1
0
Fork 0

filter ORCID e MAG identifiers

This commit is contained in:
Michele Artini 2020-05-22 12:25:01 +02:00
parent 9f2d0f1b08
commit dc4621b3cb
4 changed files with 169 additions and 174 deletions

View File

@ -10,7 +10,16 @@ import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.listFields;
import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.oaiIProvenance; import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.oaiIProvenance;
import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.qualifier; import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.qualifier;
import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.structuredProperty; import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.structuredProperty;
import static eu.dnetlib.dhp.schema.common.ModelConstants.*; import static eu.dnetlib.dhp.schema.common.ModelConstants.DATASET_DEFAULT_RESULTTYPE;
import static eu.dnetlib.dhp.schema.common.ModelConstants.DNET_PID_TYPES;
import static eu.dnetlib.dhp.schema.common.ModelConstants.IS_PRODUCED_BY;
import static eu.dnetlib.dhp.schema.common.ModelConstants.ORP_DEFAULT_RESULTTYPE;
import static eu.dnetlib.dhp.schema.common.ModelConstants.OUTCOME;
import static eu.dnetlib.dhp.schema.common.ModelConstants.PRODUCES;
import static eu.dnetlib.dhp.schema.common.ModelConstants.PUBLICATION_DEFAULT_RESULTTYPE;
import static eu.dnetlib.dhp.schema.common.ModelConstants.REPOSITORY_PROVENANCE_ACTIONS;
import static eu.dnetlib.dhp.schema.common.ModelConstants.RESULT_PROJECT;
import static eu.dnetlib.dhp.schema.common.ModelConstants.SOFTWARE_DEFAULT_RESULTTYPE;
import java.util.ArrayList; import java.util.ArrayList;
import java.util.Arrays; import java.util.Arrays;
@ -50,6 +59,8 @@ public abstract class AbstractMdRecordToOafMapper {
protected static final String DATACITE_SCHEMA_KERNEL_4 = "http://datacite.org/schema/kernel-4"; protected static final String DATACITE_SCHEMA_KERNEL_4 = "http://datacite.org/schema/kernel-4";
protected static final String DATACITE_SCHEMA_KERNEL_3 = "http://datacite.org/schema/kernel-3"; protected static final String DATACITE_SCHEMA_KERNEL_3 = "http://datacite.org/schema/kernel-3";
protected static final Qualifier ORCID_PID_TYPE = qualifier("ORCID", "Open Researcher and Contributor ID", DNET_PID_TYPES, DNET_PID_TYPES);
protected static final Qualifier MAG_PID_TYPE = qualifier("MAGIdentifier", "Microsoft Academic Graph Identifier", DNET_PID_TYPES, DNET_PID_TYPES);
protected static final Map<String, String> nsContext = new HashMap<>(); protected static final Map<String, String> nsContext = new HashMap<>();
@ -63,8 +74,7 @@ public abstract class AbstractMdRecordToOafMapper {
nsContext.put("datacite", DATACITE_SCHEMA_KERNEL_3); nsContext.put("datacite", DATACITE_SCHEMA_KERNEL_3);
} }
protected static final Qualifier MAIN_TITLE_QUALIFIER = qualifier( protected static final Qualifier MAIN_TITLE_QUALIFIER = qualifier("main title", "main title", "dnet:dataCite_title", "dnet:dataCite_title");
"main title", "main title", "dnet:dataCite_title", "dnet:dataCite_title");
protected AbstractMdRecordToOafMapper(final Map<String, String> code2name) { protected AbstractMdRecordToOafMapper(final Map<String, String> code2name) {
this.code2name = code2name; this.code2name = code2name;
@ -75,24 +85,18 @@ public abstract class AbstractMdRecordToOafMapper {
DocumentFactory.getInstance().setXPathNamespaceURIs(nsContext); DocumentFactory.getInstance().setXPathNamespaceURIs(nsContext);
final Document doc = DocumentHelper final Document doc = DocumentHelper
.parseText( .parseText(xml.replaceAll(DATACITE_SCHEMA_KERNEL_4, DATACITE_SCHEMA_KERNEL_3));
xml.replaceAll(DATACITE_SCHEMA_KERNEL_4, DATACITE_SCHEMA_KERNEL_3));
final String type = doc.valueOf("//dr:CobjCategory/@type"); final String type = doc.valueOf("//dr:CobjCategory/@type");
final KeyValue collectedFrom = getProvenanceDatasource( final KeyValue collectedFrom = getProvenanceDatasource(doc, "//oaf:collectedFrom/@id", "//oaf:collectedFrom/@name");
doc, "//oaf:collectedFrom/@id", "//oaf:collectedFrom/@name");
if (collectedFrom == null) { if (collectedFrom == null) { return null; }
return null;
}
final KeyValue hostedBy = StringUtils.isBlank(doc.valueOf("//oaf:hostedBy/@id")) final KeyValue hostedBy = StringUtils.isBlank(doc.valueOf("//oaf:hostedBy/@id"))
? collectedFrom ? collectedFrom
: getProvenanceDatasource(doc, "//oaf:hostedBy/@id", "//oaf:hostedBy/@name"); : getProvenanceDatasource(doc, "//oaf:hostedBy/@id", "//oaf:hostedBy/@name");
if (hostedBy == null) { if (hostedBy == null) { return null; }
return null;
}
final DataInfo info = prepareDataInfo(doc); final DataInfo info = prepareDataInfo(doc);
final long lastUpdateTimestamp = new Date().getTime(); final long lastUpdateTimestamp = new Date().getTime();
@ -103,17 +107,13 @@ public abstract class AbstractMdRecordToOafMapper {
} }
} }
private KeyValue getProvenanceDatasource(Document doc, String xpathId, String xpathName) { private KeyValue getProvenanceDatasource(final Document doc, final String xpathId, final String xpathName) {
final String dsId = doc.valueOf(xpathId); final String dsId = doc.valueOf(xpathId);
final String dsName = doc.valueOf(xpathName); final String dsName = doc.valueOf(xpathName);
if (StringUtils.isBlank(dsId) | StringUtils.isBlank(dsName)) { if (StringUtils.isBlank(dsId) | StringUtils.isBlank(dsName)) { return null; }
return null;
}
return keyValue( return keyValue(createOpenaireId(10, dsId, true), dsName);
createOpenaireId(10, dsId, true),
dsName);
} }
protected List<Oaf> createOafs( protected List<Oaf> createOafs(
@ -127,47 +127,47 @@ public abstract class AbstractMdRecordToOafMapper {
final List<Oaf> oafs = new ArrayList<>(); final List<Oaf> oafs = new ArrayList<>();
switch (type.toLowerCase()) { switch (type.toLowerCase()) {
case "publication": case "publication":
final Publication p = new Publication(); final Publication p = new Publication();
populateResultFields(p, doc, collectedFrom, hostedBy, info, lastUpdateTimestamp); populateResultFields(p, doc, collectedFrom, hostedBy, info, lastUpdateTimestamp);
p.setResulttype(PUBLICATION_DEFAULT_RESULTTYPE); p.setResulttype(PUBLICATION_DEFAULT_RESULTTYPE);
p.setJournal(prepareJournal(doc, info)); p.setJournal(prepareJournal(doc, info));
oafs.add(p); oafs.add(p);
break; break;
case "dataset": case "dataset":
final Dataset d = new Dataset(); final Dataset d = new Dataset();
populateResultFields(d, doc, collectedFrom, hostedBy, info, lastUpdateTimestamp); populateResultFields(d, doc, collectedFrom, hostedBy, info, lastUpdateTimestamp);
d.setResulttype(DATASET_DEFAULT_RESULTTYPE); d.setResulttype(DATASET_DEFAULT_RESULTTYPE);
d.setStoragedate(prepareDatasetStorageDate(doc, info)); d.setStoragedate(prepareDatasetStorageDate(doc, info));
d.setDevice(prepareDatasetDevice(doc, info)); d.setDevice(prepareDatasetDevice(doc, info));
d.setSize(prepareDatasetSize(doc, info)); d.setSize(prepareDatasetSize(doc, info));
d.setVersion(prepareDatasetVersion(doc, info)); d.setVersion(prepareDatasetVersion(doc, info));
d.setLastmetadataupdate(prepareDatasetLastMetadataUpdate(doc, info)); d.setLastmetadataupdate(prepareDatasetLastMetadataUpdate(doc, info));
d.setMetadataversionnumber(prepareDatasetMetadataVersionNumber(doc, info)); d.setMetadataversionnumber(prepareDatasetMetadataVersionNumber(doc, info));
d.setGeolocation(prepareDatasetGeoLocations(doc, info)); d.setGeolocation(prepareDatasetGeoLocations(doc, info));
oafs.add(d); oafs.add(d);
break; break;
case "software": case "software":
final Software s = new Software(); final Software s = new Software();
populateResultFields(s, doc, collectedFrom, hostedBy, info, lastUpdateTimestamp); populateResultFields(s, doc, collectedFrom, hostedBy, info, lastUpdateTimestamp);
s.setResulttype(SOFTWARE_DEFAULT_RESULTTYPE); s.setResulttype(SOFTWARE_DEFAULT_RESULTTYPE);
s.setDocumentationUrl(prepareSoftwareDocumentationUrls(doc, info)); s.setDocumentationUrl(prepareSoftwareDocumentationUrls(doc, info));
s.setLicense(prepareSoftwareLicenses(doc, info)); s.setLicense(prepareSoftwareLicenses(doc, info));
s.setCodeRepositoryUrl(prepareSoftwareCodeRepositoryUrl(doc, info)); s.setCodeRepositoryUrl(prepareSoftwareCodeRepositoryUrl(doc, info));
s.setProgrammingLanguage(prepareSoftwareProgrammingLanguage(doc, info)); s.setProgrammingLanguage(prepareSoftwareProgrammingLanguage(doc, info));
oafs.add(s); oafs.add(s);
break; break;
case "": case "":
case "otherresearchproducts": case "otherresearchproducts":
default: default:
final OtherResearchProduct o = new OtherResearchProduct(); final OtherResearchProduct o = new OtherResearchProduct();
populateResultFields(o, doc, collectedFrom, hostedBy, info, lastUpdateTimestamp); populateResultFields(o, doc, collectedFrom, hostedBy, info, lastUpdateTimestamp);
o.setResulttype(ORP_DEFAULT_RESULTTYPE); o.setResulttype(ORP_DEFAULT_RESULTTYPE);
o.setContactperson(prepareOtherResearchProductContactPersons(doc, info)); o.setContactperson(prepareOtherResearchProductContactPersons(doc, info));
o.setContactgroup(prepareOtherResearchProductContactGroups(doc, info)); o.setContactgroup(prepareOtherResearchProductContactGroups(doc, info));
o.setTool(prepareOtherResearchProductTools(doc, info)); o.setTool(prepareOtherResearchProductTools(doc, info));
oafs.add(o); oafs.add(o);
break; break;
} }
if (!oafs.isEmpty()) { if (!oafs.isEmpty()) {
@ -196,23 +196,23 @@ public abstract class AbstractMdRecordToOafMapper {
final String projectId = createOpenaireId(40, originalId, true); final String projectId = createOpenaireId(40, originalId, true);
res res
.add( .add(getRelation(docId, projectId, RESULT_PROJECT, OUTCOME, IS_PRODUCED_BY, collectedFrom, info, lastUpdateTimestamp));
getRelation(
docId, projectId, RESULT_PROJECT, OUTCOME, IS_PRODUCED_BY, collectedFrom, info,
lastUpdateTimestamp));
res res
.add( .add(getRelation(projectId, docId, RESULT_PROJECT, OUTCOME, PRODUCES, collectedFrom, info, lastUpdateTimestamp));
getRelation(
projectId, docId, RESULT_PROJECT, OUTCOME, PRODUCES, collectedFrom, info,
lastUpdateTimestamp));
} }
} }
return res; return res;
} }
protected Relation getRelation(String source, String target, String relType, String subRelType, String relClass, protected Relation getRelation(final String source,
KeyValue collectedFrom, DataInfo info, long lastUpdateTimestamp) { final String target,
final String relType,
final String subRelType,
final String relClass,
final KeyValue collectedFrom,
final DataInfo info,
final long lastUpdateTimestamp) {
final Relation rel = new Relation(); final Relation rel = new Relation();
rel.setRelType(relType); rel.setRelType(relType);
rel.setSubRelType(subRelType); rel.setSubRelType(subRelType);
@ -244,9 +244,7 @@ public abstract class AbstractMdRecordToOafMapper {
r.setOriginalId(Arrays.asList(doc.valueOf("//dri:objIdentifier"))); r.setOriginalId(Arrays.asList(doc.valueOf("//dri:objIdentifier")));
r.setCollectedfrom(Arrays.asList(collectedFrom)); r.setCollectedfrom(Arrays.asList(collectedFrom));
r r
.setPid( .setPid(prepareListStructProps(doc, "//oaf:identifier", "@identifierType", "dnet:pid_types", "dnet:pid_types", info));
prepareListStructProps(
doc, "//oaf:identifier", "@identifierType", "dnet:pid_types", "dnet:pid_types", info));
r.setDateofcollection(doc.valueOf("//dr:dateOfCollection")); r.setDateofcollection(doc.valueOf("//dr:dateOfCollection"));
r.setDateoftransformation(doc.valueOf("//dr:dateOfTransformation")); r.setDateoftransformation(doc.valueOf("//dr:dateOfTransformation"));
r.setExtraInfo(new ArrayList<>()); // NOT PRESENT IN MDSTORES r.setExtraInfo(new ArrayList<>()); // NOT PRESENT IN MDSTORES
@ -289,7 +287,10 @@ public abstract class AbstractMdRecordToOafMapper {
protected abstract Qualifier prepareResourceType(Document doc, DataInfo info); protected abstract Qualifier prepareResourceType(Document doc, DataInfo info);
protected abstract List<Instance> prepareInstances( protected abstract List<Instance> prepareInstances(
Document doc, DataInfo info, KeyValue collectedfrom, KeyValue hostedby); Document doc,
DataInfo info,
KeyValue collectedfrom,
KeyValue hostedby);
protected abstract List<Field<String>> prepareSources(Document doc, DataInfo info); protected abstract List<Field<String>> prepareSources(Document doc, DataInfo info);
@ -314,13 +315,16 @@ public abstract class AbstractMdRecordToOafMapper {
protected abstract List<Author> prepareAuthors(Document doc, DataInfo info); protected abstract List<Author> prepareAuthors(Document doc, DataInfo info);
protected abstract List<Field<String>> prepareOtherResearchProductTools( protected abstract List<Field<String>> prepareOtherResearchProductTools(
Document doc, DataInfo info); Document doc,
DataInfo info);
protected abstract List<Field<String>> prepareOtherResearchProductContactGroups( protected abstract List<Field<String>> prepareOtherResearchProductContactGroups(
Document doc, DataInfo info); Document doc,
DataInfo info);
protected abstract List<Field<String>> prepareOtherResearchProductContactPersons( protected abstract List<Field<String>> prepareOtherResearchProductContactPersons(
Document doc, DataInfo info); Document doc,
DataInfo info);
protected abstract Qualifier prepareSoftwareProgrammingLanguage(Document doc, DataInfo info); protected abstract Qualifier prepareSoftwareProgrammingLanguage(Document doc, DataInfo info);
@ -329,7 +333,8 @@ public abstract class AbstractMdRecordToOafMapper {
protected abstract List<StructuredProperty> prepareSoftwareLicenses(Document doc, DataInfo info); protected abstract List<StructuredProperty> prepareSoftwareLicenses(Document doc, DataInfo info);
protected abstract List<Field<String>> prepareSoftwareDocumentationUrls( protected abstract List<Field<String>> prepareSoftwareDocumentationUrls(
Document doc, DataInfo info); Document doc,
DataInfo info);
protected abstract List<GeoLocation> prepareDatasetGeoLocations(Document doc, DataInfo info); protected abstract List<GeoLocation> prepareDatasetGeoLocations(Document doc, DataInfo info);
@ -357,27 +362,16 @@ public abstract class AbstractMdRecordToOafMapper {
final String sp = n.valueOf("@sp"); final String sp = n.valueOf("@sp");
final String vol = n.valueOf("@vol"); final String vol = n.valueOf("@vol");
final String edition = n.valueOf("@edition"); final String edition = n.valueOf("@edition");
if (StringUtils.isNotBlank(name)) { if (StringUtils.isNotBlank(name)) { return journal(name, issnPrinted, issnOnline, issnLinking, ep, iss, sp, vol, edition, null, null, info); }
return journal(
name,
issnPrinted,
issnOnline,
issnLinking,
ep,
iss,
sp,
vol,
edition,
null,
null,
info);
}
} }
return null; return null;
} }
protected Qualifier prepareQualifier( protected Qualifier prepareQualifier(
final Node node, final String xpath, final String schemeId, final String schemeName) { final Node node,
final String xpath,
final String schemeId,
final String schemeName) {
final String classId = node.valueOf(xpath); final String classId = node.valueOf(xpath);
final String className = code2name.get(classId); final String className = code2name.get(classId);
return qualifier(classId, className, schemeId, schemeName); return qualifier(classId, className, schemeId, schemeName);
@ -401,7 +395,10 @@ public abstract class AbstractMdRecordToOafMapper {
} }
protected List<StructuredProperty> prepareListStructProps( protected List<StructuredProperty> prepareListStructProps(
final Node node, final String xpath, final Qualifier qualifier, final DataInfo info) { final Node node,
final String xpath,
final Qualifier qualifier,
final DataInfo info) {
final List<StructuredProperty> res = new ArrayList<>(); final List<StructuredProperty> res = new ArrayList<>();
for (final Object o : node.selectNodes(xpath)) { for (final Object o : node.selectNodes(xpath)) {
final Node n = (Node) o; final Node n = (Node) o;
@ -411,19 +408,14 @@ public abstract class AbstractMdRecordToOafMapper {
} }
protected List<StructuredProperty> prepareListStructProps( protected List<StructuredProperty> prepareListStructProps(
final Node node, final String xpath, final DataInfo info) { final Node node,
final String xpath,
final DataInfo info) {
final List<StructuredProperty> res = new ArrayList<>(); final List<StructuredProperty> res = new ArrayList<>();
for (final Object o : node.selectNodes(xpath)) { for (final Object o : node.selectNodes(xpath)) {
final Node n = (Node) o; final Node n = (Node) o;
res res
.add( .add(structuredProperty(n.getText(), n.valueOf("@classid"), n.valueOf("@classname"), n.valueOf("@schemeid"), n.valueOf("@schemename"), info));
structuredProperty(
n.getText(),
n.valueOf("@classid"),
n.valueOf("@classname"),
n.valueOf("@schemeid"),
n.valueOf("@schemename"),
info));
} }
return res; return res;
} }
@ -431,9 +423,7 @@ public abstract class AbstractMdRecordToOafMapper {
protected OAIProvenance prepareOAIprovenance(final Document doc) { protected OAIProvenance prepareOAIprovenance(final Document doc) {
final Node n = doc.selectSingleNode("//*[local-name()='provenance']/*[local-name()='originDescription']"); final Node n = doc.selectSingleNode("//*[local-name()='provenance']/*[local-name()='originDescription']");
if (n == null) { if (n == null) { return null; }
return null;
}
final String identifier = n.valueOf("./*[local-name()='identifier']"); final String identifier = n.valueOf("./*[local-name()='identifier']");
final String baseURL = n.valueOf("./*[local-name()='baseURL']"); final String baseURL = n.valueOf("./*[local-name()='baseURL']");
@ -448,10 +438,7 @@ public abstract class AbstractMdRecordToOafMapper {
protected DataInfo prepareDataInfo(final Document doc) { protected DataInfo prepareDataInfo(final Document doc) {
final Node n = doc.selectSingleNode("//oaf:datainfo"); final Node n = doc.selectSingleNode("//oaf:datainfo");
if (n == null) { if (n == null) { return dataInfo(false, null, false, false, REPOSITORY_PROVENANCE_ACTIONS, "0.9"); }
return dataInfo(
false, null, false, false, REPOSITORY_PROVENANCE_ACTIONS, "0.9");
}
final String paClassId = n.valueOf("./oaf:provenanceaction/@classid"); final String paClassId = n.valueOf("./oaf:provenanceaction/@classid");
final String paClassName = n.valueOf("./oaf:provenanceaction/@classname"); final String paClassName = n.valueOf("./oaf:provenanceaction/@classname");
@ -463,13 +450,7 @@ public abstract class AbstractMdRecordToOafMapper {
final Boolean inferred = Boolean.parseBoolean(n.valueOf("./oaf:inferred")); final Boolean inferred = Boolean.parseBoolean(n.valueOf("./oaf:inferred"));
final String trust = n.valueOf("./oaf:trust"); final String trust = n.valueOf("./oaf:trust");
return dataInfo( return dataInfo(deletedbyinference, inferenceprovenance, inferred, false, qualifier(paClassId, paClassName, paSchemeId, paSchemeName), trust);
deletedbyinference,
inferenceprovenance,
inferred,
false,
qualifier(paClassId, paClassName, paSchemeId, paSchemeName),
trust);
} }
protected Field<String> prepareField(final Node node, final String xpath, final DataInfo info) { protected Field<String> prepareField(final Node node, final String xpath, final DataInfo info) {
@ -477,7 +458,9 @@ public abstract class AbstractMdRecordToOafMapper {
} }
protected List<Field<String>> prepareListFields( protected List<Field<String>> prepareListFields(
final Node node, final String xpath, final DataInfo info) { final Node node,
final String xpath,
final DataInfo info) {
return listFields(info, prepareListString(node, xpath)); return listFields(info, prepareListString(node, xpath));
} }

View File

@ -1,10 +1,19 @@
package eu.dnetlib.dhp.oa.graph.raw; package eu.dnetlib.dhp.oa.graph.raw;
import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.*; import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.createOpenaireId;
import static eu.dnetlib.dhp.schema.common.ModelConstants.*; import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.field;
import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.structuredProperty;
import static eu.dnetlib.dhp.schema.common.ModelConstants.DNET_ACCESS_MODES;
import static eu.dnetlib.dhp.schema.common.ModelConstants.DNET_LANGUAGES;
import static eu.dnetlib.dhp.schema.common.ModelConstants.DNET_PUBLICATION_RESOURCE;
import static eu.dnetlib.dhp.schema.common.ModelConstants.IS_RELATED_TO;
import static eu.dnetlib.dhp.schema.common.ModelConstants.PUBLICATION_DATASET;
import static eu.dnetlib.dhp.schema.common.ModelConstants.RESULT_RESULT;
import java.util.*; import java.util.ArrayList;
import java.util.List;
import java.util.Map;
import java.util.stream.Collectors; import java.util.stream.Collectors;
import org.apache.commons.lang3.StringUtils; import org.apache.commons.lang3.StringUtils;
@ -15,8 +24,15 @@ import org.dom4j.Node;
import com.google.common.collect.Lists; import com.google.common.collect.Lists;
import eu.dnetlib.dhp.oa.graph.raw.common.PacePerson; import eu.dnetlib.dhp.oa.graph.raw.common.PacePerson;
import eu.dnetlib.dhp.schema.common.ModelConstants; import eu.dnetlib.dhp.schema.oaf.Author;
import eu.dnetlib.dhp.schema.oaf.*; import eu.dnetlib.dhp.schema.oaf.DataInfo;
import eu.dnetlib.dhp.schema.oaf.Field;
import eu.dnetlib.dhp.schema.oaf.GeoLocation;
import eu.dnetlib.dhp.schema.oaf.Instance;
import eu.dnetlib.dhp.schema.oaf.KeyValue;
import eu.dnetlib.dhp.schema.oaf.Oaf;
import eu.dnetlib.dhp.schema.oaf.Qualifier;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
public class OafToOafMapper extends AbstractMdRecordToOafMapper { public class OafToOafMapper extends AbstractMdRecordToOafMapper {
@ -39,14 +55,22 @@ public class OafToOafMapper extends AbstractMdRecordToOafMapper {
author.setSurname(p.getNormalisedSurname()); author.setSurname(p.getNormalisedSurname());
} }
final String pid = e.attributeValue("nameIdentifier"); final String pid = e.valueOf("./@nameIdentifier");
final String pidType = e.attributeValue("nameIdentifierScheme"); final String type = e.valueOf("./@nameIdentifierScheme")
.trim()
.toUpperCase()
.replaceAll(" ", "")
.replaceAll("_", "");
author.setPid(new ArrayList<>()); author.setPid(new ArrayList<>());
if (StringUtils.isNotBlank(pid) && StringUtils.isNotBlank(pidType)) {
author if (StringUtils.isNotBlank(pid)) {
.getPid() if (type.startsWith("ORCID")) {
.add(structuredProperty(pid, qualifier(pidType, pidType, DNET_PID_TYPES, DNET_PID_TYPES), info)); final String cleanedId = pid.replaceAll("http://orcid.org/", "").replaceAll("https://orcid.org/", "");
author.getPid().add(structuredProperty(cleanedId, ORCID_PID_TYPE, info));
} else if (type.startsWith("MAGID")) {
author.getPid().add(structuredProperty(pid, MAG_PID_TYPE, info));
}
} }
res.add(author); res.add(author);
@ -103,38 +127,29 @@ public class OafToOafMapper extends AbstractMdRecordToOafMapper {
final Instance instance = new Instance(); final Instance instance = new Instance();
instance instance
.setInstancetype( .setInstancetype(prepareQualifier(doc, "//dr:CobjCategory", DNET_PUBLICATION_RESOURCE, DNET_PUBLICATION_RESOURCE));
prepareQualifier(
doc,
"//dr:CobjCategory",
DNET_PUBLICATION_RESOURCE,
DNET_PUBLICATION_RESOURCE));
instance.setCollectedfrom(collectedfrom); instance.setCollectedfrom(collectedfrom);
instance.setHostedby(hostedby); instance.setHostedby(hostedby);
instance.setDateofacceptance(field(doc.valueOf("//oaf:dateAccepted"), info)); instance.setDateofacceptance(field(doc.valueOf("//oaf:dateAccepted"), info));
instance.setDistributionlocation(doc.valueOf("//oaf:distributionlocation")); instance.setDistributionlocation(doc.valueOf("//oaf:distributionlocation"));
instance instance
.setAccessright( .setAccessright(prepareQualifier(doc, "//oaf:accessrights", DNET_ACCESS_MODES, DNET_ACCESS_MODES));
prepareQualifier(doc, "//oaf:accessrights", DNET_ACCESS_MODES, DNET_ACCESS_MODES));
instance.setLicense(field(doc.valueOf("//oaf:license"), info)); instance.setLicense(field(doc.valueOf("//oaf:license"), info));
instance.setRefereed(field(doc.valueOf("//oaf:refereed"), info)); instance.setRefereed(field(doc.valueOf("//oaf:refereed"), info));
instance instance
.setProcessingchargeamount( .setProcessingchargeamount(field(doc.valueOf("//oaf:processingchargeamount"), info));
field(doc.valueOf("//oaf:processingchargeamount"), info));
instance instance
.setProcessingchargecurrency( .setProcessingchargecurrency(field(doc.valueOf("//oaf:processingchargeamount/@currency"), info));
field(doc.valueOf("//oaf:processingchargeamount/@currency"), info));
List<Node> nodes = Lists.newArrayList(doc.selectNodes("//dc:identifier")); final List<Node> nodes = Lists.newArrayList(doc.selectNodes("//dc:identifier"));
instance instance
.setUrl( .setUrl(nodes
nodes .stream()
.stream() .filter(n -> StringUtils.isNotBlank(n.getText()))
.filter(n -> StringUtils.isNotBlank(n.getText())) .map(n -> n.getText().trim())
.map(n -> n.getText().trim()) .filter(u -> u.startsWith("http"))
.filter(u -> u.startsWith("http")) .distinct()
.distinct() .collect(Collectors.toCollection(ArrayList::new)));
.collect(Collectors.toCollection(ArrayList::new)));
return Lists.newArrayList(instance); return Lists.newArrayList(instance);
} }
@ -158,19 +173,22 @@ public class OafToOafMapper extends AbstractMdRecordToOafMapper {
@Override @Override
protected Field<String> prepareSoftwareCodeRepositoryUrl( protected Field<String> prepareSoftwareCodeRepositoryUrl(
final Document doc, final DataInfo info) { final Document doc,
final DataInfo info) {
return null; // NOT PRESENT IN OAF return null; // NOT PRESENT IN OAF
} }
@Override @Override
protected List<StructuredProperty> prepareSoftwareLicenses( protected List<StructuredProperty> prepareSoftwareLicenses(
final Document doc, final DataInfo info) { final Document doc,
final DataInfo info) {
return new ArrayList<>(); // NOT PRESENT IN OAF return new ArrayList<>(); // NOT PRESENT IN OAF
} }
@Override @Override
protected List<Field<String>> prepareSoftwareDocumentationUrls( protected List<Field<String>> prepareSoftwareDocumentationUrls(
final Document doc, final DataInfo info) { final Document doc,
final DataInfo info) {
return new ArrayList<>(); // NOT PRESENT IN OAF return new ArrayList<>(); // NOT PRESENT IN OAF
} }
@ -182,13 +200,15 @@ public class OafToOafMapper extends AbstractMdRecordToOafMapper {
@Override @Override
protected Field<String> prepareDatasetMetadataVersionNumber( protected Field<String> prepareDatasetMetadataVersionNumber(
final Document doc, final DataInfo info) { final Document doc,
final DataInfo info) {
return null; // NOT PRESENT IN OAF return null; // NOT PRESENT IN OAF
} }
@Override @Override
protected Field<String> prepareDatasetLastMetadataUpdate( protected Field<String> prepareDatasetLastMetadataUpdate(
final Document doc, final DataInfo info) { final Document doc,
final DataInfo info) {
return null; // NOT PRESENT IN OAF return null; // NOT PRESENT IN OAF
} }
@ -216,19 +236,22 @@ public class OafToOafMapper extends AbstractMdRecordToOafMapper {
@Override @Override
protected List<Field<String>> prepareOtherResearchProductTools( protected List<Field<String>> prepareOtherResearchProductTools(
final Document doc, final DataInfo info) { final Document doc,
final DataInfo info) {
return new ArrayList<>(); // NOT PRESENT IN OAF return new ArrayList<>(); // NOT PRESENT IN OAF
} }
@Override @Override
protected List<Field<String>> prepareOtherResearchProductContactGroups( protected List<Field<String>> prepareOtherResearchProductContactGroups(
final Document doc, final DataInfo info) { final Document doc,
final DataInfo info) {
return new ArrayList<>(); // NOT PRESENT IN OAF return new ArrayList<>(); // NOT PRESENT IN OAF
} }
@Override @Override
protected List<Field<String>> prepareOtherResearchProductContactPersons( protected List<Field<String>> prepareOtherResearchProductContactPersons(
final Document doc, final DataInfo info) { final Document doc,
final DataInfo info) {
return new ArrayList<>(); // NOT PRESENT IN OAF return new ArrayList<>(); // NOT PRESENT IN OAF
} }
@ -251,15 +274,9 @@ public class OafToOafMapper extends AbstractMdRecordToOafMapper {
final String otherId = createOpenaireId(50, originalId, false); final String otherId = createOpenaireId(50, originalId, false);
res res
.add( .add(getRelation(docId, otherId, RESULT_RESULT, PUBLICATION_DATASET, IS_RELATED_TO, collectedFrom, info, lastUpdateTimestamp));
getRelation(
docId, otherId, RESULT_RESULT, PUBLICATION_DATASET, IS_RELATED_TO, collectedFrom, info,
lastUpdateTimestamp));
res res
.add( .add(getRelation(otherId, docId, RESULT_RESULT, PUBLICATION_DATASET, IS_RELATED_TO, collectedFrom, info, lastUpdateTimestamp));
getRelation(
otherId, docId, RESULT_RESULT, PUBLICATION_DATASET, IS_RELATED_TO, collectedFrom, info,
lastUpdateTimestamp));
} }
} }
return res; return res;

View File

@ -3,13 +3,11 @@ package eu.dnetlib.dhp.oa.graph.raw;
import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.createOpenaireId; import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.createOpenaireId;
import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.field; import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.field;
import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.qualifier;
import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.structuredProperty; import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.structuredProperty;
import static eu.dnetlib.dhp.schema.common.ModelConstants.DNET_ACCESS_MODES; import static eu.dnetlib.dhp.schema.common.ModelConstants.DNET_ACCESS_MODES;
import static eu.dnetlib.dhp.schema.common.ModelConstants.DNET_DATA_CITE_DATE; import static eu.dnetlib.dhp.schema.common.ModelConstants.DNET_DATA_CITE_DATE;
import static eu.dnetlib.dhp.schema.common.ModelConstants.DNET_DATA_CITE_RESOURCE; import static eu.dnetlib.dhp.schema.common.ModelConstants.DNET_DATA_CITE_RESOURCE;
import static eu.dnetlib.dhp.schema.common.ModelConstants.DNET_LANGUAGES; import static eu.dnetlib.dhp.schema.common.ModelConstants.DNET_LANGUAGES;
import static eu.dnetlib.dhp.schema.common.ModelConstants.DNET_PID_TYPES;
import static eu.dnetlib.dhp.schema.common.ModelConstants.DNET_PUBLICATION_RESOURCE; import static eu.dnetlib.dhp.schema.common.ModelConstants.DNET_PUBLICATION_RESOURCE;
import static eu.dnetlib.dhp.schema.common.ModelConstants.HAS_PARTS; import static eu.dnetlib.dhp.schema.common.ModelConstants.HAS_PARTS;
import static eu.dnetlib.dhp.schema.common.ModelConstants.IS_PART_OF; import static eu.dnetlib.dhp.schema.common.ModelConstants.IS_PART_OF;
@ -45,9 +43,6 @@ public class OdfToOafMapper extends AbstractMdRecordToOafMapper {
public static final String HTTP_DX_DOI_PREIFX = "http://dx.doi.org/"; public static final String HTTP_DX_DOI_PREIFX = "http://dx.doi.org/";
public static final Qualifier ORCID_PID_TYPE = qualifier("ORCID", "Open Researcher and Contributor ID", DNET_PID_TYPES, DNET_PID_TYPES);
public static final Qualifier MAG_PID_TYPE = qualifier("MAGIdentifier", "Microsoft Academic Graph Identifier", DNET_PID_TYPES, DNET_PID_TYPES);
public OdfToOafMapper(final Map<String, String> code2name) { public OdfToOafMapper(final Map<String, String> code2name) {
super(code2name); super(code2name);
} }

View File

@ -75,7 +75,7 @@ public class MappersTest {
.get(); .get();
assertEquals("0000-0001-6651-1178", pid.getValue()); assertEquals("0000-0001-6651-1178", pid.getValue());
assertEquals("ORCID", pid.getQualifier().getClassid()); assertEquals("ORCID", pid.getQualifier().getClassid());
assertEquals("ORCID", pid.getQualifier().getClassname()); assertEquals("Open Researcher and Contributor ID", pid.getQualifier().getClassname());
assertEquals(ModelConstants.DNET_PID_TYPES, pid.getQualifier().getSchemeid()); assertEquals(ModelConstants.DNET_PID_TYPES, pid.getQualifier().getSchemeid());
assertEquals(ModelConstants.DNET_PID_TYPES, pid.getQualifier().getSchemename()); assertEquals(ModelConstants.DNET_PID_TYPES, pid.getQualifier().getSchemename());
assertEquals("Votsi,Nefta", author.get().getFullname()); assertEquals("Votsi,Nefta", author.get().getFullname());