// isn't relevant -- if (resultSizeValue < 2) {throw new CollectorServiceException("Mode:
-					// deep-cursor, Param 'resultSizeValue' is less than 2");}
+						this.resumptionStr = encodeValue(this.xprResumptionPath.evaluate(resultNode));
+						this.queryParams = this.queryParams.replace("&cursor=*", "");
 
-					resumptionStr = encodeValue(xprResumptionPath.evaluate(resultNode));
-					queryParams = queryParams.replace("&cursor=*", "");
+						// terminating if length of nodeList is 0
+						if ((nodeList != null) && (nodeList.getLength() < this.discoverResultSize)) {
+							this.resumptionInt += ((nodeList.getLength() + 1) - this.resultSizeValue);
+						} else {
+							this.resumptionInt += (nodeList.getLength() - this.resultSizeValue); // subtract the
+																									// resultSizeValue
+							// because the iteration is over
+							// real length and the
+							// resultSizeValue is added before
+							// the switch()
+						}
 
-					// terminating if length of nodeList is 0
-					if ((nodeList != null) && (nodeList.getLength() < discoverResultSize)) {
-						resumptionInt += (nodeList.getLength() + 1 - resultSizeValue);
-					} else {
-						resumptionInt += (nodeList.getLength() - resultSizeValue); // subtract the resultSizeValue
-																					// because the iteration is over
-																					// real length and the
-																					// resultSizeValue is added before
-																					// the switch()
-					}
+						this.discoverResultSize = nodeList.getLength();
 
-					discoverResultSize = nodeList.getLength();
+						log
+							.debug(
+								"downloadPage().deep-cursor: resumptionStr=" + this.resumptionStr + " ; queryParams="
+									+ this.queryParams + " resumptionLengthIncreased: " + this.resumptionInt);
 
-					log
-						.debug(
-							"downloadPage().deep-cursor: resumptionStr=" + resumptionStr + " ; queryParams="
-								+ queryParams + " resumptionLengthIncreased: " + resumptionInt);
+						break;
 
-					break;
+					default: // otherwise: abort
+						// resultTotal = resumptionInt;
+						break;
+				}
 
-				default: // otherwise: abort
-					// resultTotal = resumptionInt;
-					break;
+			} catch (final Exception e) {
+				log.error(e.getMessage(), e);
+				throw new IllegalStateException("collection failed: " + e.getMessage());
 			}
 
-		} catch (Exception e) {
-			log.error(e.getMessage(), e);
-			throw new IllegalStateException("collection failed: " + e.getMessage());
-		}
-
-		try {
-			if (resultTotal == -1) {
-				resultTotal = Integer.parseInt(xprResultTotalPath.evaluate(resultNode));
-				if (resumptionType.equalsIgnoreCase("page") && !BASIC.equalsIgnoreCase(authMethod)) {
-					resultTotal += 1;
-				} // to correct the upper bound
-				log.info("resultTotal was -1 is now: " + resultTotal);
+			try {
+				if (this.resultTotal == -1) {
+					this.resultTotal = Integer.parseInt(this.xprResultTotalPath.evaluate(resultNode));
+					if ("page".equalsIgnoreCase(this.resumptionType) && !this.BASIC.equalsIgnoreCase(this.authMethod)) {
+						this.resultTotal += 1;
+					} // to correct the upper bound
+					log.info("resultTotal was -1 is now: " + this.resultTotal);
+				}
+			} catch (final Exception e) {
+				log.error(e.getMessage(), e);
+				throw new IllegalStateException("downloadPage resultTotal couldn't parse: " + e.getMessage());
 			}
-		} catch (Exception e) {
-			log.error(e.getMessage(), e);
-			throw new IllegalStateException("downloadPage resultTotal couldn't parse: " + e.getMessage());
+			log.debug("resultTotal: " + this.resultTotal);
+			log.debug("resInt: " + this.resumptionInt);
+			if (this.resumptionInt <= this.resultTotal) {
+				nextQuery = this.baseUrl + "?" + this.queryParams + this.querySize + "&" + this.resumptionParam + "="
+					+ this.resumptionStr
+					+ this.queryFormat;
+			} else {
+				nextQuery = "";
+				// if (resumptionType.toLowerCase().equals("deep-cursor")) { resumptionInt -= 1; } // correct the
+				// resumptionInt and prevent a NullPointer Exception at mdStore
+			}
+			log.debug("nextQueryUrl: " + nextQuery);
+			return nextQuery;
+		} catch (final Throwable e) {
+			log.warn(e.getMessage(), e);
+			return downloadPage(query, attempt + 1);
 		}
-		log.debug("resultTotal: " + resultTotal);
-		log.debug("resInt: " + resumptionInt);
-		if (resumptionInt <= resultTotal) {
-			nextQuery = baseUrl + "?" + queryParams + querySize + "&" + resumptionParam + "=" + resumptionStr
-				+ queryFormat;
-		} else {
-			nextQuery = "";
-			// if (resumptionType.toLowerCase().equals("deep-cursor")) { resumptionInt -= 1; } // correct the
-			// resumptionInt and prevent a NullPointer Exception at mdStore
-		}
-		log.debug("nextQueryUrl: " + nextQuery);
-		return nextQuery;
 
 	}
 
-	private boolean isInteger(String s) {
+	private boolean isInteger(final String s) {
 		boolean isValidInteger = false;
 		try {
 			Integer.parseInt(s);
@@ -383,7 +417,7 @@ public class RestIterator implements Iterator<String> {
 			// s is a valid integer
 
 			isValidInteger = true;
-		} catch (NumberFormatException ex) {
+		} catch (final NumberFormatException ex) {
 			// s is not an integer
 		}
 
@@ -391,20 +425,20 @@ public class RestIterator implements Iterator<String> {
 	}
 
 	// Method to encode a string value using `UTF-8` encoding scheme
-	private String encodeValue(String value) {
+	private String encodeValue(final String value) {
 		try {
 			return URLEncoder.encode(value, StandardCharsets.UTF_8.toString());
-		} catch (UnsupportedEncodingException ex) {
+		} catch (final UnsupportedEncodingException ex) {
 			throw new RuntimeException(ex.getCause());
 		}
 	}
 
 	public String getResultFormatValue() {
-		return resultFormatValue;
+		return this.resultFormatValue;
 	}
 
 	public String getResultOutputFormat() {
-		return resultOutputFormat;
+		return this.resultOutputFormat;
 	}
 
 }

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/transformation/xslt/DataFetcher.java

@@ -0,0 +1,134 @@
+package eu.dnetlib.dhp.transformation.xslt;
+
+import java.io.Serializable;
+import net.sf.saxon.s9api.*;
+
+import org.apache.commons.io.IOUtils;
+import org.json.JSONObject;
+import java.io.IOException;
+import java.net.MalformedURLException;
+import java.net.URL;
+import java.util.ArrayList;
+import java.util.List;
+
+/**
+ * This class fetches JSON from a provided link and returns
+ * a Dublin Core. This functionality is particularly needed for OSF Preprints
+ */
+
+
+public class DataFetcher implements ExtensionFunction, Serializable {
+
+    /**
+     * This method fetches JSON object from a given URL
+     * @param url a url in the metadata for fetching authors in JSON format
+     * @return
+     * @throws IOException
+     */
+    static JSONObject getJson(URL url) throws IOException {
+
+        String json = IOUtils.toString(url);
+        return new JSONObject(json);
+    }
+
+    /**
+     * This method extracts authors from a given JSON
+     *
+     * @param jsonObject
+     * @return
+     */
+    static List<String> getAuthorsFromJson(JSONObject jsonObject) {
+        List<String> authors = new ArrayList<>();
+        // count of authors
+        int countOfAuthors = jsonObject.getJSONArray("data").length();
+        for (int i = 0; i < countOfAuthors; i++) {
+
+            authors.add(jsonObject
+                    .getJSONArray("data")
+                    .getJSONObject(i)
+                    .getJSONObject("embeds")
+                    .getJSONObject("users")
+                    .getJSONObject("data")
+                    .getJSONObject("attributes")
+                    .getString("full_name"));
+        }
+        return authors;
+    }
+
+    /**
+     * This method transforms list of authors into Dublin Core
+     * @param authors
+     * @return Dublin Core list of authors
+     */
+    static List<String> transformListToDublinCore(List<String> authors) {
+
+        List<String> dublinCoreAuthors = new ArrayList<>();
+        for (String author : authors){
+
+            //splitting full name into first and last names according to OpenAIRE v3 guidelines at:
+            // https://guidelines.openaire.eu/en/latest/literature/field_creator.html
+            // “surname”, “initials” (“first name”) “prefix”.
+            String[] parts = author.split(" ");
+            String firstName = parts[0];
+            String lastName = parts[1];
+            char initialOfFirstName = firstName.charAt(0);
+
+            dublinCoreAuthors.add(
+                    "<dc:creator>" + lastName + ", " + initialOfFirstName +  ". (" + firstName + ")" + "</dc:creator>");
+        }
+        return dublinCoreAuthors;
+    }
+
+     /**
+     * This is a public method which fetches authors and transform them into Dublin Core
+     */
+    public static String getAndTransformAuthors(URL url) throws IOException{
+        return String.join(", ", transformListToDublinCore(getAuthorsFromJson(getJson(url))));
+    }
+
+
+    /**
+     * This method extracts link to fulltext from a given JSON
+     *
+     * @return
+     */
+    static private String getLinkToFulltextFromJson(JSONObject jsonObject) throws MalformedURLException {
+
+        // note: Link to JSON containing fulltextlink is in "primary_file" attribute.
+        // And in the resultant JSON,  “links->download” contains the URL to fulltext
+
+        return jsonObject
+                .getJSONObject("data")
+                .getJSONObject("links")
+                .getString("download");
+    }
+
+    /**
+     * This is a public method which fetches link to full text and returns it as a suitable format
+     */
+    public static String getFullTextLinkAndTransform (URL url )throws IOException{
+
+        return getLinkToFulltextFromJson(getJson(url));
+    }
+
+
+    @Override
+    public QName getName() {
+        return null;
+    }
+
+    @Override
+    public SequenceType getResultType() {
+        return null;
+    }
+
+    @Override
+    public SequenceType[] getArgumentTypes() {
+        return new SequenceType[0];
+    }
+
+    @Override
+    public XdmValue call(XdmValue[] xdmValues) throws SaxonApiException {
+        return null;
+    }
+}

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/transformation/xslt/XSLTTransformationFunction.java

@@ -55,6 +55,8 @@ public class XSLTTransformationFunction implements MapFunction<MetadataRecord, M
 		processor.registerExtensionFunction(new DateCleaner());
 		processor.registerExtensionFunction(new PersonCleaner());
 
+		processor.registerExtensionFunction(new DataFetcher());
+
 		final XsltCompiler comp = processor.newXsltCompiler();
 		QName datasourceIDParam = new QName(DATASOURCE_ID_PARAM);
 		comp.setParameter(datasourceIDParam, new XdmAtomicValue(value.getProvenance().getDatasourceId()));

dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/bipaffiliations/input_actionset_parameter.json

@@ -28,7 +28,13 @@
     "paramLongName": "dataciteInputPath",
     "paramDescription": "the path to get the input data from Datacite",
     "paramRequired": true
-  },
+  },{
+  "paramName": "wip",
+  "paramLongName": "webCrawlInputPath",
+  "paramDescription": "the path to get the input data from Web Crawl",
+  "paramRequired": true
+}
+,
   {
     "paramName": "o",
     "paramLongName": "outputPath",

dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/bipaffiliations/job.properties

@@ -35,5 +35,6 @@ crossrefInputPath=/data/bip-affiliations/crossref-data.json
 pubmedInputPath=/data/bip-affiliations/pubmed-data.json
 openapcInputPath=/data/bip-affiliations/openapc-data.json
 dataciteInputPath=/data/bip-affiliations/datacite-data.json
+webCrawlInputPath=/data/bip-affiliations/webCrawl/
 
 outputPath=/tmp/crossref-affiliations-output-v5

dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/bipaffiliations/oozie_app/workflow.xml

@@ -17,6 +17,10 @@
             <name>dataciteInputPath</name>
             <description>the path where to find the inferred affiliation relations from Datacite</description>
         </property>
+        <property>
+            <name>webCrawlInputPath</name>
+            <description>the path where to find the inferred affiliation relations from webCrawl</description>
+        </property>
         <property>
             <name>outputPath</name>
             <description>the path where to store the actionset</description>
@@ -112,7 +116,7 @@
             <arg>--pubmedInputPath</arg><arg>${pubmedInputPath}</arg>
             <arg>--openapcInputPath</arg><arg>${openapcInputPath}</arg>
             <arg>--dataciteInputPath</arg><arg>${dataciteInputPath}</arg>
-
+            <arg>--webCrawlInputPath</arg><arg>${webCrawlInputPath}</arg>
             <arg>--outputPath</arg><arg>${outputPath}</arg>
         </spark>
         <ok to="End"/>

dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/webcrawl/as_parameters.json

@@ -0,0 +1,25 @@
+[
+  {
+    "paramName": "sp",
+    "paramLongName": "sourcePath",
+    "paramDescription": "the zipped opencitations file",
+    "paramRequired": true
+  },
+  {
+    "paramName": "op",
+    "paramLongName": "outputPath",
+    "paramDescription": "the working path",
+    "paramRequired": true
+  },
+  {
+    "paramName": "issm",
+    "paramLongName": "isSparkSessionManaged",
+    "paramDescription": "the hdfs name node",
+    "paramRequired": false
+  },{
+  "paramName": "bl",
+  "paramLongName": "blackListPath",
+  "paramDescription": "the working path",
+  "paramRequired": true
+}
+]

dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/webcrawl/job.properties

@@ -0,0 +1,3 @@
+sourcePath=/user/miriam.baglioni/openalex-snapshot/data/works/
+outputPath=/tmp/miriam/webcrawlComplete/
+blackListPath=/user/miriam.baglioni/openalex-blackList

dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/webcrawl/oozie_app/config-default.xml

@@ -0,0 +1,58 @@
+<configuration>
+    <property>
+        <name>jobTracker</name>
+        <value>yarnRM</value>
+    </property>
+    <property>
+        <name>nameNode</name>
+        <value>hdfs://nameservice1</value>
+    </property>
+    <property>
+        <name>oozie.use.system.libpath</name>
+        <value>true</value>
+    </property>
+    <property>
+        <name>oozie.action.sharelib.for.spark</name>
+        <value>spark2</value>
+    </property>
+    <property>
+        <name>hive_metastore_uris</name>
+        <value>thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083</value>
+    </property>
+    <property>
+        <name>spark2YarnHistoryServerAddress</name>
+        <value>http://iis-cdh5-test-gw.ocean.icm.edu.pl:18089</value>
+    </property>
+    <property>
+        <name>spark2ExtraListeners</name>
+        <value>com.cloudera.spark.lineage.NavigatorAppListener</value>
+    </property>
+    <property>
+        <name>spark2SqlQueryExecutionListeners</name>
+        <value>com.cloudera.spark.lineage.NavigatorQueryListener</value>
+    </property>
+    <property>
+        <name>oozie.launcher.mapreduce.user.classpath.first</name>
+        <value>true</value>
+    </property>
+    <property>
+        <name>sparkExecutorNumber</name>
+        <value>4</value>
+    </property>
+    <property>
+        <name>spark2EventLogDir</name>
+        <value>/user/spark/spark2ApplicationHistory</value>
+    </property>
+    <property>
+        <name>sparkDriverMemory</name>
+        <value>15G</value>
+    </property>
+    <property>
+        <name>sparkExecutorMemory</name>
+        <value>6G</value>
+    </property>
+    <property>
+        <name>sparkExecutorCores</name>
+        <value>1</value>
+    </property>
+</configuration>

dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/webcrawl/oozie_app/workflow.xml

@@ -0,0 +1,54 @@
+<workflow-app name="WebCrawl Integration" xmlns="uri:oozie:workflow:0.5">
+
+    <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>${oozieActionShareLibForSpark2}</value>
+            </property>
+
+        </configuration>
+    </global>
+
+    <start to="create_actionset"/>
+
+    <kill name="Kill">
+        <message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
+    </kill>
+
+    <action name="create_actionset">
+        <spark xmlns="uri:oozie:spark-action:0.2">
+            <master>yarn</master>
+            <mode>cluster</mode>
+            <name>Produces the AS for WC</name>
+            <class>eu.dnetlib.dhp.actionmanager.webcrawl.CreateActionSetFromWebEntries</class>
+            <jar>dhp-aggregation-${projectVersion}.jar</jar>
+            <spark-opts>
+                --executor-memory=${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>${sourcePath}</arg>
+            <arg>--outputPath</arg><arg>${outputPath}</arg>
+            <arg>--blackListPath</arg><arg>${blackListPath}</arg>
+        </spark>
+        <ok to="End"/>
+        <error to="Kill"/>
+    </action>
+    <end name="End"/>
+</workflow-app>

dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/collection/crossref/irish_funder.json

@@ -1,10 +1,5 @@
 [
-  {
-    "id": "100007630",
-    "uri": "http://dx.doi.org/10.13039/100007630",
-    "name": "College of Engineering and Informatics, National University of Ireland, Galway",
-    "synonym": []
-  },
+
   {
     "id": "100007731",
     "uri": "http://dx.doi.org/10.13039/100007731",
@@ -58,7 +53,7 @@
     "uri": "http://dx.doi.org/10.13039/100010414",
     "name": "Health Research Board",
     "synonym": [
-      "501100001590"
+      "501100001590", "501100023273"
     ]
   },
   {
@@ -85,24 +80,6 @@
     "name": "Irish College of General Practitioners",
     "synonym": []
   },
-  {
-    "id": "100012734",
-    "uri": "http://dx.doi.org/10.13039/100012734",
-    "name": "Department for Culture, Heritage and the Gaeltacht, Ireland",
-    "synonym": []
-  },
-  {
-    "id": "100012754",
-    "uri": "http://dx.doi.org/10.13039/100012754",
-    "name": "Horizon Pharma",
-    "synonym": []
-  },
-  {
-    "id": "100012891",
-    "uri": "http://dx.doi.org/10.13039/100012891",
-    "name": "Medical Research Charities Group",
-    "synonym": []
-  },
   {
     "id": "100012919",
     "uri": "http://dx.doi.org/10.13039/100012919",
@@ -233,7 +210,7 @@
     "id": "100018064",
     "uri": "http://dx.doi.org/10.13039/100018064",
     "name": "Department of Tourism, Culture, Arts, Gaeltacht, Sport and Media",
-    "synonym": []
+    "synonym": ["100012734"]
   },
   {
     "id": "100018172",
@@ -271,12 +248,6 @@
     "name": "An Roinn Sl\u00e1inte",
     "synonym": []
   },
-  {
-    "id": "100018998",
-    "uri": "http://dx.doi.org/10.13039/100018998",
-    "name": "Irish Research eLibrary",
-    "synonym": []
-  },
   {
     "id": "100019428",
     "uri": "http://dx.doi.org/10.13039/100019428",
@@ -287,13 +258,13 @@
     "id": "100019637",
     "uri": "http://dx.doi.org/10.13039/100019637",
     "name": "Horizon Therapeutics",
-    "synonym": []
+    "synonym": ["100012754"]
   },
   {
     "id": "100020174",
     "uri": "http://dx.doi.org/10.13039/100020174",
     "name": "Health Research Charities Ireland",
-    "synonym": []
+    "synonym": ["100012891"]
   },
   {
     "id": "100020202",
@@ -325,12 +296,7 @@
     "name": "Centre for Ageing Research and Development in Ireland",
     "synonym": []
   },
-  {
-    "id": "501100001583",
-    "uri": "http://dx.doi.org/10.13039/501100001583",
-    "name": "Cystinosis Foundation Ireland",
-    "synonym": []
-  },
+
   {
     "id": "501100001584",
     "uri": "http://dx.doi.org/10.13039/501100001584",
@@ -461,13 +427,13 @@
     "id": "501100001634",
     "uri": "http://dx.doi.org/10.13039/501100001634",
     "name": "University of Galway",
-    "synonym": []
+    "synonym": ["501100019905", "100007630", "501100020570", "501100023852"]
   },
   {
     "id": "501100001635",
     "uri": "http://dx.doi.org/10.13039/501100001635",
     "name": "University of Limerick",
-    "synonym": []
+    "synonym": ["501100014531"]
   },
   {
     "id": "501100001636",
@@ -497,7 +463,7 @@
     "id": "501100002736",
     "uri": "http://dx.doi.org/10.13039/501100002736",
     "name": "Covidien",
-    "synonym": []
+    "synonym": ["501100003956"]
   },
   {
     "id": "501100002755",
@@ -527,7 +493,7 @@
     "id": "501100003037",
     "uri": "http://dx.doi.org/10.13039/501100003037",
     "name": "Elan",
-    "synonym": []
+    "synonym": ["501100021694"]
   },
   {
     "id": "501100003496",
@@ -547,12 +513,6 @@
     "name": "Irish Institute of Clinical Neuroscience",
     "synonym": []
   },
-  {
-    "id": "501100003956",
-    "uri": "http://dx.doi.org/10.13039/501100003956",
-    "name": "Aspect Medical Systems",
-    "synonym": []
-  },
   {
     "id": "501100004162",
     "uri": "http://dx.doi.org/10.13039/501100004162",
@@ -601,17 +561,11 @@
     "name": "Technological University Dublin",
     "synonym": []
   },
-  {
-    "id": "501100009269",
-    "uri": "http://dx.doi.org/10.13039/501100009269",
-    "name": "Programme of Competitive Forestry Research for Development",
-    "synonym": []
-  },
   {
     "id": "501100009315",
     "uri": "http://dx.doi.org/10.13039/501100009315",
     "name": "Cystinosis Ireland",
-    "synonym": []
+    "synonym": ["501100001583"]
   },
   {
     "id": "501100010808",
@@ -631,12 +585,6 @@
     "name": "Alimentary Health",
     "synonym": []
   },
-  {
-    "id": "501100011103",
-    "uri": "http://dx.doi.org/10.13039/501100011103",
-    "name": "Rann\u00eds",
-    "synonym": []
-  },
   {
     "id": "501100012354",
     "uri": "http://dx.doi.org/10.13039/501100012354",
@@ -685,12 +633,7 @@
     "name": "Irish Centre for High-End Computing",
     "synonym": []
   },
-  {
-    "id": "501100019905",
-    "uri": "http://dx.doi.org/10.13039/501100019905",
-    "name": "Galway University Foundation",
-    "synonym": []
-  },
+
   {
     "id": "501100020036",
     "uri": "http://dx.doi.org/10.13039/501100020036",
@@ -739,12 +682,6 @@
     "name": "Insight SFI Research Centre for Data Analytics",
     "synonym": []
   },
-  {
-    "id": "501100021694",
-    "uri": "http://dx.doi.org/10.13039/501100021694",
-    "name": "Elan Pharma International",
-    "synonym": []
-  },
   {
     "id": "501100021838",
     "uri": "http://dx.doi.org/10.13039/501100021838",
@@ -775,12 +712,6 @@
     "name": "Institute of Technology, Tralee",
     "synonym": []
   },
-  {
-    "id": "501100023273",
-    "uri": "http://dx.doi.org/10.13039/501100023273",
-    "name": "HRB Clinical Research Facility Galway",
-    "synonym": []
-  },
   {
     "id": "501100023378",
     "uri": "http://dx.doi.org/10.13039/501100023378",
@@ -877,12 +808,7 @@
     "name": "Energy Policy Research Centre, Economic and Social Research Institute",
     "synonym": []
   },
-  {
-    "id": "501100014531",
-    "uri": "http://dx.doi.org/10.13039/501100014531",
-    "name": "Physical Education and Sport Sciences Department, University of Limerick",
-    "synonym": []
-  },
+
   {
     "id": "501100014745",
     "uri": "http://dx.doi.org/10.13039/501100014745",
@@ -895,22 +821,11 @@
     "name": "ADAPT - Centre for Digital Content Technology",
     "synonym": []
   },
-  {
-    "id": "501100020570",
-    "uri": "http://dx.doi.org/10.13039/501100020570",
-    "name": "College of Medicine, Nursing and Health Sciences, National University of Ireland, Galway",
-    "synonym": []
-  },
+
   {
     "id": "501100020871",
     "uri": "http://dx.doi.org/10.13039/501100020871",
     "name": "Bernal Institute, University of Limerick",
     "synonym": []
-  },
-  {
-    "id": "501100023852",
-    "uri": "http://dx.doi.org/10.13039/501100023852",
-    "name": "Moore Institute for Research in the Humanities and Social Studies, University of Galway",
-    "synonym": []
   }
 ]

dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/collection/oozie_app/workflow.xml

@@ -48,12 +48,37 @@
             <description>Used to configure the heap size for the map JVM process. Should be 80% of mapreduce.map.memory.mb.</description>
         </property>
 
+        <property>
+            <name>JAVA_HOME</name>
+            <value>/srv/java/openjdk-17</value>
+            <description>Used to configure the Java home location for oozie.launcher.mapreduce.map.env</description>
+        </property>
+
+        <property>
+            <name>JAVA_OPTS</name>
+                <value>-Dcom.sun.security.enableAIAcaIssuers=true</value>
+            <description>Used to configure the JAVA_OPTS parameter</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.launcher.mapreduce.map.env</name>
+                <value>JAVA_HOME=${JAVA_HOME}</value>
+            </property>
+        </configuration>
     </global>
 
     <start to="collection_mode"/>
@@ -99,7 +124,7 @@
     <action name="CollectionWorker">
         <java>
             <main-class>eu.dnetlib.dhp.collection.CollectorWorkerApplication</main-class>
-            <java-opts>${collection_java_xmx}</java-opts>
+            <java-opts>${JAVA_OPTS} ${collection_java_xmx}</java-opts>
             <arg>--apidescriptor</arg><arg>${apiDescription}</arg>
             <arg>--namenode</arg><arg>${nameNode}</arg>
             <arg>--workflowId</arg><arg>${workflowId}</arg>

dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/sx/bio/db/oozie_app/workflow.xml

@@ -1,4 +1,4 @@
-    <workflow-app name="Transform_BioEntity_Workflow" xmlns="uri:oozie:workflow:0.5">
+<workflow-app name="Transform_BioEntity_Workflow" xmlns="uri:oozie:workflow:0.5">
     <parameters>
         <property>
             <name>sourcePath</name>
@@ -8,19 +8,40 @@
             <name>database</name>
             <description>the PDB Database Working Path</description>
         </property>
-
         <property>
-            <name>targetPath</name>
-            <description>the Target Working dir path</description>
+            <name>mdStoreOutputId</name>
+            <description>the identifier of the cleaned MDStore</description>
+        </property>
+        <property>
+            <name>mdStoreManagerURI</name>
+            <description>the path of the cleaned mdstore</description>
         </property>
     </parameters>
 
-    <start to="ConvertDB"/>
+    <start to="StartTransaction"/>
+
 
     <kill name="Kill">
         <message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
     </kill>
 
+    <action name="StartTransaction">
+        <java>
+            <configuration>
+                <property>
+                    <name>oozie.launcher.mapreduce.user.classpath.first</name>
+                    <value>true</value>
+                </property>
+            </configuration>
+            <main-class>eu.dnetlib.dhp.aggregation.mdstore.MDStoreActionNode</main-class>
+            <arg>--action</arg><arg>NEW_VERSION</arg>
+            <arg>--mdStoreID</arg><arg>${mdStoreOutputId}</arg>
+            <arg>--mdStoreManagerURI</arg><arg>${mdStoreManagerURI}</arg>
+            <capture-output/>
+        </java>
+        <ok to="ConvertDB"/>
+        <error to="RollBack"/>
+    </action>
     <action name="ConvertDB">
         <spark xmlns="uri:oozie:spark-action:0.2">
             <master>yarn</master>
@@ -41,11 +62,48 @@
             <arg>--master</arg><arg>yarn</arg>
             <arg>--dbPath</arg><arg>${sourcePath}</arg>
             <arg>--database</arg><arg>${database}</arg>
-            <arg>--targetPath</arg><arg>${targetPath}</arg>
+            <arg>--mdstoreOutputVersion</arg><arg>${wf:actionData('StartTransaction')['mdStoreVersion']}</arg>
         </spark>
-        <ok to="End"/>
-        <error to="Kill"/>
+        <ok to="CommitVersion"/>
+        <error to="RollBack"/>
+
     </action>
-    <end name="End"/>
+        <action name="CommitVersion">
+            <java>
+                <configuration>
+                    <property>
+                        <name>oozie.launcher.mapreduce.user.classpath.first</name>
+                        <value>true</value>
+                    </property>
+                </configuration>
+                <main-class>eu.dnetlib.dhp.aggregation.mdstore.MDStoreActionNode</main-class>
+                <arg>--action</arg><arg>COMMIT</arg>
+                <arg>--namenode</arg><arg>${nameNode}</arg>
+                <arg>--mdStoreVersion</arg><arg>${wf:actionData('StartTransaction')['mdStoreVersion']}</arg>
+                <arg>--mdStoreManagerURI</arg><arg>${mdStoreManagerURI}</arg>
+            </java>
+            <ok to="End"/>
+            <error to="Kill"/>
+        </action>
+
+        <action name="RollBack">
+            <java>
+                <configuration>
+                    <property>
+                        <name>oozie.launcher.mapreduce.user.classpath.first</name>
+                        <value>true</value>
+                    </property>
+                </configuration>
+                <main-class>eu.dnetlib.dhp.aggregation.mdstore.MDStoreActionNode</main-class>
+                <arg>--action</arg><arg>ROLLBACK</arg>
+                <arg>--mdStoreVersion</arg><arg>${wf:actionData('StartTransaction')['mdStoreVersion']}</arg>
+                <arg>--mdStoreManagerURI</arg><arg>${mdStoreManagerURI}</arg>
+            </java>
+            <ok to="Kill"/>
+            <error to="Kill"/>
+        </action>
+
+
+        <end name="End"/>
 
 </workflow-app>

dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/sx/bio/ebi/bio_to_oaf_params.json

@@ -2,5 +2,5 @@
   {"paramName":"mt",  "paramLongName":"master",       "paramDescription": "should be local or yarn",                  "paramRequired": true},
   {"paramName":"db",  "paramLongName":"database",     "paramDescription": "should be PDB or UNIPROT",                 "paramRequired": true},
   {"paramName":"p",   "paramLongName":"dbPath",       "paramDescription": "the path of the database to transform",    "paramRequired": true},
-  {"paramName":"t",   "paramLongName":"targetPath",   "paramDescription": "the OAF target path ",                     "paramRequired": true}
+  {"paramName":"mo",   "paramLongName":"mdstoreOutputVersion",     "paramDescription": "the oaf path ",                "paramRequired": true}
 ]

dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/sx/bio/ebi/ebi_to_df_params.json

@@ -1,5 +1,20 @@
 [
-  {"paramName":"mt",  "paramLongName":"master",     "paramDescription": "should be local or yarn",                  "paramRequired": true},
-  {"paramName":"s",   "paramLongName":"sourcePath","paramDescription": "the source Path",                              "paramRequired": true},
-  {"paramName":"t",   "paramLongName":"targetPath","paramDescription": "the  oaf path ",  "paramRequired": true}
+  {
+    "paramName": "mt",
+    "paramLongName": "master",
+    "paramDescription": "should be local or yarn",
+    "paramRequired": true
+  },
+  {
+    "paramName": "s",
+    "paramLongName": "sourcePath",
+    "paramDescription": "the source Path",
+    "paramRequired": true
+  },
+  {
+    "paramName": "mo",
+    "paramLongName": "mdstoreOutputVersion",
+    "paramDescription": "the oaf path ",
+    "paramRequired": true
+  }
 ]

dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/sx/bio/ebi/oozie_app/workflow.xml

@@ -9,34 +9,26 @@
             <description>the Working Path</description>
         </property>
         <property>
-            <name>targetPath</name>
-            <description>the OAF MDStore Path</description>
+            <name>mdStoreOutputId</name>
+            <description>the identifier of the cleaned MDStore</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>
+            <name>mdStoreManagerURI</name>
+            <description>the path of the cleaned mdstore</description>
         </property>
         <property>
             <name>resumeFrom</name>
-            <value>DownloadEBILinks</value>
+            <value>CreateEBIDataSet</value>
             <description>node to start</description>
         </property>
     </parameters>
 
-    <start to="resume_from"/>
+    <start to="StartTransaction"/>
 
     <decision name="resume_from">
         <switch>
             <case to="DownloadEBILinks">${wf:conf('resumeFrom') eq 'DownloadEBILinks'}</case>
-            <case to="CreateEBIDataSet">${wf:conf('resumeFrom') eq 'CreateEBIDataSet'}</case>
+            <case to="StartTransaction">${wf:conf('resumeFrom') eq 'CreateEBIDataSet'}</case>
             <default to="DownloadEBILinks"/>
         </switch>
     </decision>
@@ -77,9 +69,29 @@
             <move source="${sourcePath}/ebi_links_dataset" target="${sourcePath}/ebi_links_dataset_old"/>
             <move source="${workingPath}/links_final" target="${sourcePath}/ebi_links_dataset"/>
         </fs>
-        <ok to="CreateEBIDataSet"/>
+        <ok to="StartTransaction"/>
         <error to="Kill"/>
     </action>
+
+    <action name="StartTransaction">
+        <java>
+            <configuration>
+                <property>
+                    <name>oozie.launcher.mapreduce.user.classpath.first</name>
+                    <value>true</value>
+                </property>
+            </configuration>
+            <main-class>eu.dnetlib.dhp.aggregation.mdstore.MDStoreActionNode</main-class>
+            <arg>--action</arg><arg>NEW_VERSION</arg>
+            <arg>--mdStoreID</arg><arg>${mdStoreOutputId}</arg>
+            <arg>--mdStoreManagerURI</arg><arg>${mdStoreManagerURI}</arg>
+            <capture-output/>
+        </java>
+        <ok to="CreateEBIDataSet"/>
+        <error to="RollBack"/>
+    </action>
+
+
     <action name="CreateEBIDataSet">
         <spark xmlns="uri:oozie:spark-action:0.2">
             <master>yarn-cluster</master>
@@ -95,11 +107,49 @@
                 ${sparkExtraOPT}
             </spark-opts>
             <arg>--sourcePath</arg><arg>${sourcePath}/ebi_links_dataset</arg>
-            <arg>--targetPath</arg><arg>${targetPath}</arg>
+            <arg>--mdstoreOutputVersion</arg><arg>${wf:actionData('StartTransaction')['mdStoreVersion']}</arg>
             <arg>--master</arg><arg>yarn</arg>
         </spark>
         <ok to="End"/>
         <error to="Kill"/>
     </action>
+
+
+    <action name="CommitVersion">
+        <java>
+            <configuration>
+                <property>
+                    <name>oozie.launcher.mapreduce.user.classpath.first</name>
+                    <value>true</value>
+                </property>
+            </configuration>
+            <main-class>eu.dnetlib.dhp.aggregation.mdstore.MDStoreActionNode</main-class>
+            <arg>--action</arg><arg>COMMIT</arg>
+            <arg>--namenode</arg><arg>${nameNode}</arg>
+            <arg>--mdStoreVersion</arg><arg>${wf:actionData('StartTransaction')['mdStoreVersion']}</arg>
+            <arg>--mdStoreManagerURI</arg><arg>${mdStoreManagerURI}</arg>
+        </java>
+        <ok to="End"/>
+        <error to="Kill"/>
+    </action>
+
+    <action name="RollBack">
+        <java>
+            <configuration>
+                <property>
+                    <name>oozie.launcher.mapreduce.user.classpath.first</name>
+                    <value>true</value>
+                </property>
+            </configuration>
+            <main-class>eu.dnetlib.dhp.aggregation.mdstore.MDStoreActionNode</main-class>
+            <arg>--action</arg><arg>ROLLBACK</arg>
+            <arg>--mdStoreVersion</arg><arg>${wf:actionData('StartTransaction')['mdStoreVersion']}</arg>
+            <arg>--mdStoreManagerURI</arg><arg>${mdStoreManagerURI}</arg>
+        </java>
+        <ok to="Kill"/>
+        <error to="Kill"/>
+    </action>
+
     <end name="End"/>
+
 </workflow-app>

dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/collection/mag/MagUtility.scala

@@ -5,7 +5,17 @@ import eu.dnetlib.dhp.schema.action.AtomicAction
 import eu.dnetlib.dhp.schema.common.ModelConstants
 import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils._
 import eu.dnetlib.dhp.schema.oaf.utils.{OafMapperUtils, PidType}
-import eu.dnetlib.dhp.schema.oaf.{Author, DataInfo, Instance, Journal, Organization, Publication, Relation, Result, Dataset => OafDataset}
+import eu.dnetlib.dhp.schema.oaf.{
+  Author,
+  DataInfo,
+  Instance,
+  Journal,
+  Organization,
+  Publication,
+  Relation,
+  Result,
+  Dataset => OafDataset
+}
 import eu.dnetlib.dhp.utils.DHPUtils
 import org.apache.spark.sql.types._
 import org.apache.spark.sql.{Dataset, Row, SparkSession}
@@ -69,23 +79,6 @@ object MagUtility extends Serializable {
   private val MAGCollectedFrom = keyValue(ModelConstants.MAG_ID, ModelConstants.MAG_NAME)
 
   private val MAGDataInfo: DataInfo = {
-    val di = new DataInfo
-    di.setDeletedbyinference(false)
-    di.setInferred(false)
-    di.setInvisible(false)
-    di.setTrust("0.9")
-    di.setProvenanceaction(
-      OafMapperUtils.qualifier(
-        ModelConstants.SYSIMPORT_ACTIONSET,
-        ModelConstants.SYSIMPORT_ACTIONSET,
-        ModelConstants.DNET_PROVENANCE_ACTIONS,
-        ModelConstants.DNET_PROVENANCE_ACTIONS
-      )
-    )
-    di
-  }
-
-  private val MAGDataInfoInvisible: DataInfo = {
     val di = new DataInfo
     di.setDeletedbyinference(false)
     di.setInferred(false)
@@ -443,7 +436,6 @@ object MagUtility extends Serializable {
 
       case "repository" =>
         result = new Publication()
-        result.setDataInfo(MAGDataInfoInvisible)
         qualifier(
           "0038",
           "Other literature type",
@@ -478,8 +470,7 @@ object MagUtility extends Serializable {
     }
 
     if (result != null) {
-      if (result.getDataInfo == null)
-        result.setDataInfo(MAGDataInfo)
+      result.setDataInfo(MAGDataInfo)
       val i = new Instance
       i.setInstancetype(tp)
       i.setInstanceTypeMapping(
@@ -502,7 +493,7 @@ object MagUtility extends Serializable {
       return null
 
     result.setCollectedfrom(List(MAGCollectedFrom).asJava)
-    val pidList = List(
+    var pidList = List(
       structuredProperty(
         paper.paperId.get.toString,
         qualifier(
@@ -515,8 +506,6 @@ object MagUtility extends Serializable {
       )
     )
 
-    result.setPid(pidList.asJava)
-
     result.setOriginalId(pidList.map(s => s.getValue).asJava)
 
     result.setId(s"50|mag_________::${DHPUtils.md5(paper.paperId.get.toString)}")
@@ -608,22 +597,23 @@ object MagUtility extends Serializable {
     }
 
     val instance = result.getInstance().get(0)
-    instance.setPid(pidList.asJava)
-    if (paper.doi.orNull != null)
-      instance.setAlternateIdentifier(
-        List(
-          structuredProperty(
-            paper.doi.get,
-            qualifier(
-              PidType.doi.toString,
-              PidType.doi.toString,
-              ModelConstants.DNET_PID_TYPES,
-              ModelConstants.DNET_PID_TYPES
-            ),
-            null
-          )
-        ).asJava
+
+    if (paper.doi.orNull != null) {
+      pidList = pidList ::: List(
+        structuredProperty(
+          paper.doi.get,
+          qualifier(
+            PidType.doi.toString,
+            PidType.doi.toString,
+            ModelConstants.DNET_PID_TYPES,
+            ModelConstants.DNET_PID_TYPES
+          ),
+          null
+        )
       )
+    }
+    instance.setPid(pidList.asJava)
+    result.setPid(pidList.asJava)
     instance.setUrl(paper.urls.get.asJava)
     instance.setHostedby(ModelConstants.UNKNOWN_REPOSITORY)
     instance.setCollectedfrom(MAGCollectedFrom)
@@ -688,33 +678,45 @@ object MagUtility extends Serializable {
     o.setLegalname(field(r.getAs[String]("DisplayName"), null))
     val gid = r.getAs[String]("GridId")
     if (gid != null) {
-      o.setPid(List(
-        structuredProperty(gid, qualifier(
-          PidType.GRID.toString,
-          PidType.GRID.toString,
-          ModelConstants.DNET_PID_TYPES,
-          ModelConstants.DNET_PID_TYPES
-        ),
-          null),
-        structuredProperty(r.getAs[Long]("AffiliationId").toString, qualifier(
-          PidType.mag_id.toString,
-          PidType.mag_id.toString,
-          ModelConstants.DNET_PID_TYPES,
-          ModelConstants.DNET_PID_TYPES
-        ),
-          null)
-
-      ).asJava)
+      o.setPid(
+        List(
+          structuredProperty(
+            gid,
+            qualifier(
+              PidType.GRID.toString,
+              PidType.GRID.toString,
+              ModelConstants.DNET_PID_TYPES,
+              ModelConstants.DNET_PID_TYPES
+            ),
+            null
+          ),
+          structuredProperty(
+            r.getAs[Long]("AffiliationId").toString,
+            qualifier(
+              PidType.mag_id.toString,
+              PidType.mag_id.toString,
+              ModelConstants.DNET_PID_TYPES,
+              ModelConstants.DNET_PID_TYPES
+            ),
+            null
+          )
+        ).asJava
+      )
     } else {
-      o.setPid(List(
-        structuredProperty(r.getAs[Long]("AffiliationId").toString, qualifier(
-          PidType.mag_id.toString,
-          PidType.mag_id.toString,
-          ModelConstants.DNET_PID_TYPES,
-          ModelConstants.DNET_PID_TYPES
-        ),
-          null)
-      ).asJava)
+      o.setPid(
+        List(
+          structuredProperty(
+            r.getAs[Long]("AffiliationId").toString,
+            qualifier(
+              PidType.mag_id.toString,
+              PidType.mag_id.toString,
+              ModelConstants.DNET_PID_TYPES,
+              ModelConstants.DNET_PID_TYPES
+            ),
+            null
+          )
+        ).asJava
+      )
     }
     val c = r.getAs[String]("Iso3166Code")
     if (c != null)

dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/collection/mag/SparkMAGtoOAF.scala

@@ -38,6 +38,7 @@ class SparkMAGtoOAF(propertyPath: String, args: Array[String], log: Logger)
     spark.read
       .load(s"$magBasePath/mag_denormalized")
       .as[MAGPaper]
+      .filter(col("doi").isNotNull)
       .map(s => MagUtility.convertMAGtoOAF(s))
       .filter(s => s != null)
       .write

dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/collection/mag/SparkMagOrganizationAS.scala

@@ -6,33 +6,37 @@ import eu.dnetlib.dhp.schema.oaf.Organization
 import org.apache.spark.sql.{Encoder, Encoders, SaveMode, SparkSession}
 import org.slf4j.{Logger, LoggerFactory}
 
-class SparkMagOrganizationAS (propertyPath: String, args: Array[String], log: Logger)
-  extends AbstractScalaApplication(propertyPath, args, log: Logger) {
+class SparkMagOrganizationAS(propertyPath: String, args: Array[String], log: Logger)
+    extends AbstractScalaApplication(propertyPath, args, log: Logger) {
 
   /** Here all the spark applications runs this method
-   * where the whole logic of the spark node is defined
-   */
+    * where the whole logic of the spark node is defined
+    */
   override def run(): Unit = {
-    val magBasePath:String = parser.get("magBasePath")
+    val magBasePath: String = parser.get("magBasePath")
     log.info(s"magBasePath is $magBasePath")
-    val outputPath:String = parser.get("outputPath")
+    val outputPath: String = parser.get("outputPath")
     log.info(s"outputPath is $outputPath")
-    generateAS(spark,magBasePath, outputPath)
+    generateAS(spark, magBasePath, outputPath)
 
   }
 
-  def generateAS(spark:SparkSession, magBasePath:String,outputPath:String  ):Unit = {
+  def generateAS(spark: SparkSession, magBasePath: String, outputPath: String): Unit = {
     import spark.implicits._
-    val organizations = MagUtility.loadMagEntity(spark,"Affiliations", magBasePath)
-    organizations.map(r => MagUtility.generateOrganization(r)).write.mode(SaveMode.Overwrite)
+    val organizations = MagUtility.loadMagEntity(spark, "Affiliations", magBasePath)
+    organizations
+      .map(r => MagUtility.generateOrganization(r))
+      .write
+      .mode(SaveMode.Overwrite)
       .option("compression", "gzip")
       .text(outputPath)
   }
 }
 
-object SparkMagOrganizationAS{
+object SparkMagOrganizationAS {
 
   val log: Logger = LoggerFactory.getLogger(SparkMagOrganizationAS.getClass)
+
   def main(args: Array[String]): Unit = {
     new SparkMagOrganizationAS("/eu/dnetlib/dhp/collection/mag/create_organization_AS.json", args, log)
       .initialize()

dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/sx/bio/BioDBToOAF.scala

@@ -231,7 +231,7 @@ object BioDBToOAF {
   def uniprotToOAF(input: String): List[Oaf] = {
     implicit lazy val formats: DefaultFormats.type = org.json4s.DefaultFormats
     lazy val json = parse(input)
-    val pid = (json \ "pid").extract[String]
+    val pid = (json \ "pid").extract[String].trim()
 
     val d = new Dataset
 

dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/sx/bio/SparkTransformBioDatabaseToOAF.scala

@@ -2,12 +2,15 @@ package eu.dnetlib.dhp.sx.bio
 
 import eu.dnetlib.dhp.application.ArgumentApplicationParser
 import eu.dnetlib.dhp.collection.CollectionUtils
+import eu.dnetlib.dhp.common.Constants.{MDSTORE_DATA_PATH, MDSTORE_SIZE_PATH}
+import eu.dnetlib.dhp.schema.mdstore.MDStoreVersion
 import eu.dnetlib.dhp.schema.oaf.Oaf
 import eu.dnetlib.dhp.sx.bio.BioDBToOAF.ScholixResolved
 import org.apache.commons.io.IOUtils
 import org.apache.spark.SparkConf
 import org.apache.spark.sql.{Encoder, Encoders, SparkSession}
 import org.slf4j.{Logger, LoggerFactory}
+import eu.dnetlib.dhp.utils.DHPUtils.{MAPPER, writeHdfsFile}
 
 object SparkTransformBioDatabaseToOAF {
 
@@ -25,8 +28,13 @@ object SparkTransformBioDatabaseToOAF {
 
     val dbPath: String = parser.get("dbPath")
     log.info("dbPath: {}", database)
-    val targetPath: String = parser.get("targetPath")
-    log.info("targetPath: {}", database)
+
+    val mdstoreOutputVersion = parser.get("mdstoreOutputVersion")
+    log.info("mdstoreOutputVersion: {}", mdstoreOutputVersion)
+
+    val cleanedMdStoreVersion = MAPPER.readValue(mdstoreOutputVersion, classOf[MDStoreVersion])
+    val outputBasePath = cleanedMdStoreVersion.getHdfsPath
+    log.info("outputBasePath: {}", outputBasePath)
 
     val spark: SparkSession =
       SparkSession
@@ -43,24 +51,28 @@ object SparkTransformBioDatabaseToOAF {
       case "UNIPROT" =>
         CollectionUtils.saveDataset(
           spark.createDataset(sc.textFile(dbPath).flatMap(i => BioDBToOAF.uniprotToOAF(i))),
-          targetPath
+          s"$outputBasePath/$MDSTORE_DATA_PATH"
         )
       case "PDB" =>
         CollectionUtils.saveDataset(
           spark.createDataset(sc.textFile(dbPath).flatMap(i => BioDBToOAF.pdbTOOaf(i))),
-          targetPath
+          s"$outputBasePath/$MDSTORE_DATA_PATH"
         )
       case "SCHOLIX" =>
         CollectionUtils.saveDataset(
           spark.read.load(dbPath).as[ScholixResolved].map(i => BioDBToOAF.scholixResolvedToOAF(i)),
-          targetPath
+          s"$outputBasePath/$MDSTORE_DATA_PATH"
         )
       case "CROSSREF_LINKS" =>
         CollectionUtils.saveDataset(
           spark.createDataset(sc.textFile(dbPath).map(i => BioDBToOAF.crossrefLinksToOaf(i))),
-          targetPath
+          s"$outputBasePath/$MDSTORE_DATA_PATH"
         )
     }
+
+    val df = spark.read.text(s"$outputBasePath/$MDSTORE_DATA_PATH")
+    val mdStoreSize = df.count
+    writeHdfsFile(spark.sparkContext.hadoopConfiguration, s"$mdStoreSize", s"$outputBasePath/$MDSTORE_SIZE_PATH")
   }
 
 }

dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/sx/bio/ebi/SparkEBILinksToOaf.scala

@@ -9,6 +9,9 @@ import org.apache.commons.io.IOUtils
 import org.apache.spark.SparkConf
 import org.apache.spark.sql._
 import org.slf4j.{Logger, LoggerFactory}
+import eu.dnetlib.dhp.common.Constants.{MDSTORE_DATA_PATH, MDSTORE_SIZE_PATH}
+import eu.dnetlib.dhp.schema.mdstore.MDStoreVersion
+import eu.dnetlib.dhp.utils.DHPUtils.{MAPPER, writeHdfsFile}
 
 object SparkEBILinksToOaf {
 
@@ -32,8 +35,13 @@ object SparkEBILinksToOaf {
     import spark.implicits._
     val sourcePath = parser.get("sourcePath")
     log.info(s"sourcePath  -> $sourcePath")
-    val targetPath = parser.get("targetPath")
-    log.info(s"targetPath  -> $targetPath")
+    val mdstoreOutputVersion = parser.get("mdstoreOutputVersion")
+    log.info("mdstoreOutputVersion: {}", mdstoreOutputVersion)
+
+    val cleanedMdStoreVersion = MAPPER.readValue(mdstoreOutputVersion, classOf[MDStoreVersion])
+    val outputBasePath = cleanedMdStoreVersion.getHdfsPath
+    log.info("outputBasePath: {}", outputBasePath)
+
     implicit val PMEncoder: Encoder[Oaf] = Encoders.kryo(classOf[Oaf])
 
     val ebLinks: Dataset[EBILinkItem] = spark.read
@@ -46,7 +54,10 @@ object SparkEBILinksToOaf {
         .flatMap(j => BioDBToOAF.parse_ebi_links(j.links))
         .filter(p => BioDBToOAF.EBITargetLinksFilter(p))
         .flatMap(p => BioDBToOAF.convertEBILinksToOaf(p)),
-      targetPath
+      s"$outputBasePath/$MDSTORE_DATA_PATH"
     )
+    val df = spark.read.text(s"$outputBasePath/$MDSTORE_DATA_PATH")
+    val mdStoreSize = df.count
+    writeHdfsFile(spark.sparkContext.hadoopConfiguration, s"$mdStoreSize", s"$outputBasePath/$MDSTORE_SIZE_PATH")
   }
 }

dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/actionmanager/bipaffiliations/PrepareAffiliationRelationsTest.java

@@ -88,6 +88,7 @@ public class PrepareAffiliationRelationsTest {
 					"-pubmedInputPath", crossrefAffiliationRelationPath,
 					"-openapcInputPath", crossrefAffiliationRelationPath,
 					"-dataciteInputPath", crossrefAffiliationRelationPath,
+					"-webCrawlInputPath", crossrefAffiliationRelationPath,
 					"-outputPath", outputPath
 				});
 
@@ -104,7 +105,7 @@ public class PrepareAffiliationRelationsTest {
 //            );
 //        }
 		// count the number of relations
-		assertEquals(80, tmp.count());
+		assertEquals(120, tmp.count());
 
 		Dataset<Relation> dataset = spark.createDataset(tmp.rdd(), Encoders.bean(Relation.class));
 		dataset.createOrReplaceTempView("result");
@@ -115,7 +116,7 @@ public class PrepareAffiliationRelationsTest {
 		// verify that we have equal number of bi-directional relations
 		Assertions
 			.assertEquals(
-				40, execVerification
+				60, execVerification
 					.filter(
 						"relClass='" + ModelConstants.HAS_AUTHOR_INSTITUTION + "'")
 					.collectAsList()
@@ -123,7 +124,7 @@ public class PrepareAffiliationRelationsTest {
 
 		Assertions
 			.assertEquals(
-				40, execVerification
+				60, execVerification
 					.filter(
 						"relClass='" + ModelConstants.IS_AUTHOR_INSTITUTION_OF + "'")
 					.collectAsList()

dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/actionmanager/webcrawl/CreateASTest.java

@@ -0,0 +1,297 @@
+
+package eu.dnetlib.dhp.actionmanager.webcrawl;
+
+import static org.junit.jupiter.api.Assertions.assertEquals;
+
+import java.io.IOException;
+import java.nio.file.Files;
+import java.nio.file.Path;
+
+import org.apache.commons.io.FileUtils;
+import org.apache.hadoop.io.Text;
+import org.apache.spark.SparkConf;
+import org.apache.spark.api.java.JavaRDD;
+import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.sql.SparkSession;
+import org.junit.jupiter.api.AfterAll;
+import org.junit.jupiter.api.Assertions;
+import org.junit.jupiter.api.BeforeAll;
+import org.junit.jupiter.api.Test;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import com.fasterxml.jackson.databind.ObjectMapper;
+
+import eu.dnetlib.dhp.schema.action.AtomicAction;
+import eu.dnetlib.dhp.schema.oaf.Relation;
+import eu.dnetlib.dhp.schema.oaf.utils.IdentifierFactory;
+import eu.dnetlib.dhp.schema.oaf.utils.PidCleaner;
+import eu.dnetlib.dhp.schema.oaf.utils.PidType;
+
+/**
+ * @author miriam.baglioni
+ * @Date 22/04/24
+ */
+public class CreateASTest {
+	private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
+
+	private static SparkSession spark;
+
+	private static Path workingDir;
+	private static final Logger log = LoggerFactory
+		.getLogger(CreateASTest.class);
+
+	@BeforeAll
+	public static void beforeAll() throws IOException {
+		workingDir = Files
+			.createTempDirectory(CreateASTest.class.getSimpleName());
+		log.info("using work dir {}", workingDir);
+
+		SparkConf conf = new SparkConf();
+		conf.setAppName(CreateASTest.class.getSimpleName());
+
+		conf.setMaster("local[*]");
+		conf.set("spark.driver.host", "localhost");
+		conf.set("hive.metastore.local", "true");
+		conf.set("spark.ui.enabled", "false");
+		conf.set("spark.sql.warehouse.dir", workingDir.toString());
+		conf.set("hive.metastore.warehouse.dir", workingDir.resolve("warehouse").toString());
+
+		spark = SparkSession
+			.builder()
+			.appName(CreateASTest.class.getSimpleName())
+			.config(conf)
+			.getOrCreate();
+	}
+
+	@AfterAll
+	public static void afterAll() throws IOException {
+		FileUtils.deleteDirectory(workingDir.toFile());
+		spark.stop();
+	}
+
+	@Test
+	void testNumberofRelations() throws Exception {
+
+		String inputPath = getClass()
+			.getResource(
+				"/eu/dnetlib/dhp/actionmanager/webcrawl/input/")
+			.getPath();
+		String blackListPath = getClass()
+			.getResource(
+				"/eu/dnetlib/dhp/actionmanager/webcrawl/blackList/")
+			.getPath();
+
+		CreateActionSetFromWebEntries
+			.main(
+				new String[] {
+					"-isSparkSessionManaged",
+					Boolean.FALSE.toString(),
+					"-sourcePath",
+					inputPath,
+					"-outputPath",
+					workingDir.toString() + "/actionSet1",
+					"-blackListPath", blackListPath
+				});
+
+		final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
+
+		JavaRDD<Relation> tmp = sc
+			.sequenceFile(workingDir.toString() + "/actionSet1", Text.class, Text.class)
+			.map(value -> OBJECT_MAPPER.readValue(value._2().toString(), AtomicAction.class))
+			.map(aa -> ((Relation) aa.getPayload()));
+
+		Assertions.assertEquals(58, tmp.count());
+
+	}
+
+	@Test
+	void testRelations() throws Exception {
+
+//		 , "doi":"https://doi.org/10.1126/science.1188021", "pmid":"https://pubmed.ncbi.nlm.nih.gov/20448178", https://www.ncbi.nlm.nih.gov/pmc/articles/5100745
+
+		String inputPath = getClass()
+			.getResource(
+				"/eu/dnetlib/dhp/actionmanager/webcrawl/")
+			.getPath();
+		String blackListPath = getClass()
+			.getResource(
+				"/eu/dnetlib/dhp/actionmanager/webcrawl/blackList/")
+			.getPath();
+
+		CreateActionSetFromWebEntries
+			.main(
+				new String[] {
+					"-isSparkSessionManaged",
+					Boolean.FALSE.toString(),
+					"-sourcePath",
+					inputPath,
+					"-outputPath",
+					workingDir.toString() + "/actionSet1",
+					"-blackListPath", blackListPath
+				});
+
+		final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
+
+		JavaRDD<Relation> tmp = sc
+			.sequenceFile(workingDir.toString() + "/actionSet1", Text.class, Text.class)
+			.map(value -> OBJECT_MAPPER.readValue(value._2().toString(), AtomicAction.class))
+			.map(aa -> ((Relation) aa.getPayload()));
+
+		tmp.foreach(r -> System.out.println(new ObjectMapper().writeValueAsString(r)));
+
+		Assertions
+			.assertEquals(
+				1, tmp
+					.filter(
+						r -> r
+							.getSource()
+							.equals(
+								"50|doi_________::" + IdentifierFactory
+									.md5(
+										PidCleaner
+											.normalizePidValue(PidType.doi.toString(), "10.1098/rstl.1684.0023"))))
+					.count());
+
+		Assertions
+			.assertEquals(
+				1, tmp
+					.filter(
+						r -> r
+							.getTarget()
+							.equals(
+								"50|doi_________::" + IdentifierFactory
+									.md5(
+										PidCleaner
+											.normalizePidValue(PidType.doi.toString(), "10.1098/rstl.1684.0023"))))
+					.count());
+
+		Assertions
+			.assertEquals(
+				1, tmp
+					.filter(
+						r -> r
+							.getSource()
+							.equals(
+								"20|ror_________::" + IdentifierFactory
+									.md5(
+										PidCleaner
+											.normalizePidValue("ROR", "https://ror.org/03argrj65"))))
+					.count());
+
+		Assertions
+			.assertEquals(
+				1, tmp
+					.filter(
+						r -> r
+							.getTarget()
+							.equals(
+								"20|ror_________::" + IdentifierFactory
+									.md5(
+										PidCleaner
+											.normalizePidValue("ROR", "https://ror.org/03argrj65"))))
+					.count());
+
+		Assertions
+			.assertEquals(
+				2, tmp
+					.filter(
+						r -> r
+							.getSource()
+							.equals(
+								"20|ror_________::" + IdentifierFactory
+									.md5(
+										PidCleaner
+											.normalizePidValue("ROR", "https://ror.org/03265fv13"))))
+					.count());
+
+		Assertions
+			.assertEquals(
+				2, tmp
+					.filter(
+						r -> r
+							.getTarget()
+							.equals(
+								"20|ror_________::" + IdentifierFactory
+									.md5(
+										PidCleaner
+											.normalizePidValue("ROR", "https://ror.org/03265fv13"))))
+					.count());
+
+		Assertions
+			.assertEquals(
+				1, tmp
+					.filter(
+						r -> r
+							.getTarget()
+							.equals(
+								"20|ror_________::" + IdentifierFactory
+									.md5(
+										PidCleaner
+											.normalizePidValue(PidType.doi.toString(), "https://ror.org/03265fv13")))
+							&& r.getSource().startsWith("50|doi"))
+					.count());
+
+		Assertions
+			.assertEquals(
+				1, tmp
+					.filter(
+						r -> r
+							.getTarget()
+							.equals(
+								"20|ror_________::" + IdentifierFactory
+									.md5(
+										PidCleaner
+											.normalizePidValue(PidType.doi.toString(), "https://ror.org/03265fv13")))
+							&& r.getSource().startsWith("50|pmid"))
+					.count());
+
+		Assertions
+			.assertEquals(
+				0, tmp
+					.filter(
+						r -> r
+							.getTarget()
+							.equals(
+								"20|ror_________::" + IdentifierFactory
+									.md5(
+										PidCleaner
+											.normalizePidValue(PidType.doi.toString(), "https://ror.org/03265fv13")))
+							&& r.getSource().startsWith("50|pmc"))
+					.count());
+	}
+
+	@Test
+	void testRelationsCollectedFrom() throws Exception {
+
+		String inputPath = getClass()
+			.getResource(
+				"/eu/dnetlib/dhp/actionmanager/webcrawl")
+			.getPath();
+
+		CreateActionSetFromWebEntries
+			.main(
+				new String[] {
+					"-isSparkSessionManaged",
+					Boolean.FALSE.toString(),
+					"-sourcePath",
+					inputPath,
+					"-outputPath",
+					workingDir.toString() + "/actionSet1"
+				});
+
+		final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
+
+		JavaRDD<Relation> tmp = sc
+			.sequenceFile(workingDir.toString() + "/actionSet1", Text.class, Text.class)
+			.map(value -> OBJECT_MAPPER.readValue(value._2().toString(), AtomicAction.class))
+			.map(aa -> ((Relation) aa.getPayload()));
+
+		tmp.foreach(r -> {
+			assertEquals("Web Crawl", r.getCollectedfrom().get(0).getValue());
+			assertEquals("10|openaire____::fb98a192f6a055ba495ef414c330834b", r.getCollectedfrom().get(0).getKey());
+		});
+
+	}
+
+}

dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/collection/plugin/rest/OsfPreprintCollectorTest.java

@@ -1,7 +1,9 @@
+
 package eu.dnetlib.dhp.collection.plugin.rest;
 
 import java.util.HashMap;
 import java.util.concurrent.atomic.AtomicInteger;
+import java.util.concurrent.atomic.AtomicLong;
 import java.util.stream.Stream;
 
 import org.junit.jupiter.api.Assertions;
@@ -68,7 +70,7 @@ public class OsfPreprintCollectorTest {
 
 	@Test
 	@Disabled
-	void test() throws CollectorException {
+	void test_limited() throws CollectorException {
 		final AtomicInteger i = new AtomicInteger(0);
 		final Stream<String> stream = this.rcp.collect(this.api, new AggregatorReport());
 
@@ -81,4 +83,23 @@ public class OsfPreprintCollectorTest {
 		log.info("{}", i.intValue());
 		Assertions.assertTrue(i.intValue() > 0);
 	}
+
+	@Test
+	@Disabled
+	void test_all() throws CollectorException {
+		final AtomicLong i = new AtomicLong(0);
+		final Stream<String> stream = this.rcp.collect(this.api, new AggregatorReport());
+
+		stream.forEach(s -> {
+			Assertions.assertTrue(s.length() > 0);
+			if ((i.incrementAndGet() % 1000) == 0) {
+				log.info("COLLECTED: {}", i.get());
+			}
+
+		});
+
+		log.info("TOTAL: {}", i.get());
+		Assertions.assertTrue(i.get() > 0);
+	}
+
 }

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

@@ -0,0 +1,68 @@
+package eu.dnetlib.dhp.transformation.xslt;
+
+import org.json.JSONObject;
+import org.junit.jupiter.api.AfterEach;
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.Test;
+
+import java.io.IOException;
+import java.net.MalformedURLException;
+import java.net.URI;
+import java.net.URISyntaxException;
+import java.net.URL;
+import java.util.List;
+
+import static org.junit.jupiter.api.Assertions.*;
+
+class DataFetcherTest {
+
+    @BeforeEach
+    void setUp() {
+    }
+
+    @AfterEach
+    void tearDown() {
+    }
+
+    @Test
+    void getJson() throws IOException, URISyntaxException {
+        URL contributorsUrl = new URI("https://api.osf.io/v2/preprints/mrwqb/contributors/?format=json").toURL();
+        JSONObject testJsonObj = DataFetcher.getJson(contributorsUrl);
+
+        String x = testJsonObj
+                .getJSONArray("data")
+                .getJSONObject(0)
+                .getJSONObject("embeds")
+                .getJSONObject("users")
+                .getJSONObject("data")
+                .getJSONObject("attributes")
+                .getString("full_name");
+        System.out.println(x);
+        System.out.println(testJsonObj.getJSONArray("data").length());
+        testJsonObj.getJSONArray("data").forEach(System.out::println);
+    }
+
+    @Test
+    void getAuthorsFromJson() throws IOException, URISyntaxException {
+        URL contributorsUrl = new URI("https://api.osf.io/v2/preprints/mrwqb/contributors/?format=json").toURL();
+        JSONObject testJsonObj = DataFetcher.getJson(contributorsUrl);
+        List<String> authors = DataFetcher.getAuthorsFromJson(testJsonObj);
+        System.out.println(authors);
+        System.out.println(DataFetcher.transformListToDublinCore(authors));
+    }
+
+    @Test
+    void getAndTransformAuthors() throws IOException, URISyntaxException {
+        URL contributorsUrl = new URI("https://api.osf.io/v2/preprints/mrwqb/contributors/?format=json").toURL();
+        System.out.println(DataFetcher.getAndTransformAuthors(contributorsUrl));
+    }
+
+
+    @Test
+    void getLinkToFulltextFromJson() throws URISyntaxException, IOException {
+        URL linkToFullTextDocument = new URI("https://api.osf.io/v2/files/5de7c96f84c479000c7928af/?format=json").toURL();
+        System.out.println(DataFetcher.getFullTextLinkAndTransform(linkToFullTextDocument));
+
+
+    }
+}

dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/bipaffiliations/doi_to_ror.json

@@ -4,4 +4,6 @@
 {"DOI":"10.1142\/s021821650200186x","Matchings":[{"RORid":"https:\/\/ror.org\/035xkbk20","Confidence":1},{"RORid":"https:\/\/ror.org\/05apxxy63","Confidence":1}]}
 {"DOI":"10.1061\/(asce)0733-9372(2002)128:7(575)","Matchings":[{"RORid":"https:\/\/ror.org\/04j198w64","Confidence":0.82}]}
 {"DOI":"10.1061\/(asce)0733-9372(2002)128:7(588)","Matchings":[{"RORid":"https:\/\/ror.org\/03m8km719","Confidence":0.8660254038},{"RORid":"https:\/\/ror.org\/02aze4h65","Confidence":0.87}]}
-{"DOI":"10.1161\/hy0202.103001","Matchings":[{"RORid":"https:\/\/ror.org\/057xtrt18","Confidence":0.7071067812}]}
+{"DOI":"10.1161\/hy0202.103001","Matchings":[{"RORid":"https:\/\/ror.org\/057xtrt18","Confidence":0.7071067812}]}
+{"DOI": "10.1080/13669877.2015.1042504", "Matchings": [{"Confidence": 1.0, "RORid": "https://ror.org/03265fv13"}]}
+{"DOI": "10.1007/3-540-47984-8_14", "Matchings": [{"Confidence": 1.0, "RORid": "https://ror.org/00a0n9e72"}]}

dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/sx/graph/bio/pdb_dump

@@ -1,15 +1,44 @@
-{"pdb": "1CW0", "title": "crystal structure analysis of very short patch repair (vsr) endonuclease in complex with a duplex dna", "authors": ["S.E.Tsutakawa", "H.Jingami", "K.Morikawa"], "doi": "10.1016/S0092-8674(00)81550-0", "pmid": "10612397"}
-{"pdb": "2CWW", "title": "crystal structure of thermus thermophilus ttha1280, a putative sam- dependent rna methyltransferase, in complex with s-adenosyl-l- homocysteine", "authors": ["A.A.Pioszak", "K.Murayama", "N.Nakagawa", "A.Ebihara", "S.Kuramitsu", "M.Shirouzu", "S.Yokoyama", "Riken Structural Genomics/proteomics Initiative (Rsgi)"], "doi": "10.1107/S1744309105029842", "pmid": "16511182"}
-{"pdb": "6CWE", "title": "structure of alpha-gsa[8,6p] bound by cd1d and in complex with the va14vb8.2 tcr", "authors": ["J.Wang", "D.Zajonc"], "doi": null, "pmid": null}
-{"pdb": "5CWS", "title": "crystal structure of the intact chaetomium thermophilum nsp1-nup49- nup57 channel nucleoporin heterotrimer bound to its nic96 nuclear pore complex attachment site", "authors": ["C.J.Bley", "S.Petrovic", "M.Paduch", "V.Lu", "A.A.Kossiakoff", "A.Hoelz"], "doi": "10.1126/SCIENCE.AAC9176", "pmid": "26316600"}
-{"pdb": "5CWE", "title": "structure of cyp107l2 from streptomyces avermitilis with lauric acid", "authors": ["T.-V.Pham", "S.-H.Han", "J.-H.Kim", "D.-H.Kim", "L.-W.Kang"], "doi": null, "pmid": null}
-{"pdb": "7CW4", "title": "acetyl-coa acetyltransferase from bacillus cereus atcc 14579", "authors": ["J.Hong", "K.J.Kim"], "doi": "10.1016/J.BBRC.2020.09.048", "pmid": "32972748"}
-{"pdb": "2CWP", "title": "crystal structure of metrs related protein from pyrococcus horikoshii", "authors": ["K.Murayama", "M.Kato-Murayama", "M.Shirouzu", "S.Yokoyama", "Riken StructuralGenomics/proteomics Initiative (Rsgi)"], "doi": null, "pmid": null}
-{"pdb": "2CW7", "title": "crystal structure of intein homing endonuclease ii", "authors": ["H.Matsumura", "H.Takahashi", "T.Inoue", "H.Hashimoto", "M.Nishioka", "S.Fujiwara", "M.Takagi", "T.Imanaka", "Y.Kai"], "doi": "10.1002/PROT.20858", "pmid": "16493661"}
-{"pdb": "1CWU", "title": "brassica napus enoyl acp reductase a138g mutant complexed with nad+ and thienodiazaborine", "authors": ["A.Roujeinikova", "J.B.Rafferty", "D.W.Rice"], "doi": "10.1074/JBC.274.43.30811", "pmid": "10521472"}
-{"pdb": "3CWN", "title": "escherichia coli transaldolase b mutant f178y", "authors": ["T.Sandalova", "G.Schneider", "A.Samland"], "doi": "10.1074/JBC.M803184200", "pmid": "18687684"}
-{"pdb": "1CWL", "title": "human cyclophilin a complexed with 4 4-hydroxy-meleu cyclosporin", "authors": ["V.Mikol", "J.Kallen", "P.Taylor", "M.D.Walkinshaw"], "doi": "10.1006/JMBI.1998.2108", "pmid": "9769216"}
-{"pdb": "3CW2", "title": "crystal structure of the intact archaeal translation initiation factor 2 from sulfolobus solfataricus .", "authors": ["E.A.Stolboushkina", "S.V.Nikonov", "A.D.Nikulin", "U.Blaesi", "D.J.Manstein", "R.V.Fedorov", "M.B.Garber", "O.S.Nikonov"], "doi": "10.1016/J.JMB.2008.07.039", "pmid": "18675278"}
-{"pdb": "3CW9", "title": "4-chlorobenzoyl-coa ligase/synthetase in the thioester-forming conformation, bound to 4-chlorophenacyl-coa", "authors": ["A.S.Reger", "J.Cao", "R.Wu", "D.Dunaway-Mariano", "A.M.Gulick"], "doi": "10.1021/BI800696Y", "pmid": "18620418"}
-{"pdb": "3CWU", "title": "crystal structure of an alka host/guest complex 2'-fluoro-2'-deoxy-1, n6-ethenoadenine:thymine base pair", "authors": ["B.R.Bowman", "S.Lee", "S.Wang", "G.L.Verdine"], "doi": "10.1016/J.STR.2008.04.012", "pmid": "18682218"}
-{"pdb": "5CWF", "title": "crystal structure of de novo designed helical repeat protein dhr8", "authors": ["G.Bhabha", "D.C.Ekiert"], "doi": "10.1038/NATURE16162", "pmid": "26675729"}
+{"classification": "Signaling protein", "pdb": "5NM4", "deposition_date": "2017-04-05", "title": "A2a adenosine receptor room-temperature structure determined by serial Femtosecond crystallography", "Keywords": ["Oom-temperature", " serial crystallography", " signaling protein"], "authors": ["T.weinert", "R.cheng", "D.james", "D.gashi", "P.nogly", "K.jaeger", "M.hennig", "", "J.standfuss"], "pmid": "28912485", "doi": "10.1038/S41467-017-00630-4"}
+{"classification": "Oxidoreductase/oxidoreductase inhibitor", "pdb": "4KN3", "deposition_date": "2013-05-08", "title": "Structure of the y34ns91g double mutant of dehaloperoxidase from Amphitrite ornata with 2,4,6-trichlorophenol", "Keywords": ["Lobin", " oxygen storage", " peroxidase", " oxidoreductase", " oxidoreductase-", "Oxidoreductase inhibitor complex"], "authors": ["C.wang", "L.lovelace", "L.lebioda"], "pmid": "23952341", "doi": "10.1021/BI400627W"}
+{"classification": "Transport protein", "pdb": "8HKM", "deposition_date": "2022-11-27", "title": "Ion channel", "Keywords": ["On channel", " transport protein"], "authors": ["D.h.jiang", "J.t.zhang"], "pmid": "37494189", "doi": "10.1016/J.CELREP.2023.112858"}
+{"classification": "Signaling protein", "pdb": "6JT1", "deposition_date": "2019-04-08", "title": "Structure of human soluble guanylate cyclase in the heme oxidised State", "Keywords": ["Oluble guanylate cyclase", " signaling protein"], "authors": ["L.chen", "Y.kang", "R.liu", "J.-x.wu"], "pmid": "31514202", "doi": "10.1038/S41586-019-1584-6"}
+{"classification": "Immune system", "pdb": "7OW6", "deposition_date": "2021-06-16", "title": "Crystal structure of a tcr in complex with hla-a*11:01 bound to kras G12d peptide (vvvgadgvgk)", "Keywords": ["La", " kras", " tcr", " immune system"], "authors": ["V.karuppiah", "R.a.robinson"], "doi": "10.1038/S41467-022-32811-1"}
+{"classification": "Biosynthetic protein", "pdb": "5EQ8", "deposition_date": "2015-11-12", "title": "Crystal structure of medicago truncatula histidinol-phosphate Phosphatase (mthpp) in complex with l-histidinol", "Keywords": ["Istidine biosynthesis", " metabolic pathways", " dimer", " plant", "", "Biosynthetic protein"], "authors": ["M.ruszkowski", "Z.dauter"], "pmid": "26994138", "doi": "10.1074/JBC.M115.708727"}
+{"classification": "De novo protein", "pdb": "8CWA", "deposition_date": "2022-05-18", "title": "Solution nmr structure of 8-residue rosetta-designed cyclic peptide D8.21 in cdcl3 with cis/trans switching (tc conformation, 53%)", "Keywords": ["Yclic peptide", " non natural amino acids", " cis/trans", " switch peptides", "", "De novo design", "Membrane permeability", "De novo protein"], "authors": ["T.a.ramelot", "R.tejero", "G.t.montelione"], "pmid": "36041435", "doi": "10.1016/J.CELL.2022.07.019"}
+{"classification": "Hydrolase", "pdb": "3R6M", "deposition_date": "2011-03-21", "title": "Crystal structure of vibrio parahaemolyticus yeaz", "Keywords": ["Ctin/hsp70 nucleotide-binding fold", " bacterial resuscitation", " viable", "But non-culturable state", "Resuscitation promoting factor", "Ygjd", "", "Yjee", "Vibrio parahaemolyticus", "Hydrolase"], "authors": ["A.roujeinikova", "I.aydin"], "pmid": "21858042", "doi": "10.1371/JOURNAL.PONE.0023245"}
+{"classification": "Hydrolase", "pdb": "2W5J", "deposition_date": "2008-12-10", "title": "Structure of the c14-rotor ring of the proton translocating Chloroplast atp synthase", "Keywords": ["Ydrolase", " chloroplast", " atp synthase", " lipid-binding", " cf(0)", " membrane", "", "Transport", "Formylation", "Energy transduction", "Hydrogen ion transport", "", "Ion transport", "Transmembrane", "Membrane protein"], "authors": ["M.vollmar", "D.schlieper", "M.winn", "C.buechner", "G.groth"], "pmid": "19423706", "doi": "10.1074/JBC.M109.006916"}
+{"classification": "De novo protein", "pdb": "4GLU", "deposition_date": "2012-08-14", "title": "Crystal structure of the mirror image form of vegf-a", "Keywords": ["-protein", " covalent dimer", " cysteine knot protein", " growth factor", " de", "Novo protein"], "authors": ["K.mandal", "M.uppalapati", "D.ault-riche", "J.kenney", "J.lowitz", "S.sidhu", "", "S.b.h.kent"], "pmid": "22927390", "doi": "10.1073/PNAS.1210483109"}
+{"classification": "Hydrolase/hydrolase inhibitor", "pdb": "3WYL", "deposition_date": "2014-09-01", "title": "Crystal structure of the catalytic domain of pde10a complexed with 5- Methoxy-3-(1-phenyl-1h-pyrazol-5-yl)-1-(3-(trifluoromethyl)phenyl) Pyridazin-4(1h)-one", "Keywords": ["Ydrolase-hydrolase inhibitor complex"], "authors": ["H.oki", "Y.hayano"], "pmid": "25384088", "doi": "10.1021/JM5013648"}
+{"classification": "Isomerase", "pdb": "5BOR", "deposition_date": "2015-05-27", "title": "Structure of acetobacter aceti pure-s57c, sulfonate form", "Keywords": ["Cidophile", " pure", " purine biosynthesis", " isomerase"], "authors": ["K.l.sullivan", "T.j.kappock"]}
+{"classification": "Hydrolase", "pdb": "1X0C", "deposition_date": "2005-03-17", "title": "Improved crystal structure of isopullulanase from aspergillus niger Atcc 9642", "Keywords": ["Ullulan", " glycoside hydrolase family 49", " glycoprotein", " hydrolase"], "authors": ["M.mizuno", "T.tonozuka", "A.yamamura", "Y.miyasaka", "H.akeboshi", "S.kamitori", "", "A.nishikawa", "Y.sakano"], "pmid": "18155243", "doi": "10.1016/J.JMB.2007.11.098"}
+{"classification": "Oxidoreductase", "pdb": "7CUP", "deposition_date": "2020-08-23", "title": "Structure of 2,5-dihydroxypridine dioxygenase from pseudomonas putida Kt2440", "Keywords": ["On-heme dioxygenase", " oxidoreductase"], "authors": ["G.q.liu", "H.z.tang"]}
+{"classification": "Ligase", "pdb": "1VCN", "deposition_date": "2004-03-10", "title": "Crystal structure of t.th. hb8 ctp synthetase complex with sulfate Anion", "Keywords": ["Etramer", " riken structural genomics/proteomics initiative", " rsgi", "", "Structural genomics", "Ligase"], "authors": ["M.goto", "Riken structural genomics/proteomics initiative (rsgi)"], "pmid": "15296735", "doi": "10.1016/J.STR.2004.05.013"}
+{"classification": "Transferase/transferase inhibitor", "pdb": "6C9V", "deposition_date": "2018-01-28", "title": "Mycobacterium tuberculosis adenosine kinase bound to (2r,3s,4r,5r)-2- (hydroxymethyl)-5-(6-(4-phenylpiperazin-1-yl)-9h-purin-9-yl) Tetrahydrofuran-3,4-diol", "Keywords": ["Ucleoside analog", " complex", " inhibitor", " structural genomics", " psi-2", "", "Protein structure initiative", "Tb structural genomics consortium", "", "Tbsgc", "Transferase-transferase inhibitor complex"], "authors": ["R.a.crespo", "Tb structural genomics consortium (tbsgc)"], "pmid": "31002508", "doi": "10.1021/ACS.JMEDCHEM.9B00020"}
+{"classification": "De novo protein", "pdb": "4LPY", "deposition_date": "2013-07-16", "title": "Crystal structure of tencon variant g10", "Keywords": ["Ibronectin type iii fold", " alternate scaffold", " de novo protein"], "authors": ["A.teplyakov", "G.obmolova", "G.l.gilliland"], "pmid": "24375666", "doi": "10.1002/PROT.24502"}
+{"classification": "Isomerase", "pdb": "2Y88", "deposition_date": "2011-02-03", "title": "Crystal structure of mycobacterium tuberculosis phosphoribosyl Isomerase (variant d11n) with bound prfar", "Keywords": ["Romatic amino acid biosynthesis", " isomerase", " tim-barrel", " histidine", "Biosynthesis", "Tryptophan biosynthesis"], "authors": ["J.kuper", "A.v.due", "A.geerlof", "M.wilmanns"], "pmid": "21321225", "doi": "10.1073/PNAS.1015996108"}
+{"classification": "Unknown function", "pdb": "1SR0", "deposition_date": "2004-03-22", "title": "Crystal structure of signalling protein from sheep(sps-40) at 3.0a Resolution using crystal grown in the presence of polysaccharides", "Keywords": ["Ignalling protein", " involution", " unknown function"], "authors": ["D.b.srivastava", "A.s.ethayathulla", "N.singh", "J.kumar", "S.sharma", "T.p.singh"]}
+{"classification": "Dna binding protein", "pdb": "3RH2", "deposition_date": "2011-04-11", "title": "Crystal structure of a tetr-like transcriptional regulator (sama_0099) From shewanella amazonensis sb2b at 2.42 a resolution", "Keywords": ["Na/rna-binding 3-helical bundle", " structural genomics", " joint center", "For structural genomics", "Jcsg", "Protein structure initiative", "Psi-", "Biology", "Dna binding protein"], "authors": ["Joint center for structural genomics (jcsg)"]}
+{"classification": "Transferase", "pdb": "2WK5", "deposition_date": "2009-06-05", "title": "Structural features of native human thymidine phosphorylase And in complex with 5-iodouracil", "Keywords": ["Lycosyltransferase", " developmental protein", " angiogenesis", "", "5-iodouracil", "Growth factor", "Enzyme kinetics", "", "Differentiation", "Disease mutation", "Thymidine", "Phosphorylase", "Chemotaxis", "Transferase", "Mutagenesis", "", "Polymorphism"], "authors": ["E.mitsiki", "A.c.papageorgiou", "S.iyer", "N.thiyagarajan", "S.h.prior", "", "D.sleep", "C.finnis", "K.r.acharya"], "pmid": "19555658", "doi": "10.1016/J.BBRC.2009.06.104"}
+{"classification": "Hydrolase", "pdb": "3P9Y", "deposition_date": "2010-10-18", "title": "Crystal structure of the drosophila melanogaster ssu72-pctd complex", "Keywords": ["Hosphatase", " cis proline", " lmw ptp-like fold", " rna polymerase ii ctd", "", "Hydrolase"], "authors": ["J.w.werner-allen", "P.zhou"], "pmid": "21159777", "doi": "10.1074/JBC.M110.197129"}
+{"classification": "Recombination/dna", "pdb": "6OEO", "deposition_date": "2019-03-27", "title": "Cryo-em structure of mouse rag1/2 nfc complex (dna1)", "Keywords": ["(d)j recombination", " dna transposition", " rag", " scid", " recombination", "", "Recombination-dna complex"], "authors": ["X.chen", "Y.cui", "Z.h.zhou", "W.yang", "M.gellert"], "pmid": "32015552", "doi": "10.1038/S41594-019-0363-2"}
+{"classification": "Hydrolase", "pdb": "4ECA", "deposition_date": "1997-02-21", "title": "Asparaginase from e. coli, mutant t89v with covalently bound aspartate", "Keywords": ["Ydrolase", " acyl-enzyme intermediate", " threonine amidohydrolase"], "authors": ["G.j.palm", "J.lubkowski", "A.wlodawer"], "pmid": "8706862", "doi": "10.1016/0014-5793(96)00660-6"}
+{"classification": "Transcription/protein binding", "pdb": "3UVX", "deposition_date": "2011-11-30", "title": "Crystal structure of the first bromodomain of human brd4 in complex With a diacetylated histone 4 peptide (h4k12ack16ac)", "Keywords": ["Romodomain", " bromodomain containing protein 4", " cap", " hunk1", " mcap", "", "Mitotic chromosome associated protein", "Peptide complex", "Structural", "Genomics consortium", "Sgc", "Transcription-protein binding complex"], "authors": ["P.filippakopoulos", "S.picaud", "T.keates", "E.ugochukwu", "F.von delft", "", "C.h.arrowsmith", "A.m.edwards", "J.weigelt", "C.bountra", "S.knapp", "Structural", "Genomics consortium (sgc)"], "pmid": "22464331", "doi": "10.1016/J.CELL.2012.02.013"}
+{"classification": "Membrane protein", "pdb": "1TLZ", "deposition_date": "2004-06-10", "title": "Tsx structure complexed with uridine", "Keywords": ["Ucleoside transporter", " beta barrel", " uridine", " membrane", "Protein"], "authors": ["J.ye", "B.van den berg"], "pmid": "15272310", "doi": "10.1038/SJ.EMBOJ.7600330"}
+{"classification": "Dna binding protein", "pdb": "7AZD", "deposition_date": "2020-11-16", "title": "Dna polymerase sliding clamp from escherichia coli with peptide 20 Bound", "Keywords": ["Ntibacterial drug", " dna binding protein"], "authors": ["C.monsarrat", "G.compain", "C.andre", "I.martiel", "S.engilberge", "V.olieric", "", "P.wolff", "K.brillet", "M.landolfo", "C.silva da veiga", "J.wagner", "G.guichard", "", "D.y.burnouf"], "pmid": "34806883", "doi": "10.1021/ACS.JMEDCHEM.1C00918"}
+{"classification": "Transferase", "pdb": "5N3K", "deposition_date": "2017-02-08", "title": "Camp-dependent protein kinase a from cricetulus griseus in complex With fragment like molecule o-guanidino-l-homoserine", "Keywords": ["Ragment", " complex", " transferase", " serine threonine kinase", " camp", "", "Kinase", "Pka"], "authors": ["C.siefker", "A.heine", "G.klebe"]}
+{"classification": "Biosynthetic protein", "pdb": "8H52", "deposition_date": "2022-10-11", "title": "Crystal structure of helicobacter pylori carboxyspermidine Dehydrogenase in complex with nadp", "Keywords": ["Arboxyspermidine dehydrogenase", " biosynthetic protein"], "authors": ["K.y.ko", "S.c.park", "S.y.cho", "S.i.yoon"], "pmid": "36283333", "doi": "10.1016/J.BBRC.2022.10.049"}
+{"classification": "Metal binding protein", "pdb": "6DYC", "deposition_date": "2018-07-01", "title": "Co(ii)-bound structure of the engineered cyt cb562 variant, ch3", "Keywords": ["Esigned protein", " 4-helix bundle", " electron transport", " metal binding", "Protein"], "authors": ["F.a.tezcan", "J.rittle"], "pmid": "30778140", "doi": "10.1038/S41557-019-0218-9"}
+{"classification": "Protein fibril", "pdb": "6A6B", "deposition_date": "2018-06-27", "title": "Cryo-em structure of alpha-synuclein fiber", "Keywords": ["Lpha-syn fiber", " parkinson disease", " protein fibril"], "authors": ["Y.w.li", "C.y.zhao", "F.luo", "Z.liu", "X.gui", "Z.luo", "X.zhang", "D.li", "C.liu", "X.li"], "pmid": "30065316", "doi": "10.1038/S41422-018-0075-X"}
+{"classification": "Dna", "pdb": "7D5E", "deposition_date": "2020-09-25", "title": "Left-handed g-quadruplex containing two bulges", "Keywords": ["-quadruplex", " bulge", " dna", " left-handed"], "authors": ["P.das", "A.maity", "K.h.ngo", "F.r.winnerdy", "B.bakalar", "Y.mechulam", "E.schmitt", "", "A.t.phan"], "pmid": "33503265", "doi": "10.1093/NAR/GKAA1259"}
+{"classification": "Transferase", "pdb": "3RSY", "deposition_date": "2011-05-02", "title": "Cellobiose phosphorylase from cellulomonas uda in complex with sulfate And glycerol", "Keywords": ["H94", " alpha barrel", " cellobiose phosphorylase", " disaccharide", "Phosphorylase", "Transferase"], "authors": ["A.van hoorebeke", "J.stout", "W.soetaert", "J.van beeumen", "T.desmet", "S.savvides"]}
+{"classification": "Oxidoreductase", "pdb": "7MCI", "deposition_date": "2021-04-02", "title": "Mofe protein from azotobacter vinelandii with a sulfur-replenished Cofactor", "Keywords": ["Zotobacter vinelandii", " mofe-protein", " nitrogenase", " oxidoreductase"], "authors": ["W.kang", "C.lee", "Y.hu", "M.w.ribbe"], "doi": "10.1038/S41929-022-00782-7"}
+{"classification": "Dna", "pdb": "1XUW", "deposition_date": "2004-10-26", "title": "Structural rationalization of a large difference in rna affinity Despite a small difference in chemistry between two 2'-o-modified Nucleic acid analogs", "Keywords": ["Na mimetic methylcarbamate amide analog", " dna"], "authors": ["R.pattanayek", "L.sethaphong", "C.pan", "M.prhavc", "T.p.prakash", "M.manoharan", "", "M.egli"], "pmid": "15547979", "doi": "10.1021/JA044637K"}
+{"classification": "Lyase", "pdb": "7C0D", "deposition_date": "2020-05-01", "title": "Crystal structure of azospirillum brasilense l-2-keto-3-deoxyarabonate Dehydratase (hydroxypyruvate-bound form)", "Keywords": ["-2-keto-3-deoxyarabonate dehydratase", " lyase"], "authors": ["Y.watanabe", "S.watanabe"], "pmid": "32697085", "doi": "10.1021/ACS.BIOCHEM.0C00515"}
+{"classification": "Signaling protein", "pdb": "5LYK", "deposition_date": "2016-09-28", "title": "Crystal structure of intracellular b30.2 domain of btn3a1 bound to Citrate", "Keywords": ["30.2", " butyrophilin", " signaling protein"], "authors": ["F.mohammed", "A.t.baker", "M.salim", "B.e.willcox"], "pmid": "28862425", "doi": "10.1021/ACSCHEMBIO.7B00694"}
+{"classification": "Toxin", "pdb": "4IZL", "deposition_date": "2013-01-30", "title": "Structure of the n248a mutant of the panton-valentine leucocidin s Component from staphylococcus aureus", "Keywords": ["I-component leucotoxin", " staphylococcus aureus", " s component", "Leucocidin", "Beta-barrel pore forming toxin", "Toxin"], "authors": ["L.maveyraud", "B.j.laventie", "G.prevost", "L.mourey"], "pmid": "24643034", "doi": "10.1371/JOURNAL.PONE.0092094"}
+{"classification": "Dna", "pdb": "6F3C", "deposition_date": "2017-11-28", "title": "The cytotoxic [pt(h2bapbpy)] platinum complex interacting with the Cgtacg hexamer", "Keywords": ["Rug-dna complex", " four-way junction", " dna"], "authors": ["M.ferraroni", "C.bazzicalupi", "P.gratteri", "F.papi"], "pmid": "31046177", "doi": "10.1002/ANIE.201814532"}
+{"classification": "Signaling protein/inhibitor", "pdb": "4L5M", "deposition_date": "2013-06-11", "title": "Complexe of arno sec7 domain with the protein-protein interaction Inhibitor n-(4-hydroxy-2,6-dimethylphenyl)benzenesulfonamide at ph6.5", "Keywords": ["Ec-7domain", " signaling protein-inhibitor complex"], "authors": ["F.hoh", "J.rouhana"], "pmid": "24112024", "doi": "10.1021/JM4009357"}
+{"classification": "Signaling protein", "pdb": "5I6J", "deposition_date": "2016-02-16", "title": "Crystal structure of srgap2 f-barx", "Keywords": ["Rgap2", " f-bar", " fx", " signaling protein"], "authors": ["M.sporny", "J.guez-haddad", "M.n.isupov", "Y.opatowsky"], "pmid": "28333212", "doi": "10.1093/MOLBEV/MSX094"}
+{"classification": "Metal binding protein", "pdb": "1Q80", "deposition_date": "2003-08-20", "title": "Solution structure and dynamics of nereis sarcoplasmic calcium binding Protein", "Keywords": ["Ll-alpha", " metal binding protein"], "authors": ["G.rabah", "R.popescu", "J.a.cox", "Y.engelborghs", "C.t.craescu"], "pmid": "15819893", "doi": "10.1111/J.1742-4658.2005.04629.X"}
+{"classification": "Transferase", "pdb": "1TW1", "deposition_date": "2004-06-30", "title": "Beta-1,4-galactosyltransferase mutant met344his (m344h-gal-t1) complex With udp-galactose and magnesium", "Keywords": ["Et344his mutation; closed conformation; mn binding", " transferase"], "authors": ["B.ramakrishnan", "E.boeggeman", "P.k.qasba"], "pmid": "15449940", "doi": "10.1021/BI049007+"}
+{"classification": "Rna", "pdb": "2PN4", "deposition_date": "2007-04-23", "title": "Crystal structure of hepatitis c virus ires subdomain iia", "Keywords": ["Cv", " ires", " subdoamin iia", " rna", " strontium", " hepatitis"], "authors": ["Q.zhao", "Q.han", "C.r.kissinger", "P.a.thompson"], "pmid": "18391410", "doi": "10.1107/S0907444908002011"}

dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/sx/graph/bio/uniprot_dump

@@ -1,6 +1,36 @@
-{"pid": "Q6GZX4", "dates": [{"date": "28-JUN-2011", "date_info": " integrated into UniProtKB/Swiss-Prot."}, {"date": "19-JUL-2004", "date_info": " sequence version 1."}, {"date": "12-AUG-2020", "date_info": " entry version 41."}], "title": "Putative transcription factor 001R;", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3).", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus."], "references": [{"PubMed": "15165820"}, {" DOI": "10.1016/j.virol.2004.02.019"}]}
-{"pid": "Q6GZX3", "dates": [{"date": "28-JUN-2011", "date_info": " integrated into UniProtKB/Swiss-Prot."}, {"date": "19-JUL-2004", "date_info": " sequence version 1."}, {"date": "12-AUG-2020", "date_info": " entry version 42."}], "title": "Uncharacterized protein 002L;", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3).", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus."], "references": [{"PubMed": "15165820"}, {" DOI": "10.1016/j.virol.2004.02.019"}]}
-{"pid": "Q197F8", "dates": [{"date": "16-JUN-2009", "date_info": " integrated into UniProtKB/Swiss-Prot."}, {"date": "11-JUL-2006", "date_info": " sequence version 1."}, {"date": "12-AUG-2020", "date_info": " entry version 27."}], "title": "Uncharacterized protein 002R;", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus).", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus."], "references": [{"PubMed": "16912294"}, {" DOI": "10.1128/jvi.00464-06"}]}
-{"pid": "Q197F7", "dates": [{"date": "16-JUN-2009", "date_info": " integrated into UniProtKB/Swiss-Prot."}, {"date": "11-JUL-2006", "date_info": " sequence version 1."}, {"date": "12-AUG-2020", "date_info": " entry version 23."}], "title": "Uncharacterized protein 003L;", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus).", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus."], "references": [{"PubMed": "16912294"}, {" DOI": "10.1128/jvi.00464-06"}]}
-{"pid": "Q6GZX2", "dates": [{"date": "28-JUN-2011", "date_info": " integrated into UniProtKB/Swiss-Prot."}, {"date": "19-JUL-2004", "date_info": " sequence version 1."}, {"date": "12-AUG-2020", "date_info": " entry version 36."}], "title": "Uncharacterized protein 3R;", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3).", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus."], "references": [{"PubMed": "15165820"}, {" DOI": "10.1016/j.virol.2004.02.019"}]}
-{"pid": "Q6GZX1", "dates": [{"date": "28-JUN-2011", "date_info": " integrated into UniProtKB/Swiss-Prot."}, {"date": "19-JUL-2004", "date_info": " sequence version 1."}, {"date": "12-AUG-2020", "date_info": " entry version 34."}], "title": "Uncharacterized protein 004R;", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3).", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus."], "references": [{"PubMed": "15165820"}, {" DOI": "10.1016/j.virol.2004.02.019"}]}
+{"pid": " Q6GZX4", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 43"}], "title": "Putative transcription factor 001R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
+{"pid": " Q6GZX3", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 45"}], "title": "Uncharacterized protein 002L", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
+{"pid": " Q197F8", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2022-02-23", "date_info": "entry version 29"}], "title": "Uncharacterized protein 002R", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
+{"pid": " Q197F7", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2020-08-12", "date_info": "entry version 23"}], "title": "Uncharacterized protein 003L", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
+{"pid": " Q6GZX2", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 37"}], "title": "Uncharacterized protein 3R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
+{"pid": " Q6GZX1", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 38"}], "title": "Uncharacterized protein 004R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
+{"pid": " Q197F5", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2022-10-12", "date_info": "entry version 32"}], "title": "Uncharacterized protein 005L", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
+{"pid": " Q6GZX0", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 47"}], "title": "Uncharacterized protein 005R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
+{"pid": " Q91G88", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2001-12-01", "date_info": "sequence version 1"}, {"date": "2023-06-28", "date_info": "entry version 53"}], "title": "Putative KilA-N domain-containing protein 006L", "organism_species": "Invertebrate iridescent virus 6 (IIV-6) (Chilo iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Iridovirus"], "references": [{"PubMed": "17239238"}, {"DOI": "10.1186/1743-422x-4-11"}]}
+{"pid": " Q6GZW9", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 34"}], "title": "Uncharacterized protein 006R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
+{"pid": " Q6GZW8", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 32"}], "title": "Uncharacterized protein 007R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
+{"pid": " Q197F3", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2023-02-22", "date_info": "entry version 28"}], "title": "Uncharacterized protein 007R", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
+{"pid": " Q197F2", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2022-02-23", "date_info": "entry version 22"}], "title": "Uncharacterized protein 008L", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
+{"pid": " Q6GZW6", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 67"}], "title": "Putative helicase 009L", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
+{"pid": " Q91G85", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2001-12-01", "date_info": "sequence version 1"}, {"date": "2023-02-22", "date_info": "entry version 38"}], "title": "Uncharacterized protein 009R", "organism_species": "Invertebrate iridescent virus 6 (IIV-6) (Chilo iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Iridovirus"], "references": [{"PubMed": "17239238"}, {"DOI": "10.1186/1743-422x-4-11"}]}
+{"pid": " Q6GZW5", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 37"}], "title": "Uncharacterized protein 010R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
+{"pid": " Q197E9", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2023-02-22", "date_info": "entry version 28"}], "title": "Uncharacterized protein 011L", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
+{"pid": " Q6GZW4", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 37"}], "title": "Uncharacterized protein 011R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
+{"pid": " Q6GZW3", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 35"}], "title": "Uncharacterized protein 012L", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
+{"pid": " Q197E7", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2023-02-22", "date_info": "entry version 37"}], "title": "Uncharacterized protein IIV3-013L", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
+{"pid": " Q6GZW2", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 30"}], "title": "Uncharacterized protein 013R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
+{"pid": " Q6GZW1", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 35"}], "title": "Uncharacterized protein 014R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
+{"pid": " Q6GZW0", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 50"}], "title": "Uncharacterized protein 015R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
+{"pid": " Q6GZV8", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 35"}], "title": "Uncharacterized protein 017L", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
+{"pid": " Q6GZV7", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 33"}], "title": "Uncharacterized protein 018L", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
+{"pid": " Q6GZV6", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 87"}], "title": "Putative serine/threonine-protein kinase 019R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
+{"pid": " Q6GZV5", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 40"}], "title": "Uncharacterized protein 020R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
+{"pid": " Q6GZV4", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 35"}], "title": "Uncharacterized protein 021L", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
+{"pid": " Q197D8", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2022-12-14", "date_info": "entry version 35"}], "title": "Transmembrane protein 022L", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
+{"pid": " Q6GZV2", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 33"}], "title": "Uncharacterized protein 023R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
+{"pid": " Q197D7", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2023-02-22", "date_info": "entry version 25"}], "title": "Uncharacterized protein 023R", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
+{"pid": " Q6GZV1", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 37"}], "title": "Uncharacterized protein 024R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
+{"pid": " Q197D5", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2022-10-12", "date_info": "entry version 24"}], "title": "Uncharacterized protein 025R", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
+{"pid": " Q91G70", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2001-12-01", "date_info": "sequence version 1"}, {"date": "2020-08-12", "date_info": "entry version 32"}], "title": "Uncharacterized protein 026R", "organism_species": "Invertebrate iridescent virus 6 (IIV-6) (Chilo iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Iridovirus"], "references": [{"PubMed": "17239238"}, {"DOI": "10.1186/1743-422x-4-11"}]}
+{"pid": " Q6GZU9", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 49"}], "title": "Uncharacterized protein 027R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
+{"pid": " Q6GZU8", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 55"}], "title": "Uncharacterized protein 028R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}

dhp-workflows/dhp-aggregation/src/test/scala/eu/dnetlib/dhp/collection/mag/MAGMappingTest.scala

@@ -3,6 +3,7 @@ package eu.dnetlib.dhp.collection.mag
 import com.fasterxml.jackson.databind.ObjectMapper
 import eu.dnetlib.dhp.schema.oaf.{Dataset, Publication, Result}
 import org.apache.spark.sql.SparkSession
+import org.apache.spark.sql.functions.col
 import org.junit.jupiter.api.Assertions._
 import org.junit.jupiter.api.Test
 
@@ -10,7 +11,6 @@ class MAGMappingTest {
 
   val mapper = new ObjectMapper()
 
-
   def mappingTest(): Unit = {
 
     val spark = SparkSession
@@ -19,10 +19,8 @@ class MAGMappingTest {
       .master("local[*]")
       .getOrCreate()
 
-    val s = new SparkMagOrganizationAS(null, null, null)
-
-    s.generateAS(spark, "/home/sandro/Downloads/mag_test", "/home/sandro/Downloads/mag_AS")
-
+    val s = new SparkMAGtoOAF(null, null, null)
+    s.convertMAG(spark, "/Users/sandro/Downloads/", "/Users/sandro/Downloads/mag_OAF")
   }
 
   @Test

dhp-workflows/dhp-broker-events/src/main/java/eu/dnetlib/dhp/broker/oa/PrepareSimpleEntitiesJob.java

@@ -26,15 +26,15 @@ import eu.dnetlib.dhp.schema.oaf.Publication;
 import eu.dnetlib.dhp.schema.oaf.Result;
 import eu.dnetlib.dhp.schema.oaf.Software;
 
-public class PrepareSimpleEntititiesJob {
+public class PrepareSimpleEntitiesJob {
 
-	private static final Logger log = LoggerFactory.getLogger(PrepareSimpleEntititiesJob.class);
+	private static final Logger log = LoggerFactory.getLogger(PrepareSimpleEntitiesJob.class);
 
 	public static void main(final String[] args) throws Exception {
 		final ArgumentApplicationParser parser = new ArgumentApplicationParser(
 			IOUtils
 				.toString(
-					PrepareSimpleEntititiesJob.class
+					PrepareSimpleEntitiesJob.class
 						.getResourceAsStream("/eu/dnetlib/dhp/broker/oa/common_params.json")));
 		parser.parseArgument(args);
 

dhp-workflows/dhp-broker-events/src/main/java/eu/dnetlib/dhp/broker/oa/util/ConversionUtils.java

@@ -160,8 +160,7 @@ public class ConversionUtils {
 			.stream()
 			.filter(Objects::nonNull)
 			.filter(pid -> pid.getQualifier() != null)
-			.filter(pid -> pid.getQualifier().getClassid() != null)
-			.filter(pid -> pid.getQualifier().getClassid().equalsIgnoreCase(ModelConstants.ORCID))
+			.filter(pid -> StringUtils.startsWithIgnoreCase(pid.getQualifier().getClassid(), ModelConstants.ORCID))
 			.map(StructuredProperty::getValue)
 			.map(ConversionUtils::cleanOrcid)
 			.filter(StringUtils::isNotBlank)

dhp-workflows/dhp-broker-events/src/main/resources/eu/dnetlib/dhp/broker/oa/generate_all/oozie_app/workflow.xml

@@ -7,7 +7,7 @@
         </property>
         <property>
             <name>outputDir</name>
-            <description>the path where the the generated data will be stored</description>
+            <description>the path where the generated data will be stored</description>
         </property>
 		<property>
             <name>datasourceIdWhitelist</name>
@@ -179,17 +179,18 @@
             <master>yarn</master>
             <mode>cluster</mode>
             <name>PrepareSimpleEntititiesJob</name>
-            <class>eu.dnetlib.dhp.broker.oa.PrepareSimpleEntititiesJob</class>
+            <class>eu.dnetlib.dhp.broker.oa.PrepareSimpleEntitiesJob</class>
             <jar>dhp-broker-events-${projectVersion}.jar</jar>
             <spark-opts>
                 --executor-cores=${sparkExecutorCores}
                 --executor-memory=${sparkExecutorMemory}
                 --driver-memory=${sparkDriverMemory}
+                --conf spark.executor.memoryOverhead=${sparkExecutorMemory}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
                 --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-                --conf spark.sql.shuffle.partitions=3840
+                --conf spark.sql.shuffle.partitions=5000
             </spark-opts>
             <arg>--graphPath</arg><arg>${graphInputPath}</arg>
             <arg>--workingDir</arg><arg>${workingDir}</arg>
@@ -209,11 +210,12 @@
                 --executor-cores=${sparkExecutorCores}
                 --executor-memory=${sparkExecutorMemory}
                 --driver-memory=${sparkDriverMemory}
+                --conf spark.executor.memoryOverhead=${sparkExecutorMemory}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
                 --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-                --conf spark.sql.shuffle.partitions=3840
+                --conf spark.sql.shuffle.partitions=8000
             </spark-opts>
             <arg>--graphPath</arg><arg>${graphInputPath}</arg>
             <arg>--workingDir</arg><arg>${workingDir}</arg>
@@ -234,11 +236,12 @@
                 --executor-cores=${sparkExecutorCores}
                 --executor-memory=${sparkExecutorMemory}
                 --driver-memory=${sparkDriverMemory}
+                --conf spark.executor.memoryOverhead=${sparkExecutorMemory}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
                 --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-                --conf spark.sql.shuffle.partitions=3840
+                --conf spark.sql.shuffle.partitions=8000
             </spark-opts>
             <arg>--graphPath</arg><arg>${graphInputPath}</arg>
             <arg>--workingDir</arg><arg>${workingDir}</arg>
@@ -258,11 +261,12 @@
                 --executor-cores=${sparkExecutorCores}
                 --executor-memory=${sparkExecutorMemory}
                 --driver-memory=${sparkDriverMemory}
+                --conf spark.executor.memoryOverhead=${sparkExecutorMemory}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
                 --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-                --conf spark.sql.shuffle.partitions=3840
+                --conf spark.sql.shuffle.partitions=5000
             </spark-opts>
             <arg>--graphPath</arg><arg>${graphInputPath}</arg>
             <arg>--workingDir</arg><arg>${workingDir}</arg>
@@ -282,11 +286,12 @@
                 --executor-cores=${sparkExecutorCores}
                 --executor-memory=${sparkExecutorMemory}
                 --driver-memory=${sparkDriverMemory}
+                --conf spark.executor.memoryOverhead=${sparkExecutorMemory}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
                 --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-                --conf spark.sql.shuffle.partitions=3840
+                --conf spark.sql.shuffle.partitions=10000
             </spark-opts>
             <arg>--graphPath</arg><arg>${graphInputPath}</arg>
             <arg>--workingDir</arg><arg>${workingDir}</arg>
@@ -306,11 +311,12 @@
                 --executor-cores=${sparkExecutorCores}
                 --executor-memory=${sparkExecutorMemory}
                 --driver-memory=${sparkDriverMemory}
+                --conf spark.executor.memoryOverhead=${sparkExecutorMemory}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
                 --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-                --conf spark.sql.shuffle.partitions=3840
+                --conf spark.sql.shuffle.partitions=2000
             </spark-opts>
             <arg>--graphPath</arg><arg>${graphInputPath}</arg>
             <arg>--workingDir</arg><arg>${workingDir}</arg>
@@ -332,11 +338,12 @@
                 --executor-cores=${sparkExecutorCores}
                 --executor-memory=${sparkExecutorMemory}
                 --driver-memory=${sparkDriverMemory}
+                --conf spark.executor.memoryOverhead=${sparkExecutorMemory}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
                 --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-                --conf spark.sql.shuffle.partitions=3840
+                --conf spark.sql.shuffle.partitions=8000
             </spark-opts>
             <arg>--graphPath</arg><arg>${graphInputPath}</arg>
             <arg>--workingDir</arg><arg>${workingDir}</arg>
@@ -356,11 +363,12 @@
                 --executor-cores=${sparkExecutorCores}
                 --executor-memory=${sparkExecutorMemory}
                 --driver-memory=${sparkDriverMemory}
+                --conf spark.executor.memoryOverhead=${sparkExecutorMemory}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
                 --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-                --conf spark.sql.shuffle.partitions=3840
+                --conf spark.sql.shuffle.partitions=8000
             </spark-opts>
             <arg>--graphPath</arg><arg>${graphInputPath}</arg>
             <arg>--workingDir</arg><arg>${workingDir}</arg>
@@ -380,11 +388,12 @@
                 --executor-cores=${sparkExecutorCores}
                 --executor-memory=${sparkExecutorMemory}
                 --driver-memory=${sparkDriverMemory}
+                --conf spark.executor.memoryOverhead=${sparkExecutorMemory}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
                 --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-                --conf spark.sql.shuffle.partitions=3840
+                --conf spark.sql.shuffle.partitions=8000
             </spark-opts>
             <arg>--graphPath</arg><arg>${graphInputPath}</arg>
             <arg>--workingDir</arg><arg>${workingDir}</arg>
@@ -404,11 +413,12 @@
                 --executor-cores=${sparkExecutorCores}
                 --executor-memory=${sparkExecutorMemory}
                 --driver-memory=${sparkDriverMemory}
+                --conf spark.executor.memoryOverhead=${sparkExecutorMemory}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
                 --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-                --conf spark.sql.shuffle.partitions=3840
+                --conf spark.sql.shuffle.partitions=8000
             </spark-opts>
             <arg>--graphPath</arg><arg>${graphInputPath}</arg>
             <arg>--workingDir</arg><arg>${workingDir}</arg>
@@ -428,11 +438,12 @@
                 --executor-cores=${sparkExecutorCores}
                 --executor-memory=${sparkExecutorMemory}
                 --driver-memory=${sparkDriverMemory}
+                --conf spark.executor.memoryOverhead=${sparkExecutorMemory}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
                 --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-                --conf spark.sql.shuffle.partitions=3840
+                --conf spark.sql.shuffle.partitions=8000
             </spark-opts>
             <arg>--graphPath</arg><arg>${graphInputPath}</arg>
             <arg>--workingDir</arg><arg>${workingDir}</arg>
@@ -452,11 +463,12 @@
                 --executor-cores=${sparkExecutorCores}
                 --executor-memory=${sparkExecutorMemory}
                 --driver-memory=${sparkDriverMemory}
+                --conf spark.executor.memoryOverhead=${sparkExecutorMemory}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
                 --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-                --conf spark.sql.shuffle.partitions=3840
+                --conf spark.sql.shuffle.partitions=8000
             </spark-opts>
             <arg>--graphPath</arg><arg>${graphInputPath}</arg>
             <arg>--workingDir</arg><arg>${workingDir}</arg>
@@ -476,11 +488,12 @@
                 --executor-cores=${sparkExecutorCores}
                 --executor-memory=${sparkExecutorMemory}
                 --driver-memory=${sparkDriverMemory}
+                --conf spark.executor.memoryOverhead=${sparkExecutorMemory}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
                 --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-                --conf spark.sql.shuffle.partitions=3840
+                --conf spark.sql.shuffle.partitions=8000
             </spark-opts>
             <arg>--workingDir</arg><arg>${workingDir}</arg>
             <arg>--outputDir</arg><arg>${outputDir}</arg>
@@ -503,6 +516,7 @@
             <spark-opts>
                 --executor-memory=${sparkExecutorMemory}
                 --driver-memory=${sparkDriverMemory}
+                --conf spark.executor.memoryOverhead=${sparkExecutorMemory}
                 --conf spark.dynamicAllocation.maxExecutors=${sparkMaxExecutorsForIndexing} 
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
@@ -535,6 +549,7 @@
                 --executor-cores=${sparkExecutorCores}
                 --executor-memory=${sparkExecutorMemory}
                 --driver-memory=${sparkDriverMemory}
+                --conf spark.executor.memoryOverhead=${sparkExecutorMemory}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
@@ -562,6 +577,7 @@
                 --executor-cores=${sparkExecutorCores}
                 --executor-memory=${sparkExecutorMemory}
                 --driver-memory=${sparkDriverMemory}
+                --conf spark.executor.memoryOverhead=${sparkExecutorMemory}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
@@ -585,6 +601,7 @@
             <spark-opts>
                 --executor-memory=${sparkExecutorMemory}
                 --driver-memory=${sparkDriverMemory}
+                --conf spark.executor.memoryOverhead=${sparkExecutorMemory}
                 --conf spark.dynamicAllocation.maxExecutors=${sparkMaxExecutorsForIndexing} 
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}

dhp-workflows/dhp-broker-events/src/test/java/eu/dnetlib/dhp/broker/oa/matchers/simple/EnrichMissingAuthorOrcidTest.java

@@ -0,0 +1,64 @@
+package eu.dnetlib.dhp.broker.oa.matchers.simple;
+
+import static org.junit.jupiter.api.Assertions.assertEquals;
+import static org.junit.jupiter.api.Assertions.assertTrue;
+
+import java.util.List;
+
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.Test;
+
+import eu.dnetlib.broker.objects.OaBrokerAuthor;
+import eu.dnetlib.broker.objects.OaBrokerMainEntity;
+
+class EnrichMissingAuthorOrcidTest {
+
+	final EnrichMissingAuthorOrcid matcher = new EnrichMissingAuthorOrcid();
+
+	@BeforeEach
+	void setUp() throws Exception {}
+
+	@Test
+	void testFindDifferences_1() {
+		final OaBrokerMainEntity source = new OaBrokerMainEntity();
+		final OaBrokerMainEntity target = new OaBrokerMainEntity();
+		final List<OaBrokerAuthor> list = this.matcher.findDifferences(source, target);
+		assertTrue(list.isEmpty());
+	}
+
+	@Test
+	void testFindDifferences_2() {
+		final OaBrokerMainEntity source = new OaBrokerMainEntity();
+		final OaBrokerMainEntity target = new OaBrokerMainEntity();
+
+		source.getCreators().add(new OaBrokerAuthor("Claudio Atzori", "0000-0001-9613-6639"));
+		target.getCreators().add(new OaBrokerAuthor("Claudio Atzori", null));
+
+		final List<OaBrokerAuthor> list = this.matcher.findDifferences(source, target);
+		assertEquals(1, list.size());
+	}
+
+	@Test
+	void testFindDifferences_3() {
+		final OaBrokerMainEntity source = new OaBrokerMainEntity();
+		final OaBrokerMainEntity target = new OaBrokerMainEntity();
+
+		source.getCreators().add(new OaBrokerAuthor("Claudio Atzori", null));
+		target.getCreators().add(new OaBrokerAuthor("Claudio Atzori", "0000-0001-9613-6639"));
+
+		final List<OaBrokerAuthor> list = this.matcher.findDifferences(source, target);
+		assertTrue(list.isEmpty());
+	}
+
+	@Test
+	void testFindDifferences_4() {
+		final OaBrokerMainEntity source = new OaBrokerMainEntity();
+		final OaBrokerMainEntity target = new OaBrokerMainEntity();
+		source.getCreators().add(new OaBrokerAuthor("Claudio Atzori", "0000-0001-9613-6639"));
+		target.getCreators().add(new OaBrokerAuthor("Claudio Atzori", "0000-0001-9613-6639"));
+
+		final List<OaBrokerAuthor> list = this.matcher.findDifferences(source, target);
+		assertTrue(list.isEmpty());
+	}
+
+}

dhp-workflows/dhp-broker-events/src/test/java/eu/dnetlib/dhp/broker/oa/util/ConversionUtilsTest.java

@@ -2,27 +2,31 @@
 package eu.dnetlib.dhp.broker.oa.util;
 
 import static org.junit.jupiter.api.Assertions.assertEquals;
+import static org.junit.jupiter.api.Assertions.assertNull;
 
 import java.util.ArrayList;
+import java.util.Arrays;
 import java.util.List;
 
 import org.junit.jupiter.api.BeforeEach;
 import org.junit.jupiter.api.Test;
 
+import eu.dnetlib.broker.objects.OaBrokerMainEntity;
 import eu.dnetlib.broker.objects.OaBrokerTypedValue;
+import eu.dnetlib.dhp.schema.common.ModelConstants;
+import eu.dnetlib.dhp.schema.oaf.Author;
 import eu.dnetlib.dhp.schema.oaf.Instance;
 import eu.dnetlib.dhp.schema.oaf.Qualifier;
 import eu.dnetlib.dhp.schema.oaf.Result;
 import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
 
-class ConversionUtilsTest {
+public class ConversionUtilsTest {
 
 	@BeforeEach
-	void setUp() throws Exception {
-	}
+	public void setUp() throws Exception {}
 
 	@Test
-	void testAllResultPids() {
+	public void testAllResultPids() {
 		final Qualifier qf = new Qualifier();
 		qf.setClassid("test");
 		qf.setClassname("test");
@@ -91,4 +95,42 @@ class ConversionUtilsTest {
 		assertEquals(6, list.size());
 	}
 
+	public void testOafResultToBrokerResult() {
+
+		final Author a1 = createAuthor("Michele Artini", "0000-0002-4406-428X");
+		final Author a2 = createAuthor("Claudio Atzori", "http://orcid.org/0000-0001-9613-6639");
+		final Author a3 = createAuthor("Alessia Bardi", null);
+
+		final Result r = new Result();
+		r.setAuthor(Arrays.asList(a1, a2, a3));
+
+		final OaBrokerMainEntity br = ConversionUtils.oafResultToBrokerResult(r);
+
+		assertEquals(3, br.getCreators().size());
+		assertEquals("0000-0002-4406-428X", br.getCreators().get(0).getOrcid());
+		assertEquals("0000-0001-9613-6639", br.getCreators().get(1).getOrcid());
+		assertNull(br.getCreators().get(2).getOrcid());
+	}
+
+	private Author createAuthor(final String name, final String orcid) {
+
+		final Author a = new Author();
+		a.setFullname("Michele Artini");
+
+		if (orcid != null) {
+			final Qualifier q = new Qualifier();
+			q.setClassid(ModelConstants.ORCID);
+			q.setClassname(ModelConstants.ORCID);
+			q.setSchemeid("dnet:pids");
+			q.setSchemename("dnet:pids");
+
+			final StructuredProperty pid = new StructuredProperty();
+			pid.setQualifier(q);
+			pid.setValue(orcid);
+
+			a.setPid(Arrays.asList(pid));
+		}
+		return a;
+	}
+
 }

dhp-workflows/dhp-dedup-openaire/pom.xml

@@ -38,7 +38,6 @@
                 </configuration>
             </plugin>
     	</plugins>
-    
     </build>
 
     <dependencies>

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

@@ -189,7 +189,7 @@ public class DedupRecordFactory {
 			entity = swap;
 		}
 
-		entity = MergeUtils.checkedMerge(entity, duplicate);
+		entity = MergeUtils.checkedMerge(entity, duplicate, false);
 
 		if (ModelSupport.isSubClass(duplicate, Result.class)) {
 			Result re = (Result) entity;

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

@@ -175,6 +175,7 @@ public class SparkCreateMergeRels extends AbstractSparkAction {
 			}
 
 			// cap pidType at w3id as from there on they are considered equal
+
 			UserDefinedFunction mapPid = udf(
 				(String s) -> Math.min(PidType.tryValueOf(s).ordinal(), PidType.w3id.ordinal()), DataTypes.IntegerType);
 
@@ -202,8 +203,8 @@ public class SparkCreateMergeRels extends AbstractSparkAction {
 			WindowSpec w = Window
 				.partitionBy("groupId")
 				.orderBy(
-					col("lastUsage").desc_nulls_last(),
 					col("pidType").asc_nulls_last(),
+					col("lastUsage").desc_nulls_last(),
 					col("collectedfrom").desc_nulls_last(),
 					col("date").asc_nulls_last(),
 					col("id").asc_nulls_last());

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

@@ -44,8 +44,10 @@ public class SparkCreateSimRels extends AbstractSparkAction {
 		parser.parseArgument(args);
 
 		SparkConf conf = new SparkConf();
-		new SparkCreateSimRels(parser, getSparkSession(conf))
-			.run(ISLookupClientFactory.getLookUpService(parser.get("isLookUpUrl")));
+		try (SparkSession session = getSparkSession(conf)) {
+			new SparkCreateSimRels(parser, session)
+				.run(ISLookupClientFactory.getLookUpService(parser.get("isLookUpUrl")));
+		}
 	}
 
 	@Override

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

@@ -22,7 +22,9 @@ import eu.dnetlib.dhp.oa.dedup.model.OrgSimRel;
 import eu.dnetlib.dhp.schema.common.EntityType;
 import eu.dnetlib.dhp.schema.common.ModelConstants;
 import eu.dnetlib.dhp.schema.common.ModelSupport;
+import eu.dnetlib.dhp.schema.oaf.Field;
 import eu.dnetlib.dhp.schema.oaf.Organization;
+import eu.dnetlib.dhp.schema.oaf.Qualifier;
 import eu.dnetlib.dhp.schema.oaf.Relation;
 import eu.dnetlib.dhp.utils.ISLookupClientFactory;
 import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
@@ -164,12 +166,12 @@ public class SparkPrepareNewOrgs extends AbstractSparkAction {
 			.map(
 				(MapFunction<Tuple2<Tuple2<String, Organization>, Tuple2<String, String>>, OrgSimRel>) r -> new OrgSimRel(
 					"",
-					r._1()._2().getOriginalId().get(0),
-					r._1()._2().getLegalname() != null ? r._1()._2().getLegalname().getValue() : "",
-					r._1()._2().getLegalshortname() != null ? r._1()._2().getLegalshortname().getValue() : "",
-					r._1()._2().getCountry() != null ? r._1()._2().getCountry().getClassid() : "",
-					r._1()._2().getWebsiteurl() != null ? r._1()._2().getWebsiteurl().getValue() : "",
-					r._1()._2().getCollectedfrom().get(0).getValue(),
+					Optional.ofNullable(r._1()._2().getOriginalId()).map(oid -> oid.get(0)).orElse(null),
+					Optional.ofNullable(r._1()._2().getLegalname()).map(Field::getValue).orElse(""),
+					Optional.ofNullable(r._1()._2().getLegalshortname()).map(Field::getValue).orElse(""),
+					Optional.ofNullable(r._1()._2().getCountry()).map(Qualifier::getClassid).orElse(""),
+					Optional.ofNullable(r._1()._2().getWebsiteurl()).map(Field::getValue).orElse(""),
+					Optional.ofNullable(r._1()._2().getCollectedfrom()).map(cf -> cf.get(0).getValue()).orElse(null),
 					"",
 					structuredPropertyListToString(r._1()._2().getPid()),
 					parseECField(r._1()._2().getEclegalbody()),

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

@@ -217,7 +217,7 @@ public class SparkPrepareOrgRels extends AbstractSparkAction {
 					final Organization o = r._2()._2();
 					return new OrgSimRel(
 						r._1()._1(),
-						o.getOriginalId().get(0),
+						Optional.ofNullable(o.getOriginalId()).map(oid -> oid.get(0)).orElse(null),
 						Optional.ofNullable(o.getLegalname()).map(Field::getValue).orElse(""),
 						Optional.ofNullable(o.getLegalshortname()).map(Field::getValue).orElse(""),
 						Optional.ofNullable(o.getCountry()).map(Qualifier::getClassid).orElse(""),
@@ -249,7 +249,9 @@ public class SparkPrepareOrgRels extends AbstractSparkAction {
 			.map(
 				(MapFunction<Tuple2<Tuple2<String, OrgSimRel>, Tuple2<String, Organization>>, OrgSimRel>) r -> {
 					OrgSimRel orgSimRel = r._1()._2();
-					orgSimRel.setLocal_id(r._2()._2().getOriginalId().get(0));
+					orgSimRel
+						.setLocal_id(
+							Optional.ofNullable(r._2()._2().getOriginalId()).map(oid -> oid.get(0)).orElse(null));
 					return orgSimRel;
 				},
 				Encoders.bean(OrgSimRel.class));

dhp-workflows/dhp-dedup-openaire/src/main/resources/eu/dnetlib/dhp/oa/dedup/consistency/oozie_app/workflow.xml

@@ -102,6 +102,8 @@
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
                 --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
                 --conf spark.sql.shuffle.partitions=15000
+                --conf spark.network.timeout=300s
+                --conf spark.shuffle.registration.timeout=50000
             </spark-opts>
             <arg>--graphBasePath</arg><arg>${graphBasePath}</arg>
             <arg>--graphOutputPath</arg><arg>${graphOutputPath}</arg>

dhp-workflows/dhp-dedup-openaire/src/main/resources/eu/dnetlib/dhp/oa/dedup/openorgs/oozie_app/config-default.xml

@@ -15,4 +15,12 @@
         <name>oozie.action.sharelib.for.spark</name>
         <value>spark2</value>
     </property>
+    <property>
+        <name>hiveMetastoreUris</name>
+        <value>thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083</value>
+    </property>
+    <property>
+        <name>pivotHistoryDatabase</name>
+        <value>&#x200B;</value>
+    </property>
 </configuration>

dhp-workflows/dhp-dedup-openaire/src/main/resources/eu/dnetlib/dhp/oa/dedup/openorgs/oozie_app/workflow.xml

@@ -198,6 +198,8 @@
             <arg>--isLookUpUrl</arg><arg>${isLookUpUrl}</arg>
             <arg>--actionSetId</arg><arg>${actionSetId}</arg>
             <arg>--cutConnectedComponent</arg><arg>${cutConnectedComponent}</arg>
+            <arg>--hiveMetastoreUris</arg><arg>${hiveMetastoreUris}</arg>
+            <arg>--pivotHistoryDatabase</arg><arg>${pivotHistoryDatabase}</arg>
         </spark>
         <ok to="PrepareOrgRels"/>
         <error to="Kill"/>

dhp-workflows/dhp-dedup-openaire/src/main/resources/eu/dnetlib/dhp/oa/dedup/scan/oozie_app/workflow.xml

@@ -33,16 +33,14 @@
             <description>max number of elements in a connected component</description>
         </property>
         <property>
-            <name>sparkDriverMemory</name>
-            <description>memory for driver process</description>
+            <name>sparkResourceOpts</name>
+            <value>--executor-memory=6G --conf spark.executor.memoryOverhead=4G --executor-cores=6 --driver-memory=8G --driver-cores=4</value>
+            <description>spark resource options</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>
+            <name>sparkResourceOptsCreateMergeRel</name>
+            <value>--executor-memory=6G --conf spark.executor.memoryOverhead=4G --executor-cores=6 --driver-memory=8G --driver-cores=4</value>
+            <description>spark resource options</description>
         </property>
         <property>
             <name>oozieActionShareLibForSpark2</name>
@@ -119,9 +117,7 @@
             <class>eu.dnetlib.dhp.oa.dedup.SparkCreateSimRels</class>
             <jar>dhp-dedup-openaire-${projectVersion}.jar</jar>
             <spark-opts>
-                --executor-memory=${sparkExecutorMemory}
-                --executor-cores=${sparkExecutorCores}
-                --driver-memory=${sparkDriverMemory}
+                ${sparkResourceOpts}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
@@ -146,9 +142,7 @@
             <class>eu.dnetlib.dhp.oa.dedup.SparkWhitelistSimRels</class>
             <jar>dhp-dedup-openaire-${projectVersion}.jar</jar>
             <spark-opts>
-                --executor-memory=${sparkExecutorMemory}
-                --executor-cores=${sparkExecutorCores}
-                --driver-memory=${sparkDriverMemory}
+                ${sparkResourceOpts}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
@@ -174,9 +168,7 @@
             <class>eu.dnetlib.dhp.oa.dedup.SparkCreateMergeRels</class>
             <jar>dhp-dedup-openaire-${projectVersion}.jar</jar>
             <spark-opts>
-                --executor-memory=${sparkExecutorMemory}
-                --executor-cores=${sparkExecutorCores}
-                --driver-memory=${sparkDriverMemory}
+                ${sparkResourceOptsCreateMergeRel}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
@@ -203,9 +195,7 @@
             <class>eu.dnetlib.dhp.oa.dedup.SparkCreateDedupRecord</class>
             <jar>dhp-dedup-openaire-${projectVersion}.jar</jar>
             <spark-opts>
-                --executor-memory=${sparkExecutorMemory}
-                --executor-cores=${sparkExecutorCores}
-                --driver-memory=${sparkDriverMemory}
+                ${sparkResourceOpts}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
@@ -230,9 +220,7 @@
             <class>eu.dnetlib.dhp.oa.dedup.SparkCopyOpenorgsMergeRels</class>
             <jar>dhp-dedup-openaire-${projectVersion}.jar</jar>
             <spark-opts>
-                --executor-memory=${sparkExecutorMemory}
-                --executor-cores=${sparkExecutorCores}
-                --driver-memory=${sparkDriverMemory}
+                ${sparkResourceOpts}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
@@ -257,9 +245,7 @@
             <class>eu.dnetlib.dhp.oa.dedup.SparkCreateOrgsDedupRecord</class>
             <jar>dhp-dedup-openaire-${projectVersion}.jar</jar>
             <spark-opts>
-                --executor-memory=${sparkExecutorMemory}
-                --executor-cores=${sparkExecutorCores}
-                --driver-memory=${sparkDriverMemory}
+                ${sparkResourceOpts}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
@@ -283,9 +269,7 @@
             <class>eu.dnetlib.dhp.oa.dedup.SparkUpdateEntity</class>
             <jar>dhp-dedup-openaire-${projectVersion}.jar</jar>
             <spark-opts>
-                --executor-memory=${sparkExecutorMemory}
-                --executor-cores=${sparkExecutorCores}
-                --driver-memory=${sparkDriverMemory}
+                ${sparkResourceOpts}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
@@ -309,9 +293,7 @@
             <class>eu.dnetlib.dhp.oa.dedup.SparkCopyRelationsNoOpenorgs</class>
             <jar>dhp-dedup-openaire-${projectVersion}.jar</jar>
             <spark-opts>
-                --executor-memory=${sparkExecutorMemory}
-                --executor-cores=${sparkExecutorCores}
-                --driver-memory=${sparkDriverMemory}
+                ${sparkResourceOpts}
                 --conf spark.extraListeners=${spark2ExtraListeners}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}

dhp-workflows/dhp-dedup-openaire/src/test/java/eu/dnetlib/dhp/oa/dedup/DatasetMergerTest.java

@@ -0,0 +1,103 @@
+
+package eu.dnetlib.dhp.oa.dedup;
+
+import static org.junit.jupiter.api.Assertions.assertEquals;
+
+import java.io.BufferedReader;
+import java.io.FileReader;
+import java.io.IOException;
+import java.io.Serializable;
+import java.lang.reflect.InvocationTargetException;
+import java.nio.file.Paths;
+import java.util.ArrayList;
+import java.util.List;
+
+import org.codehaus.jackson.map.ObjectMapper;
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.Test;
+
+import eu.dnetlib.dhp.schema.oaf.DataInfo;
+import eu.dnetlib.dhp.schema.oaf.Dataset;
+import eu.dnetlib.dhp.schema.oaf.utils.MergeUtils;
+import eu.dnetlib.pace.util.MapDocumentUtil;
+import scala.Tuple2;
+
+class DatasetMergerTest implements Serializable {
+
+	private List<Tuple2<String, Dataset>> datasets;
+
+	private String testEntityBasePath;
+	private DataInfo dataInfo;
+	private final String dedupId = "50|doi_________::3d18564ef27ebe9ef3bd8b4dec67e148";
+	private Dataset dataset_top;
+
+	@BeforeEach
+	public void setUp() throws Exception {
+		testEntityBasePath = Paths
+			.get(SparkDedupTest.class.getResource("/eu/dnetlib/dhp/dedup/json").toURI())
+			.toFile()
+			.getAbsolutePath();
+
+		datasets = readSample(testEntityBasePath + "/dataset_merge.json", Dataset.class);
+
+		dataset_top = getTopPub(datasets);
+
+		dataInfo = setDI();
+	}
+
+	@Test
+	void datasetMergerTest() throws InstantiationException, IllegalAccessException, InvocationTargetException {
+		Dataset pub_merged = MergeUtils.mergeGroup(dedupId, datasets.stream().map(Tuple2::_2).iterator());
+
+		// verify id
+		assertEquals(dedupId, pub_merged.getId());
+		assertEquals(2, pub_merged.getInstance().size());
+	}
+
+	public DataInfo setDI() {
+		DataInfo dataInfo = new DataInfo();
+		dataInfo.setTrust("0.9");
+		dataInfo.setDeletedbyinference(false);
+		dataInfo.setInferenceprovenance("testing");
+		dataInfo.setInferred(true);
+		return dataInfo;
+	}
+
+	public Dataset getTopPub(List<Tuple2<String, Dataset>> publications) {
+
+		Double maxTrust = 0.0;
+		Dataset maxPub = new Dataset();
+		for (Tuple2<String, Dataset> publication : publications) {
+			Double pubTrust = Double.parseDouble(publication._2().getDataInfo().getTrust());
+			if (pubTrust > maxTrust) {
+				maxTrust = pubTrust;
+				maxPub = publication._2();
+			}
+		}
+		return maxPub;
+	}
+
+	public <T> List<Tuple2<String, T>> readSample(String path, Class<T> clazz) {
+		List<Tuple2<String, T>> res = new ArrayList<>();
+		BufferedReader reader;
+		try {
+			reader = new BufferedReader(new FileReader(path));
+			String line = reader.readLine();
+			while (line != null) {
+				res
+					.add(
+						new Tuple2<>(
+							MapDocumentUtil.getJPathString("$.id", line),
+							new ObjectMapper().readValue(line, clazz)));
+				// read next line
+				line = reader.readLine();
+			}
+			reader.close();
+		} catch (IOException e) {
+			e.printStackTrace();
+		}
+
+		return res;
+	}
+
+}