1
0
Fork 0

Compare commits

..

2 Commits

Author SHA1 Message Date
Serafeim Chatzopoulos 842b309922 Add test class for ingesting DBLP data 2024-03-21 13:22:48 +02:00
Serafeim Chatzopoulos b6e4d58817 Add workflow for loading DBLP data 2024-03-19 18:11:36 +02:00
409 changed files with 10567 additions and 130713 deletions

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

@ -10,7 +10,6 @@ import org.apache.commons.lang3.StringUtils;
import com.wcohen.ss.JaroWinkler;
import eu.dnetlib.dhp.schema.oaf.Author;
import eu.dnetlib.dhp.schema.oaf.Qualifier;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
import eu.dnetlib.pace.model.Person;
import scala.Tuple2;
@ -146,21 +145,110 @@ public class AuthorMerger {
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 = Optional
.ofNullable(pid)
.map(
p -> Optional
.ofNullable(p.getQualifier())
.map(Qualifier::getClassid)
.map(String::toLowerCase)
.orElse(""))
.orElse("");
return Optional
.ofNullable(pid)
.map(StructuredProperty::getValue)
.map(v -> String.join("|", v, classId))
.orElse("");
final String classid = pid.getQualifier().getClassid() != null ? pid.getQualifier().getClassid().toLowerCase()
: "";
return (pid.getQualifier() != null ? classid : "")
+ (pid.getValue() != null ? pid.getValue().toLowerCase() : "");
}
public static int countAuthorsPids(List<Author> authors) {

View File

@ -14,7 +14,7 @@ import java.util.stream.Collectors;
import org.apache.commons.io.IOUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.api.java.function.MapGroupsFunction;
import org.apache.spark.api.java.function.ReduceFunction;
import org.apache.spark.sql.*;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
@ -26,7 +26,7 @@ import eu.dnetlib.dhp.schema.common.EntityType;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.OafEntity;
import eu.dnetlib.dhp.schema.oaf.utils.GraphCleaningFunctions;
import eu.dnetlib.dhp.schema.oaf.utils.MergeUtils;
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;
@ -135,10 +135,10 @@ public class GroupEntitiesSparkJob {
.applyCoarVocabularies(entity, vocs),
OAFENTITY_KRYO_ENC)
.groupByKey((MapFunction<OafEntity, String>) OafEntity::getId, Encoders.STRING())
.mapGroups((MapGroupsFunction<String, OafEntity, OafEntity>) MergeUtils::mergeById, OAFENTITY_KRYO_ENC)
.reduceGroups((ReduceFunction<OafEntity>) OafMapperUtils::mergeEntities)
.map(
(MapFunction<OafEntity, Tuple2<String, OafEntity>>) t -> new Tuple2<>(
t.getClass().getName(), t),
(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)

View File

@ -1,76 +0,0 @@
package eu.dnetlib.dhp.schema.oaf.utils;
import java.util.HashSet;
import java.util.Objects;
import java.util.Optional;
import java.util.Set;
import org.apache.commons.lang3.StringUtils;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
public class CleaningFunctions {
public static final String DOI_PREFIX_REGEX = "(^10\\.|\\/10\\.)";
public static final String DOI_PREFIX = "10.";
public static final Set<String> PID_BLACKLIST = new HashSet<>();
static {
PID_BLACKLIST.add("none");
PID_BLACKLIST.add("na");
}
public CleaningFunctions() {
}
/**
* Utility method that filter PID values on a per-type basis.
* @param s the PID whose value will be checked.
* @return false if the pid matches the filter criteria, true otherwise.
*/
public static boolean pidFilter(StructuredProperty s) {
final String pidValue = s.getValue();
if (Objects.isNull(s.getQualifier()) ||
StringUtils.isBlank(pidValue) ||
StringUtils.isBlank(pidValue.replaceAll("(?:\\n|\\r|\\t|\\s)", ""))) {
return false;
}
if (CleaningFunctions.PID_BLACKLIST.contains(pidValue)) {
return false;
}
return !PidBlacklistProvider.getBlacklist(s.getQualifier().getClassid()).contains(pidValue);
}
/**
* Utility method that normalises PID values on a per-type basis.
* @param pid the PID whose value will be normalised.
* @return the PID containing the normalised value.
*/
public static StructuredProperty normalizePidValue(StructuredProperty pid) {
pid
.setValue(
normalizePidValue(
pid.getQualifier().getClassid(),
pid.getValue()));
return pid;
}
public static String normalizePidValue(String pidType, String pidValue) {
String value = Optional
.ofNullable(pidValue)
.map(String::trim)
.orElseThrow(() -> new IllegalArgumentException("PID value cannot be empty"));
switch (pidType) {
// TODO add cleaning for more PID types as needed
case "doi":
return value.toLowerCase().replaceFirst(DOI_PREFIX_REGEX, DOI_PREFIX);
}
return value;
}
}

View File

@ -1,8 +1,6 @@
package eu.dnetlib.dhp.schema.oaf.utils;
import org.apache.commons.lang3.StringUtils;
public class DoiCleaningRule {
public static String clean(final String doi) {
@ -13,26 +11,4 @@ public class DoiCleaningRule {
.replaceFirst(CleaningFunctions.DOI_PREFIX_REGEX, CleaningFunctions.DOI_PREFIX);
}
public static String normalizeDoi(final String input) {
if (input == null)
return null;
final String replaced = input
.replaceAll("\\n|\\r|\\t|\\s", "")
.toLowerCase()
.replaceFirst(CleaningFunctions.DOI_PREFIX_REGEX, CleaningFunctions.DOI_PREFIX);
if (StringUtils.isEmpty(replaced))
return null;
if (!replaced.contains("10."))
return null;
final String ret = replaced.substring(replaced.indexOf("10."));
if (!ret.startsWith(CleaningFunctions.DOI_PREFIX))
return null;
return ret;
}
}

View File

@ -92,8 +92,6 @@ public class GraphCleaningFunctions extends CleaningFunctions {
INVALID_AUTHOR_NAMES.add("null anonymous");
INVALID_AUTHOR_NAMES.add("unbekannt");
INVALID_AUTHOR_NAMES.add("unknown");
INVALID_AUTHOR_NAMES.add("autor, Sin");
INVALID_AUTHOR_NAMES.add("Desconocido / Inconnu,");
INVALID_URL_HOSTS.add("creativecommons.org");
INVALID_URL_HOSTS.add("www.academia.edu");
@ -119,7 +117,7 @@ public class GraphCleaningFunctions extends CleaningFunctions {
.getContext()
.stream()
.filter(c -> !StringUtils.startsWith(c.getId().toLowerCase(), contextId))
.collect(Collectors.toCollection(ArrayList::new)));
.collect(Collectors.toList()));
}
return (T) res;
} else {
@ -508,8 +506,6 @@ public class GraphCleaningFunctions extends CleaningFunctions {
.filter(Objects::nonNull)
.filter(sp -> StringUtils.isNotBlank(sp.getValue()))
.map(GraphCleaningFunctions::cleanValue)
.sorted((s1, s2) -> s2.getValue().length() - s1.getValue().length())
.limit(ModelHardLimits.MAX_ABSTRACTS)
.collect(Collectors.toList()));
}
if (Objects.isNull(r.getResourcetype()) || StringUtils.isBlank(r.getResourcetype().getClassid())) {
@ -1003,41 +999,4 @@ public class GraphCleaningFunctions extends CleaningFunctions {
.orElse(null);
}
/**
* Implements bad and ugly things that we should get rid of ASAP.
*
* @param value
* @return
* @param <T>
*/
public static <T extends Oaf> T dedicatedUglyHacks(T value) {
if (value instanceof OafEntity) {
if (value instanceof Result) {
final Result r = (Result) value;
// Fix for AMS Acta
Optional
.ofNullable(r.getInstance())
.map(
instance -> instance
.stream()
.filter(
i -> Optional
.ofNullable(i.getHostedby())
.map(KeyValue::getKey)
.map(dsId -> dsId.equals("10|re3data_____::4cc76bed7ce2fb95fd8e7a2dfde16016"))
.orElse(false)))
.ifPresent(instance -> instance.forEach(i -> {
if (Optional
.ofNullable(i.getPid())
.map(pid -> pid.stream().noneMatch(p -> p.getValue().startsWith("10.6092/unibo/amsacta")))
.orElse(false)) {
i.setHostedby(UNKNOWN_REPOSITORY);
}
}));
}
}
return value;
}
}

View File

@ -1,294 +0,0 @@
package eu.dnetlib.dhp.schema.oaf.utils;
import static com.google.common.base.Preconditions.checkArgument;
import static eu.dnetlib.dhp.schema.common.ModelConstants.*;
import java.io.Serializable;
import java.nio.charset.StandardCharsets;
import java.security.MessageDigest;
import java.util.*;
import java.util.function.Function;
import java.util.stream.Collectors;
import java.util.stream.Stream;
import org.apache.commons.codec.binary.Hex;
import org.apache.commons.lang3.StringUtils;
import com.google.common.collect.HashBiMap;
import com.google.common.collect.Maps;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.*;
/**
* Factory class for OpenAIRE identifiers in the Graph
*/
public class IdentifierFactory implements Serializable {
public static final String ID_SEPARATOR = "::";
public static final String ID_PREFIX_SEPARATOR = "|";
public static final int ID_PREFIX_LEN = 12;
/**
* Declares the associations PID_TYPE -> [DATASOURCE ID, NAME] considered authoritative for that PID_TYPE.
* The id of the record (source_::id) will be rewritten as pidType_::id)
*/
public static final Map<PidType, HashBiMap<String, String>> PID_AUTHORITY = Maps.newHashMap();
static {
PID_AUTHORITY.put(PidType.doi, HashBiMap.create());
PID_AUTHORITY.get(PidType.doi).put(CROSSREF_ID, "Crossref");
PID_AUTHORITY.get(PidType.doi).put(DATACITE_ID, "Datacite");
PID_AUTHORITY.get(PidType.doi).put(ZENODO_OD_ID, "ZENODO");
PID_AUTHORITY.get(PidType.doi).put(ZENODO_R3_ID, "Zenodo");
PID_AUTHORITY.put(PidType.pmc, HashBiMap.create());
PID_AUTHORITY.get(PidType.pmc).put(EUROPE_PUBMED_CENTRAL_ID, "Europe PubMed Central");
PID_AUTHORITY.get(PidType.pmc).put(PUBMED_CENTRAL_ID, "PubMed Central");
PID_AUTHORITY.put(PidType.pmid, HashBiMap.create());
PID_AUTHORITY.get(PidType.pmid).put(EUROPE_PUBMED_CENTRAL_ID, "Europe PubMed Central");
PID_AUTHORITY.get(PidType.pmid).put(PUBMED_CENTRAL_ID, "PubMed Central");
PID_AUTHORITY.put(PidType.arXiv, HashBiMap.create());
PID_AUTHORITY.get(PidType.arXiv).put(ARXIV_ID, "arXiv.org e-Print Archive");
PID_AUTHORITY.put(PidType.w3id, HashBiMap.create());
PID_AUTHORITY.get(PidType.w3id).put(ROHUB_ID, "ROHub");
}
/**
* Declares the associations PID_TYPE -> [DATASOURCE ID, PID SUBSTRING] considered as delegated authority for that
* PID_TYPE. Example, Zenodo is delegated to forge DOIs that contain the 'zenodo' word.
*
* If a record with the same id (same pid) comes from 2 data sources, the one coming from a delegated source wins. E.g. Zenodo records win over those from Datacite.
* See also https://code-repo.d4science.org/D-Net/dnet-hadoop/pulls/187 and the class dhp-common/src/main/java/eu/dnetlib/dhp/schema/oaf/utils/OafMapperUtils.java
*/
public static final Map<PidType, Map<String, String>> DELEGATED_PID_AUTHORITY = Maps.newHashMap();
static {
DELEGATED_PID_AUTHORITY.put(PidType.doi, new HashMap<>());
DELEGATED_PID_AUTHORITY.get(PidType.doi).put(ZENODO_OD_ID, "zenodo");
DELEGATED_PID_AUTHORITY.get(PidType.doi).put(ZENODO_R3_ID, "zenodo");
DELEGATED_PID_AUTHORITY.put(PidType.w3id, new HashMap<>());
DELEGATED_PID_AUTHORITY.get(PidType.w3id).put(ROHUB_ID, "ro-id");
}
/**
* Declares the associations PID_TYPE -> [DATASOURCE ID, NAME] whose records are considered enrichment for the graph.
* Their OpenAIRE ID is built from the declared PID type. Are merged with their corresponding record, identified by
* the same OpenAIRE id.
*/
public static final Map<PidType, HashBiMap<String, String>> ENRICHMENT_PROVIDER = Maps.newHashMap();
static {
ENRICHMENT_PROVIDER.put(PidType.doi, HashBiMap.create());
ENRICHMENT_PROVIDER.get(PidType.doi).put(OPEN_APC_ID, OPEN_APC_NAME);
}
public static Set<String> delegatedAuthorityDatasourceIds() {
return DELEGATED_PID_AUTHORITY
.values()
.stream()
.flatMap(m -> m.keySet().stream())
.collect(Collectors.toCollection(HashSet::new));
}
public static List<StructuredProperty> getPids(List<StructuredProperty> pid, KeyValue collectedFrom) {
return pidFromInstance(pid, collectedFrom, true).distinct().collect(Collectors.toList());
}
public static <T extends Result> String createDOIBoostIdentifier(T entity) {
if (entity == null)
return null;
StructuredProperty pid = null;
if (entity.getPid() != null) {
pid = entity
.getPid()
.stream()
.filter(Objects::nonNull)
.filter(s -> s.getQualifier() != null && "doi".equalsIgnoreCase(s.getQualifier().getClassid()))
.filter(CleaningFunctions::pidFilter)
.findAny()
.orElse(null);
} else {
if (entity.getInstance() != null) {
pid = entity
.getInstance()
.stream()
.filter(i -> i.getPid() != null)
.flatMap(i -> i.getPid().stream())
.filter(CleaningFunctions::pidFilter)
.findAny()
.orElse(null);
}
}
if (pid != null)
return idFromPid(entity, pid, true);
return null;
}
/**
* Creates an identifier from the most relevant PID (if available) provided by a known PID authority in the given
* entity T. Returns entity.id when none of the PIDs meet the selection criteria is available.
*
* @param entity the entity providing PIDs and a default ID.
* @param <T> the specific entity type. Currently Organization and Result subclasses are supported.
* @param md5 indicates whether should hash the PID value or not.
* @return an identifier from the most relevant PID, entity.id otherwise
*/
public static <T extends OafEntity> String createIdentifier(T entity, boolean md5) {
checkArgument(StringUtils.isNoneBlank(entity.getId()), "missing entity identifier");
final Map<String, Set<StructuredProperty>> pids = extractPids(entity);
return pids
.values()
.stream()
.flatMap(Set::stream)
.min(new PidComparator<>(entity))
.map(
min -> Optional
.ofNullable(pids.get(min.getQualifier().getClassid()))
.map(
p -> p
.stream()
.sorted(new PidValueComparator())
.findFirst()
.map(s -> idFromPid(entity, s, md5))
.orElseGet(entity::getId))
.orElseGet(entity::getId))
.orElseGet(entity::getId);
}
private static <T extends OafEntity> Map<String, Set<StructuredProperty>> extractPids(T entity) {
if (entity instanceof Result) {
return Optional
.ofNullable(((Result) entity).getInstance())
.map(IdentifierFactory::mapPids)
.orElse(new HashMap<>());
} else {
return entity
.getPid()
.stream()
.map(CleaningFunctions::normalizePidValue)
.filter(CleaningFunctions::pidFilter)
.collect(
Collectors
.groupingBy(
p -> p.getQualifier().getClassid(),
Collectors.mapping(p -> p, Collectors.toCollection(HashSet::new))));
}
}
private static Map<String, Set<StructuredProperty>> mapPids(List<Instance> instance) {
return instance
.stream()
.map(i -> pidFromInstance(i.getPid(), i.getCollectedfrom(), false))
.flatMap(Function.identity())
.collect(
Collectors
.groupingBy(
p -> p.getQualifier().getClassid(),
Collectors.mapping(p -> p, Collectors.toCollection(HashSet::new))));
}
private static Stream<StructuredProperty> pidFromInstance(List<StructuredProperty> pid, KeyValue collectedFrom,
boolean mapHandles) {
return Optional
.ofNullable(pid)
.map(
pp -> pp
.stream()
// filter away PIDs provided by a DS that is not considered an authority for the
// given PID Type
.filter(p -> shouldFilterPidByCriteria(collectedFrom, p, mapHandles))
.map(CleaningFunctions::normalizePidValue)
.filter(p -> isNotFromDelegatedAuthority(collectedFrom, p))
.filter(CleaningFunctions::pidFilter))
.orElse(Stream.empty());
}
private static boolean shouldFilterPidByCriteria(KeyValue collectedFrom, StructuredProperty p, boolean mapHandles) {
final PidType pType = PidType.tryValueOf(p.getQualifier().getClassid());
if (Objects.isNull(collectedFrom)) {
return false;
}
boolean isEnrich = Optional
.ofNullable(ENRICHMENT_PROVIDER.get(pType))
.map(
enrich -> enrich.containsKey(collectedFrom.getKey())
|| enrich.containsValue(collectedFrom.getValue()))
.orElse(false);
boolean isAuthority = Optional
.ofNullable(PID_AUTHORITY.get(pType))
.map(
authorities -> authorities.containsKey(collectedFrom.getKey())
|| authorities.containsValue(collectedFrom.getValue()))
.orElse(false);
return (mapHandles && pType.equals(PidType.handle)) || isEnrich || isAuthority;
}
private static boolean isNotFromDelegatedAuthority(KeyValue collectedFrom, StructuredProperty p) {
final PidType pType = PidType.tryValueOf(p.getQualifier().getClassid());
final Map<String, String> da = DELEGATED_PID_AUTHORITY.get(pType);
if (Objects.isNull(da)) {
return true;
}
if (!da.containsKey(collectedFrom.getKey())) {
return true;
}
return StringUtils.contains(p.getValue(), da.get(collectedFrom.getKey()));
}
/**
* @see {@link IdentifierFactory#createIdentifier(OafEntity, boolean)}
*/
public static <T extends OafEntity> String createIdentifier(T entity) {
return createIdentifier(entity, true);
}
private static <T extends OafEntity> String idFromPid(T entity, StructuredProperty s, boolean md5) {
return idFromPid(ModelSupport.getIdPrefix(entity.getClass()), s.getQualifier().getClassid(), s.getValue(), md5);
}
public static String idFromPid(String numericPrefix, String pidType, String pidValue, boolean md5) {
return new StringBuilder()
.append(numericPrefix)
.append(ID_PREFIX_SEPARATOR)
.append(createPrefix(pidType))
.append(ID_SEPARATOR)
.append(md5 ? md5(pidValue) : pidValue)
.toString();
}
// create the prefix (length = 12)
private static String createPrefix(String pidType) {
StringBuilder prefix = new StringBuilder(StringUtils.left(pidType, ID_PREFIX_LEN));
while (prefix.length() < ID_PREFIX_LEN) {
prefix.append("_");
}
return prefix.substring(0, ID_PREFIX_LEN);
}
public static String md5(final String s) {
try {
final MessageDigest md = MessageDigest.getInstance("MD5");
md.update(s.getBytes(StandardCharsets.UTF_8));
return new String(Hex.encodeHex(md.digest()));
} catch (final Exception e) {
return null;
}
}
}

View File

@ -1,78 +0,0 @@
package eu.dnetlib.dhp.schema.oaf.utils;
import java.util.Comparator;
import java.util.HashSet;
import java.util.Optional;
import java.util.stream.Collectors;
//
// Source code recreated from a .class file by IntelliJ IDEA
// (powered by FernFlower decompiler)
//
import eu.dnetlib.dhp.schema.common.EntityType;
import eu.dnetlib.dhp.schema.oaf.KeyValue;
import eu.dnetlib.dhp.schema.oaf.Oaf;
import eu.dnetlib.dhp.schema.oaf.OafEntity;
import eu.dnetlib.dhp.schema.oaf.Result;
public class MergeComparator implements Comparator<Oaf> {
public MergeComparator() {
}
public int compare(Oaf left, Oaf right) {
// nulls at the end
if (left == null && right == null) {
return 0;
} else if (left == null) {
return -1;
} else if (right == null) {
return 1;
}
// invisible
if (left.getDataInfo() != null && left.getDataInfo().getInvisible() == true) {
if (right.getDataInfo() != null && right.getDataInfo().getInvisible() == false) {
return -1;
}
}
// collectedfrom
HashSet<String> lCf = getCollectedFromIds(left);
HashSet<String> rCf = getCollectedFromIds(right);
if (lCf.contains("10|openaire____::081b82f96300b6a6e3d282bad31cb6e2")
&& !rCf.contains("10|openaire____::081b82f96300b6a6e3d282bad31cb6e2")) {
return -1;
} else if (!lCf.contains("10|openaire____::081b82f96300b6a6e3d282bad31cb6e2")
&& rCf.contains("10|openaire____::081b82f96300b6a6e3d282bad31cb6e2")) {
return 1;
}
SubEntityType lClass = SubEntityType.fromClass(left.getClass());
SubEntityType rClass = SubEntityType.fromClass(right.getClass());
return lClass.ordinal() - rClass.ordinal();
}
protected HashSet<String> getCollectedFromIds(Oaf left) {
return (HashSet) Optional.ofNullable(left.getCollectedfrom()).map((cf) -> {
return (HashSet) cf.stream().map(KeyValue::getKey).collect(Collectors.toCollection(HashSet::new));
}).orElse(new HashSet());
}
enum SubEntityType {
publication, dataset, software, otherresearchproduct, datasource, organization, project;
/**
* Resolves the EntityType, given the relative class name
*
* @param clazz the given class name
* @param <T> actual OafEntity subclass
* @return the EntityType associated to the given class
*/
public static <T extends Oaf> SubEntityType fromClass(Class<T> clazz) {
return valueOf(clazz.getSimpleName().toLowerCase());
}
}
}

View File

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

View File

@ -1,27 +0,0 @@
package eu.dnetlib.dhp.schema.oaf.utils;
public class ModelHardLimits {
private ModelHardLimits() {
}
public static final String LAYOUT = "index";
public static final String INTERPRETATION = "openaire";
public static final String SEPARATOR = "-";
public static final int MAX_EXTERNAL_ENTITIES = 50;
public static final int MAX_AUTHORS = 200;
public static final int MAX_AUTHOR_FULLNAME_LENGTH = 1000;
public static final int MAX_TITLE_LENGTH = 5000;
public static final int MAX_TITLES = 10;
public static final int MAX_ABSTRACTS = 10;
public static final int MAX_ABSTRACT_LENGTH = 150000;
public static final int MAX_RELATED_ABSTRACT_LENGTH = 500;
public static final int MAX_INSTANCES = 10;
public static String getCollectionName(String format) {
return format + SEPARATOR + LAYOUT + SEPARATOR + INTERPRETATION;
}
}

View File

@ -14,6 +14,7 @@ import java.util.stream.Collectors;
import org.apache.commons.lang3.StringUtils;
import eu.dnetlib.dhp.schema.common.AccessRightComparator;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.*;
public class OafMapperUtils {
@ -21,6 +22,65 @@ public class OafMapperUtils {
private OafMapperUtils() {
}
public static Oaf merge(final Oaf left, final Oaf right) {
if (ModelSupport.isSubClass(left, OafEntity.class)) {
return mergeEntities((OafEntity) left, (OafEntity) right);
} else if (ModelSupport.isSubClass(left, Relation.class)) {
((Relation) left).mergeFrom((Relation) right);
} else {
throw new IllegalArgumentException("invalid Oaf type:" + left.getClass().getCanonicalName());
}
return left;
}
public static OafEntity mergeEntities(OafEntity left, OafEntity right) {
if (ModelSupport.isSubClass(left, Result.class)) {
return mergeResults((Result) left, (Result) right);
} else if (ModelSupport.isSubClass(left, Datasource.class)) {
left.mergeFrom(right);
} else if (ModelSupport.isSubClass(left, Organization.class)) {
left.mergeFrom(right);
} else if (ModelSupport.isSubClass(left, Project.class)) {
left.mergeFrom(right);
} else {
throw new IllegalArgumentException("invalid OafEntity subtype:" + left.getClass().getCanonicalName());
}
return left;
}
public static Result mergeResults(Result left, Result right) {
final boolean leftFromDelegatedAuthority = isFromDelegatedAuthority(left);
final boolean rightFromDelegatedAuthority = isFromDelegatedAuthority(right);
if (leftFromDelegatedAuthority && !rightFromDelegatedAuthority) {
return left;
}
if (!leftFromDelegatedAuthority && rightFromDelegatedAuthority) {
return right;
}
if (new ResultTypeComparator().compare(left, right) < 0) {
left.mergeFrom(right);
return left;
} else {
right.mergeFrom(left);
return right;
}
}
private static boolean isFromDelegatedAuthority(Result r) {
return Optional
.ofNullable(r.getInstance())
.map(
instance -> instance
.stream()
.filter(i -> Objects.nonNull(i.getCollectedfrom()))
.map(i -> i.getCollectedfrom().getKey())
.anyMatch(cfId -> IdentifierFactory.delegatedAuthorityDatasourceIds().contains(cfId)))
.orElse(false);
}
public static KeyValue keyValue(final String k, final String v) {
final KeyValue kv = new KeyValue();
kv.setKey(k);

View File

@ -1,46 +0,0 @@
package eu.dnetlib.dhp.schema.oaf.utils;
import java.util.Comparator;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
public class OrganizationPidComparator implements Comparator<StructuredProperty> {
@Override
public int compare(StructuredProperty left, StructuredProperty right) {
if (left == null) {
return right == null ? 0 : -1;
} else if (right == null) {
return 1;
}
PidType lClass = PidType.tryValueOf(left.getQualifier().getClassid());
PidType rClass = PidType.tryValueOf(right.getQualifier().getClassid());
if (lClass.equals(rClass))
return 0;
if (lClass.equals(PidType.openorgs))
return -1;
if (rClass.equals(PidType.openorgs))
return 1;
if (lClass.equals(PidType.GRID))
return -1;
if (rClass.equals(PidType.GRID))
return 1;
if (lClass.equals(PidType.mag_id))
return -1;
if (rClass.equals(PidType.mag_id))
return 1;
if (lClass.equals(PidType.urn))
return -1;
if (rClass.equals(PidType.urn))
return 1;
return 0;
}
}

View File

@ -1,8 +0,0 @@
package eu.dnetlib.dhp.schema.oaf.utils;
import java.util.HashMap;
import java.util.HashSet;
public class PidBlacklist extends HashMap<String, HashSet<String>> {
}

View File

@ -1,40 +0,0 @@
package eu.dnetlib.dhp.schema.oaf.utils;
import java.io.IOException;
import java.util.HashSet;
import java.util.Optional;
import java.util.Set;
import org.apache.commons.io.IOUtils;
import com.fasterxml.jackson.databind.ObjectMapper;
public class PidBlacklistProvider {
private static final PidBlacklist blacklist;
static {
try {
String json = IOUtils.toString(IdentifierFactory.class.getResourceAsStream("pid_blacklist.json"));
blacklist = new ObjectMapper().readValue(json, PidBlacklist.class);
} catch (IOException e) {
throw new RuntimeException(e);
}
}
public static PidBlacklist getBlacklist() {
return blacklist;
}
public static Set<String> getBlacklist(String pidType) {
return Optional
.ofNullable(getBlacklist().get(pidType))
.orElse(new HashSet<>());
}
private PidBlacklistProvider() {
}
}

View File

@ -1,48 +0,0 @@
package eu.dnetlib.dhp.schema.oaf.utils;
import java.util.Comparator;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.OafEntity;
import eu.dnetlib.dhp.schema.oaf.Organization;
import eu.dnetlib.dhp.schema.oaf.Result;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
public class PidComparator<T extends OafEntity> implements Comparator<StructuredProperty> {
private final T entity;
public PidComparator(T entity) {
this.entity = entity;
}
@Override
public int compare(StructuredProperty left, StructuredProperty right) {
if (left == null && right == null)
return 0;
if (left == null)
return 1;
if (right == null)
return -1;
if (ModelSupport.isSubClass(entity, Result.class)) {
return compareResultPids(left, right);
}
if (ModelSupport.isSubClass(entity, Organization.class)) {
return compareOrganizationtPids(left, right);
}
// Else (but unlikely), lexicographical ordering will do.
return left.getQualifier().getClassid().compareTo(right.getQualifier().getClassid());
}
private int compareResultPids(StructuredProperty left, StructuredProperty right) {
return new ResultPidComparator().compare(left, right);
}
private int compareOrganizationtPids(StructuredProperty left, StructuredProperty right) {
return new OrganizationPidComparator().compare(left, right);
}
}

View File

@ -1,79 +0,0 @@
package eu.dnetlib.dhp.schema.oaf.utils;
import org.apache.commons.lang3.EnumUtils;
public enum PidType {
/**
* The DOI syntax shall be made up of a DOI prefix and a DOI suffix separated by a forward slash.
*
* There is no defined limit on the length of the DOI name, or of the DOI prefix or DOI suffix.
*
* The DOI name is case-insensitive and can incorporate any printable characters from the legal graphic characters
* of Unicode. Further constraints on character use (e.g. use of language-specific alphanumeric characters) can be
* defined for an application by the ISO 26324 Registration Authority.
*
*
* DOI prefix: The DOI prefix shall be composed of a directory indicator followed by a registrant code.
* These two components shall be separated by a full stop (period). The directory indicator shall be "10" and
* distinguishes the entire set of character strings (prefix and suffix) as digital object identifiers within the
* resolution system.
*
* Registrant code: The second element of the DOI prefix shall be the registrant code. The registrant code is a
* unique string assigned to a registrant.
*
* DOI suffix: The DOI suffix shall consist of a character string of any length chosen by the registrant.
* Each suffix shall be unique to the prefix element that precedes it. The unique suffix can be a sequential number,
* or it might incorporate an identifier generated from or based on another system used by the registrant
* (e.g. ISAN, ISBN, ISRC, ISSN, ISTC, ISNI; in such cases, a preferred construction for such a suffix can be
* specified, as in Example 1).
*
* Source: https://www.doi.org/doi_handbook/2_Numbering.html#2.2
*/
doi,
/**
* PubMed Unique Identifier (PMID)
*
* This field is a 1-to-8 digit accession number with no leading zeros. It is present on all records and is the
* accession number for managing and disseminating records. PMIDs are not reused after records are deleted.
*
* Beginning in February 2012 PMIDs include extensions following a decimal point to account for article versions
* (e.g., 21804956.2). All citations are considered version 1 until replaced. The extended PMID is not displayed
* on the MEDLINE format.
*
* View the citation in abstract format in PubMed to access additional versions when available (see the article in
* the Jan-Feb 2012 NLM Technical Bulletin).
*
* Source: https://www.nlm.nih.gov/bsd/mms/medlineelements.html#pmid
*/
pmid,
/**
* This field contains the unique identifier for the cited article in PubMed Central. The identifier begins with the
* prefix PMC.
*
* Source: https://www.nlm.nih.gov/bsd/mms/medlineelements.html#pmc
*/
pmc, handle, arXiv, nct, pdb, w3id,
// Organization
openorgs, ROR, GRID, PIC, ISNI, Wikidata, FundRef, corda, corda_h2020, mag_id, urn,
// Used by dedup
undefined, original;
public static boolean isValid(String type) {
return EnumUtils.isValidEnum(PidType.class, type);
}
public static PidType tryValueOf(String s) {
try {
return PidType.valueOf(s);
} catch (Exception e) {
return PidType.original;
}
}
}

View File

@ -1,33 +0,0 @@
package eu.dnetlib.dhp.schema.oaf.utils;
import java.util.Comparator;
import java.util.Optional;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
public class PidValueComparator implements Comparator<StructuredProperty> {
@Override
public int compare(StructuredProperty left, StructuredProperty right) {
if (left == null && right == null)
return 0;
if (left == null)
return 1;
if (right == null)
return -1;
StructuredProperty l = CleaningFunctions.normalizePidValue(left);
StructuredProperty r = CleaningFunctions.normalizePidValue(right);
return Optional
.ofNullable(l.getValue())
.map(
lv -> Optional
.ofNullable(r.getValue())
.map(rv -> lv.compareTo(rv))
.orElse(-1))
.orElse(1);
}
}

View File

@ -1,46 +0,0 @@
package eu.dnetlib.dhp.schema.oaf.utils;
import java.util.Comparator;
import eu.dnetlib.dhp.schema.oaf.Qualifier;
/**
* Comparator for sorting the values from the dnet:review_levels vocabulary, implements the following ordering
*
* peerReviewed (0001) > nonPeerReviewed (0002) > UNKNOWN (0000)
*/
public class RefereedComparator implements Comparator<Qualifier> {
@Override
public int compare(Qualifier left, Qualifier right) {
if (left == null || left.getClassid() == null) {
return (right == null || right.getClassid() == null) ? 0 : -1;
} else if (right == null || right.getClassid() == null) {
return 1;
}
String lClass = left.getClassid();
String rClass = right.getClassid();
if (lClass.equals(rClass))
return 0;
if ("0001".equals(lClass))
return -1;
if ("0001".equals(rClass))
return 1;
if ("0002".equals(lClass))
return -1;
if ("0002".equals(rClass))
return 1;
if ("0000".equals(lClass))
return -1;
if ("0000".equals(rClass))
return 1;
return 0;
}
}

View File

@ -1,56 +0,0 @@
package eu.dnetlib.dhp.schema.oaf.utils;
import java.util.Comparator;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
public class ResultPidComparator implements Comparator<StructuredProperty> {
@Override
public int compare(StructuredProperty left, StructuredProperty right) {
PidType lClass = PidType.tryValueOf(left.getQualifier().getClassid());
PidType rClass = PidType.tryValueOf(right.getQualifier().getClassid());
if (lClass.equals(rClass))
return 0;
if (lClass.equals(PidType.doi))
return -1;
if (rClass.equals(PidType.doi))
return 1;
if (lClass.equals(PidType.pmid))
return -1;
if (rClass.equals(PidType.pmid))
return 1;
if (lClass.equals(PidType.pmc))
return -1;
if (rClass.equals(PidType.pmc))
return 1;
if (lClass.equals(PidType.handle))
return -1;
if (rClass.equals(PidType.handle))
return 1;
if (lClass.equals(PidType.arXiv))
return -1;
if (rClass.equals(PidType.arXiv))
return 1;
if (lClass.equals(PidType.nct))
return -1;
if (rClass.equals(PidType.nct))
return 1;
if (lClass.equals(PidType.pdb))
return -1;
if (rClass.equals(PidType.pdb))
return 1;
return 0;
}
}

View File

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

View File

@ -1,8 +1,5 @@
package eu.dnetlib.dhp.application
import eu.dnetlib.dhp.common.Constants
import eu.dnetlib.dhp.utils.DHPUtils.writeHdfsFile
import scala.io.Source
/** This is the main Interface SparkApplication
@ -73,13 +70,4 @@ abstract class AbstractScalaApplication(
.getOrCreate()
}
def reportTotalSize(targetPath: String, outputBasePath: String): Unit = {
val total_items = spark.read.text(targetPath).count()
writeHdfsFile(
spark.sparkContext.hadoopConfiguration,
s"$total_items",
outputBasePath + Constants.MDSTORE_SIZE_PATH
)
}
}

View File

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

View File

@ -1,21 +0,0 @@
package eu.dnetlib.dhp.schema.oaf.utils;
import java.util.Set;
import org.junit.jupiter.api.Assertions;
import org.junit.jupiter.api.Test;
class BlackListProviderTest {
@Test
void blackListTest() {
Assertions.assertNotNull(PidBlacklistProvider.getBlacklist());
Assertions.assertNotNull(PidBlacklistProvider.getBlacklist().get("doi"));
Assertions.assertTrue(PidBlacklistProvider.getBlacklist().get("doi").size() > 0);
final Set<String> xxx = PidBlacklistProvider.getBlacklist("xxx");
Assertions.assertNotNull(xxx);
Assertions.assertEquals(0, xxx.size());
}
}

View File

@ -1,87 +0,0 @@
package eu.dnetlib.dhp.schema.oaf.utils;
import static org.junit.jupiter.api.Assertions.assertEquals;
import static org.junit.jupiter.api.Assertions.assertNotNull;
import java.io.IOException;
import org.apache.commons.io.IOUtils;
import org.junit.jupiter.api.Test;
import com.fasterxml.jackson.databind.DeserializationFeature;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.schema.oaf.Publication;
class IdentifierFactoryTest {
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper()
.configure(DeserializationFeature.FAIL_ON_UNKNOWN_PROPERTIES, false);
@Test
void testCreateIdentifierForPublication() throws IOException {
verifyIdentifier(
"publication_doi1.json", "50|doi_________::79dbc7a2a56dc1532659f9038843256e", true);
verifyIdentifier(
"publication_doi2.json", "50|doi_________::79dbc7a2a56dc1532659f9038843256e", true);
verifyIdentifier(
"publication_doi3.json", "50|pmc_________::94e4cb08c93f8733b48e2445d04002ac", true);
verifyIdentifier(
"publication_doi4.json", "50|od______2852::38861c44e6052a8d49f59a4c39ba5e66", true);
verifyIdentifier(
"publication_doi5.json", "50|doi_________::3bef95c0ca26dd55451fc8839ea69d27", true);
verifyIdentifier(
"publication_pmc1.json", "50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f", true);
verifyIdentifier(
"publication_pmc2.json", "50|pmc_________::94e4cb08c93f8733b48e2445d04002ac", true);
verifyIdentifier(
"publication_openapc.json", "50|doi_________::79dbc7a2a56dc1532659f9038843256e", true);
final String defaultID = "50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f";
verifyIdentifier("publication_3.json", defaultID, true);
verifyIdentifier("publication_4.json", defaultID, true);
verifyIdentifier("publication_5.json", defaultID, true);
}
@Test
void testCreateIdentifierForPublicationNoHash() throws IOException {
verifyIdentifier("publication_doi1.json", "50|doi_________::10.1016/j.cmet.2010.03.013", false);
verifyIdentifier("publication_doi2.json", "50|doi_________::10.1016/j.cmet.2010.03.013", false);
verifyIdentifier("publication_pmc1.json", "50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f", false);
verifyIdentifier(
"publication_urn1.json", "50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f", false);
final String defaultID = "50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f";
verifyIdentifier("publication_3.json", defaultID, false);
verifyIdentifier("publication_4.json", defaultID, false);
verifyIdentifier("publication_5.json", defaultID, false);
}
@Test
void testCreateIdentifierForROHub() throws IOException {
verifyIdentifier(
"orp-rohub.json", "50|w3id________::afc7592914ae190a50570db90f55f9c2", true);
}
protected void verifyIdentifier(String filename, String expectedID, boolean md5) throws IOException {
final String json = IOUtils.toString(getClass().getResourceAsStream(filename));
final Publication pub = OBJECT_MAPPER.readValue(json, Publication.class);
String id = IdentifierFactory.createIdentifier(pub, md5);
System.out.println(id);
assertNotNull(id);
assertEquals(expectedID, id);
}
}

View File

@ -1,130 +0,0 @@
package eu.dnetlib.dhp.schema.oaf.utils;
import static org.junit.jupiter.api.Assertions.*;
import static org.junit.jupiter.api.Assertions.assertEquals;
import java.io.IOException;
import java.lang.reflect.InvocationTargetException;
import java.util.HashSet;
import java.util.List;
import java.util.stream.Collectors;
import org.apache.commons.beanutils.BeanUtils;
import org.apache.commons.io.IOUtils;
import org.junit.jupiter.api.Test;
import com.fasterxml.jackson.databind.DeserializationFeature;
import com.fasterxml.jackson.databind.ObjectMapper;
import com.google.common.collect.Lists;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.*;
public class MergeUtilsTest {
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper()
.configure(DeserializationFeature.FAIL_ON_UNKNOWN_PROPERTIES, false);
@Test
void testMergePubs_new() throws IOException {
Publication pt = read("publication_test.json", Publication.class);
Publication p1 = read("publication_test.json", Publication.class);
assertEquals(1, pt.getCollectedfrom().size());
assertEquals(ModelConstants.CROSSREF_ID, pt.getCollectedfrom().get(0).getKey());
Instance i = new Instance();
i.setUrl(Lists.newArrayList("https://..."));
p1.getInstance().add(i);
Publication ptp1 = MergeUtils.mergePublication(pt, p1);
assertNotNull(ptp1.getInstance());
assertEquals(2, ptp1.getInstance().size());
}
@Test
void testMergePubs() throws IOException {
Publication p1 = read("publication_1.json", Publication.class);
Publication p2 = read("publication_2.json", Publication.class);
Dataset d1 = read("dataset_1.json", Dataset.class);
Dataset d2 = read("dataset_2.json", Dataset.class);
assertEquals(1, p1.getCollectedfrom().size());
assertEquals(ModelConstants.CROSSREF_ID, p1.getCollectedfrom().get(0).getKey());
assertEquals(1, d2.getCollectedfrom().size());
assertFalse(cfId(d2.getCollectedfrom()).contains(ModelConstants.CROSSREF_ID));
assertEquals(1, p2.getCollectedfrom().size());
assertFalse(cfId(p2.getCollectedfrom()).contains(ModelConstants.CROSSREF_ID));
assertEquals(1, d1.getCollectedfrom().size());
assertTrue(cfId(d1.getCollectedfrom()).contains(ModelConstants.CROSSREF_ID));
final Result p1d2 = MergeUtils.checkedMerge(p1, d2, true);
assertEquals(ModelConstants.PUBLICATION_RESULTTYPE_CLASSID, p1d2.getResulttype().getClassid());
assertTrue(p1d2 instanceof Publication);
assertEquals(p1.getId(), p1d2.getId());
}
@Test
void testMergePubs_1() throws IOException {
Publication p2 = read("publication_2.json", Publication.class);
Dataset d1 = read("dataset_1.json", Dataset.class);
final Result p2d1 = MergeUtils.checkedMerge(p2, d1, true);
assertEquals((ModelConstants.DATASET_RESULTTYPE_CLASSID), p2d1.getResulttype().getClassid());
assertTrue(p2d1 instanceof Dataset);
assertEquals(d1.getId(), p2d1.getId());
assertEquals(2, p2d1.getCollectedfrom().size());
}
@Test
void testMergePubs_2() throws IOException {
Publication p1 = read("publication_1.json", Publication.class);
Publication p2 = read("publication_2.json", Publication.class);
Result p1p2 = MergeUtils.checkedMerge(p1, p2, true);
assertTrue(p1p2 instanceof Publication);
assertEquals(p1.getId(), p1p2.getId());
assertEquals(2, p1p2.getCollectedfrom().size());
}
@Test
void testDelegatedAuthority_1() throws IOException {
Dataset d1 = read("dataset_2.json", Dataset.class);
Dataset d2 = read("dataset_delegated.json", Dataset.class);
assertEquals(1, d2.getCollectedfrom().size());
assertTrue(cfId(d2.getCollectedfrom()).contains(ModelConstants.ZENODO_OD_ID));
Result res = (Result) MergeUtils.merge(d1, d2, true);
assertEquals(d2, res);
}
@Test
void testDelegatedAuthority_2() throws IOException {
Dataset p1 = read("publication_1.json", Dataset.class);
Dataset d2 = read("dataset_delegated.json", Dataset.class);
assertEquals(1, d2.getCollectedfrom().size());
assertTrue(cfId(d2.getCollectedfrom()).contains(ModelConstants.ZENODO_OD_ID));
Result res = (Result) MergeUtils.merge(p1, d2, true);
assertEquals(d2, res);
}
protected HashSet<String> cfId(List<KeyValue> collectedfrom) {
return collectedfrom.stream().map(KeyValue::getKey).collect(Collectors.toCollection(HashSet::new));
}
protected <T extends Result> T read(String filename, Class<T> clazz) throws IOException {
final String json = IOUtils.toString(getClass().getResourceAsStream(filename));
return OBJECT_MAPPER.readValue(json, clazz);
}
}

View File

@ -149,7 +149,7 @@ class OafMapperUtilsTest {
void testDate() {
final String date = GraphCleaningFunctions.cleanDate("23-FEB-1998");
assertNotNull(date);
assertEquals("1998-02-23", date);
System.out.println(date);
}
@Test
@ -166,8 +166,8 @@ class OafMapperUtilsTest {
assertEquals(
ModelConstants.PUBLICATION_RESULTTYPE_CLASSID,
MergeUtils
.mergeResult(p1, d2)
OafMapperUtils
.mergeResults(p1, d2)
.getResulttype()
.getClassid());
@ -178,8 +178,8 @@ class OafMapperUtilsTest {
assertEquals(
ModelConstants.DATASET_RESULTTYPE_CLASSID,
((Result) MergeUtils
.merge(p2, d1))
OafMapperUtils
.mergeResults(p2, d1)
.getResulttype()
.getClassid());
}
@ -192,7 +192,7 @@ class OafMapperUtilsTest {
assertEquals(1, d2.getCollectedfrom().size());
assertTrue(cfId(d2.getCollectedfrom()).contains(ModelConstants.ZENODO_OD_ID));
Result res = MergeUtils.mergeResult(d1, d2);
Result res = OafMapperUtils.mergeResults(d1, d2);
assertEquals(d2, res);

View File

@ -1,9 +1,10 @@
package eu.dnetlib.dhp.enrich.orcid;
package eu.dnetlib.oa.merge;
import static org.junit.jupiter.api.Assertions.*;
import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.util.Collections;
import java.util.List;
import java.util.Objects;
@ -13,9 +14,10 @@ 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 ORCIDAuthorEnricherTest {
public class AuthorMergerTest {
@Test
public void testEnrcichAuthor() throws Exception {
@ -24,13 +26,12 @@ public class ORCIDAuthorEnricherTest {
BufferedReader pr = new BufferedReader(new InputStreamReader(
Objects
.requireNonNull(
ORCIDAuthorEnricherTest.class
.getResourceAsStream("/eu/dnetlib/dhp/enrich/orcid/authors_publication_sample.json"))));
AuthorMergerTest.class
.getResourceAsStream("/eu/dnetlib/dhp/oa/merge/authors_publication_sample.json"))));
BufferedReader or = new BufferedReader(new InputStreamReader(
Objects
.requireNonNull(
ORCIDAuthorEnricherTest.class
.getResourceAsStream("/eu/dnetlib/dhp/enrich/orcid/authors_orcid_sample.json"))));
AuthorMergerTest.class.getResourceAsStream("/eu/dnetlib/dhp/oa/merge/authors_orcid_sample.json"))));
TypeReference<List<Author>> aclass = new TypeReference<List<Author>>() {
};
@ -66,8 +67,7 @@ public class ORCIDAuthorEnricherTest {
long start = System.currentTimeMillis();
// final List<Author> enrichedList = AuthorMerger.enrichOrcid(publicationAuthors, orcidAuthors);
final List<Author> enrichedList = Collections.emptyList(); // SparkEnrichGraphWithOrcidAuthors.enrichOrcid(publicationAuthors,
// orcidAuthors);
final List<Author> enrichedList = AuthorMerger.enrichOrcid(publicationAuthors, orcidAuthors);
long enrichedAuthorWithPid = enrichedList
.stream()
@ -91,4 +91,24 @@ public class ORCIDAuthorEnricherTest {
}
}
@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);
}
}

View File

@ -1,12 +0,0 @@
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0000/ra.v2i3.114::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.91019644836e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.0"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"4.65008652949e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0000/ra.v2i3.114"}]}]}
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0001/(aj).v3i6.458::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.91019644836e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.0"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"4.01810569717e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0001/(aj).v3i6.458"}]}]}
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0001/1587::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.91019644836e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.0"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.39172290649e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0001/1587"}]}]}
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0001/462::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"6.33235333753e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.36"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.00285265116e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0001/462"}]}]}
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0001/731::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.91019644836e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.0"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"4.01810569717e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0001/731"}]}]}
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0001/ijllis.v9i4.2066.g2482::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.91019644836e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.0"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"8.48190886761e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0001/ijllis.v9i4.2066.g2482"}]}]}
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0118/alfahim.v3i1.140::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.91019644836e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.0"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"9.88840807598e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0118/alfahim.v3i1.140"}]}]}
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0166/fk2.stagefigshare.6442896.v3::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.91019644836e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.0"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"7.28336930301e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0166/fk2.stagefigshare.6442896.v3"}]}]}
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0301/jttb.v2i1.64::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.91019644836e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.0"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"7.28336930301e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0301/jttb.v2i1.64"}]}]}
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0809/seruni.v1i1.567::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.91019644836e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.0"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"2.62959564033e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0809/seruni.v1i1.567"}]}]}
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0809/seruni.v2i1.765::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"9.40178571921e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.0559872"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"3.67659957614e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0809/seruni.v2i1.765"}]}]}
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0901/jkip.v7i3.485::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.91019644836e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.0"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"6.26204125721e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0901/jkip.v7i3.485"}]}]}

File diff suppressed because one or more lines are too long

View File

@ -1 +0,0 @@
{"id":"50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f","pid":[{"qualifier":{"classid":"scp-number"},"value":"79953761260"}]}

View File

@ -1 +0,0 @@
{"id":"50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f","pid":[]}

View File

@ -1 +0,0 @@
{"id":"50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f"}

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

View File

@ -1,33 +0,0 @@
{
"id": "50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f",
"instance": [
{
"collectedfrom": {
"key": "10|openaire____::081b82f96300b6a6e3d282bad31cb6e2",
"value": "Crossref"
},
"pid": [
{
"qualifier": {"classid": "doi"},
"value": "10.1016/j.cmet.2010.03.013"
}
]
},
{
"pid": [
{
"qualifier": {"classid": "urn"},
"value": "urn:nbn:nl:ui:29-f3ed5f9e-edf6-457e-8848-61b58a4075e2"
},
{
"qualifier": {"classid": "scp-number"},
"value": "79953761260"
},
{
"qualifier": {"classid": "pmc"},
"value": "21459329"
}
]
}
]
}

View File

@ -1,37 +0,0 @@
{
"id": "50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f",
"instance": [
{
"collectedfrom": {
"key": "10|openaire____::081b82f96300b6a6e3d282bad31cb6e2",
"value": "Crossref"
},
"pid": [
{
"qualifier": {"classid": "doi"},
"value": "10.1016/j.cmet.2010.03.013"
}
]
},
{
"collectedfrom": {
"key": "10|opendoar____::8b6dd7db9af49e67306feb59a8bdc52c",
"value": "Europe PubMed Central"
},
"pid": [
{
"qualifier": {"classid": "urn"},
"value": "urn:nbn:nl:ui:29-f3ed5f9e-edf6-457e-8848-61b58a4075e2"
},
{
"qualifier": {"classid": "scp-number"},
"value": "79953761260"
},
{
"qualifier": {"classid": "pmc"},
"value": "21459329"
}
]
}
]
}

View File

@ -1,37 +0,0 @@
{
"id": "50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f",
"instance": [
{
"collectedfrom": {
"key": "10|opendoar____::358aee4cc897452c00244351e4d91f69",
"value": "Zenodo"
},
"pid": [
{
"qualifier": {"classid": "doi"},
"value": "10.1016/j.cmet.2010.03.013"
}
]
},
{
"collectedfrom": {
"key": "10|opendoar____::8b6dd7db9af49e67306feb59a8bdc52c",
"value": "Europe PubMed Central"
},
"pid": [
{
"qualifier": {"classid": "urn"},
"value": "urn:nbn:nl:ui:29-f3ed5f9e-edf6-457e-8848-61b58a4075e2"
},
{
"qualifier": {"classid": "scp-number"},
"value": "79953761260"
},
{
"qualifier": {"classid": "pmc"},
"value": "21459329"
}
]
}
]
}

View File

@ -1,37 +0,0 @@
{
"id": "50|od______2852::38861c44e6052a8d49f59a4c39ba5e66",
"instance": [
{
"collectedfrom": {
"key": "10|opendoar____::358aee4cc897452c00244351e4d91f69",
"value": "Zenodo"
},
"pid": [
{
"qualifier": {"classid": "doi"},
"value": "10.1016/j.cmet.2010.03.013"
},
{
"qualifier": {"classid": "handle"},
"value": "11012/83840"
}
]
},
{
"collectedfrom": {
"key": "10|opendoar____::2852",
"value": "Digital library of Brno University of Technology"
},
"pid": [
{
"qualifier": {"classid": "pmc"},
"value": "21459329"
},
{
"qualifier": {"classid": "handle"},
"value": "11012/83840"
}
]
}
]
}

View File

@ -1,37 +0,0 @@
{
"id": "50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f",
"instance": [
{
"collectedfrom": {
"key": "10|opendoar____::358aee4cc897452c00244351e4d91f69",
"value": "Zenodo"
},
"pid": [
{
"qualifier": {"classid": "doi"},
"value": "10.5281/zenodo.5121485"
}
]
},
{
"collectedfrom": {
"key": "10|opendoar____::8b6dd7db9af49e67306feb59a8bdc52c",
"value": "Europe PubMed Central"
},
"pid": [
{
"qualifier": {"classid": "urn"},
"value": "urn:nbn:nl:ui:29-f3ed5f9e-edf6-457e-8848-61b58a4075e2"
},
{
"qualifier": {"classid": "scp-number"},
"value": "79953761260"
},
{
"qualifier": {"classid": "pmc"},
"value": "21459329"
}
]
}
]
}

View File

@ -1,3 +0,0 @@
{"id":"50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f", "resulttype" : { "classid" : "publication" }, "pid":[{"qualifier":{"classid":"doi"},"value":"10.1016/j.cmet.2011.03.013"},{"qualifier":{"classid":"urn"},"value":"urn:nbn:nl:ui:29-f3ed5f9e-edf6-457e-8848-61b58a4075e2"},{"qualifier":{"classid":"scp-number"},"value":"79953761260"},{"qualifier":{"classid":"pmc"},"value":"21459329"}], "collectedfrom" : [ { "key" : "10|openaire____::081b82f96300b6a6e3d282bad31cb6e2", "value" : "Crossref"} ], "isGreen": null, "openAccessColor": "gold", "isInDiamondJournal": null, "publiclyFunded": null}
{"id":"50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1g", "resulttype" : { "classid" : "publication" }, "isGreen": true, "openAccessColor": "gold", "isInDiamondJournal": true, "publiclyFunded": false }
{"id":"50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1h", "resulttype" : { "classid" : "publication" }, "isGreen": false, "openAccessColor": null, "isInDiamondJournal": true, "publiclyFunded": false }

View File

@ -1,3 +0,0 @@
{"id":"50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f", "resulttype" : { "classid" : "publication" }, "pid":[{"qualifier":{"classid":"doi"},"value":"10.1016/j.cmet.2011.03.013"},{"qualifier":{"classid":"urn"},"value":"urn:nbn:nl:ui:29-f3ed5f9e-edf6-457e-8848-61b58a4075e2"},{"qualifier":{"classid":"scp-number"},"value":"79953761260"},{"qualifier":{"classid":"pmc"},"value":"21459329"}], "collectedfrom" : [ { "key" : "10|openaire____::081b82f96300b6a6e3d282bad31cb6e2", "value" : "Crossref"} ], "isGreen": null, "openAccessColor": "gold", "isInDiamondJournal": null, "publiclyFunded": null}
{"id":"50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1g", "resulttype" : { "classid" : "publication" }, "isGreen": true, "openAccessColor": "bronze", "isInDiamondJournal": true, "publiclyFunded": false }
{"id":"50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1h", "resulttype" : { "classid" : "publication" }, "isGreen": false, "openAccessColor": null, "isInDiamondJournal": true, "publiclyFunded": false }

View File

@ -1,31 +0,0 @@
{
"id": "50|openapc_____::000023f9cb6e3a247c764daec4273cbc",
"resuttype": {
"classid": "publication"
},
"instance": [
{
"collectedfrom": {
"key": "10|apc_________::e2b1600b229fc30663c8a1f662debddf",
"value": "OpenAPC Global Initiative"
},
"pid": [
{
"qualifier": {"classid": "doi"},
"value": "10.1016/j.cmet.2010.03.013"
},
{
"qualifier": {"classid": "pmc"},
"value": "21459329"
},
{
"qualifier": {"classid": "pmid"},
"value": "25811027"
}
],
"url":["https://doi.org/10.1155/2015/439379"]
}
]
}

View File

@ -1,17 +0,0 @@
{
"id": "50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f",
"pid": [
{
"qualifier": {"classid": "urn"},
"value": "urn:nbn:nl:ui:29-f3ed5f9e-edf6-457e-8848-61b58a4075e2"
},
{
"qualifier": {"classid": "scp-number"},
"value": "79953761260"
},
{
"qualifier": {"classid": "pmc"},
"value": "21459329"
}
]
}

View File

@ -1,21 +0,0 @@
{
"id":"50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f",
"instance": [
{
"collectedfrom": {
"key": "10|opendoar____::8b6dd7db9af49e67306feb59a8bdc52c",
"value": "Europe PubMed Central"
},
"pid": [
{
"qualifier": {"classid": "doi"},
"value": "10.1016/j.cmet.2010.03.013"
},
{
"qualifier":{"classid":"pmc"},
"value":"21459329"
}
]
}
]
}

View File

@ -1,428 +0,0 @@
{
"author": [
{
"affiliation": null,
"fullname": "Deymier, Ghislaine",
"name": "Ghislaine",
"pid": [],
"rank": 1,
"surname": "Deymier"
},
{
"affiliation": null,
"fullname": "Gaschet, Frédéric",
"name": "Frédéric",
"pid": [],
"rank": 2,
"surname": "Gaschet"
},
{
"affiliation": null,
"fullname": "Pouyanne, Guillaume",
"name": "Guillaume",
"pid": [],
"rank": 3,
"surname": "Pouyanne"
}
],
"bestaccessright": {
"classid": "OPEN",
"classname": "Open Access",
"schemeid": "dnet:access_modes",
"schemename": "dnet:access_modes"
},
"collectedfrom": [
{
"key" : "10|openaire____::081b82f96300b6a6e3d282bad31cb6e2",
"value" : "Crossref"
}
],
"context": [],
"contributor": [],
"country": [],
"coverage": [],
"dataInfo": {
"deletedbyinference": false,
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "sysimport:crosswalk:repository",
"classname": "Harvested",
"schemeid": "dnet:provenanceActions",
"schemename": "dnet:provenanceActions"
},
"trust": "0.9"
},
"dateofacceptance": {
"dataInfo": {
"deletedbyinference": false,
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "sysimport:crosswalk:repository",
"classname": "Harvested",
"schemeid": "dnet:provenanceActions",
"schemename": "dnet:provenanceActions"
},
"trust": "0.9"
},
"value": "2013-11-30"
},
"dateofcollection": "2024-02-28T00:22:13+0000",
"dateoftransformation": "2024-03-06T08:43:13.253Z",
"description": [
{
"dataInfo": {
"deletedbyinference": false,
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "sysimport:crosswalk:repository",
"classname": "Harvested",
"schemeid": "dnet:provenanceActions",
"schemename": "dnet:provenanceActions"
},
"trust": "0.9"
},
"value": "For analyzing the reciprocal interaction between urban sprawl and car use, research has first focused on the link between urban density and mobility. By looking for a reduction in energy consumption, cities have favoured a compact planning development. Then reflection has broadened from the simple density to the wider, multi-dimensional concept of urban form. This controversy has led to a renewal of analysis in term of the costs of urban growth, notably by comparing the costs of \"compact\" and \"sprawled\" development. The idea is to compare the mobility costs of different urban forms. However, most often because of a lack of data, such studies are scarce. This paper suggests an innovative method to compute mobility costs at an infra-urban scale : The Spatialized Travel Account (STA). It is based on the CERTU's travel account methodology at a metropolitan scale. It puts forward an accurate estimate of the mobility costs for each transport mode (individual and public) and for each type of payer (households, firms, local authorities...). In order to test the relationships between mobility costs and urban form, we link the computed costs to morphological characteristics of infra-urban zones, taking in account sociodemographic characteristics of households."
},
{
"dataInfo": {
"deletedbyinference": false,
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "sysimport:crosswalk:repository",
"classname": "Harvested",
"schemeid": "dnet:provenanceActions",
"schemename": "dnet:provenanceActions"
},
"trust": "0.9"
},
"value": "L'interaction réciproque entre étalement urbain et usage de l'automobile a conduit la recherche à se focaliser sur le lien entre les densités urbaines et la mobilité. En cherchant à réduire leur consommation d'énergie pour les transports, et donc leurs émissions de Gaz à Effet de Serre, les villes ont alors cherché à planifier la \" ville compacte \", privilégiant notamment la reconstruction de la ville sur elle-même et la densification. Par la suite, la réflexion s'est élargie de la simple densité à la notion de forme urbaine et à toutes ses dimensions. Cette controverse devait conduire à un renouveau des analyses en termes de coûts de la croissance urbaine : le débat reste vif, encore aujourd'hui, sur les coûts comparés de la ville étalée et de la ville compacte. Plus largement, il s'agit d'explorer les coûts des différentes formes urbaines en termes de mobilité. Malgré cela, généralement pour des raisons de disponibilité de données, les études sur le sujet restent extrêmement rares. Cet article propose un outil novateur pour mesurer les coûts de la mobilité à l'échelle intraurbaine : le Compte Déplacements Territorialisé (CDT). Il s'inspire de la méthode développée par le CERTU pour l'établissement des Comptes Déplacements Voyageurs à l'échelle métropolitaine. Le CDT propose, pour chacune des zones de l'agglomération, une estimation précise de l'ensemble des coûts liés aux déplacements de personnes, ventilés par mode de transport (individuels et collectifs) et par type de financeurs (ménages, entreprises, collectivités territoriales, etc.). Nous proposons une application de cette méthode à la controverse sur le lien entre forme urbaine et coûts de la mobilité. Les coûts sont reliés aux caractéristiques morphologiques des zones (en termes de densité et de diversité, notamment), en prenant soin de contrôler les facteurs socio-économiques qui influent traditionnellement sur les comportements de mobilité (taille du ménage, revenu, etc.)."
}
],
"eoscifguidelines": [],
"externalReference": [],
"extraInfo": [],
"format": [
{
"dataInfo": {
"deletedbyinference": false,
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "sysimport:crosswalk:repository",
"classname": "Harvested",
"schemeid": "dnet:provenanceActions",
"schemename": "dnet:provenanceActions"
},
"trust": "0.9"
},
"value": "application/pdf"
}
],
"fulltext": [],
"id": "50|06cdd3ff4700::4826ac62a11a957fe332e2c291dcfcca",
"instance": [
{
"accessright": {
"classid": "OPEN",
"classname": "Open Access",
"schemeid": "dnet:access_modes",
"schemename": "dnet:access_modes"
},
"alternateIdentifier": [
{
"dataInfo": {
"deletedbyinference": false,
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "sysimport:crosswalk:repository",
"classname": "Harvested",
"schemeid": "dnet:provenanceActions",
"schemename": "dnet:provenanceActions"
},
"trust": "0.9"
},
"qualifier": {
"classid": "doi",
"classname": "Digital Object Identifier",
"schemeid": "dnet:pid_types",
"schemename": "dnet:pid_types"
},
"value": "10.46298/cst.12132"
}
],
"collectedfrom": {
"key": "10|openaire____::6824b298c96ba906a3e6a70593affbf5",
"value": "Episciences"
},
"dateofacceptance": {
"dataInfo": {
"deletedbyinference": false,
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "sysimport:crosswalk:repository",
"classname": "Harvested",
"schemeid": "dnet:provenanceActions",
"schemename": "dnet:provenanceActions"
},
"trust": "0.9"
},
"value": "2013-11-30"
},
"hostedby": {
"key": "10|openaire____::6824b298c96ba906a3e6a70593affbf5",
"value": "Episciences"
},
"instanceTypeMapping": [
{
"originalType": "http://purl.org/coar/resource_type/c_6501",
"typeCode": "http://purl.org/coar/resource_type/c_6501",
"typeLabel": "journal article",
"vocabularyName": "openaire::coar_resource_types_3_1"
},
{
"originalType": "http://purl.org/coar/resource_type/c_6501",
"typeCode": "Article",
"typeLabel": "Article",
"vocabularyName": "openaire::user_resource_types"
}
],
"instancetype": {
"classid": "0001",
"classname": "Article",
"schemeid": "dnet:publication_resource",
"schemename": "dnet:publication_resource"
},
"license": {
"dataInfo": {
"deletedbyinference": false,
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "sysimport:crosswalk:repository",
"classname": "Harvested",
"schemeid": "dnet:provenanceActions",
"schemename": "dnet:provenanceActions"
},
"trust": "0.9"
},
"value": "CC BY NC SA"
},
"pid": [],
"refereed": {
"classid": "0002",
"classname": "nonPeerReviewed",
"schemeid": "dnet:review_levels",
"schemename": "dnet:review_levels"
},
"url": [
"https://doi.org/10.46298/cst.12132",
"https://cst.episciences.org/12132"
]
}
],
"language": {
"classid": "fra/fre",
"classname": "French",
"schemeid": "dnet:languages",
"schemename": "dnet:languages"
},
"lastupdatetimestamp": 1710636106633,
"metaResourceType": {
"classid": "Research Literature",
"classname": "Research Literature",
"schemeid": "openaire::meta_resource_types",
"schemename": "openaire::meta_resource_types"
},
"originalId": [
"oai:episciences.org:cst:12132",
"50|06cdd3ff4700::4826ac62a11a957fe332e2c291dcfcca"
],
"pid": [],
"publisher": {
"dataInfo": {
"deletedbyinference": false,
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "sysimport:crosswalk:repository",
"classname": "Harvested",
"schemeid": "dnet:provenanceActions",
"schemename": "dnet:provenanceActions"
},
"trust": "0.9"
},
"value": "episciences.org"
},
"relevantdate": [
{
"dataInfo": {
"deletedbyinference": false,
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "sysimport:crosswalk:repository",
"classname": "Harvested",
"schemeid": "dnet:provenanceActions",
"schemename": "dnet:provenanceActions"
},
"trust": "0.9"
},
"qualifier": {
"classid": "Accepted",
"classname": "Accepted",
"schemeid": "dnet:dataCite_date",
"schemename": "dnet:dataCite_date"
},
"value": "2024-02-11"
},
{
"dataInfo": {
"deletedbyinference": false,
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "sysimport:crosswalk:repository",
"classname": "Harvested",
"schemeid": "dnet:provenanceActions",
"schemename": "dnet:provenanceActions"
},
"trust": "0.9"
},
"qualifier": {
"classid": "issued",
"classname": "issued",
"schemeid": "dnet:dataCite_date",
"schemename": "dnet:dataCite_date"
},
"value": "2013-11-30"
},
{
"dataInfo": {
"deletedbyinference": false,
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "sysimport:crosswalk:repository",
"classname": "Harvested",
"schemeid": "dnet:provenanceActions",
"schemename": "dnet:provenanceActions"
},
"trust": "0.9"
},
"qualifier": {
"classid": "available",
"classname": "available",
"schemeid": "dnet:dataCite_date",
"schemename": "dnet:dataCite_date"
},
"value": "2013-11-30"
}
],
"resourcetype": {
"classid": "journal article",
"classname": "journal article",
"schemeid": "dnet:dataCite_resource",
"schemename": "dnet:dataCite_resource"
},
"resulttype": {
"classid": "publication",
"classname": "publication",
"schemeid": "dnet:result_typologies",
"schemename": "dnet:result_typologies"
},
"source": [],
"subject": [
{
"dataInfo": {
"deletedbyinference": false,
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "sysimport:crosswalk:repository",
"classname": "Harvested",
"schemeid": "dnet:provenanceActions",
"schemename": "dnet:provenanceActions"
},
"trust": "0.9"
},
"qualifier": {
"classid": "keyword",
"classname": "keyword",
"schemeid": "dnet:subject_classification_typologies",
"schemename": "dnet:subject_classification_typologies"
},
"value": "JEL: H - Public Economics/H.H7 - State and Local Government • Intergovernmental Relations/H.H7.H72 - State and Local Budget and Expenditures"
},
{
"dataInfo": {
"deletedbyinference": false,
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "sysimport:crosswalk:repository",
"classname": "Harvested",
"schemeid": "dnet:provenanceActions",
"schemename": "dnet:provenanceActions"
},
"trust": "0.9"
},
"qualifier": {
"classid": "keyword",
"classname": "keyword",
"schemeid": "dnet:subject_classification_typologies",
"schemename": "dnet:subject_classification_typologies"
},
"value": "Local public finance"
},
{
"dataInfo": {
"deletedbyinference": false,
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "sysimport:crosswalk:repository",
"classname": "Harvested",
"schemeid": "dnet:provenanceActions",
"schemename": "dnet:provenanceActions"
},
"trust": "0.9"
},
"qualifier": {
"classid": "keyword",
"classname": "keyword",
"schemeid": "dnet:subject_classification_typologies",
"schemename": "dnet:subject_classification_typologies"
},
"value": "JEL: R - Urban, Rural, Regional, Real Estate, and Transportation Economics/R.R5 - Regional Government Analysis/R.R5.R51 - Finance in Urban and Rural Economies"
}
],
"title": [
{
"dataInfo": {
"deletedbyinference": false,
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "sysimport:crosswalk:repository",
"classname": "Harvested",
"schemeid": "dnet:provenanceActions",
"schemename": "dnet:provenanceActions"
},
"trust": "0.9"
},
"qualifier": {
"classid": "main title",
"classname": "main title",
"schemeid": "dnet:dataCite_title",
"schemename": "dnet:dataCite_title"
},
"value": "Urban form and the costs of daily mobility. The spatialized travel account tool and its application to the Bordeaux metropolitan area"
}
]
}

View File

@ -1,23 +0,0 @@
{
"id": "50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f",
"pid": [
{
"qualifier": {
"classid": "urn"
},
"value": "urn:nbn:nl:ui:29-f3ed5f9e-edf6-457e-8848-61b58a4075e2"
},
{
"qualifier": {
"classid": "scp-number"
},
"value": "79953761260"
},
{
"qualifier": {
"classid": "pmcid"
},
"value": "21459329"
}
]
}

File diff suppressed because one or more lines are too long

View File

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

View File

@ -20,7 +20,7 @@ public class WordsStatsSuffixPrefixChain extends AbstractClusteringFunction {
return suffixPrefixChain(s, param("mod"));
}
static Collection<String> suffixPrefixChain(String s, int mod) {
private Collection<String> suffixPrefixChain(String s, int mod) {
// create the list of words from the string (remove short words)
List<String> wordsList = Arrays
@ -38,7 +38,7 @@ public class WordsStatsSuffixPrefixChain extends AbstractClusteringFunction {
}
static private Collection<String> doSuffixPrefixChain(List<String> wordsList, String prefix) {
private Collection<String> doSuffixPrefixChain(List<String> wordsList, String prefix) {
Set<String> set = Sets.newLinkedHashSet();
switch (wordsList.size()) {
@ -80,16 +80,12 @@ public class WordsStatsSuffixPrefixChain extends AbstractClusteringFunction {
}
private static String suffix(String s, int len) {
private String suffix(String s, int len) {
return s.substring(s.length() - len);
}
private static String prefix(String s, int len) {
private String prefix(String s, int len) {
return s.substring(0, len);
}
static public void main(String[] args) {
String title = "MY LIFE AS A BOSON: THE STORY OF \"THE HIGGS\"".toLowerCase();
System.out.println(suffixPrefixChain(title, 10));
}
}

View File

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

View File

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

View File

@ -1,10 +1,8 @@
package eu.dnetlib.pace.tree;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;
import java.util.function.BiFunction;
import java.util.stream.Collectors;
import com.wcohen.ss.AbstractStringDistance;
@ -13,7 +11,6 @@ import eu.dnetlib.pace.config.Config;
import eu.dnetlib.pace.model.Person;
import eu.dnetlib.pace.tree.support.AbstractListComparator;
import eu.dnetlib.pace.tree.support.ComparatorClass;
import eu.dnetlib.pace.util.AuthorMatchers;
@ComparatorClass("authorsMatch")
public class AuthorsMatch extends AbstractListComparator {
@ -44,36 +41,24 @@ public class AuthorsMatch extends AbstractListComparator {
}
@Override
public double compare(final List<String> left, final List<String> right, final Config conf) {
if (left.isEmpty() || right.isEmpty())
public double compare(final List<String> a, final List<String> b, final Config conf) {
if (a.isEmpty() || b.isEmpty())
return -1;
if (left.size() > SIZE_THRESHOLD || right.size() > SIZE_THRESHOLD)
if (a.size() > SIZE_THRESHOLD || b.size() > SIZE_THRESHOLD)
return 1.0;
Double threshold = getDoubleParam("threshold");
int maxMiss = Integer.MAX_VALUE;
List<Person> bList = b.stream().map(author -> new Person(author, false)).collect(Collectors.toList());
if (threshold != null && threshold >= 0.0 && threshold <= 1.0 && left.size() == right.size()) {
maxMiss = (int) Math.floor((1 - threshold) * Math.max(left.size(), right.size()));
Double threshold = getDoubleParam("threshold");
if (threshold != null && threshold >= 0.0 && threshold <= 1.0 && a.size() == b.size()) {
maxMiss = (int) Math.floor((1 - threshold) * Math.max(a.size(), b.size()));
}
int common = 0;
List<String> a = new ArrayList<>(left);
List<String> b = new ArrayList<>(right);
common += AuthorMatchers
.removeMatches(a, b, (BiFunction<String, String, Object>) AuthorMatchers::matchEqualsIgnoreCase)
.size() / 2;
common += AuthorMatchers
.removeMatches(a, b, (BiFunction<String, String, Object>) AuthorMatchers::matchOrderedTokenAndAbbreviations)
.size() / 2;
List<Person> bList = b.stream().map(author -> new Person(author, false)).collect(Collectors.toList());
// compare each element of List1 with each element of List2
int alreadyMatched = common;
for (int i = 0; i < a.size(); i++) {
Person p1 = new Person(a.get(i), false);
@ -138,13 +123,13 @@ public class AuthorsMatch extends AbstractListComparator {
}
}
if (i - common - alreadyMatched > maxMiss) {
if (i - common > maxMiss) {
return 0.0;
}
}
// normalization factor to compute the score
int normFactor = left.size() == right.size() ? left.size() : (left.size() + right.size() - common);
int normFactor = a.size() == b.size() ? a.size() : (a.size() + b.size() - common);
if (TYPE.equals("percentage")) {
return (double) common / normFactor;
@ -175,4 +160,5 @@ public class AuthorsMatch extends AbstractListComparator {
public String normalization(String s) {
return normalize(utf8(cleanup(s)));
}
}

View File

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

View File

@ -1,112 +0,0 @@
package eu.dnetlib.pace.util
import java.util.Locale
import java.util.regex.Pattern
import scala.util.control.Breaks.{break, breakable}
object AuthorMatchers {
val SPLIT_REGEX = Pattern.compile("[\\s,\\.]+")
val WORD_DIFF = 2
def matchEqualsIgnoreCase(a1: String, a2: String): Boolean = {
if (a1 == null || a2 == null)
false
else
a1 == a2 || a1.toLowerCase(Locale.ROOT).equals(a2.toLowerCase(Locale.ROOT))
}
def matchOtherNames(fullName: String, otherNames: Seq[String]): Boolean = {
if (otherNames != null) {
otherNames.exists(matchEqualsIgnoreCase(fullName, _))
} else {
false
}
}
def matchOrderedTokenAndAbbreviations(a1: String, a2: String): Boolean = {
val p1: Array[String] = SPLIT_REGEX.split(a1.trim.toLowerCase(Locale.ROOT)).filter(_.nonEmpty).sorted
val p2: Array[String] = SPLIT_REGEX.split(a2.trim.toLowerCase(Locale.ROOT)).filter(_.nonEmpty).sorted
if (p1.length < 2 || p2.length < 2) return false
if (Math.abs(p1.length - p2.length) > WORD_DIFF) return false // use alternative comparison algo
var p1Idx: Int = 0
var p2Idx: Int = 0
var shortMatches: Int = 0
var longMatches: Int = 0
while (p1Idx < p1.length && p2Idx < p2.length) {
val e1: String = p1(p1Idx)
val c1: Char = e1.charAt(0)
val e2: String = p2(p2Idx)
val c2: Char = e2.charAt(0)
if (c1 < c2) p1Idx += 1
else if (c1 > c2) p2Idx += 1
else {
var res: Boolean = false
if (e1.length != 1 && e2.length != 1) {
res = e1 == e2
if (res)
longMatches += 1
} else {
res = true
shortMatches += 1
}
if (res) {
p1Idx += 1
p2Idx += 1
} else {
val diff: Int = e1.compareTo(e2)
if (diff < 0) p1Idx += 1
else if (diff > 0) p2Idx += 1
}
}
}
longMatches > 0 && (shortMatches + longMatches) == Math.min(p1.length, p2.length)
}
def removeMatches(
graph_authors: java.util.List[String],
orcid_authors: java.util.List[String],
matchingFunc: java.util.function.BiFunction[String,String,Boolean]
) : java.util.List[String] = {
removeMatches(graph_authors, orcid_authors, (a, b) => matchingFunc(a,b))
}
def removeMatches(
graph_authors: java.util.List[String],
orcid_authors: java.util.List[String],
matchingFunc: (String, String) => Boolean
) : java.util.List[String] = {
val matched = new java.util.ArrayList[String]()
if (graph_authors != null && !graph_authors.isEmpty) {
val ait = graph_authors.iterator
while (ait.hasNext) {
val author = ait.next()
val oit = orcid_authors.iterator
breakable {
while (oit.hasNext) {
val orcid = oit.next()
if (matchingFunc(author, orcid)) {
ait.remove()
oit.remove()
matched.add(author)
matched.add(orcid)
break()
}
}
}
}
}
matched
}
}

View File

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

File diff suppressed because it is too large Load Diff

View File

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

View File

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

View File

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

View File

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

View File

@ -7,7 +7,8 @@ import java.util.function.BiFunction;
import eu.dnetlib.dhp.common.FunctionalInterfaceSupport.SerializableSupplier;
import eu.dnetlib.dhp.schema.oaf.Oaf;
import eu.dnetlib.dhp.schema.oaf.utils.MergeUtils;
import eu.dnetlib.dhp.schema.oaf.OafEntity;
import eu.dnetlib.dhp.schema.oaf.Relation;
/** OAF model merging support. */
public class MergeAndGet {
@ -45,7 +46,20 @@ public class MergeAndGet {
}
private static <G extends Oaf, A extends Oaf> G mergeFromAndGet(G x, A y) {
return (G) MergeUtils.merge(x, y);
if (isSubClass(x, Relation.class) && isSubClass(y, Relation.class)) {
((Relation) x).mergeFrom((Relation) y);
return x;
} else if (isSubClass(x, OafEntity.class)
&& isSubClass(y, OafEntity.class)
&& isSubClass(x, y)) {
((OafEntity) x).mergeFrom((OafEntity) y);
return x;
}
throw new RuntimeException(
String
.format(
"MERGE_FROM_AND_GET incompatible types: %s, %s",
x.getClass().getCanonicalName(), y.getClass().getCanonicalName()));
}
@SuppressWarnings("unchecked")

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

@ -8,7 +8,6 @@ import static org.mockito.Mockito.*;
import java.util.function.BiFunction;
import org.junit.jupiter.api.Disabled;
import org.junit.jupiter.api.Nested;
import org.junit.jupiter.api.Test;
@ -86,7 +85,6 @@ public class MergeAndGetTest {
}
@Test
@Disabled
void shouldBehaveProperlyForRelationAndRelation() {
// given
Relation a = mock(Relation.class);
@ -98,9 +96,7 @@ public class MergeAndGetTest {
// then
Oaf x = fn.get().apply(a, b);
assertTrue(Relation.class.isAssignableFrom(x.getClass()));
// TODO should be reimplemented
// verify(a).mergeFrom(b);
verify(a).mergeFrom(b);
assertEquals(a, x);
}
@ -149,7 +145,6 @@ public class MergeAndGetTest {
}
@Test
@Disabled
void shouldBehaveProperlyForOafEntityAndOafEntity() {
// given
OafEntity a = mock(OafEntity.class);
@ -161,9 +156,7 @@ public class MergeAndGetTest {
// then
Oaf x = fn.get().apply(a, b);
assertTrue(OafEntity.class.isAssignableFrom(x.getClass()));
// TODO should be reimplemented
// verify(a).mergeFrom(b);
verify(a).mergeFrom(b);
assertEquals(a, x);
}
}

View File

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

View File

@ -9,7 +9,6 @@ import java.util.List;
import org.apache.commons.io.IOUtils;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.compress.BZip2Codec;
import org.apache.hadoop.io.compress.GzipCodec;
import org.apache.hadoop.mapred.SequenceFileOutputFormat;
import org.apache.spark.SparkConf;
@ -41,9 +40,9 @@ public class PrepareAffiliationRelations implements Serializable {
private static final Logger log = LoggerFactory.getLogger(PrepareAffiliationRelations.class);
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
private static final String ID_PREFIX = "50|doi_________::";
public static final String BIP_AFFILIATIONS_CLASSID = "result:organization:openaireinference";
public static final String BIP_AFFILIATIONS_CLASSNAME = "Affiliation relation inferred by OpenAIRE";
public static final String BIP_INFERENCE_PROVENANCE = "openaire:affiliation";
public static final String BIP_AFFILIATIONS_CLASSID = "result:organization:bipinference";
public static final String BIP_AFFILIATIONS_CLASSNAME = "Affiliation relation inferred by BIP!";
public static final String BIP_INFERENCE_PROVENANCE = "bip:affiliation:crossref";
public static <I extends Result> void main(String[] args) throws Exception {
@ -65,15 +64,6 @@ public class PrepareAffiliationRelations implements Serializable {
final String pubmedInputPath = parser.get("pubmedInputPath");
log.info("pubmedInputPath: {}", pubmedInputPath);
final String openapcInputPath = parser.get("openapcInputPath");
log.info("openapcInputPath: {}", openapcInputPath);
final String dataciteInputPath = parser.get("dataciteInputPath");
log.info("dataciteInputPath: {}", dataciteInputPath);
final String webcrawlInputPath = parser.get("webCrawlInputPath");
log.info("webcrawlInputPath: {}", webcrawlInputPath);
final String outputPath = parser.get("outputPath");
log.info("outputPath: {}", outputPath);
@ -95,28 +85,10 @@ public class PrepareAffiliationRelations implements Serializable {
JavaPairRDD<Text, Text> pubmedRelations = prepareAffiliationRelations(
spark, pubmedInputPath, collectedFromPubmed);
List<KeyValue> collectedFromOpenAPC = OafMapperUtils
.listKeyValues(ModelConstants.OPEN_APC_ID, "OpenAPC");
JavaPairRDD<Text, Text> openAPCRelations = prepareAffiliationRelations(
spark, openapcInputPath, collectedFromOpenAPC);
List<KeyValue> collectedFromDatacite = OafMapperUtils
.listKeyValues(ModelConstants.DATACITE_ID, "Datacite");
JavaPairRDD<Text, Text> dataciteRelations = prepareAffiliationRelations(
spark, dataciteInputPath, collectedFromDatacite);
List<KeyValue> collectedFromWebCrawl = OafMapperUtils
.listKeyValues(Constants.WEB_CRAWL_ID, Constants.WEB_CRAWL_NAME);
JavaPairRDD<Text, Text> webCrawlRelations = prepareAffiliationRelations(
spark, webcrawlInputPath, collectedFromWebCrawl);
crossrefRelations
.union(pubmedRelations)
.union(openAPCRelations)
.union(dataciteRelations)
.union(webCrawlRelations)
.saveAsHadoopFile(
outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, BZip2Codec.class);
outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class);
});
}

View File

@ -34,10 +34,6 @@ public class BipProjectModel {
String totalCitationCount;
public String getProjectId() {
return projectId;
}
// each project bip measure has exactly one value, hence one key-value pair
private Measure createMeasure(String measureId, String measureValue) {

View File

@ -75,7 +75,6 @@ public class GetFOSSparkJob implements Serializable {
fosData.map((MapFunction<Row, FOSDataModel>) r -> {
FOSDataModel fosDataModel = new FOSDataModel();
fosDataModel.setDoi(r.getString(0).toLowerCase());
fosDataModel.setOaid(r.getString(1).toLowerCase());
fosDataModel.setLevel1(r.getString(2));
fosDataModel.setLevel2(r.getString(3));
fosDataModel.setLevel3(r.getString(4));

View File

@ -16,14 +16,12 @@ import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.SaveMode;
import org.apache.spark.sql.SparkSession;
import org.jetbrains.annotations.NotNull;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import eu.dnetlib.dhp.actionmanager.createunresolvedentities.model.FOSDataModel;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.Result;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
import eu.dnetlib.dhp.schema.oaf.Subject;
@ -54,48 +52,28 @@ public class PrepareFOSSparkJob implements Serializable {
final String outputPath = parser.get("outputPath");
log.info("outputPath: {}", outputPath);
final Boolean distributeDOI = Optional
.ofNullable(parser.get("distributeDoi"))
.map(Boolean::valueOf)
.orElse(Boolean.TRUE);
SparkConf conf = new SparkConf();
runWithSparkSession(
conf,
isSparkSessionManaged,
spark -> {
if (distributeDOI)
distributeFOSdois(
spark,
sourcePath,
outputPath);
else
distributeFOSoaid(spark, sourcePath, outputPath);
});
}
private static void distributeFOSoaid(SparkSession spark, String sourcePath, String outputPath) {
private static void distributeFOSdois(SparkSession spark, String sourcePath, String outputPath) {
Dataset<FOSDataModel> fosDataset = readPath(spark, sourcePath, FOSDataModel.class);
fosDataset
.groupByKey((MapFunction<FOSDataModel, String>) v -> v.getOaid().toLowerCase(), Encoders.STRING())
.mapGroups(
(MapGroupsFunction<String, FOSDataModel, Result>) (k,
it) -> getResult(
ModelSupport.entityIdPrefix.get(Result.class.getSimpleName().toLowerCase()) + "|" + k, it),
Encoders.bean(Result.class))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(outputPath + "/fos");
}
@NotNull
private static Result getResult(String k, Iterator<FOSDataModel> it) {
.groupByKey((MapFunction<FOSDataModel, String>) v -> v.getDoi().toLowerCase(), Encoders.STRING())
.mapGroups((MapGroupsFunction<String, FOSDataModel, Result>) (k, it) -> {
Result r = new Result();
FOSDataModel first = it.next();
r.setId(k);
r.setId(DHPUtils.generateUnresolvedIdentifier(k, DOI));
HashSet<String> level1 = new HashSet<>();
HashSet<String> level2 = new HashSet<>();
@ -115,19 +93,21 @@ public class PrepareFOSSparkJob implements Serializable {
.forEach(
l -> add(sbjs, getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID, true)));
r.setSubject(sbjs);
r
.setDataInfo(
OafMapperUtils
.dataInfo(
false, null, true,
false,
OafMapperUtils
.qualifier(
ModelConstants.PROVENANCE_ENRICH,
null,
ModelConstants.DNET_PROVENANCE_ACTIONS,
ModelConstants.DNET_PROVENANCE_ACTIONS),
null));
return r;
}
private static void distributeFOSdois(SparkSession spark, String sourcePath, String outputPath) {
Dataset<FOSDataModel> fosDataset = readPath(spark, sourcePath, FOSDataModel.class);
fosDataset
.groupByKey((MapFunction<FOSDataModel, String>) v -> v.getDoi().toLowerCase(), Encoders.STRING())
.mapGroups(
(MapGroupsFunction<String, FOSDataModel, Result>) (k,
it) -> getResult(DHPUtils.generateUnresolvedIdentifier(k, DOI), it),
Encoders.bean(Result.class))
}, Encoders.bean(Result.class))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")

View File

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

View File

@ -0,0 +1,113 @@
package eu.dnetlib.dhp.actionmanager.dblp;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import java.io.Serializable;
import java.util.Arrays;
import java.util.List;
import java.util.stream.Collectors;
import org.apache.commons.io.IOUtils;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.compress.GzipCodec;
import org.apache.hadoop.mapred.SequenceFileOutputFormat;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.sql.*;
import org.apache.spark.sql.Dataset;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.actionmanager.Constants;
import eu.dnetlib.dhp.actionmanager.bipaffiliations.PrepareAffiliationRelations;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.schema.action.AtomicAction;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.*;
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
import scala.Tuple2;
/**
* Creates action sets for DBLP data
*/
public class PrepareDblpActionSets implements Serializable {
private static final Logger log = LoggerFactory.getLogger(PrepareDblpActionSets.class);
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
private static final String ID_PREFIX = "50|doi_________::";
public static final String BIP_AFFILIATIONS_CLASSID = "result:organization:bipinference";
public static final String BIP_AFFILIATIONS_CLASSNAME = "Affiliation relation inferred by BIP!";
public static final String BIP_INFERENCE_PROVENANCE = "bip:affiliation:crossref";
public static <I extends Result> void main(String[] args) throws Exception {
String jsonConfiguration = IOUtils
.toString(
PrepareDblpActionSets.class
.getResourceAsStream(
"/eu/dnetlib/dhp/actionmanager/dblp/input_actionset_parameter.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
parser.parseArgument(args);
Boolean isSparkSessionManaged = Constants.isSparkSessionManaged(parser);
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
final String dblpInputPath = parser.get("dblpInputPath");
log.info("dblpInputPath: {}", dblpInputPath);
final String outputPath = parser.get("outputPath");
log.info("outputPath: {}", outputPath);
SparkConf conf = new SparkConf();
runWithSparkSession(
conf,
isSparkSessionManaged,
spark -> {
Constants.removeOutputDir(spark, outputPath);
// TODO: add DBLP ID in ModelConstants
List<KeyValue> collectedFromDBLP = OafMapperUtils
.listKeyValues(ModelConstants.CROSSREF_ID, "DBLP");
JavaPairRDD<Text, Text> dblpData = prepareDblpData(
spark, dblpInputPath, collectedFromDBLP);
dblpData
.saveAsHadoopFile(
outputPath, Text.class, Text.class, SequenceFileOutputFormat.class);
});
}
private static <I extends Result> JavaPairRDD<Text, Text> prepareDblpData(SparkSession spark,
String inputPath,
List<KeyValue> collectedFrom) {
log.info("Reading DBLP XML data");
//
// TODO: load DBLP data into a Dataset
Dataset<Row> df = spark
.read()
.schema("`DOI` STRING, `Matchings` ARRAY<STRUCT<`RORid`:STRING,`Confidence`:DOUBLE>>")
.json(inputPath);
return df.map((MapFunction<Row, Result>) bs -> {
Result result = new Result();
// TODO: map DBLP data to Result objects
return result;
}, Encoders.bean(Result.class))
.toJavaRDD()
.map(p -> new AtomicAction(Result.class, p))
.mapToPair(
aa -> new Tuple2<>(new Text(aa.getClazz().getCanonicalName()),
new Text(OBJECT_MAPPER.writeValueAsString(aa))));
}
}

View File

@ -1,92 +0,0 @@
package eu.dnetlib.dhp.actionmanager.fosnodoi;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import java.io.IOException;
import java.io.Serializable;
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;
import org.apache.spark.sql.Encoders;
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.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.oaf.Relation;
import eu.dnetlib.dhp.schema.oaf.Result;
import eu.dnetlib.dhp.schema.oaf.utils.*;
import scala.Tuple2;
public class CreateActionSetSparkJob implements Serializable {
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 {
final ArgumentApplicationParser parser = new ArgumentApplicationParser(
IOUtils
.toString(
Objects
.requireNonNull(
CreateActionSetSparkJob.class
.getResourceAsStream(
"/eu/dnetlib/dhp/actionmanager/fosnodoi/as_parameters.json"))));
parser.parseArgument(args);
Boolean isSparkSessionManaged = Optional
.ofNullable(parser.get("isSparkSessionManaged"))
.map(Boolean::valueOf)
.orElse(Boolean.TRUE);
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
final String inputPath = parser.get("sourcePath");
log.info("inputPath {}", inputPath);
final String outputPath = parser.get("outputPath");
log.info("outputPath {}", outputPath);
SparkConf conf = new SparkConf();
runWithSparkSession(
conf,
isSparkSessionManaged,
spark -> createActionSet(spark, inputPath, outputPath));
}
private static void createActionSet(SparkSession spark, String inputPath, String outputPath) {
spark
.read()
.textFile(inputPath)
.map(
(MapFunction<String, Result>) value -> OBJECT_MAPPER.readValue(value, Result.class),
Encoders.bean(Result.class))
.toJavaRDD()
.map(p -> new AtomicAction(p.getClass(), p))
.mapToPair(
aa -> new Tuple2<>(new Text(aa.getClazz().getCanonicalName()),
new Text(OBJECT_MAPPER.writeValueAsString(aa))))
.saveAsHadoopFile(
outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class);
}
}

View File

@ -22,14 +22,12 @@ import org.apache.spark.sql.SparkSession;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.core.JsonProcessingException;
import com.fasterxml.jackson.databind.ObjectMapper;
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.*;
import eu.dnetlib.dhp.utils.DHPUtils;
@ -39,12 +37,16 @@ public class CreateActionSetSparkJob implements Serializable {
public static final String OPENCITATIONS_CLASSID = "sysimport:crosswalk:opencitations";
public static final String OPENCITATIONS_CLASSNAME = "Imported from OpenCitations";
// 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 ARXIV_PREFIX = "50|arXiv_______::";
private static final String PMCID_PREFIX = "50|pmcid_______::";
private static final String TRUST = "0.91";
private static final Logger log = LoggerFactory.getLogger(CreateActionSetSparkJob.class);
@ -77,30 +79,38 @@ public class CreateActionSetSparkJob implements Serializable {
final String outputPath = parser.get("outputPath");
log.info("outputPath {}", outputPath);
final boolean shouldDuplicateRels = Optional
.ofNullable(parser.get("shouldDuplicateRels"))
.map(Boolean::valueOf)
.orElse(Boolean.FALSE);
SparkConf conf = new SparkConf();
runWithSparkSession(
conf,
isSparkSessionManaged,
spark -> extractContent(spark, inputPath, outputPath));
spark -> extractContent(spark, inputPath, outputPath, shouldDuplicateRels));
}
private static void extractContent(SparkSession spark, String inputPath, String outputPath) {
private static void extractContent(SparkSession spark, String inputPath, String outputPath,
boolean shouldDuplicateRels) {
getTextTextJavaPairRDD(spark, inputPath)
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) {
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)
value, shouldDuplicateRels, prefix)
.iterator(),
Encoders.bean(Relation.class))
.filter((FilterFunction<Relation>) Objects::nonNull)
@ -111,68 +121,34 @@ public class CreateActionSetSparkJob implements Serializable {
new Text(OBJECT_MAPPER.writeValueAsString(aa))));
}
private static List<Relation> createRelation(COCI value) throws JsonProcessingException {
private static List<Relation> createRelation(COCI value, boolean duplicate, String p) {
List<Relation> relationList = new ArrayList<>();
String prefix;
String citing;
String cited;
switch (value.getCiting_pid()) {
case "doi":
citing = DOI_PREFIX
switch (p) {
case COCI:
prefix = DOI_PREFIX;
citing = prefix
+ IdentifierFactory
.md5(PidCleaner.normalizePidValue(PidType.doi.toString(), value.getCiting()));
break;
case "pmid":
citing = PMID_PREFIX
+ IdentifierFactory
.md5(PidCleaner.normalizePidValue(PidType.pmid.toString(), value.getCiting()));
break;
case "arxiv":
citing = ARXIV_PREFIX
+ IdentifierFactory
.md5(PidCleaner.normalizePidValue(PidType.arXiv.toString(), value.getCiting()));
break;
case "pmcid":
citing = PMCID_PREFIX
+ IdentifierFactory
.md5(PidCleaner.normalizePidValue(PidType.pmc.toString(), value.getCiting()));
break;
case "isbn":
case "issn":
return relationList;
default:
throw new IllegalStateException("Invalid prefix: " + new ObjectMapper().writeValueAsString(value));
}
switch (value.getCited_pid()) {
case "doi":
cited = DOI_PREFIX
cited = prefix
+ IdentifierFactory
.md5(PidCleaner.normalizePidValue(PidType.doi.toString(), value.getCited()));
break;
case "pmid":
cited = PMID_PREFIX
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;
case "arxiv":
cited = ARXIV_PREFIX
+ IdentifierFactory
.md5(PidCleaner.normalizePidValue(PidType.arXiv.toString(), value.getCited()));
break;
case "pmcid":
cited = PMCID_PREFIX
+ IdentifierFactory
.md5(PidCleaner.normalizePidValue(PidType.pmc.toString(), value.getCited()));
break;
case "isbn":
case "issn":
return relationList;
default:
throw new IllegalStateException("Invalid prefix: " + new ObjectMapper().writeValueAsString(value));
throw new IllegalStateException("Invalid prefix: " + p);
}
if (!citing.equals(cited)) {
@ -181,6 +157,15 @@ public class CreateActionSetSparkJob implements Serializable {
getRelation(
citing,
cited, ModelConstants.CITES));
if (duplicate && value.getCiting().endsWith(".refs")) {
citing = prefix + IdentifierFactory
.md5(
CleaningFunctions
.normalizePidValue(
"doi", value.getCiting().substring(0, value.getCiting().indexOf(".refs"))));
relationList.add(getRelation(citing, cited, ModelConstants.CITES));
}
}
return relationList;

View File

@ -12,7 +12,10 @@ import java.util.zip.ZipInputStream;
import org.apache.commons.cli.ParseException;
import org.apache.commons.io.IOUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.*;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
@ -34,17 +37,17 @@ public class GetOpenCitationsRefs implements Serializable {
parser.parseArgument(args);
// final String[] inputFile = parser.get("inputFile").split(";");
// log.info("inputFile {}", Arrays.asList(inputFile));
final String[] inputFile = parser.get("inputFile").split(";");
log.info("inputFile {}", Arrays.asList(inputFile));
final String inputPath = parser.get("inputPath");
log.info("inputPath {}", inputPath);
final String workingPath = parser.get("workingPath");
log.info("workingPath {}", workingPath);
final String hdfsNameNode = parser.get("hdfsNameNode");
log.info("hdfsNameNode {}", hdfsNameNode);
final String outputPath = parser.get("outputPath");
log.info("outputPath {}", outputPath);
final String prefix = parser.get("prefix");
log.info("prefix {}", prefix);
Configuration conf = new Configuration();
conf.set("fs.defaultFS", hdfsNameNode);
@ -53,20 +56,20 @@ public class GetOpenCitationsRefs implements Serializable {
GetOpenCitationsRefs ocr = new GetOpenCitationsRefs();
ocr.doExtract(inputPath, outputPath, fileSystem);
for (String file : inputFile) {
ocr.doExtract(workingPath + "/Original/" + file, workingPath, fileSystem, prefix);
}
}
private void doExtract(String inputPath, String outputPath, FileSystem fileSystem)
private void doExtract(String inputFile, String workingPath, FileSystem fileSystem, String prefix)
throws IOException {
RemoteIterator<LocatedFileStatus> fileStatusListIterator = fileSystem
.listFiles(
new Path(inputPath), true);
while (fileStatusListIterator.hasNext()) {
LocatedFileStatus fileStatus = fileStatusListIterator.next();
// do stuff with the file like ...
FSDataInputStream oc_zip = fileSystem.open(fileStatus.getPath());
final Path path = new Path(inputFile);
FSDataInputStream oc_zip = fileSystem.open(path);
// int count = 1;
try (ZipInputStream zis = new ZipInputStream(oc_zip)) {
ZipEntry entry = null;
while ((entry = zis.getNextEntry()) != null) {
@ -78,7 +81,7 @@ public class GetOpenCitationsRefs implements Serializable {
// count++;
try (
FSDataOutputStream out = fileSystem
.create(new Path(outputPath + "/" + fileName + ".gz"));
.create(new Path(workingPath + "/" + prefix + "/" + fileName + ".gz"));
GZIPOutputStream gzipOs = new GZIPOutputStream(new BufferedOutputStream(out))) {
IOUtils.copy(zis, gzipOs);
@ -89,7 +92,6 @@ public class GetOpenCitationsRefs implements Serializable {
}
}
}
}

View File

@ -1,171 +0,0 @@
package eu.dnetlib.dhp.actionmanager.opencitations;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import java.io.IOException;
import java.io.Serializable;
import java.util.Arrays;
import java.util.Objects;
import java.util.Optional;
import java.util.stream.Collectors;
import java.util.zip.ZipEntry;
import java.util.zip.ZipInputStream;
import org.apache.commons.cli.ParseException;
import org.apache.commons.io.IOUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.FlatMapFunction;
import org.apache.spark.api.java.function.ForeachFunction;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.sql.*;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.actionmanager.opencitations.model.COCI;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import scala.Tuple2;
/**
* @author miriam.baglioni
* @Date 29/02/24
*/
public class MapOCIdsInPids implements Serializable {
private static final Logger log = LoggerFactory.getLogger(CreateActionSetSparkJob.class);
private static final String DELIMITER = ",";
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
public static void main(final String[] args) throws IOException, ParseException {
final ArgumentApplicationParser parser = new ArgumentApplicationParser(
IOUtils
.toString(
Objects
.requireNonNull(
MapOCIdsInPids.class
.getResourceAsStream(
"/eu/dnetlib/dhp/actionmanager/opencitations/remap_parameters.json"))));
parser.parseArgument(args);
Boolean isSparkSessionManaged = Optional
.ofNullable(parser.get("isSparkSessionManaged"))
.map(Boolean::valueOf)
.orElse(Boolean.TRUE);
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
final String inputPath = parser.get("inputPath");
log.info("inputPath {}", inputPath);
final String outputPath = parser.get("outputPath");
log.info("outputPath {}", outputPath);
final String nameNode = parser.get("nameNode");
log.info("nameNode {}", nameNode);
unzipCorrespondenceFile(inputPath, nameNode);
SparkConf conf = new SparkConf();
runWithSparkSession(
conf,
isSparkSessionManaged,
spark -> mapIdentifiers(spark, inputPath, outputPath));
}
private static void unzipCorrespondenceFile(String inputPath, String hdfsNameNode) throws IOException {
Configuration conf = new Configuration();
conf.set("fs.defaultFS", hdfsNameNode);
final Path path = new Path(inputPath + "/correspondence/omid.zip");
FileSystem fileSystem = FileSystem.get(conf);
FSDataInputStream project_zip = fileSystem.open(path);
try (ZipInputStream zis = new ZipInputStream(project_zip)) {
ZipEntry entry = null;
while ((entry = zis.getNextEntry()) != null) {
if (!entry.isDirectory()) {
String fileName = entry.getName();
byte buffer[] = new byte[1024];
int count;
try (
FSDataOutputStream out = fileSystem
.create(new Path(inputPath + "/correspondence/omid.csv"))) {
while ((count = zis.read(buffer, 0, buffer.length)) != -1)
out.write(buffer, 0, count);
}
}
}
}
}
private static void mapIdentifiers(SparkSession spark, String inputPath, String outputPath) {
Dataset<COCI> coci = spark
.read()
.textFile(inputPath + "/JSON")
.map(
(MapFunction<String, COCI>) value -> OBJECT_MAPPER.readValue(value, COCI.class),
Encoders.bean(COCI.class));
Dataset<Tuple2<String, String>> correspondenceData = spark
.read()
.format("csv")
.option("sep", DELIMITER)
.option("inferSchema", "true")
.option("header", "true")
.option("quotes", "\"")
.load(inputPath + "/correspondence/omid.csv")
.repartition(5000)
.flatMap((FlatMapFunction<Row, Tuple2<String, String>>) r -> {
String ocIdentifier = r.getAs("omid");
String[] correspondentIdentifiers = ((String) r.getAs("id")).split(" ");
return Arrays
.stream(correspondentIdentifiers)
.map(ci -> new Tuple2<String, String>(ocIdentifier, ci))
.collect(Collectors.toList())
.iterator();
}, Encoders.tuple(Encoders.STRING(), Encoders.STRING()));
Dataset<COCI> mappedCitingDataset = coci
.joinWith(correspondenceData, coci.col("citing").equalTo(correspondenceData.col("_1")))
.map((MapFunction<Tuple2<COCI, Tuple2<String, String>>, COCI>) t2 -> {
String correspondent = t2._2()._2();
t2._1().setCiting_pid(correspondent.substring(0, correspondent.indexOf(":")));
t2._1().setCiting(correspondent.substring(correspondent.indexOf(":") + 1));
return t2._1();
}, Encoders.bean(COCI.class));
mappedCitingDataset
.joinWith(correspondenceData, mappedCitingDataset.col("cited").equalTo(correspondenceData.col("_1")))
.map((MapFunction<Tuple2<COCI, Tuple2<String, String>>, COCI>) t2 -> {
String correspondent = t2._2()._2();
t2._1().setCited_pid(correspondent.substring(0, correspondent.indexOf(":")));
t2._1().setCited(correspondent.substring(correspondent.indexOf(":") + 1));
return t2._1();
}, Encoders.bean(COCI.class))
.write()
.mode(SaveMode.Append)
.option("compression", "gzip")
.json(outputPath);
}
}

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