1
0
Fork 0

attributes fixes

This commit is contained in:
Michele De Bonis 2024-12-05 14:39:42 +01:00
parent bde59a7c8f
commit 6af3fd16b6
21 changed files with 546 additions and 431 deletions

View File

@ -1,10 +1,5 @@
package eu.dnetlib.pace.tree;
import com.wcohen.ss.AbstractStringDistance; package eu.dnetlib.pace.tree;
import eu.dnetlib.pace.config.Config;
import eu.dnetlib.pace.tree.support.AbstractStringComparator;
import eu.dnetlib.pace.tree.support.ComparatorClass;
import org.joda.time.DateTime;
import java.time.DateTimeException; import java.time.DateTimeException;
import java.time.LocalDate; import java.time.LocalDate;
@ -13,6 +8,14 @@ import java.time.format.DateTimeFormatter;
import java.util.Locale; import java.util.Locale;
import java.util.Map; import java.util.Map;
import org.joda.time.DateTime;
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("dateRange") @ComparatorClass("dateRange")
public class DateRange extends AbstractStringComparator { public class DateRange extends AbstractStringComparator {
@ -32,7 +35,7 @@ public class DateRange extends AbstractStringComparator {
} }
public static boolean isNumeric(String str) { public static boolean isNumeric(String str) {
return str.matches("\\d+"); //match a number with optional '-' and decimal. return str.matches("\\d+"); // match a number with optional '-' and decimal.
} }
@Override @Override
@ -47,9 +50,8 @@ public class DateRange extends AbstractStringComparator {
LocalDate d2 = LocalDate.parse(b, formatter); LocalDate d2 = LocalDate.parse(b, formatter);
Period period = Period.between(d1, d2); Period period = Period.between(d1, d2);
return period.getYears() <= YEAR_RANGE? 1.0 : 0.0; return period.getYears() <= YEAR_RANGE ? 1.0 : 0.0;
} } catch (DateTimeException e) {
catch (DateTimeException e) {
return -1.0; return -1.0;
} }

View File

@ -72,14 +72,34 @@ public class ComparatorTest extends AbstractPaceTest {
CodeMatch codeMatch = new CodeMatch(params); CodeMatch codeMatch = new CodeMatch(params);
// names have different codes // names have different codes
assertEquals(0.0, codeMatch.distance("physical oceanography at ctd station june 1998 ev02a", "physical oceanography at ctd station june 1998 ir02", conf)); assertEquals(
0.0,
codeMatch
.distance(
"physical oceanography at ctd station june 1998 ev02a",
"physical oceanography at ctd station june 1998 ir02", conf));
// names have same code // names have same code
assertEquals(1.0, codeMatch.distance("physical oceanography at ctd station june 1998 ev02a", "physical oceanography at ctd station june 1998 ev02a", conf)); assertEquals(
1.0,
codeMatch
.distance(
"physical oceanography at ctd station june 1998 ev02a",
"physical oceanography at ctd station june 1998 ev02a", conf));
// code is not in both names // code is not in both names
assertEquals(-1, codeMatch.distance("physical oceanography at ctd station june 1998", "physical oceanography at ctd station june 1998 ev02a", conf)); assertEquals(
assertEquals(1.0, codeMatch.distance("physical oceanography at ctd station june 1998", "physical oceanography at ctd station june 1998", conf)); -1,
codeMatch
.distance(
"physical oceanography at ctd station june 1998",
"physical oceanography at ctd station june 1998 ev02a", conf));
assertEquals(
1.0,
codeMatch
.distance(
"physical oceanography at ctd station june 1998", "physical oceanography at ctd station june 1998",
conf));
} }
@Test @Test

View File

@ -3,8 +3,6 @@ package eu.dnetlib.dhp.actionmanager;
import java.util.Optional; import java.util.Optional;
import eu.dnetlib.dhp.schema.oaf.Instance;
import eu.dnetlib.dhp.schema.oaf.Qualifier;
import org.apache.spark.api.java.function.MapFunction; import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.sql.Dataset; import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoders; import org.apache.spark.sql.Encoders;
@ -15,6 +13,8 @@ import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.application.ArgumentApplicationParser; import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.HdfsSupport; import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.schema.common.ModelConstants; import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.Instance;
import eu.dnetlib.dhp.schema.oaf.Qualifier;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty; import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
import eu.dnetlib.dhp.schema.oaf.Subject; import eu.dnetlib.dhp.schema.oaf.Subject;
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils; import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;

View File

@ -1,15 +1,15 @@
package eu.dnetlib.dhp.actionmanager.raid; package eu.dnetlib.dhp.actionmanager.raid;
import com.fasterxml.jackson.databind.ObjectMapper; import static eu.dnetlib.dhp.actionmanager.personentity.ExtractPerson.OPENAIRE_DATASOURCE_ID;
import eu.dnetlib.dhp.actionmanager.raid.model.RAiDEntity; import static eu.dnetlib.dhp.actionmanager.personentity.ExtractPerson.OPENAIRE_DATASOURCE_NAME;
import eu.dnetlib.dhp.application.ArgumentApplicationParser; import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import eu.dnetlib.dhp.common.Constants; import static eu.dnetlib.dhp.schema.common.ModelConstants.*;
import eu.dnetlib.dhp.common.HdfsSupport; import static eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils.*;
import eu.dnetlib.dhp.schema.action.AtomicAction;
import eu.dnetlib.dhp.schema.common.ModelConstants; import java.util.*;
import eu.dnetlib.dhp.schema.oaf.*; import java.util.stream.Collectors;
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
import eu.dnetlib.dhp.utils.DHPUtils;
import org.apache.commons.io.IOUtils; import org.apache.commons.io.IOUtils;
import org.apache.hadoop.io.Text; import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.SequenceFileOutputFormat; import org.apache.hadoop.mapred.SequenceFileOutputFormat;
@ -19,30 +19,37 @@ import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.SparkSession; import org.apache.spark.sql.SparkSession;
import org.slf4j.Logger; import org.slf4j.Logger;
import org.slf4j.LoggerFactory; import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.actionmanager.raid.model.RAiDEntity;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.Constants;
import eu.dnetlib.dhp.common.HdfsSupport;
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 eu.dnetlib.dhp.utils.DHPUtils;
import scala.Tuple2; import scala.Tuple2;
import java.util.*;
import java.util.stream.Collectors;
import static eu.dnetlib.dhp.actionmanager.personentity.ExtractPerson.OPENAIRE_DATASOURCE_ID;
import static eu.dnetlib.dhp.actionmanager.personentity.ExtractPerson.OPENAIRE_DATASOURCE_NAME;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import static eu.dnetlib.dhp.schema.common.ModelConstants.*;
import static eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils.*;
public class GenerateRAiDActionSetJob { public class GenerateRAiDActionSetJob {
private static final Logger log = LoggerFactory.getLogger(eu.dnetlib.dhp.actionmanager.raid.GenerateRAiDActionSetJob.class); private static final Logger log = LoggerFactory
.getLogger(eu.dnetlib.dhp.actionmanager.raid.GenerateRAiDActionSetJob.class);
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper(); private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
private static final List<KeyValue> RAID_COLLECTED_FROM = listKeyValues( private static final List<KeyValue> RAID_COLLECTED_FROM = listKeyValues(
OPENAIRE_DATASOURCE_ID, OPENAIRE_DATASOURCE_NAME); OPENAIRE_DATASOURCE_ID, OPENAIRE_DATASOURCE_NAME);
private static final Qualifier RAID_QUALIFIER = qualifier("raid:openaireinference", "raid:openaireinference", DNET_PROVENANCE_ACTIONS, DNET_PROVENANCE_ACTIONS); private static final Qualifier RAID_QUALIFIER = qualifier("0049", "Research Activity Identifier", DNET_PUBLICATION_RESOURCE, DNET_PUBLICATION_RESOURCE);
private static final Qualifier RAID_INFERENCE_QUALIFIER = qualifier(
"raid:openaireinference", "Inferred by OpenAIRE", DNET_PROVENANCE_ACTIONS, DNET_PROVENANCE_ACTIONS);
private static final DataInfo RAID_DATA_INFO = dataInfo( private static final DataInfo RAID_DATA_INFO = dataInfo(
false, OPENAIRE_DATASOURCE_NAME, true, false, RAID_QUALIFIER, "0.92"); false, OPENAIRE_DATASOURCE_NAME, true, false, RAID_INFERENCE_QUALIFIER, "0.92");
public static void main(final String[] args) throws Exception { public static void main(final String[] args) throws Exception {
@ -103,59 +110,71 @@ public class GenerateRAiDActionSetJob {
orp.setId(raidId); orp.setId(raidId);
orp.setCollectedfrom(RAID_COLLECTED_FROM); orp.setCollectedfrom(RAID_COLLECTED_FROM);
orp.setDataInfo(RAID_DATA_INFO); orp.setDataInfo(RAID_DATA_INFO);
orp.setResourcetype(RAID_QUALIFIER); orp
orp.setTitle( .setTitle(
Collections.singletonList( Collections
.singletonList(
structuredProperty( structuredProperty(
r.getTitle(), r.getTitle(),
qualifier("main title", "main title", DNET_DATACITE_TITLE, DNET_DATACITE_TITLE), qualifier("main title", "main title", DNET_DATACITE_TITLE, DNET_DATACITE_TITLE),
RAID_DATA_INFO)) RAID_DATA_INFO)));
);
orp.setDescription(listFields(RAID_DATA_INFO, r.getSummary())); orp.setDescription(listFields(RAID_DATA_INFO, r.getSummary()));
orp.setAuthor(createAuthors(r.getAuthors())); // orp.setAuthor(createAuthors(r.getAuthors()));
orp.setInstance(Collections.singletonList(eu.dnetlib.dhp.actionmanager.Constants.getInstance(RAID_QUALIFIER))); orp.setInstance(Collections.singletonList(eu.dnetlib.dhp.actionmanager.Constants.getInstance(RAID_QUALIFIER)));
orp.setSubject( orp
r.getSubjects() .setSubject(
r
.getSubjects()
.stream() .stream()
.map(s -> subject(s, qualifier(DNET_SUBJECT_KEYWORD, DNET_SUBJECT_KEYWORD, DNET_SUBJECT_TYPOLOGIES, DNET_SUBJECT_TYPOLOGIES), RAID_DATA_INFO)) .map(
.collect(Collectors.toList()) s -> subject(
); s,
orp.setRelevantdate( qualifier(
Arrays.asList( DNET_SUBJECT_KEYWORD, DNET_SUBJECT_KEYWORD, DNET_SUBJECT_TYPOLOGIES,
structuredProperty(r.getEndDate(), qualifier("endDate","endDate", DNET_DATACITE_DATE, DNET_DATACITE_DATE), RAID_DATA_INFO), DNET_SUBJECT_TYPOLOGIES),
structuredProperty(r.getStartDate(), qualifier("startDate", "startDate", DNET_DATACITE_DATE, DNET_DATACITE_DATE), RAID_DATA_INFO) RAID_DATA_INFO))
) .collect(Collectors.toList()));
); orp
.setRelevantdate(
Arrays
.asList(
structuredProperty(
r.getEndDate(), qualifier("endDate", "endDate", DNET_DATACITE_DATE, DNET_DATACITE_DATE),
RAID_DATA_INFO),
structuredProperty(
r.getStartDate(),
qualifier("startDate", "startDate", DNET_DATACITE_DATE, DNET_DATACITE_DATE),
RAID_DATA_INFO)));
orp.setLastupdatetimestamp(now.getTime()); orp.setLastupdatetimestamp(now.getTime());
orp.setDateofcollection(r.getStartDate()); orp.setDateofacceptance(field(r.getStartDate(), RAID_DATA_INFO));
res.add(new AtomicAction<>(OtherResearchProduct.class, orp)); res.add(new AtomicAction<>(OtherResearchProduct.class, orp));
for(String resultId: r.getIds()) { for (String resultId : r.getIds()) {
Relation rel1 = OafMapperUtils.getRelation( Relation rel1 = OafMapperUtils
.getRelation(
raidId, raidId,
resultId, resultId,
ModelConstants.RESULT_RESULT, ModelConstants.RESULT_RESULT,
ModelConstants.OUTCOME,
PART, PART,
HAS_PART,
RAID_COLLECTED_FROM, RAID_COLLECTED_FROM,
RAID_DATA_INFO, RAID_DATA_INFO,
now.getTime(), now.getTime(),
null, null,
null null);
); Relation rel2 = OafMapperUtils
Relation rel2 = OafMapperUtils.getRelation( .getRelation(
resultId, resultId,
raidId, raidId,
ModelConstants.RESULT_RESULT, ModelConstants.RESULT_RESULT,
ModelConstants.OUTCOME, PART,
IS_PART_OF, IS_PART_OF,
RAID_COLLECTED_FROM, RAID_COLLECTED_FROM,
RAID_DATA_INFO, RAID_DATA_INFO,
now.getTime(), now.getTime(),
null, null,
null null);
);
res.add(new AtomicAction<>(Relation.class, rel1)); res.add(new AtomicAction<>(Relation.class, rel1));
res.add(new AtomicAction<>(Relation.class, rel2)); res.add(new AtomicAction<>(Relation.class, rel2));
} }
@ -168,7 +187,7 @@ public class GenerateRAiDActionSetJob {
} }
public static List<Author> createAuthors(final List<String> author) { public static List<Author> createAuthors(final List<String> author) {
return author.stream().map(s-> { return author.stream().map(s -> {
Author a = new Author(); Author a = new Author();
a.setFullname(s); a.setFullname(s);
return a; return a;

View File

@ -1,2 +1,5 @@
package eu.dnetlib.dhp.actionmanager.raid.model;public class GenerateRAiDActionSetJob {
package eu.dnetlib.dhp.actionmanager.raid.model;
public class GenerateRAiDActionSetJob {
} }

View File

@ -1,3 +1,4 @@
package eu.dnetlib.dhp.actionmanager.raid.model; package eu.dnetlib.dhp.actionmanager.raid.model;
import java.io.Serializable; import java.io.Serializable;
@ -15,8 +16,11 @@ public class RAiDEntity implements Serializable {
String title; String title;
String summary; String summary;
public RAiDEntity(){} public RAiDEntity() {
public RAiDEntity(String raid, List<String> authors, String startDate, String endDate, List<String> subjects, List<String> titles, List<String> ids, String title, String summary) { }
public RAiDEntity(String raid, List<String> authors, String startDate, String endDate, List<String> subjects,
List<String> titles, List<String> ids, String title, String summary) {
this.raid = raid; this.raid = raid;
this.authors = authors; this.authors = authors;
this.startDate = startDate; this.startDate = startDate;

View File

@ -21,7 +21,6 @@ import java.util.Optional;
import java.util.Set; import java.util.Set;
import java.util.stream.Collectors; import java.util.stream.Collectors;
import eu.dnetlib.dhp.schema.oaf.*;
import org.apache.commons.io.IOUtils; import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.StringUtils; import org.apache.commons.lang3.StringUtils;
import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.conf.Configuration;
@ -45,6 +44,7 @@ import eu.dnetlib.dhp.common.Constants;
import eu.dnetlib.dhp.common.HdfsSupport; import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.schema.action.AtomicAction; import eu.dnetlib.dhp.schema.action.AtomicAction;
import eu.dnetlib.dhp.schema.common.ModelConstants; import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.*;
import eu.dnetlib.dhp.utils.DHPUtils; import eu.dnetlib.dhp.utils.DHPUtils;
import scala.Tuple2; import scala.Tuple2;

View File

@ -1,3 +1,4 @@
package eu.dnetlib.dhp.sx.bio.pubmed; package eu.dnetlib.dhp.sx.bio.pubmed;
/** /**
@ -14,6 +15,7 @@ public class PMAffiliation {
public PMAffiliation() { public PMAffiliation() {
} }
public PMAffiliation(String name, PMIdentifier identifier) { public PMAffiliation(String name, PMIdentifier identifier) {
this.name = name; this.name = name;
this.identifier = identifier; this.identifier = identifier;

View File

@ -97,5 +97,4 @@ public class PMAuthor implements Serializable {
this.affiliation = affiliation; this.affiliation = affiliation;
} }
} }

View File

@ -1,3 +1,4 @@
package eu.dnetlib.dhp.sx.bio.pubmed; package eu.dnetlib.dhp.sx.bio.pubmed;
public class PMIdentifier { public class PMIdentifier {
@ -5,7 +6,6 @@ public class PMIdentifier {
private String pid; private String pid;
private String type; private String type;
public PMIdentifier(String pid, String type) { public PMIdentifier(String pid, String type) {
this.pid = cleanPid(pid); this.pid = cleanPid(pid);
this.type = type; this.type = type;

View File

@ -20,8 +20,6 @@
<fs> <fs>
<delete path='${raidActionSetPath}'/> <delete path='${raidActionSetPath}'/>
<mkdir path='${raidActionSetPath}'/> <mkdir path='${raidActionSetPath}'/>
<delete path='${workingDir}'/>
<mkdir path='${workingDir}'/>
</fs> </fs>
<ok to="processRAiDFile"/> <ok to="processRAiDFile"/>
<error to="Kill"/> <error to="Kill"/>

View File

@ -673,7 +673,6 @@ case object Crossref2Oaf {
val doi = input.getString(0) val doi = input.getString(0)
val rorId = input.getString(1) val rorId = input.getString(1)
val pubId = IdentifierFactory.idFromPid("50", "doi", DoiCleaningRule.clean(doi), true) val pubId = IdentifierFactory.idFromPid("50", "doi", DoiCleaningRule.clean(doi), true)
val affId = GenerateRorActionSetJob.calculateOpenaireId(rorId) val affId = GenerateRorActionSetJob.calculateOpenaireId(rorId)

View File

@ -82,21 +82,22 @@ class PMParser2 {
a.setLastName((author \ "LastName").text) a.setLastName((author \ "LastName").text)
a.setForeName((author \ "ForeName").text) a.setForeName((author \ "ForeName").text)
val id = (author \ "Identifier").text val id = (author \ "Identifier").text
val idType =(author \ "Identifier" \ "@Source").text val idType = (author \ "Identifier" \ "@Source").text
if(id != null && id.nonEmpty && idType != null && idType.nonEmpty) { if (id != null && id.nonEmpty && idType != null && idType.nonEmpty) {
a.setIdentifier(new PMIdentifier(id, idType)) a.setIdentifier(new PMIdentifier(id, idType))
} }
val affiliation = (author \ "AffiliationInfo" \ "Affiliation").text val affiliation = (author \ "AffiliationInfo" \ "Affiliation").text
val affiliationId = (author \ "AffiliationInfo" \ "Identifier").text val affiliationId = (author \ "AffiliationInfo" \ "Identifier").text
val affiliationIdType = (author \ "AffiliationInfo" \ "Identifier" \ "@Source").text val affiliationIdType = (author \ "AffiliationInfo" \ "Identifier" \ "@Source").text
if(affiliation != null && affiliation.nonEmpty) { if (affiliation != null && affiliation.nonEmpty) {
val aff = new PMAffiliation() val aff = new PMAffiliation()
aff.setName(affiliation) aff.setName(affiliation)
if(affiliationId != null && affiliationId.nonEmpty && affiliationIdType != null && affiliationIdType.nonEmpty) { if (
affiliationId != null && affiliationId.nonEmpty && affiliationIdType != null && affiliationIdType.nonEmpty
) {
aff.setIdentifier(new PMIdentifier(affiliationId, affiliationIdType)) aff.setIdentifier(new PMIdentifier(affiliationId, affiliationIdType))
} }
a.setAffiliation(aff) a.setAffiliation(aff)

View File

@ -294,11 +294,23 @@ object PubMedToOaf {
author.setName(a.getForeName) author.setName(a.getForeName)
author.setSurname(a.getLastName) author.setSurname(a.getLastName)
author.setFullname(a.getFullName) author.setFullname(a.getFullName)
if(a.getIdentifier != null) { if (a.getIdentifier != null) {
author.setPid(List(OafMapperUtils.structuredProperty(a.getIdentifier.getPid, author.setPid(
OafMapperUtils.qualifier(a.getIdentifier.getType,a.getIdentifier.getType,ModelConstants.DNET_PID_TYPES, ModelConstants.DNET_PID_TYPES), dataInfo)).asJava) List(
OafMapperUtils.structuredProperty(
a.getIdentifier.getPid,
OafMapperUtils.qualifier(
a.getIdentifier.getType,
a.getIdentifier.getType,
ModelConstants.DNET_PID_TYPES,
ModelConstants.DNET_PID_TYPES
),
dataInfo
)
).asJava
)
} }
if (a.getAffiliation!= null) if (a.getAffiliation != null)
author.setRawAffiliationString(List(a.getAffiliation.getName).asJava) author.setRawAffiliationString(List(a.getAffiliation.getName).asJava)
author.setRank(index + 1) author.setRank(index + 1)
author author

View File

@ -1,11 +1,16 @@
package eu.dnetlib.dhp.actionmanager.raid; package eu.dnetlib.dhp.actionmanager.raid;
import eu.dnetlib.dhp.actionmanager.opencitations.CreateOpenCitationsASTest; import static java.nio.file.Files.createTempDirectory;
import eu.dnetlib.dhp.actionmanager.raid.model.RAiDEntity;
import eu.dnetlib.dhp.schema.action.AtomicAction; import static eu.dnetlib.dhp.actionmanager.Constants.OBJECT_MAPPER;
import eu.dnetlib.dhp.schema.oaf.Oaf; import static org.junit.jupiter.api.Assertions.assertEquals;
import eu.dnetlib.dhp.schema.oaf.OtherResearchProduct;
import eu.dnetlib.dhp.schema.oaf.Relation; import java.io.File;
import java.nio.file.Paths;
import java.util.Arrays;
import java.util.List;
import org.apache.commons.io.FileUtils; import org.apache.commons.io.FileUtils;
import org.apache.hadoop.io.Text; import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFormat; import org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFormat;
@ -20,17 +25,15 @@ import org.junit.jupiter.api.AfterAll;
import org.junit.jupiter.api.BeforeEach; import org.junit.jupiter.api.BeforeEach;
import org.junit.jupiter.api.Disabled; import org.junit.jupiter.api.Disabled;
import org.junit.jupiter.api.Test; import org.junit.jupiter.api.Test;
import eu.dnetlib.dhp.actionmanager.opencitations.CreateOpenCitationsASTest;
import eu.dnetlib.dhp.actionmanager.raid.model.RAiDEntity;
import eu.dnetlib.dhp.schema.action.AtomicAction;
import eu.dnetlib.dhp.schema.oaf.Oaf;
import eu.dnetlib.dhp.schema.oaf.OtherResearchProduct;
import eu.dnetlib.dhp.schema.oaf.Relation;
import scala.Tuple2; import scala.Tuple2;
import java.io.File;
import java.nio.file.Paths;
import java.util.Arrays;
import java.util.List;
import static eu.dnetlib.dhp.actionmanager.Constants.OBJECT_MAPPER;
import static java.nio.file.Files.createTempDirectory;
import static org.junit.jupiter.api.Assertions.assertEquals;
public class GenerateRAiDActionSetJobTest { public class GenerateRAiDActionSetJobTest {
private static String input_path; private static String input_path;
private static String output_path; private static String output_path;
@ -40,7 +43,10 @@ public class GenerateRAiDActionSetJobTest {
void setUp() throws Exception { void setUp() throws Exception {
input_path = Paths input_path = Paths
.get(GenerateRAiDActionSetJobTest.class.getResource("/eu/dnetlib/dhp/actionmanager/raid/raid_example.json").toURI()) .get(
GenerateRAiDActionSetJobTest.class
.getResource("/eu/dnetlib/dhp/actionmanager/raid/raid_example.json")
.toURI())
.toFile() .toFile()
.getAbsolutePath(); .getAbsolutePath();
@ -88,17 +94,64 @@ public class GenerateRAiDActionSetJobTest {
@Test @Test
void testPrepareRAiD() { void testPrepareRAiD() {
List<AtomicAction<? extends Oaf>> atomicActions = GenerateRAiDActionSetJob.prepareRAiD(new RAiDEntity( List<AtomicAction<? extends Oaf>> atomicActions = GenerateRAiDActionSetJob
.prepareRAiD(
new RAiDEntity(
"-92190526", "-92190526",
Arrays.asList("Berli, Justin", "Le Mao, Bérénice", "Guillaume Touya", "Wenclik, Laura", "Courtial, Azelle", "Muehlenhaus, Ian", "Justin Berli", "Touya, Guillaume", "Gruget, Maïeul", "Azelle Courtial", "Ian Muhlenhaus", "Maïeul Gruget", "Marion Dumont", "Maïeul GRUGET", "Cécile Duchêne"), Arrays
.asList(
"Berli, Justin", "Le Mao, Bérénice", "Guillaume Touya", "Wenclik, Laura",
"Courtial, Azelle", "Muehlenhaus, Ian", "Justin Berli", "Touya, Guillaume",
"Gruget, Maïeul", "Azelle Courtial", "Ian Muhlenhaus", "Maïeul Gruget", "Marion Dumont",
"Maïeul GRUGET", "Cécile Duchêne"),
"2021-09-10", "2021-09-10",
"2024-02-16", "2024-02-16",
Arrays.asList("cartography, zoom, pan, desert fog", "Road network", "zooming", "Pan-scalar maps", "pan-scalar map", "Python library", "QGIS", "map design", "landmarks", "Cartes transscalaires", "anchor", "disorientation", "[INFO]Computer Science [cs]", "[SHS.GEO]Humanities and Social Sciences/Geography", "cognitive cartography", "eye-tracking", "Computers in Earth Sciences", "Topographic map", "National Mapping Agency", "General Medicine", "Geography, Planning and Development", "multi-scales", "pan-scalar maps", "Selection", "cartography", "General Earth and Planetary Sciences", "progressiveness", "map generalisation", "Eye-tracker", "zoom", "algorithms", "Map Design", "cartography, map generalisation, zoom, multi-scale map", "Interactive maps", "Map generalisation", "Earth and Planetary Sciences (miscellaneous)", "Cartographic generalization", "rivers", "Benchmark", "General Environmental Science", "open source", "drawing", "Constraint", "Multi-scale maps"), Arrays
Arrays.asList("Where do people look at during multi-scale map tasks?", "FogDetector survey raw data", "Collection of cartographic disorientation stories", "Anchorwhat dataset", "BasqueRoads: A Benchmark for Road Network Selection", "Progressive river network selection for pan-scalar maps", "BasqueRoads, a dataset to benchmark road selection algorithms", "Missing the city for buildings? A critical review of pan-scalar map generalization and design in contemporary zoomable maps", "Empirical approach to advance the generalisation of multi-scale maps", "L'Alpe d'Huez: a dataset to benchmark topographic map generalisation", "eye-tracking data from a survey on zooming in a pan-scalar map", "Material of the experiment 'More is Less' from the MapMuxing project", "Cartagen4py, an open source Python library for map generalisation", "LAlpe dHuez: A Benchmark for Topographic Map Generalisation"), .asList(
Arrays.asList("50|doi_dedup___::6915135e0aa39f913394513f809ae58a", "50|doi_dedup___::754e3c283639bc6e104c925ff3e34007", "50|doi_dedup___::13517477f3c1261d57a3364363ce6ce0", "50|doi_dedup___::675b16c73accc4e7242bbb4ed9b3724a", "50|doi_dedup___::94ce09906b2d7d37eb2206cea8a50153", "50|dedup_wf_002::cc575d5ca5651ff8c3029a3a76e7e70a", "50|doi_dedup___::c5e52baddda17c755d1bae012a97dc13", "50|doi_dedup___::4f5f38c9e08fe995f7278963183f8ad4", "50|doi_dedup___::a9bc4453273b2d02648a5cb453195042", "50|doi_dedup___::5e893dc0cb7624a33f41c9b428bd59f7", "50|doi_dedup___::c1ecdef48fd9be811a291deed950e1c5", "50|doi_dedup___::9e93c8f2d97c35de8a6a57a5b53ef283", "50|dedup_wf_002::d08be0ed27b13d8a880e891e08d093ea", "50|doi_dedup___::f8d8b3b9eddeca2fc0e3bc9e63996555"), "cartography, zoom, pan, desert fog", "Road network", "zooming", "Pan-scalar maps",
"pan-scalar map", "Python library", "QGIS", "map design", "landmarks",
"Cartes transscalaires", "anchor", "disorientation", "[INFO]Computer Science [cs]",
"[SHS.GEO]Humanities and Social Sciences/Geography", "cognitive cartography",
"eye-tracking", "Computers in Earth Sciences", "Topographic map", "National Mapping Agency",
"General Medicine", "Geography, Planning and Development", "multi-scales",
"pan-scalar maps", "Selection", "cartography", "General Earth and Planetary Sciences",
"progressiveness", "map generalisation", "Eye-tracker", "zoom", "algorithms", "Map Design",
"cartography, map generalisation, zoom, multi-scale map", "Interactive maps",
"Map generalisation", "Earth and Planetary Sciences (miscellaneous)",
"Cartographic generalization", "rivers", "Benchmark", "General Environmental Science",
"open source", "drawing", "Constraint", "Multi-scale maps"),
Arrays
.asList(
"Where do people look at during multi-scale map tasks?", "FogDetector survey raw data",
"Collection of cartographic disorientation stories", "Anchorwhat dataset",
"BasqueRoads: A Benchmark for Road Network Selection",
"Progressive river network selection for pan-scalar maps",
"BasqueRoads, a dataset to benchmark road selection algorithms",
"Missing the city for buildings? A critical review of pan-scalar map generalization and design in contemporary zoomable maps",
"Empirical approach to advance the generalisation of multi-scale maps",
"L'Alpe d'Huez: a dataset to benchmark topographic map generalisation",
"eye-tracking data from a survey on zooming in a pan-scalar map",
"Material of the experiment 'More is Less' from the MapMuxing project",
"Cartagen4py, an open source Python library for map generalisation",
"LAlpe dHuez: A Benchmark for Topographic Map Generalisation"),
Arrays
.asList(
"50|doi_dedup___::6915135e0aa39f913394513f809ae58a",
"50|doi_dedup___::754e3c283639bc6e104c925ff3e34007",
"50|doi_dedup___::13517477f3c1261d57a3364363ce6ce0",
"50|doi_dedup___::675b16c73accc4e7242bbb4ed9b3724a",
"50|doi_dedup___::94ce09906b2d7d37eb2206cea8a50153",
"50|dedup_wf_002::cc575d5ca5651ff8c3029a3a76e7e70a",
"50|doi_dedup___::c5e52baddda17c755d1bae012a97dc13",
"50|doi_dedup___::4f5f38c9e08fe995f7278963183f8ad4",
"50|doi_dedup___::a9bc4453273b2d02648a5cb453195042",
"50|doi_dedup___::5e893dc0cb7624a33f41c9b428bd59f7",
"50|doi_dedup___::c1ecdef48fd9be811a291deed950e1c5",
"50|doi_dedup___::9e93c8f2d97c35de8a6a57a5b53ef283",
"50|dedup_wf_002::d08be0ed27b13d8a880e891e08d093ea",
"50|doi_dedup___::f8d8b3b9eddeca2fc0e3bc9e63996555"),
"Exploring Multi-Scale Map Generalization and Design", "Exploring Multi-Scale Map Generalization and Design",
"This project aims to advance the generalization of multi-scale maps by investigating the impact of different design elements on user experience. The research involves collecting and analyzing data from various sources, including surveys, eye-tracking studies, and user experiments. The goal is to identify best practices for map generalization and design, with a focus on reducing disorientation and improving information retrieval during exploration. The project has led to the development of several datasets, including BasqueRoads, AnchorWhat, and L'Alpe d'Huez, which can be used to benchmark road selection algorithms and topographic map generalization techniques. The research has also resulted in the creation of a Python library, Cartagen4py, for map generalization. The findings of this project have the potential to improve the design and usability of multi-scale maps, making them more effective tools for navigation and information retrieval." "This project aims to advance the generalization of multi-scale maps by investigating the impact of different design elements on user experience. The research involves collecting and analyzing data from various sources, including surveys, eye-tracking studies, and user experiments. The goal is to identify best practices for map generalization and design, with a focus on reducing disorientation and improving information retrieval during exploration. The project has led to the development of several datasets, including BasqueRoads, AnchorWhat, and L'Alpe d'Huez, which can be used to benchmark road selection algorithms and topographic map generalization techniques. The research has also resulted in the creation of a Python library, Cartagen4py, for map generalization. The findings of this project have the potential to improve the design and usability of multi-scale maps, making them more effective tools for navigation and information retrieval."));
));
OtherResearchProduct orp = (OtherResearchProduct) atomicActions.get(0).getPayload(); OtherResearchProduct orp = (OtherResearchProduct) atomicActions.get(0).getPayload();
Relation rel = (Relation) atomicActions.get(1).getPayload(); Relation rel = (Relation) atomicActions.get(1).getPayload();

View File

@ -63,7 +63,6 @@ class BioScholixTest extends AbstractVocabularyTest {
"0000000333457333", "0000000333457333",
"0000000335964515", "0000000335964515",
"0000000302921949", "0000000302921949",
"http://orcid.org/0000-0001-8567-3543", "http://orcid.org/0000-0001-8567-3543",
"http://orcid.org/0000-0001-7868-8528", "http://orcid.org/0000-0001-7868-8528",
"0000-0001-9189-1440", "0000-0001-9189-1440",

View File

@ -915,7 +915,8 @@ class MappersTest {
@Test @Test
void testODFRecord_guidelines4() throws IOException { void testODFRecord_guidelines4() throws IOException {
final String xml = IOUtils.toString(Objects.requireNonNull(getClass().getResourceAsStream("odf_guidelines4.xml"))); final String xml = IOUtils
.toString(Objects.requireNonNull(getClass().getResourceAsStream("odf_guidelines4.xml")));
final List<Oaf> list = new OdfToOafMapper(vocs, false, true).processMdRecord(xml); final List<Oaf> list = new OdfToOafMapper(vocs, false, true).processMdRecord(xml);
final Publication p = (Publication) list.get(0); final Publication p = (Publication) list.get(0);

View File

@ -5,7 +5,6 @@ import java.io.StringReader;
import java.util.*; import java.util.*;
import java.util.stream.Collectors; import java.util.stream.Collectors;
import eu.dnetlib.dhp.schema.solr.PersonTopic;
import org.apache.commons.lang3.StringUtils; import org.apache.commons.lang3.StringUtils;
import org.dom4j.Document; import org.dom4j.Document;
import org.dom4j.DocumentException; import org.dom4j.DocumentException;
@ -40,6 +39,7 @@ import eu.dnetlib.dhp.schema.solr.OpenAccessColor;
import eu.dnetlib.dhp.schema.solr.OpenAccessRoute; import eu.dnetlib.dhp.schema.solr.OpenAccessRoute;
import eu.dnetlib.dhp.schema.solr.Organization; import eu.dnetlib.dhp.schema.solr.Organization;
import eu.dnetlib.dhp.schema.solr.Person; import eu.dnetlib.dhp.schema.solr.Person;
import eu.dnetlib.dhp.schema.solr.PersonTopic;
import eu.dnetlib.dhp.schema.solr.Pid; import eu.dnetlib.dhp.schema.solr.Pid;
import eu.dnetlib.dhp.schema.solr.Project; import eu.dnetlib.dhp.schema.solr.Project;
import eu.dnetlib.dhp.schema.solr.Result; import eu.dnetlib.dhp.schema.solr.Result;
@ -216,8 +216,11 @@ public class ProvisionModelSupport {
} }
private static List<PersonTopic> mapPersonTopics(List<eu.dnetlib.dhp.schema.oaf.PersonTopic> subjects) { private static List<PersonTopic> mapPersonTopics(List<eu.dnetlib.dhp.schema.oaf.PersonTopic> subjects) {
return Optional.ofNullable(subjects) return Optional
.map(ss -> ss.stream() .ofNullable(subjects)
.map(
ss -> ss
.stream()
.map(ProvisionModelSupport::mapPersonTopic) .map(ProvisionModelSupport::mapPersonTopic)
.collect(Collectors.toList())) .collect(Collectors.toList()))
.orElse(null); .orElse(null);