Merge branch 'beta' into clean_country

This commit is contained in:
Claudio Atzori 2022-09-19 11:34:02 +02:00
commit e45ec15221
41 changed files with 752 additions and 214 deletions

View File

@ -83,4 +83,10 @@ public class Vocabulary implements Serializable {
.orElse(null);
}
public Qualifier lookup(String id) {
return Optional
.ofNullable(getSynonymAsQualifier(id))
.orElse(getTermAsQualifier(id));
}
}

View File

@ -81,6 +81,13 @@ public class VocabularyGroup implements Serializable {
vocs.put(id.toLowerCase(), new Vocabulary(id, name));
}
public Optional<Vocabulary> find(final String vocId) {
return Optional
.ofNullable(vocId)
.map(String::toLowerCase)
.map(vocs::get);
}
public void addTerm(final String vocId, final String id, final String name) {
if (vocabularyExists(vocId)) {
vocs.get(vocId.toLowerCase()).addTerm(id, name);

View File

@ -1,6 +1,8 @@
package eu.dnetlib.dhp.schema.oaf.utils;
import static eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils.getProvenance;
import java.time.LocalDate;
import java.time.ZoneId;
import java.time.format.DateTimeFormatter;
@ -16,7 +18,6 @@ import com.github.sisyphsu.dateparser.DateParserUtils;
import com.google.common.collect.Lists;
import com.google.common.collect.Sets;
import eu.dnetlib.dhp.common.vocabulary.Vocabulary;
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.common.ModelSupport;
@ -191,8 +192,8 @@ public class GraphCleaningFunctions extends CleaningFunctions {
qualifier("und", "Undetermined", ModelConstants.DNET_LANGUAGES));
}
if (Objects.nonNull(r.getSubject())) {
r
.setSubject(
List<Subject> subjects = Lists
.newArrayList(
r
.getSubject()
.stream()
@ -201,7 +202,18 @@ public class GraphCleaningFunctions extends CleaningFunctions {
.filter(sp -> Objects.nonNull(sp.getQualifier()))
.filter(sp -> StringUtils.isNotBlank(sp.getQualifier().getClassid()))
.map(GraphCleaningFunctions::cleanValue)
.collect(Collectors.toList()));
.collect(
Collectors
.toMap(
s -> Optional
.ofNullable(s.getQualifier())
.map(q -> q.getClassid() + s.getValue())
.orElse(s.getValue()),
Function.identity(),
(s1, s2) -> Collections
.min(Lists.newArrayList(s1, s1), new SubjectProvenanceComparator())))
.values());
r.setSubject(subjects);
}
if (Objects.nonNull(r.getTitle())) {
r
@ -382,14 +394,7 @@ public class GraphCleaningFunctions extends CleaningFunctions {
.filter(p -> StringUtils.isNotBlank(p.getValue()))
.map(p -> {
// hack to distinguish orcid from orcid_pending
String pidProvenance = Optional
.ofNullable(p.getDataInfo())
.map(
d -> Optional
.ofNullable(d.getProvenanceaction())
.map(Qualifier::getClassid)
.orElse(""))
.orElse("");
String pidProvenance = getProvenance(p.getDataInfo());
if (p
.getQualifier()
.getClassid()
@ -520,6 +525,11 @@ public class GraphCleaningFunctions extends CleaningFunctions {
return s;
}
protected static Subject cleanValue(Subject s) {
s.setValue(s.getValue().replaceAll(CLEANING_REGEX, " "));
return s;
}
protected static Field<String> cleanValue(Field<String> s) {
s.setValue(s.getValue().replaceAll(CLEANING_REGEX, " "));
return s;

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.ModelConstants;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.*;
@ -141,7 +142,7 @@ public class OafMapperUtils {
}
public static Qualifier unknown(final String schemeid, final String schemename) {
return qualifier("UNKNOWN", "Unknown", schemeid, schemename);
return qualifier(UNKNOWN, "Unknown", schemeid, schemename);
}
public static AccessRight accessRight(
@ -189,6 +190,17 @@ public class OafMapperUtils {
return q;
}
public static Subject subject(
final String value,
final String classid,
final String classname,
final String schemeid,
final String schemename,
final DataInfo dataInfo) {
return subject(value, qualifier(classid, classname, schemeid, schemename), dataInfo);
}
public static StructuredProperty structuredProperty(
final String value,
final String classid,
@ -200,6 +212,20 @@ public class OafMapperUtils {
return structuredProperty(value, qualifier(classid, classname, schemeid, schemename), dataInfo);
}
public static Subject subject(
final String value,
final Qualifier qualifier,
final DataInfo dataInfo) {
if (value == null) {
return null;
}
final Subject s = new Subject();
s.setValue(value);
s.setQualifier(qualifier);
s.setDataInfo(dataInfo);
return s;
}
public static StructuredProperty structuredProperty(
final String value,
final Qualifier qualifier,
@ -477,4 +503,15 @@ public class OafMapperUtils {
rel.setProperties(properties);
return rel;
}
public static String getProvenance(DataInfo dataInfo) {
return Optional
.ofNullable(dataInfo)
.map(
d -> Optional
.ofNullable(d.getProvenanceaction())
.map(Qualifier::getClassid)
.orElse(""))
.orElse("");
}
}

View File

@ -0,0 +1,46 @@
package eu.dnetlib.dhp.schema.oaf.utils;
import static eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils.getProvenance;
import static org.apache.commons.lang3.StringUtils.isBlank;
import java.util.Comparator;
import eu.dnetlib.dhp.schema.oaf.Subject;
public class SubjectProvenanceComparator implements Comparator<Subject> {
@Override
public int compare(Subject left, Subject right) {
String lProv = getProvenance(left.getDataInfo());
String rProv = getProvenance(right.getDataInfo());
if (isBlank(lProv) && isBlank(rProv))
return 0;
if (isBlank(lProv))
return 1;
if (isBlank(rProv))
return -1;
if (lProv.equals(rProv))
return 0;
if (lProv.toLowerCase().contains("crosswalk"))
return -1;
if (rProv.toLowerCase().contains("crosswalk"))
return 1;
if (lProv.toLowerCase().contains("user"))
return -1;
if (rProv.toLowerCase().contains("user"))
return 1;
if (lProv.toLowerCase().contains("propagation"))
return -1;
if (rProv.toLowerCase().contains("propagation"))
return 1;
if (lProv.toLowerCase().contains("iis"))
return -1;
if (rProv.toLowerCase().contains("iis"))
return 1;
return 0;
}
}

View File

@ -13,6 +13,7 @@ import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
import eu.dnetlib.dhp.schema.oaf.Subject;
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
public class Constants {
@ -58,13 +59,13 @@ public class Constants {
.map((MapFunction<String, R>) value -> OBJECT_MAPPER.readValue(value, clazz), Encoders.bean(clazz));
}
public static StructuredProperty getSubject(String sbj, String classid, String classname,
public static Subject getSubject(String sbj, String classid, String classname,
String diqualifierclassid) {
if (sbj.equals(NULL))
return null;
StructuredProperty sp = new StructuredProperty();
sp.setValue(sbj);
sp
Subject s = new Subject();
s.setValue(sbj);
s
.setQualifier(
OafMapperUtils
.qualifier(
@ -72,7 +73,7 @@ public class Constants {
classname,
ModelConstants.DNET_SUBJECT_TYPOLOGIES,
ModelConstants.DNET_SUBJECT_TYPOLOGIES));
sp
s
.setDataInfo(
OafMapperUtils
.dataInfo(
@ -88,7 +89,7 @@ public class Constants {
ModelConstants.DNET_PROVENANCE_ACTIONS),
""));
return sp;
return s;
}
}

View File

@ -24,6 +24,7 @@ import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.Result;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
import eu.dnetlib.dhp.schema.oaf.Subject;
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
import eu.dnetlib.dhp.utils.DHPUtils;
@ -79,7 +80,7 @@ public class PrepareFOSSparkJob implements Serializable {
HashSet<String> level3 = new HashSet<>();
addLevels(level1, level2, level3, first);
it.forEachRemaining(v -> addLevels(level1, level2, level3, v));
List<StructuredProperty> sbjs = new ArrayList<>();
List<Subject> sbjs = new ArrayList<>();
level1.forEach(l -> sbjs.add(getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID)));
level2.forEach(l -> sbjs.add(getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID)));
level3.forEach(l -> sbjs.add(getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID)));

View File

@ -24,6 +24,7 @@ import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.Result;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
import eu.dnetlib.dhp.schema.oaf.Subject;
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
import eu.dnetlib.dhp.utils.DHPUtils;
@ -73,7 +74,7 @@ public class PrepareSDGSparkJob implements Serializable {
Result r = new Result();
r.setId(DHPUtils.generateUnresolvedIdentifier(k, DOI));
SDGDataModel first = it.next();
List<StructuredProperty> sbjs = new ArrayList<>();
List<Subject> sbjs = new ArrayList<>();
sbjs.add(getSubject(first.getSbj(), SDG_CLASS_ID, SDG_CLASS_NAME, UPDATE_SUBJECT_SDG_CLASS_ID));
it
.forEachRemaining(

View File

@ -19,7 +19,7 @@ import java.time.chrono.ThaiBuddhistDate
import java.time.format.DateTimeFormatter
import java.util.{Date, Locale}
import scala.collection.JavaConverters._
import scala.io.{Codec, Source}
import scala.io.Source
object DataciteToOAFTransformation {
@ -252,7 +252,7 @@ object DataciteToOAFTransformation {
.exists(i => i.getHostedby != null && "figshare".equalsIgnoreCase(i.getHostedby.getValue))
if (hosted_by_figshare) {
r.getInstance().asScala.foreach(i => i.setAccessright(ModelConstants.OPEN_ACCESS_RIGHT()))
val l: List[StructuredProperty] = List()
val l: List[Subject] = List()
r.setSubject(l.asJava)
}
}
@ -492,7 +492,7 @@ object DataciteToOAFTransformation {
subjects
.filter(s => s.subject.nonEmpty)
.map(s =>
OafMapperUtils.structuredProperty(
OafMapperUtils.subject(
s.subject.get,
SUBJ_CLASS,
SUBJ_CLASS,

View File

@ -281,7 +281,7 @@ object BioDBToOAF {
d.setSubject(
subjects
.map(s =>
OafMapperUtils.structuredProperty(
OafMapperUtils.subject(
s,
SUBJ_CLASS,
SUBJ_CLASS,

View File

@ -265,8 +265,8 @@ object PubMedToOaf {
result.setLanguage(term)
}
val subjects: List[StructuredProperty] = article.getSubjects.asScala.map(s =>
OafMapperUtils.structuredProperty(
val subjects: List[Subject] = article.getSubjects.asScala.map(s =>
OafMapperUtils.subject(
s.getValue,
SUBJ_CLASS,
SUBJ_CLASS,

View File

@ -72,7 +72,7 @@ public class ProduceTest {
JavaRDD<Result> tmp = getResultJavaRDD();
List<StructuredProperty> sbjs = tmp
List<Subject> sbjs = tmp
.filter(row -> row.getSubject() != null && row.getSubject().size() > 0)
.flatMap(row -> row.getSubject().iterator())
.collect();
@ -169,7 +169,7 @@ public class ProduceTest {
.getSubject()
.size());
List<StructuredProperty> sbjs = tmp
List<Subject> sbjs = tmp
.filter(row -> row.getId().equals(doi))
.flatMap(row -> row.getSubject().iterator())
.collect();
@ -396,7 +396,7 @@ public class ProduceTest {
.getSubject()
.size());
List<StructuredProperty> sbjs = tmp
List<Subject> sbjs = tmp
.filter(row -> row.getId().equals(doi))
.flatMap(row -> row.getSubject().iterator())
.collect();
@ -508,7 +508,7 @@ public class ProduceTest {
.getSubject()
.size());
List<StructuredProperty> sbjs = tmp
List<Subject> sbjs = tmp
.filter(row -> row.getId().equals(doi))
.flatMap(row -> row.getSubject().iterator())
.collect();
@ -537,7 +537,7 @@ public class ProduceTest {
JavaRDD<Result> tmp = getResultJavaRDDPlusSDG();
List<StructuredProperty> sbjs_sdg = tmp
List<Subject> sbjs_sdg = tmp
.filter(row -> row.getSubject() != null && row.getSubject().size() > 0)
.flatMap(row -> row.getSubject().iterator())
.filter(sbj -> sbj.getQualifier().getClassid().equals(Constants.SDG_CLASS_ID))

View File

@ -26,20 +26,7 @@ import eu.dnetlib.broker.objects.OaBrokerRelatedPublication;
import eu.dnetlib.broker.objects.OaBrokerRelatedSoftware;
import eu.dnetlib.broker.objects.OaBrokerTypedValue;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.Author;
import eu.dnetlib.dhp.schema.oaf.Dataset;
import eu.dnetlib.dhp.schema.oaf.Datasource;
import eu.dnetlib.dhp.schema.oaf.ExternalReference;
import eu.dnetlib.dhp.schema.oaf.Field;
import eu.dnetlib.dhp.schema.oaf.Instance;
import eu.dnetlib.dhp.schema.oaf.Journal;
import eu.dnetlib.dhp.schema.oaf.KeyValue;
import eu.dnetlib.dhp.schema.oaf.Project;
import eu.dnetlib.dhp.schema.oaf.Publication;
import eu.dnetlib.dhp.schema.oaf.Qualifier;
import eu.dnetlib.dhp.schema.oaf.Result;
import eu.dnetlib.dhp.schema.oaf.Software;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
import eu.dnetlib.dhp.schema.oaf.*;
public class ConversionUtils {
@ -71,6 +58,10 @@ public class ConversionUtils {
return sp != null ? new OaBrokerTypedValue(classId(sp.getQualifier()), sp.getValue()) : null;
}
public static OaBrokerTypedValue oafSubjectToBrokerTypedValue(final Subject sp) {
return sp != null ? new OaBrokerTypedValue(classId(sp.getQualifier()), sp.getValue()) : null;
}
public static OaBrokerRelatedDataset oafDatasetToBrokerDataset(final Dataset d) {
if (d == null) {
return null;
@ -115,7 +106,7 @@ public class ConversionUtils {
res.setTitles(structPropList(result.getTitle()));
res.setAbstracts(fieldList(result.getDescription()));
res.setLanguage(classId(result.getLanguage()));
res.setSubjects(structPropTypedList(result.getSubject()));
res.setSubjects(subjectList(result.getSubject()));
res.setCreators(mappedList(result.getAuthor(), ConversionUtils::oafAuthorToBrokerAuthor));
res.setPublicationdate(fieldValue(result.getDateofacceptance()));
res.setPublisher(fieldValue(result.getPublisher()));
@ -304,6 +295,18 @@ public class ConversionUtils {
.collect(Collectors.toList());
}
private static List<OaBrokerTypedValue> subjectList(final List<Subject> list) {
if (list == null) {
return new ArrayList<>();
}
return list
.stream()
.map(ConversionUtils::oafSubjectToBrokerTypedValue)
.filter(Objects::nonNull)
.collect(Collectors.toList());
}
private static <F, T> List<T> mappedList(final List<F> list, final Function<F, T> func) {
if (list == null) {
return new ArrayList<>();

View File

@ -391,6 +391,28 @@ object DoiBoostMappingUtil {
di
}
def createSubject(value: String, classId: String, schemeId: String): Subject = {
val s = new Subject
s.setQualifier(OafMapperUtils.qualifier(classId, classId, schemeId, schemeId))
s.setValue(value)
s
}
def createSubject(
value: String,
classId: String,
className: String,
schemeId: String,
schemeName: String
): Subject = {
val s = new Subject
s.setQualifier(OafMapperUtils.qualifier(classId, className, schemeId, schemeName))
s.setValue(value)
s
}
def createSP(
value: String,
classId: String,

View File

@ -201,7 +201,7 @@ case object Crossref2Oaf {
if (subjectList.nonEmpty) {
result.setSubject(
subjectList.map(s => createSP(s, "keywords", ModelConstants.DNET_SUBJECT_TYPOLOGIES)).asJava
subjectList.map(s => createSubject(s, "keyword", ModelConstants.DNET_SUBJECT_TYPOLOGIES)).asJava
)
}

View File

@ -2,7 +2,7 @@ package eu.dnetlib.doiboost.mag
import eu.dnetlib.dhp.schema.common.ModelConstants
import eu.dnetlib.dhp.schema.oaf.utils.IdentifierFactory
import eu.dnetlib.dhp.schema.oaf.{Instance, Journal, Publication, StructuredProperty}
import eu.dnetlib.dhp.schema.oaf.{Instance, Journal, Publication, StructuredProperty, Subject}
import eu.dnetlib.doiboost.DoiBoostMappingUtil
import eu.dnetlib.doiboost.DoiBoostMappingUtil._
import org.json4s
@ -210,8 +210,8 @@ case object ConversionUtil {
val className = "Microsoft Academic Graph classification"
val classid = "MAG"
val p: List[StructuredProperty] = fieldOfStudy.subjects.flatMap(s => {
val s1 = createSP(
val p: List[Subject] = fieldOfStudy.subjects.flatMap(s => {
val s1 = createSubject(
s.DisplayName,
classid,
className,
@ -219,10 +219,10 @@ case object ConversionUtil {
ModelConstants.DNET_SUBJECT_TYPOLOGIES
)
val di = DoiBoostMappingUtil.generateDataInfo(s.Score.toString)
var resList: List[StructuredProperty] = List(s1)
var resList: List[Subject] = List(s1)
if (s.MainType.isDefined) {
val maintp = s.MainType.get
val s2 = createSP(
val s2 = createSubject(
s.MainType.get,
classid,
className,
@ -232,7 +232,7 @@ case object ConversionUtil {
s2.setDataInfo(di)
resList = resList ::: List(s2)
if (maintp.contains(".")) {
val s3 = createSP(
val s3 = createSubject(
maintp.split("\\.").head,
classid,
className,

View File

@ -290,7 +290,7 @@ public class EOSCTagJobTest {
.stream()
.anyMatch(s -> s.getCode().equals("EOSC::Jupyter Notebook")));
List<StructuredProperty> subjects = tmp
List<Subject> subjects = tmp
.filter(sw -> sw.getId().equals("50|od______1582::6e7a9b21a2feef45673890432af34244"))
.collect()
.get(0)

View File

@ -57,6 +57,11 @@
<artifactId>commons-io</artifactId>
</dependency>
<dependency>
<groupId>commons-validator</groupId>
<artifactId>commons-validator</artifactId>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_2.11</artifactId>

View File

@ -3,16 +3,15 @@ package eu.dnetlib.dhp.oa.graph.clean;
import java.io.Serializable;
import java.util.HashMap;
import java.util.concurrent.atomic.AtomicReference;
import org.apache.commons.lang3.SerializationUtils;
import org.apache.commons.lang3.StringUtils;
import eu.dnetlib.dhp.common.FunctionalInterfaceSupport.SerializableConsumer;
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.AccessRight;
import eu.dnetlib.dhp.schema.oaf.Country;
import eu.dnetlib.dhp.schema.oaf.Qualifier;
import eu.dnetlib.dhp.schema.oaf.Relation;
import eu.dnetlib.dhp.schema.oaf.*;
public class CleaningRuleMap extends HashMap<Class<?>, SerializableConsumer<Object>> implements Serializable {
@ -27,9 +26,36 @@ public class CleaningRuleMap extends HashMap<Class<?>, SerializableConsumer<Obje
mapping.put(AccessRight.class, o -> cleanQualifier(vocabularies, (AccessRight) o));
mapping.put(Country.class, o -> cleanCountry(vocabularies, (Country) o));
mapping.put(Relation.class, o -> cleanRelation(vocabularies, (Relation) o));
mapping.put(Subject.class, o -> cleanSubject(vocabularies, (Subject) o));
return mapping;
}
private static void cleanSubject(VocabularyGroup vocabularies, Subject subject) {
if (cleanSubjectForVocabulary(ModelConstants.DNET_SUBJECT_FOS_CLASSID, vocabularies, subject)) {
return;
} else {
// TODO cleaning based on different subject vocabs can be added here
}
}
private static boolean cleanSubjectForVocabulary(String vocabularyId, VocabularyGroup vocabularies,
Subject subject) {
AtomicReference<Boolean> modified = new AtomicReference<>(false);
vocabularies.find(vocabularyId).ifPresent(vocabulary -> {
if (!ModelConstants.DNET_SUBJECT_KEYWORD.equalsIgnoreCase(subject.getQualifier().getClassid())) {
return;
}
Qualifier newValue = vocabulary.lookup(subject.getValue());
if (!ModelConstants.UNKNOWN.equals(newValue.getClassid())) {
subject.setValue(newValue.getClassid());
subject.getQualifier().setClassid(vocabularyId);
subject.getQualifier().setClassname(vocabulary.getName());
modified.set(true);
}
});
return modified.get();
}
private static void cleanRelation(VocabularyGroup vocabularies, Relation r) {
if (vocabularies.vocabularyExists(ModelConstants.DNET_RELATION_SUBRELTYPE)) {
Qualifier newValue = vocabularies.lookup(ModelConstants.DNET_RELATION_SUBRELTYPE, r.getSubRelType());

View File

@ -8,20 +8,18 @@ import static eu.dnetlib.dhp.schema.common.ModelConstants.PRODUCES;
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.UNKNOWN;
import static eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils.createOpenaireId;
import static eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils.dataInfo;
import static eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils.field;
import static eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils.journal;
import static eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils.keyValue;
import static eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils.listFields;
import static eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils.oaiIProvenance;
import static eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils.qualifier;
import static eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils.structuredProperty;
import static eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils.*;
import java.net.MalformedURLException;
import java.net.URL;
import java.util.*;
import java.util.stream.Collectors;
import org.apache.commons.lang3.StringUtils;
import org.apache.commons.validator.routines.UrlValidator;
import org.dom4j.*;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.google.common.collect.Lists;
import com.google.common.collect.Sets;
@ -29,26 +27,7 @@ import com.google.common.collect.Sets;
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.AccessRight;
import eu.dnetlib.dhp.schema.oaf.Author;
import eu.dnetlib.dhp.schema.oaf.Context;
import eu.dnetlib.dhp.schema.oaf.DataInfo;
import eu.dnetlib.dhp.schema.oaf.Dataset;
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.Journal;
import eu.dnetlib.dhp.schema.oaf.KeyValue;
import eu.dnetlib.dhp.schema.oaf.OAIProvenance;
import eu.dnetlib.dhp.schema.oaf.Oaf;
import eu.dnetlib.dhp.schema.oaf.OafEntity;
import eu.dnetlib.dhp.schema.oaf.OtherResearchProduct;
import eu.dnetlib.dhp.schema.oaf.Publication;
import eu.dnetlib.dhp.schema.oaf.Qualifier;
import eu.dnetlib.dhp.schema.oaf.Relation;
import eu.dnetlib.dhp.schema.oaf.Result;
import eu.dnetlib.dhp.schema.oaf.Software;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
import eu.dnetlib.dhp.schema.oaf.*;
import eu.dnetlib.dhp.schema.oaf.utils.IdentifierFactory;
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
@ -77,6 +56,8 @@ public abstract class AbstractMdRecordToOafMapper {
protected static final Map<String, String> nsContext = new HashMap<>();
private static final Logger log = LoggerFactory.getLogger(AbstractMdRecordToOafMapper.class);
static {
nsContext.put("dr", "http://www.driver-repository.eu/namespace/dr");
nsContext.put("dri", "http://www.driver-repository.eu/namespace/dri");
@ -103,40 +84,44 @@ public abstract class AbstractMdRecordToOafMapper {
this.forceOriginalId = false;
}
public List<Oaf> processMdRecord(final String xml) throws DocumentException {
public List<Oaf> processMdRecord(final String xml) {
DocumentFactory.getInstance().setXPathNamespaceURIs(nsContext);
try {
final Document doc = DocumentHelper
.parseText(
xml
.replaceAll(DATACITE_SCHEMA_KERNEL_4, DATACITE_SCHEMA_KERNEL_3)
.replaceAll(DATACITE_SCHEMA_KERNEL_4_SLASH, DATACITE_SCHEMA_KERNEL_3)
.replaceAll(DATACITE_SCHEMA_KERNEL_3_SLASH, DATACITE_SCHEMA_KERNEL_3));
final Document doc = DocumentHelper
.parseText(
xml
.replaceAll(DATACITE_SCHEMA_KERNEL_4, DATACITE_SCHEMA_KERNEL_3)
.replaceAll(DATACITE_SCHEMA_KERNEL_4_SLASH, DATACITE_SCHEMA_KERNEL_3)
.replaceAll(DATACITE_SCHEMA_KERNEL_3_SLASH, DATACITE_SCHEMA_KERNEL_3));
final KeyValue collectedFrom = getProvenanceDatasource(
doc, "//oaf:collectedFrom/@id", "//oaf:collectedFrom/@name");
final KeyValue collectedFrom = getProvenanceDatasource(
doc, "//oaf:collectedFrom/@id", "//oaf:collectedFrom/@name");
if (collectedFrom == null) {
return Lists.newArrayList();
}
if (collectedFrom == null) {
final KeyValue hostedBy = StringUtils.isBlank(doc.valueOf("//oaf:hostedBy/@id"))
? collectedFrom
: getProvenanceDatasource(doc, "//oaf:hostedBy/@id", "//oaf:hostedBy/@name");
if (hostedBy == null) {
return Lists.newArrayList();
}
final DataInfo info = prepareDataInfo(doc, invisible);
final long lastUpdateTimestamp = new Date().getTime();
final List<Instance> instances = prepareInstances(doc, info, collectedFrom, hostedBy);
final String type = getResultType(doc, instances);
return createOafs(doc, type, instances, collectedFrom, info, lastUpdateTimestamp);
} catch (DocumentException e) {
log.error("Error with record:\n" + xml);
return Lists.newArrayList();
}
final KeyValue hostedBy = StringUtils.isBlank(doc.valueOf("//oaf:hostedBy/@id"))
? collectedFrom
: getProvenanceDatasource(doc, "//oaf:hostedBy/@id", "//oaf:hostedBy/@name");
if (hostedBy == null) {
return Lists.newArrayList();
}
final DataInfo info = prepareDataInfo(doc, invisible);
final long lastUpdateTimestamp = new Date().getTime();
final List<Instance> instances = prepareInstances(doc, info, collectedFrom, hostedBy);
final String type = getResultType(doc, instances);
return createOafs(doc, type, instances, collectedFrom, info, lastUpdateTimestamp);
}
protected String getResultType(final Document doc, final List<Instance> instances) {
@ -411,7 +396,7 @@ public abstract class AbstractMdRecordToOafMapper {
protected abstract List<StructuredProperty> prepareTitles(Document doc, DataInfo info);
protected abstract List<StructuredProperty> prepareSubjects(Document doc, DataInfo info);
protected abstract List<Subject> prepareSubjects(Document doc, DataInfo info);
protected abstract Qualifier prepareLanguages(Document doc);
@ -559,6 +544,22 @@ public abstract class AbstractMdRecordToOafMapper {
return res;
}
protected List<Subject> prepareSubjectList(
final Node node,
final String xpath,
final DataInfo info) {
final List<Subject> res = new ArrayList<>();
for (final Object o : node.selectNodes(xpath)) {
final Node n = (Node) o;
res
.add(
subject(
n.getText(), n.valueOf("@classid"), n.valueOf("@classname"), n.valueOf("@schemeid"),
n.valueOf("@schemename"), info));
}
return res;
}
protected OAIProvenance prepareOAIprovenance(final Document doc) {
final Node n = doc.selectSingleNode("//*[local-name()='provenance']/*[local-name()='originDescription']");
@ -620,4 +621,15 @@ public abstract class AbstractMdRecordToOafMapper {
return res;
}
protected Set<String> validateUrl(Collection<String> url) {
UrlValidator urlValidator = UrlValidator.getInstance();
if (Objects.isNull(url)) {
return new HashSet<>();
}
return url
.stream()
.filter(u -> urlValidator.isValid(u))
.collect(Collectors.toCollection(HashSet::new));
}
}

View File

@ -16,6 +16,9 @@ import org.apache.hadoop.io.compress.GzipCodec;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.rdd.RDD;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.SaveMode;
import org.apache.spark.sql.SparkSession;
import org.dom4j.DocumentException;
import org.slf4j.Logger;
@ -127,8 +130,8 @@ public class GenerateEntitiesApplication {
.sequenceFile(sp, Text.class, Text.class)
.map(k -> new Tuple2<>(k._1().toString(), k._2().toString()))
.map(k -> convertToListOaf(k._1(), k._2(), shouldHashId, vocs))
.filter(Objects::nonNull)
.flatMap(List::iterator));
.flatMap(List::iterator)
.filter(Objects::nonNull));
}
switch (mode) {
@ -155,11 +158,11 @@ public class GenerateEntitiesApplication {
.saveAsTextFile(targetPath, GzipCodec.class);
}
private static List<Oaf> convertToListOaf(
public static List<Oaf> convertToListOaf(
final String id,
final String s,
final boolean shouldHashId,
final VocabularyGroup vocs) throws DocumentException {
final VocabularyGroup vocs) {
final String type = StringUtils.substringAfter(id, ":");
switch (type.toLowerCase()) {
@ -200,8 +203,7 @@ public class GenerateEntitiesApplication {
try {
return OBJECT_MAPPER.readValue(s, clazz);
} catch (final Exception e) {
log.error("Error parsing object of class: {}", clazz);
log.error(s);
log.error("Error parsing object of class: {}:\n{}", clazz, s);
throw new IllegalArgumentException(e);
}
}

View File

@ -84,8 +84,8 @@ public class OafToOafMapper extends AbstractMdRecordToOafMapper {
}
@Override
protected List<StructuredProperty> prepareSubjects(final Document doc, final DataInfo info) {
return prepareListStructProps(doc, "//dc:subject", info);
protected List<Subject> prepareSubjects(final Document doc, final DataInfo info) {
return prepareSubjectList(doc, "//dc:subject", info);
}
@Override
@ -159,22 +159,25 @@ public class OafToOafMapper extends AbstractMdRecordToOafMapper {
.setProcessingchargecurrency(field(doc.valueOf("//oaf:processingchargeamount/@currency"), info));
final List<Node> nodes = Lists.newArrayList(doc.selectNodes("//dc:identifier"));
instance
.setUrl(
nodes
.stream()
.filter(n -> StringUtils.isNotBlank(n.getText()))
.map(n -> n.getText().trim())
.filter(u -> u.startsWith("http"))
.map(s -> {
try {
return URLDecoder.decode(s, "UTF-8");
} catch (Throwable t) {
return s;
}
})
.distinct()
.collect(Collectors.toCollection(ArrayList::new)));
final List<String> url = nodes
.stream()
.filter(n -> StringUtils.isNotBlank(n.getText()))
.map(n -> n.getText().trim())
.filter(u -> u.startsWith("http"))
.map(s -> {
try {
return URLDecoder.decode(s, "UTF-8");
} catch (Throwable t) {
return s;
}
})
.distinct()
.collect(Collectors.toCollection(ArrayList::new));
final Set<String> validUrl = validateUrl(url);
if (!validUrl.isEmpty()) {
instance.setUrl(new ArrayList<>());
instance.getUrl().addAll(validUrl);
}
return Lists.newArrayList(instance);
}

View File

@ -6,11 +6,14 @@ import static eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils.*;
import static eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils.structuredProperty;
import java.io.UnsupportedEncodingException;
import java.net.MalformedURLException;
import java.net.URL;
import java.net.URLDecoder;
import java.util.*;
import java.util.stream.Collectors;
import org.apache.commons.lang3.StringUtils;
import org.apache.commons.validator.routines.UrlValidator;
import org.dom4j.Document;
import org.dom4j.Element;
import org.dom4j.Node;
@ -171,23 +174,31 @@ public class OdfToOafMapper extends AbstractMdRecordToOafMapper {
for (final Object o : doc.selectNodes("//*[local-name()='identifier' and ./@identifierType='landingPage']")) {
url.add(trimAndDecodeUrl(((Node) o).getText().trim()));
}
for (final Object o : doc
.selectNodes("//*[local-name()='alternateIdentifier' and ./@alternateIdentifierType='DOI']")) {
url.add(HTTP_DOI_PREIFX + ((Node) o).getText().trim());
Set<String> validUrl = validateUrl(url);
if (validUrl.stream().noneMatch(s -> s.contains("doi.org"))) {
for (final Object o : doc
.selectNodes("//*[local-name()='alternateIdentifier' and ./@alternateIdentifierType='DOI']")) {
validUrl.add(HTTP_DOI_PREIFX + ((Node) o).getText().trim());
}
for (final Object o : doc.selectNodes("//*[local-name()='identifier' and ./@identifierType='DOI']")) {
validUrl.add(HTTP_DOI_PREIFX + ((Node) o).getText().trim());
}
}
for (final Object o : doc.selectNodes("//*[local-name()='identifier' and ./@identifierType='DOI']")) {
url.add(HTTP_DOI_PREIFX + ((Node) o).getText().trim());
}
for (final Object o : doc
if (validUrl.stream().noneMatch(s -> s.contains("hdl.handle.net"))) {
for (final Object o : doc
.selectNodes("//*[local-name()='alternateIdentifier' and ./@alternateIdentifierType='Handle']")) {
url.add(HTTP_HANDLE_PREIFX + ((Node) o).getText().trim());
validUrl.add(HTTP_HANDLE_PREIFX + ((Node) o).getText().trim());
}
for (final Object o : doc.selectNodes("//*[local-name()='identifier' and ./@identifierType='Handle']")) {
validUrl.add(HTTP_HANDLE_PREIFX + ((Node) o).getText().trim());
}
}
for (final Object o : doc.selectNodes("//*[local-name()='identifier' and ./@identifierType='Handle']")) {
url.add(HTTP_HANDLE_PREIFX + ((Node) o).getText().trim());
}
if (!url.isEmpty()) {
if (!validUrl.isEmpty()) {
instance.setUrl(new ArrayList<>());
instance.getUrl().addAll(url);
instance.getUrl().addAll(validUrl);
}
return Arrays.asList(instance);
}
@ -257,8 +268,8 @@ public class OdfToOafMapper extends AbstractMdRecordToOafMapper {
}
@Override
protected List<StructuredProperty> prepareSubjects(final Document doc, final DataInfo info) {
return prepareListStructProps(doc, "//*[local-name()='subject']", info);
protected List<Subject> prepareSubjects(final Document doc, final DataInfo info) {
return prepareSubjectList(doc, "//*[local-name()='subject']", info);
}
@Override

View File

@ -0,0 +1,108 @@
package eu.dnetlib.dhp.oa.graph.raw;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import java.util.Arrays;
import java.util.List;
import java.util.Objects;
import java.util.Optional;
import java.util.stream.Collectors;
import org.apache.commons.io.IOUtils;
import org.apache.hadoop.io.Text;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.rdd.RDD;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.SaveMode;
import org.apache.spark.sql.SparkSession;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup;
import eu.dnetlib.dhp.schema.oaf.Oaf;
import eu.dnetlib.dhp.utils.ISLookupClientFactory;
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
import scala.Tuple2;
public class VerifyRecordsApplication {
private static final Logger log = LoggerFactory.getLogger(VerifyRecordsApplication.class);
public static void main(final String[] args) throws Exception {
final ArgumentApplicationParser parser = new ArgumentApplicationParser(
IOUtils
.toString(
VerifyRecordsApplication.class
.getResourceAsStream("/eu/dnetlib/dhp/oa/graph/verify_records_parameters.json")));
parser.parseArgument(args);
final Boolean isSparkSessionManaged = Optional
.ofNullable(parser.get("isSparkSessionManaged"))
.map(Boolean::valueOf)
.orElse(Boolean.TRUE);
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
final String sourcePaths = parser.get("sourcePaths");
log.info("sourcePaths: {}", sourcePaths);
final String invalidPath = parser.get("invalidPath");
log.info("invalidPath: {}", invalidPath);
final String isLookupUrl = parser.get("isLookupUrl");
log.info("isLookupUrl: {}", isLookupUrl);
final ISLookUpService isLookupService = ISLookupClientFactory.getLookUpService(isLookupUrl);
final VocabularyGroup vocs = VocabularyGroup.loadVocsFromIS(isLookupService);
final SparkConf conf = new SparkConf();
runWithSparkSession(conf, isSparkSessionManaged, spark -> {
HdfsSupport.remove(invalidPath, spark.sparkContext().hadoopConfiguration());
validateRecords(spark, sourcePaths, invalidPath, vocs);
});
}
private static void validateRecords(SparkSession spark, String sourcePaths, String invalidPath,
VocabularyGroup vocs) {
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
final List<String> existingSourcePaths = Arrays
.stream(sourcePaths.split(","))
.filter(p -> HdfsSupport.exists(p, sc.hadoopConfiguration()))
.collect(Collectors.toList());
log.info("Verify records in files:");
existingSourcePaths.forEach(log::info);
for (final String sp : existingSourcePaths) {
RDD<String> invalidRecords = sc
.sequenceFile(sp, Text.class, Text.class)
.map(k -> tryApplyMapping(k._1().toString(), k._2().toString(), true, vocs))
.filter(Objects::nonNull)
.rdd();
spark
.createDataset(invalidRecords, Encoders.STRING())
.write()
.mode(SaveMode.Append)
.option("compression", "gzip")
.text(invalidPath);
}
}
private static String tryApplyMapping(
final String id,
final String xmlRecord,
final boolean shouldHashId,
final VocabularyGroup vocs) {
final List<Oaf> oaf = GenerateEntitiesApplication.convertToListOaf(id, xmlRecord, shouldHashId, vocs);
if (Optional.ofNullable(oaf).map(List::isEmpty).orElse(false)) {
return xmlRecord;
}
return null;
}
}

View File

@ -4,6 +4,7 @@ package eu.dnetlib.dhp.oa.graph.raw.common;
import java.io.Closeable;
import java.io.IOException;
import java.util.Arrays;
import java.util.List;
import java.util.Set;
import java.util.concurrent.atomic.AtomicInteger;
import java.util.stream.Collectors;
@ -24,8 +25,11 @@ import org.apache.http.impl.client.HttpClients;
import com.fasterxml.jackson.core.JsonProcessingException;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup;
import eu.dnetlib.dhp.oa.graph.raw.OafToOafMapper;
import eu.dnetlib.dhp.oa.graph.raw.OdfToOafMapper;
import eu.dnetlib.dhp.schema.mdstore.MDStoreWithInfo;
import eu.dnetlib.dhp.schema.oaf.Oaf;
import eu.dnetlib.dhp.schema.oaf.*;
import eu.dnetlib.dhp.utils.DHPUtils;
public class AbstractMigrationApplication implements Closeable {

View File

@ -446,10 +446,34 @@
<join name="wait_import" to="fork_generate_entities"/>
<fork name="fork_generate_entities">
<path start="GenerateEntities_claim"/>
<path start="GenerateEntities"/>
<path start="VerifyRecords_claim"/>
<path start="VerifyRecords"/>
</fork>
<action name="VerifyRecords_claim">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>VerifyRecords_claim</name>
<class>eu.dnetlib.dhp.oa.graph.raw.VerifyRecordsApplication</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory ${sparkExecutorMemory}
--executor-cores ${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--sourcePaths</arg><arg>${contentPath}/db_claims,${contentPath}/oaf_claims,${contentPath}/odf_claims</arg>
<arg>--invalidPath</arg><arg>${workingDir}/invalid_records_claim</arg>
<arg>--isLookupUrl</arg><arg>${isLookupUrl}</arg>
</spark>
<ok to="GenerateEntities_claim"/>
<error to="Kill"/>
</action>
<action name="GenerateEntities_claim">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
@ -499,6 +523,30 @@
<error to="Kill"/>
</action>
<action name="VerifyRecords">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>VerifyRecords</name>
<class>eu.dnetlib.dhp.oa.graph.raw.VerifyRecordsApplication</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory ${sparkExecutorMemory}
--executor-cores ${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--sourcePaths</arg><arg>${contentPath}/db_openaire,${contentPath}/db_openorgs,${contentPath}/oaf_records,${contentPath}/odf_records,${contentPath}/oaf_records_hdfs,${contentPath}/odf_records_hdfs,${contentPath}/oaf_records_invisible</arg>
<arg>--invalidPath</arg><arg>${workingDir}/invalid_records</arg>
<arg>--isLookupUrl</arg><arg>${isLookupUrl}</arg>
</spark>
<ok to="GenerateEntities"/>
<error to="Kill"/>
</action>
<action name="GenerateEntities">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>

View File

@ -0,0 +1,26 @@
[
{
"paramName": "issm",
"paramLongName": "isSparkSessionManaged",
"paramDescription": "when true will stop SparkSession after job execution",
"paramRequired": false
},
{
"paramName": "s",
"paramLongName": "sourcePaths",
"paramDescription": "the HDFS source paths which contains the sequential file (comma separated)",
"paramRequired": true
},
{
"paramName": "i",
"paramLongName": "invalidPath",
"paramDescription": "the path of the invalid records file",
"paramRequired": false
},
{
"paramName": "isu",
"paramLongName": "isLookupUrl",
"paramDescription": "the url of the ISLookupService",
"paramRequired": true
}
]

View File

@ -251,6 +251,33 @@ public class GraphCleaningFunctionsTest {
pid.getQualifier().getClassname()));
});
assertNotNull(p_cleaned.getSubject());
List<Subject> fos_subjects = p_cleaned
.getSubject()
.stream()
.filter(s -> ModelConstants.DNET_SUBJECT_FOS_CLASSID.equals(s.getQualifier().getClassid()))
.collect(Collectors.toList());
assertNotNull(fos_subjects);
assertEquals(2, fos_subjects.size());
assertTrue(
fos_subjects
.stream()
.anyMatch(
s -> "0101 mathematics".equals(s.getValue()) &
ModelConstants.DNET_SUBJECT_FOS_CLASSID.equals(s.getQualifier().getClassid()) &
"sysimport:crosswalk:datasetarchive"
.equals(s.getDataInfo().getProvenanceaction().getClassid())));
assertTrue(
fos_subjects
.stream()
.anyMatch(
s -> "0102 computer and information sciences".equals(s.getValue()) &
ModelConstants.DNET_SUBJECT_FOS_CLASSID.equals(s.getQualifier().getClassid())));
// TODO add more assertions to verity the cleaned values
System.out.println(MAPPER.writeValueAsString(p_cleaned));
}

View File

@ -21,7 +21,6 @@ import org.junit.jupiter.api.extension.ExtendWith;
import org.mockito.Mock;
import org.mockito.junit.jupiter.MockitoExtension;
import com.fasterxml.jackson.core.JsonProcessingException;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup;
@ -928,7 +927,8 @@ class MappersTest {
@Test
void testROHub2() throws IOException, DocumentException {
final String xml = IOUtils.toString(Objects.requireNonNull(getClass().getResourceAsStream("rohub-modified.xml")));
final String xml = IOUtils
.toString(Objects.requireNonNull(getClass().getResourceAsStream("rohub-modified.xml")));
final List<Oaf> list = new OdfToOafMapper(vocs, false, true).processMdRecord(xml);
System.out.println("***************");
System.out.println(new ObjectMapper().writeValueAsString(list));
@ -947,6 +947,15 @@ class MappersTest {
}
@Test
void testNotWellFormed() throws IOException {
final String xml = IOUtils
.toString(Objects.requireNonNull(getClass().getResourceAsStream("oaf_notwellformed.xml")));
final List<Oaf> actual = new OafToOafMapper(vocs, false, true).processMdRecord(xml);
assertNotNull(actual);
assertTrue(actual.isEmpty());
}
private void assertValidId(final String id) {
// System.out.println(id);

View File

@ -251,6 +251,18 @@ class MigrateDbEntitiesApplicationTest {
assertValidId(r2.getSource());
assertEquals(r1.getSource(), r2.getTarget());
assertEquals(r2.getSource(), r1.getTarget());
assertTrue(r1.getSource().startsWith("10|"));
assertTrue(r1.getTarget().startsWith("20|"));
assertEquals(ModelConstants.DATASOURCE_ORGANIZATION, r1.getRelType());
assertEquals(ModelConstants.DATASOURCE_ORGANIZATION, r2.getRelType());
assertEquals(ModelConstants.PROVISION, r1.getSubRelType());
assertEquals(ModelConstants.PROVISION, r2.getSubRelType());
assertEquals(ModelConstants.IS_PROVIDED_BY, r1.getRelClass());
assertEquals(ModelConstants.PROVIDES, r2.getRelClass());
}
@Test

View File

@ -743,12 +743,12 @@
"trust": "0.9"
},
"qualifier": {
"classid": "",
"classname": "",
"schemeid": "",
"schemename": ""
"classid": "keyword",
"classname": "keyword",
"schemeid": "dnet:subject_classification_typologies",
"schemename": "dnet:subject_classification_typologies"
},
"value": "infrared detectors"
"value": "FOS: Mathematics"
},
{
"dataInfo": {
@ -765,12 +765,12 @@
"trust": "0.9"
},
"qualifier": {
"classid": "",
"classname": "",
"schemeid": "",
"schemename": ""
"classid": "keyword",
"classname": "keyword",
"schemeid": "dnet:subject_classification_typologies",
"schemename": "dnet:subject_classification_typologies"
},
"value": "lens antennas"
"value": "FOS: Computer and information sciences"
},
{
"dataInfo": {
@ -787,12 +787,34 @@
"trust": "0.9"
},
"qualifier": {
"classid": "",
"classname": "",
"schemeid": "",
"schemename": ""
"classid": "keyword",
"classname": "keyword",
"schemeid": "dnet:subject_classification_typologies",
"schemename": "dnet:subject_classification_typologies"
},
"value": "silicon"
"value": "0101 mathematics"
},
{
"dataInfo": {
"deletedbyinference": false,
"inferenceprovenance": "",
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "subject:fos",
"classname": "subject:fos",
"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": "0101 mathematics"
},
{
"dataInfo": {

View File

@ -1243,4 +1243,6 @@ dnet:relation_relClass @=@ IsSupplementTo @=@ isSupplementTo
dnet:relation_relClass @=@ IsSupplementedBy @=@ isSupplementedBy
dnet:relation_relClass @=@ IsRelatedTo @=@ isRelatedTo
dnet:relation_subRelType @=@ relationship @=@ publicationDataset
dnet:provenanceActions @=@ iis @=@ erroneous label to be cleaned
dnet:provenanceActions @=@ iis @=@ erroneous label to be cleaned
FOS @=@ 0101 mathematics @=@ FOS: Mathematics
FOS @=@ 0102 computer and information sciences @=@ FOS: Computer and information sciences

View File

@ -1118,4 +1118,7 @@ dnet:relation_subRelType @=@ dnet:relation_subRelType @=@ relationship @=@ relat
dnet:relation_subRelType @=@ dnet:relation_subRelType @=@ review @=@ review
dnet:relation_subRelType @=@ dnet:relation_subRelType @=@ similarity @=@ similarity
dnet:relation_subRelType @=@ dnet:relation_subRelType @=@ supplement @=@ supplement
dnet:relation_subRelType @=@ dnet:relation_subRelType @=@ version @=@ version
dnet:relation_subRelType @=@ dnet:relation_subRelType @=@ version @=@ version
FOS @=@ Fields of Science and Technology classification @=@ 0101 mathematics @=@ 0101 mathematics
FOS @=@ Fields of Science and Technology classification @=@ 0102 computer and information sciences @=@ 0102 computer and information sciences
FOS @=@ Fields of Science and Technology classification @=@ 0103 physical sciences @=@ 0103 physical sciences

View File

@ -0,0 +1,70 @@
<?xml version="1.0" encoding="UTF-8"?>
<record xmlns:dc="http://purl.org/dc/elements/1.1/"
xmlns:dr="http://www.driver-repository.eu/namespace/dr"
xmlns:dri="http://www.driver-repository.eu/namespace/dri"
xmlns:oaf="http://namespace.openaire.eu/oaf"
xmlns:oai="http://www.openarchives.org/OAI/2.0/"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
<header xmlns="http://namespace.openaire.eu/">
<dri:objIdentifier>jairo_______::000012e58ed836576ef2a0d38b0f726f</dri:objIdentifier>
<dri:recordIdentifier>oai:irdb.nii.ac.jp:01221:0000010198</dri:recordIdentifier>
<dri:dateOfCollection/>
<dri:mdFormat/>
<dri:mdFormatInterpretation/>
<dri:repositoryId/>
<dr:objectIdentifier/>
<dr:dateOfCollection>2021-05-10T11:31:09.424Z</dr:dateOfCollection>
<dr:dateOfTransformation>2021-06-03T01:45:42.536Z</dr:dateOfTransformation>
<oaf:datasourceprefix>jairo_______</oaf:datasourceprefix>
</header>
<metadata xmlns="http://namespace.openaire.eu/">
<dc:title>多項式GCDを用いた復号法に関する研究<dc:title>
<dc:creator>上原, 剛</dc:creator>
<dc:creator>甲斐, 博</dc:creator>
<dc:creator>野田, 松太郎</dc:creator>
<dc:format>application/pdf</dc:format>
<dc:identifier>http://hdl.handle.net/2433/25934</dc:identifier>
<dc:language>jpn</dc:language>
<dc:publisher>京都大学数理解析研究所</dc:publisher>
<dc:subject classid="ndc" classname="ndc"
schemeid="dnet:subject_classification_typologies" schemename="dnet:subject_classification_typologies">410</dc:subject>
<dc:type>Departmental Bulletin Paper</dc:type>
<dr:CobjCategory type="publication">0014</dr:CobjCategory>
<oaf:dateAccepted>2004-10-01</oaf:dateAccepted>
<oaf:projectid/>
<oaf:collectedDatasourceid>openaire____::554c7c2873</oaf:collectedDatasourceid>
<oaf:accessrights>OPEN</oaf:accessrights>
<oaf:hostedBy id="openaire____::554c7c2873" name="JAIRO"/>
<oaf:collectedFrom id="openaire____::554c7c2873" name="JAIRO"/>
<oaf:identifier identifierType="handle">2433/25934</oaf:identifier>
<oaf:identifier identifierType="ncid">AN00061013</oaf:identifier>
<oaf:identifier identifierType="LandingPage">http://hdl.handle.net/2433/25934</oaf:identifier>
<oaf:fulltext>http://repository.kulib.kyoto-u.ac.jp/dspace/bitstream/2433/25934/1/1395-16.pdf</oaf:fulltext>
<oaf:journal ep="110" iss="" issn="1880-2818" sp="104" vol="1395">数理解析研究所講究録</oaf:journal>
</metadata>
<about>
<provenance xmlns="http://www.openarchives.org/OAI/2.0/provenance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/provenance http://www.openarchives.org/OAI/2.0/provenance.xsd">
<originDescription altered="true" harvestDate="2021-05-10T11:31:09.424Z">
<baseURL>https%3A%2F%2Firdb.nii.ac.jp%2Foai</baseURL>
<identifier>oai:irdb.nii.ac.jp:01221:0000010198</identifier>
<datestamp>2021-04-13T13:36:29Z</datestamp>
<metadataNamespace/>
<originDescription altered="true" harvestDate="2021-04-13T13:36:29Z">
<baseURL>http://repository.kulib.kyoto-u.ac.jp/dspace-oai/request</baseURL>
<identifier>oai:repository.kulib.kyoto-u.ac.jp:2433/25934</identifier>
<datestamp>2012-07-12T14:15:41Z</datestamp>
<metadataNamespace>http://irdb.nii.ac.jp/oai</metadataNamespace>
</originDescription>
</originDescription>
</provenance>
<oaf:datainfo>
<oaf:inferred>false</oaf:inferred>
<oaf:deletedbyinference>false</oaf:deletedbyinference>
<oaf:trust>0.9</oaf:trust>
<oaf:inferenceprovenance/>
<oaf:provenanceaction classid="sysimport:crosswalk:repository"
classname="sysimport:crosswalk:repository"
schemeid="dnet:provenanceActions" schemename="dnet:provenanceActions"/>
</oaf:datainfo>
</about>
</record>

View File

@ -0,0 +1,8 @@
# Root logger option
log4j.rootLogger=DEBUG, stdout
# Direct log messages to stdout
log4j.appender.stdout=org.apache.log4j.ConsoleAppender
log4j.appender.stdout.Target=System.out
log4j.appender.stdout.layout=org.apache.log4j.PatternLayout
log4j.appender.stdout.layout.ConversionPattern=%d{yyyy-MM-dd HH:mm:ss} %-5p %c{1}:%L - %m%n

View File

@ -59,7 +59,7 @@ class ResolveEntitiesTest extends Serializable {
r.setId(id.toLowerCase.trim)
r.setSubject(
List(
OafMapperUtils.structuredProperty(
OafMapperUtils.subject(
FAKE_SUBJECT,
OafMapperUtils.qualifier("fos", "fosCS", "fossSchema", "fossiFIgo"),
null
@ -250,7 +250,7 @@ class ResolveEntitiesTest extends Serializable {
val r = new Result
r.setSubject(
List(
OafMapperUtils.structuredProperty(
OafMapperUtils.subject(
FAKE_SUBJECT,
OafMapperUtils.qualifier("fos", "fosCS", "fossSchema", "fossiFIgo"),
null

View File

@ -85,7 +85,7 @@ public class IndexRecordTransformerTest {
public void testRiunet() throws IOException, TransformerException {
final XmlRecordFactory xmlRecordFactory = new XmlRecordFactory(contextMapper, false,
XmlConverterJob.schemaLocation);
XmlConverterJob.schemaLocation);
final Publication p = load("riunet.json", Publication.class);
@ -95,7 +95,6 @@ public class IndexRecordTransformerTest {
testRecordTransformation(record);
}
@Test
public void testForEOSCFutureDataTransferPilot() throws IOException, TransformerException {
final String record = IOUtils.toString(getClass().getResourceAsStream("eosc-future/data-transfer-pilot.xml"));
@ -129,8 +128,6 @@ public class IndexRecordTransformerTest {
testRecordTransformation(record);
}
@Test
void testDoiUrlNormalization() throws MalformedURLException {

View File

@ -76,11 +76,11 @@ compute stats indi_result_with_orcid;
---- Sprint 3 ----
create table indi_funded_result_with_fundref stored as parquet as
select distinct r.id, coalesce(fundref, 0) as fundref
select distinct r.result as id, coalesce(fundref, 0) as fundref
from project_results r
left outer join (select distinct id, 1 as fundref from project_results
left outer join (select distinct result, 1 as fundref from project_results
where provenance='Harvested') tmp
on r.id= tmp.id;
on r.result= tmp.result;
compute stats indi_funded_result_with_fundref;
@ -179,17 +179,17 @@ from publication_datasources pd
compute stats indi_pub_diamond;
create table indi_pub_hybrid stored as parquet as
select distinct pd.id, coalesce(is_hybrid, 0) as is_hybrid
from publication_datasources pd
left outer join (
select pd.id, 1 as is_hybrid from publication_datasources pd
join datasource d on d.id=pd.datasource
join stats_ext.plan_s_jn ps where (ps.issn_print=d.issn_printed and ps.issn_online=d.issn_online)
and (ps.journal_is_in_doaj=false and ps.journal_is_oa=false)) tmp
on pd.id=tmp.id;
compute stats indi_pub_hybrid;
--create table indi_pub_hybrid stored as parquet as
--select distinct pd.id, coalesce(is_hybrid, 0) as is_hybrid
--from publication_datasources pd
-- left outer join (
-- select pd.id, 1 as is_hybrid from publication_datasources pd
-- join datasource d on d.id=pd.datasource
-- join stats_ext.plan_s_jn ps where (ps.issn_print=d.issn_printed and ps.issn_online=d.issn_online)
-- and (ps.journal_is_in_doaj=false and ps.journal_is_oa=false)) tmp
-- on pd.id=tmp.id;
--
--compute stats indi_pub_hybrid;
create table indi_pub_in_transformative stored as parquet as
select distinct pd.id, coalesce(is_transformative, 0) as is_transformative
@ -564,12 +564,12 @@ create table indi_org_fairness stored as parquet as
(select ro.organization organization, count(distinct ro.id) no_result_fair from result_organization ro
join result r on r.id=ro.id
--join result_pids rp on r.id=rp.id
where (title is not null) and (publisher is not null) and (abstract is true) and (year is not null) and (authors>0) and year>2003
where (title is not null) and (publisher is not null) and (abstract is true) and (year is not null) and (authors>0) and cast(year as int)>2003
group by ro.organization),
--return all results group by organization
allresults as (select organization, count(distinct ro.id) no_allresults from result_organization ro
join result r on r.id=ro.id
where year>2003
where cast(year as int)>2003
group by organization)
--return results_fair/all_results
select allresults.organization, result_fair.no_result_fair/allresults.no_allresults org_fairness
@ -638,11 +638,11 @@ create table indi_org_fairness_year stored as parquet as
(select year, ro.organization organization, count(distinct ro.id) no_result_fair from result_organization ro
join result r on r.id=ro.id
join result_pids rp on r.id=rp.id
where (title is not null) and (publisher is not null) and (abstract is true) and (year is not null) and (authors>0) and year>2003
where (title is not null) and (publisher is not null) and (abstract is true) and (year is not null) and (authors>0) and cast(year as int)>2003
group by ro.organization, year),
allresults as (select year, organization, count(distinct ro.id) no_allresults from result_organization ro
join result r on r.id=ro.id
where year>2003
where cast(year as int)>2003
group by organization, year)
--return results_fair/all_results
select allresults.year, allresults.organization, result_fair.no_result_fair/allresults.no_allresults org_fairness
@ -657,12 +657,12 @@ create table indi_org_findable_year stored as parquet as
(select year, ro.organization organization, count(distinct rp.id) no_result_with_pid from result_organization ro
join result_pids rp on rp.id=ro.id
join result r on r.id=rp.id
where year >2003
where cast(year as int) >2003
group by ro.organization, year),
--return all results group by organization,year
allresults as (select year, organization, count(distinct ro.id) no_allresults from result_organization ro
join result r on r.id=ro.id
where year >2003
where cast(year as int) >2003
group by organization, year)
--return results_with_pid/all_results
select allresults.year, allresults.organization, result_with_pid.no_result_with_pid/allresults.no_allresults org_findable
@ -677,12 +677,12 @@ create table indi_org_findable stored as parquet as
(select ro.organization organization, count(distinct rp.id) no_result_with_pid from result_organization ro
join result_pids rp on rp.id=ro.id
join result r on r.id=rp.id
where year >2003
where cast(year as int) >2003
group by ro.organization),
--return all results group by organization
allresults as (select organization, count(distinct ro.id) no_allresults from result_organization ro
join result r on r.id=ro.id
where year >2003
where cast(year as int) >2003
group by organization)
--return results_with_pid/all_results
select allresults.organization, result_with_pid.no_result_with_pid/allresults.no_allresults org_findable

View File

@ -3,20 +3,20 @@
----------------------------------------------------
-- Peer reviewed:
create table ${stats_db_name}.result_peerreviewed STORED AS PARQUET as
create table IF NOT EXISTS ${stats_db_name}.result_peerreviewed STORED AS PARQUET as
select r.id as id, case when doi.doi_from_crossref=1 and grey.grey_lit=0 then true else false end as peer_reviewed
from ${stats_db_name}.result r
left outer join ${stats_db_name}.indi_pub_doi_from_crossref doi on doi.id=r.id
left outer join ${stats_db_name}.indi_pub_grey_lit grey on grey.id=r.id;
-- Green OA:
create table ${stats_db_name}.result_greenoa STORED AS PARQUET as
create table IF NOT EXISTS ${stats_db_name}.result_greenoa STORED AS PARQUET as
select r.id, case when green.green_oa=1 then true else false end as green
from ${stats_db_name}.result r
left outer join ${stats_db_name}.indi_pub_green_oa green on green.id=r.id;
-- GOLD OA:
create table ${stats_db_name}.result_gold STORED AS PARQUET as
create table IF NOT EXISTS ${stats_db_name}.result_gold STORED AS PARQUET as
select r.id, case when gold.is_gold=1 then true else false end as gold
from ${stats_db_name}.result r
left outer join ${stats_db_name}.indi_pub_gold_oa gold on gold.id=r.id;

View File

@ -45,7 +45,10 @@ create table TARGET.result stored as parquet as
'openorgs____::15e7921fc50d9aa1229a82a84429419e', -- University Of Thessaly
'openorgs____::11f7919dadc8f8a7251af54bba60c956', -- Technical University of Crete
'openorgs____::84f0c5f5dbb6daf42748485924efde4b', -- University of Piraeus
'openorgs____::4ac562f0376fce3539504567649cb373' -- University of Patras
'openorgs____::4ac562f0376fce3539504567649cb373', -- University of Patras
'openorgs____::3e8d1f8c3f6cd7f418b09f1f58b4873b', -- Aristotle University of Thessaloniki
'openorgs____::3fcef6e1c469c10f2a84b281372c9814', -- World Bank
'openorgs____::1698a2eb1885ef8adb5a4a969e745ad3' -- École des Ponts ParisTech
) )) foo;
compute stats TARGET.result;
@ -159,10 +162,10 @@ create table TARGET.indi_pub_doi_from_crossref stored as parquet as select * fro
compute stats TARGET.indi_pub_doi_from_crossref;
create table TARGET.indi_pub_gold_oa stored as parquet as select * from SOURCE.indi_pub_gold_oa orig where exists (select 1 from TARGET.result r where r.id=orig.id);
compute stats TARGET.indi_pub_gold_oa;
create table TARGET.indi_datasets_gold_oa stored as parquet as select * from SOURCE.indi_datasets_gold_oa orig where exists (select 1 from TARGET.result r where r.id=orig.id);
compute stats TARGET.indi_datasets_gold_oa;
create table TARGET.indi_software_gold_oa stored as parquet as select * from SOURCE.indi_software_gold_oa orig where exists (select 1 from TARGET.result r where r.id=orig.id);
compute stats TARGET.indi_software_gold_oa;
--create table TARGET.indi_datasets_gold_oa stored as parquet as select * from SOURCE.indi_datasets_gold_oa orig where exists (select 1 from TARGET.result r where r.id=orig.id);
--compute stats TARGET.indi_datasets_gold_oa;
--create table TARGET.indi_software_gold_oa stored as parquet as select * from SOURCE.indi_software_gold_oa orig where exists (select 1 from TARGET.result r where r.id=orig.id);
--compute stats TARGET.indi_software_gold_oa;
create table TARGET.indi_pub_has_abstract stored as parquet as select * from SOURCE.indi_pub_has_abstract orig where exists (select 1 from TARGET.result r where r.id=orig.id);
compute stats TARGET.indi_pub_has_abstract;
create table TARGET.indi_result_has_cc_licence stored as parquet as select * from SOURCE.indi_result_has_cc_licence orig where exists (select 1 from TARGET.result r where r.id=orig.id);

View File

@ -200,6 +200,12 @@
<version>${dhp.commons.lang.version}</version>
</dependency>
<dependency>
<groupId>commons-validator</groupId>
<artifactId>commons-validator</artifactId>
<version>1.7</version>
</dependency>
<dependency>
<groupId>com.github.sisyphsu</groupId>
<artifactId>dateparser</artifactId>
@ -801,7 +807,7 @@
<mockito-core.version>3.3.3</mockito-core.version>
<mongodb.driver.version>3.4.2</mongodb.driver.version>
<vtd.version>[2.12,3.0)</vtd.version>
<dhp-schemas.version>[2.12.2-SNAPSHOT]</dhp-schemas.version>
<dhp-schemas.version>[3.14.0]</dhp-schemas.version>
<dnet-actionmanager-api.version>[4.0.3]</dnet-actionmanager-api.version>
<dnet-actionmanager-common.version>[6.0.5]</dnet-actionmanager-common.version>
<dnet-openaire-broker-common.version>[3.1.6]</dnet-openaire-broker-common.version>