andreas.czerniak
/
BrBETA_dnet-hadoop
forked from D-Net/dnet-hadoop
1
1
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Merge branch 'master' of code-repo.d4science.org:D-Net/dnet-hadoop

This commit is contained in:
Sandro La Bruzzo 2023-12-18 11:47:17 +01:00
parent 1f1a6a5f5f c4ec35b6cd
commit 1fbd4325f5
302 changed files with 12684 additions and 4060 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
dhp-common/src/main/java/eu/dnetlib/dhp/common/Constants.java
View File

@ -51,6 +51,7 @@ 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";

53
dhp-common/src/main/java/eu/dnetlib/dhp/common/api/InputStreamRequestBody.java
View File

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

8
dhp-common/src/main/java/eu/dnetlib/dhp/common/api/MissingConceptDoiException.java
View File

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

365
dhp-common/src/main/java/eu/dnetlib/dhp/common/api/ZenodoAPIClient.java
View File

@ -1,365 +0,0 @@
package eu.dnetlib.dhp.common.api;
import java.io.*;
import java.io.IOException;
import java.net.HttpURLConnection;
import java.net.URL;
import java.util.concurrent.TimeUnit;
import org.apache.http.HttpHeaders;
import org.apache.http.entity.ContentType;
import org.jetbrains.annotations.NotNull;
import com.google.gson.Gson;
import eu.dnetlib.dhp.common.api.zenodo.ZenodoModel;
import eu.dnetlib.dhp.common.api.zenodo.ZenodoModelList;
import okhttp3.*;
public class ZenodoAPIClient implements Serializable {
String urlString;
String bucket;
String deposition_id;
String access_token;
public static final MediaType MEDIA_TYPE_JSON = MediaType.parse("application/json; charset=utf-8");
private static final MediaType MEDIA_TYPE_ZIP = MediaType.parse("application/zip");
public String getUrlString() {
return urlString;
}
public void setUrlString(String urlString) {
this.urlString = urlString;
}
public String getBucket() {
return bucket;
}
public void setBucket(String bucket) {
this.bucket = bucket;
}
public void setDeposition_id(String deposition_id) {
this.deposition_id = deposition_id;
}
public ZenodoAPIClient(String urlString, String access_token) {
this.urlString = urlString;
this.access_token = access_token;
}
/**
* Brand new deposition in Zenodo. It sets the deposition_id and the bucket where to store the files to upload
*
* @return response code
* @throws IOException
*/
public int newDeposition() throws IOException {
String json = "{}";
URL url = new URL(urlString);
HttpURLConnection conn = (HttpURLConnection) url.openConnection();
conn.setRequestProperty(HttpHeaders.CONTENT_TYPE, ContentType.APPLICATION_JSON.toString());
conn.setRequestProperty(HttpHeaders.AUTHORIZATION, "Bearer " + access_token);
conn.setRequestMethod("POST");
conn.setDoOutput(true);
try (OutputStream os = conn.getOutputStream()) {
byte[] input = json.getBytes("utf-8");
os.write(input, 0, input.length);
}
String body = getBody(conn);
int responseCode = conn.getResponseCode();
conn.disconnect();
if (!checkOKStatus(responseCode))
throw new IOException("Unexpected code " + responseCode + body);
ZenodoModel newSubmission = new Gson().fromJson(body, ZenodoModel.class);
this.bucket = newSubmission.getLinks().getBucket();
this.deposition_id = newSubmission.getId();
return responseCode;
}
/**
* Upload files in Zenodo.
*
* @param is the inputStream for the file to upload
* @param file_name the name of the file as it will appear on Zenodo
* @return the response code
*/
public int uploadIS(InputStream is, String file_name) throws IOException {
URL url = new URL(bucket + "/" + file_name);
HttpURLConnection conn = (HttpURLConnection) url.openConnection();
conn.setRequestProperty(HttpHeaders.CONTENT_TYPE, "application/zip");
conn.setRequestProperty(HttpHeaders.AUTHORIZATION, "Bearer " + access_token);
conn.setDoOutput(true);
conn.setRequestMethod("PUT");
byte[] buf = new byte[8192];
int length;
try (OutputStream os = conn.getOutputStream()) {
while ((length = is.read(buf)) != -1) {
os.write(buf, 0, length);
}
}
int responseCode = conn.getResponseCode();
if (!checkOKStatus(responseCode)) {
throw new IOException("Unexpected code " + responseCode + getBody(conn));
}
return responseCode;
}
@NotNull
private String getBody(HttpURLConnection conn) throws IOException {
String body = "{}";
try (BufferedReader br = new BufferedReader(
new InputStreamReader(conn.getInputStream(), "utf-8"))) {
StringBuilder response = new StringBuilder();
String responseLine = null;
while ((responseLine = br.readLine()) != null) {
response.append(responseLine.trim());
}
body = response.toString();
}
return body;
}
/**
* Associates metadata information to the current deposition
*
* @param metadata the metadata
* @return response code
* @throws IOException
*/
public int sendMretadata(String metadata) throws IOException {
URL url = new URL(urlString + "/" + deposition_id);
HttpURLConnection conn = (HttpURLConnection) url.openConnection();
conn.setRequestProperty(HttpHeaders.CONTENT_TYPE, ContentType.APPLICATION_JSON.toString());
conn.setRequestProperty(HttpHeaders.AUTHORIZATION, "Bearer " + access_token);
conn.setDoOutput(true);
conn.setRequestMethod("PUT");
try (OutputStream os = conn.getOutputStream()) {
byte[] input = metadata.getBytes("utf-8");
os.write(input, 0, input.length);
}
final int responseCode = conn.getResponseCode();
conn.disconnect();
if (!checkOKStatus(responseCode))
throw new IOException("Unexpected code " + responseCode + getBody(conn));
return responseCode;
}
private boolean checkOKStatus(int responseCode) {
if (HttpURLConnection.HTTP_OK != responseCode ||
HttpURLConnection.HTTP_CREATED != responseCode)
return true;
return false;
}
/**
* To publish the current deposition. It works for both new deposition or new version of an old deposition
*
* @return response code
* @throws IOException
*/
@Deprecated
public int publish() throws IOException {
String json = "{}";
OkHttpClient httpClient = new OkHttpClient.Builder().connectTimeout(600, TimeUnit.SECONDS).build();
RequestBody body = RequestBody.create(json, MEDIA_TYPE_JSON);
Request request = new Request.Builder()
.url(urlString + "/" + deposition_id + "/actions/publish")
.addHeader("Authorization", "Bearer " + access_token)
.post(body)
.build();
try (Response response = httpClient.newCall(request).execute()) {
if (!response.isSuccessful())
throw new IOException("Unexpected code " + response + response.body().string());
return response.code();
}
}
/**
* To create a new version of an already published deposition. It sets the deposition_id and the bucket to be used
* for the new version.
*
* @param concept_rec_id the concept record id of the deposition for which to create a new version. It is the last
* part of the url for the DOI Zenodo suggests to use to cite all versions: DOI: 10.xxx/zenodo.656930
* concept_rec_id = 656930
* @return response code
* @throws IOException
* @throws MissingConceptDoiException
*/
public int newVersion(String concept_rec_id) throws IOException, MissingConceptDoiException {
setDepositionId(concept_rec_id, 1);
String json = "{}";
URL url = new URL(urlString + "/" + deposition_id + "/actions/newversion");
HttpURLConnection conn = (HttpURLConnection) url.openConnection();
conn.setRequestProperty(HttpHeaders.AUTHORIZATION, "Bearer " + access_token);
conn.setDoOutput(true);
conn.setRequestMethod("POST");
try (OutputStream os = conn.getOutputStream()) {
byte[] input = json.getBytes("utf-8");
os.write(input, 0, input.length);
}
String body = getBody(conn);
int responseCode = conn.getResponseCode();
conn.disconnect();
if (!checkOKStatus(responseCode))
throw new IOException("Unexpected code " + responseCode + body);
ZenodoModel zenodoModel = new Gson().fromJson(body, ZenodoModel.class);
String latest_draft = zenodoModel.getLinks().getLatest_draft();
deposition_id = latest_draft.substring(latest_draft.lastIndexOf("/") + 1);
bucket = getBucket(latest_draft);
return responseCode;
}
/**
* To finish uploading a version or new deposition not published
* It sets the deposition_id and the bucket to be used
*
*
* @param deposition_id the deposition id of the not yet published upload
* concept_rec_id = 656930
* @return response code
* @throws IOException
* @throws MissingConceptDoiException
*/
public int uploadOpenDeposition(String deposition_id) throws IOException, MissingConceptDoiException {
this.deposition_id = deposition_id;
String json = "{}";
URL url = new URL(urlString + "/" + deposition_id);
HttpURLConnection conn = (HttpURLConnection) url.openConnection();
conn.setRequestProperty(HttpHeaders.AUTHORIZATION, "Bearer " + access_token);
conn.setRequestMethod("POST");
conn.setDoOutput(true);
try (OutputStream os = conn.getOutputStream()) {
byte[] input = json.getBytes("utf-8");
os.write(input, 0, input.length);
}
String body = getBody(conn);
int responseCode = conn.getResponseCode();
conn.disconnect();
if (!checkOKStatus(responseCode))
throw new IOException("Unexpected code " + responseCode + body);
ZenodoModel zenodoModel = new Gson().fromJson(body, ZenodoModel.class);
bucket = zenodoModel.getLinks().getBucket();
return responseCode;
}
private void setDepositionId(String concept_rec_id, Integer page) throws IOException, MissingConceptDoiException {
ZenodoModelList zenodoModelList = new Gson()
.fromJson(getPrevDepositions(String.valueOf(page)), ZenodoModelList.class);
for (ZenodoModel zm : zenodoModelList) {
if (zm.getConceptrecid().equals(concept_rec_id)) {
deposition_id = zm.getId();
return;
}
}
if (zenodoModelList.size() == 0)
throw new MissingConceptDoiException(
"The concept record id specified was missing in the list of depositions");
setDepositionId(concept_rec_id, page + 1);
}
private String getPrevDepositions(String page) throws IOException {
HttpUrl.Builder urlBuilder = HttpUrl.parse(urlString).newBuilder();
urlBuilder.addQueryParameter("page", page);
URL url = new URL(urlBuilder.build().toString());
HttpURLConnection conn = (HttpURLConnection) url.openConnection();
conn.setRequestProperty(HttpHeaders.CONTENT_TYPE, ContentType.APPLICATION_JSON.toString());
conn.setRequestProperty(HttpHeaders.AUTHORIZATION, "Bearer " + access_token);
conn.setDoOutput(true);
conn.setRequestMethod("GET");
String body = getBody(conn);
int responseCode = conn.getResponseCode();
conn.disconnect();
if (!checkOKStatus(responseCode))
throw new IOException("Unexpected code " + responseCode + body);
return body;
}
private String getBucket(String inputUurl) throws IOException {
URL url = new URL(inputUurl);
HttpURLConnection conn = (HttpURLConnection) url.openConnection();
conn.setRequestProperty(HttpHeaders.CONTENT_TYPE, ContentType.APPLICATION_JSON.toString());
conn.setRequestProperty(HttpHeaders.AUTHORIZATION, "Bearer " + access_token);
conn.setDoOutput(true);
conn.setRequestMethod("GET");
String body = getBody(conn);
int responseCode = conn.getResponseCode();
conn.disconnect();
if (!checkOKStatus(responseCode))
throw new IOException("Unexpected code " + responseCode + body);
ZenodoModel zenodoModel = new Gson().fromJson(body, ZenodoModel.class);
return zenodoModel.getLinks().getBucket();
}
}

14
dhp-common/src/main/java/eu/dnetlib/dhp/common/api/zenodo/Community.java
View File

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

47
dhp-common/src/main/java/eu/dnetlib/dhp/common/api/zenodo/Creator.java
View File

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

44
dhp-common/src/main/java/eu/dnetlib/dhp/common/api/zenodo/File.java
View File

@ -1,44 +0,0 @@
package eu.dnetlib.dhp.common.api.zenodo;
import java.io.Serializable;
public class File implements Serializable {
private String checksum;
private String filename;
private long filesize;
private String id;
public String getChecksum() {
return checksum;
}
public void setChecksum(String checksum) {
this.checksum = checksum;
}
public String getFilename() {
return filename;
}
public void setFilename(String filename) {
this.filename = filename;
}
public long getFilesize() {
return filesize;
}
public void setFilesize(long filesize) {
this.filesize = filesize;
}
public String getId() {
return id;
}
public void setId(String id) {
this.id = id;
}
}

23
dhp-common/src/main/java/eu/dnetlib/dhp/common/api/zenodo/Grant.java
View File

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

92
dhp-common/src/main/java/eu/dnetlib/dhp/common/api/zenodo/Links.java
View File

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

153
dhp-common/src/main/java/eu/dnetlib/dhp/common/api/zenodo/Metadata.java
View File

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

25
dhp-common/src/main/java/eu/dnetlib/dhp/common/api/zenodo/PrereserveDoi.java
View File

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

43
dhp-common/src/main/java/eu/dnetlib/dhp/common/api/zenodo/RelatedIdentifier.java
View File

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

118
dhp-common/src/main/java/eu/dnetlib/dhp/common/api/zenodo/ZenodoModel.java
View File

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

7
dhp-common/src/main/java/eu/dnetlib/dhp/common/api/zenodo/ZenodoModelList.java
View File

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

37
dhp-common/src/main/java/eu/dnetlib/dhp/common/collection/HttpClientParams.java
View File

@ -1,6 +1,9 @@
package eu.dnetlib.dhp.common.collection;
import java.util.HashMap;
import java.util.Map;
/**
* Bundles the http connection parameters driving the client behaviour.
*/
@ -13,6 +16,8 @@ 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
*/
@ -38,17 +43,30 @@ 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);
this(_maxNumberOfRetry, _requestDelay, _retryDelay, _connectTimeOut, _readTimeOut, new HashMap<>(),
_requestMethod);
}
public HttpClientParams(int maxNumberOfRetry, int requestDelay, int retryDelay, int connectTimeOut,
int readTimeOut) {
int readTimeOut, Map<String, String> headers, String requestMethod) {
this.maxNumberOfRetry = maxNumberOfRetry;
this.requestDelay = requestDelay;
this.retryDelay = retryDelay;
this.connectTimeOut = connectTimeOut;
this.readTimeOut = readTimeOut;
this.headers = headers;
this.requestMethod = requestMethod;
}
public int getMaxNumberOfRetry() {
@ -91,4 +109,19 @@ 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;
}
}

7
dhp-common/src/main/java/eu/dnetlib/dhp/common/collection/HttpConnector2.java
View File

@ -107,7 +107,14 @@ public class HttpConnector2 {
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);
}

5
dhp-common/src/main/java/eu/dnetlib/dhp/common/vocabulary/Vocabulary.java
View File

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

18
dhp-common/src/main/java/eu/dnetlib/dhp/common/vocabulary/VocabularyGroup.java
View File

@ -135,6 +135,24 @@ 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
*

127
dhp-common/src/main/java/eu/dnetlib/dhp/oa/merge/AuthorMerger.java
View File

@ -119,6 +119,131 @@ 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()
: "";
@ -171,7 +296,7 @@ public class AuthorMerger {
}
}
private static String normalize(final String s) {
public static String normalize(final String s) {
String[] normalized = nfd(s)
.toLowerCase()
// do not compact the regexes in a single expression, would cause StackOverflowError

97
dhp-common/src/main/java/eu/dnetlib/dhp/oa/merge/DispatchEntitiesSparkJob.java
View File

@ -1,97 +0,0 @@
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.*;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.schema.common.ModelSupport;
public class DispatchEntitiesSparkJob {
private static final Logger log = LoggerFactory.getLogger(DispatchEntitiesSparkJob.class);
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);
boolean filterInvisible = Boolean.parseBoolean(parser.get("filterInvisible"));
log.info("filterInvisible: {}", filterInvisible);
SparkConf conf = new SparkConf();
runWithSparkSession(
conf,
isSparkSessionManaged,
spark -> dispatchEntities(spark, inputPath, outputPath, filterInvisible));
}
private static void dispatchEntities(
SparkSession spark,
String inputPath,
String outputPath,
boolean filterInvisible) {
Dataset<String> df = spark.read().textFile(inputPath);
ModelSupport.oafTypes.entrySet().parallelStream().forEach(entry -> {
String entityType = entry.getKey();
Class<?> clazz = entry.getValue();
final String entityPath = outputPath + "/" + entityType;
if (!entityType.equalsIgnoreCase("relation")) {
HdfsSupport.remove(entityPath, spark.sparkContext().hadoopConfiguration());
Dataset<Row> entityDF = spark
.read()
.schema(Encoders.bean(clazz).schema())
.json(
df
.filter((FilterFunction<String>) s -> s.startsWith(clazz.getName()))
.map(
(MapFunction<String, String>) s -> StringUtils.substringAfter(s, "|"),
Encoders.STRING()));
if (filterInvisible) {
entityDF = entityDF.filter("dataInfo.invisible != true");
}
entityDF
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(entityPath);
}
});
}
}

249
dhp-common/src/main/java/eu/dnetlib/dhp/oa/merge/GroupEntitiesSparkJob.java
View File

@ -2,50 +2,49 @@
package eu.dnetlib.dhp.oa.merge;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import static eu.dnetlib.dhp.utils.DHPUtils.toSeq;
import static org.apache.spark.sql.functions.col;
import static org.apache.spark.sql.functions.when;
import java.io.IOException;
import java.util.List;
import java.util.Objects;
import java.util.Map;
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.*;
import eu.dnetlib.dhp.schema.oaf.OafEntity;
import eu.dnetlib.dhp.schema.oaf.utils.GraphCleaningFunctions;
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 String ID_JPATH = "$.id";
private static final Encoder<OafEntity> OAFENTITY_KRYO_ENC = Encoders.kryo(OafEntity.class);
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper()
.configure(DeserializationFeature.FAIL_ON_UNKNOWN_PROPERTIES, false);
private ArgumentApplicationParser parser;
public GroupEntitiesSparkJob(ArgumentApplicationParser parser) {
this.parser = parser;
}
public static void main(String[] args) throws Exception {
@ -63,141 +62,133 @@ 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(outputPath, spark.sparkContext().hadoopConfiguration());
groupEntities(spark, graphInputPath, outputPath);
HdfsSupport.remove(checkpointPath, spark.sparkContext().hadoopConfiguration());
groupEntities(spark, graphInputPath, checkpointPath, outputPath, filterInvisible, vocs);
});
}
private static void groupEntities(
SparkSession spark,
String inputPath,
String outputPath) {
String checkpointPath,
String outputPath,
boolean filterInvisible, VocabularyGroup vocs) {
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)
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
.map(
(MapFunction<Tuple2<String, OafEntity>, String>) t -> t._2().getClass().getName() +
"|" + OBJECT_MAPPER.writeValueAsString(t._2()),
Encoders.STRING())
(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")
.write()
.option("compression", "gzip")
.mode(SaveMode.Overwrite)
.text(outputPath);
}
.option("compression", "gzip")
.save(checkpointPath);
public static class GroupingAggregator extends Aggregator<OafEntity, OafEntity, OafEntity> {
ForkJoinPool parPool = new ForkJoinPool(ModelSupport.entityTypes.size());
@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())
ModelSupport.entityTypes
.entrySet()
.stream()
.filter(f -> !f.toLowerCase().contains("relation"))
.collect(Collectors.toList());
}
.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);
}
});
}
}

274
dhp-common/src/main/java/eu/dnetlib/dhp/schema/oaf/utils/GraphCleaningFunctions.java
View File

@ -1,8 +1,12 @@
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;
@ -19,6 +23,7 @@ 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.*;
@ -26,6 +31,10 @@ 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)";
@ -37,6 +46,67 @@ public class GraphCleaningFunctions extends CleaningFunctions {
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)) {
final Result res = (Result) value;
@ -273,6 +343,12 @@ 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;
@ -292,6 +368,10 @@ 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()))) {
@ -334,6 +414,14 @@ public class GraphCleaningFunctions extends CleaningFunctions {
.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.isNull(r.getLanguage()) || StringUtils.isBlank(r.getLanguage().getClassid())) {
@ -493,6 +581,43 @@ 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()) {
@ -506,6 +631,15 @@ public class GraphCleaningFunctions extends CleaningFunctions {
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())
@ -528,8 +662,7 @@ public class GraphCleaningFunctions extends CleaningFunctions {
.getAuthor()
.stream()
.filter(Objects::nonNull)
.filter(a -> StringUtils.isNotBlank(a.getFullname()))
.filter(a -> StringUtils.isNotBlank(a.getFullname().replaceAll("[\\W]", "")))
.filter(GraphCleaningFunctions::isValidAuthorName)
.map(GraphCleaningFunctions::cleanupAuthor)
.collect(Collectors.toList()));
@ -556,6 +689,9 @@ 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());
@ -565,7 +701,8 @@ public class GraphCleaningFunctions extends CleaningFunctions {
.toLowerCase()
.contains(ModelConstants.ORCID)) {
if (pidProvenance
.equals(ModelConstants.SYSIMPORT_CROSSWALK_ENTITYREGISTRY)) {
.equals(ModelConstants.SYSIMPORT_CROSSWALK_ENTITYREGISTRY) ||
pidProvenance.equals("ORCID_ENRICHMENT")) {
p.getQualifier().setClassid(ModelConstants.ORCID);
} else {
p.getQualifier().setClassid(ModelConstants.ORCID_PENDING);
@ -687,12 +824,30 @@ public class GraphCleaningFunctions extends CleaningFunctions {
// HELPERS
private static boolean isValidAuthorName(Author a) {
return !Stream
.of(a.getFullname(), a.getName(), a.getSurname())
.filter(s -> s != null && !s.isEmpty())
.collect(Collectors.joining(""))
.toLowerCase()
.matches(INVALID_AUTHOR_REGEX);
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;
}
}
private static List<StructuredProperty> processPidCleaning(List<StructuredProperty> pids) {
@ -742,4 +897,105 @@ 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);
}
}

23
dhp-common/src/main/java/eu/dnetlib/dhp/schema/oaf/utils/OafMapperUtils.java
View File

@ -14,7 +14,6 @@ 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.*;
@ -141,6 +140,28 @@ 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);
}

26
dhp-common/src/main/resources/eu/dnetlib/dhp/oa/merge/dispatch_entities_parameters.json
View File

@ -1,26 +0,0 @@
[
{
"paramName": "issm",
"paramLongName": "isSparkSessionManaged",
"paramDescription": "when true will stop SparkSession after job execution",
"paramRequired": false
},
{
"paramName": "i",
"paramLongName": "inputPath",
"paramDescription": "the source path",
"paramRequired": true
},
{
"paramName": "o",
"paramLongName": "outputPath",
"paramDescription": "path of the output graph",
"paramRequired": true
},
{
"paramName": "fi",
"paramLongName": "filterInvisible",
"paramDescription": "if true filters out invisible entities",
"paramRequired": true
}
]

22
dhp-common/src/main/resources/eu/dnetlib/dhp/oa/merge/group_graph_entities_parameters.json
View File

@ -8,13 +8,31 @@
{
"paramName": "gin",
"paramLongName": "graphInputPath",
"paramDescription": "the graph root path",
"paramDescription": "the input graph root path",
"paramRequired": true
},
{
"paramName": "cp",
"paramLongName": "checkpointPath",
"paramDescription": "checkpoint directory",
"paramRequired": true
},
{
"paramName": "out",
"paramLongName": "outputPath",
"paramDescription": "the output merged graph root path",
"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",
"paramRequired": true
}
]

109
dhp-common/src/test/java/eu/dnetlib/dhp/common/api/ZenodoAPIClientTest.java
View File

@ -1,109 +0,0 @@
package eu.dnetlib.dhp.common.api;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import org.apache.commons.io.IOUtils;
import org.junit.jupiter.api.Assertions;
import org.junit.jupiter.api.Disabled;
import org.junit.jupiter.api.Test;
@Disabled
class ZenodoAPIClientTest {
private final String URL_STRING = "https://sandbox.zenodo.org/api/deposit/depositions";
private final String ACCESS_TOKEN = "";
private final String CONCEPT_REC_ID = "657113";
private final String depositionId = "674915";
@Test
void testUploadOldDeposition() throws IOException, MissingConceptDoiException {
ZenodoAPIClient client = new ZenodoAPIClient(URL_STRING,
ACCESS_TOKEN);
Assertions.assertEquals(200, client.uploadOpenDeposition(depositionId));
File file = new File(getClass()
.getResource("/eu/dnetlib/dhp/common/api/COVID-19.json.gz")
.getPath());
InputStream is = new FileInputStream(file);
Assertions.assertEquals(200, client.uploadIS(is, "COVID-19.json.gz"));
String metadata = IOUtils.toString(getClass().getResourceAsStream("/eu/dnetlib/dhp/common/api/metadata.json"));
Assertions.assertEquals(200, client.sendMretadata(metadata));
Assertions.assertEquals(202, client.publish());
}
@Test
void testNewDeposition() throws IOException {
ZenodoAPIClient client = new ZenodoAPIClient(URL_STRING,
ACCESS_TOKEN);
Assertions.assertEquals(201, client.newDeposition());
File file = new File(getClass()
.getResource("/eu/dnetlib/dhp/common/api/COVID-19.json.gz")
.getPath());
InputStream is = new FileInputStream(file);
Assertions.assertEquals(200, client.uploadIS(is, "COVID-19.json.gz"));
String metadata = IOUtils.toString(getClass().getResourceAsStream("/eu/dnetlib/dhp/common/api/metadata.json"));
Assertions.assertEquals(200, client.sendMretadata(metadata));
Assertions.assertEquals(202, client.publish());
}
@Test
void testNewVersionNewName() throws IOException, MissingConceptDoiException {
ZenodoAPIClient client = new ZenodoAPIClient(URL_STRING,
ACCESS_TOKEN);
Assertions.assertEquals(201, client.newVersion(CONCEPT_REC_ID));
File file = new File(getClass()
.getResource("/eu/dnetlib/dhp/common/api/newVersion")
.getPath());
InputStream is = new FileInputStream(file);
Assertions.assertEquals(200, client.uploadIS(is, "newVersion_deposition"));
Assertions.assertEquals(202, client.publish());
}
@Test
void testNewVersionOldName() throws IOException, MissingConceptDoiException {
ZenodoAPIClient client = new ZenodoAPIClient(URL_STRING,
ACCESS_TOKEN);
Assertions.assertEquals(201, client.newVersion(CONCEPT_REC_ID));
File file = new File(getClass()
.getResource("/eu/dnetlib/dhp/common/api/newVersion2")
.getPath());
InputStream is = new FileInputStream(file);
Assertions.assertEquals(200, client.uploadIS(is, "newVersion_deposition"));
Assertions.assertEquals(202, client.publish());
}
}

114
dhp-common/src/test/java/eu/dnetlib/oa/merge/AuthorMergerTest.java Normal file
View File

@ -0,0 +1,114 @@
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);
}
}

3
dhp-common/src/test/resources/eu/dnetlib/dhp/oa/merge/authors_orcid_sample.json Normal file
View File

File diff suppressed because one or more lines are too long

2
dhp-common/src/test/resources/eu/dnetlib/dhp/oa/merge/authors_publication_sample.json Normal file
View File

File diff suppressed because one or more lines are too long

1
dhp-pace-core/src/main/java/eu/dnetlib/pace/util/DiffPatchMatch.java
View File

@ -18,7 +18,6 @@ package eu.dnetlib.pace.util;
* See the License for the specific language governing permissions and
* limitations under the License.
*/
/*
* Diff Match and Patch
* Copyright 2018 The diff-match-patch Authors.

20
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/Constants.java
View File

@ -40,6 +40,7 @@ public class Constants {
public static final String SDG_CLASS_NAME = "Sustainable Development Goals";
public static final String NULL = "NULL";
public static final String NA = "N/A";
public static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
@ -61,10 +62,16 @@ public class Constants {
.map((MapFunction<String, R>) value -> OBJECT_MAPPER.readValue(value, clazz), Encoders.bean(clazz));
}
public static Subject getSubject(String sbj, String classid, String classname,
String diqualifierclassid) {
if (sbj == null || sbj.equals(NULL))
public static Subject getSubject(String sbj, String classid, String classname, String diqualifierclassid,
Boolean split) {
if (sbj == null || sbj.equals(NULL) || sbj.startsWith(NA))
return null;
String trust = "";
String subject = sbj;
if (split) {
sbj = subject.split("@@")[0];
trust = subject.split("@@")[1];
}
Subject s = new Subject();
s.setValue(sbj);
s
@ -89,9 +96,14 @@ public class Constants {
UPDATE_CLASS_NAME,
ModelConstants.DNET_PROVENANCE_ACTIONS,
ModelConstants.DNET_PROVENANCE_ACTIONS),
""));
trust));
return s;
}
public static Subject getSubject(String sbj, String classid, String classname,
String diqualifierclassid) {
return getSubject(sbj, classid, classname, diqualifierclassid, false);
}

40
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/bipaffiliations/PrepareAffiliationRelations.java
View File

@ -12,6 +12,7 @@ import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.compress.GzipCodec;
import org.apache.hadoop.mapred.SequenceFileOutputFormat;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.function.FlatMapFunction;
import org.apache.spark.sql.*;
import org.apache.spark.sql.Dataset;
@ -57,11 +58,14 @@ public class PrepareAffiliationRelations implements Serializable {
Boolean isSparkSessionManaged = Constants.isSparkSessionManaged(parser);
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
final String inputPath = parser.get("inputPath");
log.info("inputPath {}: ", inputPath);
final String crossrefInputPath = parser.get("crossrefInputPath");
log.info("crossrefInputPath: {}", crossrefInputPath);
final String pubmedInputPath = parser.get("pubmedInputPath");
log.info("pubmedInputPath: {}", pubmedInputPath);
final String outputPath = parser.get("outputPath");
log.info("outputPath {}: ", outputPath);
log.info("outputPath: {}", outputPath);
SparkConf conf = new SparkConf();
@ -70,12 +74,28 @@ public class PrepareAffiliationRelations implements Serializable {
isSparkSessionManaged,
spark -> {
Constants.removeOutputDir(spark, outputPath);
prepareAffiliationRelations(spark, inputPath, outputPath);
List<KeyValue> collectedFromCrossref = OafMapperUtils
.listKeyValues(ModelConstants.CROSSREF_ID, "Crossref");
JavaPairRDD<Text, Text> crossrefRelations = prepareAffiliationRelations(
spark, crossrefInputPath, collectedFromCrossref);
List<KeyValue> collectedFromPubmed = OafMapperUtils
.listKeyValues(ModelConstants.PUBMED_CENTRAL_ID, "Pubmed");
JavaPairRDD<Text, Text> pubmedRelations = prepareAffiliationRelations(
spark, pubmedInputPath, collectedFromPubmed);
crossrefRelations
.union(pubmedRelations)
.saveAsHadoopFile(
outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class);
});
}
private static <I extends Result> void prepareAffiliationRelations(SparkSession spark, String inputPath,
String outputPath) {
private static <I extends Result> JavaPairRDD<Text, Text> prepareAffiliationRelations(SparkSession spark,
String inputPath,
List<KeyValue> collectedfrom) {
// load and parse affiliation relations from HDFS
Dataset<Row> df = spark
@ -92,7 +112,7 @@ public class PrepareAffiliationRelations implements Serializable {
new Column("matching.Confidence").as("confidence"));
// prepare action sets for affiliation relations
df
return df
.toJavaRDD()
.flatMap((FlatMapFunction<Row, Relation>) row -> {
@ -120,8 +140,6 @@ public class PrepareAffiliationRelations implements Serializable {
qualifier,
Double.toString(row.getAs("confidence")));
List<KeyValue> collectedfrom = OafMapperUtils.listKeyValues(ModelConstants.CROSSREF_ID, "Crossref");
// return bi-directional relations
return getAffiliationRelationPair(paperId, affId, collectedfrom, dataInfo).iterator();
@ -129,9 +147,7 @@ public class PrepareAffiliationRelations implements Serializable {
.map(p -> new AtomicAction(Relation.class, p))
.mapToPair(
aa -> new Tuple2<>(new Text(aa.getClazz().getCanonicalName()),
new Text(OBJECT_MAPPER.writeValueAsString(aa))))
.saveAsHadoopFile(outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class);
new Text(OBJECT_MAPPER.writeValueAsString(aa))));
}
private static List<Relation> getAffiliationRelationPair(String paperId, String affId, List<KeyValue> collectedfrom,

9
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/createunresolvedentities/GetFOSSparkJob.java
View File

@ -75,9 +75,12 @@ public class GetFOSSparkJob implements Serializable {
fosData.map((MapFunction<Row, FOSDataModel>) r -> {
FOSDataModel fosDataModel = new FOSDataModel();
fosDataModel.setDoi(r.getString(0).toLowerCase());
fosDataModel.setLevel1(r.getString(1));
fosDataModel.setLevel2(r.getString(2));
fosDataModel.setLevel3(r.getString(3));
fosDataModel.setLevel1(r.getString(2));
fosDataModel.setLevel2(r.getString(3));
fosDataModel.setLevel3(r.getString(4));
fosDataModel.setLevel4(r.getString(5));
fosDataModel.setScoreL3(String.valueOf(r.getDouble(6)));
fosDataModel.setScoreL4(String.valueOf(r.getDouble(7)));
return fosDataModel;
}, Encoders.bean(FOSDataModel.class))
.write()

178
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/createunresolvedentities/PrepareBipFinder.java
View File

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

27
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/createunresolvedentities/PrepareFOSSparkJob.java
View File

@ -78,12 +78,20 @@ public class PrepareFOSSparkJob implements Serializable {
HashSet<String> level1 = new HashSet<>();
HashSet<String> level2 = new HashSet<>();
HashSet<String> level3 = new HashSet<>();
addLevels(level1, level2, level3, first);
it.forEachRemaining(v -> addLevels(level1, level2, level3, v));
HashSet<String> level4 = new HashSet<>();
addLevels(level1, level2, level3, level4, first);
it.forEachRemaining(v -> addLevels(level1, level2, level3, level4, v));
List<Subject> sbjs = new ArrayList<>();
level1.forEach(l -> sbjs.add(getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID)));
level2.forEach(l -> sbjs.add(getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID)));
level3.forEach(l -> sbjs.add(getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID)));
level1
.forEach(l -> add(sbjs, getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID)));
level2
.forEach(l -> add(sbjs, getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID)));
level3
.forEach(
l -> add(sbjs, getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID, true)));
level4
.forEach(
l -> add(sbjs, getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID, true)));
r.setSubject(sbjs);
r
.setDataInfo(
@ -106,11 +114,18 @@ public class PrepareFOSSparkJob implements Serializable {
.json(outputPath + "/fos");
}
private static void add(List<Subject> sbsjs, Subject sbj) {
if (sbj != null)
sbsjs.add(sbj);
}
private static void addLevels(HashSet<String> level1, HashSet<String> level2, HashSet<String> level3,
HashSet<String> level4,
FOSDataModel first) {
level1.add(first.getLevel1());
level2.add(first.getLevel2());
level3.add(first.getLevel3());
level3.add(first.getLevel3() + "@@" + first.getScoreL3());
level4.add(first.getLevel4() + "@@" + first.getScoreL4());
}
}

6
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/createunresolvedentities/SparkSaveUnresolved.java
View File

@ -69,9 +69,9 @@ public class SparkSaveUnresolved implements Serializable {
.mapGroups((MapGroupsFunction<String, Result, Result>) (k, it) -> {
Result ret = it.next();
it.forEachRemaining(r -> {
if (r.getInstance() != null) {
ret.setInstance(r.getInstance());
}
// if (r.getInstance() != null) {
// ret.setInstance(r.getInstance());
// }
if (r.getSubject() != null) {
if (ret.getSubject() != null)
ret.getSubject().addAll(r.getSubject());

63
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/createunresolvedentities/model/FOSDataModel.java
View File

@ -11,21 +11,43 @@ public class FOSDataModel implements Serializable {
private String doi;
@CsvBindByPosition(position = 1)
// @CsvBindByName(column = "doi")
private String oaid;
@CsvBindByPosition(position = 2)
// @CsvBindByName(column = "level1")
private String level1;
@CsvBindByPosition(position = 2)
@CsvBindByPosition(position = 3)
// @CsvBindByName(column = "level2")
private String level2;
@CsvBindByPosition(position = 3)
@CsvBindByPosition(position = 4)
// @CsvBindByName(column = "level3")
private String level3;
@CsvBindByPosition(position = 5)
// @CsvBindByName(column = "level3")
private String level4;
@CsvBindByPosition(position = 6)
private String scoreL3;
@CsvBindByPosition(position = 7)
private String scoreL4;
public FOSDataModel() {
}
public FOSDataModel(String doi, String level1, String level2, String level3, String level4, String l3score,
String l4score) {
this.doi = doi;
this.level1 = level1;
this.level2 = level2;
this.level3 = level3;
this.level4 = level4;
this.scoreL3 = l3score;
this.scoreL4 = l4score;
}
public FOSDataModel(String doi, String level1, String level2, String level3) {
this.doi = doi;
this.level1 = level1;
@ -33,8 +55,41 @@ public class FOSDataModel implements Serializable {
this.level3 = level3;
}
public static FOSDataModel newInstance(String d, String level1, String level2, String level3) {
return new FOSDataModel(d, level1, level2, level3);
public static FOSDataModel newInstance(String d, String level1, String level2, String level3, String level4,
String scorel3, String scorel4) {
return new FOSDataModel(d, level1, level2, level3, level4, scorel3, scorel4);
}
public String getOaid() {
return oaid;
}
public void setOaid(String oaid) {
this.oaid = oaid;
}
public String getLevel4() {
return level4;
}
public void setLevel4(String level4) {
this.level4 = level4;
}
public String getScoreL3() {
return scoreL3;
}
public void setScoreL3(String scoreL3) {
this.scoreL3 = scoreL3;
}
public String getScoreL4() {
return scoreL4;
}
public void setScoreL4(String scoreL4) {
this.scoreL4 = scoreL4;
}
public String getDoi() {

150
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/opencitations/CreateActionSetSparkJob.java
View File

@ -10,8 +10,10 @@ import java.util.*;
import org.apache.commons.cli.ParseException;
import org.apache.commons.io.IOUtils;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.compress.GzipCodec;
import org.apache.hadoop.mapred.SequenceFileOutputFormat;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.function.FilterFunction;
import org.apache.spark.api.java.function.FlatMapFunction;
import org.apache.spark.api.java.function.MapFunction;
@ -26,19 +28,29 @@ import eu.dnetlib.dhp.actionmanager.opencitations.model.COCI;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.schema.action.AtomicAction;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.*;
import eu.dnetlib.dhp.schema.oaf.utils.CleaningFunctions;
import eu.dnetlib.dhp.schema.oaf.utils.IdentifierFactory;
import eu.dnetlib.dhp.schema.oaf.utils.*;
import eu.dnetlib.dhp.utils.DHPUtils;
import scala.Tuple2;
public class CreateActionSetSparkJob implements Serializable {
public static final String OPENCITATIONS_CLASSID = "sysimport:crosswalk:opencitations";
public static final String OPENCITATIONS_CLASSNAME = "Imported from OpenCitations";
private static final String ID_PREFIX = "50|doi_________::";
// DOI-to-DOI citations
public static final String COCI = "COCI";
// PMID-to-PMID citations
public static final String POCI = "POCI";
private static final String DOI_PREFIX = "50|doi_________::";
private static final String PMID_PREFIX = "50|pmid________::";
private static final String TRUST = "0.91";
private static final Logger log = LoggerFactory.getLogger(CreateActionSetSparkJob.class);
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
public static void main(final String[] args) throws IOException, ParseException {
@ -62,7 +74,7 @@ public class CreateActionSetSparkJob implements Serializable {
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
final String inputPath = parser.get("inputPath");
log.info("inputPath {}", inputPath.toString());
log.info("inputPath {}", inputPath);
final String outputPath = parser.get("outputPath");
log.info("outputPath {}", outputPath);
@ -76,41 +88,68 @@ public class CreateActionSetSparkJob implements Serializable {
runWithSparkSession(
conf,
isSparkSessionManaged,
spark -> {
extractContent(spark, inputPath, outputPath, shouldDuplicateRels);
});
spark -> extractContent(spark, inputPath, outputPath, shouldDuplicateRels));
}
private static void extractContent(SparkSession spark, String inputPath, String outputPath,
boolean shouldDuplicateRels) {
spark
getTextTextJavaPairRDD(spark, inputPath, shouldDuplicateRels, COCI)
.union(getTextTextJavaPairRDD(spark, inputPath, shouldDuplicateRels, POCI))
.saveAsHadoopFile(outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class);
}
private static JavaPairRDD<Text, Text> getTextTextJavaPairRDD(SparkSession spark, String inputPath,
boolean shouldDuplicateRels, String prefix) {
return spark
.read()
.textFile(inputPath + "/*")
.textFile(inputPath + "/" + prefix + "/" + prefix + "_JSON/*")
.map(
(MapFunction<String, COCI>) value -> OBJECT_MAPPER.readValue(value, COCI.class),
Encoders.bean(COCI.class))
.flatMap(
(FlatMapFunction<COCI, Relation>) value -> createRelation(value, shouldDuplicateRels).iterator(),
(FlatMapFunction<COCI, Relation>) value -> createRelation(
value, shouldDuplicateRels, prefix)
.iterator(),
Encoders.bean(Relation.class))
.filter((FilterFunction<Relation>) value -> value != null)
.filter((FilterFunction<Relation>) Objects::nonNull)
.toJavaRDD()
.map(p -> new AtomicAction(p.getClass(), p))
.mapToPair(
aa -> new Tuple2<>(new Text(aa.getClazz().getCanonicalName()),
new Text(OBJECT_MAPPER.writeValueAsString(aa))))
.saveAsHadoopFile(outputPath, Text.class, Text.class, SequenceFileOutputFormat.class);
new Text(OBJECT_MAPPER.writeValueAsString(aa))));
}
private static List<Relation> createRelation(COCI value, boolean duplicate) {
private static List<Relation> createRelation(COCI value, boolean duplicate, String p) {
List<Relation> relationList = new ArrayList<>();
String prefix;
String citing;
String cited;
String citing = ID_PREFIX
+ IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", value.getCiting()));
final String cited = ID_PREFIX
+ IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", value.getCited()));
switch (p) {
case COCI:
prefix = DOI_PREFIX;
citing = prefix
+ IdentifierFactory
.md5(PidCleaner.normalizePidValue(PidType.doi.toString(), value.getCiting()));
cited = prefix
+ IdentifierFactory
.md5(PidCleaner.normalizePidValue(PidType.doi.toString(), value.getCited()));
break;
case POCI:
prefix = PMID_PREFIX;
citing = prefix
+ IdentifierFactory
.md5(PidCleaner.normalizePidValue(PidType.pmid.toString(), value.getCiting()));
cited = prefix
+ IdentifierFactory
.md5(PidCleaner.normalizePidValue(PidType.pmid.toString(), value.getCited()));
break;
default:
throw new IllegalStateException("Invalid prefix: " + p);
}
if (!citing.equals(cited)) {
relationList
@ -120,7 +159,7 @@ public class CreateActionSetSparkJob implements Serializable {
cited, ModelConstants.CITES));
if (duplicate && value.getCiting().endsWith(".refs")) {
citing = ID_PREFIX + IdentifierFactory
citing = prefix + IdentifierFactory
.md5(
CleaningFunctions
.normalizePidValue(
@ -132,59 +171,30 @@ public class CreateActionSetSparkJob implements Serializable {
return relationList;
}
private static Collection<Relation> getRelations(String citing, String cited) {
return Arrays
.asList(
getRelation(citing, cited, ModelConstants.CITES),
getRelation(cited, citing, ModelConstants.IS_CITED_BY));
}
public static Relation getRelation(
String source,
String target,
String relclass) {
Relation r = new Relation();
r.setCollectedfrom(getCollectedFrom());
r.setSource(source);
r.setTarget(target);
r.setRelClass(relclass);
r.setRelType(ModelConstants.RESULT_RESULT);
r.setSubRelType(ModelConstants.CITATION);
r
.setDataInfo(
getDataInfo());
return r;
}
String relClass) {
public static List<KeyValue> getCollectedFrom() {
KeyValue kv = new KeyValue();
kv.setKey(ModelConstants.OPENOCITATIONS_ID);
kv.setValue(ModelConstants.OPENOCITATIONS_NAME);
return Arrays.asList(kv);
}
public static DataInfo getDataInfo() {
DataInfo di = new DataInfo();
di.setInferred(false);
di.setDeletedbyinference(false);
di.setTrust(TRUST);
di
.setProvenanceaction(
getQualifier(OPENCITATIONS_CLASSID, OPENCITATIONS_CLASSNAME, ModelConstants.DNET_PROVENANCE_ACTIONS));
return di;
}
public static Qualifier getQualifier(String class_id, String class_name,
String qualifierSchema) {
Qualifier pa = new Qualifier();
pa.setClassid(class_id);
pa.setClassname(class_name);
pa.setSchemeid(qualifierSchema);
pa.setSchemename(qualifierSchema);
return pa;
return OafMapperUtils
.getRelation(
source,
target,
ModelConstants.RESULT_RESULT,
ModelConstants.CITATION,
relClass,
Arrays
.asList(
OafMapperUtils.keyValue(ModelConstants.OPENOCITATIONS_ID, ModelConstants.OPENOCITATIONS_NAME)),
OafMapperUtils
.dataInfo(
false, null, false, false,
OafMapperUtils
.qualifier(
OPENCITATIONS_CLASSID, OPENCITATIONS_CLASSNAME,
ModelConstants.DNET_PROVENANCE_ACTIONS, ModelConstants.DNET_PROVENANCE_ACTIONS),
TRUST),
null);
}
}

19
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/opencitations/GetOpenCitationsRefs.java
View File

@ -3,6 +3,7 @@ package eu.dnetlib.dhp.actionmanager.opencitations;
import java.io.*;
import java.io.Serializable;
import java.util.Arrays;
import java.util.Objects;
import java.util.zip.GZIPOutputStream;
import java.util.zip.ZipEntry;
@ -37,7 +38,7 @@ public class GetOpenCitationsRefs implements Serializable {
parser.parseArgument(args);
final String[] inputFile = parser.get("inputFile").split(";");
log.info("inputFile {}", inputFile.toString());
log.info("inputFile {}", Arrays.asList(inputFile));
final String workingPath = parser.get("workingPath");
log.info("workingPath {}", workingPath);
@ -45,6 +46,9 @@ public class GetOpenCitationsRefs implements Serializable {
final String hdfsNameNode = parser.get("hdfsNameNode");
log.info("hdfsNameNode {}", hdfsNameNode);
final String prefix = parser.get("prefix");
log.info("prefix {}", prefix);
Configuration conf = new Configuration();
conf.set("fs.defaultFS", hdfsNameNode);
@ -53,30 +57,31 @@ public class GetOpenCitationsRefs implements Serializable {
GetOpenCitationsRefs ocr = new GetOpenCitationsRefs();
for (String file : inputFile) {
ocr.doExtract(workingPath + "/Original/" + file, workingPath, fileSystem);
ocr.doExtract(workingPath + "/Original/" + file, workingPath, fileSystem, prefix);
}
}
private void doExtract(String inputFile, String workingPath, FileSystem fileSystem)
private void doExtract(String inputFile, String workingPath, FileSystem fileSystem, String prefix)
throws IOException {
final Path path = new Path(inputFile);
FSDataInputStream oc_zip = fileSystem.open(path);
int count = 1;
// int count = 1;
try (ZipInputStream zis = new ZipInputStream(oc_zip)) {
ZipEntry entry = null;
while ((entry = zis.getNextEntry()) != null) {
if (!entry.isDirectory()) {
String fileName = entry.getName();
fileName = fileName.substring(0, fileName.indexOf("T")) + "_" + count;
count++;
// fileName = fileName.substring(0, fileName.indexOf("T")) + "_" + count;
fileName = fileName.substring(0, fileName.lastIndexOf("."));
// count++;
try (
FSDataOutputStream out = fileSystem
.create(new Path(workingPath + "/COCI/" + fileName + ".gz"));
.create(new Path(workingPath + "/" + prefix + "/" + fileName + ".gz"));
GZIPOutputStream gzipOs = new GZIPOutputStream(new BufferedOutputStream(out))) {
IOUtils.copy(zis, gzipOs);

25
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/opencitations/ReadCOCI.java
View File

@ -7,6 +7,7 @@ import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import java.io.IOException;
import java.io.Serializable;
import java.util.Arrays;
import java.util.Optional;
import org.apache.commons.io.IOUtils;
@ -42,13 +43,16 @@ public class ReadCOCI implements Serializable {
log.info("outputPath: {}", outputPath);
final String[] inputFile = parser.get("inputFile").split(";");
log.info("inputFile {}", inputFile.toString());
log.info("inputFile {}", Arrays.asList(inputFile));
Boolean isSparkSessionManaged = isSparkSessionManaged(parser);
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
final String workingPath = parser.get("workingPath");
log.info("workingPath {}", workingPath);
final String format = parser.get("format");
log.info("format {}", format);
SparkConf sconf = new SparkConf();
final String delimiter = Optional
@ -64,16 +68,17 @@ public class ReadCOCI implements Serializable {
workingPath,
inputFile,
outputPath,
delimiter);
delimiter,
format);
});
}
private static void doRead(SparkSession spark, String workingPath, String[] inputFiles,
String outputPath,
String delimiter) throws IOException {
String delimiter, String format) {
for (String inputFile : inputFiles) {
String p_string = workingPath + "/" + inputFile + ".gz";
String pString = workingPath + "/" + inputFile + ".gz";
Dataset<Row> cociData = spark
.read()
@ -82,14 +87,20 @@ public class ReadCOCI implements Serializable {
.option("inferSchema", "true")
.option("header", "true")
.option("quotes", "\"")
.load(p_string)
.load(pString)
.repartition(100);
cociData.map((MapFunction<Row, COCI>) row -> {
COCI coci = new COCI();
if (format.equals("COCI")) {
coci.setCiting(row.getString(1));
coci.setCited(row.getString(2));
} else {
coci.setCiting(String.valueOf(row.getInt(1)));
coci.setCited(String.valueOf(row.getInt(2)));
}
coci.setOci(row.getString(0));
coci.setCiting(row.getString(1));
coci.setCited(row.getString(2));
return coci;
}, Encoders.bean(COCI.class))
.write()

102
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/collection/orcid/DownloadORCIDDumpApplication.java Normal file
View File

@ -0,0 +1,102 @@
package eu.dnetlib.dhp.collection.orcid;
import static eu.dnetlib.dhp.utils.DHPUtils.getHadoopConfiguration;
import java.io.InputStream;
import java.net.URL;
import java.net.URLConnection;
import java.util.Objects;
import org.apache.commons.io.IOUtils;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.http.client.config.RequestConfig;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClientBuilder;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.JsonNode;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
public class DownloadORCIDDumpApplication {
private static final Logger log = LoggerFactory.getLogger(DownloadORCIDDumpApplication.class);
private final FileSystem fileSystem;
public DownloadORCIDDumpApplication(FileSystem fileSystem) {
this.fileSystem = fileSystem;
}
public static void main(String[] args) throws Exception {
final ArgumentApplicationParser argumentParser = new ArgumentApplicationParser(
IOUtils
.toString(
Objects
.requireNonNull(
DownloadORCIDDumpApplication.class
.getResourceAsStream(
"/eu/dnetlib/dhp/collection/orcid/download_orcid_parameter.json"))));
argumentParser.parseArgument(args);
final String hdfsuri = argumentParser.get("namenode");
log.info("hdfsURI is {}", hdfsuri);
final String targetPath = argumentParser.get("targetPath");
log.info("targetPath is {}", targetPath);
final String apiURL = argumentParser.get("apiURL");
log.info("apiURL is {}", apiURL);
final FileSystem fileSystem = FileSystem.get(getHadoopConfiguration(hdfsuri));
new DownloadORCIDDumpApplication(fileSystem).run(targetPath, apiURL);
}
private void downloadItem(final String name, final String itemURL, final String basePath) {
try {
final Path hdfsWritePath = new Path(String.format("%s/%s", basePath, name));
final FSDataOutputStream fsDataOutputStream = fileSystem.create(hdfsWritePath, true);
final HttpGet request = new HttpGet(itemURL);
final int timeout = 60; // seconds
final RequestConfig config = RequestConfig
.custom()
.setConnectTimeout(timeout * 1000)
.setConnectionRequestTimeout(timeout * 1000)
.setSocketTimeout(timeout * 1000)
.build();
log.info("Downloading url {} into {}", itemURL, hdfsWritePath.getName());
try (CloseableHttpClient client = HttpClientBuilder.create().setDefaultRequestConfig(config).build();
CloseableHttpResponse response = client.execute(request)) {
int responseCode = response.getStatusLine().getStatusCode();
log.info("Response code is {}", responseCode);
if (responseCode >= 200 && responseCode < 400) {
IOUtils.copy(response.getEntity().getContent(), fsDataOutputStream);
}
} catch (Throwable eu) {
throw new RuntimeException(eu);
}
} catch (Throwable e) {
throw new RuntimeException(e);
}
}
protected void run(final String targetPath, final String apiURL) throws Exception {
final ObjectMapper mapper = new ObjectMapper();
final URL url = new URL(apiURL);
URLConnection conn = url.openConnection();
InputStream is = conn.getInputStream();
final String json = IOUtils.toString(is);
JsonNode jsonNode = mapper.readTree(json);
jsonNode
.get("files")
.forEach(i -> downloadItem(i.get("name").asText(), i.get("download_url").asText(), targetPath));
}
}

71
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/collection/orcid/ExtractORCIDDump.java Normal file
View File

@ -0,0 +1,71 @@
package eu.dnetlib.dhp.collection.orcid;
import static eu.dnetlib.dhp.utils.DHPUtils.getHadoopConfiguration;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import java.util.Objects;
import org.apache.commons.io.IOUtils;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.LocatedFileStatus;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.fs.RemoteIterator;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
public class ExtractORCIDDump {
private static final Logger log = LoggerFactory.getLogger(ExtractORCIDDump.class);
private final FileSystem fileSystem;
public ExtractORCIDDump(FileSystem fileSystem) {
this.fileSystem = fileSystem;
}
public static void main(String[] args) throws Exception {
final ArgumentApplicationParser argumentParser = new ArgumentApplicationParser(
IOUtils
.toString(
Objects
.requireNonNull(
DownloadORCIDDumpApplication.class
.getResourceAsStream(
"/eu/dnetlib/dhp/collection/orcid/extract_orcid_parameter.json"))));
argumentParser.parseArgument(args);
final String hdfsuri = argumentParser.get("namenode");
log.info("hdfsURI is {}", hdfsuri);
final String sourcePath = argumentParser.get("sourcePath");
log.info("sourcePath is {}", sourcePath);
final String targetPath = argumentParser.get("targetPath");
log.info("targetPath is {}", targetPath);
final FileSystem fileSystem = FileSystem.get(getHadoopConfiguration(hdfsuri));
new ExtractORCIDDump(fileSystem).run(sourcePath, targetPath);
}
public void run(final String sourcePath, final String targetPath) throws IOException, InterruptedException {
RemoteIterator<LocatedFileStatus> ls = fileSystem.listFiles(new Path(sourcePath), false);
final List<ORCIDExtractor> workers = new ArrayList<>();
int i = 0;
while (ls.hasNext()) {
LocatedFileStatus current = ls.next();
if (current.getPath().getName().endsWith("tar.gz")) {
workers.add(new ORCIDExtractor(fileSystem, "" + i++, current.getPath(), targetPath));
}
}
workers.forEach(Thread::start);
for (ORCIDExtractor worker : workers) {
worker.join();
}
}
}

171
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/collection/orcid/ORCIDExtractor.java Normal file
View File

@ -0,0 +1,171 @@
package eu.dnetlib.dhp.collection.orcid;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.util.HashMap;
import java.util.Map;
import org.apache.commons.compress.archivers.tar.TarArchiveEntry;
import org.apache.commons.compress.archivers.tar.TarArchiveInputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IOUtils;
import org.apache.hadoop.io.SequenceFile;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.compress.CompressionCodec;
import org.apache.hadoop.io.compress.CompressionCodecFactory;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
/**\
* The ORCIDExtractor class extracts ORCID data from a TAR archive.
* The class creates a map of SequenceFile.Writer objects, one for each type of data that is to be extracted (e.g., employments, works, summaries).
* Then, it iterates over the TAR archive and writes each entry to the appropriate SequenceFile.Writer object.
* Finally, it closes all the SequenceFile.Writer objects.
*/
public class ORCIDExtractor extends Thread {
private static final Logger log = LoggerFactory.getLogger(ORCIDExtractor.class);
private final FileSystem fileSystem;
private final String id;
private final Path sourcePath;
private final String baseOutputPath;
public ORCIDExtractor(FileSystem fileSystem, String id, Path sourcePath, String baseOutputPath) {
this.fileSystem = fileSystem;
this.id = id;
this.sourcePath = sourcePath;
this.baseOutputPath = baseOutputPath;
}
/**
* creates a map of SequenceFile.Writer objects,
* one for each type of data that is to be extracted. The map is created based on the filename in the TAR archive.
* For example, if the filename is employments.json, the map will contain an entry for the SequenceFile.Writer
* object that writes employment data.
* @return the Map
*/
private Map<String, SequenceFile.Writer> createMap() {
try {
log.info("Thread {} Creating sequence files starting from this input Path {}", id, sourcePath.getName());
Map<String, SequenceFile.Writer> res = new HashMap<>();
if (sourcePath.getName().contains("summaries")) {
final String summaryPath = String.format("%s/summaries_%s", baseOutputPath, id);
final SequenceFile.Writer summary_file = SequenceFile
.createWriter(
fileSystem.getConf(),
SequenceFile.Writer.file(new Path(summaryPath)),
SequenceFile.Writer.keyClass(Text.class),
SequenceFile.Writer.valueClass(Text.class));
log.info("Thread {} Creating only summary path here {}", id, summaryPath);
res.put("summary", summary_file);
return res;
} else {
String employmentsPath = String.format("%s/employments_%s", baseOutputPath, id);
final SequenceFile.Writer employments_file = SequenceFile
.createWriter(
fileSystem.getConf(),
SequenceFile.Writer.file(new Path(employmentsPath)),
SequenceFile.Writer.keyClass(Text.class),
SequenceFile.Writer.valueClass(Text.class));
res.put("employments", employments_file);
log.info("Thread {} Creating employments path here {}", id, employmentsPath);
final String worksPath = String.format("%s/works_%s", baseOutputPath, id);
final SequenceFile.Writer works_file = SequenceFile
.createWriter(
fileSystem.getConf(),
SequenceFile.Writer.file(new Path(worksPath)),
SequenceFile.Writer.keyClass(Text.class),
SequenceFile.Writer.valueClass(Text.class));
res.put("works", works_file);
log.info("Thread {} Creating works path here {}", id, worksPath);
return res;
}
} catch (Throwable e) {
throw new RuntimeException(e);
}
}
@Override
public void run() {
CompressionCodecFactory factory = new CompressionCodecFactory(fileSystem.getConf());
CompressionCodec codec = factory.getCodec(sourcePath);
if (codec == null) {
System.err.println("No codec found for " + sourcePath.getName());
System.exit(1);
}
InputStream gzipInputStream = null;
try {
gzipInputStream = codec.createInputStream(fileSystem.open(sourcePath));
final Map<String, SequenceFile.Writer> fileMap = createMap();
iterateTar(fileMap, gzipInputStream);
} catch (IOException e) {
throw new RuntimeException(e);
} finally {
log.info("Closing gzip stream");
IOUtils.closeStream(gzipInputStream);
}
}
private SequenceFile.Writer retrieveFile(Map<String, SequenceFile.Writer> fileMap, final String path) {
if (sourcePath.getName().contains("summaries")) {
return fileMap.get("summary");
}
if (path.contains("works")) {
return fileMap.get("works");
}
if (path.contains("employments"))
return fileMap.get("employments");
return null;
}
private void iterateTar(Map<String, SequenceFile.Writer> fileMap, InputStream gzipInputStream) throws IOException {
int extractedItem = 0;
try (final TarArchiveInputStream tais = new TarArchiveInputStream(gzipInputStream)) {
TarArchiveEntry entry;
while ((entry = tais.getNextTarEntry()) != null) {
if (entry.isFile()) {
final SequenceFile.Writer fl = retrieveFile(fileMap, entry.getName());
if (fl != null) {
final Text key = new Text(entry.getName());
final Text value = new Text(
org.apache.commons.io.IOUtils.toString(new BufferedReader(new InputStreamReader(tais))));
fl.append(key, value);
extractedItem++;
if (extractedItem % 100000 == 0) {
log.info("Thread {}: Extracted {} items", id, extractedItem);
break;
}
}
}
}
} finally {
for (SequenceFile.Writer k : fileMap.values()) {
log.info("Thread {}: Completed processed {} items", id, extractedItem);
k.hflush();
k.close();
}
}
}
}

251
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/collection/orcid/OrcidParser.java Normal file
View File

@ -0,0 +1,251 @@
package eu.dnetlib.dhp.collection.orcid;
import java.util.Arrays;
import java.util.Collections;
import java.util.List;
import org.apache.commons.lang3.StringUtils;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.ximpleware.*;
import eu.dnetlib.dhp.collection.orcid.model.*;
import eu.dnetlib.dhp.parser.utility.VtdException;
import eu.dnetlib.dhp.parser.utility.VtdUtilityParser;
public class OrcidParser {
final Logger log = LoggerFactory.getLogger(OrcidParser.class);
private VTDNav vn;
private AutoPilot ap;
private static final String NS_COMMON_URL = "http://www.orcid.org/ns/common";
private static final String NS_COMMON = "common";
private static final String NS_PERSON_URL = "http://www.orcid.org/ns/person";
private static final String NS_PERSON = "person";
private static final String NS_DETAILS_URL = "http://www.orcid.org/ns/personal-details";
private static final String NS_DETAILS = "personal-details";
private static final String NS_OTHER_URL = "http://www.orcid.org/ns/other-name";
private static final String NS_OTHER = "other-name";
private static final String NS_RECORD_URL = "http://www.orcid.org/ns/record";
private static final String NS_RECORD = "record";
private static final String NS_ERROR_URL = "http://www.orcid.org/ns/error";
private static final String NS_ACTIVITIES = "activities";
private static final String NS_ACTIVITIES_URL = "http://www.orcid.org/ns/activities";
private static final String NS_WORK = "work";
private static final String NS_WORK_URL = "http://www.orcid.org/ns/work";
private static final String NS_ERROR = "error";
private static final String NS_HISTORY = "history";
private static final String NS_HISTORY_URL = "http://www.orcid.org/ns/history";
private static final String NS_BULK_URL = "http://www.orcid.org/ns/bulk";
private static final String NS_BULK = "bulk";
private static final String NS_EXTERNAL = "external-identifier";
private static final String NS_EXTERNAL_URL = "http://www.orcid.org/ns/external-identifier";
private void generateParsedDocument(final String xml) throws ParseException {
final VTDGen vg = new VTDGen();
vg.setDoc(xml.getBytes());
vg.parse(true);
this.vn = vg.getNav();
this.ap = new AutoPilot(vn);
ap.declareXPathNameSpace(NS_COMMON, NS_COMMON_URL);
ap.declareXPathNameSpace(NS_PERSON, NS_PERSON_URL);
ap.declareXPathNameSpace(NS_DETAILS, NS_DETAILS_URL);
ap.declareXPathNameSpace(NS_OTHER, NS_OTHER_URL);
ap.declareXPathNameSpace(NS_RECORD, NS_RECORD_URL);
ap.declareXPathNameSpace(NS_ERROR, NS_ERROR_URL);
ap.declareXPathNameSpace(NS_HISTORY, NS_HISTORY_URL);
ap.declareXPathNameSpace(NS_WORK, NS_WORK_URL);
ap.declareXPathNameSpace(NS_EXTERNAL, NS_EXTERNAL_URL);
ap.declareXPathNameSpace(NS_ACTIVITIES, NS_ACTIVITIES_URL);
}
public Author parseSummary(final String xml) {
try {
final Author author = new Author();
generateParsedDocument(xml);
List<VtdUtilityParser.Node> recordNodes = VtdUtilityParser
.getTextValuesWithAttributes(
ap, vn, "//record:record", Arrays.asList("path"));
if (!recordNodes.isEmpty()) {
final String oid = (recordNodes.get(0).getAttributes().get("path")).substring(1);
author.setOrcid(oid);
} else {
return null;
}
List<VtdUtilityParser.Node> personNodes = VtdUtilityParser
.getTextValuesWithAttributes(
ap, vn, "//person:name", Arrays.asList("visibility"));
final String visibility = (personNodes.get(0).getAttributes().get("visibility"));
author.setVisibility(visibility);
final String name = VtdUtilityParser.getSingleValue(ap, vn, "//personal-details:given-names");
author.setGivenName(name);
final String surnames = VtdUtilityParser.getSingleValue(ap, vn, "//personal-details:family-name");
author.setFamilyName(surnames);
final String creditNames = VtdUtilityParser.getSingleValue(ap, vn, "//personal-details:credit-name");
author.setCreditName(creditNames);
final String biography = VtdUtilityParser
.getSingleValue(ap, vn, "//person:biography/personal-details:content");
author.setBiography(biography);
final List<String> otherNames = VtdUtilityParser.getTextValue(ap, vn, "//other-name:content");
if (!otherNames.isEmpty()) {
author.setOtherNames(otherNames);
}
ap.selectXPath("//external-identifier:external-identifier");
while (ap.evalXPath() != -1) {
final Pid pid = new Pid();
final AutoPilot ap1 = new AutoPilot(ap.getNav());
ap1.selectXPath("./common:external-id-type");
while (ap1.evalXPath() != -1) {
int it = vn.getText();
pid.setSchema(vn.toNormalizedString(it));
}
ap1.selectXPath("./common:external-id-value");
while (ap1.evalXPath() != -1) {
int it = vn.getText();
pid.setValue(vn.toNormalizedString(it));
}
author.addOtherPid(pid);
}
return author;
} catch (Throwable e) {
log.error("Error on parsing {}", xml);
log.error(e.getMessage());
return null;
}
}
public Work parseWork(final String xml) {
try {
final Work work = new Work();
generateParsedDocument(xml);
List<VtdUtilityParser.Node> workNodes = VtdUtilityParser
.getTextValuesWithAttributes(ap, vn, "//work:work", Arrays.asList("path", "visibility"));
if (!workNodes.isEmpty()) {
final String oid = (workNodes.get(0).getAttributes().get("path")).split("/")[1];
work.setOrcid(oid);
} else {
return null;
}
ap.selectXPath("//common:external-id");
while (ap.evalXPath() != -1) {
final Pid pid = new Pid();
final AutoPilot ap1 = new AutoPilot(ap.getNav());
ap1.selectXPath("./common:external-id-type");
while (ap1.evalXPath() != -1) {
int it = vn.getText();
pid.setSchema(vn.toNormalizedString(it));
}
ap1.selectXPath("./common:external-id-value");
while (ap1.evalXPath() != -1) {
int it = vn.getText();
pid.setValue(vn.toNormalizedString(it));
}
work.addPid(pid);
}
work.setTitle(VtdUtilityParser.getSingleValue(ap, vn, "//work:title/common:title"));
return work;
} catch (Throwable e) {
log.error("Error on parsing {}", xml);
log.error(e.getMessage());
return null;
}
}
private String extractEmploymentDate(final String xpath) throws Exception {
ap.selectXPath(xpath);
StringBuilder sb = new StringBuilder();
while (ap.evalXPath() != -1) {
final AutoPilot ap1 = new AutoPilot(ap.getNav());
ap1.selectXPath("./common:year");
while (ap1.evalXPath() != -1) {
int it = vn.getText();
sb.append(vn.toNormalizedString(it));
}
ap1.selectXPath("./common:month");
while (ap1.evalXPath() != -1) {
int it = vn.getText();
sb.append("-");
sb.append(vn.toNormalizedString(it));
}
ap1.selectXPath("./common:day");
while (ap1.evalXPath() != -1) {
int it = vn.getText();
sb.append("-");
sb.append(vn.toNormalizedString(it));
}
}
return sb.toString();
}
public Employment parseEmployment(final String xml) {
try {
final Employment employment = new Employment();
generateParsedDocument(xml);
final String oid = VtdUtilityParser
.getSingleValue(ap, vn, "//common:source-orcid/common:path");
if (StringUtils.isNotBlank(oid)) {
employment.setOrcid(oid);
} else {
return null;
}
final String depName = VtdUtilityParser
.getSingleValue(ap, vn, "//common:department-name");
final String rolTitle = VtdUtilityParser
.getSingleValue(ap, vn, "//common:role-title");
if (StringUtils.isNotBlank(rolTitle))
employment.setRoleTitle(rolTitle);
if (StringUtils.isNotBlank(depName))
employment.setDepartmentName(depName);
else
employment
.setDepartmentName(
VtdUtilityParser
.getSingleValue(ap, vn, "//common:organization/common:name"));
employment.setStartDate(extractEmploymentDate("//common:start-date"));
employment.setEndDate(extractEmploymentDate("//common:end-date"));
final String affiliationId = VtdUtilityParser
.getSingleValue(ap, vn, "//common:disambiguated-organization-identifier");
final String affiliationIdType = VtdUtilityParser
.getSingleValue(ap, vn, "//common:disambiguation-source");
if (StringUtils.isNotBlank(affiliationId) || StringUtils.isNotBlank(affiliationIdType))
employment.setAffiliationId(new Pid(affiliationId, affiliationIdType));
return employment;
} catch (Throwable e) {
log.error("Error on parsing {}", xml);
log.error(e.getMessage());
return null;
}
}
}

83
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/collection/orcid/model/Author.java Normal file
View File

@ -0,0 +1,83 @@
package eu.dnetlib.dhp.collection.orcid.model;
import java.util.ArrayList;
import java.util.List;
public class Author extends ORCIDItem {
private String givenName;
private String familyName;
private String visibility;
private String creditName;
private List<String> otherNames;
private List<Pid> otherPids;
private String biography;
public String getBiography() {
return biography;
}
public void setBiography(String biography) {
this.biography = biography;
}
public String getGivenName() {
return givenName;
}
public void setGivenName(String givenName) {
this.givenName = givenName;
}
public String getFamilyName() {
return familyName;
}
public void setFamilyName(String familyName) {
this.familyName = familyName;
}
public String getCreditName() {
return creditName;
}
public void setCreditName(String creditName) {
this.creditName = creditName;
}
public List<String> getOtherNames() {
return otherNames;
}
public void setOtherNames(List<String> otherNames) {
this.otherNames = otherNames;
}
public String getVisibility() {
return visibility;
}
public void setVisibility(String visibility) {
this.visibility = visibility;
}
public List<Pid> getOtherPids() {
return otherPids;
}
public void setOtherPids(List<Pid> otherPids) {
this.otherPids = otherPids;
}
public void addOtherPid(final Pid pid) {
if (otherPids == null)
otherPids = new ArrayList<>();
otherPids.add(pid);
}
}

54
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/collection/orcid/model/Employment.java Normal file
View File

@ -0,0 +1,54 @@
package eu.dnetlib.dhp.collection.orcid.model;
public class Employment extends ORCIDItem {
private String startDate;
private String EndDate;
private Pid affiliationId;
private String departmentName;
private String roleTitle;
public String getStartDate() {
return startDate;
}
public void setStartDate(String startDate) {
this.startDate = startDate;
}
public String getEndDate() {
return EndDate;
}
public void setEndDate(String endDate) {
EndDate = endDate;
}
public Pid getAffiliationId() {
return affiliationId;
}
public void setAffiliationId(Pid affiliationId) {
this.affiliationId = affiliationId;
}
public String getDepartmentName() {
return departmentName;
}
public void setDepartmentName(String departmentName) {
this.departmentName = departmentName;
}
public String getRoleTitle() {
return roleTitle;
}
public void setRoleTitle(String roleTitle) {
this.roleTitle = roleTitle;
}
}

14
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/collection/orcid/model/ORCIDItem.java Normal file
View File

@ -0,0 +1,14 @@
package eu.dnetlib.dhp.collection.orcid.model;
public class ORCIDItem {
private String orcid;
public String getOrcid() {
return orcid;
}
public void setOrcid(String orcid) {
this.orcid = orcid;
}
}

33
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/collection/orcid/model/Pid.java Normal file
View File

@ -0,0 +1,33 @@
package eu.dnetlib.dhp.collection.orcid.model;
public class Pid {
private String value;
private String schema;
public Pid() {
}
public Pid(String value, String schema) {
this.value = value;
this.schema = schema;
}
public String getValue() {
return value;
}
public void setValue(String value) {
this.value = value;
}
public String getSchema() {
return schema;
}
public void setSchema(String schema) {
this.schema = schema;
}
}

35
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/collection/orcid/model/Work.java Normal file
View File

@ -0,0 +1,35 @@
package eu.dnetlib.dhp.collection.orcid.model;
import java.util.ArrayList;
import java.util.List;
public class Work extends ORCIDItem {
private String title;
private List<Pid> pids;
public String getTitle() {
return title;
}
public void setTitle(String title) {
this.title = title;
}
public List<Pid> getPids() {
return pids;
}
public void setPids(List<Pid> pids) {
this.pids = pids;
}
public void addPid(Pid pid) {
if (pids == null)
pids = new ArrayList<>();
pids.add(pid);
}
}

12
dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/bipaffiliations/input_actionset_parameter.json
View File

@ -6,9 +6,15 @@
"paramRequired": false
},
{
"paramName": "ip",
"paramLongName": "inputPath",
"paramDescription": "the URL from where to get the programme file",
"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",
"paramRequired": true
},
{

3
dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/bipaffiliations/job.properties
View File

@ -31,5 +31,6 @@ spark2SqlQueryExecutionListeners=com.cloudera.spark.lineage.NavigatorQueryListen
# The following is needed as a property of a workflow
oozie.wf.application.path=${oozieTopWfApplicationPath}
inputPath=/data/bip-affiliations/data.json
crossrefInputPath=/data/bip-affiliations/data.json
pubmedInputPath=/data/bip-affiliations/pubmed-data.json
outputPath=/tmp/crossref-affiliations-output-v5

13
dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/bipaffiliations/oozie_app/workflow.xml
View File

@ -2,8 +2,12 @@
<parameters>
<property>
<name>inputPath</name>
<description>the path where to find the inferred affiliation relations</description>
<name>crossrefInputPath</name>
<description>the path where to find the inferred affiliation relations from Crossref</description>
</property>
<property>
<name>pubmedInputPath</name>
<description>the path where to find the inferred affiliation relations from Pubmed</description>
</property>
<property>
<name>outputPath</name>
@ -83,7 +87,7 @@
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Produces the atomic action with the inferred by BIP! affiliation relations from Crossref</name>
<name>Produces the atomic action with the inferred by BIP! affiliation relations (from Crossref and Pubmed)</name>
<class>eu.dnetlib.dhp.actionmanager.bipaffiliations.PrepareAffiliationRelations</class>
<jar>dhp-aggregation-${projectVersion}.jar</jar>
<spark-opts>
@ -96,7 +100,8 @@
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--inputPath</arg><arg>${inputPath}</arg>
<arg>--crossrefInputPath</arg><arg>${crossrefInputPath}</arg>
<arg>--pubmedInputPath</arg><arg>${pubmedInputPath}</arg>
<arg>--outputPath</arg><arg>${outputPath}</arg>
</spark>
<ok to="End"/>

33
dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/createunresolvedentities/oozie_app/workflow.xml
View File

@ -5,11 +5,6 @@
<name>fosPath</name>
<description>the input path of the resources to be extended</description>
</property>
<property>
<name>bipScorePath</name>
<description>the path where to find the bipFinder scores</description>
</property>
<property>
<name>outputPath</name>
<description>the path where to store the actionset</description>
@ -77,35 +72,10 @@
<fork name="prepareInfo">
<path start="prepareBip"/>
<path start="getFOS"/>
<path start="getSDG"/>
</fork>
<action name="prepareBip">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Produces the unresolved from BIP! Finder</name>
<class>eu.dnetlib.dhp.actionmanager.createunresolvedentities.PrepareBipFinder</class>
<jar>dhp-aggregation-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${bipScorePath}</arg>
<arg>--outputPath</arg><arg>${workingDir}/prepared</arg>
</spark>
<ok to="join"/>
<error to="Kill"/>
</action>
<action name="getFOS">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
@ -125,6 +95,7 @@
</spark-opts>
<arg>--sourcePath</arg><arg>${fosPath}</arg>
<arg>--outputPath</arg><arg>${workingDir}/input/fos</arg>
<arg>--delimiter</arg><arg>${delimiter}</arg>
</spark>
<ok to="prepareFos"/>
<error to="Kill"/>
@ -213,7 +184,7 @@
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Saves the result produced for bip and fos by grouping results with the same id</name>
<name>Save the unresolved entities grouping results with the same id</name>
<class>eu.dnetlib.dhp.actionmanager.createunresolvedentities.SparkSaveUnresolved</class>
<jar>dhp-aggregation-${projectVersion}.jar</jar>
<spark-opts>

13
dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/opencitations/as_parameters.json
View File

@ -16,10 +16,11 @@
"paramLongName": "isSparkSessionManaged",
"paramDescription": "the hdfs name node",
"paramRequired": false
}, {
"paramName": "sdr",
"paramLongName": "shouldDuplicateRels",
"paramDescription": "the hdfs name node",
"paramRequired": false
}
},
{
"paramName": "sdr",
"paramLongName": "shouldDuplicateRels",
"paramDescription": "activates/deactivates the construction of bidirectional relations Cites/IsCitedBy",
"paramRequired": false
}
]

6
dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/opencitations/input_parameters.json
View File

@ -16,5 +16,11 @@
"paramLongName": "hdfsNameNode",
"paramDescription": "the hdfs name node",
"paramRequired": true
},
{
"paramName": "p",
"paramLongName": "prefix",
"paramDescription": "COCI or POCI",
"paramRequired": true
}
]

7
dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/opencitations/input_readcoci_parameters.json
View File

@ -30,7 +30,12 @@
"paramLongName": "inputFile",
"paramDescription": "the hdfs name node",
"paramRequired": true
}
}, {
"paramName": "f",
"paramLongName": "format",
"paramDescription": "the hdfs name node",
"paramRequired": true
}
]

14
dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/opencitations/oozie_app/workflow.xml
View File

@ -34,6 +34,7 @@
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="download">
<shell xmlns="uri:oozie:shell-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
@ -46,7 +47,7 @@
</configuration>
<exec>download.sh</exec>
<argument>${filelist}</argument>
<argument>${workingPath}/Original</argument>
<argument>${workingPath}/${prefix}/Original</argument>
<env-var>HADOOP_USER_NAME=${wf:user()}</env-var>
<file>download.sh</file>
<capture-output/>
@ -54,12 +55,14 @@
<ok to="extract"/>
<error to="Kill"/>
</action>
<action name="extract">
<java>
<main-class>eu.dnetlib.dhp.actionmanager.opencitations.GetOpenCitationsRefs</main-class>
<arg>--hdfsNameNode</arg><arg>${nameNode}</arg>
<arg>--inputFile</arg><arg>${inputFile}</arg>
<arg>--workingPath</arg><arg>${workingPath}</arg>
<arg>--workingPath</arg><arg>${workingPath}/${prefix}</arg>
<arg>--prefix</arg><arg>${prefix}</arg>
</java>
<ok to="read"/>
<error to="Kill"/>
@ -82,10 +85,11 @@
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--workingPath</arg><arg>${workingPath}/COCI</arg>
<arg>--outputPath</arg><arg>${workingPath}/COCI_JSON/</arg>
<arg>--workingPath</arg><arg>${workingPath}/${prefix}/${prefix}</arg>
<arg>--outputPath</arg><arg>${workingPath}/${prefix}/${prefix}_JSON/</arg>
<arg>--delimiter</arg><arg>${delimiter}</arg>
<arg>--inputFile</arg><arg>${inputFileCoci}</arg>
<arg>--format</arg><arg>${prefix}</arg>
</spark>
<ok to="create_actionset"/>
<error to="Kill"/>
@ -108,7 +112,7 @@
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--inputPath</arg><arg>${workingPath}/COCI_JSON</arg>
<arg>--inputPath</arg><arg>${workingPath}</arg>
<arg>--outputPath</arg><arg>${outputPath}</arg>
</spark>
<ok to="End"/>

21
dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/collection/orcid/download_orcid_parameter.json Normal file
View File

@ -0,0 +1,21 @@
[
{
"paramName": "n",
"paramLongName": "namenode",
"paramDescription": "the Name Node URI",
"paramRequired": true
},
{
"paramName": "t",
"paramLongName": "targetPath",
"paramDescription": "the target PATH where download the files",
"paramRequired": true
},
{
"paramName": "a",
"paramLongName": "apiURL",
"paramDescription": "the FIGSHARE API id URL to retrieve all the dump files",
"paramRequired": true
}
]

21
dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/collection/orcid/extract_orcid_parameter.json Normal file
View File

@ -0,0 +1,21 @@
[
{
"paramName": "n",
"paramLongName": "namenode",
"paramDescription": "the Name Node URI",
"paramRequired": true
},
{
"paramName": "t",
"paramLongName": "targetPath",
"paramDescription": "the target PATH to extract files",
"paramRequired": true
},
{
"paramName": "s",
"paramLongName": "sourcePath",
"paramDescription": "the PATH where the tar.gz files were downloaded",
"paramRequired": true
}
]

21
dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/collection/orcid/generate_orcid_table_parameter.json Normal file
View File

@ -0,0 +1,21 @@
[
{
"paramName": "m",
"paramLongName": "master",
"paramDescription": "the master name",
"paramRequired": true
},
{
"paramName": "t",
"paramLongName": "targetPath",
"paramDescription": "the target PATH of the DF tables",
"paramRequired": true
},
{
"paramName": "s",
"paramLongName": "sourcePath",
"paramDescription": "the PATH of the ORCID sequence file",
"paramRequired": true
}
]

23
dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/collection/orcid/oozie_app/config-default.xml Normal file
View File

@ -0,0 +1,23 @@
<configuration>
<property>
<name>jobTracker</name>
<value>yarnRM</value>
</property>
<property>
<name>nameNode</name>
<value>hdfs://nameservice1</value>
</property>
<property>
<name>oozie.use.system.libpath</name>
<value>true</value>
</property>
<property>
<name>oozie.action.sharelib.for.spark</name>
<value>spark2</value>
</property>
<property>
<name>oozie.launcher.mapreduce.user.classpath.first</name>
<value>true</value>
</property>
</configuration>

81
dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/collection/orcid/oozie_app/workflow.xml Normal file
View File

@ -0,0 +1,81 @@
<workflow-app name="download_ORCID_DUMP" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>targetPath</name>
<description>the path to store the original ORCID dump</description>
</property>
<property>
<name>apiURL</name>
<description>The figshare API URL to retrieve the list file to download</description>
</property>
</parameters>
<start to="generateTables"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="DownloadDUMP">
<java>
<configuration>
<property>
<name>oozie.launcher.mapreduce.user.classpath.first</name>
<value>true</value>
</property>
</configuration>
<main-class>eu.dnetlib.dhp.collection.orcid.DownloadORCIDDumpApplication</main-class>
<arg>--namenode</arg><arg>${nameNode}</arg>
<arg>--targetPath</arg><arg>${targetPath}</arg>
<arg>--apiURL</arg><arg>${apiURL}</arg>
</java>
<ok to="extractDump"/>
<error to="Kill"/>
</action>
<action name="extractDump">
<java>
<configuration>
<property>
<name>oozie.launcher.mapreduce.user.classpath.first</name>
<value>true</value>
</property>
</configuration>
<main-class>eu.dnetlib.dhp.collection.orcid.ExtractORCIDDump</main-class>
<java-opts> -Xmx6g </java-opts>
<arg>--namenode</arg><arg>${nameNode}</arg>
<arg>--sourcePath</arg><arg>${targetPath}</arg>
<arg>--targetPath</arg><arg>${targetPath}/extracted</arg>
</java>
<ok to="generateTables"/>
<error to="Kill"/>
</action>
<action name="generateTables">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Generate ORCID Tables</name>
<class>eu.dnetlib.dhp.collection.orcid.SparkGenerateORCIDTable</class>
<jar>dhp-aggregation-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.executor.memoryOverhead=2g
--conf spark.sql.shuffle.partitions=3000
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${targetPath}/extracted</arg>
<arg>--targetPath</arg><arg>${targetPath}/tables</arg>
<arg>--master</arg><arg>yarn</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>

21
dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/collection/orcid/preprocess_orcid_dump_parameter.json Normal file
View File

@ -0,0 +1,21 @@
[
{
"paramName": "n",
"paramLongName": "namenode",
"paramDescription": "the Name Node URI",
"paramRequired": true
},
{
"paramName": "t",
"paramLongName": "targetPath",
"paramDescription": "the target PATH where download the files",
"paramRequired": true
},
{
"paramName": "a",
"paramLongName": "apiURL",
"paramDescription": "the FIGSHARE API id URL to retrieve all the dump files",
"paramRequired": true
}
]

101
dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/collection/orcid/SparkGenerateORCIDTable.scala Normal file
View File

@ -0,0 +1,101 @@
package eu.dnetlib.dhp.collection.orcid
import eu.dnetlib.dhp.application.AbstractScalaApplication
import eu.dnetlib.dhp.collection.orcid.model.{Author, Employment, Pid, Work}
import org.apache.hadoop.io.Text
import org.apache.spark.SparkContext
import org.apache.spark.sql.{Encoder, Encoders, SaveMode, SparkSession}
import org.slf4j.{Logger, LoggerFactory}
class SparkGenerateORCIDTable(propertyPath: String, args: Array[String], log: Logger)
extends AbstractScalaApplication(propertyPath, args, log: Logger) {
/** Here all the spark applications runs this method
* where the whole logic of the spark node is defined
*/
override def run(): Unit = {
val sourcePath: String = parser.get("sourcePath")
log.info("found parameters sourcePath: {}", sourcePath)
val targetPath: String = parser.get("targetPath")
log.info("found parameters targetPath: {}", targetPath)
extractORCIDTable(spark, sourcePath, targetPath)
extractORCIDEmploymentsTable(spark, sourcePath, targetPath)
extractORCIDWorksTable(spark, sourcePath, targetPath)
}
def extractORCIDTable(spark: SparkSession, sourcePath: String, targetPath: String): Unit = {
val sc: SparkContext = spark.sparkContext
import spark.implicits._
val df = sc
.sequenceFile(sourcePath, classOf[Text], classOf[Text])
.map { case (x, y) => (x.toString, y.toString) }
.toDF
.as[(String, String)]
implicit val orcidAuthor: Encoder[Author] = Encoders.bean(classOf[Author])
// implicit val orcidPID:Encoder[Pid] = Encoders.bean(classOf[Pid])
df.filter(r => r._1.contains("summaries"))
.map { r =>
val p = new OrcidParser
p.parseSummary(r._2)
}
.filter(p => p != null)
.write
.mode(SaveMode.Overwrite)
.save(s"$targetPath/Authors")
}
def extractORCIDWorksTable(spark: SparkSession, sourcePath: String, targetPath: String): Unit = {
val sc: SparkContext = spark.sparkContext
import spark.implicits._
val df = sc
.sequenceFile(sourcePath, classOf[Text], classOf[Text])
.map { case (x, y) => (x.toString, y.toString) }
.toDF
.as[(String, String)]
implicit val orcidWorkAuthor: Encoder[Work] = Encoders.bean(classOf[Work])
implicit val orcidPID: Encoder[Pid] = Encoders.bean(classOf[Pid])
df.filter(r => r._1.contains("works"))
.map { r =>
val p = new OrcidParser
p.parseWork(r._2)
}
.filter(p => p != null)
.write
.mode(SaveMode.Overwrite)
.save(s"$targetPath/Works")
}
def extractORCIDEmploymentsTable(spark: SparkSession, sourcePath: String, targetPath: String): Unit = {
val sc: SparkContext = spark.sparkContext
import spark.implicits._
val df = sc
.sequenceFile(sourcePath, classOf[Text], classOf[Text])
.map { case (x, y) => (x.toString, y.toString) }
.toDF
.as[(String, String)]
implicit val orcidEmploymentAuthor: Encoder[Employment] = Encoders.bean(classOf[Employment])
implicit val orcidPID: Encoder[Pid] = Encoders.bean(classOf[Pid])
df.filter(r => r._1.contains("employments"))
.map { r =>
val p = new OrcidParser
p.parseEmployment(r._2)
}
.filter(p => p != null)
.write
.mode(SaveMode.Overwrite)
.save(s"$targetPath/Employments")
}
}
object SparkGenerateORCIDTable {
val log: Logger = LoggerFactory.getLogger(SparkGenerateORCIDTable.getClass)
def main(args: Array[String]): Unit = {
new SparkGenerateORCIDTable("/eu/dnetlib/dhp/collection/orcid/generate_orcid_table_parameter.json", args, log)
.initialize()
.run()
}
}

19
dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/datacite/DataciteToOAFTransformation.scala
View File

@ -166,7 +166,7 @@ object DataciteToOAFTransformation {
resourceTypeGeneral: String,
schemaOrg: String,
vocabularies: VocabularyGroup
): (Qualifier, Qualifier) = {
): (Qualifier, Qualifier, String) = {
if (resourceType != null && resourceType.nonEmpty) {
val typeQualifier =
vocabularies.getSynonymAsQualifier(ModelConstants.DNET_PUBLICATION_RESOURCE, resourceType)
@ -176,7 +176,8 @@ object DataciteToOAFTransformation {
vocabularies.getSynonymAsQualifier(
ModelConstants.DNET_RESULT_TYPOLOGIES,
typeQualifier.getClassid
)
),
resourceType
)
}
if (schemaOrg != null && schemaOrg.nonEmpty) {
@ -188,7 +189,8 @@ object DataciteToOAFTransformation {
vocabularies.getSynonymAsQualifier(
ModelConstants.DNET_RESULT_TYPOLOGIES,
typeQualifier.getClassid
)
),
schemaOrg
)
}
@ -203,7 +205,8 @@ object DataciteToOAFTransformation {
vocabularies.getSynonymAsQualifier(
ModelConstants.DNET_RESULT_TYPOLOGIES,
typeQualifier.getClassid
)
),
resourceTypeGeneral
)
}
@ -216,12 +219,18 @@ object DataciteToOAFTransformation {
schemaOrg: String,
vocabularies: VocabularyGroup
): Result = {
val typeQualifiers: (Qualifier, Qualifier) =
val typeQualifiers: (Qualifier, Qualifier, String) =
getTypeQualifier(resourceType, resourceTypeGeneral, schemaOrg, vocabularies)
if (typeQualifiers == null)
return null
val i = new Instance
i.setInstancetype(typeQualifiers._1)
// ADD ORIGINAL TYPE
val itm = new InstanceTypeMapping
itm.setOriginalType(typeQualifiers._3)
itm.setVocabularyName(ModelConstants.OPENAIRE_COAR_RESOURCE_TYPES_3_1)
i.setInstanceTypeMapping(List(itm).asJava)
typeQualifiers._2.getClassname match {
case "dataset" =>
val r = new OafDataset

25
dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/sx/bio/BioDBToOAF.scala
View File

@ -176,7 +176,7 @@ object BioDBToOAF {
i.setUrl(List(s"${resolvedURL(input.pidType)}${input.pid}").asJava)
}
if (input.pidType.equalsIgnoreCase("clinicaltrials.gov"))
if (input.pidType.equalsIgnoreCase("clinicaltrials.gov")) {
i.setInstancetype(
OafMapperUtils.qualifier(
"0037",
@ -185,7 +185,11 @@ object BioDBToOAF {
ModelConstants.DNET_PUBLICATION_RESOURCE
)
)
else
val itm = new InstanceTypeMapping
itm.setOriginalType(input.pidType)
itm.setVocabularyName(ModelConstants.OPENAIRE_COAR_RESOURCE_TYPES_3_1)
i.setInstanceTypeMapping(List(itm).asJava)
} else {
i.setInstancetype(
OafMapperUtils.qualifier(
"0046",
@ -194,6 +198,11 @@ object BioDBToOAF {
ModelConstants.DNET_PUBLICATION_RESOURCE
)
)
val itm = new InstanceTypeMapping
itm.setOriginalType("Bioentity")
itm.setVocabularyName(ModelConstants.OPENAIRE_COAR_RESOURCE_TYPES_3_1)
i.setInstanceTypeMapping(List(itm).asJava)
}
if (input.datasource == null || input.datasource.isEmpty)
return null
@ -265,6 +274,10 @@ object BioDBToOAF {
ModelConstants.DNET_PUBLICATION_RESOURCE
)
)
val itm = new InstanceTypeMapping
itm.setOriginalType("Bioentity")
itm.setVocabularyName(ModelConstants.OPENAIRE_COAR_RESOURCE_TYPES_3_1)
i.setInstanceTypeMapping(List(itm).asJava)
i.setCollectedfrom(collectedFromMap("uniprot"))
d.setInstance(List(i).asJava)
@ -471,6 +484,10 @@ object BioDBToOAF {
ModelConstants.DNET_PUBLICATION_RESOURCE
)
)
val itm = new InstanceTypeMapping
itm.setOriginalType("Bioentity")
itm.setVocabularyName(ModelConstants.OPENAIRE_COAR_RESOURCE_TYPES_3_1)
i.setInstanceTypeMapping(List(itm).asJava)
i.setCollectedfrom(collectedFromMap("pdb"))
d.setInstance(List(i).asJava)
@ -571,6 +588,10 @@ object BioDBToOAF {
ModelConstants.DNET_PUBLICATION_RESOURCE
)
)
val itm = new InstanceTypeMapping
itm.setOriginalType("Bioentity")
itm.setVocabularyName(ModelConstants.OPENAIRE_COAR_RESOURCE_TYPES_3_1)
i.setInstanceTypeMapping(List(itm).asJava)
i.setCollectedfrom(collectedFromMap("ebi"))
d.setInstance(List(i).asJava)

21
dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/sx/bio/pubmed/PubMedToOaf.scala
View File

@ -188,13 +188,24 @@ object PubMedToOaf {
val cojbCategory =
getVocabularyTerm(ModelConstants.DNET_PUBLICATION_RESOURCE, vocabularies, ja.get.getValue)
pubmedInstance.setInstancetype(cojbCategory)
// ADD ORIGINAL TYPE to the publication
val itm = new InstanceTypeMapping
itm.setOriginalType(ja.get.getValue)
itm.setVocabularyName(ModelConstants.OPENAIRE_COAR_RESOURCE_TYPES_3_1)
pubmedInstance.setInstanceTypeMapping(List(itm).asJava)
} else {
val i_type = article.getPublicationTypes.asScala
.map(s => getVocabularyTerm(ModelConstants.DNET_PUBLICATION_RESOURCE, vocabularies, s.getValue))
.find(q => q != null)
if (i_type.isDefined)
pubmedInstance.setInstancetype(i_type.get)
else
.map(s => (s.getValue, getVocabularyTerm(ModelConstants.DNET_PUBLICATION_RESOURCE, vocabularies, s.getValue)))
.find(q => q._2 != null)
if (i_type.isDefined) {
pubmedInstance.setInstancetype(i_type.get._2)
// ADD ORIGINAL TYPE to the publication
val itm = new InstanceTypeMapping
itm.setOriginalType(i_type.get._1)
itm.setVocabularyName(ModelConstants.OPENAIRE_COAR_RESOURCE_TYPES_3_1)
pubmedInstance.setInstanceTypeMapping(List(itm).asJava)
} else
return null
}
val result = createResult(pubmedInstance.getInstancetype, vocabularies)

15
dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/actionmanager/bipaffiliations/PrepareAffiliationRelationsTest.java
View File

@ -74,7 +74,11 @@ public class PrepareAffiliationRelationsTest {
@Test
void testMatch() throws Exception {
String affiliationRelationsPath = getClass()
String crossrefAffiliationRelationPath = getClass()
.getResource("/eu/dnetlib/dhp/actionmanager/bipaffiliations/doi_to_ror.json")
.getPath();
String pubmedAffiliationRelationsPath = getClass()
.getResource("/eu/dnetlib/dhp/actionmanager/bipaffiliations/doi_to_ror.json")
.getPath();
@ -84,7 +88,8 @@ public class PrepareAffiliationRelationsTest {
.main(
new String[] {
"-isSparkSessionManaged", Boolean.FALSE.toString(),
"-inputPath", affiliationRelationsPath,
"-crossrefInputPath", crossrefAffiliationRelationPath,
"-pubmedInputPath", pubmedAffiliationRelationsPath,
"-outputPath", outputPath
});
@ -101,7 +106,7 @@ public class PrepareAffiliationRelationsTest {
// );
// }
// count the number of relations
assertEquals(20, tmp.count());
assertEquals(40, tmp.count());
Dataset<Relation> dataset = spark.createDataset(tmp.rdd(), Encoders.bean(Relation.class));
dataset.createOrReplaceTempView("result");
@ -112,7 +117,7 @@ public class PrepareAffiliationRelationsTest {
// verify that we have equal number of bi-directional relations
Assertions
.assertEquals(
10, execVerification
20, execVerification
.filter(
"relClass='" + ModelConstants.HAS_AUTHOR_INSTITUTION + "'")
.collectAsList()
@ -120,7 +125,7 @@ public class PrepareAffiliationRelationsTest {
Assertions
.assertEquals(
10, execVerification
20, execVerification
.filter(
"relClass='" + ModelConstants.IS_AUTHOR_INSTITUTION_OF + "'")
.collectAsList()

39
dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/actionmanager/createunresolvedentities/GetFosTest.java
View File

@ -13,10 +13,7 @@ import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.sql.SparkSession;
import org.junit.jupiter.api.AfterAll;
import org.junit.jupiter.api.Assertions;
import org.junit.jupiter.api.BeforeAll;
import org.junit.jupiter.api.Test;
import org.junit.jupiter.api.*;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
@ -68,6 +65,7 @@ public class GetFosTest {
}
@Test
@Disabled
void test3() throws Exception {
final String sourcePath = getClass()
.getResource("/eu/dnetlib/dhp/actionmanager/createunresolvedentities/fos/fos_sbs.tsv")
@ -96,4 +94,37 @@ public class GetFosTest {
tmp.foreach(t -> Assertions.assertTrue(t.getLevel3() != null));
}
@Test
void test4() throws Exception {
final String sourcePath = getClass()
.getResource("/eu/dnetlib/dhp/actionmanager/createunresolvedentities/fos/fos_sbs2.csv")
.getPath();
final String outputPath = workingDir.toString() + "/fos.json";
GetFOSSparkJob
.main(
new String[] {
"--isSparkSessionManaged", Boolean.FALSE.toString(),
"--sourcePath", sourcePath,
"--delimiter", ",",
"-outputPath", outputPath
});
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
JavaRDD<FOSDataModel> tmp = sc
.textFile(outputPath)
.map(item -> OBJECT_MAPPER.readValue(item, FOSDataModel.class));
tmp.foreach(t -> Assertions.assertTrue(t.getDoi() != null));
tmp.foreach(t -> Assertions.assertTrue(t.getLevel1() != null));
tmp.foreach(t -> Assertions.assertTrue(t.getLevel2() != null));
tmp.foreach(t -> Assertions.assertTrue(t.getLevel3() != null));
tmp.foreach(t -> Assertions.assertTrue(t.getLevel4() != null));
tmp.foreach(t -> Assertions.assertTrue(t.getScoreL3() != null));
tmp.foreach(t -> Assertions.assertTrue(t.getScoreL4() != null));
}
}

209
dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/actionmanager/createunresolvedentities/PrepareTest.java
View File

@ -67,92 +67,6 @@ public class PrepareTest {
spark.stop();
}
@Test
void bipPrepareTest() throws Exception {
final String sourcePath = getClass()
.getResource("/eu/dnetlib/dhp/actionmanager/createunresolvedentities/bip/bip.json")
.getPath();
PrepareBipFinder
.main(
new String[] {
"--isSparkSessionManaged", Boolean.FALSE.toString(),
"--sourcePath", sourcePath,
"--outputPath", workingDir.toString() + "/work"
});
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
JavaRDD<Result> tmp = sc
.textFile(workingDir.toString() + "/work/bip")
.map(item -> OBJECT_MAPPER.readValue(item, Result.class));
Assertions.assertEquals(86, tmp.count());
String doi1 = "unresolved::10.0000/096020199389707::doi";
Assertions.assertEquals(1, tmp.filter(r -> r.getId().equals(doi1)).count());
Assertions.assertEquals(1, tmp.filter(r -> r.getId().equals(doi1)).collect().get(0).getInstance().size());
Assertions
.assertEquals(
3, tmp.filter(r -> r.getId().equals(doi1)).collect().get(0).getInstance().get(0).getMeasures().size());
Assertions
.assertEquals(
"6.34596412687e-09", tmp
.filter(r -> r.getId().equals(doi1))
.collect()
.get(0)
.getInstance()
.get(0)
.getMeasures()
.stream()
.filter(sl -> sl.getId().equals("influence"))
.collect(Collectors.toList())
.get(0)
.getUnit()
.get(0)
.getValue());
Assertions
.assertEquals(
"0.641151896994", tmp
.filter(r -> r.getId().equals(doi1))
.collect()
.get(0)
.getInstance()
.get(0)
.getMeasures()
.stream()
.filter(sl -> sl.getId().equals("popularity_alt"))
.collect(Collectors.toList())
.get(0)
.getUnit()
.get(0)
.getValue());
Assertions
.assertEquals(
"2.33375102921e-09", tmp
.filter(r -> r.getId().equals(doi1))
.collect()
.get(0)
.getInstance()
.get(0)
.getMeasures()
.stream()
.filter(sl -> sl.getId().equals("popularity"))
.collect(Collectors.toList())
.get(0)
.getUnit()
.get(0)
.getValue());
final String doi2 = "unresolved::10.3390/s18072310::doi";
Assertions.assertEquals(1, tmp.filter(r -> r.getId().equals(doi2)).count());
Assertions.assertEquals(1, tmp.filter(r -> r.getId().equals(doi2)).collect().get(0).getInstance().size());
}
@Test
void fosPrepareTest() throws Exception {
final String sourcePath = getClass()
@ -222,6 +136,76 @@ public class PrepareTest {
}
@Test
void fosPrepareTest2() throws Exception {
final String sourcePath = getClass()
.getResource("/eu/dnetlib/dhp/actionmanager/createunresolvedentities/fos/fos_sbs_2.json")
.getPath();
PrepareFOSSparkJob
.main(
new String[] {
"--isSparkSessionManaged", Boolean.FALSE.toString(),
"--sourcePath", sourcePath,
"-outputPath", workingDir.toString() + "/work"
});
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
JavaRDD<Result> tmp = sc
.textFile(workingDir.toString() + "/work/fos")
.map(item -> OBJECT_MAPPER.readValue(item, Result.class));
String doi1 = "unresolved::10.1016/j.revmed.2006.07.012::doi";
assertEquals(13, tmp.count());
assertEquals(1, tmp.filter(row -> row.getId().equals(doi1)).count());
Result result = tmp
.filter(r -> r.getId().equals(doi1))
.first();
result.getSubject().forEach(s -> System.out.println(s.getValue() + " trust = " + s.getDataInfo().getTrust()));
Assertions.assertEquals(6, result.getSubject().size());
assertTrue(
result
.getSubject()
.stream()
.anyMatch(
s -> s.getValue().contains("03 medical and health sciences")
&& s.getDataInfo().getTrust().equals("")));
assertTrue(
result
.getSubject()
.stream()
.anyMatch(
s -> s.getValue().contains("0302 clinical medicine") && s.getDataInfo().getTrust().equals("")));
assertTrue(
result
.getSubject()
.stream()
.anyMatch(
s -> s
.getValue()
.contains("030204 cardiovascular system & hematology")
&& s.getDataInfo().getTrust().equals("0.5101401805877686")));
assertTrue(
result
.getSubject()
.stream()
.anyMatch(
s -> s
.getValue()
.contains("03020409 Hematology/Coagulopathies")
&& s.getDataInfo().getTrust().equals("0.0546871414174914")));
}
@Test
void sdgPrepareTest() throws Exception {
final String sourcePath = getClass()
@ -268,57 +252,4 @@ public class PrepareTest {
}
// @Test
// void test3() throws Exception {
// final String sourcePath = "/Users/miriam.baglioni/Downloads/doi_fos_results_20_12_2021.csv.gz";
//
// final String outputPath = workingDir.toString() + "/fos.json";
// GetFOSSparkJob
// .main(
// new String[] {
// "--isSparkSessionManaged", Boolean.FALSE.toString(),
// "--sourcePath", sourcePath,
//
// "-outputPath", outputPath
//
// });
//
// final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
//
// JavaRDD<FOSDataModel> tmp = sc
// .textFile(outputPath)
// .map(item -> OBJECT_MAPPER.readValue(item, FOSDataModel.class));
//
// tmp.foreach(t -> Assertions.assertTrue(t.getDoi() != null));
// tmp.foreach(t -> Assertions.assertTrue(t.getLevel1() != null));
// tmp.foreach(t -> Assertions.assertTrue(t.getLevel2() != null));
// tmp.foreach(t -> Assertions.assertTrue(t.getLevel3() != null));
//
// }
//
// @Test
// void test4() throws Exception {
// final String sourcePath = "/Users/miriam.baglioni/Downloads/doi_sdg_results_20_12_21.csv.gz";
//
// final String outputPath = workingDir.toString() + "/sdg.json";
// GetSDGSparkJob
// .main(
// new String[] {
// "--isSparkSessionManaged", Boolean.FALSE.toString(),
// "--sourcePath", sourcePath,
//
// "-outputPath", outputPath
//
// });
//
// final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
//
// JavaRDD<SDGDataModel> tmp = sc
// .textFile(outputPath)
// .map(item -> OBJECT_MAPPER.readValue(item, SDGDataModel.class));
//
// tmp.foreach(t -> Assertions.assertTrue(t.getDoi() != null));
// tmp.foreach(t -> Assertions.assertTrue(t.getSbj() != null));
//
// }
}

64
dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/actionmanager/createunresolvedentities/ProduceTest.java
View File

@ -340,18 +340,7 @@ public class ProduceTest {
}
private JavaRDD<Result> getResultJavaRDD() throws Exception {
final String bipPath = getClass()
.getResource("/eu/dnetlib/dhp/actionmanager/createunresolvedentities/bip/bip.json")
.getPath();
PrepareBipFinder
.main(
new String[] {
"--isSparkSessionManaged", Boolean.FALSE.toString(),
"--sourcePath", bipPath,
"--outputPath", workingDir.toString() + "/work"
});
final String fosPath = getClass()
.getResource("/eu/dnetlib/dhp/actionmanager/createunresolvedentities/fos/fos.json")
.getPath();
@ -379,6 +368,40 @@ public class ProduceTest {
.map(item -> OBJECT_MAPPER.readValue(item, Result.class));
}
@Test
public JavaRDD<Result> getResultFosJavaRDD() throws Exception {
final String fosPath = getClass()
.getResource("/eu/dnetlib/dhp/actionmanager/createunresolvedentities/fos/fos_sbs_2.json")
.getPath();
PrepareFOSSparkJob
.main(
new String[] {
"--isSparkSessionManaged", Boolean.FALSE.toString(),
"--sourcePath", fosPath,
"-outputPath", workingDir.toString() + "/work"
});
SparkSaveUnresolved.main(new String[] {
"--isSparkSessionManaged", Boolean.FALSE.toString(),
"--sourcePath", workingDir.toString() + "/work",
"-outputPath", workingDir.toString() + "/unresolved"
});
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
JavaRDD<Result> tmp = sc
.textFile(workingDir.toString() + "/unresolved")
.map(item -> OBJECT_MAPPER.readValue(item, Result.class));
tmp.foreach(r -> System.out.println(new ObjectMapper().writeValueAsString(r)));
return tmp;
}
@Test
void prepareTest5Subjects() throws Exception {
final String doi = "unresolved::10.1063/5.0032658::doi";
@ -415,18 +438,7 @@ public class ProduceTest {
}
private JavaRDD<Result> getResultJavaRDDPlusSDG() throws Exception {
final String bipPath = getClass()
.getResource("/eu/dnetlib/dhp/actionmanager/createunresolvedentities/bip/bip.json")
.getPath();
PrepareBipFinder
.main(
new String[] {
"--isSparkSessionManaged", Boolean.FALSE.toString(),
"--sourcePath", bipPath,
"--outputPath", workingDir.toString() + "/work"
});
final String fosPath = getClass()
.getResource("/eu/dnetlib/dhp/actionmanager/createunresolvedentities/fos/fos.json")
.getPath();
@ -483,14 +495,6 @@ public class ProduceTest {
.filter(row -> row.getSubject() != null)
.count());
Assertions
.assertEquals(
85,
tmp
.filter(row -> !row.getId().equals(doi))
.filter(r -> r.getInstance() != null && r.getInstance().size() > 0)
.count());
}
@Test

119
dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/collection/orcid/DownloadORCIDTest.java Normal file
View File

@ -0,0 +1,119 @@
package eu.dnetlib.dhp.collection.orcid;
import java.io.IOException;
import java.util.Arrays;
import java.util.List;
import java.util.Objects;
import org.apache.commons.io.IOUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.io.Text;
import org.apache.spark.SparkContext;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.SparkSession;
import org.junit.jupiter.api.Test;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.core.JsonProcessingException;
import com.fasterxml.jackson.databind.ObjectMapper;
import com.ximpleware.NavException;
import com.ximpleware.ParseException;
import com.ximpleware.XPathEvalException;
import com.ximpleware.XPathParseException;
import eu.dnetlib.dhp.collection.orcid.model.Author;
import eu.dnetlib.dhp.collection.orcid.model.ORCIDItem;
import eu.dnetlib.dhp.parser.utility.VtdException;
public class DownloadORCIDTest {
private final Logger log = LoggerFactory.getLogger(DownloadORCIDTest.class);
@Test
public void testSummary() throws Exception {
final String xml = IOUtils
.toString(
Objects.requireNonNull(getClass().getResourceAsStream("/eu/dnetlib/dhp/collection/orcid/summary.xml")));
final OrcidParser parser = new OrcidParser();
ORCIDItem orcidItem = parser.parseSummary(xml);
final ObjectMapper mapper = new ObjectMapper();
System.out.println(mapper.writeValueAsString(orcidItem));
}
@Test
public void testParsingWork() throws Exception {
final List<String> works_path = Arrays
.asList(
"/eu/dnetlib/dhp/collection/orcid/activity_work_0000-0002-2536-4498.xml",
"/eu/dnetlib/dhp/collection/orcid/activity_work_0000-0002-5982-8983.xml",
"/eu/dnetlib/dhp/collection/orcid/activity_work_0000-0003-2760-1191.xml",
"/eu/dnetlib/dhp/collection/orcid/activity_work_0000-0003-2760-1191-similarity.xml",
"/eu/dnetlib/dhp/collection/orcid/activity_work_0000-0003-2760-1191_contributors.xml"
);
final OrcidParser parser = new OrcidParser();
final ObjectMapper mapper = new ObjectMapper();
works_path.stream().map(s -> {
try {
return IOUtils
.toString(
Objects
.requireNonNull(
getClass()
.getResourceAsStream(
s)));
} catch (IOException e) {
throw new RuntimeException(e);
}
}).forEach(s -> {
try {
System.out.println(mapper.writeValueAsString(parser.parseWork(s)));
} catch (Exception e) {
throw new RuntimeException(e);
}
});
}
@Test
public void testParsingEmployments() throws Exception {
final List<String> works_path = Arrays
.asList(
"/eu/dnetlib/dhp/collection/orcid/employment.xml",
"/eu/dnetlib/dhp/collection/orcid/employment_2.xml",
"/eu/dnetlib/dhp/collection/orcid/employment_3.xml"
);
final OrcidParser parser = new OrcidParser();
final ObjectMapper mapper = new ObjectMapper();
works_path.stream().map(s -> {
try {
return IOUtils
.toString(
Objects
.requireNonNull(
getClass()
.getResourceAsStream(
s)));
} catch (IOException e) {
throw new RuntimeException(e);
}
}).forEach(s -> {
try {
System.out.println(mapper.writeValueAsString(parser.parseEmployment(s)));
} catch (Exception e) {
throw new RuntimeException(e);
}
});
}
}

26
dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/createunresolvedentities/fos/fos_sbs2.csv Normal file
View File

@ -0,0 +1,26 @@
DOI,OAID,level1,level2,level3,level4,score_for_L3,score_for_L4
10.1016/j.anucene.2006.02.004,doi_________::00059d9963edf633bec756fb21b5bd72,02 engineering and technology,"0202 electrical engineering, electronic engineering, information engineering",020209 energy,02020908 Climate change policy/Ethanol fuel,0.5,0.5
10.1016/j.anucene.2006.02.004,doi_________::00059d9963edf633bec756fb21b5bd72,02 engineering and technology,0211 other engineering and technologies,021108 energy,02110808 Climate change policy/Ethanol fuel,0.5,0.5
10.1016/j.revmed.2006.07.010,doi_________::0026476c1651a92c933d752ff12496c7,03 medical and health sciences,0302 clinical medicine,030220 oncology & carcinogenesis,N/A,0.5036656856536865,0.0
10.1016/j.revmed.2006.07.010,doi_________::0026476c1651a92c933d752ff12496c7,03 medical and health sciences,0302 clinical medicine,030212 general & internal medicine,N/A,0.4963343143463135,0.0
10.20965/jrm.2006.p0312,doi_________::0028336a2f3826cc83c47dbefac71543,02 engineering and technology,0209 industrial biotechnology,020901 industrial engineering & automation,02090104 Robotics/Robots,0.6111094951629639,0.5053805979936855
10.20965/jrm.2006.p0312,doi_________::0028336a2f3826cc83c47dbefac71543,01 natural sciences,0104 chemical sciences,010401 analytical chemistry,N/A,0.3888905048370361,0.0
10.1111/j.1747-7379.2006.040_1.x,doi_________::002c7077e7c114a8304eb90f59e45fa4,05 social sciences,0506 political science,050602 political science & public administration,05060202 Ethnic groups/Ethnicity,0.6159052848815918,0.7369035568037298
10.1111/j.1747-7379.2006.040_1.x,doi_________::002c7077e7c114a8304eb90f59e45fa4,05 social sciences,0502 economics and business,050207 economics,N/A,0.3840946555137634,0.0
10.1007/s10512-006-0049-9,doi_________::003f29f9254819cf4c78558b1bc25f10,02 engineering and technology,"0202 electrical engineering, electronic engineering, information engineering",020209 energy,02020908 Climate change policy/Ethanol fuel,0.5,0.5
10.1007/s10512-006-0049-9,doi_________::003f29f9254819cf4c78558b1bc25f10,02 engineering and technology,0211 other engineering and technologies,021108 energy,02110808 Climate change policy/Ethanol fuel,0.5,0.5
10.1111/j.1365-2621.2005.01045.x,doi_________::00419355b4c3e0646bd0e1b301164c8e,04 agricultural and veterinary sciences,0404 agricultural biotechnology,040401 food science,04040102 Food science/Food industry,0.5,0.5
10.1111/j.1365-2621.2005.01045.x,doi_________::00419355b4c3e0646bd0e1b301164c8e,04 agricultural and veterinary sciences,0405 other agricultural sciences,040502 food science,04050202 Food science/Food industry,0.5,0.5
10.1002/chin.200617262,doi_________::004c8cef80668904961b9e62841793c8,01 natural sciences,0104 chemical sciences,010405 organic chemistry,01040508 Functional groups/Ethers,0.5566747188568115,0.5582916736602783
10.1002/chin.200617262,doi_________::004c8cef80668904961b9e62841793c8,01 natural sciences,0104 chemical sciences,010402 general chemistry,01040207 Chemical synthesis/Total synthesis,0.4433253407478332,0.4417082965373993
10.1016/j.revmed.2006.07.012,doi_________::005b1d0fb650b680abaf6cfe26a21604,03 medical and health sciences,0302 clinical medicine,030204 cardiovascular system & hematology,03020409 Hematology/Coagulopathies,0.5101401805877686,0.0546871414174914
10.1016/j.revmed.2006.07.012,doi_________::005b1d0fb650b680abaf6cfe26a21604,03 medical and health sciences,0301 basic medicine,030105 genetics & heredity,N/A,0.4898599088191986,0.0
10.4109/jslab.17.132,doi_________::00889baa06de363e37930daaf8e800c0,03 medical and health sciences,0301 basic medicine,030104 developmental biology,N/A,0.5,0.0
10.4109/jslab.17.132,doi_________::00889baa06de363e37930daaf8e800c0,03 medical and health sciences,0303 health sciences,030304 developmental biology,N/A,0.5,0.0
10.1108/00251740610715687,doi_________::0092cb1b1920d556719385a26363ecaa,05 social sciences,0502 economics and business,050203 business & management,05020311 International business/International trade,0.605047881603241,0.2156608108845153
10.1108/00251740610715687,doi_________::0092cb1b1920d556719385a26363ecaa,05 social sciences,0502 economics and business,050211 marketing,N/A,0.394952118396759,0.0
10.1080/03067310500248098,doi_________::00a76678d230e3f20b6356804448028f,04 agricultural and veterinary sciences,0404 agricultural biotechnology,040401 food science,04040102 Food science/Food industry,0.5,0.5
10.1080/03067310500248098,doi_________::00a76678d230e3f20b6356804448028f,04 agricultural and veterinary sciences,0405 other agricultural sciences,040502 food science,04050202 Food science/Food industry,0.5,0.5
10.3152/147154306781778533,doi_________::00acc520f3939e5a6675343881fed4f2,05 social sciences,0502 economics and business,050203 business & management,05020307 Innovation/Product management,0.5293408632278442,0.5326762795448303
10.3152/147154306781778533,doi_________::00acc520f3939e5a6675343881fed4f2,05 social sciences,0509 other social sciences,050905 science studies,05090502 Social philosophy/Capitalism,0.4706590473651886,0.4673237204551697
10.1785/0120050806,doi_________::00d5831d329e7ae4523d78bfc3042e98,02 engineering and technology,0211 other engineering and technologies,021101 geological & geomatics engineering,02110103 Concrete/Building materials,0.5343400835990906,0.3285667930180677
1 DOI OAID level1 level2 level3 level4 score_for_L3 score_for_L4
2 10.1016/j.anucene.2006.02.004 doi_________::00059d9963edf633bec756fb21b5bd72 02 engineering and technology 0202 electrical engineering, electronic engineering, information engineering 020209 energy 02020908 Climate change policy/Ethanol fuel 0.5 0.5
3 10.1016/j.anucene.2006.02.004 doi_________::00059d9963edf633bec756fb21b5bd72 02 engineering and technology 0211 other engineering and technologies 021108 energy 02110808 Climate change policy/Ethanol fuel 0.5 0.5
4 10.1016/j.revmed.2006.07.010 doi_________::0026476c1651a92c933d752ff12496c7 03 medical and health sciences 0302 clinical medicine 030220 oncology & carcinogenesis N/A 0.5036656856536865 0.0
5 10.1016/j.revmed.2006.07.010 doi_________::0026476c1651a92c933d752ff12496c7 03 medical and health sciences 0302 clinical medicine 030212 general & internal medicine N/A 0.4963343143463135 0.0
6 10.20965/jrm.2006.p0312 doi_________::0028336a2f3826cc83c47dbefac71543 02 engineering and technology 0209 industrial biotechnology 020901 industrial engineering & automation 02090104 Robotics/Robots 0.6111094951629639 0.5053805979936855
7 10.20965/jrm.2006.p0312 doi_________::0028336a2f3826cc83c47dbefac71543 01 natural sciences 0104 chemical sciences 010401 analytical chemistry N/A 0.3888905048370361 0.0
8 10.1111/j.1747-7379.2006.040_1.x doi_________::002c7077e7c114a8304eb90f59e45fa4 05 social sciences 0506 political science 050602 political science & public administration 05060202 Ethnic groups/Ethnicity 0.6159052848815918 0.7369035568037298
9 10.1111/j.1747-7379.2006.040_1.x doi_________::002c7077e7c114a8304eb90f59e45fa4 05 social sciences 0502 economics and business 050207 economics N/A 0.3840946555137634 0.0
10 10.1007/s10512-006-0049-9 doi_________::003f29f9254819cf4c78558b1bc25f10 02 engineering and technology 0202 electrical engineering, electronic engineering, information engineering 020209 energy 02020908 Climate change policy/Ethanol fuel 0.5 0.5
11 10.1007/s10512-006-0049-9 doi_________::003f29f9254819cf4c78558b1bc25f10 02 engineering and technology 0211 other engineering and technologies 021108 energy 02110808 Climate change policy/Ethanol fuel 0.5 0.5
12 10.1111/j.1365-2621.2005.01045.x doi_________::00419355b4c3e0646bd0e1b301164c8e 04 agricultural and veterinary sciences 0404 agricultural biotechnology 040401 food science 04040102 Food science/Food industry 0.5 0.5
13 10.1111/j.1365-2621.2005.01045.x doi_________::00419355b4c3e0646bd0e1b301164c8e 04 agricultural and veterinary sciences 0405 other agricultural sciences 040502 food science 04050202 Food science/Food industry 0.5 0.5
14 10.1002/chin.200617262 doi_________::004c8cef80668904961b9e62841793c8 01 natural sciences 0104 chemical sciences 010405 organic chemistry 01040508 Functional groups/Ethers 0.5566747188568115 0.5582916736602783
15 10.1002/chin.200617262 doi_________::004c8cef80668904961b9e62841793c8 01 natural sciences 0104 chemical sciences 010402 general chemistry 01040207 Chemical synthesis/Total synthesis 0.4433253407478332 0.4417082965373993
16 10.1016/j.revmed.2006.07.012 doi_________::005b1d0fb650b680abaf6cfe26a21604 03 medical and health sciences 0302 clinical medicine 030204 cardiovascular system & hematology 03020409 Hematology/Coagulopathies 0.5101401805877686 0.0546871414174914
17 10.1016/j.revmed.2006.07.012 doi_________::005b1d0fb650b680abaf6cfe26a21604 03 medical and health sciences 0301 basic medicine 030105 genetics & heredity N/A 0.4898599088191986 0.0
18 10.4109/jslab.17.132 doi_________::00889baa06de363e37930daaf8e800c0 03 medical and health sciences 0301 basic medicine 030104 developmental biology N/A 0.5 0.0
19 10.4109/jslab.17.132 doi_________::00889baa06de363e37930daaf8e800c0 03 medical and health sciences 0303 health sciences 030304 developmental biology N/A 0.5 0.0
20 10.1108/00251740610715687 doi_________::0092cb1b1920d556719385a26363ecaa 05 social sciences 0502 economics and business 050203 business & management 05020311 International business/International trade 0.605047881603241 0.2156608108845153
21 10.1108/00251740610715687 doi_________::0092cb1b1920d556719385a26363ecaa 05 social sciences 0502 economics and business 050211 marketing N/A 0.394952118396759 0.0
22 10.1080/03067310500248098 doi_________::00a76678d230e3f20b6356804448028f 04 agricultural and veterinary sciences 0404 agricultural biotechnology 040401 food science 04040102 Food science/Food industry 0.5 0.5
23 10.1080/03067310500248098 doi_________::00a76678d230e3f20b6356804448028f 04 agricultural and veterinary sciences 0405 other agricultural sciences 040502 food science 04050202 Food science/Food industry 0.5 0.5
24 10.3152/147154306781778533 doi_________::00acc520f3939e5a6675343881fed4f2 05 social sciences 0502 economics and business 050203 business & management 05020307 Innovation/Product management 0.5293408632278442 0.5326762795448303
25 10.3152/147154306781778533 doi_________::00acc520f3939e5a6675343881fed4f2 05 social sciences 0509 other social sciences 050905 science studies 05090502 Social philosophy/Capitalism 0.4706590473651886 0.4673237204551697
26 10.1785/0120050806 doi_________::00d5831d329e7ae4523d78bfc3042e98 02 engineering and technology 0211 other engineering and technologies 021101 geological & geomatics engineering 02110103 Concrete/Building materials 0.5343400835990906 0.3285667930180677

25
dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/createunresolvedentities/fos/fos_sbs_2.json Normal file
View File

@ -0,0 +1,25 @@
{"doi":"10.1016/j.anucene.2006.02.004","level1":"02 engineering and technology","level2":"0202 electrical engineering, electronic engineering, information engineering","level3":"020209 energy","level4":"02020908 Climate change policy/Ethanol fuel","scoreL3":"0.5","scoreL4":"0.5"}
{"doi":"10.1016/j.anucene.2006.02.004","level1":"02 engineering and technology","level2":"0211 other engineering and technologies","level3":"021108 energy","level4":"02110808 Climate change policy/Ethanol fuel","scoreL3":"0.5","scoreL4":"0.5"}
{"doi":"10.1016/j.revmed.2006.07.010","level1":"03 medical and health sciences","level2":"0302 clinical medicine","level3":"030220 oncology & carcinogenesis","level4":"N/A","scoreL3":"0.5036656856536865","scoreL4":"0.0"}
{"doi":"10.1016/j.revmed.2006.07.010","level1":"03 medical and health sciences","level2":"0302 clinical medicine","level3":"030212 general & internal medicine","level4":"N/A","scoreL3":"0.4963343143463135","scoreL4":"0.0"}
{"doi":"10.20965/jrm.2006.p0312","level1":"02 engineering and technology","level2":"0209 industrial biotechnology","level3":"020901 industrial engineering & automation","level4":"02090104 Robotics/Robots","scoreL3":"0.6111094951629639","scoreL4":"0.5053805979936855"}
{"doi":"10.20965/jrm.2006.p0312","level1":"01 natural sciences","level2":"0104 chemical sciences","level3":"010401 analytical chemistry","level4":"N/A","scoreL3":"0.3888905048370361","scoreL4":"0.0"}
{"doi":"10.1111/j.1747-7379.2006.040_1.x","level1":"05 social sciences","level2":"0506 political science","level3":"050602 political science & public administration","level4":"05060202 Ethnic groups/Ethnicity","scoreL3":"0.6159052848815918","scoreL4":"0.7369035568037298"}
{"doi":"10.1111/j.1747-7379.2006.040_1.x","level1":"05 social sciences","level2":"0502 economics and business","level3":"050207 economics","level4":"N/A","scoreL3":"0.3840946555137634","scoreL4":"0.0"}
{"doi":"10.1007/s10512-006-0049-9","level1":"02 engineering and technology","level2":"0202 electrical engineering, electronic engineering, information engineering","level3":"020209 energy","level4":"02020908 Climate change policy/Ethanol fuel","scoreL3":"0.5","scoreL4":"0.5"}
{"doi":"10.1007/s10512-006-0049-9","level1":"02 engineering and technology","level2":"0211 other engineering and technologies","level3":"021108 energy","level4":"02110808 Climate change policy/Ethanol fuel","scoreL3":"0.5","scoreL4":"0.5"}
{"doi":"10.1111/j.1365-2621.2005.01045.x","level1":"04 agricultural and veterinary sciences","level2":"0404 agricultural biotechnology","level3":"040401 food science","level4":"04040102 Food science/Food industry","scoreL3":"0.5","scoreL4":"0.5"}
{"doi":"10.1111/j.1365-2621.2005.01045.x","level1":"04 agricultural and veterinary sciences","level2":"0405 other agricultural sciences","level3":"040502 food science","level4":"04050202 Food science/Food industry","scoreL3":"0.5","scoreL4":"0.5"}
{"doi":"10.1002/chin.200617262","level1":"01 natural sciences","level2":"0104 chemical sciences","level3":"010405 organic chemistry","level4":"01040508 Functional groups/Ethers","scoreL3":"0.5566747188568115","scoreL4":"0.5582916736602783"}
{"doi":"10.1002/chin.200617262","level1":"01 natural sciences","level2":"0104 chemical sciences","level3":"010402 general chemistry","level4":"01040207 Chemical synthesis/Total synthesis","scoreL3":"0.4433253407478332","scoreL4":"0.4417082965373993"}
{"doi":"10.1016/j.revmed.2006.07.012","level1":"03 medical and health sciences","level2":"0302 clinical medicine","level3":"030204 cardiovascular system & hematology","level4":"03020409 Hematology/Coagulopathies","scoreL3":"0.5101401805877686","scoreL4":"0.0546871414174914"}
{"doi":"10.1016/j.revmed.2006.07.012","level1":"03 medical and health sciences","level2":"0301 basic medicine","level3":"030105 genetics & heredity","level4":"N/A","scoreL3":"0.4898599088191986","scoreL4":"0.0"}
{"doi":"10.4109/jslab.17.132","level1":"03 medical and health sciences","level2":"0301 basic medicine","level3":"030104 developmental biology","level4":"N/A","scoreL3":"0.5","scoreL4":"0.0"}
{"doi":"10.4109/jslab.17.132","level1":"03 medical and health sciences","level2":"0303 health sciences","level3":"030304 developmental biology","level4":"N/A","scoreL3":"0.5","scoreL4":"0.0"}
{"doi":"10.1108/00251740610715687","level1":"05 social sciences","level2":"0502 economics and business","level3":"050203 business & management","level4":"05020311 International business/International trade","scoreL3":"0.605047881603241","scoreL4":"0.2156608108845153"}
{"doi":"10.1108/00251740610715687","level1":"05 social sciences","level2":"0502 economics and business","level3":"050211 marketing","level4":"N/A","scoreL3":"0.394952118396759","scoreL4":"0.0"}
{"doi":"10.1080/03067310500248098","level1":"04 agricultural and veterinary sciences","level2":"0404 agricultural biotechnology","level3":"040401 food science","level4":"04040102 Food science/Food industry","scoreL3":"0.5","scoreL4":"0.5"}
{"doi":"10.1080/03067310500248098","level1":"04 agricultural and veterinary sciences","level2":"0405 other agricultural sciences","level3":"040502 food science","level4":"04050202 Food science/Food industry","scoreL3":"0.5","scoreL4":"0.5"}
{"doi":"10.3152/147154306781778533","level1":"05 social sciences","level2":"0502 economics and business","level3":"050203 business & management","level4":"05020307 Innovation/Product management","scoreL3":"0.5293408632278442","scoreL4":"0.5326762795448303"}
{"doi":"10.3152/147154306781778533","level1":"05 social sciences","level2":"0509 other social sciences","level3":"050905 science studies","level4":"05090502 Social philosophy/Capitalism","scoreL3":"0.4706590473651886","scoreL4":"0.4673237204551697"}
{"doi":"10.1785/0120050806","level1":"02 engineering and technology","level2":"0211 other engineering and technologies","level3":"021101 geological & geomatics engineering","level4":"02110103 Concrete/Building materials","scoreL3":"0.5343400835990906","scoreL4":"0.3285667930180677"}

69
dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/collection/orcid/activity_work_0000-0002-2536-4498.xml Normal file
View File

@ -0,0 +1,69 @@
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<work:work xmlns:address="http://www.orcid.org/ns/address" xmlns:email="http://www.orcid.org/ns/email" xmlns:history="http://www.orcid.org/ns/history" xmlns:employment="http://www.orcid.org/ns/employment" xmlns:education="http://www.orcid.org/ns/education" xmlns:other-name="http://www.orcid.org/ns/other-name" xmlns:deprecated="http://www.orcid.org/ns/deprecated" xmlns:funding="http://www.orcid.org/ns/funding" xmlns:research-resource="http://www.orcid.org/ns/research-resource" xmlns:service="http://www.orcid.org/ns/service" xmlns:researcher-url="http://www.orcid.org/ns/researcher-url" xmlns:distinction="http://www.orcid.org/ns/distinction" xmlns:internal="http://www.orcid.org/ns/internal" xmlns:membership="http://www.orcid.org/ns/membership" xmlns:person="http://www.orcid.org/ns/person" xmlns:personal-details="http://www.orcid.org/ns/personal-details" xmlns:bulk="http://www.orcid.org/ns/bulk" xmlns:common="http://www.orcid.org/ns/common" xmlns:record="http://www.orcid.org/ns/record" xmlns:keyword="http://www.orcid.org/ns/keyword" xmlns:activities="http://www.orcid.org/ns/activities" xmlns:qualification="http://www.orcid.org/ns/qualification" xmlns:external-identifier="http://www.orcid.org/ns/external-identifier" xmlns:error="http://www.orcid.org/ns/error" xmlns:preferences="http://www.orcid.org/ns/preferences" xmlns:invited-position="http://www.orcid.org/ns/invited-position" xmlns:work="http://www.orcid.org/ns/work" xmlns:peer-review="http://www.orcid.org/ns/peer-review" put-code="26448226" path="/0000-0001-5010-5001/work/26448226" visibility="public">
<common:created-date>2016-09-01T19:22:46.768Z</common:created-date>
<common:last-modified-date>2022-05-25T03:48:56.968Z</common:last-modified-date>
<common:source>
<common:source-client-id>
<common:uri>https://orcid.org/client/0000-0002-5982-8983</common:uri>
<common:path>0000-0002-5982-8983</common:path>
<common:host>orcid.org</common:host>
</common:source-client-id>
<common:source-name>Scopus - Elsevier</common:source-name>
<common:assertion-origin-orcid>
<common:uri>https://orcid.org/0000-0001-5010-5001</common:uri>
<common:path>0000-0001-5010-5001</common:path>
<common:host>orcid.org</common:host>
</common:assertion-origin-orcid>
<common:assertion-origin-name>Quang Nguyen</common:assertion-origin-name>
</common:source>
<work:title>
<common:title>Vision outcomes and major complications after endovascular coil embolization of ophthalmic segment aneurysms</common:title>
</work:title>
<work:journal-title>American Journal of Neuroradiology</work:journal-title>
<work:citation>
<work:citation-type>bibtex</work:citation-type>
<work:citation-value>@article{Nguyen2014,title = {Vision outcomes and major complications after endovascular coil embolization of ophthalmic segment aneurysms},journal = {American Journal of Neuroradiology},year = {2014},volume = {35},number = {11},pages = {2140-2145},author = {Durst, C. and Starke, R.M. and Gaughen, J. and Nguyen, Q. and Patrie, J. and Jensen, M.E. and Evans, A.J.}}</work:citation-value>
</work:citation>
<work:type>journal-article</work:type>
<common:publication-date>
<common:year>2014</common:year>
</common:publication-date>
<common:external-ids>
<common:external-id>
<common:external-id-type>doi</common:external-id-type>
<common:external-id-value>10.3174/ajnr.A4032</common:external-id-value>
<common:external-id-normalized transient="true">10.3174/ajnr.a4032</common:external-id-normalized>
<common:external-id-relationship>self</common:external-id-relationship>
</common:external-id>
<common:external-id>
<common:external-id-type>eid</common:external-id-type>
<common:external-id-value>2-s2.0-84911865199</common:external-id-value>
<common:external-id-normalized transient="true">2-s2.0-84911865199</common:external-id-normalized>
<common:external-id-relationship>self</common:external-id-relationship>
</common:external-id>
</common:external-ids>
<common:url>http://www.scopus.com/inward/record.url?eid=2-s2.0-84911865199&amp;partnerID=MN8TOARS</common:url>
<work:contributors>
<work:contributor>
<work:credit-name>Durst, C.</work:credit-name>
</work:contributor>
<work:contributor>
<work:credit-name>Starke, R.M.</work:credit-name>
</work:contributor>
<work:contributor>
<work:credit-name>Gaughen, J.</work:credit-name>
</work:contributor>
<work:contributor>
<work:credit-name>Nguyen, Q.</work:credit-name>
</work:contributor>
<work:contributor>
<work:credit-name>Patrie, J.</work:credit-name>
</work:contributor>
<work:contributor>
<work:credit-name>Jensen, M.E.</work:credit-name>
</work:contributor>
<work:contributor>
<work:credit-name>Evans, A.J.</work:credit-name>
</work:contributor>
</work:contributors>
</work:work>

79
dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/collection/orcid/activity_work_0000-0002-5982-8983.xml Normal file
View File

@ -0,0 +1,79 @@
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<work:work xmlns:address="http://www.orcid.org/ns/address"
xmlns:email="http://www.orcid.org/ns/email" xmlns:history="http://www.orcid.org/ns/history"
xmlns:employment="http://www.orcid.org/ns/employment"
xmlns:education="http://www.orcid.org/ns/education"
xmlns:other-name="http://www.orcid.org/ns/other-name"
xmlns:deprecated="http://www.orcid.org/ns/deprecated"
xmlns:funding="http://www.orcid.org/ns/funding"
xmlns:research-resource="http://www.orcid.org/ns/research-resource"
xmlns:service="http://www.orcid.org/ns/service"
xmlns:researcher-url="http://www.orcid.org/ns/researcher-url"
xmlns:distinction="http://www.orcid.org/ns/distinction"
xmlns:internal="http://www.orcid.org/ns/internal"
xmlns:membership="http://www.orcid.org/ns/membership"
xmlns:person="http://www.orcid.org/ns/person"
xmlns:personal-details="http://www.orcid.org/ns/personal-details"
xmlns:bulk="http://www.orcid.org/ns/bulk" xmlns:common="http://www.orcid.org/ns/common"
xmlns:record="http://www.orcid.org/ns/record" xmlns:keyword="http://www.orcid.org/ns/keyword"
xmlns:activities="http://www.orcid.org/ns/activities"
xmlns:qualification="http://www.orcid.org/ns/qualification"
xmlns:external-identifier="http://www.orcid.org/ns/external-identifier"
xmlns:error="http://www.orcid.org/ns/error"
xmlns:preferences="http://www.orcid.org/ns/preferences"
xmlns:invited-position="http://www.orcid.org/ns/invited-position"
xmlns:work="http://www.orcid.org/ns/work"
xmlns:peer-review="http://www.orcid.org/ns/peer-review" put-code="50101152"
path="/0000-0001-5349-4030/work/50101152" visibility="public">
<common:created-date>2018-11-01T19:49:45.562Z</common:created-date>
<common:last-modified-date>2018-11-01T19:49:45.562Z</common:last-modified-date>
<common:source>
<common:source-client-id>
<common:uri>https://orcid.org/client/0000-0002-5982-8983</common:uri>
<common:path>0000-0002-5982-8983</common:path>
<common:host>orcid.org</common:host>
</common:source-client-id>
<common:source-name>Scopus - Elsevier</common:source-name>
</common:source>
<work:title>
<common:title>"Calling Out" in class: Degrees of candor in addressing social injustices in
racially homogenous and heterogeneous U.S. history classrooms</common:title>
</work:title>
<work:journal-title>Journal of Social Studies Research</work:journal-title>
<work:citation>
<work:citation-type>bibtex</work:citation-type>
<work:citation-value>@article{Massaro2018,title = {{"}Calling Out{"} in class: Degrees of
candor in addressing social injustices in racially homogenous and heterogeneous U.S.
history classrooms},journal = {Journal of Social Studies Research},year = {2018},author
= {Parkhouse, H. and Massaro, V.R.}}</work:citation-value>
</work:citation>
<work:type>journal-article</work:type>
<common:publication-date>
<common:year>2018</common:year>
</common:publication-date>
<common:external-ids>
<common:external-id>
<common:external-id-type>doi</common:external-id-type>
<common:external-id-value>10.1016/j.jssr.2018.01.004</common:external-id-value>
<common:external-id-normalized transient="true"
>10.1016/j.jssr.2018.01.004</common:external-id-normalized>
<common:external-id-relationship>self</common:external-id-relationship>
</common:external-id>
<common:external-id>
<common:external-id-type>eid</common:external-id-type>
<common:external-id-value>2-s2.0-85041949043</common:external-id-value>
<common:external-id-normalized transient="true"
>2-s2.0-85041949043</common:external-id-normalized>
<common:external-id-relationship>self</common:external-id-relationship>
</common:external-id>
</common:external-ids>
<common:url>http://www.scopus.com/inward/record.url?eid=2-s2.0-85041949043&amp;partnerID=MN8TOARS</common:url>
<work:contributors>
<work:contributor>
<work:credit-name>Parkhouse, H.</work:credit-name>
</work:contributor>
<work:contributor>
<work:credit-name>Massaro, V.R.</work:credit-name>
</work:contributor>
</work:contributors>
</work:work>

113
dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/collection/orcid/activity_work_0000-0003-2760-1191-similarity.xml Normal file
View File

@ -0,0 +1,113 @@
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<work:work xmlns:address="http://www.orcid.org/ns/address"
xmlns:email="http://www.orcid.org/ns/email" xmlns:history="http://www.orcid.org/ns/history"
xmlns:employment="http://www.orcid.org/ns/employment"
xmlns:education="http://www.orcid.org/ns/education"
xmlns:other-name="http://www.orcid.org/ns/other-name"
xmlns:deprecated="http://www.orcid.org/ns/deprecated"
xmlns:funding="http://www.orcid.org/ns/funding"
xmlns:research-resource="http://www.orcid.org/ns/research-resource"
xmlns:service="http://www.orcid.org/ns/service"
xmlns:researcher-url="http://www.orcid.org/ns/researcher-url"
xmlns:distinction="http://www.orcid.org/ns/distinction"
xmlns:internal="http://www.orcid.org/ns/internal"
xmlns:membership="http://www.orcid.org/ns/membership"
xmlns:person="http://www.orcid.org/ns/person"
xmlns:personal-details="http://www.orcid.org/ns/personal-details"
xmlns:bulk="http://www.orcid.org/ns/bulk" xmlns:common="http://www.orcid.org/ns/common"
xmlns:record="http://www.orcid.org/ns/record" xmlns:keyword="http://www.orcid.org/ns/keyword"
xmlns:activities="http://www.orcid.org/ns/activities"
xmlns:qualification="http://www.orcid.org/ns/qualification"
xmlns:external-identifier="http://www.orcid.org/ns/external-identifier"
xmlns:error="http://www.orcid.org/ns/error"
xmlns:preferences="http://www.orcid.org/ns/preferences"
xmlns:invited-position="http://www.orcid.org/ns/invited-position"
xmlns:work="http://www.orcid.org/ns/work"
xmlns:peer-review="http://www.orcid.org/ns/peer-review" put-code="28776099"
path="/0000-0003-2760-1191/work/28776099" visibility="public">
<common:created-date>2016-12-12T23:02:05.233Z</common:created-date>
<common:last-modified-date>2016-12-13T09:08:16.412Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0002-9157-3431</common:uri>
<common:path>0000-0002-9157-3431</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
<common:source-name>Europe PubMed Central</common:source-name>
</common:source>
<work:title>
<common:title>Cutoff Value of Admission N-Terminal Pro-Brain Natriuretic Peptide Which
Predicts Poor Myocardial Perfusion after Primary Percutaneous Coronary Intervention for
ST-Segment-Elevation Myocardial Infarction.</common:title>
</work:title>
<work:citation>
<work:citation-type>formatted-unspecified</work:citation-type>
<work:citation-value>Abdel-Dayem K, Eweda II, El-Sherbiny A, Dimitry MO, Nammas W, Acta
Cardiologica Sinica, 2016, vol. 32, no. 6, pp. 649-655, 2016</work:citation-value>
</work:citation>
<work:type>journal-article</work:type>
<common:publication-date>
<common:year>2016</common:year>
<common:month>11</common:month>
</common:publication-date>
<common:external-ids>
<common:external-id>
<common:external-id-type>pmid</common:external-id-type>
<common:external-id-value>27899851</common:external-id-value>
<common:external-id-normalized transient="true">27899851</common:external-id-normalized>
<common:external-id-relationship>self</common:external-id-relationship>
</common:external-id>
<common:external-id>
<common:external-id-type>pmc</common:external-id-type>
<common:external-id-value>PMC5126442</common:external-id-value>
<common:external-id-normalized transient="true"
>PMC5126442</common:external-id-normalized>
<common:external-id-relationship>self</common:external-id-relationship>
</common:external-id>
</common:external-ids>
<common:url>http://europepmc.org/abstract/med/27899851</common:url>
<work:contributors>
<work:contributor>
<work:credit-name>Abdel-Dayem K</work:credit-name>
<work:contributor-attributes>
<work:contributor-sequence>first</work:contributor-sequence>
<work:contributor-role>author</work:contributor-role>
</work:contributor-attributes>
</work:contributor>
<work:contributor>
<work:credit-name>Abdel-Dayem Fake</work:credit-name>
<work:contributor-attributes>
<work:contributor-sequence>first</work:contributor-sequence>
<work:contributor-role>author</work:contributor-role>
</work:contributor-attributes>
</work:contributor>
<work:contributor>
<work:credit-name>Eweda II</work:credit-name>
<work:contributor-attributes>
<work:contributor-sequence>first</work:contributor-sequence>
<work:contributor-role>author</work:contributor-role>
</work:contributor-attributes>
</work:contributor>
<work:contributor>
<work:credit-name>El-Sherbiny A</work:credit-name>
<work:contributor-attributes>
<work:contributor-sequence>first</work:contributor-sequence>
<work:contributor-role>author</work:contributor-role>
</work:contributor-attributes>
</work:contributor>
<work:contributor>
<work:credit-name>Dimitry MO</work:credit-name>
<work:contributor-attributes>
<work:contributor-sequence>first</work:contributor-sequence>
<work:contributor-role>author</work:contributor-role>
</work:contributor-attributes>
</work:contributor>
<work:contributor>
<work:credit-name>Nammas W</work:credit-name>
<work:contributor-attributes>
<work:contributor-sequence>first</work:contributor-sequence>
<work:contributor-role>author</work:contributor-role>
</work:contributor-attributes>
</work:contributor>
</work:contributors>
</work:work>

106
dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/collection/orcid/activity_work_0000-0003-2760-1191.xml Normal file
View File

@ -0,0 +1,106 @@
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<work:work xmlns:address="http://www.orcid.org/ns/address"
xmlns:email="http://www.orcid.org/ns/email" xmlns:history="http://www.orcid.org/ns/history"
xmlns:employment="http://www.orcid.org/ns/employment"
xmlns:education="http://www.orcid.org/ns/education"
xmlns:other-name="http://www.orcid.org/ns/other-name"
xmlns:deprecated="http://www.orcid.org/ns/deprecated"
xmlns:funding="http://www.orcid.org/ns/funding"
xmlns:research-resource="http://www.orcid.org/ns/research-resource"
xmlns:service="http://www.orcid.org/ns/service"
xmlns:researcher-url="http://www.orcid.org/ns/researcher-url"
xmlns:distinction="http://www.orcid.org/ns/distinction"
xmlns:internal="http://www.orcid.org/ns/internal"
xmlns:membership="http://www.orcid.org/ns/membership"
xmlns:person="http://www.orcid.org/ns/person"
xmlns:personal-details="http://www.orcid.org/ns/personal-details"
xmlns:bulk="http://www.orcid.org/ns/bulk" xmlns:common="http://www.orcid.org/ns/common"
xmlns:record="http://www.orcid.org/ns/record" xmlns:keyword="http://www.orcid.org/ns/keyword"
xmlns:activities="http://www.orcid.org/ns/activities"
xmlns:qualification="http://www.orcid.org/ns/qualification"
xmlns:external-identifier="http://www.orcid.org/ns/external-identifier"
xmlns:error="http://www.orcid.org/ns/error"
xmlns:preferences="http://www.orcid.org/ns/preferences"
xmlns:invited-position="http://www.orcid.org/ns/invited-position"
xmlns:work="http://www.orcid.org/ns/work"
xmlns:peer-review="http://www.orcid.org/ns/peer-review" put-code="28776099"
path="/0000-0003-2760-1191/work/28776099" visibility="public">
<common:created-date>2016-12-12T23:02:05.233Z</common:created-date>
<common:last-modified-date>2016-12-13T09:08:16.412Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0002-9157-3431</common:uri>
<common:path>0000-0002-9157-3431</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
<common:source-name>Europe PubMed Central</common:source-name>
</common:source>
<work:title>
<common:title>Cutoff Value of Admission N-Terminal Pro-Brain Natriuretic Peptide Which
Predicts Poor Myocardial Perfusion after Primary Percutaneous Coronary Intervention for
ST-Segment-Elevation Myocardial Infarction.</common:title>
</work:title>
<work:citation>
<work:citation-type>formatted-unspecified</work:citation-type>
<work:citation-value>Abdel-Dayem K, Eweda II, El-Sherbiny A, Dimitry MO, Nammas W, Acta
Cardiologica Sinica, 2016, vol. 32, no. 6, pp. 649-655, 2016</work:citation-value>
</work:citation>
<work:type>journal-article</work:type>
<common:publication-date>
<common:year>2016</common:year>
<common:month>11</common:month>
</common:publication-date>
<common:external-ids>
<common:external-id>
<common:external-id-type>pmid</common:external-id-type>
<common:external-id-value>27899851</common:external-id-value>
<common:external-id-normalized transient="true">27899851</common:external-id-normalized>
<common:external-id-relationship>self</common:external-id-relationship>
</common:external-id>
<common:external-id>
<common:external-id-type>pmc</common:external-id-type>
<common:external-id-value>PMC5126442</common:external-id-value>
<common:external-id-normalized transient="true"
>PMC5126442</common:external-id-normalized>
<common:external-id-relationship>self</common:external-id-relationship>
</common:external-id>
</common:external-ids>
<common:url>http://europepmc.org/abstract/med/27899851</common:url>
<work:contributors>
<work:contributor>
<work:credit-name>Khair Abde Daye</work:credit-name>
<work:contributor-attributes>
<work:contributor-sequence>first</work:contributor-sequence>
<work:contributor-role>author</work:contributor-role>
</work:contributor-attributes>
</work:contributor>
<work:contributor>
<work:credit-name>Eweda II</work:credit-name>
<work:contributor-attributes>
<work:contributor-sequence>first</work:contributor-sequence>
<work:contributor-role>author</work:contributor-role>
</work:contributor-attributes>
</work:contributor>
<work:contributor>
<work:credit-name>El-Sherbiny A</work:credit-name>
<work:contributor-attributes>
<work:contributor-sequence>first</work:contributor-sequence>
<work:contributor-role>author</work:contributor-role>
</work:contributor-attributes>
</work:contributor>
<work:contributor>
<work:credit-name>Dimitry MO</work:credit-name>
<work:contributor-attributes>
<work:contributor-sequence>first</work:contributor-sequence>
<work:contributor-role>author</work:contributor-role>
</work:contributor-attributes>
</work:contributor>
<work:contributor>
<work:credit-name>Nammas W</work:credit-name>
<work:contributor-attributes>
<work:contributor-sequence>first</work:contributor-sequence>
<work:contributor-role>author</work:contributor-role>
</work:contributor-attributes>
</work:contributor>
</work:contributors>
</work:work>

101
dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/collection/orcid/activity_work_0000-0003-2760-1191_contributors.xml Normal file
View File

@ -0,0 +1,101 @@
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<work:work xmlns:address="http://www.orcid.org/ns/address"
xmlns:email="http://www.orcid.org/ns/email" xmlns:history="http://www.orcid.org/ns/history"
xmlns:employment="http://www.orcid.org/ns/employment"
xmlns:education="http://www.orcid.org/ns/education"
xmlns:other-name="http://www.orcid.org/ns/other-name"
xmlns:deprecated="http://www.orcid.org/ns/deprecated"
xmlns:funding="http://www.orcid.org/ns/funding"
xmlns:research-resource="http://www.orcid.org/ns/research-resource"
xmlns:service="http://www.orcid.org/ns/service"
xmlns:researcher-url="http://www.orcid.org/ns/researcher-url"
xmlns:distinction="http://www.orcid.org/ns/distinction"
xmlns:internal="http://www.orcid.org/ns/internal"
xmlns:membership="http://www.orcid.org/ns/membership"
xmlns:person="http://www.orcid.org/ns/person"
xmlns:personal-details="http://www.orcid.org/ns/personal-details"
xmlns:bulk="http://www.orcid.org/ns/bulk" xmlns:common="http://www.orcid.org/ns/common"
xmlns:record="http://www.orcid.org/ns/record" xmlns:keyword="http://www.orcid.org/ns/keyword"
xmlns:activities="http://www.orcid.org/ns/activities"
xmlns:qualification="http://www.orcid.org/ns/qualification"
xmlns:external-identifier="http://www.orcid.org/ns/external-identifier"
xmlns:error="http://www.orcid.org/ns/error"
xmlns:preferences="http://www.orcid.org/ns/preferences"
xmlns:invited-position="http://www.orcid.org/ns/invited-position"
xmlns:work="http://www.orcid.org/ns/work"
xmlns:peer-review="http://www.orcid.org/ns/peer-review" put-code="28776099"
path="/0000-0003-2760-1191/work/28776099" visibility="public">
<common:created-date>2016-12-12T23:02:05.233Z</common:created-date>
<common:last-modified-date>2016-12-13T09:08:16.412Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0002-9157-3431</common:uri>
<common:path>0000-0002-9157-3431</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
<common:source-name>Europe PubMed Central</common:source-name>
</common:source>
<work:title>
<common:title>Cutoff Value of Admission N-Terminal Pro-Brain Natriuretic Peptide Which
Predicts Poor Myocardial Perfusion after Primary Percutaneous Coronary Intervention for
ST-Segment-Elevation Myocardial Infarction.</common:title>
</work:title>
<work:citation>
<work:citation-type>formatted-unspecified</work:citation-type>
<work:citation-value>Abdel-Dayem K, Eweda II, El-Sherbiny A, Dimitry MO, Nammas W, Acta
Cardiologica Sinica, 2016, vol. 32, no. 6, pp. 649-655, 2016</work:citation-value>
</work:citation>
<work:type>journal-article</work:type>
<common:publication-date>
<common:year>2016</common:year>
<common:month>11</common:month>
</common:publication-date>
<common:external-ids>
<common:external-id>
<common:external-id-type>pmid</common:external-id-type>
<common:external-id-value>27899851</common:external-id-value>
<common:external-id-normalized transient="true">27899851</common:external-id-normalized>
<common:external-id-relationship>self</common:external-id-relationship>
</common:external-id>
<common:external-id>
<common:external-id-type>pmc</common:external-id-type>
<common:external-id-value>PMC5126442</common:external-id-value>
<common:external-id-normalized transient="true"
>PMC5126442</common:external-id-normalized>
<common:external-id-relationship>self</common:external-id-relationship>
</common:external-id>
</common:external-ids>
<common:url>http://europepmc.org/abstract/med/27899851</common:url>
<work:contributors>
<work:contributor>
<work:contributor-attributes>
<work:contributor-sequence>seq0</work:contributor-sequence>
<work:contributor-role>role0</work:contributor-role>
</work:contributor-attributes>
</work:contributor>
<work:contributor>
<work:credit-name>creditname1</work:credit-name>
</work:contributor>
<work:contributor>
<work:credit-name>creditname2</work:credit-name>
<work:contributor-attributes>
<work:contributor-sequence>seq2</work:contributor-sequence>
<work:contributor-role></work:contributor-role>
</work:contributor-attributes>
</work:contributor>
<work:contributor>
<work:credit-name>creditname3</work:credit-name>
<work:contributor-attributes>
<work:contributor-sequence></work:contributor-sequence>
<work:contributor-role>role3</work:contributor-role>
</work:contributor-attributes>
</work:contributor>
<work:contributor>
<work:credit-name></work:credit-name>
<work:contributor-attributes>
<work:contributor-sequence>seq4</work:contributor-sequence>
<work:contributor-role>role4</work:contributor-role>
</work:contributor-attributes>
</work:contributor>
</work:contributors>
</work:work>

50
dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/collection/orcid/employment.xml Normal file
View File

@ -0,0 +1,50 @@
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<employment:employment xmlns:address="http://www.orcid.org/ns/address" xmlns:email="http://www.orcid.org/ns/email"
xmlns:history="http://www.orcid.org/ns/history"
xmlns:employment="http://www.orcid.org/ns/employment"
xmlns:education="http://www.orcid.org/ns/education"
xmlns:other-name="http://www.orcid.org/ns/other-name"
xmlns:deprecated="http://www.orcid.org/ns/deprecated"
xmlns:funding="http://www.orcid.org/ns/funding"
xmlns:research-resource="http://www.orcid.org/ns/research-resource"
xmlns:service="http://www.orcid.org/ns/service"
xmlns:researcher-url="http://www.orcid.org/ns/researcher-url"
xmlns:distinction="http://www.orcid.org/ns/distinction"
xmlns:internal="http://www.orcid.org/ns/internal"
xmlns:membership="http://www.orcid.org/ns/membership"
xmlns:person="http://www.orcid.org/ns/person"
xmlns:personal-details="http://www.orcid.org/ns/personal-details"
xmlns:bulk="http://www.orcid.org/ns/bulk" xmlns:common="http://www.orcid.org/ns/common"
xmlns:record="http://www.orcid.org/ns/record" xmlns:keyword="http://www.orcid.org/ns/keyword"
xmlns:activities="http://www.orcid.org/ns/activities"
xmlns:qualification="http://www.orcid.org/ns/qualification"
xmlns:external-identifier="http://www.orcid.org/ns/external-identifier"
xmlns:error="http://www.orcid.org/ns/error"
xmlns:preferences="http://www.orcid.org/ns/preferences"
xmlns:invited-position="http://www.orcid.org/ns/invited-position"
xmlns:work="http://www.orcid.org/ns/work" xmlns:peer-review="http://www.orcid.org/ns/peer-review"
put-code="2205087" path="/0000-0001-5010-5001/employment/2205087" display-index="0"
visibility="public">
<common:created-date>2016-09-01T19:21:05.791Z</common:created-date>
<common:last-modified-date>2016-09-01T19:21:05.791Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-5010-5001</common:uri>
<common:path>0000-0001-5010-5001</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
<common:source-name>Quang Nguyen</common:source-name>
</common:source>
<common:organization>
<common:name>Beth Israel Deaconess Medical Center</common:name>
<common:address>
<common:city>Boston</common:city>
<common:region>MA</common:region>
<common:country>US</common:country>
</common:address>
<common:disambiguated-organization>
<common:disambiguated-organization-identifier>1859</common:disambiguated-organization-identifier>
<common:disambiguation-source>RINGGOLD</common:disambiguation-source>
</common:disambiguated-organization>
</common:organization>
</employment:employment>

55
dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/collection/orcid/employment_2.xml Normal file
View File

@ -0,0 +1,55 @@
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<employment:employment xmlns:address="http://www.orcid.org/ns/address" xmlns:email="http://www.orcid.org/ns/email"
xmlns:history="http://www.orcid.org/ns/history"
xmlns:employment="http://www.orcid.org/ns/employment"
xmlns:education="http://www.orcid.org/ns/education"
xmlns:other-name="http://www.orcid.org/ns/other-name"
xmlns:deprecated="http://www.orcid.org/ns/deprecated"
xmlns:funding="http://www.orcid.org/ns/funding"
xmlns:research-resource="http://www.orcid.org/ns/research-resource"
xmlns:service="http://www.orcid.org/ns/service"
xmlns:researcher-url="http://www.orcid.org/ns/researcher-url"
xmlns:distinction="http://www.orcid.org/ns/distinction"
xmlns:internal="http://www.orcid.org/ns/internal"
xmlns:membership="http://www.orcid.org/ns/membership"
xmlns:person="http://www.orcid.org/ns/person"
xmlns:personal-details="http://www.orcid.org/ns/personal-details"
xmlns:bulk="http://www.orcid.org/ns/bulk" xmlns:common="http://www.orcid.org/ns/common"
xmlns:record="http://www.orcid.org/ns/record" xmlns:keyword="http://www.orcid.org/ns/keyword"
xmlns:activities="http://www.orcid.org/ns/activities"
xmlns:qualification="http://www.orcid.org/ns/qualification"
xmlns:external-identifier="http://www.orcid.org/ns/external-identifier"
xmlns:error="http://www.orcid.org/ns/error"
xmlns:preferences="http://www.orcid.org/ns/preferences"
xmlns:invited-position="http://www.orcid.org/ns/invited-position"
xmlns:work="http://www.orcid.org/ns/work" xmlns:peer-review="http://www.orcid.org/ns/peer-review"
put-code="6364960" path="/0000-0001-5011-3001/employment/6364960" display-index="1"
visibility="public">
<common:created-date>2018-09-03T01:46:19.474Z</common:created-date>
<common:last-modified-date>2018-09-03T01:46:19.474Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-5011-3001</common:uri>
<common:path>0000-0001-5011-3001</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
<common:source-name>zhengyan li</common:source-name>
</common:source>
<common:start-date>
<common:year>2008</common:year>
<common:month>09</common:month>
<common:day>01</common:day>
</common:start-date>
<common:organization>
<common:name>Anhui Academy of Agricultural Sciences</common:name>
<common:address>
<common:city>Hefei</common:city>
<common:region>Anhui</common:region>
<common:country>CN</common:country>
</common:address>
<common:disambiguated-organization>
<common:disambiguated-organization-identifier>125385</common:disambiguated-organization-identifier>
<common:disambiguation-source>RINGGOLD</common:disambiguation-source>
</common:disambiguated-organization>
</common:organization>
</employment:employment>

62
dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/collection/orcid/employment_3.xml Normal file
View File

@ -0,0 +1,62 @@
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<employment:employment xmlns:address="http://www.orcid.org/ns/address" xmlns:email="http://www.orcid.org/ns/email"
xmlns:history="http://www.orcid.org/ns/history"
xmlns:employment="http://www.orcid.org/ns/employment"
xmlns:education="http://www.orcid.org/ns/education"
xmlns:other-name="http://www.orcid.org/ns/other-name"
xmlns:deprecated="http://www.orcid.org/ns/deprecated"
xmlns:funding="http://www.orcid.org/ns/funding"
xmlns:research-resource="http://www.orcid.org/ns/research-resource"
xmlns:service="http://www.orcid.org/ns/service"
xmlns:researcher-url="http://www.orcid.org/ns/researcher-url"
xmlns:distinction="http://www.orcid.org/ns/distinction"
xmlns:internal="http://www.orcid.org/ns/internal"
xmlns:membership="http://www.orcid.org/ns/membership"
xmlns:person="http://www.orcid.org/ns/person"
xmlns:personal-details="http://www.orcid.org/ns/personal-details"
xmlns:bulk="http://www.orcid.org/ns/bulk" xmlns:common="http://www.orcid.org/ns/common"
xmlns:record="http://www.orcid.org/ns/record" xmlns:keyword="http://www.orcid.org/ns/keyword"
xmlns:activities="http://www.orcid.org/ns/activities"
xmlns:qualification="http://www.orcid.org/ns/qualification"
xmlns:external-identifier="http://www.orcid.org/ns/external-identifier"
xmlns:error="http://www.orcid.org/ns/error"
xmlns:preferences="http://www.orcid.org/ns/preferences"
xmlns:invited-position="http://www.orcid.org/ns/invited-position"
xmlns:work="http://www.orcid.org/ns/work" xmlns:peer-review="http://www.orcid.org/ns/peer-review"
put-code="7210424" path="/0000-0001-5022-8001/employment/7210424" display-index="1"
visibility="public">
<common:created-date>2021-03-11T14:48:29.603Z</common:created-date>
<common:last-modified-date>2021-03-11T14:48:29.603Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-5012-1001</common:uri>
<common:path>0000-0001-5012-1001</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
<common:source-name>Asma Bazzi</common:source-name>
</common:source>
<common:department-name>Pathology and Laboratory Medicine</common:department-name>
<common:role-title>Medical Laboratory Technologist</common:role-title>
<common:start-date>
<common:year>1994</common:year>
<common:month>10</common:month>
<common:day>01</common:day>
</common:start-date>
<common:end-date>
<common:year>2000</common:year>
<common:month>06</common:month>
<common:day>30</common:day>
</common:end-date>
<common:organization>
<common:name>American University of Beirut</common:name>
<common:address>
<common:city>Hamra</common:city>
<common:region>Beirut</common:region>
<common:country>LB</common:country>
</common:address>
<common:disambiguated-organization>
<common:disambiguated-organization-identifier>11238</common:disambiguated-organization-identifier>
<common:disambiguation-source>RINGGOLD</common:disambiguation-source>
</common:disambiguated-organization>
</common:organization>
</employment:employment>

581
dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/collection/orcid/summary.xml Normal file
View File

@ -0,0 +1,581 @@
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<record:record xmlns:address="http://www.orcid.org/ns/address" xmlns:email="http://www.orcid.org/ns/email" xmlns:history="http://www.orcid.org/ns/history" xmlns:employment="http://www.orcid.org/ns/employment" xmlns:education="http://www.orcid.org/ns/education" xmlns:other-name="http://www.orcid.org/ns/other-name" xmlns:deprecated="http://www.orcid.org/ns/deprecated" xmlns:funding="http://www.orcid.org/ns/funding" xmlns:research-resource="http://www.orcid.org/ns/research-resource" xmlns:service="http://www.orcid.org/ns/service" xmlns:researcher-url="http://www.orcid.org/ns/researcher-url" xmlns:distinction="http://www.orcid.org/ns/distinction" xmlns:internal="http://www.orcid.org/ns/internal" xmlns:membership="http://www.orcid.org/ns/membership" xmlns:person="http://www.orcid.org/ns/person" xmlns:personal-details="http://www.orcid.org/ns/personal-details" xmlns:bulk="http://www.orcid.org/ns/bulk" xmlns:common="http://www.orcid.org/ns/common" xmlns:record="http://www.orcid.org/ns/record" xmlns:keyword="http://www.orcid.org/ns/keyword" xmlns:activities="http://www.orcid.org/ns/activities" xmlns:qualification="http://www.orcid.org/ns/qualification" xmlns:external-identifier="http://www.orcid.org/ns/external-identifier" xmlns:error="http://www.orcid.org/ns/error" xmlns:preferences="http://www.orcid.org/ns/preferences" xmlns:invited-position="http://www.orcid.org/ns/invited-position" xmlns:work="http://www.orcid.org/ns/work" xmlns:peer-review="http://www.orcid.org/ns/peer-review" path="/0000-0001-5045-1000">
<common:orcid-identifier>
<common:uri>https://orcid.org/0000-0001-5045-1000</common:uri>
<common:path>0000-0001-5045-1000</common:path>
<common:host>orcid.org</common:host>
</common:orcid-identifier>
<preferences:preferences>
<preferences:locale>es</preferences:locale>
</preferences:preferences>
<history:history>
<history:creation-method>Direct</history:creation-method>
<history:submission-date>2023-01-17T23:50:40.215Z</history:submission-date>
<common:last-modified-date>2023-09-04T17:51:57.749Z</common:last-modified-date>
<history:claimed>true</history:claimed>
<history:verified-email>true</history:verified-email>
<history:verified-primary-email>true</history:verified-primary-email>
</history:history>
<person:person path="/0000-0001-5045-1000/person">
<person:name visibility="public" path="0000-0001-5045-1000">
<common:created-date>2023-01-17T23:50:40.472Z</common:created-date>
<common:last-modified-date>2023-01-17T23:50:40.472Z</common:last-modified-date>
<personal-details:given-names>Patricio</personal-details:given-names>
<personal-details:family-name>Sánchez Quinchuela</personal-details:family-name>
</person:name>
<other-name:other-names path="/0000-0001-5045-1000/other-names"/>
<person:biography visibility="public" path="/0000-0001-5045-1000/biography">
<common:created-date>2023-01-19T13:47:33.653Z</common:created-date>
<common:last-modified-date>2023-01-19T13:47:33.653Z</common:last-modified-date>
<personal-details:content>Especialista de vinculación con la sociedad y docente de la Universidad de las Artes. Magister en Economía Social y Solidaria por el IAEN; Magister en Proyectos Sociales y Productivos por la UNACH. Licenciado en Artes UCE. Licenciado en Castellano y Literatura por la UNACH. Doctorando del programa de Sociología de la UNED España. Larga trayectoria vinculado a las organizaciones sociales acompañando procesos de gestión cultural, formación de liderazgos y economía solidaria.</personal-details:content>
</person:biography>
<researcher-url:researcher-urls path="/0000-0001-5045-1000/researcher-urls"/>
<email:emails path="/0000-0001-5045-1000/email"/>
<address:addresses path="/0000-0001-5045-1000/address"/>
<keyword:keywords path="/0000-0001-5045-1000/keywords"/>
<external-identifier:external-identifiers path="/0000-0001-7291-3210/external-identifiers">
<common:last-modified-date>2018-02-05T23:27:36.636Z</common:last-modified-date>
<external-identifier:external-identifier put-code="134902" visibility="public" path="/0000-0001-7291-3210/external-identifiers/134902" display-index="1">
<common:created-date>2013-03-08T03:20:39.347Z</common:created-date>
<common:last-modified-date>2018-02-05T23:27:36.636Z</common:last-modified-date>
<common:source>
<common:source-client-id>
<common:uri>https://orcid.org/client/0000-0002-5982-8983</common:uri>
<common:path>0000-0002-5982-8983</common:path>
<common:host>orcid.org</common:host>
</common:source-client-id>
<common:source-name>Scopus - Elsevier</common:source-name>
<common:assertion-origin-orcid>
<common:uri>https://orcid.org/0000-0001-7291-3210</common:uri>
<common:path>0000-0001-7291-3210</common:path>
<common:host>orcid.org</common:host>
</common:assertion-origin-orcid>
<common:assertion-origin-name>Paolo Manghi</common:assertion-origin-name>
</common:source>
<common:external-id-type>Scopus Author ID</common:external-id-type>
<common:external-id-value>6602255248</common:external-id-value>
<common:external-id-url>http://www.scopus.com/inward/authorDetails.url?authorID=6602255248&amp;partnerID=MN8TOARS</common:external-id-url>
<common:external-id-relationship>self</common:external-id-relationship>
</external-identifier:external-identifier>
</external-identifier:external-identifiers>
</person:person>
<activities:activities-summary path="/0000-0001-5045-1000/activities">
<common:last-modified-date>2023-09-04T17:51:57.749Z</common:last-modified-date>
<activities:distinctions path="/0000-0001-5045-1000/distinctions">
<common:last-modified-date>2023-01-19T13:49:48.482Z</common:last-modified-date>
<activities:affiliation-group>
<common:last-modified-date>2023-01-19T13:49:48.482Z</common:last-modified-date>
<common:external-ids/>
<distinction:distinction-summary put-code="19395146" display-index="1" path="/0000-0001-5045-1000/distinction/19395146" visibility="public">
<common:created-date>2023-01-19T13:49:48.482Z</common:created-date>
<common:last-modified-date>2023-01-19T13:49:48.482Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-5045-1000</common:uri>
<common:path>0000-0001-5045-1000</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
<common:source-name>Patricio Sánchez Quinchuela</common:source-name>
</common:source>
<common:department-name>Programa de Maestría</common:department-name>
<common:role-title>Becario del programa de Maestría en Economía Social y Solidaria</common:role-title>
<common:start-date>
<common:year>2014</common:year>
<common:month>10</common:month>
<common:day>20</common:day>
</common:start-date>
<common:organization>
<common:name>Instituto de Altos Estudios Nacionales</common:name>
<common:address>
<common:city>Quito</common:city>
<common:region>Pichincha</common:region>
<common:country>EC</common:country>
</common:address>
<common:disambiguated-organization>
<common:disambiguated-organization-identifier>https://ror.org/011g3me54</common:disambiguated-organization-identifier>
<common:disambiguation-source>ROR</common:disambiguation-source>
</common:disambiguated-organization>
</common:organization>
</distinction:distinction-summary>
</activities:affiliation-group>
</activities:distinctions>
<activities:educations path="/0000-0001-5045-1000/educations">
<common:last-modified-date>2023-01-18T21:41:03.175Z</common:last-modified-date>
<activities:affiliation-group>
<common:last-modified-date>2023-01-18T21:41:03.175Z</common:last-modified-date>
<common:external-ids/>
<education:education-summary put-code="19389331" display-index="1" path="/0000-0001-5045-1000/education/19389331" visibility="public">
<common:created-date>2023-01-18T21:41:03.175Z</common:created-date>
<common:last-modified-date>2023-01-18T21:41:03.175Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-5045-1000</common:uri>
<common:path>0000-0001-5045-1000</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
<common:source-name>Patricio Sánchez Quinchuela</common:source-name>
</common:source>
<common:department-name>Programa de Doctorado en Sociología</common:department-name>
<common:role-title>Doctorando del Programa de Sociología</common:role-title>
<common:start-date>
<common:year>2020</common:year>
<common:month>11</common:month>
<common:day>06</common:day>
</common:start-date>
<common:organization>
<common:name>Universidad Nacional de Educación a Distancia Facultad de Ciencias Políticas y Sociología</common:name>
<common:address>
<common:city>Madrid</common:city>
<common:region>Comunidad de Madrid</common:region>
<common:country>ES</common:country>
</common:address>
<common:disambiguated-organization>
<common:disambiguated-organization-identifier>223339</common:disambiguated-organization-identifier>
<common:disambiguation-source>RINGGOLD</common:disambiguation-source>
</common:disambiguated-organization>
</common:organization>
</education:education-summary>
</activities:affiliation-group>
</activities:educations>
<activities:employments path="/0000-0001-5045-1000/employments">
<common:last-modified-date>2023-01-18T21:25:07.138Z</common:last-modified-date>
<activities:affiliation-group>
<common:last-modified-date>2023-01-18T21:22:21.513Z</common:last-modified-date>
<common:external-ids/>
<employment:employment-summary put-code="19379757" display-index="1" path="/0000-0001-5045-1000/employment/19379757" visibility="public">
<common:created-date>2023-01-17T23:57:08.246Z</common:created-date>
<common:last-modified-date>2023-01-18T21:22:21.513Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-5045-1000</common:uri>
<common:path>0000-0001-5045-1000</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
<common:source-name>Patricio Sánchez Quinchuela</common:source-name>
</common:source>
<common:department-name>Dirección de Vinculación con la Sociedad</common:department-name>
<common:role-title>Especialista de Proyectos y docente</common:role-title>
<common:start-date>
<common:year>2021</common:year>
<common:month>11</common:month>
<common:day>01</common:day>
</common:start-date>
<common:organization>
<common:name>Universidad de las Artes</common:name>
<common:address>
<common:city>Guayaquil</common:city>
<common:region>Guayas</common:region>
<common:country>EC</common:country>
</common:address>
<common:disambiguated-organization>
<common:disambiguated-organization-identifier>https://ror.org/016drwn73</common:disambiguated-organization-identifier>
<common:disambiguation-source>ROR</common:disambiguation-source>
</common:disambiguated-organization>
</common:organization>
</employment:employment-summary>
</activities:affiliation-group>
<activities:affiliation-group>
<common:last-modified-date>2023-01-18T21:25:07.138Z</common:last-modified-date>
<common:external-ids/>
<employment:employment-summary put-code="19389234" display-index="1" path="/0000-0001-5045-1000/employment/19389234" visibility="public">
<common:created-date>2023-01-18T21:25:07.138Z</common:created-date>
<common:last-modified-date>2023-01-18T21:25:07.138Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-5045-1000</common:uri>
<common:path>0000-0001-5045-1000</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
<common:source-name>Patricio Sánchez Quinchuela</common:source-name>
</common:source>
<common:department-name>Dirección de Vinculación con la Sociedad</common:department-name>
<common:role-title>Director</common:role-title>
<common:start-date>
<common:year>2019</common:year>
<common:month>11</common:month>
<common:day>05</common:day>
</common:start-date>
<common:end-date>
<common:year>2021</common:year>
<common:month>10</common:month>
<common:day>31</common:day>
</common:end-date>
<common:organization>
<common:name>Universidad Regional Amazónica IKIAM</common:name>
<common:address>
<common:city>Tena</common:city>
<common:region>Napo</common:region>
<common:country>EC</common:country>
</common:address>
<common:disambiguated-organization>
<common:disambiguated-organization-identifier>https://ror.org/05xedqd83</common:disambiguated-organization-identifier>
<common:disambiguation-source>ROR</common:disambiguation-source>
</common:disambiguated-organization>
</common:organization>
<common:url>http://ikiam.edu.ec</common:url>
</employment:employment-summary>
</activities:affiliation-group>
</activities:employments>
<activities:fundings path="/0000-0001-5045-1000/fundings"/>
<activities:invited-positions path="/0000-0001-5045-1000/invited-positions"/>
<activities:memberships path="/0000-0001-5045-1000/memberships">
<common:last-modified-date>2023-03-24T18:16:09.131Z</common:last-modified-date>
<activities:affiliation-group>
<common:last-modified-date>2023-03-24T18:16:09.131Z</common:last-modified-date>
<common:external-ids/>
<membership:membership-summary put-code="19927715" display-index="1" path="/0000-0001-5045-1000/membership/19927715" visibility="public">
<common:created-date>2023-03-24T18:16:09.131Z</common:created-date>
<common:last-modified-date>2023-03-24T18:16:09.131Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-5045-1000</common:uri>
<common:path>0000-0001-5045-1000</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
<common:source-name>Patricio Sánchez Quinchuela</common:source-name>
</common:source>
<common:department-name>Artes Escénicas</common:department-name>
<common:role-title>Miembro</common:role-title>
<common:start-date>
<common:year>2000</common:year>
<common:month>07</common:month>
<common:day>15</common:day>
</common:start-date>
<common:organization>
<common:name>Casa de la Cultura Ecuatoriana</common:name>
<common:address>
<common:city>Riobamba</common:city>
<common:region>Sierra Centro</common:region>
<common:country>EC</common:country>
</common:address>
</common:organization>
</membership:membership-summary>
</activities:affiliation-group>
</activities:memberships>
<activities:peer-reviews path="/0000-0001-5045-1000/peer-reviews"/>
<activities:qualifications path="/0000-0001-5045-1000/qualifications">
<common:last-modified-date>2023-01-18T21:45:07.379Z</common:last-modified-date>
<activities:affiliation-group>
<common:last-modified-date>2023-01-18T21:29:11.300Z</common:last-modified-date>
<common:external-ids/>
<qualification:qualification-summary put-code="19389264" display-index="1" path="/0000-0001-5045-1000/qualification/19389264" visibility="public">
<common:created-date>2023-01-18T21:29:11.300Z</common:created-date>
<common:last-modified-date>2023-01-18T21:29:11.300Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-5045-1000</common:uri>
<common:path>0000-0001-5045-1000</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
<common:source-name>Patricio Sánchez Quinchuela</common:source-name>
</common:source>
<common:department-name>Programa de Gobernabilidad</common:department-name>
<common:role-title>Magister en Economïa Social y Solidaria</common:role-title>
<common:start-date>
<common:year>2014</common:year>
<common:month>10</common:month>
<common:day>20</common:day>
</common:start-date>
<common:end-date>
<common:year>2017</common:year>
<common:month>01</common:month>
<common:day>26</common:day>
</common:end-date>
<common:organization>
<common:name>Instituto de Altos Estudios Nacionales</common:name>
<common:address>
<common:city>Quito</common:city>
<common:region>Pichincha</common:region>
<common:country>EC</common:country>
</common:address>
<common:disambiguated-organization>
<common:disambiguated-organization-identifier>https://ror.org/011g3me54</common:disambiguated-organization-identifier>
<common:disambiguation-source>ROR</common:disambiguation-source>
</common:disambiguated-organization>
</common:organization>
</qualification:qualification-summary>
</activities:affiliation-group>
<activities:affiliation-group>
<common:last-modified-date>2023-01-18T21:34:32.093Z</common:last-modified-date>
<common:external-ids/>
<qualification:qualification-summary put-code="19389298" display-index="1" path="/0000-0001-5045-1000/qualification/19389298" visibility="public">
<common:created-date>2023-01-18T21:34:32.093Z</common:created-date>
<common:last-modified-date>2023-01-18T21:34:32.093Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-5045-1000</common:uri>
<common:path>0000-0001-5045-1000</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
<common:source-name>Patricio Sánchez Quinchuela</common:source-name>
</common:source>
<common:department-name>Posgrados</common:department-name>
<common:role-title>Magister en Proyectos Sociales y Productivos</common:role-title>
<common:start-date>
<common:year>2001</common:year>
<common:month>03</common:month>
<common:day>09</common:day>
</common:start-date>
<common:end-date>
<common:year>2003</common:year>
<common:month>02</common:month>
<common:day>27</common:day>
</common:end-date>
<common:organization>
<common:name>Universidad Nacional de Chimborazo</common:name>
<common:address>
<common:city>Riobamba</common:city>
<common:region>Chimborazo</common:region>
<common:country>EC</common:country>
</common:address>
<common:disambiguated-organization>
<common:disambiguated-organization-identifier>https://ror.org/059wmd288</common:disambiguated-organization-identifier>
<common:disambiguation-source>ROR</common:disambiguation-source>
</common:disambiguated-organization>
</common:organization>
</qualification:qualification-summary>
</activities:affiliation-group>
<activities:affiliation-group>
<common:last-modified-date>2023-01-18T21:45:07.379Z</common:last-modified-date>
<common:external-ids/>
<qualification:qualification-summary put-code="19389353" display-index="1" path="/0000-0001-5045-1000/qualification/19389353" visibility="public">
<common:created-date>2023-01-18T21:45:07.379Z</common:created-date>
<common:last-modified-date>2023-01-18T21:45:07.379Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-5045-1000</common:uri>
<common:path>0000-0001-5045-1000</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
<common:source-name>Patricio Sánchez Quinchuela</common:source-name>
</common:source>
<common:department-name>Ciencias de la Educación</common:department-name>
<common:role-title>Licenciado en Ciencias de la Educación en Castellano y Literatura</common:role-title>
<common:start-date>
<common:year>1994</common:year>
<common:month>10</common:month>
<common:day>03</common:day>
</common:start-date>
<common:end-date>
<common:year>2000</common:year>
<common:month>01</common:month>
<common:day>31</common:day>
</common:end-date>
<common:organization>
<common:name>Universidad Nacional de Chimborazo</common:name>
<common:address>
<common:city>Riobamba</common:city>
<common:region>Chimborazo</common:region>
<common:country>EC</common:country>
</common:address>
<common:disambiguated-organization>
<common:disambiguated-organization-identifier>https://ror.org/059wmd288</common:disambiguated-organization-identifier>
<common:disambiguation-source>ROR</common:disambiguation-source>
</common:disambiguated-organization>
</common:organization>
</qualification:qualification-summary>
</activities:affiliation-group>
<activities:affiliation-group>
<common:last-modified-date>2023-01-18T21:37:42.186Z</common:last-modified-date>
<common:external-ids/>
<qualification:qualification-summary put-code="19389317" display-index="1" path="/0000-0001-5045-1000/qualification/19389317" visibility="public">
<common:created-date>2023-01-18T21:37:42.186Z</common:created-date>
<common:last-modified-date>2023-01-18T21:37:42.186Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-5045-1000</common:uri>
<common:path>0000-0001-5045-1000</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
<common:source-name>Patricio Sánchez Quinchuela</common:source-name>
</common:source>
<common:department-name>Facultad de Artes</common:department-name>
<common:role-title>Licenciado en Artes</common:role-title>
<common:start-date>
<common:year>1989</common:year>
<common:month>09</common:month>
<common:day>05</common:day>
</common:start-date>
<common:end-date>
<common:year>1997</common:year>
<common:month>08</common:month>
<common:day>07</common:day>
</common:end-date>
<common:organization>
<common:name>Universidad Central del Ecuador</common:name>
<common:address>
<common:city>Quito</common:city>
<common:region>Pichincha</common:region>
<common:country>EC</common:country>
</common:address>
<common:disambiguated-organization>
<common:disambiguated-organization-identifier>http://dx.doi.org/10.13039/100019134</common:disambiguated-organization-identifier>
<common:disambiguation-source>FUNDREF</common:disambiguation-source>
</common:disambiguated-organization>
</common:organization>
</qualification:qualification-summary>
</activities:affiliation-group>
</activities:qualifications>
<activities:research-resources path="/0000-0001-5045-1000/research-resources"/>
<activities:services path="/0000-0001-5045-1000/services"/>
<activities:works path="/0000-0001-5045-1000/works">
<common:last-modified-date>2023-09-04T17:51:57.749Z</common:last-modified-date>
<activities:group>
<common:last-modified-date>2023-06-09T22:15:12.910Z</common:last-modified-date>
<common:external-ids/>
<work:work-summary put-code="131526645" path="/0000-0001-5045-1000/work/131526645" visibility="public" display-index="1">
<common:created-date>2023-03-24T18:36:56.180Z</common:created-date>
<common:last-modified-date>2023-06-09T22:15:12.910Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-5045-1000</common:uri>
<common:path>0000-0001-5045-1000</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
<common:source-name>Patricio Sánchez Quinchuela</common:source-name>
</common:source>
<work:title>
<common:title>Experience in a non-capitalist way: solidarity funds that do not tax interest on the use of money</common:title>
</work:title>
<common:external-ids>
<common:external-id>
<common:external-id-type>isbn</common:external-id-type>
<common:external-id-value>978-9942-29-089-2</common:external-id-value>
<common:external-id-normalized transient="true">9789942290892</common:external-id-normalized>
<common:external-id-relationship>part-of</common:external-id-relationship>
</common:external-id>
</common:external-ids>
<work:type>book-chapter</work:type>
<common:publication-date>
<common:year>2023</common:year>
<common:month>06</common:month>
<common:day>07</common:day>
</common:publication-date>
<work:journal-title>Finanzas éticas y solidarias en América Latina: diagnósticos, debates y propuestas</work:journal-title>
</work:work-summary>
</activities:group>
<activities:group>
<common:last-modified-date>2023-03-24T19:05:36.384Z</common:last-modified-date>
<common:external-ids/>
<work:work-summary put-code="131527819" path="/0000-0001-5045-1000/work/131527819" visibility="public" display-index="1">
<common:created-date>2023-03-24T19:05:36.384Z</common:created-date>
<common:last-modified-date>2023-03-24T19:05:36.384Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-5045-1000</common:uri>
<common:path>0000-0001-5045-1000</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
<common:source-name>Patricio Sánchez Quinchuela</common:source-name>
</common:source>
<work:title>
<common:title>Incidence of artistic practices in the social transformation of the territory. study of case: Hilarte Association, Guayaquil-Ecuador</common:title>
</work:title>
<common:external-ids/>
<work:type>conference-abstract</work:type>
<common:publication-date>
<common:year>2022</common:year>
<common:month>10</common:month>
<common:day>06</common:day>
</common:publication-date>
</work:work-summary>
</activities:group>
<activities:group>
<common:last-modified-date>2023-09-04T17:40:30.215Z</common:last-modified-date>
<common:external-ids>
<common:external-id>
<common:external-id-type>other-id</common:external-id-type>
<common:external-id-value>2018</common:external-id-value>
<common:external-id-normalized transient="true">2018</common:external-id-normalized>
<common:external-id-relationship>self</common:external-id-relationship>
</common:external-id>
</common:external-ids>
<work:work-summary put-code="141716337" path="/0000-0001-5045-1000/work/141716337" visibility="public" display-index="1">
<common:created-date>2023-09-04T17:40:30.215Z</common:created-date>
<common:last-modified-date>2023-09-04T17:40:30.215Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-5045-1000</common:uri>
<common:path>0000-0001-5045-1000</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
<common:source-name>Patricio Sánchez Quinchuela</common:source-name>
</common:source>
<work:title>
<common:title>Más allá de la transferencia de conocimientos, un espacio para el interaprendizaje y el diálogo de saberes</common:title>
</work:title>
<common:external-ids>
<common:external-id>
<common:external-id-type>other-id</common:external-id-type>
<common:external-id-value>2018</common:external-id-value>
<common:external-id-normalized transient="true">2018</common:external-id-normalized>
<common:external-id-relationship>self</common:external-id-relationship>
</common:external-id>
</common:external-ids>
<common:url>https://drive.google.com/drive/folders/1Tclz6isxGzSjTq-hfTnxe6M1nux-88wF?usp=drive_link</common:url>
<work:type>conference-poster</work:type>
<common:publication-date>
<common:year>2018</common:year>
<common:month>11</common:month>
<common:day>30</common:day>
</common:publication-date>
<work:journal-title>Más allá de la transferencia de conocimientos, un espacio para el interaprendizaje y el diálogo de saberes</work:journal-title>
</work:work-summary>
</activities:group>
<activities:group>
<common:last-modified-date>2023-03-24T18:57:10.095Z</common:last-modified-date>
<common:external-ids/>
<work:work-summary put-code="131527433" path="/0000-0001-5045-1000/work/131527433" visibility="public" display-index="1">
<common:created-date>2023-03-24T18:57:10.095Z</common:created-date>
<common:last-modified-date>2023-03-24T18:57:10.095Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-5045-1000</common:uri>
<common:path>0000-0001-5045-1000</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
<common:source-name>Patricio Sánchez Quinchuela</common:source-name>
</common:source>
<work:title>
<common:title>Promotion of the popular and solidarity economy from the state: principles and challenges in the experience of Ecuador</common:title>
</work:title>
<common:external-ids/>
<work:type>dissertation-thesis</work:type>
<common:publication-date>
<common:year>2017</common:year>
<common:month>01</common:month>
<common:day>26</common:day>
</common:publication-date>
</work:work-summary>
</activities:group>
<activities:group>
<common:last-modified-date>2023-09-04T17:51:57.749Z</common:last-modified-date>
<common:external-ids/>
<work:work-summary put-code="141716713" path="/0000-0001-5045-1000/work/141716713" visibility="public" display-index="1">
<common:created-date>2023-09-04T17:51:57.749Z</common:created-date>
<common:last-modified-date>2023-09-04T17:51:57.749Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-5045-1000</common:uri>
<common:path>0000-0001-5045-1000</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
<common:source-name>Patricio Sánchez Quinchuela</common:source-name>
</common:source>
<work:title>
<common:title>La Rebelión de los Dioses</common:title>
</work:title>
<common:external-ids/>
<common:url>https://drive.google.com/drive/folders/1Tclz6isxGzSjTq-hfTnxe6M1nux-88wF?usp=drive_link</common:url>
<work:type>registered-copyright</work:type>
<common:publication-date>
<common:year>2001</common:year>
<common:month>08</common:month>
<common:day>28</common:day>
</common:publication-date>
<work:journal-title>Editorial pedagógica freire</work:journal-title>
</work:work-summary>
</activities:group>
</activities:works>
</activities:activities-summary>
</record:record>

57
dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/RelationAggregator.java
View File

@ -1,57 +0,0 @@
package eu.dnetlib.dhp.oa.dedup;
import java.util.Objects;
import org.apache.spark.sql.Encoder;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.expressions.Aggregator;
import eu.dnetlib.dhp.schema.oaf.Relation;
public class RelationAggregator extends Aggregator<Relation, Relation, Relation> {
private static final Relation ZERO = new Relation();
@Override
public Relation zero() {
return ZERO;
}
@Override
public Relation reduce(Relation b, Relation a) {
return mergeRel(b, a);
}
@Override
public Relation merge(Relation b, Relation a) {
return mergeRel(b, a);
}
@Override
public Relation finish(Relation r) {
return r;
}
private Relation mergeRel(Relation b, Relation a) {
if (Objects.equals(b, ZERO)) {
return a;
}
if (Objects.equals(a, ZERO)) {
return b;
}
b.mergeFrom(a);
return b;
}
@Override
public Encoder<Relation> bufferEncoder() {
return Encoders.kryo(Relation.class);
}
@Override
public Encoder<Relation> outputEncoder() {
return Encoders.kryo(Relation.class);
}
}

78
dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/SparkCleanRelation.scala
View File

@ -1,78 +0,0 @@
package eu.dnetlib.dhp.oa.dedup
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.common.HdfsSupport
import eu.dnetlib.dhp.schema.oaf.Relation
import eu.dnetlib.dhp.utils.ISLookupClientFactory
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService
import org.apache.commons.io.IOUtils
import org.apache.spark.SparkConf
import org.apache.spark.sql._
import org.apache.spark.sql.functions.col
import org.apache.spark.sql.types.{DataTypes, StructField, StructType}
import org.slf4j.LoggerFactory
object SparkCleanRelation {
private val log = LoggerFactory.getLogger(classOf[SparkCleanRelation])
@throws[Exception]
def main(args: Array[String]): Unit = {
val parser = new ArgumentApplicationParser(
IOUtils.toString(
classOf[SparkCleanRelation].getResourceAsStream("/eu/dnetlib/dhp/oa/dedup/cleanRelation_parameters.json")
)
)
parser.parseArgument(args)
val conf = new SparkConf
new SparkCleanRelation(parser, AbstractSparkAction.getSparkSession(conf))
.run(ISLookupClientFactory.getLookUpService(parser.get("isLookUpUrl")))
}
}
class SparkCleanRelation(parser: ArgumentApplicationParser, spark: SparkSession)
extends AbstractSparkAction(parser, spark) {
override def run(isLookUpService: ISLookUpService): Unit = {
val graphBasePath = parser.get("graphBasePath")
val inputPath = parser.get("inputPath")
val outputPath = parser.get("outputPath")
SparkCleanRelation.log.info("graphBasePath: '{}'", graphBasePath)
SparkCleanRelation.log.info("inputPath: '{}'", inputPath)
SparkCleanRelation.log.info("outputPath: '{}'", outputPath)
AbstractSparkAction.removeOutputDir(spark, outputPath)
val entities =
Seq("datasource", "project", "organization", "publication", "dataset", "software", "otherresearchproduct")
val idsSchema = StructType.fromDDL("`id` STRING, `dataInfo` STRUCT<`deletedbyinference`:BOOLEAN,`invisible`:BOOLEAN>")
val emptyIds = spark.createDataFrame(spark.sparkContext.emptyRDD[Row].setName("empty"),
idsSchema)
val ids = entities
.foldLeft(emptyIds)((ds, entity) => {
val entityPath = graphBasePath + '/' + entity
if (HdfsSupport.exists(entityPath, spark.sparkContext.hadoopConfiguration)) {
ds.union(spark.read.schema(idsSchema).json(entityPath))
} else {
ds
}
})
.filter("dataInfo.deletedbyinference != true AND dataInfo.invisible != true")
.select("id")
.distinct()
val relations = spark.read.schema(Encoders.bean(classOf[Relation]).schema).json(inputPath)
.filter("dataInfo.deletedbyinference != true AND dataInfo.invisible != true")
AbstractSparkAction.save(
relations
.join(ids, col("source") === ids("id"), "leftsemi")
.join(ids, col("target") === ids("id"), "leftsemi"),
outputPath,
SaveMode.Overwrite
)
}
}

10
dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/SparkCopyOpenorgsMergeRels.java
View File

@ -7,6 +7,7 @@ import java.util.Optional;
import org.apache.commons.io.IOUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.SaveMode;
import org.apache.spark.sql.SparkSession;
@ -77,13 +78,12 @@ public class SparkCopyOpenorgsMergeRels extends AbstractSparkAction {
log.info("Number of Openorgs Merge Relations collected: {}", mergeRelsRDD.count());
spark
final Dataset<Relation> relations = spark
.createDataset(
mergeRelsRDD.rdd(),
Encoders.bean(Relation.class))
.write()
.mode(SaveMode.Append)
.parquet(outputPath);
Encoders.bean(Relation.class));
saveParquet(relations, outputPath, SaveMode.Append);
}
private boolean isMergeRel(Relation rel) {

7
dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/SparkCopyRelationsNoOpenorgs.java
View File

@ -67,12 +67,7 @@ public class SparkCopyRelationsNoOpenorgs extends AbstractSparkAction {
log.debug("Number of non-Openorgs relations collected: {}", simRels.count());
}
spark
.createDataset(simRels.rdd(), Encoders.bean(Relation.class))
.write()
.mode(SaveMode.Overwrite)
.json(outputPath);
save(spark.createDataset(simRels.rdd(), Encoders.bean(Relation.class)), outputPath, SaveMode.Overwrite);
}
}

2
dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/SparkCreateMergeRels.java
View File

@ -155,7 +155,7 @@ public class SparkCreateMergeRels extends AbstractSparkAction {
(FlatMapFunction<ConnectedComponent, Relation>) cc -> ccToMergeRel(cc, dedupConf),
Encoders.bean(Relation.class));
mergeRels.write().mode(SaveMode.Overwrite).parquet(mergeRelPath);
saveParquet(mergeRels, mergeRelPath, SaveMode.Overwrite);
}
}

6
dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/SparkCreateOrgsDedupRecord.java
View File

@ -72,11 +72,7 @@ public class SparkCreateOrgsDedupRecord extends AbstractSparkAction {
final String mergeRelsPath = DedupUtility.createMergeRelPath(workingPath, actionSetId, "organization");
rootOrganization(spark, entityPath, mergeRelsPath)
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(outputPath);
save(rootOrganization(spark, entityPath, mergeRelsPath), outputPath, SaveMode.Overwrite);
}

2
dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/SparkCreateSimRels.java
View File

@ -82,8 +82,6 @@ public class SparkCreateSimRels extends AbstractSparkAction {
final String outputPath = DedupUtility.createSimRelPath(workingPath, actionSetId, subEntity);
removeOutputDir(spark, outputPath);
JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
SparkDeduper deduper = new SparkDeduper(dedupConf);
Dataset<?> simRels = spark

120
dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/SparkPropagateRelation.java
View File

@ -3,23 +3,19 @@ package eu.dnetlib.dhp.oa.dedup;
import static org.apache.spark.sql.functions.col;
import java.util.Arrays;
import java.util.Collections;
import java.util.Iterator;
import java.util.Objects;
import org.apache.commons.beanutils.BeanUtils;
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.api.java.function.ReduceFunction;
import org.apache.spark.sql.*;
import org.apache.spark.sql.catalyst.encoders.RowEncoder;
import org.apache.spark.sql.types.StructType;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.schema.common.EntityType;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.DataInfo;
@ -70,73 +66,63 @@ public class SparkPropagateRelation extends AbstractSparkAction {
log.info("workingPath: '{}'", workingPath);
log.info("graphOutputPath: '{}'", graphOutputPath);
final String outputRelationPath = DedupUtility.createEntityPath(graphOutputPath, "relation");
removeOutputDir(spark, outputRelationPath);
Dataset<Relation> mergeRels = spark
.read()
.load(DedupUtility.createMergeRelPath(workingPath, "*", "*"))
.as(REL_BEAN_ENC);
// <mergedObjectID, dedupID>
Dataset<Row> mergedIds = mergeRels
Dataset<Row> idsToMerge = mergeRels
.where(col("relClass").equalTo(ModelConstants.MERGES))
.select(col("source").as("dedupID"), col("target").as("mergedObjectID"))
.distinct()
.cache();
.distinct();
Dataset<Row> allRels = spark
.read()
.schema(REL_BEAN_ENC.schema())
.json(DedupUtility.createEntityPath(graphBasePath, "relation"));
.json(graphBasePath + "/relation");
Dataset<Relation> dedupedRels = allRels
.joinWith(mergedIds, allRels.col("source").equalTo(mergedIds.col("mergedObjectID")), "left_outer")
.joinWith(mergedIds, col("_1.target").equalTo(mergedIds.col("mergedObjectID")), "left_outer")
.joinWith(idsToMerge, allRels.col("source").equalTo(idsToMerge.col("mergedObjectID")), "left_outer")
.joinWith(idsToMerge, col("_1.target").equalTo(idsToMerge.col("mergedObjectID")), "left_outer")
.select("_1._1", "_1._2.dedupID", "_2.dedupID")
.as(Encoders.tuple(REL_BEAN_ENC, Encoders.STRING(), Encoders.STRING()))
.flatMap(SparkPropagateRelation::addInferredRelations, REL_KRYO_ENC);
.map((MapFunction<Tuple3<Relation, String, String>, Relation>) t -> {
Relation rel = t._1();
String newSource = t._2();
String newTarget = t._3();
Dataset<Relation> processedRelations = distinctRelations(
dedupedRels.union(mergeRels.map((MapFunction<Relation, Relation>) r -> r, REL_KRYO_ENC)))
.filter((FilterFunction<Relation>) r -> !Objects.equals(r.getSource(), r.getTarget()));
if (rel.getDataInfo() == null) {
rel.setDataInfo(new DataInfo());
}
save(processedRelations, outputRelationPath, SaveMode.Overwrite);
}
if (newSource != null || newTarget != null) {
rel.getDataInfo().setDeletedbyinference(false);
private static Iterator<Relation> addInferredRelations(Tuple3<Relation, String, String> t) throws Exception {
Relation existingRel = t._1();
String newSource = t._2();
String newTarget = t._3();
if (newSource != null)
rel.setSource(newSource);
if (newSource == null && newTarget == null) {
return Collections.singleton(t._1()).iterator();
}
if (newTarget != null)
rel.setTarget(newTarget);
}
// update existing relation
if (existingRel.getDataInfo() == null) {
existingRel.setDataInfo(new DataInfo());
}
existingRel.getDataInfo().setDeletedbyinference(true);
return rel;
}, REL_BEAN_ENC);
// Create new relation inferred by dedupIDs
Relation inferredRel = (Relation) BeanUtils.cloneBean(existingRel);
// ids of records that are both not deletedbyinference and not invisible
Dataset<Row> ids = validIds(spark, graphBasePath);
inferredRel.setDataInfo((DataInfo) BeanUtils.cloneBean(existingRel.getDataInfo()));
inferredRel.getDataInfo().setDeletedbyinference(false);
// filter relations that point to valid records, can force them to be visible
Dataset<Relation> cleanedRels = dedupedRels
.join(ids, col("source").equalTo(ids.col("id")), "leftsemi")
.join(ids, col("target").equalTo(ids.col("id")), "leftsemi")
.as(REL_BEAN_ENC)
.map((MapFunction<Relation, Relation>) r -> {
r.getDataInfo().setInvisible(false);
return r;
}, REL_KRYO_ENC);
if (newSource != null)
inferredRel.setSource(newSource);
if (newTarget != null)
inferredRel.setTarget(newTarget);
return Arrays.asList(existingRel, inferredRel).iterator();
}
private Dataset<Relation> distinctRelations(Dataset<Relation> rels) {
return rels
.filter(getRelationFilterFunction())
Dataset<Relation> distinctRels = cleanedRels
.groupByKey(
(MapFunction<Relation, String>) r -> String
.join(" ", r.getSource(), r.getTarget(), r.getRelType(), r.getSubRelType(), r.getRelClass()),
@ -146,13 +132,33 @@ public class SparkPropagateRelation extends AbstractSparkAction {
return b;
})
.map((MapFunction<Tuple2<String, Relation>, Relation>) Tuple2::_2, REL_BEAN_ENC);
final String outputRelationPath = graphOutputPath + "/relation";
removeOutputDir(spark, outputRelationPath);
save(
distinctRels
.union(mergeRels)
.filter("source != target AND dataInfo.deletedbyinference != true AND dataInfo.invisible != true"),
outputRelationPath,
SaveMode.Overwrite);
}
private FilterFunction<Relation> getRelationFilterFunction() {
return r -> StringUtils.isNotBlank(r.getSource()) ||
StringUtils.isNotBlank(r.getTarget()) ||
StringUtils.isNotBlank(r.getRelType()) ||
StringUtils.isNotBlank(r.getSubRelType()) ||
StringUtils.isNotBlank(r.getRelClass());
static Dataset<Row> validIds(SparkSession spark, String graphBasePath) {
StructType idsSchema = StructType
.fromDDL("`id` STRING, `dataInfo` STRUCT<`deletedbyinference`:BOOLEAN,`invisible`:BOOLEAN>");
Dataset<Row> allIds = spark.emptyDataset(RowEncoder.apply(idsSchema));
for (EntityType entityType : ModelSupport.entityTypes.keySet()) {
String entityPath = graphBasePath + '/' + entityType.name();
if (HdfsSupport.exists(entityPath, spark.sparkContext().hadoopConfiguration())) {
allIds = allIds.union(spark.read().schema(idsSchema).json(entityPath));
}
}
return allIds
.filter("dataInfo.deletedbyinference != true AND dataInfo.invisible != true")
.select("id")
.distinct();
}
}

2
dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/SparkWhitelistSimRels.java
View File

@ -67,8 +67,6 @@ public class SparkWhitelistSimRels extends AbstractSparkAction {
log.info("workingPath: '{}'", workingPath);
log.info("whiteListPath: '{}'", whiteListPath);
JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
// file format: source####target
Dataset<Row> whiteListRels = spark
.read()

20
dhp-workflows/dhp-dedup-openaire/src/main/resources/eu/dnetlib/dhp/oa/dedup/cleanRelation_parameters.json
View File

@ -1,20 +0,0 @@
[
{
"paramName": "i",
"paramLongName": "graphBasePath",
"paramDescription": "the base path of raw graph",
"paramRequired": true
},
{
"paramName": "w",
"paramLongName": "inputPath",
"paramDescription": "the path to the input relation to cleanup",
"paramRequired": true
},
{
"paramName": "o",
"paramLongName": "outputPath",
"paramDescription": "the path of the output relation cleaned",
"paramRequired": true
}
]

59
dhp-workflows/dhp-dedup-openaire/src/main/resources/eu/dnetlib/dhp/oa/dedup/consistency/oozie_app/workflow.xml
View File

@ -16,6 +16,10 @@
<name>filterInvisible</name>
<description>whether filter out invisible entities after merge</description>
</property>
<property>
<name>isLookupUrl</name>
<description>the URL address of the lookUp service</description>
</property>
<property>
<name>sparkDriverMemory</name>
<description>heap memory for driver process</description>
@ -100,35 +104,9 @@
--conf spark.sql.shuffle.partitions=15000
</spark-opts>
<arg>--graphBasePath</arg><arg>${graphBasePath}</arg>
<arg>--graphOutputPath</arg><arg>${workingPath}/propagaterelation/</arg>
<arg>--graphOutputPath</arg><arg>${graphOutputPath}</arg>
<arg>--workingPath</arg><arg>${workingPath}</arg>
</spark>
<ok to="CleanRelation"/>
<error to="Kill"/>
</action>
<action name="CleanRelation">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Clean Relations</name>
<class>eu.dnetlib.dhp.oa.dedup.SparkCleanRelation</class>
<jar>dhp-dedup-openaire-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--conf spark.executor.memoryOverhead=${sparkExecutorMemoryOverhead}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=15000
</spark-opts>
<arg>--graphBasePath</arg><arg>${graphBasePath}</arg>
<arg>--inputPath</arg><arg>${workingPath}/propagaterelation/relation</arg>
<arg>--outputPath</arg><arg>${graphOutputPath}/relation</arg>
</spark>
<ok to="group_entities"/>
<error to="Kill"/>
</action>
@ -152,32 +130,9 @@
--conf spark.sql.shuffle.partitions=15000
</spark-opts>
<arg>--graphInputPath</arg><arg>${graphBasePath}</arg>
<arg>--outputPath</arg><arg>${workingPath}/grouped_entities</arg>
</spark>
<ok to="dispatch_entities"/>
<error to="Kill"/>
</action>
<action name="dispatch_entities">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Dispatch grouped entitities</name>
<class>eu.dnetlib.dhp.oa.merge.DispatchEntitiesSparkJob</class>
<jar>dhp-dedup-openaire-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--conf spark.executor.memoryOverhead=${sparkExecutorMemoryOverhead}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=7680
</spark-opts>
<arg>--inputPath</arg><arg>${workingPath}/grouped_entities</arg>
<arg>--checkpointPath</arg><arg>${workingPath}/grouped_entities</arg>
<arg>--outputPath</arg><arg>${graphOutputPath}</arg>
<arg>--isLookupUrl</arg><arg>${isLookupUrl}</arg>
<arg>--filterInvisible</arg><arg>${filterInvisible}</arg>
</spark>
<ok to="End"/>

150
dhp-workflows/dhp-dedup-openaire/src/test/java/eu/dnetlib/dhp/oa/dedup/SparkDedupTest.java
View File

@ -3,7 +3,6 @@ package eu.dnetlib.dhp.oa.dedup;
import static java.nio.file.Files.createTempDirectory;
import static org.apache.spark.sql.functions.col;
import static org.apache.spark.sql.functions.count;
import static org.junit.jupiter.api.Assertions.*;
import static org.mockito.Mockito.lenient;
@ -23,14 +22,13 @@ import java.util.stream.Collectors;
import org.apache.commons.io.FileUtils;
import org.apache.commons.io.IOUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaRDD;
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.PairFunction;
import org.apache.spark.sql.*;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.SparkSession;
import org.junit.jupiter.api.*;
import org.junit.jupiter.api.extension.ExtendWith;
import org.mockito.Mock;
@ -46,8 +44,6 @@ import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.*;
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpException;
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
import eu.dnetlib.pace.util.MapDocumentUtil;
import scala.Tuple2;
@ExtendWith(MockitoExtension.class)
@TestMethodOrder(MethodOrderer.OrderAnnotation.class)
@ -62,6 +58,8 @@ public class SparkDedupTest implements Serializable {
private static String testGraphBasePath;
private static String testOutputBasePath;
private static String testDedupGraphBasePath;
private static String testConsistencyGraphBasePath;
private static final String testActionSetId = "test-orchestrator";
private static String whitelistPath;
private static List<String> whiteList;
@ -75,6 +73,7 @@ public class SparkDedupTest implements Serializable {
.get(SparkDedupTest.class.getResource("/eu/dnetlib/dhp/dedup/entities").toURI())
.toFile()
.getAbsolutePath();
testOutputBasePath = createTempDirectory(SparkDedupTest.class.getSimpleName() + "-")
.toAbsolutePath()
.toString();
@ -83,6 +82,10 @@ public class SparkDedupTest implements Serializable {
.toAbsolutePath()
.toString();
testConsistencyGraphBasePath = createTempDirectory(SparkDedupTest.class.getSimpleName() + "-")
.toAbsolutePath()
.toString();
whitelistPath = Paths
.get(SparkDedupTest.class.getResource("/eu/dnetlib/dhp/dedup/whitelist.simrels.txt").toURI())
.toFile()
@ -674,22 +677,45 @@ public class SparkDedupTest implements Serializable {
assertEquals(mergedOrp, deletedOrp);
}
@Test
@Order(6)
void copyRelationsNoOpenorgsTest() throws Exception {
ArgumentApplicationParser parser = new ArgumentApplicationParser(
IOUtils
.toString(
SparkCopyRelationsNoOpenorgs.class
.getResourceAsStream(
"/eu/dnetlib/dhp/oa/dedup/updateEntity_parameters.json")));
parser
.parseArgument(
new String[] {
"-i", testGraphBasePath, "-w", testOutputBasePath, "-o", testDedupGraphBasePath
});
new SparkCopyRelationsNoOpenorgs(parser, spark).run(isLookUpService);
final Dataset<Row> outputRels = spark.read().text(testDedupGraphBasePath + "/relation");
System.out.println(outputRels.count());
// assertEquals(2382, outputRels.count());
}
@Test
@Order(7)
void propagateRelationTest() throws Exception {
ArgumentApplicationParser parser = new ArgumentApplicationParser(
classPathResourceAsString("/eu/dnetlib/dhp/oa/dedup/propagateRelation_parameters.json"));
String outputRelPath = testDedupGraphBasePath + "/propagaterelation";
parser
.parseArgument(
new String[] {
"-i", testGraphBasePath, "-w", testOutputBasePath, "-o", outputRelPath
"-i", testDedupGraphBasePath, "-w", testOutputBasePath, "-o", testConsistencyGraphBasePath
});
new SparkPropagateRelation(parser, spark).run(isLookUpService);
long relations = jsc.textFile(outputRelPath + "/relation").count();
long relations = jsc.textFile(testDedupGraphBasePath + "/relation").count();
// assertEquals(4860, relations);
System.out.println("relations = " + relations);
@ -699,95 +725,52 @@ public class SparkDedupTest implements Serializable {
.read()
.load(DedupUtility.createMergeRelPath(testOutputBasePath, "*", "*"))
.as(Encoders.bean(Relation.class));
final JavaPairRDD<String, String> mergedIds = mergeRels
.where("relClass == 'merges'")
.select(mergeRels.col("target"))
.distinct()
.toJavaRDD()
.mapToPair(
(PairFunction<Row, String, String>) r -> new Tuple2<String, String>(r.getString(0), "d"));
JavaRDD<String> toCheck = jsc
.textFile(outputRelPath + "/relation")
.mapToPair(json -> new Tuple2<>(MapDocumentUtil.getJPathString("$.source", json), json))
.join(mergedIds)
.map(t -> t._2()._1())
.mapToPair(json -> new Tuple2<>(MapDocumentUtil.getJPathString("$.target", json), json))
.join(mergedIds)
.map(t -> t._2()._1());
Dataset<Row> inputRels = spark
.read()
.json(testDedupGraphBasePath + "/relation");
long deletedbyinference = toCheck.filter(this::isDeletedByInference).count();
long updated = toCheck.count();
Dataset<Row> outputRels = spark
.read()
.json(testConsistencyGraphBasePath + "/relation");
assertEquals(updated, deletedbyinference);
assertEquals(
0, outputRels
.filter("dataInfo.deletedbyinference == true OR dataInfo.invisible == true")
.count());
assertEquals(
5, outputRels
.filter("relClass NOT IN ('merges', 'isMergedIn')")
.count());
assertEquals(5 + mergeRels.count(), outputRels.count());
}
@Test
@Order(8)
void testCleanBaseRelations() throws Exception {
ArgumentApplicationParser parser = new ArgumentApplicationParser(
classPathResourceAsString("/eu/dnetlib/dhp/oa/dedup/cleanRelation_parameters.json"));
// append dangling relations to be cleaned up
void testCleanedPropagatedRelations() throws Exception {
Dataset<Row> df_before = spark
.read()
.schema(Encoders.bean(Relation.class).schema())
.json(testGraphBasePath + "/relation");
Dataset<Row> df_input = df_before
.unionByName(df_before.drop("source").withColumn("source", functions.lit("n/a")))
.unionByName(df_before.drop("target").withColumn("target", functions.lit("n/a")));
df_input.write().mode(SaveMode.Overwrite).json(testOutputBasePath + "_tmp");
parser
.parseArgument(
new String[] {
"--graphBasePath", testGraphBasePath,
"--inputPath", testGraphBasePath + "/relation",
"--outputPath", testDedupGraphBasePath + "/relation"
});
new SparkCleanRelation(parser, spark).run(isLookUpService);
.json(testDedupGraphBasePath + "/relation");
Dataset<Row> df_after = spark
.read()
.schema(Encoders.bean(Relation.class).schema())
.json(testDedupGraphBasePath + "/relation");
assertNotEquals(df_before.count(), df_input.count());
assertNotEquals(df_input.count(), df_after.count());
assertEquals(5, df_after.count());
}
@Test
@Order(9)
void testCleanDedupedRelations() throws Exception {
ArgumentApplicationParser parser = new ArgumentApplicationParser(
classPathResourceAsString("/eu/dnetlib/dhp/oa/dedup/cleanRelation_parameters.json"));
String inputRelPath = testDedupGraphBasePath + "/propagaterelation/relation";
// append dangling relations to be cleaned up
Dataset<Row> df_before = spark.read().schema(Encoders.bean(Relation.class).schema()).json(inputRelPath);
df_before.filter(col("dataInfo.deletedbyinference").notEqual(true)).show(50, false);
parser
.parseArgument(
new String[] {
"--graphBasePath", testGraphBasePath,
"--inputPath", inputRelPath,
"--outputPath", testDedupGraphBasePath + "/relation"
});
new SparkCleanRelation(parser, spark).run(isLookUpService);
Dataset<Row> df_after = spark
.read()
.schema(Encoders.bean(Relation.class).schema())
.json(testDedupGraphBasePath + "/relation");
.json(testConsistencyGraphBasePath + "/relation");
assertNotEquals(df_before.count(), df_after.count());
assertEquals(0, df_after.count());
assertEquals(
0, df_after
.filter("dataInfo.deletedbyinference == true OR dataInfo.invisible == true")
.count());
assertEquals(
5, df_after
.filter("relClass NOT IN ('merges', 'isMergedIn')")
.count());
}
@Test
@ -813,6 +796,7 @@ public class SparkDedupTest implements Serializable {
public static void finalCleanUp() throws IOException {
FileUtils.deleteDirectory(new File(testOutputBasePath));
FileUtils.deleteDirectory(new File(testDedupGraphBasePath));
FileUtils.deleteDirectory(new File(testConsistencyGraphBasePath));
}
public boolean isDeletedByInference(String s) {

103
dhp-workflows/dhp-dedup-openaire/src/test/java/eu/dnetlib/dhp/oa/dedup/SparkOpenorgsProvisionTest.java
View File

@ -3,6 +3,7 @@ package eu.dnetlib.dhp.oa.dedup;
import static java.nio.file.Files.createTempDirectory;
import static org.apache.spark.sql.functions.col;
import static org.junit.jupiter.api.Assertions.assertEquals;
import static org.mockito.Mockito.lenient;
@ -15,10 +16,6 @@ import java.nio.file.Paths;
import org.apache.commons.io.FileUtils;
import org.apache.commons.io.IOUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.PairFunction;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.Row;
@ -33,8 +30,6 @@ import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.schema.oaf.Relation;
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpException;
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
import eu.dnetlib.pace.util.MapDocumentUtil;
import scala.Tuple2;
@ExtendWith(MockitoExtension.class)
@TestMethodOrder(MethodOrderer.OrderAnnotation.class)
@ -44,11 +39,11 @@ public class SparkOpenorgsProvisionTest implements Serializable {
ISLookUpService isLookUpService;
private static SparkSession spark;
private static JavaSparkContext jsc;
private static String testGraphBasePath;
private static String testOutputBasePath;
private static String testDedupGraphBasePath;
private static String testConsistencyGraphBasePath;
private static final String testActionSetId = "test-orchestrator";
@BeforeAll
@ -64,6 +59,9 @@ public class SparkOpenorgsProvisionTest implements Serializable {
testDedupGraphBasePath = createTempDirectory(SparkOpenorgsProvisionTest.class.getSimpleName() + "-")
.toAbsolutePath()
.toString();
testConsistencyGraphBasePath = createTempDirectory(SparkOpenorgsProvisionTest.class.getSimpleName() + "-")
.toAbsolutePath()
.toString();
FileUtils.deleteDirectory(new File(testOutputBasePath));
FileUtils.deleteDirectory(new File(testDedupGraphBasePath));
@ -76,8 +74,13 @@ public class SparkOpenorgsProvisionTest implements Serializable {
.master("local[*]")
.config(conf)
.getOrCreate();
}
jsc = JavaSparkContext.fromSparkContext(spark.sparkContext());
@AfterAll
public static void finalCleanUp() throws IOException {
FileUtils.deleteDirectory(new File(testOutputBasePath));
FileUtils.deleteDirectory(new File(testDedupGraphBasePath));
FileUtils.deleteDirectory(new File(testConsistencyGraphBasePath));
}
@BeforeEach
@ -186,26 +189,21 @@ public class SparkOpenorgsProvisionTest implements Serializable {
new SparkUpdateEntity(parser, spark).run(isLookUpService);
long organizations = jsc.textFile(testDedupGraphBasePath + "/organization").count();
Dataset<Row> organizations = spark.read().json(testDedupGraphBasePath + "/organization");
long mergedOrgs = spark
Dataset<Row> mergedOrgs = spark
.read()
.load(testOutputBasePath + "/" + testActionSetId + "/organization_mergerel")
.as(Encoders.bean(Relation.class))
.where("relClass=='merges'")
.javaRDD()
.map(Relation::getTarget)
.distinct()
.count();
.select("target")
.distinct();
assertEquals(80, organizations);
assertEquals(80, organizations.count());
long deletedOrgs = jsc
.textFile(testDedupGraphBasePath + "/organization")
.filter(this::isDeletedByInference)
.count();
Dataset<Row> deletedOrgs = organizations
.filter("dataInfo.deletedbyinference = TRUE");
assertEquals(mergedOrgs, deletedOrgs);
assertEquals(mergedOrgs.count(), deletedOrgs.count());
}
@Test
@ -226,10 +224,9 @@ public class SparkOpenorgsProvisionTest implements Serializable {
new SparkCopyRelationsNoOpenorgs(parser, spark).run(isLookUpService);
final JavaRDD<String> rels = jsc.textFile(testDedupGraphBasePath + "/relation");
assertEquals(2382, rels.count());
final Dataset<Row> outputRels = spark.read().text(testDedupGraphBasePath + "/relation");
assertEquals(2382, outputRels.count());
}
@Test
@ -244,51 +241,41 @@ public class SparkOpenorgsProvisionTest implements Serializable {
parser
.parseArgument(
new String[] {
"-i", testGraphBasePath, "-w", testOutputBasePath, "-o", testDedupGraphBasePath
"-i", testDedupGraphBasePath, "-w", testOutputBasePath, "-o", testConsistencyGraphBasePath
});
new SparkPropagateRelation(parser, spark).run(isLookUpService);
long relations = jsc.textFile(testDedupGraphBasePath + "/relation").count();
assertEquals(4896, relations);
// check deletedbyinference
final Dataset<Relation> mergeRels = spark
.read()
.load(DedupUtility.createMergeRelPath(testOutputBasePath, "*", "*"))
.as(Encoders.bean(Relation.class));
final JavaPairRDD<String, String> mergedIds = mergeRels
Dataset<Row> inputRels = spark
.read()
.json(testDedupGraphBasePath + "/relation");
Dataset<Row> outputRels = spark
.read()
.json(testConsistencyGraphBasePath + "/relation");
final Dataset<Row> mergedIds = mergeRels
.where("relClass == 'merges'")
.select(mergeRels.col("target"))
.distinct()
.toJavaRDD()
.mapToPair(
(PairFunction<Row, String, String>) r -> new Tuple2<String, String>(r.getString(0), "d"));
.select(col("target").as("id"))
.distinct();
JavaRDD<String> toCheck = jsc
.textFile(testDedupGraphBasePath + "/relation")
.mapToPair(json -> new Tuple2<>(MapDocumentUtil.getJPathString("$.source", json), json))
.join(mergedIds)
.map(t -> t._2()._1())
.mapToPair(json -> new Tuple2<>(MapDocumentUtil.getJPathString("$.target", json), json))
.join(mergedIds)
.map(t -> t._2()._1());
Dataset<Row> toUpdateRels = inputRels
.as("rel")
.join(mergedIds.as("s"), col("rel.source").equalTo(col("s.id")), "left_outer")
.join(mergedIds.as("t"), col("rel.target").equalTo(col("t.id")), "left_outer")
.filter("s.id IS NOT NULL OR t.id IS NOT NULL")
.distinct();
long deletedbyinference = toCheck.filter(this::isDeletedByInference).count();
long updated = toCheck.count();
Dataset<Row> updatedRels = inputRels
.select("source", "target", "relClass")
.except(outputRels.select("source", "target", "relClass"));
assertEquals(updated, deletedbyinference);
assertEquals(toUpdateRels.count(), updatedRels.count());
assertEquals(140, outputRels.count());
}
@AfterAll
public static void finalCleanUp() throws IOException {
FileUtils.deleteDirectory(new File(testOutputBasePath));
FileUtils.deleteDirectory(new File(testDedupGraphBasePath));
}
public boolean isDeletedByInference(String s) {
return s.contains("\"deletedbyinference\":true");
}
}

940
dhp-workflows/dhp-doiboost/src/main/resources/eu/dnetlib/dhp/doiboost/crossref/irish_funder.json Normal file
View File

@ -0,0 +1,940 @@
[
{
"id": "100007630",
"uri": "http://dx.doi.org/10.13039/100007630",
"name": "College of Engineering and Informatics, National University of Ireland, Galway",
"synonym": []
},
{
"id": "100007731",
"uri": "http://dx.doi.org/10.13039/100007731",
"name": "Endo International",
"synonym": []
},
{
"id": "100008099",
"uri": "http://dx.doi.org/10.13039/100008099",
"name": "Food Safety Authority of Ireland",
"synonym": []
},
{
"id": "100008124",
"uri": "http://dx.doi.org/10.13039/100008124",
"name": "Department of Jobs, Enterprise and Innovation",
"synonym": []
},
{
"id": "100009098",
"uri": "http://dx.doi.org/10.13039/100009098",
"name": "Department of Foreign Affairs and Trade, Ireland",
"synonym": []
},
{
"id": "100009099",
"uri": "http://dx.doi.org/10.13039/100009099",
"name": "Irish Aid",
"synonym": []
},
{
"id": "100009770",
"uri": "http://dx.doi.org/10.13039/100009770",
"name": "National University of Ireland",
"synonym": []
},
{
"id": "100009985",
"uri": "http://dx.doi.org/10.13039/100009985",
"name": "Parkinson's Association of Ireland",
"synonym": []
},
{
"id": "100010399",
"uri": "http://dx.doi.org/10.13039/100010399",
"name": "European Society of Cataract and Refractive Surgeons",
"synonym": []
},
{
"id": "100010414",
"uri": "http://dx.doi.org/10.13039/100010414",
"name": "Health Research Board",
"synonym": [
"501100001590"
]
},
{
"id": "100010546",
"uri": "http://dx.doi.org/10.13039/100010546",
"name": "Deparment of Children and Youth Affairs, Ireland",
"synonym": []
},
{
"id": "100010993",
"uri": "http://dx.doi.org/10.13039/100010993",
"name": "Irish Nephrology Society",
"synonym": []
},
{
"id": "100011062",
"uri": "http://dx.doi.org/10.13039/100011062",
"name": "Asian Spinal Cord Network",
"synonym": []
},
{
"id": "100011096",
"uri": "http://dx.doi.org/10.13039/100011096",
"name": "Jazz Pharmaceuticals",
"synonym": []
},
{
"id": "100011396",
"uri": "http://dx.doi.org/10.13039/100011396",
"name": "Irish College of General Practitioners",
"synonym": []
},
{
"id": "100012734",
"uri": "http://dx.doi.org/10.13039/100012734",
"name": "Department for Culture, Heritage and the Gaeltacht, Ireland",
"synonym": []
},
{
"id": "100012754",
"uri": "http://dx.doi.org/10.13039/100012754",
"name": "Horizon Pharma",
"synonym": []
},
{
"id": "100012891",
"uri": "http://dx.doi.org/10.13039/100012891",
"name": "Medical Research Charities Group",
"synonym": []
},
{
"id": "100012919",
"uri": "http://dx.doi.org/10.13039/100012919",
"name": "Epilepsy Ireland",
"synonym": []
},
{
"id": "100012920",
"uri": "http://dx.doi.org/10.13039/100012920",
"name": "GLEN",
"synonym": []
},
{
"id": "100012921",
"uri": "http://dx.doi.org/10.13039/100012921",
"name": "Royal College of Surgeons in Ireland",
"synonym": []
},
{
"id": "100013029",
"uri": "http://dx.doi.org/10.13039/100013029",
"name": "Iris O'Brien Foundation",
"synonym": []
},
{
"id": "100013206",
"uri": "http://dx.doi.org/10.13039/100013206",
"name": "Food Institutional Research Measure",
"synonym": []
},
{
"id": "100013381",
"uri": "http://dx.doi.org/10.13039/100013381",
"name": "Irish Phytochemical Food Network",
"synonym": []
},
{
"id": "100013433",
"uri": "http://dx.doi.org/10.13039/100013433",
"name": "Transport Infrastructure Ireland",
"synonym": []
},
{
"id": "100013461",
"uri": "http://dx.doi.org/10.13039/100013461",
"name": "Arts and Disability Ireland",
"synonym": []
},
{
"id": "100013548",
"uri": "http://dx.doi.org/10.13039/100013548",
"name": "Filmbase",
"synonym": []
},
{
"id": "100013917",
"uri": "http://dx.doi.org/10.13039/100013917",
"name": "Society for Musicology in Ireland",
"synonym": []
},
{
"id": "100014251",
"uri": "http://dx.doi.org/10.13039/100014251",
"name": "Humanities in the European Research Area",
"synonym": []
},
{
"id": "100014364",
"uri": "http://dx.doi.org/10.13039/100014364",
"name": "National Children's Research Centre",
"synonym": []
},
{
"id": "100014384",
"uri": "http://dx.doi.org/10.13039/100014384",
"name": "Amarin Corporation",
"synonym": []
},
{
"id": "100014902",
"uri": "http://dx.doi.org/10.13039/100014902",
"name": "Irish Association for Cancer Research",
"synonym": []
},
{
"id": "100015023",
"uri": "http://dx.doi.org/10.13039/100015023",
"name": "Ireland Funds",
"synonym": []
},
{
"id": "100015037",
"uri": "http://dx.doi.org/10.13039/100015037",
"name": "Simon Cumbers Media Fund",
"synonym": []
},
{
"id": "100015319",
"uri": "http://dx.doi.org/10.13039/100015319",
"name": "Sport Ireland Institute",
"synonym": []
},
{
"id": "100015320",
"uri": "http://dx.doi.org/10.13039/100015320",
"name": "Paralympics Ireland",
"synonym": []
},
{
"id": "100015442",
"uri": "http://dx.doi.org/10.13039/100015442",
"name": "Global Brain Health Institute",
"synonym": []
},
{
"id": "100015776",
"uri": "http://dx.doi.org/10.13039/100015776",
"name": "Health and Social Care Board",
"synonym": []
},
{
"id": "100015992",
"uri": "http://dx.doi.org/10.13039/100015992",
"name": "St. Luke's Institute of Cancer Research",
"synonym": []
},
{
"id": "100017897",
"uri": "http://dx.doi.org/10.13039/100017897",
"name": "Friedreich\u2019s Ataxia Research Alliance Ireland",
"synonym": []
},
{
"id": "100018064",
"uri": "http://dx.doi.org/10.13039/100018064",
"name": "Department of Tourism, Culture, Arts, Gaeltacht, Sport and Media",
"synonym": []
},
{
"id": "100018172",
"uri": "http://dx.doi.org/10.13039/100018172",
"name": "Department of the Environment, Climate and Communications",
"synonym": []
},
{
"id": "100018175",
"uri": "http://dx.doi.org/10.13039/100018175",
"name": "Dairy Processing Technology Centre",
"synonym": []
},
{
"id": "100018270",
"uri": "http://dx.doi.org/10.13039/100018270",
"name": "Health Service Executive",
"synonym": []
},
{
"id": "100018529",
"uri": "http://dx.doi.org/10.13039/100018529",
"name": "Alkermes",
"synonym": []
},
{
"id": "100018542",
"uri": "http://dx.doi.org/10.13039/100018542",
"name": "Irish Endocrine Society",
"synonym": []
},
{
"id": "100018754",
"uri": "http://dx.doi.org/10.13039/100018754",
"name": "An Roinn Sl\u00e1inte",
"synonym": []
},
{
"id": "100018998",
"uri": "http://dx.doi.org/10.13039/100018998",
"name": "Irish Research eLibrary",
"synonym": []
},
{
"id": "100019428",
"uri": "http://dx.doi.org/10.13039/100019428",
"name": "Nabriva Therapeutics",
"synonym": []
},
{
"id": "100019637",
"uri": "http://dx.doi.org/10.13039/100019637",
"name": "Horizon Therapeutics",
"synonym": []
},
{
"id": "100020174",
"uri": "http://dx.doi.org/10.13039/100020174",
"name": "Health Research Charities Ireland",
"synonym": []
},
{
"id": "100020202",
"uri": "http://dx.doi.org/10.13039/100020202",
"name": "UCD Foundation",
"synonym": []
},
{
"id": "100020233",
"uri": "http://dx.doi.org/10.13039/100020233",
"name": "Ireland Canada University Foundation",
"synonym": []
},
{
"id": "100022943",
"uri": "http://dx.doi.org/10.13039/100022943",
"name": "National Cancer Registry Ireland",
"synonym": []
},
{
"id": "501100001581",
"uri": "http://dx.doi.org/10.13039/501100001581",
"name": "Arts Council of Ireland",
"synonym": []
},
{
"id": "501100001582",
"uri": "http://dx.doi.org/10.13039/501100001582",
"name": "Centre for Ageing Research and Development in Ireland",
"synonym": []
},
{
"id": "501100001583",
"uri": "http://dx.doi.org/10.13039/501100001583",
"name": "Cystinosis Foundation Ireland",
"synonym": []
},
{
"id": "501100001584",
"uri": "http://dx.doi.org/10.13039/501100001584",
"name": "Department of Agriculture, Food and the Marine, Ireland",
"synonym": []
},
{
"id": "501100001586",
"uri": "http://dx.doi.org/10.13039/501100001586",
"name": "Department of Education and Skills, Ireland",
"synonym": []
},
{
"id": "501100001587",
"uri": "http://dx.doi.org/10.13039/501100001587",
"name": "Economic and Social Research Institute",
"synonym": []
},
{
"id": "501100001588",
"uri": "http://dx.doi.org/10.13039/501100001588",
"name": "Enterprise Ireland",
"synonym": []
},
{
"id": "501100001589",
"uri": "http://dx.doi.org/10.13039/501100001589",
"name": "Environmental Protection Agency",
"synonym": []
},
{
"id": "501100001591",
"uri": "http://dx.doi.org/10.13039/501100001591",
"name": "Heritage Council",
"synonym": []
},
{
"id": "501100001592",
"uri": "http://dx.doi.org/10.13039/501100001592",
"name": "Higher Education Authority",
"synonym": []
},
{
"id": "501100001593",
"uri": "http://dx.doi.org/10.13039/501100001593",
"name": "Irish Cancer Society",
"synonym": []
},
{
"id": "501100001594",
"uri": "http://dx.doi.org/10.13039/501100001594",
"name": "Irish Heart Foundation",
"synonym": []
},
{
"id": "501100001595",
"uri": "http://dx.doi.org/10.13039/501100001595",
"name": "Irish Hospice Foundation",
"synonym": []
},
{
"id": "501100001596",
"uri": "http://dx.doi.org/10.13039/501100001596",
"name": "Irish Research Council for Science, Engineering and Technology",
"synonym": []
},
{
"id": "501100001597",
"uri": "http://dx.doi.org/10.13039/501100001597",
"name": "Irish Research Council for the Humanities and Social Sciences",
"synonym": []
},
{
"id": "501100001598",
"uri": "http://dx.doi.org/10.13039/501100001598",
"name": "Mental Health Commission",
"synonym": []
},
{
"id": "501100001600",
"uri": "http://dx.doi.org/10.13039/501100001600",
"name": "Research and Education Foundation, Sligo General Hospital",
"synonym": []
},
{
"id": "501100001601",
"uri": "http://dx.doi.org/10.13039/501100001601",
"name": "Royal Irish Academy",
"synonym": []
},
{
"id": "501100001603",
"uri": "http://dx.doi.org/10.13039/501100001603",
"name": "Sustainable Energy Authority of Ireland",
"synonym": []
},
{
"id": "501100001604",
"uri": "http://dx.doi.org/10.13039/501100001604",
"name": "Teagasc",
"synonym": []
},
{
"id": "501100001627",
"uri": "http://dx.doi.org/10.13039/501100001627",
"name": "Marine Institute",
"synonym": []
},
{
"id": "501100001628",
"uri": "http://dx.doi.org/10.13039/501100001628",
"name": "Central Remedial Clinic",
"synonym": []
},
{
"id": "501100001629",
"uri": "http://dx.doi.org/10.13039/501100001629",
"name": "Royal Dublin Society",
"synonym": []
},
{
"id": "501100001630",
"uri": "http://dx.doi.org/10.13039/501100001630",
"name": "Dublin Institute for Advanced Studies",
"synonym": []
},
{
"id": "501100001631",
"uri": "http://dx.doi.org/10.13039/501100001631",
"name": "University College Dublin",
"synonym": []
},
{
"id": "501100001633",
"uri": "http://dx.doi.org/10.13039/501100001633",
"name": "National University of Ireland, Maynooth",
"synonym": []
},
{
"id": "501100001634",
"uri": "http://dx.doi.org/10.13039/501100001634",
"name": "University of Galway",
"synonym": []
},
{
"id": "501100001635",
"uri": "http://dx.doi.org/10.13039/501100001635",
"name": "University of Limerick",
"synonym": []
},
{
"id": "501100001636",
"uri": "http://dx.doi.org/10.13039/501100001636",
"name": "University College Cork",
"synonym": []
},
{
"id": "501100001637",
"uri": "http://dx.doi.org/10.13039/501100001637",
"name": "Trinity College Dublin",
"synonym": []
},
{
"id": "501100001638",
"uri": "http://dx.doi.org/10.13039/501100001638",
"name": "Dublin City University",
"synonym": []
},
{
"id": "501100002081",
"uri": "http://dx.doi.org/10.13039/501100002081",
"name": "Irish Research Council",
"synonym": []
},
{
"id": "501100002736",
"uri": "http://dx.doi.org/10.13039/501100002736",
"name": "Covidien",
"synonym": []
},
{
"id": "501100002755",
"uri": "http://dx.doi.org/10.13039/501100002755",
"name": "Brennan and Company",
"synonym": []
},
{
"id": "501100002919",
"uri": "http://dx.doi.org/10.13039/501100002919",
"name": "Cork Institute of Technology",
"synonym": []
},
{
"id": "501100002959",
"uri": "http://dx.doi.org/10.13039/501100002959",
"name": "Dublin City Council",
"synonym": []
},
{
"id": "501100003036",
"uri": "http://dx.doi.org/10.13039/501100003036",
"name": "Perrigo Company Charitable Foundation",
"synonym": []
},
{
"id": "501100003037",
"uri": "http://dx.doi.org/10.13039/501100003037",
"name": "Elan",
"synonym": []
},
{
"id": "501100003496",
"uri": "http://dx.doi.org/10.13039/501100003496",
"name": "HeyStaks Technologies",
"synonym": []
},
{
"id": "501100003553",
"uri": "http://dx.doi.org/10.13039/501100003553",
"name": "Gaelic Athletic Association",
"synonym": []
},
{
"id": "501100003840",
"uri": "http://dx.doi.org/10.13039/501100003840",
"name": "Irish Institute of Clinical Neuroscience",
"synonym": []
},
{
"id": "501100003956",
"uri": "http://dx.doi.org/10.13039/501100003956",
"name": "Aspect Medical Systems",
"synonym": []
},
{
"id": "501100004162",
"uri": "http://dx.doi.org/10.13039/501100004162",
"name": "Meath Foundation",
"synonym": []
},
{
"id": "501100004210",
"uri": "http://dx.doi.org/10.13039/501100004210",
"name": "Our Lady's Children's Hospital, Crumlin",
"synonym": []
},
{
"id": "501100004321",
"uri": "http://dx.doi.org/10.13039/501100004321",
"name": "Shire",
"synonym": []
},
{
"id": "501100004981",
"uri": "http://dx.doi.org/10.13039/501100004981",
"name": "Athlone Institute of Technology",
"synonym": []
},
{
"id": "501100006518",
"uri": "http://dx.doi.org/10.13039/501100006518",
"name": "Department of Communications, Energy and Natural Resources, Ireland",
"synonym": []
},
{
"id": "501100006553",
"uri": "http://dx.doi.org/10.13039/501100006553",
"name": "Collaborative Centre for Applied Nanotechnology",
"synonym": []
},
{
"id": "501100006759",
"uri": "http://dx.doi.org/10.13039/501100006759",
"name": "CLARITY Centre for Sensor Web Technologies",
"synonym": []
},
{
"id": "501100009246",
"uri": "http://dx.doi.org/10.13039/501100009246",
"name": "Technological University Dublin",
"synonym": []
},
{
"id": "501100009269",
"uri": "http://dx.doi.org/10.13039/501100009269",
"name": "Programme of Competitive Forestry Research for Development",
"synonym": []
},
{
"id": "501100009315",
"uri": "http://dx.doi.org/10.13039/501100009315",
"name": "Cystinosis Ireland",
"synonym": []
},
{
"id": "501100010808",
"uri": "http://dx.doi.org/10.13039/501100010808",
"name": "Geological Survey of Ireland",
"synonym": []
},
{
"id": "501100011030",
"uri": "http://dx.doi.org/10.13039/501100011030",
"name": "Alimentary Glycoscience Research Cluster",
"synonym": []
},
{
"id": "501100011031",
"uri": "http://dx.doi.org/10.13039/501100011031",
"name": "Alimentary Health",
"synonym": []
},
{
"id": "501100011103",
"uri": "http://dx.doi.org/10.13039/501100011103",
"name": "Rann\u00eds",
"synonym": []
},
{
"id": "501100012354",
"uri": "http://dx.doi.org/10.13039/501100012354",
"name": "Inland Fisheries Ireland",
"synonym": []
},
{
"id": "501100014384",
"uri": "http://dx.doi.org/10.13039/501100014384",
"name": "X-Bolt Orthopaedics",
"synonym": []
},
{
"id": "501100014710",
"uri": "http://dx.doi.org/10.13039/501100014710",
"name": "PrecisionBiotics Group",
"synonym": []
},
{
"id": "501100014827",
"uri": "http://dx.doi.org/10.13039/501100014827",
"name": "Dormant Accounts Fund",
"synonym": []
},
{
"id": "501100016041",
"uri": "http://dx.doi.org/10.13039/501100016041",
"name": "St Vincents Anaesthesia Foundation",
"synonym": []
},
{
"id": "501100017501",
"uri": "http://dx.doi.org/10.13039/501100017501",
"name": "FotoNation",
"synonym": []
},
{
"id": "501100018641",
"uri": "http://dx.doi.org/10.13039/501100018641",
"name": "Dairy Research Ireland",
"synonym": []
},
{
"id": "501100018839",
"uri": "http://dx.doi.org/10.13039/501100018839",
"name": "Irish Centre for High-End Computing",
"synonym": []
},
{
"id": "501100019905",
"uri": "http://dx.doi.org/10.13039/501100019905",
"name": "Galway University Foundation",
"synonym": []
},
{
"id": "501100020036",
"uri": "http://dx.doi.org/10.13039/501100020036",
"name": "Dystonia Ireland",
"synonym": []
},
{
"id": "501100020221",
"uri": "http://dx.doi.org/10.13039/501100020221",
"name": "Irish Motor Neurone Disease Association",
"synonym": []
},
{
"id": "501100020270",
"uri": "http://dx.doi.org/10.13039/501100020270",
"name": "Advanced Materials and Bioengineering Research",
"synonym": []
},
{
"id": "501100020403",
"uri": "http://dx.doi.org/10.13039/501100020403",
"name": "Irish Composites Centre",
"synonym": []
},
{
"id": "501100020425",
"uri": "http://dx.doi.org/10.13039/501100020425",
"name": "Irish Thoracic Society",
"synonym": []
},
{
"id": "501100021102",
"uri": "http://dx.doi.org/10.13039/501100021102",
"name": "Waterford Institute of Technology",
"synonym": []
},
{
"id": "501100021110",
"uri": "http://dx.doi.org/10.13039/501100021110",
"name": "Irish MPS Society",
"synonym": []
},
{
"id": "501100021525",
"uri": "http://dx.doi.org/10.13039/501100021525",
"name": "Insight SFI Research Centre for Data Analytics",
"synonym": []
},
{
"id": "501100021694",
"uri": "http://dx.doi.org/10.13039/501100021694",
"name": "Elan Pharma International",
"synonym": []
},
{
"id": "501100021838",
"uri": "http://dx.doi.org/10.13039/501100021838",
"name": "Royal College of Physicians of Ireland",
"synonym": []
},
{
"id": "501100022542",
"uri": "http://dx.doi.org/10.13039/501100022542",
"name": "Breakthrough Cancer Research",
"synonym": []
},
{
"id": "501100022610",
"uri": "http://dx.doi.org/10.13039/501100022610",
"name": "Breast Cancer Ireland",
"synonym": []
},
{
"id": "501100022728",
"uri": "http://dx.doi.org/10.13039/501100022728",
"name": "Munster Technological University",
"synonym": []
},
{
"id": "501100022729",
"uri": "http://dx.doi.org/10.13039/501100022729",
"name": "Institute of Technology, Tralee",
"synonym": []
},
{
"id": "501100023273",
"uri": "http://dx.doi.org/10.13039/501100023273",
"name": "HRB Clinical Research Facility Galway",
"synonym": []
},
{
"id": "501100023378",
"uri": "http://dx.doi.org/10.13039/501100023378",
"name": "Lauritzson Foundation",
"synonym": []
},
{
"id": "501100023551",
"uri": "http://dx.doi.org/10.13039/501100023551",
"name": "Cystic Fibrosis Ireland",
"synonym": []
},
{
"id": "501100023970",
"uri": "http://dx.doi.org/10.13039/501100023970",
"name": "Tyndall National Institute",
"synonym": []
},
{
"id": "501100024094",
"uri": "http://dx.doi.org/10.13039/501100024094",
"name": "Raidi\u00f3 Teilif\u00eds \u00c9ireann",
"synonym": []
},
{
"id": "501100024242",
"uri": "http://dx.doi.org/10.13039/501100024242",
"name": "Synthesis and Solid State Pharmaceutical Centre",
"synonym": []
},
{
"id": "501100024313",
"uri": "http://dx.doi.org/10.13039/501100024313",
"name": "Irish Rugby Football Union",
"synonym": []
},
{
"id": "100007490",
"uri": "http://dx.doi.org/10.13039/100007490",
"name": "Bausch and Lomb Ireland",
"synonym": []
},
{
"id": "100007819",
"uri": "http://dx.doi.org/10.13039/100007819",
"name": "Allergan",
"synonym": []
},
{
"id": "100010547",
"uri": "http://dx.doi.org/10.13039/100010547",
"name": "Irish Youth Justice Service",
"synonym": []
},
{
"id": "100012733",
"uri": "http://dx.doi.org/10.13039/100012733",
"name": "National Parks and Wildlife Service",
"synonym": []
},
{
"id": "100015278",
"uri": "http://dx.doi.org/10.13039/100015278",
"name": "Pfizer Healthcare Ireland",
"synonym": []
},
{
"id": "100017144",
"uri": "http://dx.doi.org/10.13039/100017144",
"name": "Shell E and P Ireland",
"synonym": []
},
{
"id": "100022895",
"uri": "http://dx.doi.org/10.13039/100022895",
"name": "Health Research Institute, University of Limerick",
"synonym": []
},
{
"id": "501100001599",
"uri": "http://dx.doi.org/10.13039/501100001599",
"name": "National Council for Forest Research and Development",
"synonym": []
},
{
"id": "501100006554",
"uri": "http://dx.doi.org/10.13039/501100006554",
"name": "IDA Ireland",
"synonym": []
},
{
"id": "501100011626",
"uri": "http://dx.doi.org/10.13039/501100011626",
"name": "Energy Policy Research Centre, Economic and Social Research Institute",
"synonym": []
},
{
"id": "501100014531",
"uri": "http://dx.doi.org/10.13039/501100014531",
"name": "Physical Education and Sport Sciences Department, University of Limerick",
"synonym": []
},
{
"id": "501100014745",
"uri": "http://dx.doi.org/10.13039/501100014745",
"name": "APC Microbiome Institute",
"synonym": []
},
{
"id": "501100014826",
"uri": "http://dx.doi.org/10.13039/501100014826",
"name": "ADAPT - Centre for Digital Content Technology",
"synonym": []
},
{
"id": "501100020570",
"uri": "http://dx.doi.org/10.13039/501100020570",
"name": "College of Medicine, Nursing and Health Sciences, National University of Ireland, Galway",
"synonym": []
},
{
"id": "501100020871",
"uri": "http://dx.doi.org/10.13039/501100020871",
"name": "Bernal Institute, University of Limerick",
"synonym": []
},
{
"id": "501100023852",
"uri": "http://dx.doi.org/10.13039/501100023852",
"name": "Moore Institute for Research in the Humanities and Social Studies, University of Galway",
"synonym": []
}
]

26
dhp-workflows/dhp-doiboost/src/main/resources/eu/dnetlib/dhp/doiboost/preprocess/oozie_app/workflow.xml
View File

@ -133,32 +133,6 @@
<arg>--targetPath</arg><arg>${inputPathMAG}/dataset</arg>
<arg>--master</arg><arg>yarn-cluster</arg>
</spark>
<ok to="PreProcessORCID"/>
<error to="Kill"/>
</action>
<!-- ORCID SECTION -->
<action name="PreProcessORCID">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>Convert ORCID to Dataset</name>
<class>eu.dnetlib.doiboost.orcid.SparkPreprocessORCID</class>
<jar>dhp-doiboost-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.sql.shuffle.partitions=3840
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${inputPathOrcid}</arg>
<arg>--workingPath</arg><arg>${workingPathOrcid}</arg>
<arg>--master</arg><arg>yarn-cluster</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>

35
dhp-workflows/dhp-doiboost/src/main/resources/eu/dnetlib/dhp/doiboost/process/oozie_app/workflow.xml
View File

@ -59,10 +59,10 @@
</property>
<!-- ORCID Parameters -->
<property>
<name>workingPathOrcid</name>
<description>the ORCID working path</description>
</property>
<!-- <property>-->
<!-- <name>workingPathOrcid</name>-->
<!-- <description>the ORCID working path</description>-->
<!-- </property>-->
</parameters>
@ -84,7 +84,6 @@
<case to="End">${wf:conf('resumeFrom') eq 'Skip'}</case>
<case to="ProcessMAG">${wf:conf('resumeFrom') eq 'PreprocessMag'}</case>
<case to="ProcessUW">${wf:conf('resumeFrom') eq 'PreprocessUW'}</case>
<case to="ProcessORCID">${wf:conf('resumeFrom') eq 'ProcessORCID'}</case>
<case to="CreateDOIBoost">${wf:conf('resumeFrom') eq 'CreateDOIBoost'}</case>
<case to="GenerateActionSet">${wf:conf('resumeFrom') eq 'GenerateActionSet'}</case>
<default to="ConvertCrossrefToOAF"/>
@ -170,32 +169,6 @@
<arg>--targetPath</arg><arg>${workingPath}/uwPublication</arg>
<arg>--master</arg><arg>yarn-cluster</arg>
</spark>
<ok to="ProcessORCID"/>
<error to="Kill"/>
</action>
<!-- ORCID SECTION -->
<action name="ProcessORCID">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>Convert ORCID to Dataset</name>
<class>eu.dnetlib.doiboost.orcid.SparkConvertORCIDToOAF</class>
<jar>dhp-doiboost-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.sql.shuffle.partitions=3840
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--workingPath</arg><arg>${workingPathOrcid}</arg>
<arg>--targetPath</arg><arg>${workingPath}/orcidPublication</arg>
<arg>--master</arg><arg>yarn-cluster</arg>
</spark>
<ok to="CreateDOIBoost"/>
<error to="Kill"/>
</action>

16
dhp-workflows/dhp-doiboost/src/main/scala/eu/dnetlib/doiboost/SparkGenerateDoiBoost.scala
View File

@ -66,7 +66,7 @@ object SparkGenerateDoiBoost {
Encoders.tuple(Encoders.STRING, mapEncoderPub)
implicit val mapEncoderRel: Encoder[Relation] = Encoders.kryo[Relation]
logger.info("Phase 2) Join Crossref with UnpayWall")
logger.info("Phase 1) Join Crossref with UnpayWall")
val crossrefPublication: Dataset[(String, Publication)] =
spark.read.load(s"$workingDirPath/crossrefPublication").as[Publication].map(p => (p.getId, p))
@ -91,20 +91,10 @@ object SparkGenerateDoiBoost {
.write
.mode(SaveMode.Overwrite)
.save(s"$workingDirPath/firstJoin")
logger.info("Phase 3) Join Result with ORCID")
val fj: Dataset[(String, Publication)] =
spark.read.load(s"$workingDirPath/firstJoin").as[Publication].map(p => (p.getId, p))
val orcidPublication: Dataset[(String, Publication)] =
spark.read.load(s"$workingDirPath/orcidPublication").as[Publication].map(p => (p.getId, p))
fj.joinWith(orcidPublication, fj("_1").equalTo(orcidPublication("_1")), "left")
.map(applyMerge)
.write
.mode(SaveMode.Overwrite)
.save(s"$workingDirPath/secondJoin")
logger.info("Phase 4) Join Result with MAG")
logger.info("Phase 2) Join Result with MAG")
val sj: Dataset[(String, Publication)] =
spark.read.load(s"$workingDirPath/secondJoin").as[Publication].map(p => (p.getId, p))
spark.read.load(s"$workingDirPath/firstJoin").as[Publication].map(p => (p.getId, p))
val magPublication: Dataset[(String, Publication)] =
spark.read.load(s"$workingDirPath/magPublication").as[Publication].map(p => (p.getId, p))

Some files were not shown because too many files have changed in this diff Show More