minor fix

.gitignore

@@ -26,4 +26,3 @@ spark-warehouse
 /**/*.log
 /**/.factorypath
 /**/.scalafmt.conf
-/.java-version

CODE_OF_CONDUCT.md

@@ -1,43 +0,0 @@
-# Contributor Code of Conduct
-
-Openness, transparency and our community-driven participatory approach guide us in our day-to-day interactions and decision-making. Our open source projects are no exception. Trust, respect, collaboration and transparency are core values we believe should live and breathe within our projects. Our community welcomes participants from around the world with different experiences, unique perspectives, and great ideas to share.
-
-## Our Pledge
-
-In the interest of fostering an open and welcoming environment, we as contributors and maintainers pledge to making participation in our project and our community a harassment-free experience for everyone, regardless of age, body size, disability, ethnicity, sex characteristics, gender identity and expression, level of experience, education, socio-economic status, nationality, personal appearance, race, religion, or sexual identity and orientation.
-
-## Our Standards
-
-Examples of behavior that contributes to creating a positive environment include:
-
-- Using welcoming and inclusive language
-- Being respectful of differing viewpoints and experiences
-- Gracefully accepting constructive criticism
-- Attempting collaboration before conflict
-- Focusing on what is best for the community
-- Showing empathy towards other community members
-
-Examples of unacceptable behavior by participants include:
-
-- Violence, threats of violence, or inciting others to commit self-harm
-- The use of sexualized language or imagery and unwelcome sexual attention or advances
-- Trolling, intentionally spreading misinformation, insulting/derogatory comments, and personal or political attacks
-- Public or private harassment
-- Publishing others' private information, such as a physical or electronic address, without explicit permission
-- Abuse of the reporting process to intentionally harass or exclude others
-- Advocating for, or encouraging, any of the above behavior
-- Other conduct which could reasonably be considered inappropriate in a professional setting
-
-## Our Responsibilities
-
-Project maintainers are responsible for clarifying the standards of acceptable behavior and are expected to take appropriate and fair corrective action in response to any instances of unacceptable behavior.
-
-Project maintainers have the right and responsibility to remove, edit, or reject comments, commits, code, wiki edits, issues, and other contributions that are not aligned to this Code of Conduct, or to ban temporarily or permanently any contributor for other behaviors that they deem inappropriate, threatening, offensive, or harmful.
-
-## Scope
-
-This Code of Conduct applies both within project spaces and in public spaces when an individual is representing the project or its community. Examples of representing a project or community include using an official project e-mail address, posting via an official social media account, or acting as an appointed representative at an online or offline event. Representation of a project may be further defined and clarified by project maintainers.
-
-## Attribution
-
-This Code of Conduct is adapted from the [Contributor Covenant](https://www.contributor-covenant.org/), [version 1.4](https://www.contributor-covenant.org/version/1/4/code-of-conduct.html).

CONTRIBUTING.md

@@ -1,10 +0,0 @@
-# Contributing to D-Net Hadoop
-
-:+1::tada: First off, thanks for taking the time to contribute! :tada::+1:
-
-This project and everyone participating in it is governed by our [Code of Conduct](CODE_OF_CONDUCT.md). By participating, you are expected to uphold this code. Please report unacceptable behavior to [dnet-team@isti.cnr.it](mailto:dnet-team@isti.cnr.it).
-
-The following is a set of guidelines for contributing to this project and its packages. These are mostly guidelines, not rules, which applies to this project as a while, including all its sub-modules. 
-Use your best judgment, and feel free to propose changes to this document in a pull request.
-
-All contributions are welcome, all contributions will be considered to be contributed under the [project license](LICENSE.md).

README.md

@@ -1,133 +1,2 @@
 # dnet-hadoop
-
-Dnet-hadoop is the project that defined all the [OOZIE workflows](https://oozie.apache.org/) for the OpenAIRE Graph construction, processing, provisioning.
-
-This project adheres to the Contributor Covenant [code of conduct](CODE_OF_CONDUCT.md).
-By participating, you are expected to uphold this code. Please report unacceptable behavior to [dnet-team@isti.cnr.it](mailto:dnet-team@isti.cnr.it).
-
-This project is licensed under the [AGPL v3 or later version](#LICENSE.md).
-
-How to build, package and run oozie workflows
-====================
-
-Oozie-installer is a utility allowing building, uploading and running oozie workflows. In practice, it creates a `*.tar.gz` 
-package that contains resources that define a workflow and some helper scripts.
-
-This module is automatically executed when running:
-
-`mvn package -Poozie-package -Dworkflow.source.dir=classpath/to/parent/directory/of/oozie_app`
-
-on module having set:
-
-```
-<parent>
-    <groupId>eu.dnetlib.dhp</groupId>
-    <artifactId>dhp-workflows</artifactId>
-</parent>
-```
-
-in `pom.xml` file. `oozie-package` profile initializes oozie workflow packaging, `workflow.source.dir` property points to 
-a workflow (notice: this is not a relative path but a classpath to directory usually holding `oozie_app` subdirectory).
-
-The outcome of this packaging is `oozie-package.tar.gz` file containing inside all the resources required to run Oozie workflow:
-
-- jar packages
-- workflow definitions
-- job properties
-- maintenance scripts
-
-Required properties
-====================
-
-In order to include proper workflow within package, `workflow.source.dir` property has to be set. It could be provided 
-by setting `-Dworkflow.source.dir=some/job/dir` maven parameter.
-
-In oder to define full set of cluster environment properties one should create `~/.dhp/application.properties` file with 
-the following properties:
-
-- `dhp.hadoop.frontend.user.name` - your user name on hadoop cluster and frontend machine
-- `dhp.hadoop.frontend.host.name` - frontend host name
-- `dhp.hadoop.frontend.temp.dir` - frontend directory for temporary files
-- `dhp.hadoop.frontend.port.ssh` - frontend machine ssh port
-- `oozieServiceLoc` - oozie service location required by run_workflow.sh script executing oozie job
-- `nameNode` - name node address
-- `jobTracker` - job tracker address
-- `oozie.execution.log.file.location` - location of file that will be created when executing oozie job, it contains output 
-produced by `run_workflow.sh` script (needed to obtain oozie job id)
-- `maven.executable` - mvn command location, requires parameterization due to a different setup of CI cluster
-- `sparkDriverMemory` - amount of memory assigned to spark jobs driver
-- `sparkExecutorMemory` - amount of memory assigned to spark jobs executors
-- `sparkExecutorCores` - number of cores assigned to spark jobs executors
-
-All values will be overriden with the ones from `job.properties` and eventually `job-override.properties` stored in module's 
-main folder.
-
-When overriding properties from `job.properties`, `job-override.properties` file can be created in main module directory 
-(the one containing `pom.xml` file) and define all new properties which will override existing properties. 
-One can provide those properties one by one as command line `-D` arguments.
-
-Properties overriding order is the following:
-
-1. `pom.xml` defined properties (located in the project root dir)
-2. `~/.dhp/application.properties` defined properties
-3. `${workflow.source.dir}/job.properties`
-4. `job-override.properties` (located in the project root dir)
-5. `maven -Dparam=value`
-
-where the maven `-Dparam` property is overriding all the other ones.
-
-Workflow definition requirements
-====================
-
-`workflow.source.dir` property should point to the following directory structure:
-
-	[${workflow.source.dir}]
-		|
-		|-job.properties (optional)
-		|
-		\-[oozie_app]
-			|
-			\-workflow.xml
-
-This property can be set using maven `-D` switch.
-
-`[oozie_app]` is the default directory name however it can be set to any value as soon as `oozieAppDir` property is 
-provided with directory name as value.
-
-Sub-workflows are supported as well and sub-workflow directories should be nested within `[oozie_app]` directory.
-
-Creating oozie installer step-by-step
-=====================================
-
-Automated oozie-installer steps are the following:
-
-1. creating jar packages:  `*.jar` and `*tests.jar` along with copying all dependencies in `target/dependencies`
-2. reading properties from maven, `~/.dhp/application.properties`, `job.properties`, `job-override.properties`
-3. invoking priming mechanism linking resources from import.txt file (currently resolving subworkflow resources)
-4. assembling shell scripts for preparing Hadoop filesystem, uploading Oozie application and starting workflow
-5. copying whole `${workflow.source.dir}` content to `target/${oozie.package.file.name}`
-6. generating updated `job.properties` file in `target/${oozie.package.file.name}` based on maven, 
-`~/.dhp/application.properties`, `job.properties` and `job-override.properties`
-7. creating `lib` directory (or multiple directories for sub-workflows for each nested directory) and copying jar packages 
-created at step (1) to each one of them
-8. bundling whole `${oozie.package.file.name}` directory into single tar.gz package
-
-Uploading oozie package and running workflow on cluster
-=======================================================
-
-In order to simplify deployment and execution process two dedicated profiles were introduced:
-
-- `deploy`
-- `run`
-
-to be used along with `oozie-package` profile e.g. by providing `-Poozie-package,deploy,run` maven parameters.
-
-The `deploy` profile supplements packaging process with:
-1) uploading oozie-package via scp to `/home/${user.name}/oozie-packages` directory on `${dhp.hadoop.frontend.host.name}` machine
-2) extracting uploaded package
-3) uploading oozie content to hadoop cluster HDFS location defined in `oozie.wf.application.path` property (generated dynamically by maven build process, based on `${dhp.hadoop.frontend.user.name}` and `workflow.source.dir` properties)
-
-The `run` profile introduces:
-1) executing oozie application uploaded to HDFS cluster using `deploy` command. Triggers `run_workflow.sh` script providing runtime properties defined in `job.properties` file.
-
-Notice: ssh access to frontend machine has to be configured on system level and it is preferable to set key-based authentication in order to simplify remote operations.
+Dnet-hadoop is the project that defined all the OOZIE workflows for the OpenAIRE Graph construction, processing, provisioning.

dhp-common/pom.xml

@@ -62,11 +62,6 @@
 	</build>
 
 	<dependencies>
-		<dependency>
-			<groupId>eu.dnetlib.dhp</groupId>
-			<artifactId>dhp-pace-core</artifactId>
-			<version>${project.version}</version>
-		</dependency>
 
 		<dependency>
 			<groupId>org.apache.hadoop</groupId>
@@ -129,6 +124,12 @@
 		<dependency>
 			<groupId>eu.dnetlib</groupId>
 			<artifactId>cnr-rmi-api</artifactId>
+			<exclusions>
+				<exclusion>
+					<groupId>log4j</groupId>
+					<artifactId>log4j</artifactId>
+				</exclusion>
+			</exclusions>
 		</dependency>
 
 		<dependency>
@@ -149,6 +150,11 @@
 			<artifactId>okhttp</artifactId>
 		</dependency>
 
+		<dependency>
+			<groupId>eu.dnetlib.dhp</groupId>
+			<artifactId>dhp-pace-core</artifactId>
+		</dependency>
+
 		<dependency>
 			<groupId>org.apache.httpcomponents</groupId>
 			<artifactId>httpclient</artifactId>
@@ -161,7 +167,7 @@
 
 		<dependency>
 			<groupId>eu.dnetlib.dhp</groupId>
-			<artifactId>${dhp-schemas.artifact}</artifactId>
+			<artifactId>dhp-schemas_${scala.binary.version}</artifactId>
 		</dependency>
 
 		<dependency>

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

@@ -51,7 +51,6 @@ public class Constants {
 	public static final String RETRY_DELAY = "retryDelay";
 	public static final String CONNECT_TIMEOUT = "connectTimeOut";
 	public static final String READ_TIMEOUT = "readTimeOut";
-	public static final String REQUEST_METHOD = "requestMethod";
 	public static final String FROM_DATE_OVERRIDE = "fromDateOverride";
 	public static final String UNTIL_DATE_OVERRIDE = "untilDateOverride";
 

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

@@ -0,0 +1,53 @@
+
+package eu.dnetlib.dhp.common.api;
+
+import java.io.IOException;
+import java.io.InputStream;
+
+import okhttp3.MediaType;
+import okhttp3.RequestBody;
+import okhttp3.internal.Util;
+import okio.BufferedSink;
+import okio.Okio;
+import okio.Source;
+
+public class InputStreamRequestBody extends RequestBody {
+
+	private 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

@@ -0,0 +1,8 @@
+
+package eu.dnetlib.dhp.common.api;
+
+public class MissingConceptDoiException extends Throwable {
+	public MissingConceptDoiException(String message) {
+		super(message);
+	}
+}

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

@@ -0,0 +1,365 @@
+
+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/context/CategorySummary.java

@@ -1,39 +0,0 @@
-
-package eu.dnetlib.dhp.common.api.context;
-
-public class CategorySummary {
-
-	private String id;
-
-	private String label;
-
-	private boolean hasConcept;
-
-	public String getId() {
-		return id;
-	}
-
-	public String getLabel() {
-		return label;
-	}
-
-	public boolean isHasConcept() {
-		return hasConcept;
-	}
-
-	public CategorySummary setId(final String id) {
-		this.id = id;
-		return this;
-	}
-
-	public CategorySummary setLabel(final String label) {
-		this.label = label;
-		return this;
-	}
-
-	public CategorySummary setHasConcept(final boolean hasConcept) {
-		this.hasConcept = hasConcept;
-		return this;
-	}
-
-}

dhp-common/src/main/java/eu/dnetlib/dhp/common/api/context/CategorySummaryList.java

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

dhp-common/src/main/java/eu/dnetlib/dhp/common/api/context/ConceptSummary.java

@@ -1,52 +0,0 @@
-
-package eu.dnetlib.dhp.common.api.context;
-
-import java.util.List;
-
-public class ConceptSummary {
-
-	private String id;
-
-	private String label;
-
-	public boolean hasSubConcept;
-
-	private List<ConceptSummary> concepts;
-
-	public String getId() {
-		return id;
-	}
-
-	public String getLabel() {
-		return label;
-	}
-
-	public List<ConceptSummary> getConcepts() {
-		return concepts;
-	}
-
-	public ConceptSummary setId(final String id) {
-		this.id = id;
-		return this;
-	}
-
-	public ConceptSummary setLabel(final String label) {
-		this.label = label;
-		return this;
-	}
-
-	public boolean isHasSubConcept() {
-		return hasSubConcept;
-	}
-
-	public ConceptSummary setHasSubConcept(final boolean hasSubConcept) {
-		this.hasSubConcept = hasSubConcept;
-		return this;
-	}
-
-	public ConceptSummary setConcept(final List<ConceptSummary> concepts) {
-		this.concepts = concepts;
-		return this;
-	}
-
-}

dhp-common/src/main/java/eu/dnetlib/dhp/common/api/context/ConceptSummaryList.java

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

dhp-common/src/main/java/eu/dnetlib/dhp/common/api/context/ContextSummary.java

@@ -1,50 +0,0 @@
-
-package eu.dnetlib.dhp.common.api.context;
-
-public class ContextSummary {
-
-	private String id;
-
-	private String label;
-
-	private String type;
-
-	private String status;
-
-	public String getId() {
-		return id;
-	}
-
-	public String getLabel() {
-		return label;
-	}
-
-	public String getType() {
-		return type;
-	}
-
-	public String getStatus() {
-		return status;
-	}
-
-	public ContextSummary setId(final String id) {
-		this.id = id;
-		return this;
-	}
-
-	public ContextSummary setLabel(final String label) {
-		this.label = label;
-		return this;
-	}
-
-	public ContextSummary setType(final String type) {
-		this.type = type;
-		return this;
-	}
-
-	public ContextSummary setStatus(final String status) {
-		this.status = status;
-		return this;
-	}
-
-}

dhp-common/src/main/java/eu/dnetlib/dhp/common/api/context/ContextSummaryList.java

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

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

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

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

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

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

@@ -0,0 +1,44 @@
+
+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

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

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

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

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

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

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

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

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

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

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

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

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

@@ -0,0 +1,7 @@
+
+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/common/collection/HttpClientParams.java

@@ -1,9 +1,6 @@
 
 package eu.dnetlib.dhp.common.collection;
 
-import java.util.HashMap;
-import java.util.Map;
-
 /**
  * Bundles the http connection parameters driving the client behaviour.
  */
@@ -16,8 +13,6 @@ public class HttpClientParams {
 	public static int _connectTimeOut = 10; // seconds
 	public static int _readTimeOut = 30; // seconds
 
-	public static String _requestMethod = "GET";
-
 	/**
 	 * Maximum number of allowed retires before failing
 	 */
@@ -43,30 +38,17 @@ public class HttpClientParams {
 	 */
 	private int readTimeOut;
 
-	/**
-	 * Custom http headers
-	 */
-	private Map<String, String> headers;
-
-	/**
-	 * Request method (i.e., GET, POST etc)
-	 */
-	private String requestMethod;
-
 	public HttpClientParams() {
-		this(_maxNumberOfRetry, _requestDelay, _retryDelay, _connectTimeOut, _readTimeOut, new HashMap<>(),
-			_requestMethod);
+		this(_maxNumberOfRetry, _requestDelay, _retryDelay, _connectTimeOut, _readTimeOut);
 	}
 
 	public HttpClientParams(int maxNumberOfRetry, int requestDelay, int retryDelay, int connectTimeOut,
-		int readTimeOut, Map<String, String> headers, String requestMethod) {
+		int readTimeOut) {
 		this.maxNumberOfRetry = maxNumberOfRetry;
 		this.requestDelay = requestDelay;
 		this.retryDelay = retryDelay;
 		this.connectTimeOut = connectTimeOut;
 		this.readTimeOut = readTimeOut;
-		this.headers = headers;
-		this.requestMethod = requestMethod;
 	}
 
 	public int getMaxNumberOfRetry() {
@@ -109,19 +91,4 @@ public class HttpClientParams {
 		this.readTimeOut = readTimeOut;
 	}
 
-	public Map<String, String> getHeaders() {
-		return headers;
-	}
-
-	public void setHeaders(Map<String, String> headers) {
-		this.headers = headers;
-	}
-
-	public String getRequestMethod() {
-		return requestMethod;
-	}
-
-	public void setRequestMethod(String requestMethod) {
-		this.requestMethod = requestMethod;
-	}
 }

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

@@ -8,13 +8,10 @@ import java.io.InputStream;
 import java.net.*;
 import java.util.List;
 import java.util.Map;
-import java.util.concurrent.TimeUnit;
 
 import org.apache.commons.io.IOUtils;
 import org.apache.commons.lang3.math.NumberUtils;
-import org.apache.commons.lang3.time.DateUtils;
 import org.apache.http.HttpHeaders;
-import org.joda.time.Instant;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 
@@ -97,32 +94,24 @@ public class HttpConnector2 {
 			throw new CollectorException(msg);
 		}
 
+		log.info("Request attempt {} [{}]", retryNumber, requestUrl);
+
 		InputStream input = null;
 
-		long start = System.currentTimeMillis();
 		try {
 			if (getClientParams().getRequestDelay() > 0) {
 				backoffAndSleep(getClientParams().getRequestDelay());
 			}
-
-			log.info("Request attempt {} [{}]", retryNumber, requestUrl);
-
 			final HttpURLConnection urlConn = (HttpURLConnection) new URL(requestUrl).openConnection();
 			urlConn.setInstanceFollowRedirects(false);
 			urlConn.setReadTimeout(getClientParams().getReadTimeOut() * 1000);
 			urlConn.setConnectTimeout(getClientParams().getConnectTimeOut() * 1000);
 			urlConn.addRequestProperty(HttpHeaders.USER_AGENT, userAgent);
-			urlConn.setRequestMethod(getClientParams().getRequestMethod());
 
-			// if provided, add custom headers
-			if (!getClientParams().getHeaders().isEmpty()) {
-				for (Map.Entry<String, String> headerEntry : getClientParams().getHeaders().entrySet()) {
-					urlConn.addRequestProperty(headerEntry.getKey(), headerEntry.getValue());
-				}
+			if (log.isDebugEnabled()) {
+				logHeaderFields(urlConn);
 			}
 
-			logHeaderFields(urlConn);
-
 			int retryAfter = obtainRetryAfter(urlConn.getHeaderFields());
 			String rateLimit = urlConn.getHeaderField(Constants.HTTPHEADER_IETF_DRAFT_RATELIMIT_LIMIT);
 			String rateRemaining = urlConn.getHeaderField(Constants.HTTPHEADER_IETF_DRAFT_RATELIMIT_REMAINING);
@@ -136,7 +125,9 @@ public class HttpConnector2 {
 			}
 
 			if (is2xx(urlConn.getResponseCode())) {
-				return getInputStream(urlConn, start);
+				input = urlConn.getInputStream();
+				responseType = urlConn.getContentType();
+				return input;
 			}
 			if (is3xx(urlConn.getResponseCode())) {
 				// REDIRECTS
@@ -146,7 +137,6 @@ public class HttpConnector2 {
 					.put(
 						REPORT_PREFIX + urlConn.getResponseCode(),
 						String.format("Moved to: %s", newUrl));
-				logRequestTime(start);
 				urlConn.disconnect();
 				if (retryAfter > 0) {
 					backoffAndSleep(retryAfter);
@@ -162,50 +152,26 @@ public class HttpConnector2 {
 						if (retryAfter > 0) {
 							log
 								.warn(
-									"waiting and repeating request after suggested retry-after {} sec for URL {}",
-									retryAfter, requestUrl);
+									"{} - waiting and repeating request after suggested retry-after {} sec.",
+									requestUrl, retryAfter);
 							backoffAndSleep(retryAfter * 1000);
 						} else {
 							log
 								.warn(
-									"waiting and repeating request after default delay of {} sec for URL {}",
-									getClientParams().getRetryDelay(), requestUrl);
-							backoffAndSleep(retryNumber * getClientParams().getRetryDelay());
+									"{} - waiting and repeating request after default delay of {} sec.",
+									requestUrl, getClientParams().getRetryDelay());
+							backoffAndSleep(retryNumber * getClientParams().getRetryDelay() * 1000);
 						}
 						report.put(REPORT_PREFIX + urlConn.getResponseCode(), requestUrl);
-
-						logRequestTime(start);
-
 						urlConn.disconnect();
-
 						return attemptDownload(requestUrl, retryNumber + 1, report);
-					case 422: // UNPROCESSABLE ENTITY
-						report.put(REPORT_PREFIX + urlConn.getResponseCode(), requestUrl);
-						log.warn("waiting and repeating request after 10 sec for URL {}", requestUrl);
-						backoffAndSleep(10000);
-						urlConn.disconnect();
-						logRequestTime(start);
-						try {
-							return getInputStream(urlConn, start);
-						} catch (IOException e) {
-							log
-								.error(
-									"server returned 422 and got IOException accessing the response body from URL {}",
-									requestUrl);
-							log.error("IOException:", e);
-							return attemptDownload(requestUrl, retryNumber + 1, report);
-						}
 					default:
-						log.error("gor error {} from URL: {}", urlConn.getResponseCode(), urlConn.getURL());
-						log.error("response message: {}", urlConn.getResponseMessage());
 						report
 							.put(
 								REPORT_PREFIX + urlConn.getResponseCode(),
 								String
 									.format(
 										"%s Error: %s", requestUrl, urlConn.getResponseMessage()));
-						logRequestTime(start);
-						urlConn.disconnect();
 						throw new CollectorException(urlConn.getResponseCode() + " error " + report);
 				}
 			}
@@ -226,27 +192,13 @@ public class HttpConnector2 {
 		}
 	}
 
-	private InputStream getInputStream(HttpURLConnection urlConn, long start) throws IOException {
-		InputStream input = urlConn.getInputStream();
-		responseType = urlConn.getContentType();
-		logRequestTime(start);
-		return input;
-	}
-
-	private static void logRequestTime(long start) {
-		log
-			.info(
-				"request time elapsed: {}sec",
-				TimeUnit.MILLISECONDS.toSeconds(System.currentTimeMillis() - start));
-	}
-
 	private void logHeaderFields(final HttpURLConnection urlConn) throws IOException {
-		log.info("Response: {} - {}", urlConn.getResponseCode(), urlConn.getResponseMessage());
+		log.debug("StatusCode: {}", urlConn.getResponseMessage());
 
 		for (Map.Entry<String, List<String>> e : urlConn.getHeaderFields().entrySet()) {
 			if (e.getKey() != null) {
 				for (String v : e.getValue()) {
-					log.info("  key: {} - value: {}", e.getKey(), v);
+					log.debug("  key: {} - value: {}", e.getKey(), v);
 				}
 			}
 		}
@@ -266,7 +218,7 @@ public class HttpConnector2 {
 		for (String key : headerMap.keySet()) {
 			if ((key != null) && key.equalsIgnoreCase(HttpHeaders.RETRY_AFTER) && (!headerMap.get(key).isEmpty())
 				&& NumberUtils.isCreatable(headerMap.get(key).get(0))) {
-				return Integer.parseInt(headerMap.get(key).get(0));
+				return Integer.parseInt(headerMap.get(key).get(0)) + 10;
 			}
 		}
 		return -1;

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

@@ -63,10 +63,7 @@ public class Vocabulary implements Serializable {
 	}
 
 	public VocabularyTerm getTermBySynonym(final String syn) {
-		return Optional
-			.ofNullable(syn)
-			.map(s -> getTerm(synonyms.get(s.toLowerCase())))
-			.orElse(null);
+		return getTerm(synonyms.get(syn.toLowerCase()));
 	}
 
 	public Qualifier getTermAsQualifier(final String termId) {

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

@@ -135,24 +135,6 @@ public class VocabularyGroup implements Serializable {
 		return vocs.get(vocId.toLowerCase()).getSynonymAsQualifier(syn);
 	}
 
-	public Qualifier lookupTermBySynonym(final String vocId, final String syn) {
-		return find(vocId)
-			.map(
-				vocabulary -> Optional
-					.ofNullable(vocabulary.getTerm(syn))
-					.map(
-						term -> OafMapperUtils
-							.qualifier(term.getId(), term.getName(), vocabulary.getId(), vocabulary.getName()))
-					.orElse(
-						Optional
-							.ofNullable(vocabulary.getTermBySynonym(syn))
-							.map(
-								term -> OafMapperUtils
-									.qualifier(term.getId(), term.getName(), vocabulary.getId(), vocabulary.getName()))
-							.orElse(null)))
-			.orElse(null);
-	}
-
 	/**
 	 * getSynonymAsQualifierCaseSensitive
 	 *

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

@@ -119,131 +119,6 @@ public class AuthorMerger {
 				});
 	}
 
-	public static String normalizeFullName(final String fullname) {
-		return nfd(fullname)
-			.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();
-	}
-
-	private static String authorFieldToBeCompared(Author author) {
-		if (StringUtils.isNotBlank(author.getSurname())) {
-			return author.getSurname();
-
-		}
-		if (StringUtils.isNotBlank(author.getFullname())) {
-			return author.getFullname();
-		}
-		return null;
-	}
-
-	/**
-	 * This method tries to figure out when two author are the same in the contest
-	 * of ORCID enrichment
-	 *
-	 * @param left  Author in the OAF entity
-	 * @param right Author ORCID
-	 * @return based on a heuristic on the names of the authors if they are the same.
-	 */
-	public static boolean checkORCIDSimilarity(final Author left, final Author right) {
-		final Person pl = parse(left);
-		final Person pr = parse(right);
-
-		// If one of them didn't have a surname we verify if they have the fullName not empty
-		// and verify if the normalized version is equal
-		if (!(pl.getSurname() != null && pl.getSurname().stream().anyMatch(StringUtils::isNotBlank) &&
-			pr.getSurname() != null && pr.getSurname().stream().anyMatch(StringUtils::isNotBlank))) {
-
-			if (pl.getFullname() != null && !pl.getFullname().isEmpty() && pr.getFullname() != null
-				&& !pr.getFullname().isEmpty()) {
-				return pl
-					.getFullname()
-					.stream()
-					.anyMatch(
-						fl -> pr.getFullname().stream().anyMatch(fr -> normalize(fl).equalsIgnoreCase(normalize(fr))));
-			} else {
-				return false;
-			}
-		}
-		// The Authors have one surname in common
-		if (pl.getSurname().stream().anyMatch(sl -> pr.getSurname().stream().anyMatch(sr -> sr.equalsIgnoreCase(sl)))) {
-
-			// If one of them has only a surname and is the same we can say that they are the same author
-			if ((pl.getName() == null || pl.getName().stream().allMatch(StringUtils::isBlank)) ||
-				(pr.getName() == null || pr.getName().stream().allMatch(StringUtils::isBlank)))
-				return true;
-			// The authors have the same initials of Name in common
-			if (pl
-				.getName()
-				.stream()
-				.anyMatch(
-					nl -> pr
-						.getName()
-						.stream()
-						.anyMatch(nr -> nr.equalsIgnoreCase(nl))))
-				return true;
-		}
-
-		// Sometimes we noticed that publication have author wrote in inverse order Surname, Name
-		// We verify if we have an exact match between name and surname
-		if (pl.getSurname().stream().anyMatch(sl -> pr.getName().stream().anyMatch(nr -> nr.equalsIgnoreCase(sl))) &&
-			pl.getName().stream().anyMatch(nl -> pr.getSurname().stream().anyMatch(sr -> sr.equalsIgnoreCase(nl))))
-			return true;
-		else
-			return false;
-	}
-	//
-
-	/**
-	 * Method to enrich ORCID information in one list of authors based on another list
-	 *
-	 * @param baseAuthor  the Author List in the OAF Entity
-	 * @param orcidAuthor The list of ORCID Author intersected
-	 * @return The Author List of the OAF Entity enriched with the orcid Author
-	 */
-	public static List<Author> enrichOrcid(List<Author> baseAuthor, List<Author> orcidAuthor) {
-
-		if (baseAuthor == null || baseAuthor.isEmpty())
-			return orcidAuthor;
-
-		if (orcidAuthor == null || orcidAuthor.isEmpty())
-			return baseAuthor;
-
-		if (baseAuthor.size() == 1 && orcidAuthor.size() > 10)
-			return baseAuthor;
-
-		final List<Author> oAuthor = new ArrayList<>();
-		oAuthor.addAll(orcidAuthor);
-
-		baseAuthor.forEach(ba -> {
-			Optional<Author> aMatch = oAuthor.stream().filter(oa -> checkORCIDSimilarity(ba, oa)).findFirst();
-			if (aMatch.isPresent()) {
-				final Author sameAuthor = aMatch.get();
-				addPid(ba, sameAuthor.getPid());
-				oAuthor.remove(sameAuthor);
-			}
-		});
-		return baseAuthor;
-	}
-
-	private static void addPid(final Author a, final List<StructuredProperty> pids) {
-
-		if (a.getPid() == null) {
-			a.setPid(new ArrayList<>());
-		}
-
-		a.getPid().addAll(pids);
-
-	}
-
 	public static String pidToComparableString(StructuredProperty pid) {
 		final String classid = pid.getQualifier().getClassid() != null ? pid.getQualifier().getClassid().toLowerCase()
 			: "";
@@ -296,7 +171,7 @@ public class AuthorMerger {
 		}
 	}
 
-	public static String normalize(final String s) {
+	private static String normalize(final String s) {
 		String[] normalized = nfd(s)
 			.toLowerCase()
 			// do not compact the regexes in a single expression, would cause StackOverflowError

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

@@ -0,0 +1,97 @@
+
+package eu.dnetlib.dhp.oa.merge;
+
+import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
+
+import java.util.Objects;
+import java.util.Optional;
+
+import org.apache.commons.io.IOUtils;
+import org.apache.commons.lang3.StringUtils;
+import org.apache.spark.SparkConf;
+import org.apache.spark.api.java.function.FilterFunction;
+import org.apache.spark.api.java.function.MapFunction;
+import org.apache.spark.sql.Encoders;
+import org.apache.spark.sql.SaveMode;
+import org.apache.spark.sql.SparkSession;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import com.fasterxml.jackson.databind.ObjectMapper;
+
+import eu.dnetlib.dhp.application.ArgumentApplicationParser;
+import eu.dnetlib.dhp.common.HdfsSupport;
+import eu.dnetlib.dhp.schema.oaf.Oaf;
+import eu.dnetlib.dhp.schema.oaf.OafEntity;
+
+public class DispatchEntitiesSparkJob {
+
+	private static final Logger log = LoggerFactory.getLogger(DispatchEntitiesSparkJob.class);
+
+	private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
+
+	public static void main(String[] args) throws Exception {
+
+		String jsonConfiguration = IOUtils
+			.toString(
+				Objects
+					.requireNonNull(
+						DispatchEntitiesSparkJob.class
+							.getResourceAsStream(
+								"/eu/dnetlib/dhp/oa/merge/dispatch_entities_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);
+
+		String inputPath = parser.get("inputPath");
+		log.info("inputPath: {}", inputPath);
+
+		String outputPath = parser.get("outputPath");
+		log.info("outputPath: {}", outputPath);
+
+		String graphTableClassName = parser.get("graphTableClassName");
+		log.info("graphTableClassName: {}", graphTableClassName);
+
+		@SuppressWarnings("unchecked")
+		Class<? extends OafEntity> entityClazz = (Class<? extends OafEntity>) Class.forName(graphTableClassName);
+
+		SparkConf conf = new SparkConf();
+		runWithSparkSession(
+			conf,
+			isSparkSessionManaged,
+			spark -> {
+				HdfsSupport.remove(outputPath, spark.sparkContext().hadoopConfiguration());
+				dispatchEntities(spark, inputPath, entityClazz, outputPath);
+			});
+	}
+
+	private static <T extends Oaf> void dispatchEntities(
+		SparkSession spark,
+		String inputPath,
+		Class<T> clazz,
+		String outputPath) {
+
+		spark
+			.read()
+			.textFile(inputPath)
+			.filter((FilterFunction<String>) s -> isEntityType(s, clazz))
+			.map((MapFunction<String, String>) s -> StringUtils.substringAfter(s, "|"), Encoders.STRING())
+			.map(
+				(MapFunction<String, T>) value -> OBJECT_MAPPER.readValue(value, clazz),
+				Encoders.bean(clazz))
+			.write()
+			.mode(SaveMode.Overwrite)
+			.option("compression", "gzip")
+			.json(outputPath);
+	}
+
+	private static <T extends Oaf> boolean isEntityType(final String s, final Class<T> clazz) {
+		return StringUtils.substringBefore(s, "|").equals(clazz.getName());
+	}
+
+}

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

@@ -2,49 +2,50 @@
 package eu.dnetlib.dhp.oa.merge;
 
 import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
-import static org.apache.spark.sql.functions.col;
-import static org.apache.spark.sql.functions.when;
+import static eu.dnetlib.dhp.utils.DHPUtils.toSeq;
 
-import java.util.Map;
+import java.io.IOException;
+import java.util.List;
+import java.util.Objects;
 import java.util.Optional;
-import java.util.concurrent.ExecutionException;
-import java.util.concurrent.ForkJoinPool;
 import java.util.stream.Collectors;
 
 import org.apache.commons.io.IOUtils;
+import org.apache.commons.lang3.StringUtils;
 import org.apache.spark.SparkConf;
+import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.api.java.function.FilterFunction;
 import org.apache.spark.api.java.function.MapFunction;
-import org.apache.spark.api.java.function.ReduceFunction;
 import org.apache.spark.sql.*;
+import org.apache.spark.sql.expressions.Aggregator;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 
+import com.fasterxml.jackson.databind.DeserializationFeature;
+import com.fasterxml.jackson.databind.ObjectMapper;
+import com.jayway.jsonpath.Configuration;
+import com.jayway.jsonpath.DocumentContext;
+import com.jayway.jsonpath.JsonPath;
+import com.jayway.jsonpath.Option;
+
 import eu.dnetlib.dhp.application.ArgumentApplicationParser;
 import eu.dnetlib.dhp.common.HdfsSupport;
-import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup;
-import eu.dnetlib.dhp.schema.common.EntityType;
 import eu.dnetlib.dhp.schema.common.ModelSupport;
-import eu.dnetlib.dhp.schema.oaf.OafEntity;
-import eu.dnetlib.dhp.schema.oaf.utils.GraphCleaningFunctions;
+import eu.dnetlib.dhp.schema.oaf.*;
 import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
-import eu.dnetlib.dhp.utils.ISLookupClientFactory;
-import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpException;
-import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
 import scala.Tuple2;
 
 /**
  * Groups the graph content by entity identifier to ensure ID uniqueness
  */
 public class GroupEntitiesSparkJob {
+
 	private static final Logger log = LoggerFactory.getLogger(GroupEntitiesSparkJob.class);
 
-	private static final Encoder<OafEntity> OAFENTITY_KRYO_ENC = Encoders.kryo(OafEntity.class);
+	private static final String ID_JPATH = "$.id";
 
-	private ArgumentApplicationParser parser;
-
-	public GroupEntitiesSparkJob(ArgumentApplicationParser parser) {
-		this.parser = parser;
-	}
+	private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper()
+		.configure(DeserializationFeature.FAIL_ON_UNKNOWN_PROPERTIES, false);
 
 	public static void main(String[] args) throws Exception {
 
@@ -62,133 +63,141 @@ public class GroupEntitiesSparkJob {
 			.orElse(Boolean.TRUE);
 		log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
 
-		final String isLookupUrl = parser.get("isLookupUrl");
-		log.info("isLookupUrl: {}", isLookupUrl);
-
-		final ISLookUpService isLookupService = ISLookupClientFactory.getLookUpService(isLookupUrl);
-
-		new GroupEntitiesSparkJob(parser).run(isSparkSessionManaged, isLookupService);
-	}
-
-	public void run(Boolean isSparkSessionManaged, ISLookUpService isLookUpService)
-		throws ISLookUpException {
-
 		String graphInputPath = parser.get("graphInputPath");
 		log.info("graphInputPath: {}", graphInputPath);
 
-		String checkpointPath = parser.get("checkpointPath");
-		log.info("checkpointPath: {}", checkpointPath);
-
 		String outputPath = parser.get("outputPath");
 		log.info("outputPath: {}", outputPath);
 
-		boolean filterInvisible = Boolean.parseBoolean(parser.get("filterInvisible"));
-		log.info("filterInvisible: {}", filterInvisible);
-
 		SparkConf conf = new SparkConf();
 		conf.set("spark.serializer", "org.apache.spark.serializer.KryoSerializer");
 		conf.registerKryoClasses(ModelSupport.getOafModelClasses());
 
-		final VocabularyGroup vocs = VocabularyGroup.loadVocsFromIS(isLookUpService);
-
 		runWithSparkSession(
 			conf,
 			isSparkSessionManaged,
 			spark -> {
-				HdfsSupport.remove(checkpointPath, spark.sparkContext().hadoopConfiguration());
-				groupEntities(spark, graphInputPath, checkpointPath, outputPath, filterInvisible, vocs);
+				HdfsSupport.remove(outputPath, spark.sparkContext().hadoopConfiguration());
+				groupEntities(spark, graphInputPath, outputPath);
 			});
 	}
 
 	private static void groupEntities(
 		SparkSession spark,
 		String inputPath,
-		String checkpointPath,
-		String outputPath,
-		boolean filterInvisible, VocabularyGroup vocs) {
+		String outputPath) {
 
-		Dataset<OafEntity> allEntities = spark.emptyDataset(OAFENTITY_KRYO_ENC);
-
-		for (Map.Entry<EntityType, Class> e : ModelSupport.entityTypes.entrySet()) {
-			String entity = e.getKey().name();
-			Class<? extends OafEntity> entityClass = e.getValue();
-			String entityInputPath = inputPath + "/" + entity;
-
-			if (!HdfsSupport.exists(entityInputPath, spark.sparkContext().hadoopConfiguration())) {
-				continue;
-			}
-
-			allEntities = allEntities
-				.union(
-					((Dataset<OafEntity>) spark
-						.read()
-						.schema(Encoders.bean(entityClass).schema())
-						.json(entityInputPath)
-						.filter("length(id) > 0")
-						.as(Encoders.bean(entityClass)))
-							.map((MapFunction<OafEntity, OafEntity>) r -> r, OAFENTITY_KRYO_ENC));
-		}
-
-		Dataset<?> groupedEntities = allEntities
+		final TypedColumn<OafEntity, OafEntity> aggregator = new GroupingAggregator().toColumn();
+		final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
+		spark
+			.read()
+			.textFile(toSeq(listEntityPaths(inputPath, sc)))
+			.map((MapFunction<String, OafEntity>) GroupEntitiesSparkJob::parseOaf, Encoders.kryo(OafEntity.class))
+			.filter((FilterFunction<OafEntity>) e -> StringUtils.isNotBlank(ModelSupport.idFn().apply(e)))
+			.groupByKey((MapFunction<OafEntity, String>) oaf -> ModelSupport.idFn().apply(oaf), Encoders.STRING())
+			.agg(aggregator)
 			.map(
-				(MapFunction<OafEntity, OafEntity>) entity -> GraphCleaningFunctions
-					.applyCoarVocabularies(entity, vocs),
-				OAFENTITY_KRYO_ENC)
-			.groupByKey((MapFunction<OafEntity, String>) OafEntity::getId, Encoders.STRING())
-			.reduceGroups((ReduceFunction<OafEntity>) OafMapperUtils::mergeEntities)
-			.map(
-				(MapFunction<Tuple2<String, OafEntity>, Tuple2<String, OafEntity>>) t -> new Tuple2<>(
-					t._2().getClass().getName(), t._2()),
-				Encoders.tuple(Encoders.STRING(), OAFENTITY_KRYO_ENC));
-
-		// pivot on "_1" (classname of the entity)
-		// created columns containing only entities of the same class
-		for (Map.Entry<EntityType, Class> e : ModelSupport.entityTypes.entrySet()) {
-			String entity = e.getKey().name();
-			Class<? extends OafEntity> entityClass = e.getValue();
-
-			groupedEntities = groupedEntities
-				.withColumn(
-					entity,
-					when(col("_1").equalTo(entityClass.getName()), col("_2")));
-		}
-
-		groupedEntities
-			.drop("_1", "_2")
+				(MapFunction<Tuple2<String, OafEntity>, String>) t -> t._2().getClass().getName() +
+					"|" + OBJECT_MAPPER.writeValueAsString(t._2()),
+				Encoders.STRING())
 			.write()
-			.mode(SaveMode.Overwrite)
 			.option("compression", "gzip")
-			.save(checkpointPath);
-
-		ForkJoinPool parPool = new ForkJoinPool(ModelSupport.entityTypes.size());
-
-		ModelSupport.entityTypes
-			.entrySet()
-			.stream()
-			.map(e -> parPool.submit(() -> {
-				String entity = e.getKey().name();
-				Class<? extends OafEntity> entityClass = e.getValue();
-
-				spark
-					.read()
-					.load(checkpointPath)
-					.select(col(entity).as("value"))
-					.filter("value IS NOT NULL")
-					.as(OAFENTITY_KRYO_ENC)
-					.map((MapFunction<OafEntity, OafEntity>) r -> r, (Encoder<OafEntity>) Encoders.bean(entityClass))
-					.filter(filterInvisible ? "dataInfo.invisible != TRUE" : "TRUE")
-					.write()
-					.mode(SaveMode.Overwrite)
-					.option("compression", "gzip")
-					.json(outputPath + "/" + entity);
-			}))
-			.collect(Collectors.toList())
-			.forEach(t -> {
-				try {
-					t.get();
-				} catch (InterruptedException | ExecutionException e) {
-					throw new RuntimeException(e);
-				}
-			});
+			.mode(SaveMode.Overwrite)
+			.text(outputPath);
 	}
+
+	public static class GroupingAggregator extends Aggregator<OafEntity, OafEntity, OafEntity> {
+
+		@Override
+		public OafEntity zero() {
+			return null;
+		}
+
+		@Override
+		public OafEntity reduce(OafEntity b, OafEntity a) {
+			return mergeAndGet(b, a);
+		}
+
+		private OafEntity mergeAndGet(OafEntity b, OafEntity a) {
+			if (Objects.nonNull(a) && Objects.nonNull(b)) {
+				return OafMapperUtils.mergeEntities(b, a);
+			}
+			return Objects.isNull(a) ? b : a;
+		}
+
+		@Override
+		public OafEntity merge(OafEntity b, OafEntity a) {
+			return mergeAndGet(b, a);
+		}
+
+		@Override
+		public OafEntity finish(OafEntity j) {
+			return j;
+		}
+
+		@Override
+		public Encoder<OafEntity> bufferEncoder() {
+			return Encoders.kryo(OafEntity.class);
+		}
+
+		@Override
+		public Encoder<OafEntity> outputEncoder() {
+			return Encoders.kryo(OafEntity.class);
+		}
+
+	}
+
+	private static OafEntity parseOaf(String s) {
+
+		DocumentContext dc = JsonPath
+			.parse(s, Configuration.defaultConfiguration().addOptions(Option.SUPPRESS_EXCEPTIONS));
+		final String id = dc.read(ID_JPATH);
+		if (StringUtils.isNotBlank(id)) {
+
+			String prefix = StringUtils.substringBefore(id, "|");
+			switch (prefix) {
+				case "10":
+					return parse(s, Datasource.class);
+				case "20":
+					return parse(s, Organization.class);
+				case "40":
+					return parse(s, Project.class);
+				case "50":
+					String resultType = dc.read("$.resulttype.classid");
+					switch (resultType) {
+						case "publication":
+							return parse(s, Publication.class);
+						case "dataset":
+							return parse(s, eu.dnetlib.dhp.schema.oaf.Dataset.class);
+						case "software":
+							return parse(s, Software.class);
+						case "other":
+							return parse(s, OtherResearchProduct.class);
+						default:
+							throw new IllegalArgumentException(String.format("invalid resultType: '%s'", resultType));
+					}
+				default:
+					throw new IllegalArgumentException(String.format("invalid id prefix: '%s'", prefix));
+			}
+		} else {
+			throw new IllegalArgumentException(String.format("invalid oaf: '%s'", s));
+		}
+	}
+
+	private static <T extends OafEntity> OafEntity parse(String s, Class<T> clazz) {
+		try {
+			return OBJECT_MAPPER.readValue(s, clazz);
+		} catch (IOException e) {
+			throw new IllegalArgumentException(e);
+		}
+	}
+
+	private static List<String> listEntityPaths(String inputPath, JavaSparkContext sc) {
+		return HdfsSupport
+			.listFiles(inputPath, sc.hadoopConfiguration())
+			.stream()
+			.filter(f -> !f.toLowerCase().contains("relation"))
+			.collect(Collectors.toList());
+	}
+
 }

dhp-common/src/main/java/eu/dnetlib/dhp/oozie/RunSQLSparkJob.java

@@ -1,77 +0,0 @@
-
-package eu.dnetlib.dhp.oozie;
-
-import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkHiveSession;
-
-import java.net.URL;
-import java.nio.charset.StandardCharsets;
-import java.util.HashMap;
-import java.util.Map;
-import java.util.Optional;
-
-import org.apache.commons.lang3.time.DurationFormatUtils;
-import org.apache.commons.text.StringSubstitutor;
-import org.apache.spark.SparkConf;
-import org.slf4j.Logger;
-import org.slf4j.LoggerFactory;
-
-import com.google.common.io.Resources;
-
-import eu.dnetlib.dhp.application.ArgumentApplicationParser;
-
-public class RunSQLSparkJob {
-	private static final Logger log = LoggerFactory.getLogger(RunSQLSparkJob.class);
-
-	private final ArgumentApplicationParser parser;
-
-	public RunSQLSparkJob(ArgumentApplicationParser parser) {
-		this.parser = parser;
-	}
-
-	public static void main(String[] args) throws Exception {
-
-		Map<String, String> params = new HashMap<>();
-		for (int i = 0; i < args.length - 1; i++) {
-			if (args[i].startsWith("--")) {
-				params.put(args[i].substring(2), args[++i]);
-			}
-		}
-
-		/*
-		 * String jsonConfiguration = IOUtils .toString( Objects .requireNonNull( RunSQLSparkJob.class
-		 * .getResourceAsStream( "/eu/dnetlib/dhp/oozie/run_sql_parameters.json"))); final ArgumentApplicationParser
-		 * parser = new ArgumentApplicationParser(jsonConfiguration); parser.parseArgument(args);
-		 */
-
-		Boolean isSparkSessionManaged = Optional
-			.ofNullable(params.get("isSparkSessionManaged"))
-			.map(Boolean::valueOf)
-			.orElse(Boolean.TRUE);
-		log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
-
-		URL url = com.google.common.io.Resources.getResource(params.get("sql"));
-		String raw_sql = Resources.toString(url, StandardCharsets.UTF_8);
-
-		String sql = StringSubstitutor.replace(raw_sql, params);
-		log.info("sql: {}", sql);
-
-		SparkConf conf = new SparkConf();
-		conf.set("hive.metastore.uris", params.get("hiveMetastoreUris"));
-
-		runWithSparkHiveSession(
-			conf,
-			isSparkSessionManaged,
-			spark -> {
-				for (String statement : sql.split(";\\s*/\\*\\s*EOS\\s*\\*/\\s*")) {
-					log.info("executing: {}", statement);
-					long startTime = System.currentTimeMillis();
-					spark.sql(statement).show();
-					log
-						.info(
-							"executed in {}",
-							DurationFormatUtils.formatDuration(System.currentTimeMillis() - startTime, "HH:mm:ss.S"));
-				}
-			});
-	}
-
-}

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

@@ -6,16 +6,14 @@ import java.util.regex.Pattern;
 
 public class FundRefCleaningRule {
 
-	public static final Pattern PATTERN = Pattern.compile("\\d+");
+	public static String clean(final String fundrefId) {
 
-	public static String clean(final String fundRefId) {
-
-		String s = fundRefId
+		String s = fundrefId
 			.toLowerCase()
 			.replaceAll("\\s", "");
 
-		Matcher m = PATTERN.matcher(s);
-		if (m.find()) {
+		Matcher m = Pattern.compile("\\d+").matcher(s);
+		if (m.matches()) {
 			return m.group();
 		} else {
 			return "";

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

@@ -1,12 +1,8 @@
 
 package eu.dnetlib.dhp.schema.oaf.utils;
 
-import static eu.dnetlib.dhp.schema.common.ModelConstants.*;
-import static eu.dnetlib.dhp.schema.common.ModelConstants.OPENAIRE_META_RESOURCE_TYPE;
 import static eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils.getProvenance;
 
-import java.net.MalformedURLException;
-import java.net.URL;
 import java.time.LocalDate;
 import java.time.ZoneId;
 import java.time.format.DateTimeFormatter;
@@ -17,13 +13,16 @@ import java.util.stream.Collectors;
 import java.util.stream.Stream;
 
 import org.apache.commons.lang3.StringUtils;
+import org.apache.spark.api.java.function.MapFunction;
+import org.apache.spark.sql.Encoders;
 
+import com.fasterxml.jackson.core.JsonProcessingException;
+import com.fasterxml.jackson.databind.ObjectMapper;
 import com.github.sisyphsu.dateparser.DateParserUtils;
 import com.google.common.collect.Lists;
 import com.google.common.collect.Sets;
 
 import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup;
-import eu.dnetlib.dhp.common.vocabulary.VocabularyTerm;
 import eu.dnetlib.dhp.schema.common.ModelConstants;
 import eu.dnetlib.dhp.schema.common.ModelSupport;
 import eu.dnetlib.dhp.schema.oaf.*;
@@ -31,10 +30,6 @@ import me.xuender.unidecode.Unidecode;
 
 public class GraphCleaningFunctions extends CleaningFunctions {
 
-	public static final String DNET_PUBLISHERS = "dnet:publishers";
-
-	public static final String DNET_LICENSES = "dnet:licenses";
-
 	public static final String ORCID_CLEANING_REGEX = ".*([0-9]{4}).*[-–—−=].*([0-9]{4}).*[-–—−=].*([0-9]{4}).*[-–—−=].*([0-9x]{4})";
 	public static final int ORCID_LEN = 19;
 	public static final String CLEANING_REGEX = "(?:\\n|\\r|\\t)";
@@ -44,68 +39,6 @@ public class GraphCleaningFunctions extends CleaningFunctions {
 	public static final String TITLE_FILTER_REGEX = String.format("(%s)|\\W|\\d", TITLE_TEST);
 
 	public static final int TITLE_FILTER_RESIDUAL_LENGTH = 5;
-	private static final String NAME_CLEANING_REGEX = "[\\r\\n\\t\\s]+";
-
-	private static final Set<String> INVALID_AUTHOR_NAMES = new HashSet<>();
-
-	private static final Set<String> INVALID_URLS = new HashSet<>();
-
-	private static final Set<String> INVALID_URL_HOSTS = new HashSet<>();
-
-	private static final HashSet<String> PEER_REVIEWED_TYPES = new HashSet<>();
-
-	static {
-		PEER_REVIEWED_TYPES.add("Article");
-		PEER_REVIEWED_TYPES.add("Part of book or chapter of book");
-		PEER_REVIEWED_TYPES.add("Book");
-		PEER_REVIEWED_TYPES.add("Doctoral thesis");
-		PEER_REVIEWED_TYPES.add("Master thesis");
-		PEER_REVIEWED_TYPES.add("Data Paper");
-		PEER_REVIEWED_TYPES.add("Thesis");
-		PEER_REVIEWED_TYPES.add("Bachelor thesis");
-		PEER_REVIEWED_TYPES.add("Conference object");
-
-		INVALID_AUTHOR_NAMES.add("(:null)");
-		INVALID_AUTHOR_NAMES.add("(:unap)");
-		INVALID_AUTHOR_NAMES.add("(:tba)");
-		INVALID_AUTHOR_NAMES.add("(:unas)");
-		INVALID_AUTHOR_NAMES.add("(:unav)");
-		INVALID_AUTHOR_NAMES.add("(:unkn)");
-		INVALID_AUTHOR_NAMES.add("(:unkn) unknown");
-		INVALID_AUTHOR_NAMES.add(":none");
-		INVALID_AUTHOR_NAMES.add(":null");
-		INVALID_AUTHOR_NAMES.add(":unas");
-		INVALID_AUTHOR_NAMES.add(":unav");
-		INVALID_AUTHOR_NAMES.add(":unkn");
-		INVALID_AUTHOR_NAMES.add("[autor desconocido]");
-		INVALID_AUTHOR_NAMES.add("[s. n.]");
-		INVALID_AUTHOR_NAMES.add("[s.n]");
-		INVALID_AUTHOR_NAMES.add("[unknown]");
-		INVALID_AUTHOR_NAMES.add("anonymous");
-		INVALID_AUTHOR_NAMES.add("n.n.");
-		INVALID_AUTHOR_NAMES.add("nn");
-		INVALID_AUTHOR_NAMES.add("no name supplied");
-		INVALID_AUTHOR_NAMES.add("none");
-		INVALID_AUTHOR_NAMES.add("none available");
-		INVALID_AUTHOR_NAMES.add("not available not available");
-		INVALID_AUTHOR_NAMES.add("null &na;");
-		INVALID_AUTHOR_NAMES.add("null anonymous");
-		INVALID_AUTHOR_NAMES.add("unbekannt");
-		INVALID_AUTHOR_NAMES.add("unknown");
-
-		INVALID_URL_HOSTS.add("creativecommons.org");
-		INVALID_URL_HOSTS.add("www.academia.edu");
-		INVALID_URL_HOSTS.add("academia.edu");
-		INVALID_URL_HOSTS.add("researchgate.net");
-		INVALID_URL_HOSTS.add("www.researchgate.net");
-
-		INVALID_URLS.add("http://repo.scoap3.org/api");
-		INVALID_URLS.add("http://ora.ox.ac.uk/objects/uuid:");
-		INVALID_URLS.add("http://ntur.lib.ntu.edu.tw/news/agent_contract.pdf");
-		INVALID_URLS.add("https://media.springer.com/full/springer-instructions-for-authors-assets/pdf/SN_BPF_EN.pdf");
-		INVALID_URLS.add("http://www.tobaccoinduceddiseases.org/dl/61aad426c96519bea4040a374c6a6110/");
-		INVALID_URLS.add("https://www.bilboard.nl/verenigingsbladen/bestuurskundige-berichten");
-	}
 
 	public static <T extends Oaf> T cleanContext(T value, String contextId, String verifyParam) {
 		if (ModelSupport.isSubClass(value, Result.class)) {
@@ -295,7 +228,7 @@ public class GraphCleaningFunctions extends CleaningFunctions {
 	}
 
 	public static <T extends Oaf> boolean filter(T value) {
-		if (!(value instanceof Relation) && (Boolean.TRUE
+		if (Boolean.TRUE
 			.equals(
 				Optional
 					.ofNullable(value)
@@ -306,17 +239,15 @@ public class GraphCleaningFunctions extends CleaningFunctions {
 								d -> Optional
 									.ofNullable(d.getInvisible())
 									.orElse(true))
-							.orElse(false))
-					.orElse(true)))) {
+							.orElse(true))
+					.orElse(true))) {
 			return true;
 		}
 
 		if (value instanceof Datasource) {
-			final Datasource d = (Datasource) value;
-			return Objects.nonNull(d.getOfficialname()) && StringUtils.isNotBlank(d.getOfficialname().getValue());
+			// nothing to evaluate here
 		} else if (value instanceof Project) {
-			final Project p = (Project) value;
-			return Objects.nonNull(p.getCode()) && StringUtils.isNotBlank(p.getCode().getValue());
+			// nothing to evaluate here
 		} else if (value instanceof Organization) {
 			// nothing to evaluate here
 		} else if (value instanceof Relation) {
@@ -344,12 +275,6 @@ public class GraphCleaningFunctions extends CleaningFunctions {
 
 	public static <T extends Oaf> T cleanup(T value, VocabularyGroup vocs) {
 
-		if (Objects.isNull(value.getDataInfo())) {
-			final DataInfo d = new DataInfo();
-			d.setDeletedbyinference(false);
-			value.setDataInfo(d);
-		}
-
 		if (value instanceof OafEntity) {
 
 			OafEntity e = (OafEntity) value;
@@ -369,17 +294,6 @@ public class GraphCleaningFunctions extends CleaningFunctions {
 			} else if (value instanceof Result) {
 				Result r = (Result) value;
 
-				if (Objects.isNull(r.getContext())) {
-					r.setContext(new ArrayList<>());
-				}
-
-				if (Objects.nonNull(r.getFulltext())
-					&& (ModelConstants.SOFTWARE_RESULTTYPE_CLASSID.equals(r.getResulttype().getClassid()) ||
-						ModelConstants.DATASET_RESULTTYPE_CLASSID.equals(r.getResulttype().getClassid()))) {
-					r.setFulltext(null);
-
-				}
-
 				if (Objects.nonNull(r.getDateofacceptance())) {
 					Optional<String> date = cleanDateField(r.getDateofacceptance());
 					if (date.isPresent()) {
@@ -404,26 +318,8 @@ public class GraphCleaningFunctions extends CleaningFunctions {
 								.filter(sp -> StringUtils.isNotBlank(sp.getValue()))
 								.collect(Collectors.toList()));
 				}
-				if (Objects.nonNull(r.getPublisher())) {
-					if (StringUtils.isBlank(r.getPublisher().getValue())) {
-						r.setPublisher(null);
-					} else {
-						r
-							.getPublisher()
-							.setValue(
-								r
-									.getPublisher()
-									.getValue()
-									.replaceAll(NAME_CLEANING_REGEX, " "));
-
-						if (vocs.vocabularyExists(DNET_PUBLISHERS)) {
-							vocs
-								.find(DNET_PUBLISHERS)
-								.map(voc -> voc.getTermBySynonym(r.getPublisher().getValue()))
-								.map(VocabularyTerm::getName)
-								.ifPresent(publisher -> r.getPublisher().setValue(publisher));
-						}
-					}
+				if (Objects.nonNull(r.getPublisher()) && StringUtils.isBlank(r.getPublisher().getValue())) {
+					r.setPublisher(null);
 				}
 				if (Objects.isNull(r.getLanguage()) || StringUtils.isBlank(r.getLanguage().getClassid())) {
 					r
@@ -582,43 +478,6 @@ public class GraphCleaningFunctions extends CleaningFunctions {
 						if (Objects.isNull(i.getRefereed()) || StringUtils.isBlank(i.getRefereed().getClassid())) {
 							i.setRefereed(qualifier("0000", "Unknown", ModelConstants.DNET_REVIEW_LEVELS));
 						}
-
-						if (Objects.nonNull(i.getLicense()) && Objects.nonNull(i.getLicense().getValue())) {
-							vocs
-								.find(DNET_LICENSES)
-								.map(voc -> voc.getTermBySynonym(i.getLicense().getValue()))
-								.map(VocabularyTerm::getId)
-								.ifPresent(license -> i.getLicense().setValue(license));
-						}
-
-						// from the script from Dimitris
-						if ("0000".equals(i.getRefereed().getClassid())) {
-							final boolean isFromCrossref = Optional
-								.ofNullable(i.getCollectedfrom())
-								.map(KeyValue::getKey)
-								.map(id -> id.equals(ModelConstants.CROSSREF_ID))
-								.orElse(false);
-							final boolean hasDoi = Optional
-								.ofNullable(i.getPid())
-								.map(
-									pid -> pid
-										.stream()
-										.anyMatch(
-											p -> PidType.doi.toString().equals(p.getQualifier().getClassid())))
-								.orElse(false);
-							final boolean isPeerReviewedType = PEER_REVIEWED_TYPES
-								.contains(i.getInstancetype().getClassname());
-							final boolean noOtherLitType = r
-								.getInstance()
-								.stream()
-								.noneMatch(ii -> "Other literature type".equals(ii.getInstancetype().getClassname()));
-							if (isFromCrossref && hasDoi && isPeerReviewedType && noOtherLitType) {
-								i.setRefereed(qualifier("0001", "peerReviewed", ModelConstants.DNET_REVIEW_LEVELS));
-							} else {
-								i.setRefereed(qualifier("0002", "nonPeerReviewed", ModelConstants.DNET_REVIEW_LEVELS));
-							}
-						}
-
 						if (Objects.nonNull(i.getDateofacceptance())) {
 							Optional<String> date = cleanDateField(i.getDateofacceptance());
 							if (date.isPresent()) {
@@ -627,20 +486,6 @@ public class GraphCleaningFunctions extends CleaningFunctions {
 								i.setDateofacceptance(null);
 							}
 						}
-						if (StringUtils.isNotBlank(i.getFulltext()) &&
-							(ModelConstants.SOFTWARE_RESULTTYPE_CLASSID.equals(r.getResulttype().getClassid()) ||
-								ModelConstants.DATASET_RESULTTYPE_CLASSID.equals(r.getResulttype().getClassid()))) {
-							i.setFulltext(null);
-						}
-						if (Objects.nonNull(i.getUrl())) {
-							i
-								.setUrl(
-									i
-										.getUrl()
-										.stream()
-										.filter(GraphCleaningFunctions::urlFilter)
-										.collect(Collectors.toList()));
-						}
 					}
 				}
 				if (Objects.isNull(r.getBestaccessright())
@@ -663,8 +508,8 @@ public class GraphCleaningFunctions extends CleaningFunctions {
 								.getAuthor()
 								.stream()
 								.filter(Objects::nonNull)
-								.filter(GraphCleaningFunctions::isValidAuthorName)
-								.map(GraphCleaningFunctions::cleanupAuthor)
+								.filter(a -> StringUtils.isNotBlank(a.getFullname()))
+								.filter(a -> StringUtils.isNotBlank(a.getFullname().replaceAll("[\\W]", "")))
 								.collect(Collectors.toList()));
 
 					boolean nullRank = r
@@ -690,9 +535,6 @@ public class GraphCleaningFunctions extends CleaningFunctions {
 										.filter(Objects::nonNull)
 										.filter(p -> Objects.nonNull(p.getQualifier()))
 										.filter(p -> StringUtils.isNotBlank(p.getValue()))
-										.filter(
-											p -> StringUtils
-												.contains(StringUtils.lowerCase(p.getQualifier().getClassid()), ORCID))
 										.map(p -> {
 											// hack to distinguish orcid from orcid_pending
 											String pidProvenance = getProvenance(p.getDataInfo());
@@ -702,8 +544,7 @@ public class GraphCleaningFunctions extends CleaningFunctions {
 												.toLowerCase()
 												.contains(ModelConstants.ORCID)) {
 												if (pidProvenance
-													.equals(ModelConstants.SYSIMPORT_CROSSWALK_ENTITYREGISTRY) ||
-													pidProvenance.equals("ORCID_ENRICHMENT")) {
+													.equals(ModelConstants.SYSIMPORT_CROSSWALK_ENTITYREGISTRY)) {
 													p.getQualifier().setClassid(ModelConstants.ORCID);
 												} else {
 													p.getQualifier().setClassid(ModelConstants.ORCID_PENDING);
@@ -763,35 +604,6 @@ public class GraphCleaningFunctions extends CleaningFunctions {
 		return value;
 	}
 
-	private static Author cleanupAuthor(Author author) {
-		if (StringUtils.isNotBlank(author.getFullname())) {
-			author
-				.setFullname(
-					author
-						.getFullname()
-						.replaceAll(NAME_CLEANING_REGEX, " ")
-						.replace("\"", "\\\""));
-		}
-		if (StringUtils.isNotBlank(author.getName())) {
-			author
-				.setName(
-					author
-						.getName()
-						.replaceAll(NAME_CLEANING_REGEX, " ")
-						.replace("\"", "\\\""));
-		}
-		if (StringUtils.isNotBlank(author.getSurname())) {
-			author
-				.setSurname(
-					author
-						.getSurname()
-						.replaceAll(NAME_CLEANING_REGEX, " ")
-						.replace("\"", "\\\""));
-		}
-
-		return author;
-	}
-
 	private static Optional<String> cleanDateField(Field<String> dateofacceptance) {
 		return Optional
 			.ofNullable(dateofacceptance)
@@ -825,30 +637,12 @@ public class GraphCleaningFunctions extends CleaningFunctions {
 	// HELPERS
 
 	private static boolean isValidAuthorName(Author a) {
-		return StringUtils.isNotBlank(a.getFullname()) &&
-			StringUtils.isNotBlank(a.getFullname().replaceAll("[\\W]", "")) &&
-			!INVALID_AUTHOR_NAMES.contains(StringUtils.lowerCase(a.getFullname()).trim()) &&
-			!Stream
-				.of(a.getFullname(), a.getName(), a.getSurname())
-				.filter(StringUtils::isNotBlank)
-				.collect(Collectors.joining(""))
-				.toLowerCase()
-				.matches(INVALID_AUTHOR_REGEX);
-	}
-
-	private static boolean urlFilter(String u) {
-		try {
-			final URL url = new URL(u);
-			if (StringUtils.isBlank(url.getPath()) || "/".equals(url.getPath())) {
-				return false;
-			}
-			if (INVALID_URL_HOSTS.contains(url.getHost())) {
-				return false;
-			}
-			return !INVALID_URLS.contains(url.toString());
-		} catch (MalformedURLException ex) {
-			return false;
-		}
+		return !Stream
+			.of(a.getFullname(), a.getName(), a.getSurname())
+			.filter(s -> s != null && !s.isEmpty())
+			.collect(Collectors.joining(""))
+			.toLowerCase()
+			.matches(INVALID_AUTHOR_REGEX);
 	}
 
 	private static List<StructuredProperty> processPidCleaning(List<StructuredProperty> pids) {
@@ -898,105 +692,4 @@ public class GraphCleaningFunctions extends CleaningFunctions {
 		return s;
 	}
 
-	public static OafEntity applyCoarVocabularies(OafEntity entity, VocabularyGroup vocs) {
-
-		if (entity instanceof Result) {
-			final Result result = (Result) entity;
-
-			Optional
-				.ofNullable(result.getInstance())
-				.ifPresent(
-					instances -> instances
-						.forEach(
-							instance -> {
-								if (Objects.isNull(instance.getInstanceTypeMapping())) {
-									List<InstanceTypeMapping> mapping = Lists.newArrayList();
-									mapping
-										.add(
-											OafMapperUtils
-												.instanceTypeMapping(
-													instance.getInstancetype().getClassname(),
-													OPENAIRE_COAR_RESOURCE_TYPES_3_1));
-									instance.setInstanceTypeMapping(mapping);
-								}
-								Optional<InstanceTypeMapping> optionalItm = instance
-									.getInstanceTypeMapping()
-									.stream()
-									.filter(GraphCleaningFunctions::originalResourceType)
-									.findFirst();
-								if (optionalItm.isPresent()) {
-									InstanceTypeMapping coarItm = optionalItm.get();
-									Optional
-										.ofNullable(
-											vocs
-												.lookupTermBySynonym(
-													OPENAIRE_COAR_RESOURCE_TYPES_3_1, coarItm.getOriginalType()))
-										.ifPresent(type -> {
-											coarItm.setTypeCode(type.getClassid());
-											coarItm.setTypeLabel(type.getClassname());
-										});
-									final List<InstanceTypeMapping> mappings = Lists.newArrayList();
-									if (vocs.vocabularyExists(OPENAIRE_USER_RESOURCE_TYPES)) {
-										Optional
-											.ofNullable(
-												vocs
-													.lookupTermBySynonym(
-														OPENAIRE_USER_RESOURCE_TYPES, coarItm.getTypeCode()))
-											.ifPresent(
-												type -> mappings
-													.add(
-														OafMapperUtils
-															.instanceTypeMapping(coarItm.getTypeCode(), type)));
-									}
-									if (!mappings.isEmpty()) {
-										instance.getInstanceTypeMapping().addAll(mappings);
-									}
-								}
-							}));
-			result.setMetaResourceType(getMetaResourceType(result.getInstance(), vocs));
-		}
-
-		return entity;
-	}
-
-	private static boolean originalResourceType(InstanceTypeMapping itm) {
-		return StringUtils.isNotBlank(itm.getOriginalType()) &&
-			OPENAIRE_COAR_RESOURCE_TYPES_3_1.equals(itm.getVocabularyName()) &&
-			StringUtils.isBlank(itm.getTypeCode()) &&
-			StringUtils.isBlank(itm.getTypeLabel());
-	}
-
-	private static Qualifier getMetaResourceType(final List<Instance> instances, final VocabularyGroup vocs) {
-		return Optional
-			.ofNullable(instances)
-			.map(ii -> {
-				if (vocs.vocabularyExists(OPENAIRE_META_RESOURCE_TYPE)) {
-					Optional<InstanceTypeMapping> itm = ii
-						.stream()
-						.filter(Objects::nonNull)
-						.flatMap(
-							i -> Optional
-								.ofNullable(i.getInstanceTypeMapping())
-								.map(Collection::stream)
-								.orElse(Stream.empty()))
-						.filter(t -> OPENAIRE_COAR_RESOURCE_TYPES_3_1.equals(t.getVocabularyName()))
-						.findFirst();
-
-					if (!itm.isPresent() || Objects.isNull(itm.get().getTypeCode())) {
-						return null;
-					} else {
-						final String typeCode = itm.get().getTypeCode();
-						return Optional
-							.ofNullable(vocs.lookupTermBySynonym(OPENAIRE_META_RESOURCE_TYPE, typeCode))
-							.orElseThrow(
-								() -> new IllegalStateException("unable to find a synonym for '" + typeCode + "' in " +
-									OPENAIRE_META_RESOURCE_TYPE));
-					}
-				} else {
-					throw new IllegalStateException("vocabulary '" + OPENAIRE_META_RESOURCE_TYPE + "' not available");
-				}
-			})
-			.orElse(null);
-	}
-
 }

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

@@ -6,19 +6,13 @@ import java.util.regex.Pattern;
 
 public class GridCleaningRule {
 
-	public static final Pattern PATTERN = Pattern.compile("(?<grid>\\d{4,6}\\.[0-9a-z]{1,2})");
-
 	public static String clean(String grid) {
 		String s = grid
 			.replaceAll("\\s", "")
 			.toLowerCase();
 
-		Matcher m = PATTERN.matcher(s);
-		if (m.find()) {
-			return "grid." + m.group("grid");
-		}
-
-		return "";
+		Matcher m = Pattern.compile("\\d{4,6}\\.[0-9a-z]{1,2}").matcher(s);
+		return m.matches() ? "grid." + m.group() : "";
 	}
 
 }

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

@@ -7,12 +7,10 @@ import java.util.regex.Pattern;
 // https://www.wikidata.org/wiki/Property:P213
 public class ISNICleaningRule {
 
-	public static final Pattern PATTERN = Pattern.compile("([0]{4}) ?([0-9]{4}) ?([0-9]{4}) ?([0-9]{3}[0-9X])");
-
 	public static String clean(final String isni) {
 
-		Matcher m = PATTERN.matcher(isni);
-		if (m.find()) {
+		Matcher m = Pattern.compile("([0]{4}) ?([0-9]{4}) ?([0-9]{4}) ?([0-9]{3}[0-9X])").matcher(isni);
+		if (m.matches()) {
 			return String.join("", m.group(1), m.group(2), m.group(3), m.group(4));
 		} else {
 			return "";

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

@@ -14,6 +14,7 @@ import java.util.stream.Collectors;
 import org.apache.commons.lang3.StringUtils;
 
 import eu.dnetlib.dhp.schema.common.AccessRightComparator;
+import eu.dnetlib.dhp.schema.common.ModelConstants;
 import eu.dnetlib.dhp.schema.common.ModelSupport;
 import eu.dnetlib.dhp.schema.oaf.*;
 
@@ -140,28 +141,6 @@ public class OafMapperUtils {
 			.collect(Collectors.toList());
 	}
 
-	public static InstanceTypeMapping instanceTypeMapping(String originalType, String code, String label,
-		String vocabularyName) {
-		final InstanceTypeMapping m = new InstanceTypeMapping();
-		m.setVocabularyName(vocabularyName);
-		m.setOriginalType(originalType);
-		m.setTypeCode(code);
-		m.setTypeLabel(label);
-		return m;
-	}
-
-	public static InstanceTypeMapping instanceTypeMapping(String originalType, Qualifier term) {
-		return instanceTypeMapping(originalType, term.getClassid(), term.getClassname(), term.getSchemeid());
-	}
-
-	public static InstanceTypeMapping instanceTypeMapping(String originalType) {
-		return instanceTypeMapping(originalType, null, null, null);
-	}
-
-	public static InstanceTypeMapping instanceTypeMapping(String originalType, String vocabularyName) {
-		return instanceTypeMapping(originalType, null, null, vocabularyName);
-	}
-
 	public static Qualifier unknown(final String schemeid, final String schemename) {
 		return qualifier(UNKNOWN, "Unknown", schemeid, schemename);
 	}

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

@@ -6,12 +6,10 @@ import java.util.regex.Pattern;
 
 public class PICCleaningRule {
 
-	public static final Pattern PATTERN = Pattern.compile("\\d{9}");
-
 	public static String clean(final String pic) {
 
-		Matcher m = PATTERN.matcher(pic);
-		if (m.find()) {
+		Matcher m = Pattern.compile("\\d{9}").matcher(pic);
+		if (m.matches()) {
 			return m.group();
 		} else {
 			return "";

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

@@ -1,24 +1,13 @@
 
 package eu.dnetlib.dhp.schema.oaf.utils;
 
-import java.util.regex.Matcher;
-import java.util.regex.Pattern;
-
 public class PmcCleaningRule {
 
-	public static final Pattern PATTERN = Pattern.compile("PMC\\d{1,8}");
-
 	public static String clean(String pmc) {
 		String s = pmc
 			.replaceAll("\\s", "")
 			.toUpperCase();
-
-		final Matcher m = PATTERN.matcher(s);
-
-		if (m.find()) {
-			return m.group();
-		}
-		return "";
+		return s.matches("^PMC\\d{1,8}$") ? s : "";
 	}
 
 }

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

@@ -1,25 +1,16 @@
 
 package eu.dnetlib.dhp.schema.oaf.utils;
 
-import java.util.regex.Matcher;
-import java.util.regex.Pattern;
-
 // https://researchguides.stevens.edu/c.php?g=442331&p=6577176
 public class PmidCleaningRule {
 
-	public static final Pattern PATTERN = Pattern.compile("0*(\\d{1,8})");
-
 	public static String clean(String pmid) {
 		String s = pmid
 			.toLowerCase()
-			.replaceAll("\\s", "");
-
-		final Matcher m = PATTERN.matcher(s);
-
-		if (m.find()) {
-			return m.group(1);
-		}
-		return "";
+			.replaceAll("\\s", "")
+			.trim()
+			.replaceAll("^0+", "");
+		return s.matches("^\\d{1,8}$") ? s : "";
 	}
 
 }

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

@@ -7,21 +7,12 @@ import java.util.regex.Pattern;
 // https://ror.readme.io/docs/ror-identifier-pattern
 public class RorCleaningRule {
 
-	public static final String ROR_PREFIX = "https://ror.org/";
-
-	private static final Pattern PATTERN = Pattern.compile("(?<ror>0[a-hj-km-np-tv-z|0-9]{6}[0-9]{2})");
-
 	public static String clean(String ror) {
 		String s = ror
 			.replaceAll("\\s", "")
 			.toLowerCase();
-
-		Matcher m = PATTERN.matcher(s);
-
-		if (m.find()) {
-			return ROR_PREFIX + m.group("ror");
-		}
-		return "";
+		Matcher m = Pattern.compile("0[a-hj-km-np-tv-z|0-9]{6}[0-9]{2}").matcher(s);
+		return m.matches() ? "https://ror.org/" + m.group() : "";
 	}
 
 }

dhp-common/src/main/resources/eu/dnetlib/dhp/oa/merge/dispatch_entities_parameters.json

@@ -6,21 +6,21 @@
     "paramRequired": false
   },
   {
-    "paramName": "cip",
-    "paramLongName": "crossrefInputPath",
-    "paramDescription": "the path to get the input data from Crossref",
-    "paramRequired": true
-  },
-  {
-    "paramName": "pip",
-    "paramLongName": "pubmedInputPath",
-    "paramDescription": "the path to get the input data from Pubmed",
+    "paramName": "i",
+    "paramLongName": "inputPath",
+    "paramDescription": "the source path",
     "paramRequired": true
   },
   {
     "paramName": "o",
     "paramLongName": "outputPath",
-    "paramDescription": "the path of the new ActionSet",
+    "paramDescription": "path of the output graph",
+    "paramRequired": true
+  },
+  {
+    "paramName": "c",
+    "paramLongName": "graphTableClassName",
+    "paramDescription": "the graph entity class name",
     "paramRequired": true
   }
 ]

dhp-common/src/main/resources/eu/dnetlib/dhp/oa/merge/group_graph_entities_parameters.json

@@ -8,31 +8,13 @@
   {
     "paramName": "gin",
     "paramLongName": "graphInputPath",
-    "paramDescription": "the input graph root path",
-    "paramRequired": true
-  },
-  {
-    "paramName": "cp",
-    "paramLongName": "checkpointPath",
-    "paramDescription": "checkpoint directory",
+    "paramDescription": "the graph root path",
     "paramRequired": true
   },
   {
     "paramName": "out",
     "paramLongName": "outputPath",
-    "paramDescription": "the output graph root path",
-    "paramRequired": true
-  },
-  {
-    "paramName": "fi",
-    "paramLongName": "filterInvisible",
-    "paramDescription": "if true filters out invisible entities",
-    "paramRequired": true
-  },
-  {
-    "paramName": "isu",
-    "paramLongName": "isLookupUrl",
-    "paramDescription": "url to the ISLookup Service",
+    "paramDescription": "the output merged graph root path",
     "paramRequired": true
   }
 ]

dhp-common/src/main/resources/eu/dnetlib/dhp/oozie/run_sql_parameters.json

@@ -1,20 +0,0 @@
-[
-  {
-    "paramName": "issm",
-    "paramLongName": "isSparkSessionManaged",
-    "paramDescription": "when true will stop SparkSession after job execution",
-    "paramRequired": false
-  },
-  {
-    "paramName": "hmu",
-    "paramLongName": "hiveMetastoreUris",
-    "paramDescription": "the hive metastore uris",
-    "paramRequired": true
-  },
-  {
-    "paramName": "sql",
-    "paramLongName": "sql",
-    "paramDescription": "sql script to execute",
-    "paramRequired": true
-  }
-]

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

@@ -50,13 +50,10 @@ object ScholixUtils extends Serializable {
     }
   }
 
-  def extractRelationDate(summary: ScholixSummary): String = {
+  def extractRelationDate(summary: ScholixResource): String = {
+
+    summary.getPublicationDate
 
-    if (summary.getDate == null || summary.getDate.isEmpty)
-      null
-    else {
-      summary.getDate.get(0)
-    }
   }
 
   def inverseRelationShip(rel: ScholixRelationship): ScholixRelationship = {
@@ -144,11 +141,7 @@ object ScholixUtils extends Serializable {
     s.setRelationship(inverseRelationShip(scholix.getRelationship))
     s.setSource(scholix.getTarget)
     s.setTarget(scholix.getSource)
-    s.setIdentifier(
-      DHPUtils.md5(
-        s"${s.getSource.getIdentifier}::${s.getRelationship.getName}::${s.getTarget.getIdentifier}"
-      )
-    )
+    updateId(s)
     s
 
   }
@@ -187,6 +180,21 @@ object ScholixUtils extends Serializable {
     } else List()
   }
 
+  def updateId(scholix: Scholix): Scholix = {
+    scholix.setIdentifier(
+      generateIdentifier(
+        scholix.getSource.getDnetIdentifier,
+        scholix.getTarget.getDnetIdentifier,
+        scholix.getRelationship.getName
+      )
+    )
+    scholix
+  }
+
+  def generateIdentifier(sourceId: String, targetId: String, relation: String): String = {
+    DHPUtils.md5(s"$sourceId::$relation::$targetId")
+  }
+
   def generateCompleteScholix(scholix: Scholix, target: ScholixSummary): Scholix = {
     val s = new Scholix
     s.setPublicationDate(scholix.getPublicationDate)
@@ -195,11 +203,7 @@ object ScholixUtils extends Serializable {
     s.setRelationship(scholix.getRelationship)
     s.setSource(scholix.getSource)
     s.setTarget(generateScholixResourceFromSummary(target))
-    s.setIdentifier(
-      DHPUtils.md5(
-        s"${s.getSource.getIdentifier}::${s.getRelationship.getName}::${s.getTarget.getIdentifier}"
-      )
-    )
+    updateId(s)
     s
   }
 
@@ -211,11 +215,7 @@ object ScholixUtils extends Serializable {
     s.setRelationship(scholix.getRelationship)
     s.setSource(scholix.getSource)
     s.setTarget(target)
-    s.setIdentifier(
-      DHPUtils.md5(
-        s"${s.getSource.getIdentifier}::${s.getRelationship.getName}::${s.getTarget.getIdentifier}"
-      )
-    )
+    updateId(s)
     s
   }
 
@@ -232,7 +232,7 @@ object ScholixUtils extends Serializable {
 
     if (summaryObject.getAuthor != null && !summaryObject.getAuthor.isEmpty) {
       val l: List[ScholixEntityId] =
-        summaryObject.getAuthor.asScala.map(a => new ScholixEntityId(a, null)).toList
+        summaryObject.getAuthor.asScala.map(a => new ScholixEntityId(a, null)).take(100).toList
       if (l.nonEmpty)
         r.setCreator(l.asJava)
     }
@@ -241,7 +241,7 @@ object ScholixUtils extends Serializable {
       r.setPublicationDate(summaryObject.getDate.get(0))
     if (summaryObject.getPublisher != null && !summaryObject.getPublisher.isEmpty) {
       val plist: List[ScholixEntityId] =
-        summaryObject.getPublisher.asScala.map(p => new ScholixEntityId(p, null)).toList
+        summaryObject.getPublisher.asScala.map(p => new ScholixEntityId(p, null)).take(100).toList
 
       if (plist.nonEmpty)
         r.setPublisher(plist.asJava)
@@ -260,6 +260,7 @@ object ScholixUtils extends Serializable {
             "complete"
           )
         )
+        .take(100)
         .toList
 
       if (l.nonEmpty)
@@ -269,38 +270,38 @@ object ScholixUtils extends Serializable {
     r
   }
 
+//  def scholixFromSource(relation: Relation, source: ScholixResource): Scholix = {
+//    if (relation == null || source == null)
+//      return null
+//    val s = new Scholix
+//    var l: List[ScholixEntityId] = extractCollectedFrom(relation)
+//    if (l.isEmpty)
+//      l = extractCollectedFrom(source)
+//    if (l.isEmpty)
+//      return null
+//    s.setLinkprovider(l.asJava)
+//    var d = extractRelationDate(relation)
+//    if (d == null)
+//      d = source.getPublicationDate
+//
+//    s.setPublicationDate(d)
+//
+//    if (source.getPublisher != null && !source.getPublisher.isEmpty) {
+//      s.setPublisher(source.getPublisher)
+//    }
+//
+//    val semanticRelation = relations.getOrElse(relation.getRelClass.toLowerCase, null)
+//    if (semanticRelation == null)
+//      return null
+//    s.setRelationship(
+//      new ScholixRelationship(semanticRelation.original, "datacite", semanticRelation.inverse)
+//    )
+//    s.setSource(source)
+//
+//    s
+//  }
+
   def scholixFromSource(relation: Relation, source: ScholixResource): Scholix = {
-    if (relation == null || source == null)
-      return null
-    val s = new Scholix
-    var l: List[ScholixEntityId] = extractCollectedFrom(relation)
-    if (l.isEmpty)
-      l = extractCollectedFrom(source)
-    if (l.isEmpty)
-      return null
-    s.setLinkprovider(l.asJava)
-    var d = extractRelationDate(relation)
-    if (d == null)
-      d = source.getPublicationDate
-
-    s.setPublicationDate(d)
-
-    if (source.getPublisher != null && !source.getPublisher.isEmpty) {
-      s.setPublisher(source.getPublisher)
-    }
-
-    val semanticRelation = relations.getOrElse(relation.getRelClass.toLowerCase, null)
-    if (semanticRelation == null)
-      return null
-    s.setRelationship(
-      new ScholixRelationship(semanticRelation.original, "datacite", semanticRelation.inverse)
-    )
-    s.setSource(source)
-
-    s
-  }
-
-  def scholixFromSource(relation: Relation, source: ScholixSummary): Scholix = {
 
     if (relation == null || source == null)
       return null
@@ -322,11 +323,8 @@ object ScholixUtils extends Serializable {
     s.setPublicationDate(d)
 
     if (source.getPublisher != null && !source.getPublisher.isEmpty) {
-      val l: List[ScholixEntityId] = source.getPublisher.asScala
-        .map { p =>
-          new ScholixEntityId(p, null)
-        }(collection.breakOut)
-
+      source.getPublisher
+      val l: List[ScholixEntityId] = source.getPublisher.asScala.toList
       if (l.nonEmpty)
         s.setPublisher(l.asJava)
     }
@@ -337,7 +335,7 @@ object ScholixUtils extends Serializable {
     s.setRelationship(
       new ScholixRelationship(semanticRelation.original, "datacite", semanticRelation.inverse)
     )
-    s.setSource(generateScholixResourceFromSummary(source))
+    s.setSource(source)
 
     s
   }

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

@@ -15,7 +15,7 @@ import com.fasterxml.jackson.databind.ObjectMapper;
 
 public class MdStoreClientTest {
 
-	// @Test
+	@Test
 	public void testMongoCollection() throws IOException {
 		final MdstoreClient client = new MdstoreClient("mongodb://localhost:27017", "mdstore");
 

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

@@ -0,0 +1,109 @@
+
+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/GridCleaningRuleTest.java

@@ -1,18 +0,0 @@
-
-package eu.dnetlib.dhp.schema.oaf.utils;
-
-import static org.junit.jupiter.api.Assertions.assertEquals;
-
-import org.junit.jupiter.api.Test;
-
-class GridCleaningRuleTest {
-
-	@Test
-	void testCleaning() {
-		assertEquals("grid.493784.5", GridCleaningRule.clean("grid.493784.5"));
-		assertEquals("grid.493784.5x", GridCleaningRule.clean("grid.493784.5x"));
-		assertEquals("grid.493784.5x", GridCleaningRule.clean("493784.5x"));
-		assertEquals("", GridCleaningRule.clean("493x784.5x"));
-	}
-
-}

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

@@ -1,19 +0,0 @@
-
-package eu.dnetlib.dhp.schema.oaf.utils;
-
-import static org.junit.jupiter.api.Assertions.assertEquals;
-
-import org.junit.jupiter.api.Test;
-
-class ISNICleaningRuleTest {
-
-	@Test
-	void testCleaning() {
-		assertEquals("0000000463436020", ISNICleaningRule.clean("0000 0004 6343 6020"));
-		assertEquals("0000000463436020", ISNICleaningRule.clean("0000000463436020"));
-		assertEquals("", ISNICleaningRule.clean("Q30256598"));
-		assertEquals("0000000493403529", ISNICleaningRule.clean("ISNI:0000000493403529"));
-		assertEquals("000000008614884X", ISNICleaningRule.clean("0000 0000 8614 884X"));
-	}
-
-}

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

@@ -1,19 +0,0 @@
-
-package eu.dnetlib.dhp.schema.oaf.utils;
-
-import static org.junit.jupiter.api.Assertions.assertEquals;
-
-import org.junit.jupiter.api.Test;
-
-class PICCleaningRuleTest {
-
-	@Test
-	void testCleaning() {
-		assertEquals("887624982", PICCleaningRule.clean("887624982"));
-		assertEquals("", PICCleaningRule.clean("887 624982"));
-		assertEquals("887624982", PICCleaningRule.clean(" 887624982 "));
-		assertEquals("887624982", PICCleaningRule.clean(" 887624982x "));
-		assertEquals("887624982", PICCleaningRule.clean(" 88762498200 "));
-	}
-
-}

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

@@ -1,19 +0,0 @@
-
-package eu.dnetlib.dhp.schema.oaf.utils;
-
-import static org.junit.jupiter.api.Assertions.assertEquals;
-
-import org.junit.jupiter.api.Test;
-
-class PmcCleaningRuleTest {
-
-	@Test
-	void testCleaning() {
-		assertEquals("PMC1234", PmcCleaningRule.clean("PMC1234"));
-		assertEquals("PMC1234", PmcCleaningRule.clean(" PMC1234"));
-		assertEquals("PMC12345678", PmcCleaningRule.clean("PMC12345678"));
-		assertEquals("PMC12345678", PmcCleaningRule.clean("PMC123456789"));
-		assertEquals("PMC12345678", PmcCleaningRule.clean("PMC 12345678"));
-	}
-
-}

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

@@ -1,24 +0,0 @@
-
-package eu.dnetlib.dhp.schema.oaf.utils;
-
-import static org.junit.jupiter.api.Assertions.assertEquals;
-
-import org.junit.jupiter.api.Test;
-
-class PmidCleaningRuleTest {
-
-	@Test
-	void testCleaning() {
-		// leading zeros are removed
-		assertEquals("1234", PmidCleaningRule.clean("01234"));
-		// tolerant to spaces in the middle
-		assertEquals("1234567", PmidCleaningRule.clean("0123 4567"));
-		// stop parsing at first not numerical char
-		assertEquals("123", PmidCleaningRule.clean("0123x4567"));
-		// invalid id leading to empty result
-		assertEquals("", PmidCleaningRule.clean("abc"));
-		// valid id with zeroes in the number
-		assertEquals("20794075", PmidCleaningRule.clean("20794075"));
-	}
-
-}

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

@@ -1,17 +0,0 @@
-
-package eu.dnetlib.dhp.schema.oaf.utils;
-
-import static org.junit.jupiter.api.Assertions.assertEquals;
-
-import org.junit.jupiter.api.Test;
-
-class RorCleaningRuleTest {
-
-	@Test
-	void testCleaning() {
-		assertEquals("https://ror.org/05rpz9w55", RorCleaningRule.clean("https://ror.org/05rpz9w55"));
-		assertEquals("https://ror.org/05rpz9w55", RorCleaningRule.clean("05rpz9w55"));
-		assertEquals("", RorCleaningRule.clean("05rpz9w_55"));
-	}
-
-}

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

@@ -1,114 +0,0 @@
-
-package eu.dnetlib.oa.merge;
-
-import static org.junit.jupiter.api.Assertions.*;
-
-import java.io.BufferedReader;
-import java.io.InputStreamReader;
-import java.util.List;
-import java.util.Objects;
-
-import org.junit.jupiter.api.Test;
-import org.junit.platform.commons.util.StringUtils;
-
-import com.fasterxml.jackson.core.type.TypeReference;
-import com.fasterxml.jackson.databind.ObjectMapper;
-
-import eu.dnetlib.dhp.oa.merge.AuthorMerger;
-import eu.dnetlib.dhp.schema.oaf.Author;
-
-public class AuthorMergerTest {
-
-	@Test
-	public void testEnrcichAuthor() throws Exception {
-		final ObjectMapper mapper = new ObjectMapper();
-
-		BufferedReader pr = new BufferedReader(new InputStreamReader(
-			Objects
-				.requireNonNull(
-					AuthorMergerTest.class
-						.getResourceAsStream("/eu/dnetlib/dhp/oa/merge/authors_publication_sample.json"))));
-		BufferedReader or = new BufferedReader(new InputStreamReader(
-			Objects
-				.requireNonNull(
-					AuthorMergerTest.class.getResourceAsStream("/eu/dnetlib/dhp/oa/merge/authors_orcid_sample.json"))));
-
-		TypeReference<List<Author>> aclass = new TypeReference<List<Author>>() {
-		};
-		String pubLine;
-
-		int i = 0;
-		while ((pubLine = pr.readLine()) != null) {
-			final String pubId = pubLine;
-			final String MatchPidOrcid = or.readLine();
-			final String pubOrcid = or.readLine();
-
-			final String data = pr.readLine();
-
-			if (StringUtils.isNotBlank(data)) {
-				List<Author> publicationAuthors = mapper.readValue(data, aclass);
-				List<Author> orcidAuthors = mapper.readValue(or.readLine(), aclass);
-				System.out.printf("OAF ID = %s \n", pubId);
-				System.out.printf("ORCID Intersected ID = %s \n", pubOrcid);
-				System.out.printf("OAF Author Size = %d \n", publicationAuthors.size());
-				System.out.printf("Oricd Author Size = %d \n", orcidAuthors.size());
-				System.out.printf("Oricd Matched PID = %s \n", MatchPidOrcid);
-
-				long originalAuthorWithPiD = publicationAuthors
-					.stream()
-					.filter(
-						a -> a.getPid() != null && a
-							.getPid()
-							.stream()
-							.anyMatch(
-								p -> p.getQualifier() != null
-									&& p.getQualifier().getClassid().toLowerCase().contains("orcid")))
-					.count();
-				long start = System.currentTimeMillis();
-
-//                final List<Author> enrichedList = AuthorMerger.enrichOrcid(publicationAuthors, orcidAuthors);
-				final List<Author> enrichedList = AuthorMerger.enrichOrcid(publicationAuthors, orcidAuthors);
-
-				long enrichedAuthorWithPid = enrichedList
-					.stream()
-					.filter(
-						a -> a.getPid() != null && a
-							.getPid()
-							.stream()
-							.anyMatch(
-								p -> p.getQualifier() != null
-									&& p.getQualifier().getClassid().toLowerCase().contains("orcid")))
-					.count();
-
-				long totalTime = (System.currentTimeMillis() - start) / 1000;
-				System.out
-					.printf(
-						"Enriched authors in %d seconds from %d pid to %d pid \n", totalTime, originalAuthorWithPiD,
-						enrichedAuthorWithPid);
-
-				System.out.println("=================");
-			}
-		}
-	}
-
-	@Test
-	public void checkSimilarityTest() {
-		final Author left = new Author();
-		left.setName("Anand");
-		left.setSurname("Rachna");
-		left.setFullname("Anand, Rachna");
-
-		System.out.println(AuthorMerger.normalizeFullName(left.getFullname()));
-
-		final Author right = new Author();
-		right.setName("Rachna");
-		right.setSurname("Anand");
-		right.setFullname("Rachna, Anand");
-//        System.out.println(AuthorMerger.normalize(right.getFullname()));
-		boolean same = AuthorMerger.checkORCIDSimilarity(left, right);
-
-		assertTrue(same);
-
-	}
-
-}

dhp-pace-core/pom.xml

@@ -7,7 +7,7 @@
 		<groupId>eu.dnetlib.dhp</groupId>
 		<artifactId>dhp</artifactId>
 		<version>1.2.5-SNAPSHOT</version>
-        <relativePath>../pom.xml</relativePath>
+		<relativePath>../pom.xml</relativePath>
 	</parent>
 
 	<groupId>eu.dnetlib.dhp</groupId>

dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/AbstractClusteringFunction.java

@@ -14,9 +14,9 @@ import eu.dnetlib.pace.config.Config;
 
 public abstract class AbstractClusteringFunction extends AbstractPaceFunctions implements ClusteringFunction {
 
-	protected Map<String, Object> params;
+	protected Map<String, Integer> params;
 
-	public AbstractClusteringFunction(final Map<String, Object> params) {
+	public AbstractClusteringFunction(final Map<String, Integer> params) {
 		this.params = params;
 	}
 
@@ -27,7 +27,7 @@ public abstract class AbstractClusteringFunction extends AbstractPaceFunctions i
 		return fields
 			.stream()
 			.filter(f -> !f.isEmpty())
-			.map(s -> normalize(s))
+			.map(this::normalize)
 			.map(s -> filterAllStopWords(s))
 			.map(s -> doApply(conf, s))
 			.map(c -> filterBlacklisted(c, ngramBlacklist))
@@ -36,24 +36,11 @@ public abstract class AbstractClusteringFunction extends AbstractPaceFunctions i
 			.collect(Collectors.toCollection(HashSet::new));
 	}
 
-	public Map<String, Object> getParams() {
+	public Map<String, Integer> getParams() {
 		return params;
 	}
 
 	protected Integer param(String name) {
-		Object val = params.get(name);
-		if (val == null)
-			return null;
-		if (val instanceof Number) {
-			return ((Number) val).intValue();
-		}
-		return Integer.parseInt(val.toString());
-	}
-
-	protected int paramOrDefault(String name, int i) {
-		Integer res = param(name);
-		if (res == null)
-			res = i;
-		return res;
+		return params.get(name);
 	}
 }

dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/Acronyms.java

@@ -13,7 +13,7 @@ import eu.dnetlib.pace.config.Config;
 @ClusteringClass("acronyms")
 public class Acronyms extends AbstractClusteringFunction {
 
-	public Acronyms(Map<String, Object> params) {
+	public Acronyms(Map<String, Integer> params) {
 		super(params);
 	}
 

dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/ClusteringFunction.java

@@ -11,6 +11,6 @@ public interface ClusteringFunction {
 
 	public Collection<String> apply(Config config, List<String> fields);
 
-	public Map<String, Object> getParams();
+	public Map<String, Integer> getParams();
 
 }

dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/ImmutableFieldValue.java

@@ -12,7 +12,7 @@ import eu.dnetlib.pace.config.Config;
 @ClusteringClass("immutablefieldvalue")
 public class ImmutableFieldValue extends AbstractClusteringFunction {
 
-	public ImmutableFieldValue(final Map<String, Object> params) {
+	public ImmutableFieldValue(final Map<String, Integer> params) {
 		super(params);
 	}
 

dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/JSONListClustering.java

@@ -1,69 +0,0 @@
-
-package eu.dnetlib.pace.clustering;
-
-import java.util.Collection;
-import java.util.HashSet;
-import java.util.List;
-import java.util.Map;
-import java.util.stream.Collectors;
-
-import org.apache.commons.lang3.StringUtils;
-
-import com.jayway.jsonpath.Configuration;
-import com.jayway.jsonpath.DocumentContext;
-import com.jayway.jsonpath.JsonPath;
-import com.jayway.jsonpath.Option;
-
-import eu.dnetlib.pace.common.AbstractPaceFunctions;
-import eu.dnetlib.pace.config.Config;
-import eu.dnetlib.pace.util.MapDocumentUtil;
-
-@ClusteringClass("jsonlistclustering")
-public class JSONListClustering extends AbstractPaceFunctions implements ClusteringFunction {
-
-	private Map<String, Object> params;
-
-	public JSONListClustering(Map<String, Object> params) {
-		this.params = params;
-	}
-
-	@Override
-	public Map<String, Object> getParams() {
-		return params;
-	}
-
-	@Override
-	public Collection<String> apply(Config conf, List<String> fields) {
-		return fields
-			.stream()
-			.filter(f -> !f.isEmpty())
-			.map(s -> doApply(conf, s))
-			.filter(StringUtils::isNotBlank)
-			.collect(Collectors.toCollection(HashSet::new));
-	}
-
-	private String doApply(Config conf, String json) {
-		StringBuilder st = new StringBuilder(); // to build the string used for comparisons basing on the jpath into
-		// parameters
-		final DocumentContext documentContext = JsonPath
-			.using(Configuration.defaultConfiguration().addOptions(Option.SUPPRESS_EXCEPTIONS))
-			.parse(json);
-
-		// for each path in the param list
-		for (String key : params.keySet().stream().filter(k -> k.contains("jpath")).collect(Collectors.toList())) {
-			String path = params.get(key).toString();
-			String value = MapDocumentUtil.getJPathString(path, documentContext);
-			if (value == null || value.isEmpty())
-				value = "";
-			st.append(value);
-			st.append(" ");
-		}
-
-		st.setLength(st.length() - 1);
-
-		if (StringUtils.isBlank(st)) {
-			return "1";
-		}
-		return st.toString();
-	}
-}

dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/KeywordsClustering.java

@@ -11,7 +11,7 @@ import eu.dnetlib.pace.config.Config;
 @ClusteringClass("keywordsclustering")
 public class KeywordsClustering extends AbstractClusteringFunction {
 
-	public KeywordsClustering(Map<String, Object> params) {
+	public KeywordsClustering(Map<String, Integer> params) {
 		super(params);
 	}
 
@@ -19,8 +19,8 @@ public class KeywordsClustering extends AbstractClusteringFunction {
 	protected Collection<String> doApply(final Config conf, String s) {
 
 		// takes city codes and keywords codes without duplicates
-		Set<String> keywords = getKeywords(s, conf.translationMap(), paramOrDefault("windowSize", 4));
-		Set<String> cities = getCities(s, paramOrDefault("windowSize", 4));
+		Set<String> keywords = getKeywords(s, conf.translationMap(), params.getOrDefault("windowSize", 4));
+		Set<String> cities = getCities(s, params.getOrDefault("windowSize", 4));
 
 		// list of combination to return as result
 		final Collection<String> combinations = new LinkedHashSet<String>();
@@ -28,7 +28,7 @@ public class KeywordsClustering extends AbstractClusteringFunction {
 		for (String keyword : keywordsToCodes(keywords, conf.translationMap())) {
 			for (String city : citiesToCodes(cities)) {
 				combinations.add(keyword + "-" + city);
-				if (combinations.size() >= paramOrDefault("max", 2)) {
+				if (combinations.size() >= params.getOrDefault("max", 2)) {
 					return combinations;
 				}
 			}
@@ -42,8 +42,8 @@ public class KeywordsClustering extends AbstractClusteringFunction {
 		return fields
 			.stream()
 			.filter(f -> !f.isEmpty())
-			.map(KeywordsClustering::cleanup)
-			.map(KeywordsClustering::normalize)
+			.map(this::cleanup)
+			.map(this::normalize)
 			.map(s -> filterAllStopWords(s))
 			.map(s -> doApply(conf, s))
 			.map(c -> filterBlacklisted(c, ngramBlacklist))

dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/LastNameFirstInitial.java

@@ -16,7 +16,7 @@ public class LastNameFirstInitial extends AbstractClusteringFunction {
 
 	private boolean DEFAULT_AGGRESSIVE = true;
 
-	public LastNameFirstInitial(final Map<String, Object> params) {
+	public LastNameFirstInitial(final Map<String, Integer> params) {
 		super(params);
 	}
 
@@ -25,7 +25,7 @@ public class LastNameFirstInitial extends AbstractClusteringFunction {
 		return fields
 			.stream()
 			.filter(f -> !f.isEmpty())
-			.map(LastNameFirstInitial::normalize)
+			.map(this::normalize)
 			.map(s -> doApply(conf, s))
 			.map(c -> filterBlacklisted(c, ngramBlacklist))
 			.flatMap(c -> c.stream())
@@ -33,7 +33,8 @@ public class LastNameFirstInitial extends AbstractClusteringFunction {
 			.collect(Collectors.toCollection(HashSet::new));
 	}
 
-	public static String normalize(final String s) {
+	@Override
+	protected String normalize(final String s) {
 		return fixAliases(transliterate(nfd(unicodeNormalization(s))))
 			// do not compact the regexes in a single expression, would cause StackOverflowError in case of large input
 			// strings

dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/LowercaseClustering.java

@@ -15,7 +15,7 @@ import eu.dnetlib.pace.config.Config;
 @ClusteringClass("lowercase")
 public class LowercaseClustering extends AbstractClusteringFunction {
 
-	public LowercaseClustering(final Map<String, Object> params) {
+	public LowercaseClustering(final Map<String, Integer> params) {
 		super(params);
 	}
 

dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/NGramUtils.java

@@ -16,9 +16,8 @@ public class NGramUtils extends AbstractPaceFunctions {
 		.loadFromClasspath("/eu/dnetlib/pace/config/stopwords_en.txt");
 
 	public static String cleanupForOrdering(String s) {
-		return (NGRAMUTILS.filterStopWords(NGRAMUTILS.normalize(s), stopwords) + StringUtils.repeat(" ", SIZE))
-			.substring(0, SIZE)
-			.replaceAll(" ", "");
+		String result = NGRAMUTILS.filterStopWords(NGRAMUTILS.normalize(s), stopwords);
+		return result.isEmpty() ? result : result.replace(" ", "");
 	}
 
 }

dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/NgramPairs.java

@@ -2,6 +2,7 @@
 package eu.dnetlib.pace.clustering;
 
 import java.util.Collection;
+import java.util.HashMap;
 import java.util.List;
 import java.util.Map;
 
@@ -12,11 +13,11 @@ import eu.dnetlib.pace.config.Config;
 @ClusteringClass("ngrampairs")
 public class NgramPairs extends Ngrams {
 
-	public NgramPairs(Map<String, Object> params) {
+	public NgramPairs(Map<String, Integer> params) {
 		super(params, false);
 	}
 
-	public NgramPairs(Map<String, Object> params, boolean sorted) {
+	public NgramPairs(Map<String, Integer> params, boolean sorted) {
 		super(params, sorted);
 	}
 

dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/Ngrams.java

@@ -10,11 +10,11 @@ public class Ngrams extends AbstractClusteringFunction {
 
 	private final boolean sorted;
 
-	public Ngrams(Map<String, Object> params) {
+	public Ngrams(Map<String, Integer> params) {
 		this(params, false);
 	}
 
-	public Ngrams(Map<String, Object> params, boolean sorted) {
+	public Ngrams(Map<String, Integer> params, boolean sorted) {
 		super(params);
 		this.sorted = sorted;
 	}

dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/NumAuthorsTitleSuffixPrefixChain.java

@@ -1,113 +0,0 @@
-
-package eu.dnetlib.pace.clustering;
-
-import java.util.*;
-import java.util.stream.Collectors;
-import java.util.stream.StreamSupport;
-
-import com.google.common.base.Splitter;
-import com.google.common.collect.Sets;
-
-import eu.dnetlib.pace.config.Config;
-
-@ClusteringClass("numAuthorsTitleSuffixPrefixChain")
-public class NumAuthorsTitleSuffixPrefixChain extends AbstractClusteringFunction {
-
-	public NumAuthorsTitleSuffixPrefixChain(Map<String, Object> params) {
-		super(params);
-	}
-
-	@Override
-	public Collection<String> apply(Config conf, List<String> fields) {
-
-		try {
-			int num_authors = Math.min(Integer.parseInt(fields.get(0)), 21); // SIZE threshold is 20, +1
-
-			if (num_authors > 0) {
-				return super.apply(conf, fields.subList(1, fields.size()))
-					.stream()
-					.map(s -> num_authors + "-" + s)
-					.collect(Collectors.toList());
-			}
-		} catch (NumberFormatException e) {
-			// missing or null authors array
-		}
-
-		return Collections.emptyList();
-	}
-
-	@Override
-	protected Collection<String> doApply(Config conf, String s) {
-		return suffixPrefixChain(cleanup(s), param("mod"));
-	}
-
-	private Collection<String> suffixPrefixChain(String s, int mod) {
-		// create the list of words from the string (remove short words)
-		List<String> wordsList = Arrays
-			.stream(s.split(" "))
-			.filter(si -> si.length() > 3)
-			.collect(Collectors.toList());
-
-		final int words = wordsList.size();
-		final int letters = s.length();
-
-		// create the prefix: number of words + number of letters/mod
-		String prefix = words / mod + "-";
-
-		return doSuffixPrefixChain(wordsList, prefix);
-
-	}
-
-	private Collection<String> doSuffixPrefixChain(List<String> wordsList, String prefix) {
-
-		Set<String> set = Sets.newLinkedHashSet();
-		switch (wordsList.size()) {
-			case 0:
-				break;
-			case 1:
-				set.add(wordsList.get(0));
-				break;
-			case 2:
-				set
-					.add(
-						prefix +
-							suffix(wordsList.get(0), 3) +
-							prefix(wordsList.get(1), 3));
-
-				set
-					.add(
-						prefix +
-							prefix(wordsList.get(0), 3) +
-							suffix(wordsList.get(1), 3));
-
-				break;
-			default:
-				set
-					.add(
-						prefix +
-							suffix(wordsList.get(0), 3) +
-							prefix(wordsList.get(1), 3) +
-							suffix(wordsList.get(2), 3));
-
-				set
-					.add(
-						prefix +
-							prefix(wordsList.get(0), 3) +
-							suffix(wordsList.get(1), 3) +
-							prefix(wordsList.get(2), 3));
-				break;
-		}
-
-		return set;
-
-	}
-
-	private String suffix(String s, int len) {
-		return s.substring(s.length() - len);
-	}
-
-	private String prefix(String s, int len) {
-		return s.substring(0, len);
-	}
-
-}

dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/PersonClustering.java

@@ -17,11 +17,11 @@ import eu.dnetlib.pace.model.Person;
 @ClusteringClass("personClustering")
 public class PersonClustering extends AbstractPaceFunctions implements ClusteringFunction {
 
-	private Map<String, Object> params;
+	private Map<String, Integer> params;
 
 	private static final int MAX_TOKENS = 5;
 
-	public PersonClustering(final Map<String, Object> params) {
+	public PersonClustering(final Map<String, Integer> params) {
 		this.params = params;
 	}
 
@@ -77,7 +77,7 @@ public class PersonClustering extends AbstractPaceFunctions implements Clusterin
 //	}
 
 	@Override
-	public Map<String, Object> getParams() {
+	public Map<String, Integer> getParams() {
 		return params;
 	}
 

dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/PersonHash.java

@@ -15,7 +15,7 @@ public class PersonHash extends AbstractClusteringFunction {
 
 	private boolean DEFAULT_AGGRESSIVE = false;
 
-	public PersonHash(final Map<String, Object> params) {
+	public PersonHash(final Map<String, Integer> params) {
 		super(params);
 	}
 

dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/RandomClusteringFunction.java

@@ -8,7 +8,7 @@ import eu.dnetlib.pace.config.Config;
 
 public class RandomClusteringFunction extends AbstractClusteringFunction {
 
-	public RandomClusteringFunction(Map<String, Object> params) {
+	public RandomClusteringFunction(Map<String, Integer> params) {
 		super(params);
 	}
 

dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/SortedNgramPairs.java

@@ -1,10 +1,7 @@
 
 package eu.dnetlib.pace.clustering;
 
-import java.util.Collection;
-import java.util.Collections;
-import java.util.List;
-import java.util.Map;
+import java.util.*;
 
 import com.google.common.base.Joiner;
 import com.google.common.base.Splitter;
@@ -15,20 +12,8 @@ import eu.dnetlib.pace.config.Config;
 @ClusteringClass("sortedngrampairs")
 public class SortedNgramPairs extends NgramPairs {
 
-	public SortedNgramPairs(Map<String, Object> params) {
-		super(params, false);
-	}
-
-	@Override
-	protected Collection<String> doApply(Config conf, String s) {
-
-		final List<String> tokens = Lists.newArrayList(Splitter.on(" ").omitEmptyStrings().trimResults().split(s));
-
-		Collections.sort(tokens);
-
-		return ngramPairs(
-			Lists.newArrayList(getNgrams(Joiner.on(" ").join(tokens), param("ngramLen"), param("max") * 2, 1, 2)),
-			param("max"));
+	public SortedNgramPairs(Map<String, Integer> params) {
+		super(params, true);
 	}
 
 }

dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/SpaceTrimmingFieldValue.java

@@ -15,7 +15,7 @@ import eu.dnetlib.pace.config.Config;
 @ClusteringClass("spacetrimmingfieldvalue")
 public class SpaceTrimmingFieldValue extends AbstractClusteringFunction {
 
-	public SpaceTrimmingFieldValue(final Map<String, Object> params) {
+	public SpaceTrimmingFieldValue(final Map<String, Integer> params) {
 		super(params);
 	}
 
@@ -25,7 +25,7 @@ public class SpaceTrimmingFieldValue extends AbstractClusteringFunction {
 
 		res
 			.add(
-				StringUtils.isBlank(s) ? RandomStringUtils.random(param("randomLength"))
+				StringUtils.isBlank(s) ? RandomStringUtils.random(getParams().get("randomLength"))
 					: s.toLowerCase().replaceAll("\\s+", ""));
 
 		return res;

dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/SuffixPrefix.java

@@ -12,7 +12,7 @@ import eu.dnetlib.pace.config.Config;
 @ClusteringClass("suffixprefix")
 public class SuffixPrefix extends AbstractClusteringFunction {
 
-	public SuffixPrefix(Map<String, Object> params) {
+	public SuffixPrefix(Map<String, Integer> params) {
 		super(params);
 	}
 

dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/UrlClustering.java

@@ -15,17 +15,12 @@ import eu.dnetlib.pace.config.Config;
 @ClusteringClass("urlclustering")
 public class UrlClustering extends AbstractPaceFunctions implements ClusteringFunction {
 
-	protected Map<String, Object> params;
+	protected Map<String, Integer> params;
 
-	public UrlClustering(final Map<String, Object> params) {
+	public UrlClustering(final Map<String, Integer> params) {
 		this.params = params;
 	}
 
-	@Override
-	public Map<String, Object> getParams() {
-		return params;
-	}
-
 	@Override
 	public Collection<String> apply(final Config conf, List<String> fields) {
 		try {
@@ -40,6 +35,11 @@ public class UrlClustering extends AbstractPaceFunctions implements ClusteringFu
 		}
 	}
 
+	@Override
+	public Map<String, Integer> getParams() {
+		return null;
+	}
+
 	private URL asUrl(String value) {
 		try {
 			return new URL(value);

dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/WordsStatsSuffixPrefixChain.java

@@ -11,7 +11,7 @@ import eu.dnetlib.pace.config.Config;
 @ClusteringClass("wordsStatsSuffixPrefixChain")
 public class WordsStatsSuffixPrefixChain extends AbstractClusteringFunction {
 
-	public WordsStatsSuffixPrefixChain(Map<String, Object> params) {
+	public WordsStatsSuffixPrefixChain(Map<String, Integer> params) {
 		super(params);
 	}
 

dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/WordsSuffixPrefix.java

@@ -12,7 +12,7 @@ import eu.dnetlib.pace.config.Config;
 @ClusteringClass("wordssuffixprefix")
 public class WordsSuffixPrefix extends AbstractClusteringFunction {
 
-	public WordsSuffixPrefix(Map<String, Object> params) {
+	public WordsSuffixPrefix(Map<String, Integer> params) {
 		super(params);
 	}
 

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

@@ -16,6 +16,7 @@ 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.Lists;
 import com.google.common.collect.Sets;
 import com.ibm.icu.text.Transliterator;
 
@@ -26,7 +27,7 @@ import eu.dnetlib.pace.clustering.NGramUtils;
  *
  * @author claudio
  */
-public class AbstractPaceFunctions {
+public abstract class AbstractPaceFunctions {
 
 	// city map to be used when translating the city names into codes
 	private static Map<String, String> cityMap = AbstractPaceFunctions
@@ -48,27 +49,24 @@ public class AbstractPaceFunctions {
 	protected static Set<String> ngramBlacklist = loadFromClasspath("/eu/dnetlib/pace/config/ngram_blacklist.txt");
 
 	// html regex for normalization
-	public static final Pattern HTML_REGEX = Pattern.compile("<[^>]*>");
+	public 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:)");
+	public final Pattern DOI_PREFIX = Pattern.compile("(https?:\\/\\/dx\\.doi\\.org\\/)|(doi:)");
 
-	private static Pattern numberPattern = Pattern.compile("-?\\d+(\\.\\d+)?");
+	private Pattern numberPattern = Pattern.compile("-?\\d+(\\.\\d+)?");
 
-	private static Pattern hexUnicodePattern = Pattern.compile("\\\\u(\\p{XDigit}{4})");
+	private Pattern hexUnicodePattern = Pattern.compile("\\\\u(\\p{XDigit}{4})");
 
-	private static Pattern romanNumberPattern = Pattern
-		.compile("^M{0,4}(CM|CD|D?C{0,3})(XC|XL|L?X{0,3})(IX|IV|V?I{0,3})$");
-
-	protected static String concat(final List<String> l) {
+	protected String concat(final List<String> l) {
 		return Joiner.on(" ").skipNulls().join(l);
 	}
 
-	public static String cleanup(final String s) {
+	protected String cleanup(final String s) {
 		final String s1 = HTML_REGEX.matcher(s).replaceAll("");
 		final String s2 = unicodeNormalization(s1.toLowerCase());
 		final String s3 = nfd(s2);
@@ -84,7 +82,7 @@ public class AbstractPaceFunctions {
 		return s12;
 	}
 
-	protected static String fixXML(final String a) {
+	protected String fixXML(final String a) {
 
 		return a
 			.replaceAll("&ndash;", " ")
@@ -93,7 +91,7 @@ public class AbstractPaceFunctions {
 			.replaceAll("&minus;", " ");
 	}
 
-	protected static boolean checkNumbers(final String a, final String b) {
+	protected boolean checkNumbers(final String a, final String b) {
 		final String numbersA = getNumbers(a);
 		final String numbersB = getNumbers(b);
 		final String romansA = getRomans(a);
@@ -101,7 +99,7 @@ public class AbstractPaceFunctions {
 		return !numbersA.equals(numbersB) || !romansA.equals(romansB);
 	}
 
-	protected static String getRomans(final String s) {
+	protected String getRomans(final String s) {
 		final StringBuilder sb = new StringBuilder();
 		for (final String t : s.split(" ")) {
 			sb.append(isRoman(t) ? t : "");
@@ -109,12 +107,13 @@ public class AbstractPaceFunctions {
 		return sb.toString();
 	}
 
-	protected static boolean isRoman(final String s) {
-		Matcher m = romanNumberPattern.matcher(s);
-		return m.matches() && m.hitEnd();
+	protected boolean isRoman(final String s) {
+		return s
+			.replaceAll("^M{0,4}(CM|CD|D?C{0,3})(XC|XL|L?X{0,3})(IX|IV|V?I{0,3})$", "qwertyuiop")
+			.equals("qwertyuiop");
 	}
 
-	protected static String getNumbers(final String s) {
+	protected String getNumbers(final String s) {
 		final StringBuilder sb = new StringBuilder();
 		for (final String t : s.split(" ")) {
 			sb.append(isNumber(t) ? t : "");
@@ -122,7 +121,7 @@ public class AbstractPaceFunctions {
 		return sb.toString();
 	}
 
-	public static boolean isNumber(String strNum) {
+	public boolean isNumber(String strNum) {
 		if (strNum == null) {
 			return false;
 		}
@@ -131,12 +130,10 @@ public class AbstractPaceFunctions {
 
 	protected static String fixAliases(final String s) {
 		final StringBuilder sb = new StringBuilder();
-
-		s.chars().forEach(ch -> {
+		for (final char ch : Lists.charactersOf(s)) {
 			final int i = StringUtils.indexOf(aliases_from, ch);
-			sb.append(i >= 0 ? aliases_to.charAt(i) : (char) ch);
-		});
-
+			sb.append(i >= 0 ? aliases_to.charAt(i) : ch);
+		}
 		return sb.toString();
 	}
 
@@ -148,21 +145,20 @@ public class AbstractPaceFunctions {
 		}
 	}
 
-	protected static String removeSymbols(final String s) {
+	protected String removeSymbols(final String s) {
 		final StringBuilder sb = new StringBuilder();
 
-		s.chars().forEach(ch -> {
-			sb.append(StringUtils.contains(alpha, ch) ? (char) ch : ' ');
-		});
-
+		for (final char ch : Lists.charactersOf(s)) {
+			sb.append(StringUtils.contains(alpha, ch) ? ch : " ");
+		}
 		return sb.toString().replaceAll("\\s+", " ");
 	}
 
-	protected static boolean notNull(final String s) {
+	protected boolean notNull(final String s) {
 		return s != null;
 	}
 
-	public static String normalize(final String s) {
+	protected 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
@@ -175,16 +171,16 @@ public class AbstractPaceFunctions {
 			.trim();
 	}
 
-	public static String nfd(final String s) {
+	public String nfd(final String s) {
 		return Normalizer.normalize(s, Normalizer.Form.NFD);
 	}
 
-	public static String utf8(final String s) {
+	public String utf8(final String s) {
 		byte[] bytes = s.getBytes(StandardCharsets.UTF_8);
 		return new String(bytes, StandardCharsets.UTF_8);
 	}
 
-	public static String unicodeNormalization(final String s) {
+	public String unicodeNormalization(final String s) {
 
 		Matcher m = hexUnicodePattern.matcher(s);
 		StringBuffer buf = new StringBuffer(s.length());
@@ -196,7 +192,7 @@ public class AbstractPaceFunctions {
 		return buf.toString();
 	}
 
-	protected static String filterStopWords(final String s, final Set<String> stopwords) {
+	protected String filterStopWords(final String s, final Set<String> stopwords) {
 		final StringTokenizer st = new StringTokenizer(s);
 		final StringBuilder sb = new StringBuilder();
 		while (st.hasMoreTokens()) {
@@ -209,7 +205,7 @@ public class AbstractPaceFunctions {
 		return sb.toString().trim();
 	}
 
-	public static String filterAllStopWords(String s) {
+	public String filterAllStopWords(String s) {
 
 		s = filterStopWords(s, stopwords_en);
 		s = filterStopWords(s, stopwords_de);
@@ -222,8 +218,7 @@ public class AbstractPaceFunctions {
 		return s;
 	}
 
-	protected static Collection<String> filterBlacklisted(final Collection<String> set,
-		final Set<String> ngramBlacklist) {
+	protected Collection<String> filterBlacklisted(final Collection<String> set, final Set<String> ngramBlacklist) {
 		final Set<String> newset = Sets.newLinkedHashSet();
 		for (final String s : set) {
 			if (!ngramBlacklist.contains(s)) {
@@ -239,8 +234,7 @@ public class AbstractPaceFunctions {
 
 		final Set<String> h = Sets.newHashSet();
 		try {
-			for (final String s : IOUtils
-				.readLines(NGramUtils.class.getResourceAsStream(classpath), StandardCharsets.UTF_8)) {
+			for (final String s : IOUtils.readLines(NGramUtils.class.getResourceAsStream(classpath))) {
 				h.add(fixAliases(transliterator.transliterate(s))); // transliteration of the stopwords
 			}
 		} catch (final Throwable e) {
@@ -255,8 +249,7 @@ public class AbstractPaceFunctions {
 
 		final Map<String, String> m = new HashMap<>();
 		try {
-			for (final String s : IOUtils
-				.readLines(AbstractPaceFunctions.class.getResourceAsStream(classpath), StandardCharsets.UTF_8)) {
+			for (final String s : IOUtils.readLines(AbstractPaceFunctions.class.getResourceAsStream(classpath))) {
 				// string is like this: code;word1;word2;word3
 				String[] line = s.split(";");
 				String value = line[0];
@@ -270,7 +263,7 @@ public class AbstractPaceFunctions {
 		return m;
 	}
 
-	public static String removeKeywords(String s, Set<String> keywords) {
+	public String removeKeywords(String s, Set<String> keywords) {
 
 		s = " " + s + " ";
 		for (String k : keywords) {
@@ -280,39 +273,39 @@ public class AbstractPaceFunctions {
 		return s.trim();
 	}
 
-	public static double commonElementsPercentage(Set<String> s1, Set<String> s2) {
+	public double commonElementsPercentage(Set<String> s1, Set<String> s2) {
 
 		double longer = Math.max(s1.size(), s2.size());
 		return (double) s1.stream().filter(s2::contains).count() / longer;
 	}
 
 	// convert the set of keywords to codes
-	public static Set<String> toCodes(Set<String> keywords, Map<String, String> translationMap) {
+	public Set<String> toCodes(Set<String> keywords, Map<String, String> translationMap) {
 		return keywords.stream().map(s -> translationMap.get(s)).collect(Collectors.toSet());
 	}
 
-	public static Set<String> keywordsToCodes(Set<String> keywords, Map<String, String> translationMap) {
+	public Set<String> keywordsToCodes(Set<String> keywords, Map<String, String> translationMap) {
 		return toCodes(keywords, translationMap);
 	}
 
-	public static Set<String> citiesToCodes(Set<String> keywords) {
+	public Set<String> citiesToCodes(Set<String> keywords) {
 		return toCodes(keywords, cityMap);
 	}
 
-	protected static String firstLC(final String s) {
+	protected String firstLC(final String s) {
 		return StringUtils.substring(s, 0, 1).toLowerCase();
 	}
 
-	protected static Iterable<String> tokens(final String s, final int maxTokens) {
+	protected 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) {
+	public String normalizePid(String pid) {
 		return DOI_PREFIX.matcher(pid.toLowerCase()).replaceAll("");
 	}
 
 	// get the list of keywords into the input string
-	public static Set<String> getKeywords(String s1, Map<String, String> translationMap, int windowSize) {
+	public Set<String> getKeywords(String s1, Map<String, String> translationMap, int windowSize) {
 
 		String s = s1;
 
@@ -342,14 +335,14 @@ public class AbstractPaceFunctions {
 		return codes;
 	}
 
-	public static Set<String> getCities(String s1, int windowSize) {
+	public Set<String> getCities(String s1, int windowSize) {
 		return getKeywords(s1, cityMap, windowSize);
 	}
 
 	public static <T> String readFromClasspath(final String filename, final Class<T> clazz) {
 		final StringWriter sw = new StringWriter();
 		try {
-			IOUtils.copy(clazz.getResourceAsStream(filename), sw, StandardCharsets.UTF_8);
+			IOUtils.copy(clazz.getResourceAsStream(filename), sw);
 			return sw.toString();
 		} catch (final IOException e) {
 			throw new RuntimeException("cannot load resource from classpath: " + filename);

dhp-pace-core/src/main/java/eu/dnetlib/pace/config/Config.java

@@ -4,6 +4,7 @@ package eu.dnetlib.pace.config;
 import java.util.List;
 import java.util.Map;
 import java.util.function.Predicate;
+import java.util.regex.Pattern;
 
 import eu.dnetlib.pace.model.ClusteringDef;
 import eu.dnetlib.pace.model.FieldDef;

dhp-pace-core/src/main/java/eu/dnetlib/pace/model/ClusteringDef.java

@@ -18,7 +18,7 @@ public class ClusteringDef implements Serializable {
 
 	private List<String> fields;
 
-	private Map<String, Object> params;
+	private Map<String, Integer> params;
 
 	public ClusteringDef() {
 	}
@@ -43,11 +43,11 @@ public class ClusteringDef implements Serializable {
 		this.fields = fields;
 	}
 
-	public Map<String, Object> getParams() {
+	public Map<String, Integer> getParams() {
 		return params;
 	}
 
-	public void setParams(final Map<String, Object> params) {
+	public void setParams(final Map<String, Integer> params) {
 		this.params = params;
 	}
 

dhp-pace-core/src/main/java/eu/dnetlib/pace/model/FieldDef.java

@@ -2,7 +2,6 @@
 package eu.dnetlib.pace.model;
 
 import java.io.Serializable;
-import java.util.HashSet;
 import java.util.List;
 
 import com.fasterxml.jackson.core.JsonProcessingException;
@@ -37,16 +36,6 @@ public class FieldDef implements Serializable {
 	 */
 	private int length = -1;
 
-	private HashSet<String> filter;
-
-	private boolean sorted;
-
-	public boolean isSorted() {
-		return sorted;
-	}
-
-	private String clean;
-
 	public FieldDef() {
 	}
 
@@ -102,30 +91,6 @@ public class FieldDef implements Serializable {
 		this.path = path;
 	}
 
-	public HashSet<String> getFilter() {
-		return filter;
-	}
-
-	public void setFilter(HashSet<String> filter) {
-		this.filter = filter;
-	}
-
-	public boolean getSorted() {
-		return sorted;
-	}
-
-	public void setSorted(boolean sorted) {
-		this.sorted = sorted;
-	}
-
-	public String getClean() {
-		return clean;
-	}
-
-	public void setClean(String clean) {
-		this.clean = clean;
-	}
-
 	@Override
 	public String toString() {
 		try {

dhp-pace-core/src/main/java/eu/dnetlib/pace/model/RowDataOrderingComparator.java

@@ -13,8 +13,7 @@ import eu.dnetlib.pace.clustering.NGramUtils;
 public class RowDataOrderingComparator implements Comparator<Row> {
 
 	/** The comparator field. */
-	private final int comparatorField;
-	private final int identityFieldPosition;
+	private int comparatorField;
 
 	/**
 	 * Instantiates a new map document comparator.
@@ -22,9 +21,8 @@ public class RowDataOrderingComparator implements Comparator<Row> {
 	 * @param comparatorField
 	 *            the comparator field
 	 */
-	public RowDataOrderingComparator(final int comparatorField, int identityFieldPosition) {
+	public RowDataOrderingComparator(final int comparatorField) {
 		this.comparatorField = comparatorField;
-		this.identityFieldPosition = identityFieldPosition;
 	}
 
 	/*
@@ -53,10 +51,7 @@ public class RowDataOrderingComparator implements Comparator<Row> {
 
 		int res = to1.compareTo(to2);
 		if (res == 0) {
-			res = o1.compareTo(o2);
-			if (res == 0) {
-				return d1.getString(identityFieldPosition).compareTo(d2.getString(identityFieldPosition));
-			}
+			return o1.compareTo(o2);
 		}
 
 		return res;

dhp-pace-core/src/main/java/eu/dnetlib/pace/model/SparkDedupConfig.scala

@@ -0,0 +1,644 @@
+package eu.dnetlib.pace.model
+
+import com.jayway.jsonpath.{Configuration, JsonPath, Option}
+import eu.dnetlib.pace.config.{DedupConfig, Type}
+import eu.dnetlib.pace.tree.support.TreeProcessor
+import eu.dnetlib.pace.util.MapDocumentUtil.truncateValue
+import eu.dnetlib.pace.util.{BlockProcessor, MapDocumentUtil, SparkReporter}
+import org.apache.spark.SparkContext
+import org.apache.spark.rdd.RDD.rddToPairRDDFunctions
+import org.apache.spark.sql.catalyst.encoders.{ExpressionEncoder, RowEncoder}
+import org.apache.spark.sql.{Column, Dataset, Encoder, Encoders, Row, functions}
+import org.apache.spark.sql.catalyst.expressions.{GenericRowWithSchema, Literal}
+import org.apache.spark.sql.expressions.{Aggregator, MutableAggregationBuffer, UserDefinedAggregateFunction, UserDefinedFunction, Window}
+import org.apache.spark.sql.types.{ArrayType, DataType, DataTypes, Metadata, StructField, StructType}
+
+import java.util
+import java.util.function.Predicate
+import java.util.regex.Pattern
+import scala.collection.JavaConverters._
+import scala.collection.mutable
+import org.apache.spark.sql.functions.{col, lit, udf}
+
+import java.util.Collections
+import java.util.stream.Collectors
+
+case class SparkDedupConfig(conf: DedupConfig, numPartitions: Int) extends Serializable {
+
+  private val URL_REGEX: Pattern = Pattern.compile("^\\s*(http|https|ftp)\\://.*")
+
+  private val CONCAT_REGEX: Pattern = Pattern.compile("\\|\\|\\|")
+
+  private val urlFilter = (s: String) => URL_REGEX.matcher(s).matches
+
+  val modelExtractor: (Dataset[String] => Dataset[Row]) = df => {
+
+    df.withColumn("mapDocument", rowFromJsonUDF.apply(df.col(df.columns(0))))
+      .withColumn("identifier", new Column("mapDocument.identifier"))
+      //.repartition(new Column("identifier"))
+      .dropDuplicates("identifier")
+      .select("mapDocument.*")
+
+    df.map(r => rowFromJson(r))(RowEncoder(rowDataType))
+      .dropDuplicates("identifier")
+  }
+
+  val generateClusters: (Dataset[Row] => Dataset[Row]) = df => {
+
+    val df_with_filters = conf.getPace.getModel.asScala.foldLeft(df)((res, fdef) => {
+      if (conf.blacklists.containsKey(fdef.getName)) {
+        res.withColumn(
+          fdef.getName + "_filtered",
+          filterColumnUDF(fdef).apply(new Column(fdef.getName))
+        )
+      } else {
+        res
+      }
+    })
+
+    val df_with_keys = conf
+      .clusterings()
+      .asScala
+      .foldLeft(df_with_filters)((res, cd) => {
+        res.withColumn(
+          cd.getName + "_clustered",
+          functions.explode_outer(
+            clusterValuesUDF(cd).apply(
+              functions.array(
+                cd.getFields.asScala
+                  .map(f => res.col(if (conf.blacklists.containsKey(f)) f.concat("_filtered") else f)): _*
+              )
+            )
+          )
+        )
+      })
+
+    // filter blacklisted values// filter blacklisted values
+    // create one column per cluster prefix// create one column per cluster prefix
+
+    // GROUPING sets approach// GROUPING sets approach
+    val tempTable = this.getClass.getSimpleName + "__generateClusters";
+
+    df_with_keys.createOrReplaceTempView(this.getClass.getSimpleName + "__generateClusters")
+
+    val keys = conf.clusterings().asScala.map(_.getName + "_clustered").mkString(",")
+    val fields = rowDataType.fieldNames.mkString(",")
+
+    //  Using SQL because GROUPING SETS are not available through Scala/Java DSL
+    df_with_keys.sqlContext.sql(
+      ("SELECT coalesce(" + keys + ") as key, sort_array(collect_sort_slice(" + fields + ")) as block FROM " + tempTable + " WHERE coalesce(" + keys + ") IS NOT NULL GROUP BY GROUPING SETS (" + keys + ") HAVING size(block) > 1")
+    )
+
+  }
+
+  val generateClustersWithDFAPI: (Dataset[Row] => Dataset[Row]) = df => {
+
+   System.out.println(conf.getWf.getEntityType + "::" +conf.getWf.getSubEntityType)
+
+    val df_with_filters = conf.getPace.getModel.asScala.foldLeft(df)((res, fdef) => {
+      if (conf.blacklists.containsKey(fdef.getName)) {
+        res.withColumn(
+          fdef.getName + "_filtered",
+          filterColumnUDF(fdef).apply(new Column(fdef.getName))
+        )
+      } else {
+        res
+      }
+    })
+
+    var relBlocks: Dataset[Row] = null
+
+    import scala.collection.JavaConversions._
+
+    for (cd <- conf.clusterings()) {
+      val columns: util.List[Column] = new util.ArrayList[Column](cd.getFields().size)
+
+      for (fName <- cd.getFields()) {
+        if (conf.blacklists.containsKey(fName))
+          columns.add(new Column(fName + "_filtered"))
+        else
+          columns.add(new Column(fName))
+      }
+
+      val tmp: Dataset[Row] = df_with_filters.withColumn("key", functions.explode(clusterValuesUDF(cd).apply(functions.array(columns.asScala: _*))))
+
+
+
+
+       /*.select((Seq(rowDataType.fieldNames: _*) ++ Seq("key")).map(col): _*)
+       .groupByKey(r => r.getAs[String]("key"))(Encoders.STRING)
+        .agg(collectSortSliceAggregator.toColumn)
+        .toDF("key", "block")
+        .select(col("block.block").as("block"))*/
+
+      System.out.println(cd.getName)
+
+      val  ds = tmp.groupBy("key")
+      // .agg(functions.sort_array(collectSortSliceUDAF(rowDataType.fieldNames.map(col): _*)).as("block"))
+       .agg(functions.collect_set(functions.struct(rowDataType.fieldNames.map(col): _*)).as("block"))
+        //.filter(functions.size(new Column("block")).geq(new Literal(2, DataTypes.IntegerType)))
+
+
+      //df_with_filters.printSchema()
+      //ds.printSchema()
+
+      if (relBlocks == null) relBlocks = ds
+      else relBlocks = relBlocks.union(ds)
+    }
+
+   // System.out.println()
+
+    relBlocks
+  }
+
+  val generateClustersWithWindows: (Dataset[Row] => Dataset[Row]) = df => {
+
+    val df_with_filters = conf.getPace.getModel.asScala.foldLeft(df)((res, fdef) => {
+      if (conf.blacklists.containsKey(fdef.getName)) {
+        res.withColumn(
+          fdef.getName + "_filtered",
+          filterColumnUDF(fdef).apply(new Column(fdef.getName))
+        )
+      } else {
+        res
+      }
+    })
+
+    var relBlocks: Dataset[Row] = null
+
+    import scala.collection.JavaConversions._
+
+    for (cd <- conf.clusterings()) {
+      System.out.println(conf.getWf.getEntityType + "::" + conf.getWf.getSubEntityType+ ": " + cd.getName + " " + cd.toString)
+
+      val columns: util.List[Column] = new util.ArrayList[Column](cd.getFields().size)
+
+      for (fName <- cd.getFields()) {
+        if (conf.blacklists.containsKey(fName))
+          columns.add(new Column(fName + "_filtered"))
+        else
+          columns.add(new Column(fName))
+      }
+
+      // Add 'key' column with the value generated by the given clustering definition
+      val ds: Dataset[Row] = df_with_filters.withColumn("key", functions.explode(clusterValuesUDF(cd).apply(functions.array(columns.asScala: _*))))
+        // Add position column having the position of the row within the set of rows having the same key value ordered by the sorting value
+        .withColumn("position", functions.row_number().over(Window.partitionBy("key").orderBy(col(conf.getWf.getOrderField))))
+        // filter out rows with position exceeding the maxqueuesize parameter
+        .filter(col("position").leq(conf.getWf.getQueueMaxSize))
+        .groupBy("key")
+        .agg(functions.collect_set(functions.struct(rowDataType.fieldNames.map(col): _*)).as("block"))
+        .filter(functions.size(new Column("block")).geq(new Literal(2, DataTypes.IntegerType)))
+
+      if (relBlocks == null) relBlocks = ds
+      else relBlocks = relBlocks.union(ds)
+    }
+
+    relBlocks
+  }
+
+  val generateClustersWithDFAPIMerged: (Dataset[Row] => Dataset[Row]) = df => {
+    val df_with_filters = conf.getPace.getModel.asScala.foldLeft(df)((res, fdef) => {
+      if (conf.blacklists.containsKey(fdef.getName)) {
+        res.withColumn(
+          fdef.getName + "_filtered",
+          filterColumnUDF(fdef).apply(new Column(fdef.getName))
+        )
+      } else {
+        res
+      }
+    })
+
+    import scala.collection.JavaConversions._
+
+   val keys = conf.clusterings().foldLeft(null : Column)((res, cd) => {
+     val columns: util.List[Column] = new util.ArrayList[Column](cd.getFields().size)
+
+     for (fName <- cd.getFields()) {
+       if (conf.blacklists.containsKey(fName))
+         columns.add(new Column(fName + "_filtered"))
+       else
+         columns.add(new Column(fName))
+     }
+
+     if (res != null)
+     functions.array_union(res, clusterValuesUDF(cd).apply(functions.array(columns.asScala: _*)))
+     else
+     clusterValuesUDF(cd).apply(functions.array(columns.asScala: _*))
+   })
+
+      val ds: Dataset[Row] = df_with_filters.withColumn("key", functions.explode(keys))
+        .select((Seq(rowDataType.fieldNames: _*) ++ Seq("key")).map(col): _*)
+        .groupByKey(r => r.getAs[String]("key"))(Encoders.STRING)
+        .agg(collectSortSliceAggregator.toColumn)
+        .toDF("key", "block")
+        .select(col("block.block").as("block"))
+
+        /*.groupBy("key")
+        .agg(collectSortSliceUDAF(rowDataType.fieldNames.map(col): _*).as("block"))*/
+        .filter(functions.size(new Column("block")).geq(new Literal(2, DataTypes.IntegerType)))
+
+    ds
+  }
+
+  val generateClustersWithRDDReduction: (Dataset[Row] => Dataset[Row]) = df => {
+    val df_with_filters = conf.getPace.getModel.asScala.foldLeft(df)((res, fdef) => {
+      if (conf.blacklists.containsKey(fdef.getName)) {
+        res.withColumn(
+          fdef.getName + "_filtered",
+          filterColumnUDF(fdef).apply(new Column(fdef.getName))
+        )
+      } else {
+        res
+      }
+    })
+
+    var relBlocks: Dataset[Row] = null
+
+    import scala.collection.JavaConversions._
+
+    for (cd <- conf.clusterings()) {
+      val columns: util.List[Column] = new util.ArrayList[Column](cd.getFields().size)
+
+      for (fName <- cd.getFields()) {
+        if (conf.blacklists.containsKey(fName))
+          columns.add(new Column(fName + "_filtered"))
+        else
+          columns.add(new Column(fName))
+      }
+
+      val ds: Dataset[Row] = df.sparkSession.createDataFrame(df_with_filters.withColumn("key", functions.explode(clusterValuesUDF(cd).apply(functions.array(columns.asScala: _*))))
+        .select(col("key"), functions.array(functions.struct(rowDataType.fieldNames.map(col): _*).as("value")))
+        .rdd.keyBy(_.getString(0))
+        .reduceByKey((a, b) => {
+          val b1 = a.getSeq[Row](1)
+          val b2 = b.getSeq[Row](1)
+
+          if (b1.size + b2.size > conf.getWf.getQueueMaxSize)
+            Row(a.get(0), b1.union(b2).sortBy(_.getString(orderingFieldPosition)).slice(0, conf.getWf.getQueueMaxSize))
+          else
+            Row(a.get(0), b1.union(b2))
+        })
+        .map(_._2)
+        .filter(k => k.getSeq(1).size > 1),
+        new StructType().add(StructField("key", DataTypes.StringType)).add(StructField("block", ArrayType(rowDataType)))
+      )
+
+      if (relBlocks == null) relBlocks = ds
+      else relBlocks = relBlocks.union(ds)
+    }
+
+    relBlocks
+  }
+
+  val printAnalytics: (Dataset[Row] => Dataset[Row]) = df => {
+
+    val df_with_filters = conf.getPace.getModel.asScala.foldLeft(df)((res, fdef) => {
+      if (conf.blacklists.containsKey(fdef.getName)) {
+        res.withColumn(
+          fdef.getName + "_filtered",
+          filterColumnUDF(fdef).apply(new Column(fdef.getName))
+        )
+      } else {
+        res
+      }
+    })
+
+    var relBlocks: Dataset[Row] = null
+
+    import scala.collection.JavaConversions._
+
+    for (cd <- conf.clusterings()) {
+      val columns: util.List[Column] = new util.ArrayList[Column](cd.getFields().size)
+
+      for (fName <- cd.getFields()) {
+        if (conf.blacklists.containsKey(fName))
+          columns.add(new Column(fName + "_filtered"))
+        else
+          columns.add(new Column(fName))
+      }
+
+      // Add 'key' column with the value generated by the given clustering definition
+      val ds: Dataset[Row] = df_with_filters.withColumn("key", functions.explode(clusterValuesUDF(cd).apply(functions.array(columns.asScala: _*))))
+        // Add position column having the position of the row within the set of rows having the same key value ordered by the sorting value
+        .withColumn("position", functions.row_number().over(Window.partitionBy("key").orderBy(conf.getWf.getOrderField)))
+        // filter out rows with position exceeding the maxqueuesize parameter
+        .filter(col("position").lt(conf.getWf.getQueueMaxSize))
+
+
+      // inner join to compute all combination of rows to compare
+      // note the condition on position to obtain 'windowing': given a row this is compared at most with the next
+      // SlidingWindowSize rows following the sort order
+      val dsWithMatch = ds.as("l").join(ds.as("r"),
+        col("l.key").equalTo(col("r.key")),
+        "inner"
+      )
+        .filter((col("l.position").lt(col("r.position")))
+          && (col("r.position").lt(col("l.position").plus(lit(conf.getWf.getSlidingWindowSize)))))
+        // Add match column with the result of comparison
+      // dsWithMatch.show(false)
+
+      if (relBlocks == null)
+        relBlocks = dsWithMatch
+      else
+        relBlocks = relBlocks.union(dsWithMatch)
+    }
+
+    System.out.println(conf.getWf.getEntityType + "::" + conf.getWf.getSubEntityType)
+    System.out.println("Total number of comparations: " + relBlocks.count())
+
+
+    df
+  }
+
+
+  val generateAndProcessClustersWithJoins: (Dataset[Row] => Dataset[Row]) = df => {
+
+    val df_with_filters = conf.getPace.getModel.asScala.foldLeft(df)((res, fdef) => {
+      if (conf.blacklists.containsKey(fdef.getName)) {
+        res.withColumn(
+          fdef.getName + "_filtered",
+          filterColumnUDF(fdef).apply(new Column(fdef.getName))
+        )
+      } else {
+        res
+      }
+    })
+
+    var relBlocks: Dataset[Row] = null
+
+    import scala.collection.JavaConversions._
+
+    for (cd <- conf.clusterings()) {
+      val columns: util.List[Column] = new util.ArrayList[Column](cd.getFields().size)
+
+      for (fName <- cd.getFields()) {
+        if (conf.blacklists.containsKey(fName))
+          columns.add(new Column(fName + "_filtered"))
+        else
+          columns.add(new Column(fName))
+      }
+
+      // Add 'key' column with the value generated by the given clustering definition
+      val ds: Dataset[Row] = df_with_filters.withColumn("key", functions.explode(clusterValuesUDF(cd).apply(functions.array(columns.asScala: _*))))
+        // Add position column having the position of the row within the set of rows having the same key value ordered by the sorting value
+        .withColumn("position", functions.row_number().over(Window.partitionBy("key").orderBy(conf.getWf.getOrderField)))
+        // filter out rows with position exceeding the maxqueuesize parameter
+        .filter(col("position").lt(conf.getWf.getQueueMaxSize))
+
+
+      // inner join to compute all combination of rows to compare
+      // note the condition on position to obtain 'windowing': given a row this is compared at most with the next
+      // SlidingWindowSize rows following the sort order
+      val dsWithMatch = ds.as("l").join(ds.as("r"),
+        col("l.key").equalTo(col("r.key")),
+        "inner"
+        )
+        .filter((col("l.position").lt(col("r.position")))
+          && (col("r.position").lt(col("l.position").plus(lit(conf.getWf.getSlidingWindowSize)))))
+        // Add match column with the result of comparison
+        .withColumn("match", udf[Boolean, Row, Row]((a, b) => {
+          val treeProcessor = new TreeProcessor(conf)
+
+         treeProcessor.compare(a, b)
+        }).apply(functions.struct(rowDataType.fieldNames.map(s => col("l.".concat(s))): _*), functions.struct(rowDataType.fieldNames.map(s => col("r.".concat(s))): _*)))
+        .filter(col("match").equalTo(true))
+        .select(col("l.identifier").as("from"), col("r.identifier").as("to"))
+
+     // dsWithMatch.show(false)
+
+      if (relBlocks == null)
+        relBlocks = dsWithMatch
+      else
+        relBlocks = relBlocks.union(dsWithMatch)
+    }
+
+    val res = relBlocks
+      //.select(col("l.identifier").as("from"), col("r.identifier").as("to"))
+      //.repartition()
+      .distinct()
+
+   // res.show(false)
+    res.select(functions.struct("from", "to"))
+  }
+
+  val processClusters: (Dataset[Row] => Dataset[Row]) = df => {
+
+    val entity = conf.getWf.getEntityType
+
+    df.filter(functions.size(new Column("block")).geq(new Literal(2, DataTypes.IntegerType)))
+      .withColumn("relations", processBlock(df.sqlContext.sparkContext).apply(new Column("block")))
+      .select(functions.explode(new Column("relations")).as("relation"))
+      //.repartition(new Column("relation"))
+      .dropDuplicates("relation")
+  }
+
+  val rowDataType: StructType = {
+//    val unordered = conf.getPace.getModel.asScala.foldLeft(
+//      new StructType()
+//    )((resType, fdef) => {
+//      resType.add(fdef.getType match {
+//        case Type.List | Type.JSON =>
+//          StructField(fdef.getName, DataTypes.createArrayType(DataTypes.StringType), true, Metadata.empty)
+//        case Type.DoubleArray =>
+//          StructField(fdef.getName, DataTypes.createArrayType(DataTypes.DoubleType), true, Metadata.empty)
+//        case _ =>
+//          StructField(fdef.getName, DataTypes.StringType, true, Metadata.empty)
+//      })
+//    })
+//
+//    conf.getPace.getModel.asScala.filterNot(_.getName.equals(conf.getWf.getOrderField)).foldLeft(
+//      new StructType()
+//        .add(unordered(conf.getWf.getOrderField))
+//        .add(StructField("identifier", DataTypes.StringType, false, Metadata.empty))
+//    )((resType, fdef) => resType.add(unordered(fdef.getName)))
+
+    val identifier = new FieldDef()
+    identifier.setName("identifier")
+    identifier.setType(Type.String)
+
+    (conf.getPace.getModel.asScala ++ Seq(identifier)).sortBy(_.getName)
+      .foldLeft(
+          new StructType()
+        )((resType, fdef) => {
+          resType.add(fdef.getType match {
+            case Type.List | Type.JSON =>
+              StructField(fdef.getName, DataTypes.createArrayType(DataTypes.StringType), true, Metadata.empty)
+            case Type.DoubleArray =>
+              StructField(fdef.getName, DataTypes.createArrayType(DataTypes.DoubleType), true, Metadata.empty)
+            case _ =>
+              StructField(fdef.getName, DataTypes.StringType, true, Metadata.empty)
+          })
+        })
+
+
+
+  }
+
+  val identityFieldPosition: Int = rowDataType.fieldIndex("identifier")
+
+  val orderingFieldPosition: Int = rowDataType.fieldIndex(conf.getWf.getOrderField)
+
+  def rowFromJson(json: String) : Row = {
+    val documentContext =
+      JsonPath.using(Configuration.defaultConfiguration.addOptions(Option.SUPPRESS_EXCEPTIONS)).parse(json)
+    val values = new Array[Any](rowDataType.size)
+
+    values(identityFieldPosition) = MapDocumentUtil.getJPathString(conf.getWf.getIdPath, documentContext)
+
+    rowDataType.fieldNames.zipWithIndex.foldLeft(values) {
+      case ((res, (fname, index))) => {
+        val fdef = conf.getPace.getModelMap.get(fname)
+
+        if (fdef != null) {
+          res(index) = fdef.getType match {
+            case Type.String | Type.Int =>
+              MapDocumentUtil.truncateValue(
+                MapDocumentUtil.getJPathString(fdef.getPath, documentContext),
+                fdef.getLength
+              )
+
+            case Type.URL =>
+              var uv = MapDocumentUtil.getJPathString(fdef.getPath, documentContext)
+              if (!urlFilter(uv)) uv = ""
+              uv
+
+            case Type.List | Type.JSON =>
+              MapDocumentUtil.truncateList(
+                MapDocumentUtil.getJPathList(fdef.getPath, documentContext, fdef.getType),
+                fdef.getSize
+              ).toArray
+
+            case Type.StringConcat =>
+              val jpaths = CONCAT_REGEX.split(fdef.getPath)
+
+              truncateValue(
+                jpaths
+                  .map(jpath => MapDocumentUtil.getJPathString(jpath, documentContext))
+                  .mkString(" "),
+                fdef.getLength
+              )
+
+            case Type.DoubleArray =>
+              MapDocumentUtil.getJPathArray(fdef.getPath, json)
+          }
+        }
+
+        res
+      }
+    }
+
+    new GenericRowWithSchema(values, rowDataType)
+  }
+
+  val rowFromJsonUDF = udf(rowFromJson(_), rowDataType)
+
+  def filterColumnUDF(fdef: FieldDef): UserDefinedFunction = {
+
+    val blacklist: Predicate[String] = conf.blacklists().get(fdef.getName)
+
+    if (blacklist == null) {
+      throw new IllegalArgumentException("Column: " + fdef.getName + " does not have any filter")
+    } else {
+      fdef.getType match {
+        case Type.List | Type.JSON =>
+          udf[Array[String], Array[String]](values => {
+            values.filter((v: String) => !blacklist.test(v))
+          })
+
+        case _ =>
+          udf[String, String](v => {
+            if (blacklist.test(v)) ""
+            else v
+          })
+      }
+    }
+  }
+
+  def clusterValuesUDF(cd: ClusteringDef) = {
+    udf[mutable.WrappedArray[String], mutable.WrappedArray[Object]](values => {
+      values.flatMap(f => cd.clusteringFunction().apply(conf, Seq(f.toString).asJava).asScala).map(cd.getName.concat(_))
+    })
+  }
+
+  def processBlock(implicit sc: SparkContext) = {
+    val accumulators = SparkReporter.constructAccumulator(conf, sc)
+
+    udf[Array[Tuple2[String, String]], mutable.WrappedArray[Row]](block => {
+      val reporter = new SparkReporter(accumulators)
+
+      val mapDocuments = block.asJava.stream
+        .sorted(new RowDataOrderingComparator(orderingFieldPosition))
+        .limit(conf.getWf.getQueueMaxSize)
+        .collect(Collectors.toList[Row]())
+
+      new BlockProcessor(conf, identityFieldPosition, orderingFieldPosition).processSortedRows(mapDocuments, reporter)
+
+      reporter.getRelations.asScala.toArray
+    }).asNondeterministic()
+  }
+
+  val collectSortSliceAggregator : Aggregator[Row,Seq[Row], Row] = new Aggregator[Row, Seq[Row], Row] () {
+    override def zero: Seq[Row] = Seq[Row]()
+
+
+    override def reduce(buffer: Seq[Row], input: Row): Seq[Row] = {
+      merge(buffer, Seq(input))
+    }
+
+    override def merge(buffer: Seq[Row], toMerge: Seq[Row]): Seq[Row] = {
+      val newBlock = buffer ++ toMerge
+
+      if (newBlock.size > conf.getWf.getQueueMaxSize)
+        newBlock.sortBy(_.getString(orderingFieldPosition)).slice(0, conf.getWf.getQueueMaxSize)
+      else
+        newBlock
+    }
+
+    override def finish(reduction: Seq[Row]): Row = {
+      Row(reduction.toArray)
+    }
+
+    override def bufferEncoder: Encoder[Seq[Row]] = Encoders.kryo[Seq[Row]]
+
+    override def outputEncoder: Encoder[Row] = RowEncoder.apply(new StructType().add("block", DataTypes.createArrayType(rowDataType), nullable = true))
+  }
+
+  val collectSortSliceUDAF : UserDefinedAggregateFunction = new UserDefinedAggregateFunction {
+    override def inputSchema: StructType = rowDataType
+
+    override def bufferSchema: StructType = {
+      new StructType().add("block", DataTypes.createArrayType(rowDataType), nullable = true)
+    }
+
+    override def dataType: DataType = DataTypes.createArrayType(rowDataType)
+
+    override def deterministic: Boolean = true
+
+    override def initialize(buffer: MutableAggregationBuffer): Unit = {
+      buffer(0) = Seq[Row]()
+    }
+
+    override def update(buffer: MutableAggregationBuffer, input: Row): Unit = {
+      val newBlock = buffer.getSeq[Row](0) ++ Seq(input)
+
+      if (newBlock.size > conf.getWf.getQueueMaxSize)
+        buffer(0) = newBlock.sortBy(_.getString(orderingFieldPosition)).slice(0, conf.getWf.getQueueMaxSize)
+      else
+        buffer(0) = newBlock
+    }
+
+    override def merge(buffer: MutableAggregationBuffer, row: Row): Unit = {
+      val newBlock = buffer.getSeq[Row](0) ++ row.getSeq[Row](0)
+
+      if (newBlock.size > conf.getWf.getQueueMaxSize)
+        buffer(0) = newBlock.sortBy(_.getString(orderingFieldPosition)).slice(0, conf.getWf.getQueueMaxSize)
+      else
+        buffer(0) = newBlock
+    }
+
+    override def evaluate(buffer: Row): Any = {
+      buffer.getSeq[Row](0)
+    }
+  }
+}

dhp-pace-core/src/main/java/eu/dnetlib/pace/model/SparkDeduper.scala

@@ -1,157 +0,0 @@
-package eu.dnetlib.pace.model
-
-import eu.dnetlib.pace.config.{DedupConfig, Type}
-import eu.dnetlib.pace.util.{BlockProcessor, SparkReporter}
-import org.apache.spark.SparkContext
-import org.apache.spark.sql.catalyst.expressions.Literal
-import org.apache.spark.sql.expressions._
-import org.apache.spark.sql.functions.{col, desc, expr, lit, udf}
-import org.apache.spark.sql.types._
-import org.apache.spark.sql.{Column, Dataset, Row, SaveMode, functions}
-
-import java.util.function.Predicate
-import java.util.stream.Collectors
-import scala.collection.JavaConversions._
-import scala.collection.JavaConverters._
-import scala.collection.mutable
-case class SparkDeduper(conf: DedupConfig) extends Serializable {
-
-  val model: SparkModel = SparkModel(conf)
-
-  val dedup: (Dataset[Row] => Dataset[Row]) = df => {
-    df.transform(filterAndCleanup)
-      .transform(generateClustersWithCollect)
-      .transform(processBlocks)
-  }
-
-
-  val filterAndCleanup: (Dataset[Row] => Dataset[Row]) = df => {
-    val df_with_filters = conf.getPace.getModel.asScala.foldLeft(df)((res, fdef) => {
-      if (conf.blacklists.containsKey(fdef.getName)) {
-        res.withColumn(
-          fdef.getName + "_filtered",
-          filterColumnUDF(fdef).apply(new Column(fdef.getName))
-        )
-      } else {
-        res
-      }
-    })
-
-    df_with_filters
-  }
-
-  def filterColumnUDF(fdef: FieldDef): UserDefinedFunction = {
-    val blacklist: Predicate[String] = conf.blacklists().get(fdef.getName)
-
-    if (blacklist == null) {
-      throw new IllegalArgumentException("Column: " + fdef.getName + " does not have any filter")
-    } else {
-      fdef.getType match {
-        case Type.List | Type.JSON =>
-          udf[Array[String], Array[String]](values => {
-            values.filter((v: String) => !blacklist.test(v))
-          })
-
-        case _ =>
-          udf[String, String](v => {
-            if (blacklist.test(v)) ""
-            else v
-          })
-      }
-    }
-  }
-
-  val generateClustersWithCollect: (Dataset[Row] => Dataset[Row]) = df_with_filters => {
-    var df_with_clustering_keys: Dataset[Row] = null
-
-    for ((cd, idx) <- conf.clusterings().zipWithIndex) {
-      val inputColumns = cd.getFields().foldLeft(Seq[Column]())((acc, fName) => {
-        val column = if (conf.blacklists.containsKey(fName))
-          Seq(col(fName + "_filtered"))
-        else
-          Seq(col(fName))
-
-        acc ++ column
-      })
-
-      // Add 'key' column with the value generated by the given clustering definition
-      val ds: Dataset[Row] = df_with_filters
-        .withColumn("clustering", lit(cd.getName + "::" + idx))
-        .withColumn("key", functions.explode(clusterValuesUDF(cd).apply(functions.array(inputColumns: _*))))
-        // Add position column having the position of the row within the set of rows having the same key value ordered by the sorting value
-        .withColumn("position", functions.row_number().over(Window.partitionBy("key").orderBy(col(model.orderingFieldName), col(model.identifierFieldName))))
-       // .withColumn("count", functions.max("position").over(Window.partitionBy("key").orderBy(col(model.orderingFieldName), col(model.identifierFieldName)).rowsBetween(Window.unboundedPreceding,Window.unboundedFollowing) ))
-       // .filter("count > 1")
-
-      if (df_with_clustering_keys == null)
-        df_with_clustering_keys = ds
-      else
-        df_with_clustering_keys = df_with_clustering_keys.union(ds)
-    }
-
-    //TODO: analytics
-    /*df_with_clustering_keys.groupBy(col("clustering"), col("key"))
-      .agg(expr("max(count) AS size"))
-      .orderBy(desc("size"))
-      .show*/
-
-    val df_with_blocks = df_with_clustering_keys
-      // split the clustering block into smaller blocks of queuemaxsize
-      .groupBy(col("clustering"), col("key"), functions.floor(col("position").divide(lit(conf.getWf.getQueueMaxSize))))
-      .agg(functions.collect_set(functions.struct(model.schema.fieldNames.map(col): _*)).as("block"))
-      .filter(functions.size(new Column("block")).gt(1))
-       .union(
-        //adjacency blocks
-        df_with_clustering_keys
-          // filter out leading and trailing elements
-          .filter(col("position").gt(conf.getWf.getSlidingWindowSize/2))
-          //.filter(col("position").lt(col("count").minus(conf.getWf.getSlidingWindowSize/2)))
-          // create small blocks of records on "the border" of maxqueuesize: getSlidingWindowSize/2 elements before and after
-          .filter(
-            col("position").mod(conf.getWf.getQueueMaxSize).lt(conf.getWf.getSlidingWindowSize/2) // slice of the start of block
-            || col("position").mod(conf.getWf.getQueueMaxSize).gt(conf.getWf.getQueueMaxSize - (conf.getWf.getSlidingWindowSize/2)) //slice of the end of the block
-          )
-          .groupBy(col("clustering"), col("key"), functions.floor((col("position") + lit(conf.getWf.getSlidingWindowSize/2)).divide(lit(conf.getWf.getQueueMaxSize))))
-          .agg(functions.collect_set(functions.struct(model.schema.fieldNames.map(col): _*)).as("block"))
-          .filter(functions.size(new Column("block")).gt(1))
-      )
-
-    df_with_blocks
-  }
-
-  def clusterValuesUDF(cd: ClusteringDef) = {
-    udf[mutable.WrappedArray[String], mutable.WrappedArray[Any]](values => {
-      val valueList = values.flatMap {
-        case a: mutable.WrappedArray[Any] => a.map(_.toString)
-        case s: Any => Seq(s.toString)
-      }.asJava;
-
-      mutable.WrappedArray.make(cd.clusteringFunction().apply(conf, valueList).toArray())
-
-    })
-  }
-
-  val processBlocks: (Dataset[Row] => Dataset[Row]) = df => {
-    df.filter(functions.size(new Column("block")).geq(new Literal(2, DataTypes.IntegerType)))
-      .withColumn("relations", processBlock(df.sqlContext.sparkContext).apply(new Column("block")))
-      .select(functions.explode(new Column("relations")).as("relation"))
-  }
-
-  def processBlock(implicit sc: SparkContext) = {
-    val accumulators = SparkReporter.constructAccumulator(conf, sc)
-
-    udf[Array[(String, String)], mutable.WrappedArray[Row]](block => {
-      val reporter = new SparkReporter(accumulators)
-
-      val mapDocuments = block.asJava.stream()
-        .sorted(new RowDataOrderingComparator(model.orderingFieldPosition, model.identityFieldPosition))
-        .limit(conf.getWf.getQueueMaxSize)
-        .collect(Collectors.toList[Row]())
-
-      new BlockProcessor(conf, model.identityFieldPosition, model.orderingFieldPosition).processSortedRows(mapDocuments, reporter)
-
-      reporter.getRelations.asScala.toArray
-    }).asNondeterministic()
-  }
-
-}

dhp-pace-core/src/main/java/eu/dnetlib/pace/model/SparkModel.scala

@@ -1,150 +0,0 @@
-package eu.dnetlib.pace.model
-
-import com.jayway.jsonpath.{Configuration, JsonPath}
-import eu.dnetlib.pace.common.AbstractPaceFunctions
-import eu.dnetlib.pace.config.{DedupConfig, Type}
-import eu.dnetlib.pace.util.MapDocumentUtil
-import org.apache.commons.lang3.StringUtils
-import org.apache.spark.sql.catalyst.encoders.RowEncoder
-import org.apache.spark.sql.catalyst.expressions.GenericRowWithSchema
-import org.apache.spark.sql.types.{DataTypes, Metadata, StructField, StructType}
-import org.apache.spark.sql.{Dataset, Row}
-
-import java.util.Locale
-import java.util.regex.Pattern
-import scala.collection.JavaConverters._
-
-case class SparkModel(conf: DedupConfig) {
-  private val URL_REGEX: Pattern = Pattern.compile("^\\s*(http|https|ftp)\\://.*")
-
-  private val CONCAT_REGEX: Pattern = Pattern.compile("\\|\\|\\|")
-
-  val identifierFieldName = "identifier"
-
-  val orderingFieldName = if (!conf.getWf.getOrderField.isEmpty) conf.getWf.getOrderField else identifierFieldName
-
-  val schema: StructType = {
-    // create an implicit identifier field
-    val identifier = new FieldDef()
-    identifier.setName(identifierFieldName)
-    identifier.setType(Type.String)
-
-    // Construct a Spark StructType representing the schema of the model
-    (Seq(identifier) ++ conf.getPace.getModel.asScala)
-      .foldLeft(
-        new StructType()
-      )((resType, fieldDef) => {
-        resType.add(fieldDef.getType match {
-          case Type.List | Type.JSON =>
-            StructField(fieldDef.getName, DataTypes.createArrayType(DataTypes.StringType), true, Metadata.empty)
-          case Type.DoubleArray =>
-            StructField(fieldDef.getName, DataTypes.createArrayType(DataTypes.DoubleType), true, Metadata.empty)
-          case _ =>
-            StructField(fieldDef.getName, DataTypes.StringType, true, Metadata.empty)
-        })
-      })
-
-
-  }
-
-  val identityFieldPosition: Int = schema.fieldIndex(identifierFieldName)
-
-  val orderingFieldPosition: Int = schema.fieldIndex(orderingFieldName)
-
-  val parseJsonDataset: (Dataset[String] => Dataset[Row]) = df => {
-    df.map(r => rowFromJson(r))(RowEncoder(schema))
-  }
-
-  def rowFromJson(json: String): Row = {
-    val documentContext =
-      JsonPath.using(Configuration.defaultConfiguration.addOptions(com.jayway.jsonpath.Option.SUPPRESS_EXCEPTIONS)).parse(json)
-    val values = new Array[Any](schema.size)
-
-    values(identityFieldPosition) = MapDocumentUtil.getJPathString(conf.getWf.getIdPath, documentContext)
-
-    schema.fieldNames.zipWithIndex.foldLeft(values) {
-      case ((res, (fname, index))) =>
-        val fdef = conf.getPace.getModelMap.get(fname)
-
-        if (fdef != null) {
-          res(index) = fdef.getType match {
-            case Type.String | Type.Int =>
-              MapDocumentUtil.truncateValue(
-                MapDocumentUtil.getJPathString(fdef.getPath, documentContext),
-                fdef.getLength
-              )
-
-            case Type.URL =>
-              var uv = MapDocumentUtil.getJPathString(fdef.getPath, documentContext)
-              if (!URL_REGEX.matcher(uv).matches)
-                uv = ""
-              uv
-
-            case Type.List | Type.JSON =>
-              MapDocumentUtil.truncateList(
-                MapDocumentUtil.getJPathList(fdef.getPath, documentContext, fdef.getType),
-                fdef.getSize
-              ).asScala
-
-            case Type.StringConcat =>
-              val jpaths = CONCAT_REGEX.split(fdef.getPath)
-
-              MapDocumentUtil.truncateValue(
-                jpaths
-                  .map(jpath => MapDocumentUtil.getJPathString(jpath, documentContext))
-                  .mkString(" "),
-                fdef.getLength
-              )
-
-            case Type.DoubleArray =>
-              MapDocumentUtil.getJPathArray(fdef.getPath, json)
-          }
-
-          val filter = fdef.getFilter
-
-          if (StringUtils.isNotBlank(fdef.getClean)) {
-            res(index) = res(index) match {
-              case x: Seq[String] => x.map(clean(_, fdef.getClean)).toSeq
-              case _ => clean(res(index).toString, fdef.getClean)
-            }
-          }
-
-          if (filter != null && !filter.isEmpty) {
-            res(index) = res(index) match {
-              case x: String if filter.contains(x.toLowerCase(Locale.ROOT)) => null
-              case x: Seq[String] => x.filter(s => !filter.contains(s.toLowerCase(Locale.ROOT))).toSeq
-              case _ => res(index)
-            }
-          }
-
-          if (fdef.getSorted) {
-            res(index) = res(index) match {
-              case x: Seq[String] => x.sorted.toSeq
-              case _ => res(index)
-            }
-          }
-        }
-
-        res
-    }
-
-    new GenericRowWithSchema(values, schema)
-  }
-
-  def clean(value: String, cleantype: String) : String = {
-    val res = cleantype match {
-      case "title" => AbstractPaceFunctions.cleanup(value)
-      case _ => value
-    }
-
-//    if (!res.equals(AbstractPaceFunctions.normalize(value))) {
-//      println(res)
-//      println(AbstractPaceFunctions.normalize(value))
-//      println()
-//    }
-
-    res
-  }
-
-}
-

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

@@ -23,6 +23,7 @@ public class AuthorsMatch extends AbstractListComparator {
 	private String MODE; // full or surname
 	private int SIZE_THRESHOLD;
 	private String TYPE; // count or percentage
+	private int common;
 
 	public AuthorsMatch(Map<String, String> params) {
 		super(params, new com.wcohen.ss.JaroWinkler());
@@ -34,6 +35,7 @@ public class AuthorsMatch extends AbstractListComparator {
 		FULLNAME_THRESHOLD = Double.parseDouble(params.getOrDefault("fullname_th", "0.9"));
 		SIZE_THRESHOLD = Integer.parseInt(params.getOrDefault("size_th", "20"));
 		TYPE = params.getOrDefault("type", "percentage");
+		common = 0;
 	}
 
 	protected AuthorsMatch(double w, AbstractStringDistance ssalgo) {
@@ -42,27 +44,22 @@ public class AuthorsMatch extends AbstractListComparator {
 
 	@Override
 	public double compare(final List<String> a, final List<String> b, final Config conf) {
+
 		if (a.isEmpty() || b.isEmpty())
 			return -1;
 
 		if (a.size() > SIZE_THRESHOLD || b.size() > SIZE_THRESHOLD)
 			return 1.0;
 
-		int maxMiss = Integer.MAX_VALUE;
+		List<Person> aList = a.stream().map(author -> new Person(author, false)).collect(Collectors.toList());
 		List<Person> bList = b.stream().map(author -> new Person(author, false)).collect(Collectors.toList());
 
-		Double threshold = getDoubleParam("threshold");
-
-		if (threshold != null && threshold >= 0.0 && threshold <= 1.0 && a.size() == b.size()) {
-			maxMiss = (int) Math.floor((1 - threshold) * Math.max(a.size(), b.size()));
-		}
-
-		int common = 0;
+		common = 0;
 		// compare each element of List1 with each element of List2
-		for (int i = 0; i < a.size(); i++) {
-			Person p1 = new Person(a.get(i), false);
+		for (Person p1 : aList)
 
 			for (Person p2 : bList) {
+
 				// both persons are inaccurate
 				if (!p1.isAccurate() && !p2.isAccurate()) {
 					// compare just normalized fullnames
@@ -121,15 +118,11 @@ public class AuthorsMatch extends AbstractListComparator {
 					}
 
 				}
-			}
 
-			if (i - common > maxMiss) {
-				return 0.0;
 			}
-		}
 
 		// normalization factor to compute the score
-		int normFactor = a.size() == b.size() ? a.size() : (a.size() + b.size() - common);
+		int normFactor = aList.size() == bList.size() ? aList.size() : (aList.size() + bList.size() - common);
 
 		if (TYPE.equals("percentage")) {
 			return (double) common / normFactor;

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

@@ -1,8 +1,11 @@
 
 package eu.dnetlib.pace.tree;
 
+import java.util.List;
 import java.util.Map;
 
+import com.google.common.base.Joiner;
+
 import eu.dnetlib.pace.config.Config;
 import eu.dnetlib.pace.tree.support.AbstractStringComparator;
 import eu.dnetlib.pace.tree.support.ComparatorClass;

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

@@ -25,7 +25,6 @@ public class InstanceTypeMatch extends AbstractListComparator {
 		translationMap.put("Conference object", "*");
 		translationMap.put("Other literature type", "*");
 		translationMap.put("Unknown", "*");
-		translationMap.put("UNKNOWN", "*");
 
 		// article types
 		translationMap.put("Article", "Article");
@@ -77,4 +76,5 @@ public class InstanceTypeMatch extends AbstractListComparator {
 	protected double normalize(final double d) {
 		return d;
 	}
+
 }

dhp-pace-core/src/main/java/eu/dnetlib/pace/tree/Level2JaroWinkler.java

@@ -5,6 +5,7 @@ import java.util.Map;
 
 import com.wcohen.ss.AbstractStringDistance;
 
+import eu.dnetlib.pace.tree.support.AbstractComparator;
 import eu.dnetlib.pace.tree.support.AbstractStringComparator;
 import eu.dnetlib.pace.tree.support.ComparatorClass;
 

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

@@ -3,7 +3,6 @@ package eu.dnetlib.pace.tree;
 
 import java.util.Map;
 
-import org.apache.commons.lang3.StringUtils;
 import org.apache.commons.logging.Log;
 import org.apache.commons.logging.LogFactory;
 
@@ -31,25 +30,16 @@ public class LevensteinTitle extends AbstractStringComparator {
 	}
 
 	@Override
-	public double distance(final String ca, final String cb, final Config conf) {
+	public double distance(final String a, final String b, final Config conf) {
+		final String ca = cleanup(a);
+		final String cb = cleanup(b);
+
 		final boolean check = checkNumbers(ca, cb);
 
 		if (check)
 			return 0.5;
 
-		Double threshold = getDoubleParam("threshold");
-
-		// reduce Levenshtein algo complexity when target threshold is known
-		if (threshold != null && threshold >= 0.0 && threshold <= 1.0) {
-			int maxdistance = (int) Math.floor((1 - threshold) * Math.max(ca.length(), cb.length()));
-			int score = StringUtils.getLevenshteinDistance(ca, cb, maxdistance);
-			if (score == -1) {
-				return 0;
-			}
-			return normalize(score, ca.length(), cb.length());
-		} else {
-			return normalize(StringUtils.getLevenshteinDistance(ca, cb), ca.length(), cb.length());
-		}
+		return normalize(ssalgo.score(ca, cb), ca.length(), cb.length());
 	}
 
 	private double normalize(final double score, final int la, final int lb) {

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

@@ -1,29 +0,0 @@
-
-package eu.dnetlib.pace.tree;
-
-import java.util.Map;
-
-import eu.dnetlib.pace.config.Config;
-import eu.dnetlib.pace.tree.support.AbstractStringComparator;
-import eu.dnetlib.pace.tree.support.ComparatorClass;
-
-@ComparatorClass("maxLengthMatch")
-public class MaxLengthMatch extends AbstractStringComparator {
-
-	private final int limit;
-
-	public MaxLengthMatch(Map<String, String> params) {
-		super(params);
-
-		limit = Integer.parseInt(params.getOrDefault("limit", "200"));
-	}
-
-	@Override
-	public double compare(String a, String b, final Config conf) {
-		return a.length() < limit && b.length() < limit ? 1.0 : -1.0;
-	}
-
-	protected String toString(final Object object) {
-		return toFirstString(object);
-	}
-}

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

@@ -4,6 +4,7 @@ package eu.dnetlib.pace.tree;
 import java.util.Map;
 
 import eu.dnetlib.pace.config.Config;
+import eu.dnetlib.pace.tree.support.AbstractComparator;
 import eu.dnetlib.pace.tree.support.AbstractStringComparator;
 import eu.dnetlib.pace.tree.support.ComparatorClass;
 

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

@@ -4,6 +4,7 @@ package eu.dnetlib.pace.tree;
 import java.util.Map;
 
 import eu.dnetlib.pace.config.Config;
+import eu.dnetlib.pace.tree.support.AbstractComparator;
 import eu.dnetlib.pace.tree.support.AbstractStringComparator;
 import eu.dnetlib.pace.tree.support.ComparatorClass;
 

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

@@ -4,6 +4,8 @@ package eu.dnetlib.pace.tree;
 import java.util.List;
 import java.util.Map;
 
+import com.google.common.collect.Lists;
+
 import eu.dnetlib.pace.config.Config;
 import eu.dnetlib.pace.tree.support.AbstractListComparator;
 import eu.dnetlib.pace.tree.support.ComparatorClass;

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

@@ -4,6 +4,7 @@ package eu.dnetlib.pace.tree;
 import java.util.Map;
 
 import eu.dnetlib.pace.config.Config;
+import eu.dnetlib.pace.tree.support.AbstractComparator;
 import eu.dnetlib.pace.tree.support.AbstractStringComparator;
 import eu.dnetlib.pace.tree.support.ComparatorClass;
 
@@ -43,25 +44,22 @@ public class StringContainsMatch extends AbstractStringComparator {
 			STRING = STRING.toLowerCase();
 		}
 
-		if (AGGREGATOR != null) {
-			switch (AGGREGATOR) {
-				case "AND":
-					if (ca.contains(STRING) && cb.contains(STRING))
-						return 1.0;
-					break;
-				case "OR":
-					if (ca.contains(STRING) || cb.contains(STRING))
-						return 1.0;
-					break;
-				case "XOR":
-					if (ca.contains(STRING) ^ cb.contains(STRING))
-						return 1.0;
-					break;
-				default:
-					return 0.0;
-			}
+		switch (AGGREGATOR) {
+			case "AND":
+				if (ca.contains(STRING) && cb.contains(STRING))
+					return 1.0;
+				break;
+			case "OR":
+				if (ca.contains(STRING) || cb.contains(STRING))
+					return 1.0;
+				break;
+			case "XOR":
+				if (ca.contains(STRING) ^ cb.contains(STRING))
+					return 1.0;
+				break;
+			default:
+				return 0.0;
 		}
-
 		return 0.0;
 	}
 }

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

@@ -1,6 +1,7 @@
 
 package eu.dnetlib.pace.tree.support;
 
+import java.util.Collections;
 import java.util.List;
 import java.util.Map;
 
@@ -127,14 +128,4 @@ public abstract class AbstractComparator<T> extends AbstractPaceFunctions implem
 		return this.weight;
 	}
 
-	public Double getDoubleParam(String name) {
-		String svalue = params.get(name);
-
-		try {
-			return Double.parseDouble(svalue);
-		} catch (Throwable t) {
-		}
-
-		return null;
-	}
 }

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

@@ -4,9 +4,11 @@ package eu.dnetlib.pace.tree.support;
 import java.util.List;
 import java.util.Map;
 
+import com.google.common.collect.Lists;
 import com.wcohen.ss.AbstractStringDistance;
 
 import eu.dnetlib.pace.config.Config;
+import eu.dnetlib.pace.config.Type;
 
 abstract public class AbstractListComparator extends AbstractComparator<List<String>> {
 	protected AbstractListComparator(Map<String, String> params) {