D-Net
/
dnet-hadoop
14
5
Fork 11
Code Issues 14 Pull Requests 12 Projects 2 Releases 2 Wiki Activity

bulkTaggingPathMapExtention #381

Merged
claudio.atzori merged 7 commits from bulkTaggingPathMapExtention into beta 2024-03-25 16:02:02 +01:00
Conversation 1 Commits 7 Files Changed 16 +110094 -960
112 changed files with 110094 additions and 960 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files
Showing only changes of commit 91b61687fa - Show all commits

99
dhp-common/src/main/java/eu/dnetlib/dhp/oa/merge/AuthorMerger.java
View File

@ -145,105 +145,6 @@ public class AuthorMerger {
return null;
}
/**
* This method tries to figure out when two author are the same in the contest
* of ORCID enrichment
*
* @param left Author in the OAF entity
* @param right Author ORCID
* @return based on a heuristic on the names of the authors if they are the same.
*/
public static boolean checkORCIDSimilarity(final Author left, final Author right) {
final Person pl = parse(left);
final Person pr = parse(right);
// If one of them didn't have a surname we verify if they have the fullName not empty
// and verify if the normalized version is equal
if (!(pl.getSurname() != null && pl.getSurname().stream().anyMatch(StringUtils::isNotBlank) &&
pr.getSurname() != null && pr.getSurname().stream().anyMatch(StringUtils::isNotBlank))) {
if (pl.getFullname() != null && !pl.getFullname().isEmpty() && pr.getFullname() != null
&& !pr.getFullname().isEmpty()) {
return pl
.getFullname()
.stream()
.anyMatch(
fl -> pr.getFullname().stream().anyMatch(fr -> normalize(fl).equalsIgnoreCase(normalize(fr))));
} else {
return false;
}
}
// The Authors have one surname in common
if (pl.getSurname().stream().anyMatch(sl -> pr.getSurname().stream().anyMatch(sr -> sr.equalsIgnoreCase(sl)))) {
// If one of them has only a surname and is the same we can say that they are the same author
if ((pl.getName() == null || pl.getName().stream().allMatch(StringUtils::isBlank)) ||
(pr.getName() == null || pr.getName().stream().allMatch(StringUtils::isBlank)))
return true;
// The authors have the same initials of Name in common
if (pl
.getName()
.stream()
.anyMatch(
nl -> pr
.getName()
.stream()
.anyMatch(nr -> nr.equalsIgnoreCase(nl))))
return true;
}
// Sometimes we noticed that publication have author wrote in inverse order Surname, Name
// We verify if we have an exact match between name and surname
if (pl.getSurname().stream().anyMatch(sl -> pr.getName().stream().anyMatch(nr -> nr.equalsIgnoreCase(sl))) &&
pl.getName().stream().anyMatch(nl -> pr.getSurname().stream().anyMatch(sr -> sr.equalsIgnoreCase(nl))))
return true;
else
return false;
}
//
/**
* Method to enrich ORCID information in one list of authors based on another list
*
* @param baseAuthor the Author List in the OAF Entity
* @param orcidAuthor The list of ORCID Author intersected
* @return The Author List of the OAF Entity enriched with the orcid Author
*/
public static List<Author> enrichOrcid(List<Author> baseAuthor, List<Author> orcidAuthor) {
if (baseAuthor == null || baseAuthor.isEmpty())
return orcidAuthor;
if (orcidAuthor == null || orcidAuthor.isEmpty())
return baseAuthor;
if (baseAuthor.size() == 1 && orcidAuthor.size() > 10)
return baseAuthor;
final List<Author> oAuthor = new ArrayList<>();
oAuthor.addAll(orcidAuthor);
baseAuthor.forEach(ba -> {
Optional<Author> aMatch = oAuthor.stream().filter(oa -> checkORCIDSimilarity(ba, oa)).findFirst();
if (aMatch.isPresent()) {
final Author sameAuthor = aMatch.get();
addPid(ba, sameAuthor.getPid());
oAuthor.remove(sameAuthor);
}
});
return baseAuthor;
}
private static void addPid(final Author a, final List<StructuredProperty> pids) {
if (a.getPid() == null) {
a.setPid(new ArrayList<>());
}
a.getPid().addAll(pids);
}
public static String pidToComparableString(StructuredProperty pid) {
final String classid = pid.getQualifier().getClassid() != null ? pid.getQualifier().getClassid().toLowerCase()
: "";

39
dhp-common/src/main/java/eu/dnetlib/dhp/oa/merge/GroupEntitiesSparkJob.java
View File

@ -1,24 +1,6 @@
package eu.dnetlib.dhp.oa.merge;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import static org.apache.spark.sql.functions.col;
import static org.apache.spark.sql.functions.when;
import java.util.Map;
import java.util.Optional;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.ForkJoinPool;
import java.util.stream.Collectors;
import org.apache.commons.io.IOUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.api.java.function.ReduceFunction;
import org.apache.spark.sql.*;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup;
@ -26,12 +8,29 @@ import eu.dnetlib.dhp.schema.common.EntityType;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.OafEntity;
import eu.dnetlib.dhp.schema.oaf.utils.GraphCleaningFunctions;
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
import eu.dnetlib.dhp.schema.oaf.utils.MergeUtils;
import eu.dnetlib.dhp.utils.ISLookupClientFactory;
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpException;
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
import org.apache.commons.io.IOUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.api.java.function.ReduceFunction;
import org.apache.spark.sql.*;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import scala.Tuple2;
import java.util.Map;
import java.util.Optional;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.ForkJoinPool;
import java.util.stream.Collectors;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import static org.apache.spark.sql.functions.col;
import static org.apache.spark.sql.functions.when;
/**
* Groups the graph content by entity identifier to ensure ID uniqueness
*/
@ -135,7 +134,7 @@ public class GroupEntitiesSparkJob {
.applyCoarVocabularies(entity, vocs),
OAFENTITY_KRYO_ENC)
.groupByKey((MapFunction<OafEntity, String>) OafEntity::getId, Encoders.STRING())
.reduceGroups((ReduceFunction<OafEntity>) OafMapperUtils::mergeEntities)
.reduceGroups((ReduceFunction<OafEntity>) MergeUtils::checkedMerge)
.map(
(MapFunction<Tuple2<String, OafEntity>, Tuple2<String, OafEntity>>) t -> new Tuple2<>(
t._2().getClass().getName(), t._2()),

3
dhp-common/src/main/java/eu/dnetlib/dhp/schema/oaf/utils/GraphCleaningFunctions.java
View File

@ -312,7 +312,8 @@ public class GraphCleaningFunctions extends CleaningFunctions {
}
if (value instanceof Datasource) {
// nothing to evaluate here
final Datasource d = (Datasource) value;
return Objects.nonNull(d.getOfficialname()) && StringUtils.isNotBlank(d.getOfficialname().getValue());
} else if (value instanceof Project) {
final Project p = (Project) value;
return Objects.nonNull(p.getCode()) && StringUtils.isNotBlank(p.getCode().getValue());

79
dhp-common/src/main/java/eu/dnetlib/dhp/schema/oaf/utils/MergeComparator.java Normal file
View File

@ -0,0 +1,79 @@
package eu.dnetlib.dhp.schema.oaf.utils;
//
// Source code recreated from a .class file by IntelliJ IDEA
// (powered by FernFlower decompiler)
//
import eu.dnetlib.dhp.schema.common.EntityType;
import eu.dnetlib.dhp.schema.oaf.KeyValue;
import eu.dnetlib.dhp.schema.oaf.Oaf;
import eu.dnetlib.dhp.schema.oaf.OafEntity;
import eu.dnetlib.dhp.schema.oaf.Result;
import java.util.Comparator;
import java.util.HashSet;
import java.util.Optional;
import java.util.stream.Collectors;
public class MergeComparator implements Comparator<Oaf> {
public MergeComparator() {
}
public int compare(Oaf left, Oaf right) {
// nulls at the end
if (left == null && right == null) {
return 0;
} else if (left == null) {
return -1;
} else if (right == null) {
return 1;
}
// invisible
if (left.getDataInfo() != null && left.getDataInfo().getInvisible() == true) {
if (right.getDataInfo() != null && right.getDataInfo().getInvisible() == false) {
return -1;
}
}
// collectedfrom
HashSet<String> lCf = getCollectedFromIds(left);
HashSet<String> rCf = getCollectedFromIds(right);
if (lCf.contains("10|openaire____::081b82f96300b6a6e3d282bad31cb6e2") && !rCf.contains("10|openaire____::081b82f96300b6a6e3d282bad31cb6e2")) {
return -1;
} else if (!lCf.contains("10|openaire____::081b82f96300b6a6e3d282bad31cb6e2") && rCf.contains("10|openaire____::081b82f96300b6a6e3d282bad31cb6e2")) {
return 1;
}
SubEntityType lClass = SubEntityType.fromClass(left.getClass());
SubEntityType rClass = SubEntityType.fromClass(right.getClass());
return lClass.ordinal() - rClass.ordinal();
}
protected HashSet<String> getCollectedFromIds(Oaf left) {
return (HashSet) Optional.ofNullable(left.getCollectedfrom()).map((cf) -> {
return (HashSet) cf.stream().map(KeyValue::getKey).collect(Collectors.toCollection(HashSet::new));
}).orElse(new HashSet());
}
enum SubEntityType {
publication, dataset, software, otherresearchproduct, datasource, organization, project;
/**
* Resolves the EntityType, given the relative class name
*
* @param clazz the given class name
* @param <T> actual OafEntity subclass
* @return the EntityType associated to the given class
*/
public static <T extends Oaf> SubEntityType fromClass(Class<T> clazz) {
return valueOf(clazz.getSimpleName().toLowerCase());
}
}
}

707
dhp-common/src/main/java/eu/dnetlib/dhp/schema/oaf/utils/MergeUtils.java Normal file
View File

@ -0,0 +1,707 @@
package eu.dnetlib.dhp.schema.oaf.utils;
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.*;
import org.apache.commons.lang3.StringUtils;
import org.apache.commons.lang3.tuple.ImmutablePair;
import org.apache.commons.lang3.tuple.Pair;
import java.text.ParseException;
import java.util.*;
import java.util.stream.Collectors;
import java.util.stream.Stream;
import static com.google.common.base.Objects.firstNonNull;
import static com.google.common.base.Preconditions.checkArgument;
public class MergeUtils {
public static <T extends Oaf> T checkedMerge(final T left, final T right) {
return (T) merge(left, right, false);
}
public static Oaf merge(final Oaf left, final Oaf right) {
return merge(left, right, false);
}
public static Oaf merge(final Oaf left, final Oaf right, boolean checkDelegatedAuthority) {
if (sameClass(left, right, OafEntity.class)) {
return mergeEntities(left, right, checkDelegatedAuthority);
} else if (sameClass(left, right, Relation.class)) {
return mergeRelation((Relation) left, (Relation) right);
} else {
throw new RuntimeException(
String
.format(
"MERGE_FROM_AND_GET incompatible types: %s, %s",
left.getClass().getCanonicalName(), right.getClass().getCanonicalName()));
}
}
private static <T extends Oaf> boolean sameClass(Object left, Object right, Class<T> cls) {
return cls.isAssignableFrom(left.getClass()) && cls.isAssignableFrom(right.getClass());
}
private static Oaf mergeEntities(Oaf left, Oaf right, boolean checkDelegatedAuthority) {
if (sameClass(left, right, Result.class)) {
if (!left.getClass().equals(right.getClass()) || checkDelegatedAuthority) {
return mergeResultsOfDifferentTypes((Result)left, (Result) right);
}
if (sameClass(left, right, Publication.class)) {
return mergePublication((Publication) left, (Publication) right);
}
if (sameClass(left, right, Dataset.class)) {
return mergeDataset((Dataset) left, (Dataset) right);
}
if (sameClass(left, right, OtherResearchProduct.class)) {
return mergeORP((OtherResearchProduct) left, (OtherResearchProduct) right);
}
if (sameClass(left, right, Software.class)) {
return mergeSoftware((Software) left, (Software) right);
}
return mergeResult((Result) left, (Result) right);
} else if (sameClass(left, right, Datasource.class)) {
// TODO
final int trust = compareTrust(left, right);
return mergeOafEntityFields((Datasource) left, (Datasource) right, trust);
} else if (sameClass(left, right, Organization.class)) {
return mergeOrganization((Organization) left, (Organization) right);
} else if (sameClass(left, right, Project.class)) {
return mergeProject((Project) left, (Project) right);
} else {
throw new RuntimeException(
String
.format(
"MERGE_FROM_AND_GET incompatible types: %s, %s",
left.getClass().getCanonicalName(), right.getClass().getCanonicalName()));
}
}
/**
* This method is used in the global result grouping phase. It checks if one of the two is from a delegated authority
* https://graph.openaire.eu/docs/data-model/pids-and-identifiers#delegated-authorities and in that case it prefers
* such version.
* <p>
* Otherwise, it considers a resulttype priority order implemented in {@link ResultTypeComparator}
* and proceeds with the canonical property merging.
*
* @param left
* @param right
* @return
*/
private static <T extends Result> T mergeResultsOfDifferentTypes(T left, T right) {
final boolean leftFromDelegatedAuthority = isFromDelegatedAuthority(left);
final boolean rightFromDelegatedAuthority = isFromDelegatedAuthority(right);
if (leftFromDelegatedAuthority && !rightFromDelegatedAuthority) {
return left;
}
if (!leftFromDelegatedAuthority && rightFromDelegatedAuthority) {
return right;
}
//TODO: raise trust to have preferred fields from one or the other??
if (new ResultTypeComparator().compare(left, right) < 0) {
return mergeResult(left, right);
} else {
return mergeResult(right, left);
}
}
private static DataInfo chooseDataInfo(DataInfo left, DataInfo right, int trust) {
if (trust > 0) {
return left;
} else if (trust == 0) {
if (left == null || (left.getInvisible() != null && left.getInvisible().equals(Boolean.TRUE))) {
return right;
} else {
return left;
}
} else {
return right;
}
}
private static String chooseString(String left, String right, int trust) {
if (trust > 0) {
return left;
} else if (trust == 0) {
return StringUtils.isNotBlank(left) ? left : right;
} else {
return right;
}
}
private static <T> T chooseReference(T left, T right, int trust) {
if (trust > 0) {
return left;
} else if (trust == 0) {
return left != null ? left : right;
} else {
return right;
}
}
private static Long max(Long left, Long right) {
if (left == null)
return right;
if (right == null)
return left;
return Math.max(left, right);
}
// trust ??
private static Boolean booleanOR(Boolean a, Boolean b) {
if (a == null) {
return b;
} else if (b == null) {
return a;
}
return a || b;
}
private static <T> List<T> unionDistinctLists(final List<T> left, final List<T> right, int trust) {
if (left == null) {
return right;
} else if (right == null) {
return left;
}
List<T> h = trust >= 0 ? left : right;
List<T> l = trust >= 0 ? right : left;
return Stream.concat(h.stream(), l.stream())
.filter(Objects::nonNull)
.distinct()
.collect(Collectors.toList());
}
private static List<String> unionDistinctListOfString(final List<String> l, final List<String> r) {
if (l == null) {
return r;
} else if (r == null) {
return l;
}
return Stream.concat(l.stream(), r.stream())
.filter(StringUtils::isNotBlank)
.distinct()
.collect(Collectors.toList());
}
//TODO review
private static List<KeyValue> mergeKeyValue(List<KeyValue> left, List<KeyValue> right, int trust) {
if (trust < 0) {
List<KeyValue> s = left;
left = right;
right = s;
}
HashMap<String, KeyValue> values = new HashMap<>();
left.forEach(kv -> values.put(kv.getKey(), kv));
right.forEach(kv -> values.putIfAbsent(kv.getKey(), kv));
return new ArrayList<>(values.values());
}
private static List<StructuredProperty> unionTitle(List<StructuredProperty> left, List<StructuredProperty> right, int trust) {
if (left == null) {
return right;
} else if (right == null) {
return left;
}
List<StructuredProperty> h = trust >= 0 ? left : right;
List<StructuredProperty> l = trust >= 0 ? right : left;
return Stream.concat(h.stream(), l.stream())
.filter(Objects::isNull)
.distinct()
.collect(Collectors.toList());
}
/**
* Internal utility that merges the common OafEntity fields
*
* @param merged
* @param enrich
* @param <T>
* @return
*/
private static <T extends Oaf> T mergeOafFields(T merged, T enrich, int trust) {
//TODO: union of all values, but what does it mean with KeyValue pairs???
merged.setCollectedfrom(mergeKeyValue(merged.getCollectedfrom(), enrich.getCollectedfrom(), trust));
merged.setDataInfo(chooseDataInfo(merged.getDataInfo(), enrich.getDataInfo(), trust));
merged.setLastupdatetimestamp(max(merged.getLastupdatetimestamp(), enrich.getLastupdatetimestamp()));
return merged;
}
/**
* Internal utility that merges the common OafEntity fields
*
* @param original
* @param enrich
* @param <T>
* @return
*/
private static <T extends OafEntity> T mergeOafEntityFields(T original, T enrich, int trust) {
final T merged = mergeOafFields(original, enrich, trust);
merged.setOriginalId(unionDistinctListOfString(merged.getOriginalId(), enrich.getOriginalId()));
merged.setPid(unionDistinctLists(merged.getPid(), enrich.getPid(), trust));
// dateofcollection mettere today quando si fa merge
merged.setDateofcollection(chooseString(merged.getDateofcollection(), enrich.getDateofcollection(), trust));
// setDateoftransformation mettere vuota in dedup, nota per Claudio
merged.setDateoftransformation(chooseString(merged.getDateoftransformation(), enrich.getDateoftransformation(), trust));
// TODO: was missing in OafEntity.merge
merged.setExtraInfo(unionDistinctLists(merged.getExtraInfo(), enrich.getExtraInfo(), trust));
//oaiprovenanze da mettere a null quando si genera merge
merged.setOaiprovenance(chooseReference(merged.getOaiprovenance(), enrich.getOaiprovenance(), trust));
merged.setMeasures(unionDistinctLists(merged.getMeasures(), enrich.getMeasures(), trust));
return merged;
}
public static <T extends Relation> T mergeRelation(T original, T enrich) {
int trust = compareTrust(original, enrich);
T merge = mergeOafFields(original, enrich, trust);
checkArgument(Objects.equals(merge.getSource(), enrich.getSource()), "source ids must be equal");
checkArgument(Objects.equals(merge.getTarget(), enrich.getTarget()), "target ids must be equal");
checkArgument(Objects.equals(merge.getRelType(), enrich.getRelType()), "relType(s) must be equal");
checkArgument(
Objects.equals(merge.getSubRelType(), enrich.getSubRelType()), "subRelType(s) must be equal");
checkArgument(Objects.equals(merge.getRelClass(), enrich.getRelClass()), "relClass(es) must be equal");
//merge.setProvenance(mergeLists(merge.getProvenance(), enrich.getProvenance()));
//TODO: trust ??
merge.setValidated(booleanOR(merge.getValidated(), enrich.getValidated()));
try {
merge.setValidationDate(ModelSupport.oldest(merge.getValidationDate(), enrich.getValidationDate()));
} catch (ParseException e) {
throw new IllegalArgumentException(String
.format(
"invalid validation date format in relation [s:%s, t:%s]: %s", merge.getSource(),
merge.getTarget(),
merge.getValidationDate()));
}
// TODO keyvalue merge
merge.setProperties(mergeKeyValue(merge.getProperties(), enrich.getProperties(), trust));
return merge;
}
public static <T extends Result> T mergeResult(T original, T enrich) {
final int trust = compareTrust(original, enrich);
T merge = mergeOafEntityFields(original, enrich, trust);
if (merge.getProcessingchargeamount() == null || StringUtils.isBlank(merge.getProcessingchargeamount().getValue())) {
merge.setProcessingchargeamount(enrich.getProcessingchargeamount());
merge.setProcessingchargecurrency(enrich.getProcessingchargecurrency());
}
// author = usare la stessa logica che in dedup
merge.setAuthor(chooseReference(merge.getAuthor(), enrich.getAuthor(), trust));
// il primo che mi arriva secondo l'ordinamento per priorita'
merge.setResulttype(chooseReference(merge.getResulttype(), enrich.getResulttype(), trust));
// gestito come il resulttype perche' e' un subtype
merge.setMetaResourceType(chooseReference(merge.getMetaResourceType(), enrich.getMetaResourceType(), trust));
// spostiamo nell'instance e qui prendo il primo che arriva
merge.setLanguage(chooseReference(merge.getLanguage(), enrich.getLanguage(), trust));
// country lasicamo,o cosi' -> parentesi sul datainfo
merge.setCountry(unionDistinctLists(merge.getCountry(), enrich.getCountry(), trust));
//ok
merge.setSubject(unionDistinctLists(merge.getSubject(), enrich.getSubject(), trust));
// union per priority quindi vanno in append
merge.setTitle(unionTitle(merge.getTitle(), enrich.getTitle(), trust));
//ok
merge.setRelevantdate(unionDistinctLists(merge.getRelevantdate(), enrich.getRelevantdate(), trust));
// prima trust e poi longest list
merge.setDescription(longestLists(merge.getDescription(), enrich.getDescription()));
// trust piu' alto e poi piu' vecchia
merge.setDateofacceptance(chooseReference(merge.getDateofacceptance(), enrich.getDateofacceptance(), trust));
// ok, ma publisher va messo ripetibile
merge.setPublisher(chooseReference(merge.getPublisher(), enrich.getPublisher(), trust));
// ok
merge.setEmbargoenddate(chooseReference(merge.getEmbargoenddate(), enrich.getEmbargoenddate(), trust));
// ok
merge.setSource(unionDistinctLists(merge.getSource(), enrich.getSource(), trust));
// ok
merge.setFulltext(unionDistinctLists(merge.getFulltext(), enrich.getFulltext(), trust));
// ok
merge.setFormat(unionDistinctLists(merge.getFormat(), enrich.getFormat(), trust));
// ok
merge.setContributor(unionDistinctLists(merge.getContributor(), enrich.getContributor(), trust));
// prima prendo l'higher trust, su questo prendo il valore migliore nelle istanze TODO
// trust maggiore ma a parita' di trust il piu' specifico (base del vocabolario)
// vedi note
merge.setResourcetype(firstNonNull(merge.getResourcetype(), enrich.getResourcetype()));
// ok
merge.setCoverage(unionDistinctLists(merge.getCoverage(), enrich.getCoverage(), trust));
// most open ok
if (enrich.getBestaccessright() != null
&& new AccessRightComparator<>()
.compare(enrich.getBestaccessright(), merge.getBestaccessright()) < 0) {
merge.setBestaccessright(enrich.getBestaccessright());
}
// TODO merge of datainfo given same id
merge.setContext(unionDistinctLists(merge.getContext(), enrich.getContext(), trust));
//ok
merge.setExternalReference(unionDistinctLists(merge.getExternalReference(), enrich.getExternalReference(), trust));
//instance enrichment or union
// review instance equals => add pid to comparision
if (!isAnEnrichment(merge) && !isAnEnrichment(enrich))
merge.setInstance(unionDistinctLists(merge.getInstance(), enrich.getInstance(), trust));
else {
final List<Instance> enrichmentInstances = isAnEnrichment(merge) ? merge.getInstance()
: enrich.getInstance();
final List<Instance> enrichedInstances = isAnEnrichment(merge) ? enrich.getInstance()
: merge.getInstance();
if (isAnEnrichment(merge))
merge.setDataInfo(enrich.getDataInfo());
merge.setInstance(enrichInstances(enrichedInstances, enrichmentInstances));
}
merge.setEoscifguidelines(unionDistinctLists(merge.getEoscifguidelines(), enrich.getEoscifguidelines(), trust));
merge.setIsGreen(booleanOR(merge.getIsGreen(), enrich.getIsGreen()));
// OK but should be list of values
merge.setOpenAccessColor(chooseReference(merge.getOpenAccessColor(), enrich.getOpenAccessColor(), trust));
merge.setIsInDiamondJournal(booleanOR(merge.getIsInDiamondJournal(), enrich.getIsInDiamondJournal()));
merge.setPubliclyFunded(booleanOR(merge.getPubliclyFunded(), enrich.getPubliclyFunded()));
return merge;
}
private static <T extends OtherResearchProduct> T mergeORP(T original, T enrich) {
int trust = compareTrust(original, enrich);
final T merge = mergeResult(original, enrich);
merge.setContactperson(unionDistinctLists(merge.getContactperson(), enrich.getContactperson(), trust));
merge.setContactgroup(unionDistinctLists(merge.getContactgroup(), enrich.getContactgroup(), trust));
merge.setTool(unionDistinctLists(merge.getTool(), enrich.getTool(), trust));
return merge;
}
private static <T extends Software> T mergeSoftware(T original, T enrich) {
int trust = compareTrust(original, enrich);
final T merge = mergeResult(original, enrich);
merge.setDocumentationUrl(unionDistinctLists(merge.getDocumentationUrl(), enrich.getDocumentationUrl(), trust));
merge.setLicense(unionDistinctLists(merge.getLicense(), enrich.getLicense(), trust));
merge.setCodeRepositoryUrl(chooseReference(merge.getCodeRepositoryUrl(), enrich.getCodeRepositoryUrl(), trust));
merge.setProgrammingLanguage(chooseReference(merge.getProgrammingLanguage(), enrich.getProgrammingLanguage(), trust));
return merge;
}
private static <T extends Dataset> T mergeDataset(T original, T enrich) {
int trust = compareTrust(original, enrich);
T merge = mergeResult(original, enrich);
merge.setStoragedate(chooseReference(merge.getStoragedate(), enrich.getStoragedate(), trust));
merge.setDevice(chooseReference(merge.getDevice(), enrich.getDevice(), trust));
merge.setSize(chooseReference(merge.getSize(), enrich.getSize(), trust));
merge.setVersion(chooseReference(merge.getVersion(), enrich.getVersion(), trust));
merge.setLastmetadataupdate(chooseReference(merge.getLastmetadataupdate(), enrich.getLastmetadataupdate(), trust));
merge.setMetadataversionnumber(chooseReference(merge.getMetadataversionnumber(), enrich.getMetadataversionnumber(), trust));
merge.setGeolocation(unionDistinctLists(merge.getGeolocation(), enrich.getGeolocation(), trust));
return merge;
}
public static <T extends Publication> T mergePublication(T original, T enrich) {
final int trust = compareTrust(original, enrich);
T merged = mergeResult(original, enrich);
merged.setJournal(chooseReference(merged.getJournal(), enrich.getJournal(), trust));
return merged;
}
private static <T extends Organization> T mergeOrganization(T left, T enrich) {
int trust = compareTrust(left, enrich);
T merged = mergeOafEntityFields(left, enrich, trust);
merged.setLegalshortname(chooseReference(merged.getLegalshortname(), enrich.getLegalshortname(), trust));
merged.setLegalname(chooseReference(merged.getLegalname(), enrich.getLegalname(), trust));
merged.setAlternativeNames(unionDistinctLists(enrich.getAlternativeNames(), merged.getAlternativeNames(), trust));
merged.setWebsiteurl(chooseReference(merged.getWebsiteurl(), enrich.getWebsiteurl(), trust));
merged.setLogourl(chooseReference(merged.getLogourl(), enrich.getLogourl(), trust));
merged.setEclegalbody(chooseReference(merged.getEclegalbody(), enrich.getEclegalbody(), trust));
merged.setEclegalperson(chooseReference(merged.getEclegalperson(), enrich.getEclegalperson(), trust));
merged.setEcnonprofit(chooseReference(merged.getEcnonprofit(), enrich.getEcnonprofit(), trust));
merged.setEcresearchorganization(chooseReference(merged.getEcresearchorganization(), enrich.getEcresearchorganization(), trust));
merged.setEchighereducation(chooseReference(merged.getEchighereducation(), enrich.getEchighereducation(), trust));
merged.setEcinternationalorganizationeurinterests(chooseReference(merged.getEcinternationalorganizationeurinterests(), enrich.getEcinternationalorganizationeurinterests(), trust));
merged.setEcinternationalorganization(chooseReference(merged.getEcinternationalorganization(), enrich.getEcinternationalorganization(), trust));
merged.setEcenterprise(chooseReference(merged.getEcenterprise(), enrich.getEcenterprise(), trust));
merged.setEcsmevalidated(chooseReference(merged.getEcsmevalidated(), enrich.getEcsmevalidated(), trust));
merged.setEcnutscode(chooseReference(merged.getEcnutscode(), enrich.getEcnutscode(), trust));
merged.setCountry(chooseReference(merged.getCountry(), enrich.getCountry(), trust));
return merged;
}
public static <T extends Project> T mergeProject(T original, T enrich) {
int trust = compareTrust(original, enrich);
T merged = mergeOafEntityFields(original, enrich, trust);
merged.setWebsiteurl(chooseReference(merged.getWebsiteurl(), enrich.getWebsiteurl(), trust));
merged.setCode(chooseReference(merged.getCode(), enrich.getCode(), trust));
merged.setAcronym(chooseReference(merged.getAcronym(), enrich.getAcronym(), trust));
merged.setTitle(chooseReference(merged.getTitle(), enrich.getTitle(), trust));
merged.setStartdate(chooseReference(merged.getStartdate(), enrich.getStartdate(), trust));
merged.setEnddate(chooseReference(merged.getEnddate(), enrich.getEnddate(), trust));
merged.setCallidentifier(chooseReference(merged.getCallidentifier(), enrich.getCallidentifier(), trust));
merged.setKeywords(chooseReference(merged.getKeywords(), enrich.getKeywords(), trust));
merged.setDuration(chooseReference(merged.getDuration(), enrich.getDuration(), trust));
merged.setEcsc39(chooseReference(merged.getEcsc39(), enrich.getEcsc39(), trust));
merged.setOamandatepublications(chooseReference(merged.getOamandatepublications(), enrich.getOamandatepublications(), trust));
merged.setEcarticle29_3(chooseReference(merged.getEcarticle29_3(), enrich.getEcarticle29_3(), trust));
merged.setSubjects(unionDistinctLists(merged.getSubjects(), enrich.getSubjects(), trust));
merged.setFundingtree(unionDistinctLists(merged.getFundingtree(), enrich.getFundingtree(), trust));
merged.setContracttype(chooseReference(merged.getContracttype(), enrich.getContracttype(), trust));
merged.setOptional1(chooseReference(merged.getOptional1(), enrich.getOptional1(), trust));
merged.setOptional2(chooseReference(merged.getOptional2(), enrich.getOptional2(), trust));
merged.setJsonextrainfo(chooseReference(merged.getJsonextrainfo(), enrich.getJsonextrainfo(), trust));
merged.setContactfullname(chooseReference(merged.getContactfullname(), enrich.getContactfullname(), trust));
merged.setContactfax(chooseReference(merged.getContactfax(), enrich.getContactfax(), trust));
merged.setContactphone(chooseReference(merged.getContactphone(), enrich.getContactphone(), trust));
merged.setContactemail(chooseReference(merged.getContactemail(), enrich.getContactemail(), trust));
merged.setSummary(chooseReference(merged.getSummary(), enrich.getSummary(), trust));
merged.setCurrency(chooseReference(merged.getCurrency(), enrich.getCurrency(), trust));
//missin in Project.merge
merged.setTotalcost(chooseReference(merged.getTotalcost(), enrich.getTotalcost(), trust));
merged.setFundedamount(chooseReference(merged.getFundedamount(), enrich.getFundedamount(), trust));
// trust ??
if (enrich.getH2020topiccode() != null && StringUtils.isEmpty(merged.getH2020topiccode())) {
merged.setH2020topiccode(enrich.getH2020topiccode());
merged.setH2020topicdescription(enrich.getH2020topicdescription());
}
merged.setH2020classification(unionDistinctLists(merged.getH2020classification(), enrich.getH2020classification(), trust));
return merged;
}
/**
* Longest lists list.
*
* @param a the a
* @param b the b
* @return the list
*/
public static List<Field<String>> longestLists(List<Field<String>> a, List<Field<String>> b) {
if (a == null || b == null)
return a == null ? b : a;
return a.size() >= b.size() ? a : b;
}
/**
* This main method apply the enrichment of the instances
*
* @param toEnrichInstances the instances that could be enriched
* @param enrichmentInstances the enrichment instances
* @return list of instances possibly enriched
*/
private static List<Instance> enrichInstances(final List<Instance> toEnrichInstances,
final List<Instance> enrichmentInstances) {
final List<Instance> enrichmentResult = new ArrayList<>();
if (toEnrichInstances == null) {
return enrichmentResult;
}
if (enrichmentInstances == null) {
return enrichmentResult;
}
Map<String, Instance> ri = toInstanceMap(enrichmentInstances);
toEnrichInstances.forEach(i -> {
final List<Instance> e = findEnrichmentsByPID(i.getPid(), ri);
if (e != null && e.size() > 0) {
e.forEach(enr -> applyEnrichment(i, enr));
} else {
final List<Instance> a = findEnrichmentsByPID(i.getAlternateIdentifier(), ri);
if (a != null && a.size() > 0) {
a.forEach(enr -> applyEnrichment(i, enr));
}
}
enrichmentResult.add(i);
});
return enrichmentResult;
}
/**
* This method converts the list of instance enrichments
* into a Map where the key is the normalized identifier
* and the value is the instance itself
*
* @param ri the list of enrichment instances
* @return the result map
*/
private static Map<String, Instance> toInstanceMap(final List<Instance> ri) {
return ri
.stream()
.filter(i -> i.getPid() != null || i.getAlternateIdentifier() != null)
.flatMap(i -> {
final List<Pair<String, Instance>> result = new ArrayList<>();
if (i.getPid() != null)
i
.getPid()
.stream()
.filter(MergeUtils::validPid)
.forEach(p -> result.add(new ImmutablePair<>(extractKeyFromPid(p), i)));
if (i.getAlternateIdentifier() != null)
i
.getAlternateIdentifier()
.stream()
.filter(MergeUtils::validPid)
.forEach(p -> result.add(new ImmutablePair<>(extractKeyFromPid(p), i)));
return result.stream();
})
.collect(
Collectors
.toMap(
Pair::getLeft,
Pair::getRight,
(a, b) -> a));
}
private static boolean isFromDelegatedAuthority(Result r) {
return Optional
.ofNullable(r.getInstance())
.map(
instance -> instance
.stream()
.filter(i -> Objects.nonNull(i.getCollectedfrom()))
.map(i -> i.getCollectedfrom().getKey())
.anyMatch(cfId -> IdentifierFactory.delegatedAuthorityDatasourceIds().contains(cfId)))
.orElse(false);
}
/**
* Valid pid boolean.
*
* @param p the p
* @return the boolean
*/
private static boolean validPid(final StructuredProperty p) {
return p.getValue() != null && p.getQualifier() != null && p.getQualifier().getClassid() != null;
}
/**
* Normalize pid string.
*
* @param pid the pid
* @return the string
*/
private static String extractKeyFromPid(final StructuredProperty pid) {
if (pid == null)
return null;
final StructuredProperty normalizedPid = CleaningFunctions.normalizePidValue(pid);
return String.format("%s::%s", normalizedPid.getQualifier().getClassid(), normalizedPid.getValue());
}
/**
* This utility method finds the list of enrichment instances
* that match one or more PIDs in the input list
*
* @param pids the list of PIDs
* @param enrichments the List of enrichment instances having the same pid
* @return the list
*/
private static List<Instance> findEnrichmentsByPID(final List<StructuredProperty> pids,
final Map<String, Instance> enrichments) {
if (pids == null || enrichments == null)
return null;
return pids
.stream()
.map(MergeUtils::extractKeyFromPid)
.map(enrichments::get)
.filter(Objects::nonNull)
.collect(Collectors.toList());
}
/**
* Is an enrichment boolean.
*
* @param e the e
* @return the boolean
*/
private static boolean isAnEnrichment(OafEntity e) {
return e.getDataInfo() != null &&
e.getDataInfo().getProvenanceaction() != null
&& ModelConstants.PROVENANCE_ENRICH.equalsIgnoreCase(e.getDataInfo().getProvenanceaction().getClassid());
}
/**
* This method apply enrichment on a single instance
* The enrichment consists of replacing values on
* single attribute only if in the current instance is missing
* The only repeatable field enriched is measures
*
* @param merge the current instance
* @param enrichment the enrichment instance
*/
private static void applyEnrichment(final Instance merge, final Instance enrichment) {
if (merge == null || enrichment == null)
return;
merge.setLicense(firstNonNull(merge.getLicense(), enrichment.getLicense()));
merge.setAccessright(firstNonNull(merge.getAccessright(), enrichment.getAccessright()));
merge.setInstancetype(firstNonNull(merge.getInstancetype(), enrichment.getInstancetype()));
merge.setInstanceTypeMapping(firstNonNull(merge.getInstanceTypeMapping(), enrichment.getInstanceTypeMapping()));
merge.setHostedby(firstNonNull(merge.getHostedby(), enrichment.getHostedby()));
merge.setUrl(unionDistinctLists(merge.getUrl(), enrichment.getUrl(), 0));
merge.setDistributionlocation(firstNonNull(merge.getDistributionlocation(), enrichment.getDistributionlocation()));
merge.setCollectedfrom(firstNonNull(merge.getCollectedfrom(), enrichment.getCollectedfrom()));
// pid and alternateId are used for matching
merge.setDateofacceptance(firstNonNull(merge.getDateofacceptance(), enrichment.getDateofacceptance()));
merge.setProcessingchargeamount(firstNonNull(merge.getProcessingchargeamount(), enrichment.getProcessingchargeamount()));
merge.setProcessingchargecurrency(firstNonNull(merge.getProcessingchargecurrency(), enrichment.getProcessingchargecurrency()));
merge.setRefereed(firstNonNull(merge.getRefereed(), enrichment.getRefereed()));
merge.setMeasures(unionDistinctLists(merge.getMeasures(), enrichment.getMeasures(), 0));
merge.setFulltext(firstNonNull(merge.getFulltext(), enrichment.getFulltext()));
}
private static int compareTrust(Oaf a, Oaf b) {
String left = Optional
.ofNullable(a.getDataInfo())
.map(DataInfo::getTrust)
.orElse("0.0");
String right = Optional
.ofNullable(b.getDataInfo())
.map(DataInfo::getTrust)
.orElse("0.0");
return left.compareTo(right);
}
}

60
dhp-common/src/main/java/eu/dnetlib/dhp/schema/oaf/utils/OafMapperUtils.java
View File

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

111
dhp-common/src/test/java/eu/dnetlib/dhp/schema/oaf/utils/MergeUtilsTest.java Normal file
View File

@ -0,0 +1,111 @@
package eu.dnetlib.dhp.schema.oaf.utils;
import static org.junit.jupiter.api.Assertions.*;
import static org.junit.jupiter.api.Assertions.assertEquals;
import java.io.IOException;
import java.util.HashSet;
import java.util.List;
import java.util.stream.Collectors;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import org.apache.commons.io.IOUtils;
import org.junit.jupiter.api.Test;
import com.fasterxml.jackson.databind.DeserializationFeature;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.Dataset;
import eu.dnetlib.dhp.schema.oaf.KeyValue;
import eu.dnetlib.dhp.schema.oaf.Publication;
import eu.dnetlib.dhp.schema.oaf.Result;
public class MergeUtilsTest {
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper()
.configure(DeserializationFeature.FAIL_ON_UNKNOWN_PROPERTIES, false);
@Test
void testMergePubs() throws IOException {
Publication p1 = read("publication_1.json", Publication.class);
Publication p2 = read("publication_2.json", Publication.class);
Dataset d1 = read("dataset_1.json", Dataset.class);
Dataset d2 = read("dataset_2.json", Dataset.class);
assertEquals(1, p1.getCollectedfrom().size());
assertEquals(ModelConstants.CROSSREF_ID, p1.getCollectedfrom().get(0).getKey());
assertEquals(1, d2.getCollectedfrom().size());
assertFalse(cfId(d2.getCollectedfrom()).contains(ModelConstants.CROSSREF_ID));
assertEquals(1, p2.getCollectedfrom().size());
assertFalse(cfId(p2.getCollectedfrom()).contains(ModelConstants.CROSSREF_ID));
assertEquals(1, d1.getCollectedfrom().size());
assertTrue(cfId(d1.getCollectedfrom()).contains(ModelConstants.CROSSREF_ID));
final Result p1d2 = MergeUtils.checkedMerge(p1, d2);
assertEquals(ModelConstants.PUBLICATION_RESULTTYPE_CLASSID, p1d2.getResulttype().getClassid());
assertTrue(p1d2 instanceof Publication);
assertEquals(p1.getId(), p1d2.getId());
}
@Test
void testMergePubs_1() throws IOException {
Publication p2 = read("publication_2.json", Publication.class);
Dataset d1 = read("dataset_1.json", Dataset.class);
final Result p2d1 = MergeUtils.checkedMerge(p2, d1);
assertEquals((ModelConstants.DATASET_RESULTTYPE_CLASSID), p2d1.getResulttype().getClassid());
assertTrue(p2d1 instanceof Dataset);
assertEquals(d1.getId(), p2d1.getId());
assertEquals(2, p2d1.getCollectedfrom().size());
}
@Test
void testMergePubs_2() throws IOException {
Publication p1 = read("publication_1.json", Publication.class);
Publication p2 = read("publication_2.json", Publication.class);
Result p1p2 = MergeUtils.checkedMerge(p1, p2);
assertTrue(p1p2 instanceof Publication);
assertEquals(p1.getId(), p1p2.getId());
assertEquals(2, p1p2.getCollectedfrom().size());
}
@Test
void testDelegatedAuthority_1() throws IOException {
Dataset d1 = read("dataset_2.json", Dataset.class);
Dataset d2 = read("dataset_delegated.json", Dataset.class);
assertEquals(1, d2.getCollectedfrom().size());
assertTrue(cfId(d2.getCollectedfrom()).contains(ModelConstants.ZENODO_OD_ID));
Result res = (Result) MergeUtils.merge(d1, d2, true);
assertEquals(d2, res);
}
@Test
void testDelegatedAuthority_2() throws IOException {
Dataset p1 = read("publication_1.json", Dataset.class);
Dataset d2 = read("dataset_delegated.json", Dataset.class);
assertEquals(1, d2.getCollectedfrom().size());
assertTrue(cfId(d2.getCollectedfrom()).contains(ModelConstants.ZENODO_OD_ID));
Result res = (Result) MergeUtils.merge(p1, d2, true);
assertEquals(d2, res);
}
protected HashSet<String> cfId(List<KeyValue> collectedfrom) {
return collectedfrom.stream().map(KeyValue::getKey).collect(Collectors.toCollection(HashSet::new));
}
protected <T extends Result> T read(String filename, Class<T> clazz) throws IOException {
final String json = IOUtils.toString(getClass().getResourceAsStream(filename));
return OBJECT_MAPPER.readValue(json, clazz);
}
}

12
dhp-common/src/test/java/eu/dnetlib/dhp/schema/oaf/utils/OafMapperUtilsTest.java
View File

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

3
dhp-pace-core/src/main/java/eu/dnetlib/pace/tree/InstanceTypeMatch.java
View File

@ -23,15 +23,18 @@ public class InstanceTypeMatch extends AbstractListComparator {
// jolly types
translationMap.put("Conference object", "*");
translationMap.put("Research", "*");
translationMap.put("Other literature type", "*");
translationMap.put("Unknown", "*");
translationMap.put("UNKNOWN", "*");
// article types
translationMap.put("Article", "Article");
translationMap.put("Journal", "Article");
translationMap.put("Data Paper", "Article");
translationMap.put("Software Paper", "Article");
translationMap.put("Preprint", "Article");
translationMap.put("Part of book or chapter of book", "Article");
// thesis types
translationMap.put("Thesis", "Thesis");

24
dhp-workflows/dhp-actionmanager/src/main/java/eu/dnetlib/dhp/actionmanager/promote/MergeAndGet.java
View File

@ -1,14 +1,13 @@
package eu.dnetlib.dhp.actionmanager.promote;
import static eu.dnetlib.dhp.schema.common.ModelSupport.isSubClass;
import eu.dnetlib.dhp.common.FunctionalInterfaceSupport.SerializableSupplier;
import eu.dnetlib.dhp.schema.oaf.Oaf;
import eu.dnetlib.dhp.schema.oaf.utils.MergeUtils;
import java.util.function.BiFunction;
import eu.dnetlib.dhp.common.FunctionalInterfaceSupport.SerializableSupplier;
import eu.dnetlib.dhp.schema.oaf.Oaf;
import eu.dnetlib.dhp.schema.oaf.OafEntity;
import eu.dnetlib.dhp.schema.oaf.Relation;
import static eu.dnetlib.dhp.schema.common.ModelSupport.isSubClass;
/** OAF model merging support. */
public class MergeAndGet {
@ -46,20 +45,7 @@ public class MergeAndGet {
}
private static <G extends Oaf, A extends Oaf> G mergeFromAndGet(G x, A y) {
if (isSubClass(x, Relation.class) && isSubClass(y, Relation.class)) {
((Relation) x).mergeFrom((Relation) y);
return x;
} else if (isSubClass(x, OafEntity.class)
&& isSubClass(y, OafEntity.class)
&& isSubClass(x, y)) {
((OafEntity) x).mergeFrom((OafEntity) y);
return x;
}
throw new RuntimeException(
String
.format(
"MERGE_FROM_AND_GET incompatible types: %s, %s",
x.getClass().getCanonicalName(), y.getClass().getCanonicalName()));
return (G) MergeUtils.merge(x, y);
}
@SuppressWarnings("unchecked")

39
dhp-workflows/dhp-actionmanager/src/main/java/eu/dnetlib/dhp/actionmanager/promote/PromoteAction.java Normal file
View File

@ -0,0 +1,39 @@
/*
* Copyright (c) 2024.
* SPDX-FileCopyrightText: © 2023 Consiglio Nazionale delle Ricerche
* SPDX-License-Identifier: AGPL-3.0-or-later
*/
package eu.dnetlib.dhp.actionmanager.promote;
/** Encodes the Actionset promotion strategies */
public class PromoteAction {
/** The supported actionset promotion strategies
*
* ENRICH: promotes only records in the actionset matching another record in the
* graph and enriches them applying the given MergeAndGet strategy
* UPSERT: promotes all the records in an actionset, matching records are updated
* using the given MergeAndGet strategy, the non-matching record as inserted as they are.
*/
public enum Strategy {
ENRICH, UPSERT
}
/**
* Returns the string representation of the join type implementing the given PromoteAction.
*
* @param strategy the strategy to be used to promote the Actionset contents
* @return the join type used to implement the promotion strategy
*/
public static String joinTypeForStrategy(PromoteAction.Strategy strategy) {
switch (strategy) {
case ENRICH:
return "left_outer";
case UPSERT:
return "full_outer";
default:
throw new IllegalStateException("unsupported PromoteAction: " + strategy.toString());
}
}
}

29
dhp-workflows/dhp-actionmanager/src/main/java/eu/dnetlib/dhp/actionmanager/promote/PromoteActionPayloadForGraphTableJob.java
View File

@ -67,8 +67,9 @@ public class PromoteActionPayloadForGraphTableJob {
String outputGraphTablePath = parser.get("outputGraphTablePath");
logger.info("outputGraphTablePath: {}", outputGraphTablePath);
MergeAndGet.Strategy strategy = MergeAndGet.Strategy.valueOf(parser.get("mergeAndGetStrategy").toUpperCase());
logger.info("strategy: {}", strategy);
MergeAndGet.Strategy mergeAndGetStrategy = MergeAndGet.Strategy
.valueOf(parser.get("mergeAndGetStrategy").toUpperCase());
logger.info("mergeAndGetStrategy: {}", mergeAndGetStrategy);
Boolean shouldGroupById = Optional
.ofNullable(parser.get("shouldGroupById"))
@ -76,6 +77,12 @@ public class PromoteActionPayloadForGraphTableJob {
.orElse(true);
logger.info("shouldGroupById: {}", shouldGroupById);
PromoteAction.Strategy promoteActionStrategy = Optional
.ofNullable(parser.get("promoteActionStrategy"))
.map(PromoteAction.Strategy::valueOf)
.orElse(PromoteAction.Strategy.UPSERT);
logger.info("promoteActionStrategy: {}", promoteActionStrategy);
@SuppressWarnings("unchecked")
Class<? extends Oaf> rowClazz = (Class<? extends Oaf>) Class.forName(graphTableClassName);
@SuppressWarnings("unchecked")
@ -97,7 +104,8 @@ public class PromoteActionPayloadForGraphTableJob {
inputGraphTablePath,
inputActionPayloadPath,
outputGraphTablePath,
strategy,
mergeAndGetStrategy,
promoteActionStrategy,
rowClazz,
actionPayloadClazz,
shouldGroupById);
@ -124,14 +132,16 @@ public class PromoteActionPayloadForGraphTableJob {
String inputGraphTablePath,
String inputActionPayloadPath,
String outputGraphTablePath,
MergeAndGet.Strategy strategy,
MergeAndGet.Strategy mergeAndGetStrategy,
PromoteAction.Strategy promoteActionStrategy,
Class<G> rowClazz,
Class<A> actionPayloadClazz, Boolean shouldGroupById) {
Dataset<G> rowDS = readGraphTable(spark, inputGraphTablePath, rowClazz);
Dataset<A> actionPayloadDS = readActionPayload(spark, inputActionPayloadPath, actionPayloadClazz);
Dataset<G> result = promoteActionPayloadForGraphTable(
rowDS, actionPayloadDS, strategy, rowClazz, actionPayloadClazz, shouldGroupById)
rowDS, actionPayloadDS, mergeAndGetStrategy, promoteActionStrategy, rowClazz, actionPayloadClazz,
shouldGroupById)
.map((MapFunction<G, G>) value -> value, Encoders.bean(rowClazz));
saveGraphTable(result, outputGraphTablePath);
@ -183,7 +193,8 @@ public class PromoteActionPayloadForGraphTableJob {
private static <G extends Oaf, A extends Oaf> Dataset<G> promoteActionPayloadForGraphTable(
Dataset<G> rowDS,
Dataset<A> actionPayloadDS,
MergeAndGet.Strategy strategy,
MergeAndGet.Strategy mergeAndGetStrategy,
PromoteAction.Strategy promoteActionStrategy,
Class<G> rowClazz,
Class<A> actionPayloadClazz,
Boolean shouldGroupById) {
@ -195,8 +206,9 @@ public class PromoteActionPayloadForGraphTableJob {
SerializableSupplier<Function<G, String>> rowIdFn = ModelSupport::idFn;
SerializableSupplier<Function<A, String>> actionPayloadIdFn = ModelSupport::idFn;
SerializableSupplier<BiFunction<G, A, G>> mergeRowWithActionPayloadAndGetFn = MergeAndGet.functionFor(strategy);
SerializableSupplier<BiFunction<G, G, G>> mergeRowsAndGetFn = MergeAndGet.functionFor(strategy);
SerializableSupplier<BiFunction<G, A, G>> mergeRowWithActionPayloadAndGetFn = MergeAndGet
.functionFor(mergeAndGetStrategy);
SerializableSupplier<BiFunction<G, G, G>> mergeRowsAndGetFn = MergeAndGet.functionFor(mergeAndGetStrategy);
SerializableSupplier<G> zeroFn = zeroFn(rowClazz);
SerializableSupplier<Function<G, Boolean>> isNotZeroFn = PromoteActionPayloadForGraphTableJob::isNotZeroFnUsingIdOrSourceAndTarget;
@ -207,6 +219,7 @@ public class PromoteActionPayloadForGraphTableJob {
rowIdFn,
actionPayloadIdFn,
mergeRowWithActionPayloadAndGetFn,
promoteActionStrategy,
rowClazz,
actionPayloadClazz);

4
dhp-workflows/dhp-actionmanager/src/main/java/eu/dnetlib/dhp/actionmanager/promote/PromoteActionPayloadFunctions.java
View File

@ -34,6 +34,7 @@ public class PromoteActionPayloadFunctions {
* @param rowIdFn Function used to get the id of graph table row
* @param actionPayloadIdFn Function used to get id of action payload instance
* @param mergeAndGetFn Function used to merge graph table row and action payload instance
* @param promoteActionStrategy the Actionset promotion strategy
* @param rowClazz Class of graph table
* @param actionPayloadClazz Class of action payload
* @param <G> Type of graph table row
@ -46,6 +47,7 @@ public class PromoteActionPayloadFunctions {
SerializableSupplier<Function<G, String>> rowIdFn,
SerializableSupplier<Function<A, String>> actionPayloadIdFn,
SerializableSupplier<BiFunction<G, A, G>> mergeAndGetFn,
PromoteAction.Strategy promoteActionStrategy,
Class<G> rowClazz,
Class<A> actionPayloadClazz) {
if (!isSubClass(rowClazz, actionPayloadClazz)) {
@ -61,7 +63,7 @@ public class PromoteActionPayloadFunctions {
.joinWith(
actionPayloadWithIdDS,
rowWithIdDS.col("_1").equalTo(actionPayloadWithIdDS.col("_1")),
"full_outer")
PromoteAction.joinTypeForStrategy(promoteActionStrategy))
.map(
(MapFunction<Tuple2<Tuple2<String, G>, Tuple2<String, A>>, G>) value -> {
Optional<G> rowOpt = Optional.ofNullable(value._1()).map(Tuple2::_2);

6
dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/promote/promote_action_payload_for_graph_table_input_parameters.json
View File

@ -41,6 +41,12 @@
"paramDescription": "strategy for merging graph table objects with action payload instances, MERGE_FROM_AND_GET or SELECT_NEWER_AND_GET",
"paramRequired": true
},
{
"paramName": "pas",
"paramLongName": "promoteActionStrategy",
"paramDescription": "strategy for promoting the actionset contents into the graph tables, ENRICH or UPSERT (default)",
"paramRequired": false
},
{
"paramName": "sgid",
"paramLongName": "shouldGroupById",

2
dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/dataset/oozie_app/workflow.xml
View File

@ -115,6 +115,7 @@
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
<arg>--outputGraphTablePath</arg><arg>${workingDir}/dataset</arg>
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
<arg>--promoteActionStrategy</arg><arg>${promoteActionStrategy}</arg>
<arg>--shouldGroupById</arg><arg>${shouldGroupById}</arg>
</spark>
<ok to="DecisionPromoteResultActionPayloadForDatasetTable"/>
@ -167,6 +168,7 @@
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Result</arg>
<arg>--outputGraphTablePath</arg><arg>${outputGraphRootPath}/dataset</arg>
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
<arg>--promoteActionStrategy</arg><arg>${promoteActionStrategy}</arg>
<arg>--shouldGroupById</arg><arg>${shouldGroupById}</arg>
</spark>
<ok to="End"/>

1
dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/datasource/oozie_app/workflow.xml
View File

@ -106,6 +106,7 @@
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Datasource</arg>
<arg>--outputGraphTablePath</arg><arg>${outputGraphRootPath}/datasource</arg>
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
<arg>--promoteActionStrategy</arg><arg>${promoteActionStrategy}</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>

1
dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/organization/oozie_app/workflow.xml
View File

@ -106,6 +106,7 @@
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Organization</arg>
<arg>--outputGraphTablePath</arg><arg>${outputGraphRootPath}/organization</arg>
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
<arg>--promoteActionStrategy</arg><arg>${promoteActionStrategy}</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>

2
dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/otherresearchproduct/oozie_app/workflow.xml
View File

@ -114,6 +114,7 @@
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
<arg>--outputGraphTablePath</arg><arg>${workingDir}/otherresearchproduct</arg>
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
<arg>--promoteActionStrategy</arg><arg>${promoteActionStrategy}</arg>
<arg>--shouldGroupById</arg><arg>${shouldGroupById}</arg>
</spark>
<ok to="DecisionPromoteResultActionPayloadForOtherResearchProductTable"/>
@ -166,6 +167,7 @@
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Result</arg>
<arg>--outputGraphTablePath</arg><arg>${outputGraphRootPath}/otherresearchproduct</arg>
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
<arg>--promoteActionStrategy</arg><arg>${promoteActionStrategy}</arg>
<arg>--shouldGroupById</arg><arg>${shouldGroupById}</arg>
</spark>
<ok to="End"/>

1
dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/project/oozie_app/workflow.xml
View File

@ -106,6 +106,7 @@
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Project</arg>
<arg>--outputGraphTablePath</arg><arg>${outputGraphRootPath}/project</arg>
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
<arg>--promoteActionStrategy</arg><arg>${promoteActionStrategy}</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>

2
dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/publication/oozie_app/workflow.xml
View File

@ -115,6 +115,7 @@
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
<arg>--outputGraphTablePath</arg><arg>${workingDir}/publication</arg>
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
<arg>--promoteActionStrategy</arg><arg>${promoteActionStrategy}</arg>
<arg>--shouldGroupById</arg><arg>${shouldGroupById}</arg>
</spark>
<ok to="DecisionPromoteResultActionPayloadForPublicationTable"/>
@ -167,6 +168,7 @@
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Result</arg>
<arg>--outputGraphTablePath</arg><arg>${outputGraphRootPath}/publication</arg>
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
<arg>--promoteActionStrategy</arg><arg>${promoteActionStrategy}</arg>
<arg>--shouldGroupById</arg><arg>${shouldGroupById}</arg>
</spark>
<ok to="End"/>

1
dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/relation/oozie_app/workflow.xml
View File

@ -107,6 +107,7 @@
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Relation</arg>
<arg>--outputGraphTablePath</arg><arg>${outputGraphRootPath}/relation</arg>
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
<arg>--promoteActionStrategy</arg><arg>${promoteActionStrategy}</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>

2
dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/software/oozie_app/workflow.xml
View File

@ -114,6 +114,7 @@
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
<arg>--outputGraphTablePath</arg><arg>${workingDir}/software</arg>
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
<arg>--promoteActionStrategy</arg><arg>${promoteActionStrategy}</arg>
<arg>--shouldGroupById</arg><arg>${shouldGroupById}</arg>
</spark>
<ok to="DecisionPromoteResultActionPayloadForSoftwareTable"/>
@ -166,6 +167,7 @@
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Result</arg>
<arg>--outputGraphTablePath</arg><arg>${outputGraphRootPath}/software</arg>
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
<arg>--promoteActionStrategy</arg><arg>${promoteActionStrategy}</arg>
<arg>--shouldGroupById</arg><arg>${shouldGroupById}</arg>
</spark>
<ok to="End"/>

4
dhp-workflows/dhp-actionmanager/src/test/java/eu/dnetlib/dhp/actionmanager/promote/PromoteActionPayloadFunctionsTest.java
View File

@ -54,7 +54,7 @@ public class PromoteActionPayloadFunctionsTest {
RuntimeException.class,
() -> PromoteActionPayloadFunctions
.joinGraphTableWithActionPayloadAndMerge(
null, null, null, null, null, OafImplSubSub.class, OafImpl.class));
null, null, null, null, null, null, OafImplSubSub.class, OafImpl.class));
}
@Test
@ -104,6 +104,7 @@ public class PromoteActionPayloadFunctionsTest {
rowIdFn,
actionPayloadIdFn,
mergeAndGetFn,
PromoteAction.Strategy.UPSERT,
OafImplSubSub.class,
OafImplSubSub.class)
.collectAsList();
@ -183,6 +184,7 @@ public class PromoteActionPayloadFunctionsTest {
rowIdFn,
actionPayloadIdFn,
mergeAndGetFn,
PromoteAction.Strategy.UPSERT,
OafImplSubSub.class,
OafImplSub.class)
.collectAsList();

9
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/bipaffiliations/PrepareAffiliationRelations.java
View File

@ -64,6 +64,9 @@ public class PrepareAffiliationRelations implements Serializable {
final String pubmedInputPath = parser.get("pubmedInputPath");
log.info("pubmedInputPath: {}", pubmedInputPath);
final String openapcInputPath = parser.get("openapcInputPath");
log.info("openapcInputPath: {}", openapcInputPath);
final String outputPath = parser.get("outputPath");
log.info("outputPath: {}", outputPath);
@ -85,8 +88,14 @@ public class PrepareAffiliationRelations implements Serializable {
JavaPairRDD<Text, Text> pubmedRelations = prepareAffiliationRelations(
spark, pubmedInputPath, collectedFromPubmed);
List<KeyValue> collectedFromOpenAPC = OafMapperUtils
.listKeyValues(ModelConstants.OPEN_APC_ID, "OpenAPC");
JavaPairRDD<Text, Text> openAPCRelations = prepareAffiliationRelations(
spark, openapcInputPath, collectedFromOpenAPC);
crossrefRelations
.union(pubmedRelations)
.union(openAPCRelations)
.saveAsHadoopFile(
outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class);

5
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/bipmodel/score/deserializers/BipProjectModel.java
View File

@ -34,6 +34,11 @@ public class BipProjectModel {
String totalCitationCount;
public String getProjectId() {
return projectId;
}
// each project bip measure has exactly one value, hence one key-value pair
private Measure createMeasure(String measureId, String measureValue) {

50
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/project/SparkAtomicActionJob.java
View File

@ -1,12 +1,20 @@
package eu.dnetlib.dhp.actionmanager.project;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import java.util.Arrays;
import java.util.Objects;
import java.util.Optional;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.actionmanager.project.utils.model.CSVProgramme;
import eu.dnetlib.dhp.actionmanager.project.utils.model.CSVProject;
import eu.dnetlib.dhp.actionmanager.project.utils.model.JsonTopic;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.schema.action.AtomicAction;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.H2020Classification;
import eu.dnetlib.dhp.schema.oaf.H2020Programme;
import eu.dnetlib.dhp.schema.oaf.OafEntity;
import eu.dnetlib.dhp.schema.oaf.Project;
import eu.dnetlib.dhp.schema.oaf.utils.MergeUtils;
import eu.dnetlib.dhp.utils.DHPUtils;
import org.apache.commons.io.IOUtils;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.SequenceFileOutputFormat;
@ -18,24 +26,14 @@ import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.SparkSession;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.actionmanager.project.utils.model.CSVProgramme;
import eu.dnetlib.dhp.actionmanager.project.utils.model.CSVProject;
import eu.dnetlib.dhp.actionmanager.project.utils.model.EXCELTopic;
import eu.dnetlib.dhp.actionmanager.project.utils.model.JsonTopic;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.schema.action.AtomicAction;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.H2020Classification;
import eu.dnetlib.dhp.schema.oaf.H2020Programme;
import eu.dnetlib.dhp.schema.oaf.OafEntity;
import eu.dnetlib.dhp.schema.oaf.Project;
import eu.dnetlib.dhp.utils.DHPUtils;
import scala.Tuple2;
import java.util.Arrays;
import java.util.Objects;
import java.util.Optional;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
/**
* Class that makes the ActionSet. To prepare the AS two joins are needed
*
@ -160,9 +158,11 @@ public class SparkAtomicActionJob {
(MapFunction<Project, String>) OafEntity::getId,
Encoders.STRING())
.mapGroups((MapGroupsFunction<String, Project, Project>) (s, it) -> {
Project first = it.next();
it.forEachRemaining(first::mergeFrom);
return first;
Project merge = it.next();
while (it.hasNext()) {
merge = MergeUtils.mergeProject(merge, it.next());
}
return merge;
}, Encoders.bean(Project.class))
.toJavaRDD()
.map(p -> new AtomicAction(Project.class, p))

195
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/transformativeagreement/CreateActionSetSparkJob.java Normal file
View File

@ -0,0 +1,195 @@
package eu.dnetlib.dhp.actionmanager.transformativeagreement;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import java.io.IOException;
import java.io.Serializable;
import java.util.*;
import org.apache.commons.cli.ParseException;
import org.apache.commons.io.IOUtils;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.compress.GzipCodec;
import org.apache.hadoop.mapred.SequenceFileOutputFormat;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.function.FilterFunction;
import org.apache.spark.api.java.function.FlatMapFunction;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.SparkSession;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.actionmanager.transformativeagreement.model.TransformativeAgreementModel;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.schema.action.AtomicAction;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.Country;
import eu.dnetlib.dhp.schema.oaf.Relation;
import eu.dnetlib.dhp.schema.oaf.Result;
import eu.dnetlib.dhp.schema.oaf.utils.*;
import scala.Tuple2;
public class CreateActionSetSparkJob implements Serializable {
private static final Logger log = LoggerFactory.getLogger(CreateActionSetSparkJob.class);
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
private static final String IREL_PROJECT = "40|100018998___::1e5e62235d094afd01cd56e65112fc63";
private static final String TRANSFORMATIVE_AGREEMENT = "openapc::transformativeagreement";
public static void main(final String[] args) throws IOException, ParseException {
final ArgumentApplicationParser parser = new ArgumentApplicationParser(
IOUtils
.toString(
Objects
.requireNonNull(
CreateActionSetSparkJob.class
.getResourceAsStream(
"/eu/dnetlib/dhp/actionmanager/transformativeagreement/as_parameters.json"))));
parser.parseArgument(args);
Boolean isSparkSessionManaged = Optional
.ofNullable(parser.get("isSparkSessionManaged"))
.map(Boolean::valueOf)
.orElse(Boolean.TRUE);
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
final String inputPath = parser.get("inputPath");
log.info("inputPath {}", inputPath);
final String outputPath = parser.get("outputPath");
log.info("outputPath {}", outputPath);
SparkConf conf = new SparkConf();
runWithSparkSession(
conf,
isSparkSessionManaged,
spark -> createActionSet(spark, inputPath, outputPath));
}
private static void createActionSet(SparkSession spark, String inputPath, String outputPath) {
JavaRDD<AtomicAction> relations = spark
.read()
.textFile(inputPath)
.map(
(MapFunction<String, TransformativeAgreementModel>) value -> OBJECT_MAPPER
.readValue(value, TransformativeAgreementModel.class),
Encoders.bean(TransformativeAgreementModel.class))
.flatMap(
(FlatMapFunction<TransformativeAgreementModel, Relation>) value -> createRelation(
value)
.iterator(),
Encoders.bean(Relation.class))
.filter((FilterFunction<Relation>) Objects::nonNull)
.toJavaRDD()
.map(p -> new AtomicAction(p.getClass(), p));
//TODO relations in stand-by waiting to know if we need to create them or not In case we need just make a union before saving the sequence file
spark
.read()
.textFile(inputPath)
.map(
(MapFunction<String, TransformativeAgreementModel>) value -> OBJECT_MAPPER
.readValue(value, TransformativeAgreementModel.class),
Encoders.bean(TransformativeAgreementModel.class))
.map(
(MapFunction<TransformativeAgreementModel, Result>) value -> createResult(
value),
Encoders.bean(Result.class))
.filter((FilterFunction<Result>) r -> r != null)
.toJavaRDD()
.map(p -> new AtomicAction(p.getClass(), p))
.mapToPair(
aa -> new Tuple2<>(new Text(aa.getClazz().getCanonicalName()),
new Text(OBJECT_MAPPER.writeValueAsString(aa))))
.saveAsHadoopFile(
outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class);
}
private static Result createResult(TransformativeAgreementModel value) {
Result r = new Result();
r
.setId(
"50|doi_________::"
+ IdentifierFactory
.md5(PidCleaner.normalizePidValue(PidType.doi.toString(), value.getDoi())));
r.setTransformativeAgreement(value.getAgreement());
Country country = new Country();
country.setClassid(value.getCountry());
country.setClassname(value.getCountry());
country
.setDataInfo(
OafMapperUtils
.dataInfo(
false, ModelConstants.SYSIMPORT_ACTIONSET, false, false,
OafMapperUtils
.qualifier(
"openapc::transformativeagreement",
"Harvested from Trnasformative Agreement file from OpenAPC",
ModelConstants.DNET_PROVENANCE_ACTIONS, ModelConstants.DNET_PROVENANCE_ACTIONS),
"0.9"));
country.setSchemeid(ModelConstants.DNET_COUNTRY_TYPE);
country.setSchemename(ModelConstants.DNET_COUNTRY_TYPE);
r.setCountry(Arrays.asList(country));
return r;
}
private static List<Relation> createRelation(TransformativeAgreementModel value) {
List<Relation> relationList = new ArrayList<>();
if (value.getAgreement().startsWith("IReL")) {
String paper;
paper = "50|doi_________::"
+ IdentifierFactory
.md5(PidCleaner.normalizePidValue(PidType.doi.toString(), value.getDoi()));
relationList
.add(
getRelation(
paper,
IREL_PROJECT, ModelConstants.IS_PRODUCED_BY));
relationList.add(getRelation(IREL_PROJECT, paper, ModelConstants.PRODUCES));
}
return relationList;
}
public static Relation getRelation(
String source,
String target,
String relClass) {
return OafMapperUtils
.getRelation(
source,
target,
ModelConstants.RESULT_PROJECT,
ModelConstants.OUTCOME,
relClass,
Arrays
.asList(
OafMapperUtils.keyValue(ModelConstants.OPEN_APC_ID, ModelConstants.OPEN_APC_NAME)),
OafMapperUtils
.dataInfo(
false, null, false, false,
OafMapperUtils
.qualifier(
TRANSFORMATIVE_AGREEMENT, "Transformative Agreement",
ModelConstants.DNET_PROVENANCE_ACTIONS, ModelConstants.DNET_PROVENANCE_ACTIONS),
"0.9"),
null);
}
}

51
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/transformativeagreement/model/TransformativeAgreementModel.java Normal file
View File

@ -0,0 +1,51 @@
package eu.dnetlib.dhp.actionmanager.transformativeagreement.model;
import java.io.Serializable;
import com.fasterxml.jackson.annotation.JsonIgnoreProperties;
/**
* @author miriam.baglioni
* @Date 18/12/23
*/
@JsonIgnoreProperties(ignoreUnknown = true)
public class TransformativeAgreementModel implements Serializable {
private String institution;
private String doi;
private String agreement;
private String country;
public String getCountry() {
return country;
}
public void setCountry(String country) {
this.country = country;
}
public String getInstitution() {
return institution;
}
public void setInstitution(String institution) {
this.institution = institution;
}
public String getDoi() {
return doi;
}
public void setDoi(String doi) {
this.doi = doi;
}
public String getAgreement() {
return agreement;
}
public void setAgreement(String agreement) {
this.agreement = agreement;
}
}

3
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/collection/CollectorWorker.java
View File

@ -19,6 +19,7 @@ import org.slf4j.LoggerFactory;
import eu.dnetlib.dhp.aggregation.common.ReporterCallback;
import eu.dnetlib.dhp.aggregation.common.ReportingJob;
import eu.dnetlib.dhp.collection.plugin.CollectorPlugin;
import eu.dnetlib.dhp.collection.plugin.base.BaseCollectorPlugin;
import eu.dnetlib.dhp.collection.plugin.file.FileCollectorPlugin;
import eu.dnetlib.dhp.collection.plugin.file.FileGZipCollectorPlugin;
import eu.dnetlib.dhp.collection.plugin.mongodb.MDStoreCollectorPlugin;
@ -120,6 +121,8 @@ public class CollectorWorker extends ReportingJob {
return new FileCollectorPlugin(fileSystem);
case fileGzip:
return new FileGZipCollectorPlugin(fileSystem);
case baseDump:
return new BaseCollectorPlugin(this.fileSystem);
case other:
final CollectorPlugin.NAME.OTHER_NAME plugin = Optional
.ofNullable(api.getParams().get("other_plugin_type"))

244
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/collection/orcid/ORCIDWorker.java Normal file
View File

@ -0,0 +1,244 @@
package eu.dnetlib.dhp.collection.orcid;
import java.io.IOException;
import java.io.InputStream;
import java.net.HttpURLConnection;
import java.net.URL;
import java.util.concurrent.BlockingQueue;
import javax.swing.*;
import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.StringUtils;
import org.apache.hadoop.io.SequenceFile;
import org.apache.hadoop.io.Text;
import org.apache.http.HttpHeaders;
import org.jetbrains.annotations.NotNull;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import eu.dnetlib.dhp.common.collection.HttpClientParams;
public class ORCIDWorker extends Thread {
final static Logger log = LoggerFactory.getLogger(ORCIDWorker.class);
public static String JOB_COMPLETE = "JOB_COMPLETE";
private static final String userAgent = "Mozilla/5.0 (compatible; OAI; +http://www.openaire.eu)";
private final BlockingQueue<String> queue;
private boolean hasComplete = false;
private final SequenceFile.Writer employments;
private final SequenceFile.Writer summary;
private final SequenceFile.Writer works;
private final String token;
private final String id;
public static ORCIDWorkerBuilder builder() {
return new ORCIDWorkerBuilder();
}
public ORCIDWorker(String id, BlockingQueue<String> myqueue, SequenceFile.Writer employments,
SequenceFile.Writer summary, SequenceFile.Writer works, String token) {
this.id = id;
this.queue = myqueue;
this.employments = employments;
this.summary = summary;
this.works = works;
this.token = token;
}
public static String retrieveURL(final String id, final String apiUrl, String token) {
try {
final HttpURLConnection urlConn = getHttpURLConnection(apiUrl, token);
if (urlConn.getResponseCode() > 199 && urlConn.getResponseCode() < 300) {
InputStream input = urlConn.getInputStream();
return IOUtils.toString(input);
} else {
log
.error(
"Thread {} UNABLE TO DOWNLOAD FROM THIS URL {} , status code {}", id, apiUrl,
urlConn.getResponseCode());
}
} catch (Exception e) {
log.error("Thread {} Error on retrieving URL {} {}", id, apiUrl, e);
}
return null;
}
@NotNull
private static HttpURLConnection getHttpURLConnection(String apiUrl, String token) throws IOException {
final HttpURLConnection urlConn = (HttpURLConnection) new URL(apiUrl).openConnection();
final HttpClientParams clientParams = new HttpClientParams();
urlConn.setInstanceFollowRedirects(false);
urlConn.setReadTimeout(clientParams.getReadTimeOut() * 1000);
urlConn.setConnectTimeout(clientParams.getConnectTimeOut() * 1000);
urlConn.addRequestProperty(HttpHeaders.USER_AGENT, userAgent);
urlConn.addRequestProperty(HttpHeaders.AUTHORIZATION, String.format("Bearer %s", token));
return urlConn;
}
private static String generateSummaryURL(final String orcidId) {
return "https://api.orcid.org/v3.0/" + orcidId + "/record";
}
private static String generateWorksURL(final String orcidId) {
return "https://api.orcid.org/v3.0/" + orcidId + "/works";
}
private static String generateEmploymentsURL(final String orcidId) {
return "https://api.orcid.org/v3.0/" + orcidId + "/employments";
}
private static void writeResultToSequenceFile(String id, String url, String token, String orcidId,
SequenceFile.Writer file) throws IOException {
final String response = retrieveURL(id, url, token);
if (response != null) {
if (orcidId == null) {
log.error("Thread {} {} {}", id, orcidId, response);
throw new RuntimeException("null items ");
}
if (file == null) {
log.error("Thread {} file is null for {} URL:{}", id, url, orcidId);
} else {
file.append(new Text(orcidId), new Text(response));
file.hflush();
}
} else
log.error("Thread {} response is null for {} URL:{}", id, url, orcidId);
}
@Override
public void run() {
final Text key = new Text();
final Text value = new Text();
long start;
long total_time;
String orcidId = "";
int requests = 0;
if (summary == null || employments == null || works == null)
throw new RuntimeException("Null files");
while (!hasComplete) {
try {
orcidId = queue.take();
if (orcidId.equalsIgnoreCase(JOB_COMPLETE)) {
hasComplete = true;
} else {
start = System.currentTimeMillis();
writeResultToSequenceFile(id, generateSummaryURL(orcidId), token, orcidId, summary);
total_time = System.currentTimeMillis() - start;
requests++;
if (total_time < 1000) {
// I know making a sleep on a thread is bad, but we need to stay to 24 requests per seconds,
// hence
// the time between two http request in a thread must be 1 second
Thread.sleep(1000L - total_time);
}
start = System.currentTimeMillis();
writeResultToSequenceFile(id, generateWorksURL(orcidId), token, orcidId, works);
total_time = System.currentTimeMillis() - start;
requests++;
if (total_time < 1000) {
// I know making a sleep on a thread is bad, but we need to stay to 24 requests per seconds,
// hence
// the time between two http request in a thread must be 1 second
Thread.sleep(1000L - total_time);
}
start = System.currentTimeMillis();
writeResultToSequenceFile(id, generateEmploymentsURL(orcidId), token, orcidId, employments);
total_time = System.currentTimeMillis() - start;
requests++;
if (total_time < 1000) {
// I know making a sleep on a thread is bad, but we need to stay to 24 requests per seconds,
// hence
// the time between two http request in a thread must be 1 second
Thread.sleep(1000L - total_time);
}
if (requests % 30 == 0) {
log.info("Thread {} Downloaded {}", id, requests);
}
}
} catch (Throwable e) {
log.error("Thread {} Unable to save ORICD: {} item error", id, orcidId, e);
}
}
try {
works.close();
summary.close();
employments.close();
} catch (Throwable e) {
throw new RuntimeException(e);
}
log.info("Thread {} COMPLETE ", id);
log.info("Thread {} Downloaded {}", id, requests);
}
public static class ORCIDWorkerBuilder {
private String id;
private SequenceFile.Writer employments;
private SequenceFile.Writer summary;
private SequenceFile.Writer works;
private BlockingQueue<String> queue;
private String token;
public ORCIDWorkerBuilder withId(final String id) {
this.id = id;
return this;
}
public ORCIDWorkerBuilder withEmployments(final SequenceFile.Writer sequenceFile) {
this.employments = sequenceFile;
return this;
}
public ORCIDWorkerBuilder withSummary(final SequenceFile.Writer sequenceFile) {
this.summary = sequenceFile;
return this;
}
public ORCIDWorkerBuilder withWorks(final SequenceFile.Writer sequenceFile) {
this.works = sequenceFile;
return this;
}
public ORCIDWorkerBuilder withAccessToken(final String accessToken) {
this.token = accessToken;
return this;
}
public ORCIDWorkerBuilder withBlockingQueue(final BlockingQueue<String> queue) {
this.queue = queue;
return this;
}
public ORCIDWorker build() {
if (this.summary == null || this.works == null || this.employments == null || StringUtils.isEmpty(token)
|| queue == null)
throw new RuntimeException("Unable to build missing required params");
return new ORCIDWorker(id, queue, employments, summary, works, token);
}
}
}

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

@ -0,0 +1,171 @@
package eu.dnetlib.dhp.collection.orcid;
import static eu.dnetlib.dhp.utils.DHPUtils.getHadoopConfiguration;
import java.io.*;
import java.net.HttpURLConnection;
import java.net.URL;
import java.util.ArrayList;
import java.util.List;
import java.util.Objects;
import java.util.concurrent.ArrayBlockingQueue;
import java.util.concurrent.BlockingQueue;
import org.apache.commons.compress.archivers.tar.TarArchiveEntry;
import org.apache.commons.compress.archivers.tar.TarArchiveInputStream;
import org.apache.commons.compress.compressors.gzip.GzipCompressorInputStream;
import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.StringUtils;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.SequenceFile;
import org.apache.hadoop.io.Text;
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.collection.HttpClientParams;
public class OrcidGetUpdatesFile {
private static Logger log = LoggerFactory.getLogger(OrcidGetUpdatesFile.class);
public static void main(String[] args) throws Exception {
ArgumentApplicationParser parser = new ArgumentApplicationParser(
IOUtils
.toString(
Objects
.requireNonNull(
OrcidGetUpdatesFile.class
.getResourceAsStream(
"/eu/dnetlib/dhp/collection/orcid/download_orcid_update_parameter.json")))
);
parser.parseArgument(args);
final String namenode = parser.get("namenode");
log.info("got variable namenode: {}", namenode);
final String master = parser.get("master");
log.info("got variable master: {}", master);
final String targetPath = parser.get("targetPath");
log.info("got variable targetPath: {}", targetPath);
final String apiURL = parser.get("apiURL");
log.info("got variable apiURL: {}", apiURL);
final String accessToken = parser.get("accessToken");
log.info("got variable accessToken: {}", accessToken);
final String graphPath = parser.get("graphPath");
log.info("got variable graphPath: {}", graphPath);
final SparkSession spark = SparkSession
.builder()
.appName(OrcidGetUpdatesFile.class.getName())
.master(master)
.getOrCreate();
final String latestDate = spark
.read()
.load(graphPath + "/Authors")
.selectExpr("max(lastModifiedDate)")
.first()
.getString(0);
log.info("latest date is {}", latestDate);
final FileSystem fileSystem = FileSystem.get(getHadoopConfiguration(namenode));
new OrcidGetUpdatesFile().readTar(fileSystem, accessToken, apiURL, targetPath, latestDate);
}
private SequenceFile.Writer createFile(Path aPath, FileSystem fileSystem) throws IOException {
return SequenceFile
.createWriter(
fileSystem.getConf(),
SequenceFile.Writer.file(aPath),
SequenceFile.Writer.keyClass(Text.class),
SequenceFile.Writer.valueClass(Text.class));
}
private ORCIDWorker createWorker(final String id, final String targetPath, final BlockingQueue<String> queue,
final String accessToken, FileSystem fileSystem) throws Exception {
return ORCIDWorker
.builder()
.withId(id)
.withEmployments(createFile(new Path(String.format("%s/employments_%s", targetPath, id)), fileSystem))
.withSummary(createFile(new Path(String.format("%s/summary_%s", targetPath, id)), fileSystem))
.withWorks(createFile(new Path(String.format("%s/works_%s", targetPath, id)), fileSystem))
.withAccessToken(accessToken)
.withBlockingQueue(queue)
.build();
}
public void readTar(FileSystem fileSystem, final String accessToken, final String apiURL, final String targetPath,
final String startDate) throws Exception {
final HttpURLConnection urlConn = (HttpURLConnection) new URL(apiURL).openConnection();
final HttpClientParams clientParams = new HttpClientParams();
urlConn.setInstanceFollowRedirects(false);
urlConn.setReadTimeout(clientParams.getReadTimeOut() * 1000);
urlConn.setConnectTimeout(clientParams.getConnectTimeOut() * 1000);
if (urlConn.getResponseCode() > 199 && urlConn.getResponseCode() < 300) {
InputStream input = urlConn.getInputStream();
Path hdfsWritePath = new Path("/tmp/orcid_updates.tar.gz");
final FSDataOutputStream fsDataOutputStream = fileSystem.create(hdfsWritePath, true);
IOUtils.copy(input, fsDataOutputStream);
fsDataOutputStream.flush();
fsDataOutputStream.close();
FSDataInputStream updateFile = fileSystem.open(hdfsWritePath);
TarArchiveInputStream tais = new TarArchiveInputStream(new GzipCompressorInputStream(
new BufferedInputStream(
updateFile.getWrappedStream())));
TarArchiveEntry entry;
BlockingQueue<String> queue = new ArrayBlockingQueue<String>(3000);
final List<ORCIDWorker> workers = new ArrayList<>();
for (int i = 0; i < 22; i++) {
workers.add(createWorker("" + i, targetPath, queue, accessToken, fileSystem));
}
workers.forEach(Thread::start);
while ((entry = tais.getNextTarEntry()) != null) {
if (entry.isFile()) {
BufferedReader br = new BufferedReader(new InputStreamReader(tais));
System.out.println(br.readLine());
br
.lines()
.map(l -> l.split(","))
.filter(s -> StringUtils.compare(s[3].substring(0, 10), startDate) > 0)
.map(s -> s[0])
.forEach(s -> {
try {
queue.put(s);
} catch (InterruptedException e) {
throw new RuntimeException(e);
}
});
}
}
for (int i = 0; i < 22; i++) {
queue.put(ORCIDWorker.JOB_COMPLETE);
}
for (ORCIDWorker worker : workers) {
worker.join();
}
}
}
}

185
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/collection/orcid/OrcidParser.java
View File

@ -1,11 +1,15 @@
package eu.dnetlib.dhp.collection.orcid;
import java.util.Arrays;
import java.util.Collections;
import java.util.List;
import java.util.*;
import java.util.stream.Collectors;
import org.apache.commons.lang3.StringUtils;
import org.dom4j.Document;
import org.dom4j.DocumentFactory;
import org.dom4j.DocumentHelper;
import org.dom4j.Node;
import org.jetbrains.annotations.NotNull;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
@ -40,8 +44,8 @@ public class OrcidParser {
private static final String NS_ERROR = "error";
private static final String NS_HISTORY = "history";
private static final String NS_HISTORY_URL = "http://www.orcid.org/ns/history";
private static final String NS_BULK_URL = "http://www.orcid.org/ns/bulk";
private static final String NS_BULK = "bulk";
private static final String NS_EMPLOYMENT = "employment";
private static final String NS_EMPLOYMENT_URL = "http://www.orcid.org/ns/employment";
private static final String NS_EXTERNAL = "external-identifier";
private static final String NS_EXTERNAL_URL = "http://www.orcid.org/ns/external-identifier";
@ -61,6 +65,7 @@ public class OrcidParser {
ap.declareXPathNameSpace(NS_WORK, NS_WORK_URL);
ap.declareXPathNameSpace(NS_EXTERNAL, NS_EXTERNAL_URL);
ap.declareXPathNameSpace(NS_ACTIVITIES, NS_ACTIVITIES_URL);
ap.declareXPathNameSpace(NS_EMPLOYMENT, NS_EMPLOYMENT_URL);
}
public Author parseSummary(final String xml) {
@ -70,13 +75,15 @@ public class OrcidParser {
generateParsedDocument(xml);
List<VtdUtilityParser.Node> recordNodes = VtdUtilityParser
.getTextValuesWithAttributes(
ap, vn, "//record:record", Arrays.asList("path"));
ap, vn, "//record:record", Collections.singletonList("path"));
if (!recordNodes.isEmpty()) {
final String oid = (recordNodes.get(0).getAttributes().get("path")).substring(1);
author.setOrcid(oid);
} else {
return null;
}
final String ltm = VtdUtilityParser.getSingleValue(ap, vn, "//common:last-modified-date");
author.setLastModifiedDate(ltm);
List<VtdUtilityParser.Node> personNodes = VtdUtilityParser
.getTextValuesWithAttributes(
ap, vn, "//person:name", Arrays.asList("visibility"));
@ -129,6 +136,64 @@ public class OrcidParser {
}
}
public List<Work> parseWorks(final String xml) {
try {
String oid;
generateParsedDocument(xml);
List<VtdUtilityParser.Node> workNodes = VtdUtilityParser
.getTextValuesWithAttributes(ap, vn, "//activities:works", Arrays.asList("path", "visibility"));
if (!workNodes.isEmpty()) {
oid = (workNodes.get(0).getAttributes().get("path")).split("/")[1];
} else {
return null;
}
final List<Work> works = new ArrayList<>();
ap.selectXPath("//work:work-summary");
while (ap.evalXPath() != -1) {
final Work work = new Work();
work.setOrcid(oid);
final AutoPilot ap1 = new AutoPilot(ap.getNav());
ap1.selectXPath("./work:title/common:title");
while (ap1.evalXPath() != -1) {
int it = vn.getText();
work.setTitle(vn.toNormalizedString(it));
}
ap1.selectXPath(".//common:external-id");
while (ap1.evalXPath() != -1) {
final Pid pid = new Pid();
final AutoPilot ap2 = new AutoPilot(ap1.getNav());
ap2.selectXPath("./common:external-id-type");
while (ap2.evalXPath() != -1) {
int it = vn.getText();
pid.setSchema(vn.toNormalizedString(it));
}
ap2.selectXPath("./common:external-id-value");
while (ap2.evalXPath() != -1) {
int it = vn.getText();
pid.setValue(vn.toNormalizedString(it));
}
work.addPid(pid);
}
works.add(work);
}
return works;
} catch (Throwable e) {
log.error("Error on parsing {}", xml);
log.error(e.getMessage());
return null;
}
}
public Work parseWork(final String xml) {
try {
@ -176,11 +241,15 @@ public class OrcidParser {
}
private String extractEmploymentDate(final String xpath) throws Exception {
return extractEmploymentDate(xpath, ap);
}
ap.selectXPath(xpath);
private String extractEmploymentDate(final String xpath, AutoPilot pp) throws Exception {
pp.selectXPath(xpath);
StringBuilder sb = new StringBuilder();
while (ap.evalXPath() != -1) {
final AutoPilot ap1 = new AutoPilot(ap.getNav());
while (pp.evalXPath() != -1) {
final AutoPilot ap1 = new AutoPilot(pp.getNav());
ap1.selectXPath("./common:year");
while (ap1.evalXPath() != -1) {
int it = vn.getText();
@ -203,6 +272,104 @@ public class OrcidParser {
}
public List<Employment> parseEmployments(final String xml) {
try {
String oid;
Map<String, String> nsContext = getNameSpaceMap();
DocumentFactory.getInstance().setXPathNamespaceURIs(nsContext);
Document doc = DocumentHelper.parseText(xml);
oid = doc.valueOf("//activities:employments/@path");
if (oid == null || StringUtils.isEmpty(oid))
return null;
final String orcid = oid.split("/")[1];
List<Node> nodes = doc.selectNodes("//employment:employment-summary");
return nodes.stream().map(n -> {
final Employment e = new Employment();
e.setOrcid(orcid);
final String depName = n.valueOf(".//common:department-name");
if (StringUtils.isNotBlank(depName))
e.setDepartmentName(depName);
final String roleTitle = n.valueOf(".//common:role-title");
e.setRoleTitle(roleTitle);
final String organizationName = n.valueOf(".//common:organization/common:name");
if (StringUtils.isEmpty(e.getDepartmentName()))
e.setDepartmentName(organizationName);
final Pid p = new Pid();
final String pid = n
.valueOf(
"./common:organization/common:disambiguated-organization/common:disambiguated-organization-identifier");
p.setValue(pid);
final String pidType = n
.valueOf("./common:organization/common:disambiguated-organization/common:disambiguation-source");
p.setSchema(pidType);
e.setAffiliationId(p);
final StringBuilder aDate = new StringBuilder();
final String sy = n.valueOf("./common:start-date/common:year");
if (StringUtils.isNotBlank(sy)) {
aDate.append(sy);
final String sm = n.valueOf("./common:start-date/common:month");
final String sd = n.valueOf("./common:start-date/common:day");
aDate.append("-");
if (StringUtils.isNotBlank(sm))
aDate.append(sm);
else
aDate.append("01");
aDate.append("-");
if (StringUtils.isNotBlank(sd))
aDate.append(sd);
else
aDate.append("01");
e.setEndDate(aDate.toString());
}
final String ey = n.valueOf("./common:end-date/common:year");
if (StringUtils.isNotBlank(ey)) {
aDate.append(ey);
final String em = n.valueOf("./common:end-date/common:month");
final String ed = n.valueOf("./common:end-date/common:day");
aDate.append("-");
if (StringUtils.isNotBlank(em))
aDate.append(em);
else
aDate.append("01");
aDate.append("-");
if (StringUtils.isNotBlank(ed))
aDate.append(ed);
else
aDate.append("01");
e.setEndDate(aDate.toString());
}
return e;
}).collect(Collectors.toList());
} catch (Throwable e) {
log.error("Error on parsing {}", xml);
log.error(e.getMessage());
return null;
}
}
@NotNull
private static Map<String, String> getNameSpaceMap() {
Map<String, String> nsContext = new HashMap<>();
nsContext.put(NS_COMMON, NS_COMMON_URL);
nsContext.put(NS_PERSON, NS_PERSON_URL);
nsContext.put(NS_DETAILS, NS_DETAILS_URL);
nsContext.put(NS_OTHER, NS_OTHER_URL);
nsContext.put(NS_RECORD, NS_RECORD_URL);
nsContext.put(NS_ERROR, NS_ERROR_URL);
nsContext.put(NS_HISTORY, NS_HISTORY_URL);
nsContext.put(NS_WORK, NS_WORK_URL);
nsContext.put(NS_EXTERNAL, NS_EXTERNAL_URL);
nsContext.put(NS_ACTIVITIES, NS_ACTIVITIES_URL);
nsContext.put(NS_EMPLOYMENT, NS_EMPLOYMENT_URL);
return nsContext;
}
public Employment parseEmployment(final String xml) {
try {
final Employment employment = new Employment();

10
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/collection/orcid/model/Author.java
View File

@ -18,6 +18,8 @@ public class Author extends ORCIDItem {
private String biography;
private String lastModifiedDate;
public String getBiography() {
return biography;
}
@ -74,6 +76,14 @@ public class Author extends ORCIDItem {
this.otherPids = otherPids;
}
public String getLastModifiedDate() {
return lastModifiedDate;
}
public void setLastModifiedDate(String lastModifiedDate) {
this.lastModifiedDate = lastModifiedDate;
}
public void addOtherPid(final Pid pid) {
if (otherPids == null)

3
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/collection/plugin/CollectorPlugin.java
View File

@ -10,7 +10,8 @@ import eu.dnetlib.dhp.common.collection.CollectorException;
public interface CollectorPlugin {
enum NAME {
oai, other, rest_json2xml, file, fileGzip;
oai, other, rest_json2xml, file, fileGzip, baseDump;
public enum OTHER_NAME {
mdstore_mongodb_dump, mdstore_mongodb

171
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/collection/plugin/base/BaseCollectorIterator.java Normal file
View File

@ -0,0 +1,171 @@
package eu.dnetlib.dhp.collection.plugin.base;
import java.io.BufferedInputStream;
import java.io.ByteArrayInputStream;
import java.io.InputStream;
import java.io.StringWriter;
import java.util.Iterator;
import java.util.concurrent.BlockingQueue;
import java.util.concurrent.LinkedBlockingQueue;
import javax.xml.stream.XMLEventReader;
import javax.xml.stream.XMLEventWriter;
import javax.xml.stream.XMLInputFactory;
import javax.xml.stream.XMLOutputFactory;
import javax.xml.stream.events.EndElement;
import javax.xml.stream.events.StartElement;
import javax.xml.stream.events.XMLEvent;
import org.apache.commons.compress.archivers.tar.TarArchiveEntry;
import org.apache.commons.compress.archivers.tar.TarArchiveInputStream;
import org.apache.commons.compress.compressors.CompressorInputStream;
import org.apache.commons.compress.compressors.CompressorStreamFactory;
import org.apache.commons.io.IOUtils;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import eu.dnetlib.dhp.common.aggregation.AggregatorReport;
public class BaseCollectorIterator implements Iterator<String> {
private String nextElement;
private final BlockingQueue<String> queue = new LinkedBlockingQueue<>(100);
private static final Logger log = LoggerFactory.getLogger(BaseCollectorIterator.class);
private static final String END_ELEM = "__END__";
public BaseCollectorIterator(final FileSystem fs, final Path filePath, final AggregatorReport report) {
new Thread(() -> importHadoopFile(fs, filePath, report)).start();
try {
this.nextElement = this.queue.take();
} catch (final InterruptedException e) {
throw new RuntimeException(e);
}
}
protected BaseCollectorIterator(final String resourcePath, final AggregatorReport report) {
new Thread(() -> importTestFile(resourcePath, report)).start();
try {
this.nextElement = this.queue.take();
} catch (final InterruptedException e) {
throw new RuntimeException(e);
}
}
@Override
public synchronized boolean hasNext() {
return (this.nextElement != null) & !END_ELEM.equals(this.nextElement);
}
@Override
public synchronized String next() {
try {
return END_ELEM.equals(this.nextElement) ? null : this.nextElement;
} finally {
try {
this.nextElement = this.queue.take();
} catch (final InterruptedException e) {
throw new RuntimeException(e);
}
}
}
private void importHadoopFile(final FileSystem fs, final Path filePath, final AggregatorReport report) {
log.info("I start to read the TAR stream");
try (InputStream origInputStream = fs.open(filePath);
final TarArchiveInputStream tarInputStream = new TarArchiveInputStream(origInputStream)) {
importTarStream(tarInputStream, report);
} catch (final Throwable e) {
throw new RuntimeException("Error processing BASE records", e);
}
}
private void importTestFile(final String resourcePath, final AggregatorReport report) {
try (final InputStream origInputStream = BaseCollectorIterator.class.getResourceAsStream(resourcePath);
final TarArchiveInputStream tarInputStream = new TarArchiveInputStream(origInputStream)) {
importTarStream(tarInputStream, report);
} catch (final Throwable e) {
throw new RuntimeException("Error processing BASE records", e);
}
}
private void importTarStream(final TarArchiveInputStream tarInputStream, final AggregatorReport report) {
long count = 0;
final XMLInputFactory xmlInputFactory = XMLInputFactory.newInstance();
final XMLOutputFactory xmlOutputFactory = XMLOutputFactory.newInstance();
try {
TarArchiveEntry entry;
while ((entry = (TarArchiveEntry) tarInputStream.getNextEntry()) != null) {
final String name = entry.getName();
if (!entry.isDirectory() && name.contains("ListRecords") && name.endsWith(".bz2")) {
log.info("Processing file (BZIP): " + name);
final byte[] bzipData = new byte[(int) entry.getSize()];
IOUtils.readFully(tarInputStream, bzipData);
try (InputStream bzipIs = new ByteArrayInputStream(bzipData);
final BufferedInputStream bzipBis = new BufferedInputStream(bzipIs);
final CompressorInputStream bzipInput = new CompressorStreamFactory()
.createCompressorInputStream(bzipBis)) {
final XMLEventReader reader = xmlInputFactory.createXMLEventReader(bzipInput);
XMLEventWriter eventWriter = null;
StringWriter xmlWriter = null;
while (reader.hasNext()) {
final XMLEvent nextEvent = reader.nextEvent();
if (nextEvent.isStartElement()) {
final StartElement startElement = nextEvent.asStartElement();
if ("record".equals(startElement.getName().getLocalPart())) {
xmlWriter = new StringWriter();
eventWriter = xmlOutputFactory.createXMLEventWriter(xmlWriter);
}
}
if (eventWriter != null) {
eventWriter.add(nextEvent);
}
if (nextEvent.isEndElement()) {
final EndElement endElement = nextEvent.asEndElement();
if ("record".equals(endElement.getName().getLocalPart())) {
eventWriter.flush();
eventWriter.close();
this.queue.put(xmlWriter.toString());
eventWriter = null;
xmlWriter = null;
count++;
}
}
}
}
}
}
this.queue.put(END_ELEM); // TO INDICATE THE END OF THE QUEUE
} catch (final Throwable e) {
log.error("Error processing BASE records", e);
report.put(e.getClass().getName(), e.getMessage());
throw new RuntimeException("Error processing BASE records", e);
} finally {
log.info("Total records (written in queue): " + count);
}
}
}

159
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/collection/plugin/base/BaseCollectorPlugin.java Normal file
View File

@ -0,0 +1,159 @@
package eu.dnetlib.dhp.collection.plugin.base;
import java.io.IOException;
import java.sql.SQLException;
import java.util.HashSet;
import java.util.Iterator;
import java.util.Optional;
import java.util.Set;
import java.util.Spliterator;
import java.util.Spliterators;
import java.util.stream.Stream;
import java.util.stream.StreamSupport;
import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.StringUtils;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.dom4j.Document;
import org.dom4j.DocumentException;
import org.dom4j.DocumentHelper;
import org.dom4j.Node;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import eu.dnetlib.dhp.collection.ApiDescriptor;
import eu.dnetlib.dhp.collection.plugin.CollectorPlugin;
import eu.dnetlib.dhp.collection.plugin.file.AbstractSplittedRecordPlugin;
import eu.dnetlib.dhp.common.DbClient;
import eu.dnetlib.dhp.common.aggregation.AggregatorReport;
import eu.dnetlib.dhp.common.collection.CollectorException;
public class BaseCollectorPlugin implements CollectorPlugin {
private final FileSystem fs;
private static final Logger log = LoggerFactory.getLogger(AbstractSplittedRecordPlugin.class);
// MAPPING AND FILTERING ARE DEFINED HERE:
// https://docs.google.com/document/d/1Aj-ZAV11b44MCrAAUCPiS2TUlXb6PnJEu1utCMAcCOU/edit
public BaseCollectorPlugin(final FileSystem fs) {
this.fs = fs;
}
@Override
public Stream<String> collect(final ApiDescriptor api, final AggregatorReport report) throws CollectorException {
// the path of the dump file on HDFS
// http://oai.base-search.net/initial_load/base_oaipmh_dump-current.tar
// it could be downloaded from iis-cdh5-test-gw.ocean.icm.edu.pl and then copied on HDFS
final Path filePath = Optional
.ofNullable(api.getBaseUrl())
.map(Path::new)
.orElseThrow(() -> new CollectorException("missing baseUrl"));
// get the parameters for the connection to the OpenAIRE database.
// the database is used to obtain the list of the datasources that the plugin will collect
final String dbUrl = api.getParams().get("dbUrl");
final String dbUser = api.getParams().get("dbUser");
final String dbPassword = api.getParams().get("dbPassword");
// the types(comma separated, empty value for all) that the plugin will collect,
// the types should be expressed in the format of the normalized types of BASE (for example 1,121,...)
final String acceptedNormTypesString = api.getParams().get("acceptedNormTypes");
log.info("baseUrl: {}", filePath);
log.info("dbUrl: {}", dbUrl);
log.info("dbUser: {}", dbUser);
log.info("dbPassword: {}", "***");
log.info("acceptedNormTypes: {}", acceptedNormTypesString);
try {
if (!this.fs.exists(filePath)) {
throw new CollectorException("path does not exist: " + filePath);
}
} catch (final Throwable e) {
throw new CollectorException(e);
}
final Set<String> acceptedOpendoarIds = findAcceptedOpendoarIds(dbUrl, dbUser, dbPassword);
final Set<String> acceptedNormTypes = new HashSet<>();
if (StringUtils.isNotBlank(acceptedNormTypesString)) {
for (final String s : StringUtils.split(acceptedNormTypesString, ",")) {
if (StringUtils.isNotBlank(s)) {
acceptedNormTypes.add(s.trim());
}
}
}
final Iterator<String> iterator = new BaseCollectorIterator(this.fs, filePath, report);
final Spliterator<String> spliterator = Spliterators.spliteratorUnknownSize(iterator, Spliterator.ORDERED);
return StreamSupport
.stream(spliterator, false)
.filter(doc -> filterXml(doc, acceptedOpendoarIds, acceptedNormTypes));
}
private Set<String> findAcceptedOpendoarIds(final String dbUrl, final String dbUser, final String dbPassword)
throws CollectorException {
final Set<String> accepted = new HashSet<>();
try (final DbClient dbClient = new DbClient(dbUrl, dbUser, dbPassword)) {
final String sql = IOUtils
.toString(
getClass().getResourceAsStream("/eu/dnetlib/dhp/collection/plugin/base/sql/opendoar-accepted.sql"));
dbClient.processResults(sql, row -> {
try {
final String dsId = row.getString("id");
log.info("Accepted Datasource: " + dsId);
accepted.add(dsId);
} catch (final SQLException e) {
log.error("Error in SQL", e);
throw new RuntimeException("Error in SQL", e);
}
});
} catch (final IOException e) {
log.error("Error accessong SQL", e);
throw new CollectorException("Error accessong SQL", e);
}
log.info("Accepted Datasources (TOTAL): " + accepted.size());
return accepted;
}
protected static boolean filterXml(final String xml,
final Set<String> acceptedOpendoarIds,
final Set<String> acceptedNormTypes) {
try {
final Document doc = DocumentHelper.parseText(xml);
final String id = doc.valueOf("//*[local-name()='collection']/@opendoar_id").trim();
if (StringUtils.isBlank(id) || !acceptedOpendoarIds.contains("opendoar____::" + id)) {
return false;
}
if (acceptedNormTypes.isEmpty()) {
return true;
}
for (final Object s : doc.selectNodes("//*[local-name()='typenorm']")) {
if (acceptedNormTypes.contains(((Node) s).getText().trim())) {
return true;
}
}
return false;
} catch (final DocumentException e) {
log.error("Error parsing document", e);
throw new RuntimeException("Error parsing document", e);
}
}
}

8
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/collection/plugin/rest/RestIterator.java
View File

@ -52,8 +52,6 @@ public class RestIterator implements Iterator<String> {
private final String BASIC = "basic";
private final JsonUtils jsonUtils;
private final String baseUrl;
private final String resumptionType;
private final String resumptionParam;
@ -106,7 +104,6 @@ public class RestIterator implements Iterator<String> {
final String resultOutputFormat) {
this.clientParams = clientParams;
this.jsonUtils = new JsonUtils();
this.baseUrl = baseUrl;
this.resumptionType = resumptionType;
this.resumptionParam = resumptionParam;
@ -126,6 +123,7 @@ public class RestIterator implements Iterator<String> {
} catch (Exception e) {
throw new IllegalStateException("xml transformation init failed: " + e.getMessage());
}
initQueue();
}
@ -190,7 +188,7 @@ public class RestIterator implements Iterator<String> {
String resultJson;
String resultXml = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>";
String nextQuery = "";
String emptyXml = resultXml + "<" + JsonUtils.wrapName + "></" + JsonUtils.wrapName + ">";
String emptyXml = resultXml + "<" + JsonUtils.XML_WRAP_TAG + "></" + JsonUtils.XML_WRAP_TAG + ">";
Node resultNode = null;
NodeList nodeList = null;
String qUrlArgument = "";
@ -231,7 +229,7 @@ public class RestIterator implements Iterator<String> {
resultStream = theHttpInputStream;
if ("json".equals(resultOutputFormat)) {
resultJson = IOUtils.toString(resultStream, StandardCharsets.UTF_8);
resultXml = jsonUtils.convertToXML(resultJson);
resultXml = JsonUtils.convertToXML(resultJson);
resultStream = IOUtils.toInputStream(resultXml, UTF_8);
}

158
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/collection/plugin/utils/JsonUtils.java
View File

@ -3,82 +3,142 @@ package eu.dnetlib.dhp.collection.plugin.utils;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.json.JSONArray;
import org.json.JSONObject;
public class JsonUtils {
public static final String XML_WRAP_TAG = "recordWrap";
private static final String XML_HEADER = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>";
private static final String INVALID_XMLTAG_CHARS = "!\"#$%&'()*+,/;<=>?@[\\]^`{|}~,";
private static final Log log = LogFactory.getLog(JsonUtils.class);
public static final String wrapName = "recordWrap";
/**
* convert in JSON-KeyName 'whitespace(s)' to '_' and '/' to '_', '(' and ')' to ''
* cleanup in JSON-KeyName
* check W3C XML syntax: https://www.w3.org/TR/2006/REC-xml11-20060816/#sec-starttags for valid tag names
* and work-around for the JSON to XML converting of org.json.XML-package.
*
* known bugs: doesn't prevent "key name":" ["sexy name",": penari","erotic dance"],
*
* @param jsonInput
* @return convertedJsonKeynameOutput
* @param input
* @return converted json object
*/
public String syntaxConvertJsonKeyNames(String jsonInput) {
log.trace("before convertJsonKeyNames: " + jsonInput);
// pre-clean json - rid spaces of element names (misinterpreted as elements with attributes in xml)
// replace ' 's in JSON Namens with '_'
while (jsonInput.matches(".*\"([^\"]*)\\s+([^\"]*)\":.*")) {
jsonInput = jsonInput.replaceAll("\"([^\"]*)\\s+([^\"]*)\":", "\"$1_$2\":");
public static JSONObject cleanJsonObject(final JSONObject input) {
if (null == input) {
return null;
}
// replace forward-slash (sign '/' ) in JSON Names with '_'
while (jsonInput.matches(".*\"([^\"]*)/([^\"]*)\":.*")) {
jsonInput = jsonInput.replaceAll("\"([^\"]*)/([^\"]*)\":", "\"$1_$2\":");
JSONObject result = new JSONObject();
for (String key : input.keySet()) {
Object value = input.opt(key);
if (value != null) {
result.put(cleanKey(key), cleanValue(value));
}
}
// replace '(' in JSON Names with ''
while (jsonInput.matches(".*\"([^\"]*)[(]([^\"]*)\":.*")) {
jsonInput = jsonInput.replaceAll("\"([^\"]*)[(]([^\"]*)\":", "\"$1$2\":");
return result;
}
// replace ')' in JSON Names with ''
while (jsonInput.matches(".*\"([^\"]*)[)]([^\"]*)\":.*")) {
jsonInput = jsonInput.replaceAll("\"([^\"]*)[)]([^\"]*)\":", "\"$1$2\":");
private static Object cleanValue(Object object) {
if (object instanceof JSONObject) {
return cleanJsonObject((JSONObject) object);
} else if (object instanceof JSONArray) {
JSONArray array = (JSONArray) object;
JSONArray res = new JSONArray();
for (int i = array.length() - 1; i >= 0; i--) {
res.put(i, cleanValue(array.opt(i)));
}
return res;
} else if (object instanceof String) {
String value = (String) object;
// XML 1.0 Allowed characters
// Char ::= #x9 | #xA | #xD | [#x20-#xD7FF] | [#xE000-#xFFFD] | [#x10000-#x10FFFF]
return value
.codePoints()
.filter(
cp -> cp == 0x9 || cp == 0xA || cp == 0xD || (cp >= 0x20 && cp <= 0xD7FF)
|| (cp >= 0xE000 && cp <= 0xFFFD)
|| (cp >= 0x10000 && cp <= 0x10FFFF))
.collect(
StringBuilder::new,
StringBuilder::appendCodePoint,
StringBuilder::append)
.toString();
}
// add prefix of startNumbers in JSON Keynames with 'n_'
while (jsonInput.matches(".*\"([^\"][0-9])([^\"]*)\":.*")) {
jsonInput = jsonInput.replaceAll("\"([^\"][0-9])([^\"]*)\":", "\"n_$1$2\":");
return object;
}
private static String cleanKey(String key) {
if (key == null || key.isEmpty()) {
return key;
}
// xml tag cannot begin with "-", ".", or a numeric digit.
switch (key.charAt(0)) {
case '-':
case '.':
key = "_" + key.substring(1);
break;
}
if (Character.isDigit(key.charAt(0))) {
if (key.matches("^[0-9]+$")) {
// add prefix of only numbers in JSON Keynames with 'm_'
while (jsonInput.matches(".*\"([0-9]+)\":.*")) {
jsonInput = jsonInput.replaceAll("\"([0-9]+)\":", "\"m_$1\":");
key = "m_" + key;
} else {
// add prefix of startNumbers in JSON Keynames with 'n_'
key = "n_" + key;
}
}
// replace ':' between number like '2018-08-28T11:05:00Z' in JSON keynames with ''
while (jsonInput.matches(".*\"([^\"]*[0-9]):([0-9][^\"]*)\":.*")) {
jsonInput = jsonInput.replaceAll("\"([^\"]*[0-9]):([0-9][^\"]*)\":", "\"$1$2\":");
StringBuilder res = new StringBuilder(key.length());
for (int i = 0; i < key.length(); i++) {
char c = key.charAt(i);
// sequence of whitespaces are rendered as a single '_'
if (Character.isWhitespace(c)) {
while (i + 1 < key.length() && Character.isWhitespace(key.charAt(i + 1))) {
i++;
}
res.append('_');
}
// remove invalid chars for xml tags with the expception of '=' and '/'
else if (INVALID_XMLTAG_CHARS.indexOf(c) >= 0) {
switch (c) {
case '=':
res.append('-');
break;
case '/':
res.append('_');
break;
default:
break;
}
// nothing
}
// all other chars are kept
else {
res.append(c);
}
}
// replace ',' in JSON Keynames with '.' to prevent , in xml tagnames.
// while (jsonInput.matches(".*\"([^\"]*),([^\"]*)\":.*")) {
// jsonInput = jsonInput.replaceAll("\"([^\"]*),([^\"]*)\":", "\"$1.$2\":");
// }
// replace '=' in JSON Keynames with '-'
while (jsonInput.matches(".*\"([^\"]*)=([^\"]*)\":.*")) {
jsonInput = jsonInput.replaceAll("\"([^\"]*)=([^\"]*)\":", "\"$1-$2\":");
return res.toString();
}
log.trace("after syntaxConvertJsonKeyNames: " + jsonInput);
return jsonInput;
static public String convertToXML(final String jsonRecord) {
if (log.isTraceEnabled()) {
log.trace("input json: " + jsonRecord);
}
public String convertToXML(final String jsonRecord) {
String resultXml = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>";
org.json.JSONObject jsonObject = new org.json.JSONObject(syntaxConvertJsonKeyNames(jsonRecord));
resultXml += org.json.XML.toString(jsonObject, wrapName); // wrap xml in single root element
log.trace("before inputStream: " + resultXml);
resultXml = XmlCleaner.cleanAllEntities(resultXml);
log.trace("after cleaning: " + resultXml);
return resultXml;
JSONObject jsonObject = cleanJsonObject(new org.json.JSONObject(jsonRecord));
String res = XML_HEADER + org.json.XML.toString(jsonObject, XML_WRAP_TAG); // wrap xml in single root element
if (log.isTraceEnabled()) {
log.trace("outout xml: " + res);
}
return res;
}
}

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

@ -17,6 +17,12 @@
"paramDescription": "the path to get the input data from Pubmed",
"paramRequired": true
},
{
"paramName": "oip",
"paramLongName": "openapcInputPath",
"paramDescription": "the path to get the input data from OpenAPC",
"paramRequired": true
},
{
"paramName": "o",
"paramLongName": "outputPath",

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

@ -31,6 +31,7 @@ spark2SqlQueryExecutionListeners=com.cloudera.spark.lineage.NavigatorQueryListen
# The following is needed as a property of a workflow
oozie.wf.application.path=${oozieTopWfApplicationPath}
crossrefInputPath=/data/bip-affiliations/data.json
crossrefInputPath=/data/bip-affiliations/crossref-data.json
pubmedInputPath=/data/bip-affiliations/pubmed-data.json
openapcInputPath=/data/bip-affiliations/openapc-data.json
outputPath=/tmp/crossref-affiliations-output-v5

5
dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/bipaffiliations/oozie_app/workflow.xml
View File

@ -9,6 +9,10 @@
<name>pubmedInputPath</name>
<description>the path where to find the inferred affiliation relations from Pubmed</description>
</property>
<property>
<name>openapcInputPath</name>
<description>the path where to find the inferred affiliation relations from OpenAPC</description>
</property>
<property>
<name>outputPath</name>
<description>the path where to store the actionset</description>
@ -102,6 +106,7 @@
</spark-opts>
<arg>--crossrefInputPath</arg><arg>${crossrefInputPath}</arg>
<arg>--pubmedInputPath</arg><arg>${pubmedInputPath}</arg>
<arg>--openapcInputPath</arg><arg>${openapcInputPath}</arg>
<arg>--outputPath</arg><arg>${outputPath}</arg>
</spark>
<ok to="End"/>

20
dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/transformativeagreement/as_parameters.json Normal file
View File

@ -0,0 +1,20 @@
[
{
"paramName": "ip",
"paramLongName": "inputPath",
"paramDescription": "the zipped opencitations file",
"paramRequired": true
},
{
"paramName": "op",
"paramLongName": "outputPath",
"paramDescription": "the working path",
"paramRequired": true
},
{
"paramName": "issm",
"paramLongName": "isSparkSessionManaged",
"paramDescription": "the hdfs name node",
"paramRequired": false
}
]

30
dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/transformativeagreement/input_read_parameters.json Normal file
View File

@ -0,0 +1,30 @@
[
{
"paramName": "issm",
"paramLongName": "isSparkSessionManaged",
"paramDescription": "the hdfs name node",
"paramRequired": false
},
{
"paramName": "d",
"paramLongName": "delimiter",
"paramDescription": "the hdfs name node",
"paramRequired": false
},
{
"paramName": "op",
"paramLongName": "outputPath",
"paramDescription": "the hdfs name node",
"paramRequired": true
},
{
"paramName": "if",
"paramLongName": "inputFile",
"paramDescription": "the hdfs name node",
"paramRequired": true
}
]

58
dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/transformativeagreement/oozie_app/config-default.xml Normal file
View File

@ -0,0 +1,58 @@
<configuration>
<property>
<name>jobTracker</name>
<value>yarnRM</value>
</property>
<property>
<name>nameNode</name>
<value>hdfs://nameservice1</value>
</property>
<property>
<name>oozie.use.system.libpath</name>
<value>true</value>
</property>
<property>
<name>oozie.action.sharelib.for.spark</name>
<value>spark2</value>
</property>
<property>
<name>hive_metastore_uris</name>
<value>thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083</value>
</property>
<property>
<name>spark2YarnHistoryServerAddress</name>
<value>http://iis-cdh5-test-gw.ocean.icm.edu.pl:18089</value>
</property>
<property>
<name>spark2ExtraListeners</name>
<value>com.cloudera.spark.lineage.NavigatorAppListener</value>
</property>
<property>
<name>spark2SqlQueryExecutionListeners</name>
<value>com.cloudera.spark.lineage.NavigatorQueryListener</value>
</property>
<property>
<name>oozie.launcher.mapreduce.user.classpath.first</name>
<value>true</value>
</property>
<property>
<name>sparkExecutorNumber</name>
<value>4</value>
</property>
<property>
<name>spark2EventLogDir</name>
<value>/user/spark/spark2ApplicationHistory</value>
</property>
<property>
<name>sparkDriverMemory</name>
<value>15G</value>
</property>
<property>
<name>sparkExecutorMemory</name>
<value>6G</value>
</property>
<property>
<name>sparkExecutorCores</name>
<value>1</value>
</property>
</configuration>

2
dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/transformativeagreement/oozie_app/download.sh Normal file
View File

@ -0,0 +1,2 @@
#!/bin/bash
curl -L $1 | hdfs dfs -put - $2

82
dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/transformativeagreement/oozie_app/workflow.xml Normal file
View File

@ -0,0 +1,82 @@
<workflow-app name="Transfomative Agreement Integration" xmlns="uri:oozie:workflow:0.5">
<global>
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>mapreduce.job.queuename</name>
<value>${queueName}</value>
</property>
<property>
<name>oozie.launcher.mapred.job.queue.name</name>
<value>${oozieLauncherQueueName}</value>
</property>
<property>
<name>oozie.action.sharelib.for.spark</name>
<value>${oozieActionShareLibForSpark2}</value>
</property>
</configuration>
</global>
<start to="resume_from"/>
<decision name="resume_from">
<switch>
<case to="download">${wf:conf('resumeFrom') eq 'DownloadDump'}</case>
<default to="create_actionset"/> <!-- first action to be done when downloadDump is to be performed -->
</switch>
</decision>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="download">
<shell xmlns="uri:oozie:shell-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>mapred.job.queue.name</name>
<value>${queueName}</value>
</property>
</configuration>
<exec>download.sh</exec>
<argument>${inputFile}</argument>
<argument>${workingDir}/transformativeagreement/transformativeAgreement.json</argument>
<env-var>HADOOP_USER_NAME=${wf:user()}</env-var>
<file>download.sh</file>
<capture-output/>
</shell>
<ok to="create_actionset"/>
<error to="Kill"/>
</action>
<action name="create_actionset">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Produces the AS for the Transformative Agreement</name>
<class>eu.dnetlib.dhp.actionmanager.transformativeagreement.CreateActionSetSparkJob</class>
<jar>dhp-aggregation-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--inputPath</arg><arg>${workingDir}/transformativeagreement/</arg>
<arg>--outputPath</arg><arg>${outputPath}</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>

26
dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/collection/orcid/apply_orcid_table_parameter.json Normal file
View File

@ -0,0 +1,26 @@
[
{
"paramName": "m",
"paramLongName": "master",
"paramDescription": "the master name",
"paramRequired": true
},
{
"paramName": "t",
"paramLongName": "targetPath",
"paramDescription": "the target PATH of the DF tables",
"paramRequired": true
},
{
"paramName": "g",
"paramLongName": "graphPath",
"paramDescription": "the PATH of the current graph path",
"paramRequired": true
},
{
"paramName": "u",
"paramLongName": "updatePath",
"paramDescription": "the PATH of the current graph update path",
"paramRequired": true
}
]

37
dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/collection/orcid/download_orcid_update_parameter.json Normal file
View File

@ -0,0 +1,37 @@
[ {
"paramName": "n",
"paramLongName": "namenode",
"paramDescription": "the Name Node URI",
"paramRequired": true
},
{
"paramName": "m",
"paramLongName": "master",
"paramDescription": "the master name",
"paramRequired": true
},
{
"paramName": "t",
"paramLongName": "targetPath",
"paramDescription": "the target PATH where download the files",
"paramRequired": true
},
{
"paramName": "a",
"paramLongName": "apiURL",
"paramDescription": "the URL to download the tar file",
"paramRequired": true
},
{
"paramName": "g",
"paramLongName": "graphPath",
"paramDescription": "the path of the input graph",
"paramRequired": true
},
{
"paramName": "at",
"paramLongName": "accessToken",
"paramDescription": "the accessToken to contact API",
"paramRequired": true
}
]

6
dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/collection/orcid/generate_orcid_table_parameter.json
View File

@ -16,6 +16,12 @@
"paramLongName": "sourcePath",
"paramDescription": "the PATH of the ORCID sequence file",
"paramRequired": true
},
{
"paramName": "fu",
"paramLongName": "fromUpdate",
"paramDescription": "whether we have to generate table from dump or from update",
"paramRequired": false
}
]

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

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

114
dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/collection/orcid/update/oozie_app/workflow.xml Normal file
View File

@ -0,0 +1,114 @@
<workflow-app name="download_Update_ORCID" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>graphPath</name>
<description>the path to store the original ORCID dump</description>
</property>
<property>
<name>targetPath</name>
<description>the path to store the original ORCID dump</description>
</property>
<property>
<name>apiURL</name>
<value>http://74804fb637bd8e2fba5b-e0a029c2f87486cddec3b416996a6057.r3.cf1.rackcdn.com/last_modified.csv.tar</value>
<description>The URL of the update CSV list </description>
</property>
<property>
<name>accessToken</name>
<description>The access token</description>
</property>
</parameters>
<start to="startUpdate"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="startUpdate">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Check Latest Orcid and Download updates</name>
<class>eu.dnetlib.dhp.collection.orcid.OrcidGetUpdatesFile</class>
<jar>dhp-aggregation-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.executor.memoryOverhead=2g
--conf spark.sql.shuffle.partitions=3000
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--master</arg><arg>yarn</arg>
<arg>--namenode</arg><arg>${nameNode}</arg>
<arg>--graphPath</arg><arg>${graphPath}</arg>
<arg>--targetPath</arg><arg>${targetPath}</arg>
<arg>--apiURL</arg><arg>${apiURL}</arg>
<arg>--accessToken</arg><arg>${accessToken}</arg>
</spark>
<ok to="generateTables"/>
<error to="Kill"/>
</action>
<action name="generateTables">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Generate ORCID Tables</name>
<class>eu.dnetlib.dhp.collection.orcid.SparkGenerateORCIDTable</class>
<jar>dhp-aggregation-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.executor.memoryOverhead=2g
--conf spark.sql.shuffle.partitions=3000
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${targetPath}</arg>
<arg>--targetPath</arg><arg>${targetPath}/updateTable</arg>
<arg>--fromUpdate</arg><arg>true</arg>
<arg>--master</arg><arg>yarn</arg>
</spark>
<ok to="updateTable"/>
<error to="Kill"/>
</action>
<action name="updateTable">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Update ORCID Tables</name>
<class>eu.dnetlib.dhp.collection.orcid.SparkApplyUpdate</class>
<jar>dhp-aggregation-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.executor.memoryOverhead=2g
--conf spark.sql.shuffle.partitions=3000
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--graphPath</arg><arg>${graphPath}</arg>
<arg>--updatePath</arg><arg>${targetPath}/updateTable</arg>
<arg>--targetPath</arg><arg>${targetPath}/newTable</arg>
<arg>--master</arg><arg>yarn</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>

114
dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/collection/plugin/base/sql/base.sql Normal file
View File

@ -0,0 +1,114 @@
BEGIN;
INSERT INTO dsm_services(
_dnet_resource_identifier_,
id,
officialname,
englishname,
namespaceprefix,
websiteurl,
logourl,
platform,
contactemail,
collectedfrom,
provenanceaction,
_typology_to_remove_,
eosc_type,
eosc_datasource_type,
research_entity_types,
thematic
) VALUES (
'openaire____::base_search',
'openaire____::base_search',
'Bielefeld Academic Search Engine (BASE)',
'Bielefeld Academic Search Engine (BASE)',
'base_search_',
'https://www.base-search.net',
'https://www.base-search.net/about/download/logo_224x57_white.gif',
'BASE',
'openaire-helpdesk@uni-bielefeld.de',
'infrastruct_::openaire',
'user:insert',
'aggregator::pubsrepository::unknown',
'Data Source',
'Aggregator',
ARRAY['Research Products'],
false
);
INSERT INTO dsm_service_organization(
_dnet_resource_identifier_,
organization,
service
) VALUES (
'fairsharing_::org::214@@openaire____::base_search',
'fairsharing_::org::214',
'openaire____::base_search'
);
INSERT INTO dsm_api(
_dnet_resource_identifier_,
id,
service,
protocol,
baseurl,
metadata_identifier_path
) VALUES (
'api_________::openaire____::base_search::dump',
'api_________::openaire____::base_search::dump',
'openaire____::base_search',
'baseDump',
'/user/michele.artini/base-import/base_oaipmh_dump-current.tar',
'//*[local-name()=''header'']/*[local-name()=''identifier'']'
);
INSERT INTO dsm_apiparams(
_dnet_resource_identifier_,
api,
param,
value
) VALUES (
'api_________::openaire____::base_search::dump@@dbUrl',
'api_________::openaire____::base_search::dump',
'dbUrl',
'jdbc:postgresql://postgresql.services.openaire.eu:5432/dnet_openaireplus'
);
INSERT INTO dsm_apiparams(
_dnet_resource_identifier_,
api,
param,
value
) VALUES (
'api_________::openaire____::base_search::dump@@dbUser',
'api_________::openaire____::base_search::dump',
'dbUser',
'dnet'
);
INSERT INTO dsm_apiparams(
_dnet_resource_identifier_,
api,
param,
value
) VALUES (
'api_________::openaire____::base_search::dump@@dbPassword',
'api_________::openaire____::base_search::dump',
'dbPassword',
'***'
);
INSERT INTO dsm_apiparams(
_dnet_resource_identifier_,
api,
param,
value
) VALUES (
'api_________::openaire____::base_search::dump@@acceptedNormTypes',
'api_________::openaire____::base_search::dump',
'acceptedNormTypes',
'1,11,111,121,14,15,18,181,182,183,1A,6,7'
);
COMMIT;

9
dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/collection/plugin/base/sql/opendoar-accepted.sql Normal file
View File

@ -0,0 +1,9 @@
select s.id as id
from dsm_services s
where collectedfrom = 'openaire____::opendoar'
and jurisdiction = 'Institutional'
and s.id in (
select service from dsm_api where coalesce(compatibility_override, compatibility) = 'driver' or coalesce(compatibility_override, compatibility) = 'UNKNOWN'
) and s.id not in (
select service from dsm_api where coalesce(compatibility_override, compatibility) like '%openaire%'
);

11
dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/collection/plugin/base/sql/opendoar-aggregation-status.sql Normal file
View File

@ -0,0 +1,11 @@
select
s.id as id,
s.jurisdiction as jurisdiction,
array_remove(array_agg(a.id || ' (compliance: ' || coalesce(a.compatibility_override, a.compatibility, 'UNKNOWN') || ')@@@' || coalesce(a.last_collection_total, 0)), NULL) as aggregations
from
dsm_services s
join dsm_api a on (s.id = a.service)
where
collectedfrom = 'openaire____::opendoar'
group by
s.id;

180
dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/collection/plugin/base/xml/base-types.vocabulary.xml Normal file
View File

@ -0,0 +1,180 @@
<RESOURCE_PROFILE>
<HEADER>
<RESOURCE_IDENTIFIER value="c67911d6-9988-4a3b-b965-7d39bdd4a31d_Vm9jYWJ1bGFyeURTUmVzb3VyY2VzL1ZvY2FidWxhcnlEU1Jlc291cmNlVHlwZQ==" />
<RESOURCE_TYPE value="VocabularyDSResourceType" />
<RESOURCE_KIND value="VocabularyDSResources" />
<RESOURCE_URI value="" />
<DATE_OF_CREATION value="2024-02-13T11:15:48+00:00" />
</HEADER>
<BODY>
<CONFIGURATION>
<VOCABULARY_NAME code="base:normalized_types">base:normalized_types</VOCABULARY_NAME>
<VOCABULARY_DESCRIPTION>base:normalized_types</VOCABULARY_DESCRIPTION>
<TERMS>
<TERM native_name="Text" code="Text" english_name="Text" encoding="BASE">
<SYNONYMS>
<SYNONYM term="1" encoding="BASE" />
</SYNONYMS>
<RELATIONS />
</TERM>
<TERM native_name="Book" code="Book" english_name="Book" encoding="BASE">
<SYNONYMS>
<SYNONYM term="11" encoding="BASE" />
</SYNONYMS>
<RELATIONS />
</TERM>
<TERM native_name="Book part" code="Book part" english_name="Book part" encoding="BASE">
<SYNONYMS>
<SYNONYM term="111" encoding="BASE" />
</SYNONYMS>
<RELATIONS />
</TERM>
<TERM native_name="Journal/Newspaper" code="Journal/Newspaper" english_name="Journal/Newspaper" encoding="BASE">
<SYNONYMS>
<SYNONYM term="12" encoding="BASE" />
</SYNONYMS>
<RELATIONS />
</TERM>
<TERM native_name="Article contribution" code="Article contribution" english_name="Article contribution" encoding="BASE">
<SYNONYMS>
<SYNONYM term="121" encoding="BASE" />
</SYNONYMS>
<RELATIONS />
</TERM>
<TERM native_name="Other non-article" code="Other non-article" english_name="Other non-article" encoding="BASE">
<SYNONYMS>
<SYNONYM term="122" encoding="BASE" />
</SYNONYMS>
<RELATIONS />
</TERM>
<TERM native_name="Conference object" code="Conference object" english_name="Conference object" encoding="BASE">
<SYNONYMS>
<SYNONYM term="13" encoding="BASE" />
</SYNONYMS>
<RELATIONS />
</TERM>
<TERM native_name="Report" code="Report" english_name="Report" encoding="BASE">
<SYNONYMS>
<SYNONYM term="14" encoding="BASE" />
</SYNONYMS>
<RELATIONS />
</TERM>
<TERM native_name="Review" code="Review" english_name="Review" encoding="BASE">
<SYNONYMS>
<SYNONYM term="15" encoding="BASE" />
</SYNONYMS>
<RELATIONS />
</TERM>
<TERM native_name="Course material" code="Course material" english_name="Course material" encoding="BASE">
<SYNONYMS>
<SYNONYM term="16" encoding="BASE" />
</SYNONYMS>
<RELATIONS />
</TERM>
<TERM native_name="Lecture" code="Lecture" english_name="Lecture" encoding="BASE">
<SYNONYMS>
<SYNONYM term="17" encoding="BASE" />
</SYNONYMS>
<RELATIONS />
</TERM>
<TERM native_name="Thesis" code="Thesis" english_name="Thesis" encoding="BASE">
<SYNONYMS>
<SYNONYM term="18" encoding="BASE" />
</SYNONYMS>
<RELATIONS />
</TERM>
<TERM native_name="Bachelor's thesis" code="Bachelor's thesis" english_name="Bachelor's thesis" encoding="BASE">
<SYNONYMS>
<SYNONYM term="181" encoding="BASE" />
</SYNONYMS>
<RELATIONS />
</TERM>
<TERM native_name="Master's thesis" code="Master's thesis" english_name="Master's thesis" encoding="BASE">
<SYNONYMS>
<SYNONYM term="182" encoding="BASE" />
</SYNONYMS>
<RELATIONS />
</TERM>
<TERM native_name="Doctoral and postdoctoral thesis" code="Doctoral and postdoctoral thesis" english_name="Doctoral and postdoctoral thesis" encoding="BASE">
<SYNONYMS>
<SYNONYM term="183" encoding="BASE" />
</SYNONYMS>
<RELATIONS />
</TERM>
<TERM native_name="Manuscript" code="Manuscript" english_name="Manuscript" encoding="BASE">
<SYNONYMS>
<SYNONYM term="19" encoding="BASE" />
</SYNONYMS>
<RELATIONS />
</TERM>
<TERM native_name="Patent" code="Patent" english_name="Patent" encoding="BASE">
<SYNONYMS>
<SYNONYM term="1A" encoding="BASE" />
</SYNONYMS>
<RELATIONS />
</TERM>
<TERM native_name="Musical notation" code="Musical notation" english_name="Musical notation" encoding="BASE">
<SYNONYMS>
<SYNONYM term="2" encoding="BASE" />
</SYNONYMS>
<RELATIONS />
</TERM>
<TERM native_name="Map" code="Map" english_name="Map" encoding="BASE">
<SYNONYMS>
<SYNONYM term="3" encoding="BASE" />
</SYNONYMS>
<RELATIONS />
</TERM>
<TERM native_name="Audio" code="Audio" english_name="Audio" encoding="BASE">
<SYNONYMS>
<SYNONYM term="4" encoding="BASE" />
</SYNONYMS>
<RELATIONS />
</TERM>
<TERM native_name="Image/Video" code="Image/Video" english_name="Image/Video" encoding="BASE">
<SYNONYMS>
<SYNONYM term="5" encoding="BASE" />
</SYNONYMS>
<RELATIONS />
</TERM>
<TERM native_name="Still image" code="Still image" english_name="Still image" encoding="BASE">
<SYNONYMS>
<SYNONYM term="51" encoding="BASE" />
</SYNONYMS>
<RELATIONS />
</TERM>
<TERM native_name="Moving image/Video" code="Moving image/Video" english_name="Moving image/Video" encoding="BASE">
<SYNONYMS>
<SYNONYM term="52" encoding="BASE" />
</SYNONYMS>
<RELATIONS />
</TERM>
<TERM native_name="Software" code="Software" english_name="Software" encoding="BASE">
<SYNONYMS>
<SYNONYM term="6" encoding="BASE" />
</SYNONYMS>
<RELATIONS />
</TERM>
<TERM native_name="Dataset" code="Dataset" english_name="Dataset" encoding="BASE">
<SYNONYMS>
<SYNONYM term="7" encoding="BASE" />
</SYNONYMS>
<RELATIONS />
</TERM>
<TERM native_name="Unknown" code="Unknown" english_name="Unknown" encoding="BASE">
<SYNONYMS>
<SYNONYM term="F" encoding="BASE" />
</SYNONYMS>
<RELATIONS />
</TERM>
</TERMS>
</CONFIGURATION>
<STATUS>
<LAST_UPDATE value="2013-11-18T10:46:36Z" />
</STATUS>
<SECURITY_PARAMETERS>String</SECURITY_PARAMETERS>
</BODY>
</RESOURCE_PROFILE>

432
dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/collection/plugin/base/xml/base2oaf.transformationRule.xml Normal file
View File

@ -0,0 +1,432 @@
<RESOURCE_PROFILE>
<HEADER>
<RESOURCE_IDENTIFIER value="" />
<RESOURCE_TYPE value="TransformationRuleDSResourceType" />
<RESOURCE_KIND value="TransformationRuleDSResources" />
<RESOURCE_URI value="" />
<DATE_OF_CREATION value="2024-03-05T11:23:00+00:00" />
</HEADER>
<BODY>
<CONFIGURATION>
<SOURCE_METADATA_FORMAT interpretation="cleaned" layout="store" name="dc" />
<SINK_METADATA_FORMAT name="oaf_hbase" />
<IMPORTED />
<SCRIPT>
<TITLE>xslt_base2oaf_hadoop</TITLE>
<CODE>
<xsl:stylesheet xmlns:oaire="http://namespace.openaire.eu/schema/oaire/" xmlns:dateCleaner="http://eu/dnetlib/transform/dateISO"
xmlns:base_dc="http://oai.base-search.net/base_dc/"
xmlns:datacite="http://datacite.org/schema/kernel-4" xmlns:dr="http://www.driver-repository.eu/namespace/dr" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xmlns:xsl="http://www.w3.org/1999/XSL/Transform" xmlns:vocabulary="http://eu/dnetlib/transform/clean" xmlns:oaf="http://namespace.openaire.eu/oaf"
xmlns:oai="http://www.openarchives.org/OAI/2.0/" xmlns:dri="http://www.driver-repository.eu/namespace/dri" xmlns:xs="http://www.w3.org/2001/XMLSchema" xmlns:dc="http://purl.org/dc/elements/1.1/"
exclude-result-prefixes="xsl vocabulary dateCleaner base_dc" version="2.0">
<xsl:param name="varOfficialName" />
<xsl:param name="varDataSourceId" />
<xsl:param name="varFP7" select="'corda_______::'" />
<xsl:param name="varH2020" select="'corda__h2020::'" />
<xsl:param name="repoCode" select="substring-before(//*[local-name() = 'header']/*[local-name()='recordIdentifier'], ':')" />
<xsl:param name="index" select="0" />
<xsl:param name="transDate" select="current-dateTime()" />
<xsl:template name="terminate">
<xsl:message terminate="yes">
record is not compliant, transformation is interrupted.
</xsl:message>
</xsl:template>
<xsl:template match="/">
<record>
<xsl:apply-templates select="//*[local-name() = 'header']" />
<!-- TO EVALUATE
base_dc:authod_id
base_dc:authod_id/base_dc:creator_id
base_dc:authod_id/base_dc:creator_name
example:
<dc:creator>ALBU, Svetlana</dc:creator>
<base_dc:authod_id>
<base_dc:creator_name>ALBU, Svetlana</base_dc:creator_name>
<base_dc:creator_id>https://orcid.org/0000-0002-8648-950X</base_dc:creator_id>
</base_dc:authod_id>
-->
<!-- NOT USED
base_dc:global_id (I used oai:identifier)
base_dc:collection/text()
base_dc:continent
base_dc:country
base_dc:year (I used dc:date)
dc:coverage
dc:language (I used base_dc:lang)
base_dc:link (I used dc:identifier)
-->
<metadata>
<xsl:call-template name="allElements">
<xsl:with-param name="sourceElement" select="//dc:title" />
<xsl:with-param name="targetElement" select="'dc:title'" />
</xsl:call-template>
<xsl:call-template name="allElements">
<xsl:with-param name="sourceElement" select="//dc:creator/replace(., '^(.*)\|.*$', '$1')" />
<xsl:with-param name="targetElement" select="'dc:creator'" />
</xsl:call-template>
<xsl:call-template name="allElements">
<xsl:with-param name="sourceElement" select="//dc:contributor" />
<xsl:with-param name="targetElement" select="'dc:contributor'" />
</xsl:call-template>
<xsl:call-template name="allElements">
<xsl:with-param name="sourceElement" select="//dc:description" />
<xsl:with-param name="targetElement" select="'dc:description'" />
</xsl:call-template>
<xsl:call-template name="allElements">
<xsl:with-param name="sourceElement" select="//dc:subject" />
<xsl:with-param name="targetElement" select="'dc:subject'" />
</xsl:call-template>
<!-- TODO: I'm not sure if this is the correct encoding -->
<xsl:for-each select="//base_dc:classcode|//base_dc:autoclasscode">
<dc:subject><xsl:value-of select="concat(@type, ':', .)" /></dc:subject>
</xsl:for-each>
<!-- END TODO -->
<xsl:call-template name="allElements">
<xsl:with-param name="sourceElement" select="//dc:publisher" />
<xsl:with-param name="targetElement" select="'dc:publisher'" />
</xsl:call-template>
<xsl:call-template name="allElements">
<xsl:with-param name="sourceElement" select="//dc:format" />
<xsl:with-param name="targetElement" select="'dc:format'" />
</xsl:call-template>
<xsl:for-each select="//base_dc:typenorm">
<dc:type>
<xsl:value-of select="vocabulary:clean(., 'base:normalized_types')" />
</dc:type>
</xsl:for-each>
<xsl:call-template name="allElements">
<xsl:with-param name="sourceElement" select="//dc:type" />
<xsl:with-param name="targetElement" select="'dc:type'" />
</xsl:call-template>
<xsl:call-template name="allElements">
<xsl:with-param name="sourceElement" select="//dc:source" />
<xsl:with-param name="targetElement" select="'dc:source'" />
</xsl:call-template>
<dc:language>
<xsl:value-of select="vocabulary:clean( //base_dc:lang, 'dnet:languages')" />
</dc:language>
<xsl:call-template name="allElements">
<xsl:with-param name="sourceElement" select="//dc:rights" />
<xsl:with-param name="targetElement" select="'dc:rights'" />
</xsl:call-template>
<xsl:call-template name="allElements">
<xsl:with-param name="sourceElement" select="//dc:relation" />
<xsl:with-param name="targetElement" select="'dc:relation'" />
</xsl:call-template>
<xsl:if test="not(//dc:identifier[starts-with(., 'http')])">
<xsl:call-template name="terminate" />
</xsl:if>
<xsl:call-template name="allElements">
<xsl:with-param name="sourceElement" select="//dc:identifier[starts-with(., 'http')]" />
<xsl:with-param name="targetElement" select="'dc:identifier'" />
</xsl:call-template>
<xsl:for-each select="//dc:relation">
<xsl:if test="matches(normalize-space(.), '(info:eu-repo/grantagreement/ec/fp7/)(\d\d\d\d\d\d)(.*)', 'i')">
<oaf:projectid>
<xsl:value-of select="concat($varFP7, replace(normalize-space(.), '(info:eu-repo/grantagreement/ec/fp7/)(\d\d\d\d\d\d)(.*)', '$2', 'i'))" />
</oaf:projectid>
</xsl:if>
<xsl:if test="matches(normalize-space(.), '(info:eu-repo/grantagreement/ec/h2020/)(\d\d\d\d\d\d)(.*)', 'i')">
<oaf:projectid>
<xsl:value-of select="concat($varH2020, replace(normalize-space(.), '(info:eu-repo/grantagreement/ec/h2020/)(\d\d\d\d\d\d)(.*)', '$2', 'i'))" />
</oaf:projectid>
</xsl:if>
</xsl:for-each>
<xsl:choose>
<!-- I used an inline mapping because the field typenorm could be repeated and I have to specify a list of priority -->
<!-- Book part -->
<xsl:when test="//base_dc:typenorm = '111'">
<dr:CobjCategory type="publication">0013</dr:CobjCategory>
</xsl:when>
<!-- Book -->
<xsl:when test="//base_dc:typenorm = '11'">
<dr:CobjCategory type="publication">0002</dr:CobjCategory>
</xsl:when>
<!-- Article contribution -->
<xsl:when test="//base_dc:typenorm = '121'">
<dr:CobjCategory type="publication">0001</dr:CobjCategory>
</xsl:when>
<!-- Journal/Newspaper -->
<xsl:when test="//base_dc:typenorm = '12'">
<dr:CobjCategory type="publication">0043</dr:CobjCategory>
</xsl:when>
<!-- Report -->
<xsl:when test="//base_dc:typenorm = '14'">
<dr:CobjCategory type="publication">0017</dr:CobjCategory>
</xsl:when>
<!-- Review -->
<xsl:when test="//base_dc:typenorm = '15'">
<dr:CobjCategory type="publication">0015</dr:CobjCategory>
</xsl:when>
<!-- Lecture -->
<xsl:when test="//base_dc:typenorm = '17'">
<dr:CobjCategory type="publication">0010</dr:CobjCategory>
</xsl:when>
<!-- Bachelor's thesis -->
<xsl:when test="//base_dc:typenorm = '181'">
<dr:CobjCategory type="publication">0008</dr:CobjCategory>
</xsl:when>
<!-- Master's thesis -->
<xsl:when test="//base_dc:typenorm = '182'">
<dr:CobjCategory type="publication">0007</dr:CobjCategory>
</xsl:when>
<!-- Doctoral and postdoctoral thesis -->
<xsl:when test="//base_dc:typenorm = '183'">
<dr:CobjCategory type="publication">0006</dr:CobjCategory>
</xsl:when>
<!-- Thesis -->
<xsl:when test="//base_dc:typenorm = '18'">
<dr:CobjCategory type="publication">0044</dr:CobjCategory>
</xsl:when>
<!-- Patent -->
<xsl:when test="//base_dc:typenorm = '1A'">
<dr:CobjCategory type="publication">0019</dr:CobjCategory>
</xsl:when>
<!-- Text -->
<xsl:when test="//base_dc:typenorm = '1'">
<dr:CobjCategory type="publication">0001</dr:CobjCategory>
</xsl:when>
<!-- Software -->
<xsl:when test="//base_dc:typenorm = '6'">
<dr:CobjCategory type="software">0029</dr:CobjCategory>
</xsl:when>
<!-- Dataset -->
<xsl:when test="//base_dc:typenorm = '7'">
<dr:CobjCategory type="dataset">0021</dr:CobjCategory>
</xsl:when>
<!-- Still image -->
<xsl:when test="//base_dc:typenorm = '51'">
<dr:CobjCategory type="other">0025</dr:CobjCategory>
</xsl:when>
<!-- Moving image/Video -->
<xsl:when test="//base_dc:typenorm = '52'">
<dr:CobjCategory type="other">0024</dr:CobjCategory>
</xsl:when>
<!-- Image/Video -->
<xsl:when test="//base_dc:typenorm = '5'">
<dr:CobjCategory type="other">0033</dr:CobjCategory>
</xsl:when>
<!-- Audio -->
<xsl:when test="//base_dc:typenorm = '4'">
<dr:CobjCategory type="other">0030</dr:CobjCategory>
</xsl:when>
<!-- Musical notation -->
<xsl:when test="//base_dc:typenorm = '2'">
<dr:CobjCategory type="other">0020</dr:CobjCategory>
</xsl:when>
<!-- Map -->
<xsl:when test="//base_dc:typenorm = '3'">
<dr:CobjCategory type="other">0020</dr:CobjCategory>
</xsl:when>
<!-- Other non-article -->
<xsl:when test="//base_dc:typenorm = '122'">
<dr:CobjCategory type="publication">0038</dr:CobjCategory>
</xsl:when>
<!-- Course material -->
<xsl:when test="//base_dc:typenorm = '16'">
<dr:CobjCategory type="publication">0038</dr:CobjCategory>
</xsl:when>
<!-- Manuscript -->
<xsl:when test="//base_dc:typenorm = '19'">
<dr:CobjCategory type="publication">0038</dr:CobjCategory>
</xsl:when>
<!-- Conference object -->
<xsl:when test="//base_dc:typenorm = '13'">
<dr:CobjCategory type="publication">0004</dr:CobjCategory>
</xsl:when>
<!-- Unknown -->
<xsl:when test="//base_dc:typenorm = 'F'">
<dr:CobjCategory type="other">0000</dr:CobjCategory>
</xsl:when>
<xsl:otherwise>
<dr:CobjCategory type="other">0000</dr:CobjCategory>
</xsl:otherwise>
</xsl:choose>
<oaf:accessrights>
<xsl:choose>
<xsl:when test="//base_dc:oa[.='0']">CLOSED</xsl:when>
<xsl:when test="//base_dc:oa[.='1']">OPEN</xsl:when>
<xsl:when test="//base_dc:oa[.='2']">UNKNOWN</xsl:when>
<xsl:when test="//base_dc:rightsnorm">
<xsl:value-of select="vocabulary:clean(//base_dc:rightsnorm, 'dnet:access_modes')" />
</xsl:when>
<xsl:when test="//dc:rights">
<xsl:value-of select="vocabulary:clean( //dc:rights, 'dnet:access_modes')" />
</xsl:when>
<xsl:otherwise>UNKNOWN</xsl:otherwise>
</xsl:choose>
</oaf:accessrights>
<xsl:for-each select="//base_dc:doi">
<oaf:identifier identifierType="doi">
<xsl:value-of select="." />
</oaf:identifier>
</xsl:for-each>
<xsl:for-each select="distinct-values(//dc:identifier[starts-with(., 'http') and (not(contains(., '://dx.doi.org/') or contains(., '://doi.org/') or contains(., '://hdl.handle.net/')))])">
<oaf:identifier identifierType="url">
<xsl:value-of select="." />
</oaf:identifier>
</xsl:for-each>
<xsl:for-each select="distinct-values(//dc:identifier[starts-with(., 'http') and contains(., '://hdl.handle.net/')]/substring-after(., 'hdl.handle.net/'))">
<oaf:identifier identifierType="handle">
<xsl:value-of select="." />
</oaf:identifier>
</xsl:for-each>
<xsl:for-each select="distinct-values(//dc:identifier[starts-with(., 'urn:nbn:nl:') or starts-with(., 'URN:NBN:NL:')])">
<oaf:identifier identifierType='urn'>
<xsl:value-of select="." />
</oaf:identifier>
</xsl:for-each>
<oaf:identifier identifierType="oai-original">
<xsl:value-of
select="//oai:header/oai:identifier" />
</oaf:identifier>
<oaf:hostedBy>
<xsl:attribute name="name">
<xsl:value-of select="//base_dc:collname" />
</xsl:attribute>
<xsl:attribute name="id">
<xsl:value-of select="concat('opendoar____::', //base_dc:collection/@opendoar_id)" />
</xsl:attribute>
</oaf:hostedBy>
<oaf:collectedFrom>
<xsl:attribute name="name">
<xsl:value-of select="$varOfficialName" />
</xsl:attribute>
<xsl:attribute name="id">
<xsl:value-of select="$varDataSourceId" />
</xsl:attribute>
</oaf:collectedFrom>
<oaf:dateAccepted>
<xsl:value-of select="dateCleaner:dateISO( //dc:date[1] )" />
</oaf:dateAccepted>
<xsl:if test="//base_dc:oa[.='1']">
<xsl:for-each select="//dc:relation[starts-with(., 'http')]">
<oaf:fulltext>
<xsl:value-of select="normalize-space(.)" />
</oaf:fulltext>
</xsl:for-each>
</xsl:if>
<xsl:for-each select="//base_dc:collection/@ror_id">
<oaf:relation relType="resultOrganization"
subRelType="affiliation"
relClass="hasAuthorInstitution"
targetType="organization">
<xsl:choose>
<xsl:when test="contains(.,'https://ror.org/')">
<xsl:value-of select="concat('ror_________::', normalize-space(.))" />
</xsl:when>
<xsl:otherwise>
<xsl:value-of select="concat('ror_________::https://ror.org/', normalize-space(.))" />
</xsl:otherwise>
</xsl:choose>
</oaf:relation>
</xsl:for-each>
</metadata>
<xsl:copy-of select="//*[local-name() = 'about']" />
</record>
</xsl:template>
<xsl:template name="allElements">
<xsl:param name="sourceElement" />
<xsl:param name="targetElement" />
<xsl:for-each select="$sourceElement">
<xsl:element name="{$targetElement}">
<xsl:value-of select="normalize-space(.)" />
</xsl:element>
</xsl:for-each>
</xsl:template>
<xsl:template match="//*[local-name() = 'header']">
<xsl:if test="//oai:header/@status='deleted'">
<xsl:call-template name="terminate" />
</xsl:if>
<xsl:copy>
<xsl:apply-templates select="node()|@*" />
<xsl:element name="dr:dateOfTransformation">
<xsl:value-of select="$transDate" />
</xsl:element>
</xsl:copy>
</xsl:template>
<xsl:template match="node()|@*">
<xsl:copy>
<xsl:apply-templates select="node()|@*" />
</xsl:copy>
</xsl:template>
</xsl:stylesheet>
</CODE>
</SCRIPT>
</CONFIGURATION>
<STATUS />
<SECURITY_PARAMETERS />
</BODY>
</RESOURCE_PROFILE>

461
dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/collection/plugin/base/xml/base2odf.transformationRule.xml Normal file
View File

@ -0,0 +1,461 @@
<RESOURCE_PROFILE>
<HEADER>
<RESOURCE_IDENTIFIER value="2ad0cdd9-c96c-484c-8b0e-ed56d86891fe_VHJhbnNmb3JtYXRpb25SdWxlRFNSZXNvdXJjZXMvVHJhbnNmb3JtYXRpb25SdWxlRFNSZXNvdXJjZVR5cGU=" />
<RESOURCE_TYPE value="TransformationRuleDSResourceType" />
<RESOURCE_KIND value="TransformationRuleDSResources" />
<RESOURCE_URI value="" />
<DATE_OF_CREATION value="2024-03-05T11:23:00+00:00" />
</HEADER>
<BODY>
<CONFIGURATION>
<SOURCE_METADATA_FORMAT interpretation="cleaned" layout="store" name="dc" />
<SINK_METADATA_FORMAT name="odf_hbase" />
<IMPORTED />
<SCRIPT>
<TITLE>xslt_base2odf_hadoop</TITLE>
<CODE>
<xsl:stylesheet xmlns:oaire="http://namespace.openaire.eu/schema/oaire/" xmlns:dateCleaner="http://eu/dnetlib/transform/dateISO" xmlns:base_dc="http://oai.base-search.net/base_dc/"
xmlns:datacite="http://datacite.org/schema/kernel-4" xmlns:dr="http://www.driver-repository.eu/namespace/dr" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xmlns:xsl="http://www.w3.org/1999/XSL/Transform" xmlns:vocabulary="http://eu/dnetlib/transform/clean" xmlns:oaf="http://namespace.openaire.eu/oaf"
xmlns:oai="http://www.openarchives.org/OAI/2.0/" xmlns:dri="http://www.driver-repository.eu/namespace/dri" xmlns:xs="http://www.w3.org/2001/XMLSchema" xmlns:dc="http://purl.org/dc/elements/1.1/"
exclude-result-prefixes="xsl vocabulary dateCleaner base_dc" version="2.0">
<xsl:param name="varOfficialName" />
<xsl:param name="varDataSourceId" />
<xsl:param name="varFP7" select="'corda_______::'" />
<xsl:param name="varH2020" select="'corda__h2020::'" />
<xsl:param name="repoCode" select="substring-before(//*[local-name() = 'header']/*[local-name()='recordIdentifier'], ':')" />
<xsl:param name="index" select="0" />
<xsl:param name="transDate" select="current-dateTime()" />
<xsl:template name="terminate">
<xsl:message terminate="yes">
record is not compliant, transformation is interrupted.
</xsl:message>
</xsl:template>
<xsl:template match="/">
<record>
<xsl:apply-templates select="//*[local-name() = 'header']" />
<!-- NOT USED
base_dc:global_id (I used oai:identifier)
base_dc:collection/text()
base_dc:continent
base_dc:country
dc:coverage
dc:source
dc:relation
dc:type (I used //base_dc:typenorm)
dc:language (I used base_dc:lang)
base_dc:link (I used dc:identifier)
-->
<metadata>
<datacite:resource>
<xsl:for-each select="//base_dc:doi">
<datacite:identifier identifierType="DOI">
<xsl:value-of select="." />
</datacite:identifier>
</xsl:for-each>
<datacite:alternateIdentifiers>
<xsl:for-each
select="distinct-values(//dc:identifier[starts-with(., 'http') and (not(contains(., '://dx.doi.org/') or contains(., '://doi.org/') or contains(., '://hdl.handle.net/')))])">
<datacite:identifier alternateIdentifierType="url">
<xsl:value-of select="." />
</datacite:identifier>
</xsl:for-each>
<xsl:for-each select="distinct-values(//dc:identifier[starts-with(., 'http') and contains(., '://hdl.handle.net/')]/substring-after(., 'hdl.handle.net/'))">
<datacite:identifier alternateIdentifierType="handle">
<xsl:value-of select="." />
</datacite:identifier>
</xsl:for-each>
<xsl:for-each select="distinct-values(//dc:identifier[starts-with(., 'urn:nbn:nl:') or starts-with(., 'URN:NBN:NL:')])">
<datacite:identifier alternateIdentifierType='urn'>
<xsl:value-of select="." />
</datacite:identifier>
</xsl:for-each>
<datacite:identifier alternateIdentifierType="oai-original">
<xsl:value-of
select="//oai:header/oai:identifier" />
</datacite:identifier>
</datacite:alternateIdentifiers>
<datacite:relatedIdentifiers />
<xsl:for-each select="//base_dc:typenorm">
<datacite:resourceType><xsl:value-of select="vocabulary:clean(., 'base:normalized_types')" /></datacite:resourceType>
</xsl:for-each>
<datacite:titles>
<xsl:for-each select="//dc:title">
<datacite:title>
<xsl:value-of select="normalize-space(.)" />
</datacite:title>
</xsl:for-each>
</datacite:titles>
<datacite:creators>
<xsl:for-each select="//dc:creator">
<xsl:variable name="author" select="normalize-space(.)" />
<datacite:creator>
<datacite:creatorName>
<xsl:value-of select="$author" />
</datacite:creatorName>
<xsl:for-each select="//base_dc:authod_id[normalize-space(./base_dc:creator_name) = $author]/base_dc:creator_id ">
<xsl:if test="contains(.,'https://orcid.org/')">
<nameIdentifier schemeURI="https://orcid.org/" nameIdentifierScheme="ORCID">
<xsl:value-of select="substring-after(., 'https://orcid.org/')" />
</nameIdentifier>
</xsl:if>
</xsl:for-each>
</datacite:creator>
</xsl:for-each>
</datacite:creators>
<datacite:contributors>
<xsl:for-each select="//dc:contributor">
<datacite:contributor>
<datacite:contributorName>
<xsl:value-of select="normalize-space(.)" />
</datacite:contributorName>
</datacite:contributor>
</xsl:for-each>
</datacite:contributors>
<datacite:descriptions>
<xsl:for-each select="//dc:description">
<datacite:description descriptionType="Abstract">
<xsl:value-of select="normalize-space(.)" />
</datacite:description>
</xsl:for-each>
</datacite:descriptions>
<datacite:subjects>
<xsl:for-each select="//dc:subject">
<datacite:subject>
<xsl:value-of select="normalize-space(.)" />
</datacite:subject>
</xsl:for-each>
<xsl:for-each select="//base_dc:classcode|//base_dc:autoclasscode">
<datacite:subject subjectScheme="{@type}" classificationCode="{normalize-space(.)}">
<!-- TODO the value should be obtained by the Code -->
<xsl:value-of select="normalize-space(.)" />
</datacite:subject>
</xsl:for-each>
</datacite:subjects>
<xsl:for-each select="//dc:publisher">
<datacite:publisher>
<xsl:value-of select="normalize-space(.)" />
</datacite:publisher>
</xsl:for-each>
<xsl:for-each select="//base_dc:year">
<datacite:publicationYear>
<xsl:value-of select="normalize-space(.)" />
</datacite:publicationYear>
</xsl:for-each>
<datacite:formats>
<xsl:for-each select="//dc:format">
<datacite:format>
<xsl:value-of select="normalize-space(.)" />
</datacite:format>
</xsl:for-each>
</datacite:formats>
<datacite:language>
<xsl:value-of select="vocabulary:clean( //base_dc:lang, 'dnet:languages')" />
</datacite:language>
<oaf:accessrights>
<xsl:if test="//base_dc:oa[.='0']">
<datacite:rights rightsURI="http://purl.org/coar/access_right/c_16ec">restricted access</datacite:rights>
</xsl:if>
<xsl:if test="//base_dc:oa[.='1']">
<datacite:rights rightsURI="http://purl.org/coar/access_right/c_abf2">open access</datacite:rights>
</xsl:if>
<xsl:for-each select="//dc:rights|//base_dc:rightsnorm">
<datacite:rights><xsl:value-of select="vocabulary:clean(., 'dnet:access_modes')" /></datacite:rights>
</xsl:for-each>
</oaf:accessrights>
</datacite:resource>
<xsl:for-each select="//dc:relation">
<xsl:if test="matches(normalize-space(.), '(info:eu-repo/grantagreement/ec/fp7/)(\d\d\d\d\d\d)(.*)', 'i')">
<oaf:projectid>
<xsl:value-of select="concat($varFP7, replace(normalize-space(.), '(info:eu-repo/grantagreement/ec/fp7/)(\d\d\d\d\d\d)(.*)', '$2', 'i'))" />
</oaf:projectid>
</xsl:if>
<xsl:if test="matches(normalize-space(.), '(info:eu-repo/grantagreement/ec/h2020/)(\d\d\d\d\d\d)(.*)', 'i')">
<oaf:projectid>
<xsl:value-of select="concat($varH2020, replace(normalize-space(.), '(info:eu-repo/grantagreement/ec/h2020/)(\d\d\d\d\d\d)(.*)', '$2', 'i'))" />
</oaf:projectid>
</xsl:if>
</xsl:for-each>
<xsl:choose>
<!-- I used an inline mapping because the field typenorm could be repeated and I have to specify a list of priority -->
<!-- Book part -->
<xsl:when test="//base_dc:typenorm = '111'">
<dr:CobjCategory type="publication">0013</dr:CobjCategory>
</xsl:when>
<!-- Book -->
<xsl:when test="//base_dc:typenorm = '11'">
<dr:CobjCategory type="publication">0002</dr:CobjCategory>
</xsl:when>
<!-- Article contribution -->
<xsl:when test="//base_dc:typenorm = '121'">
<dr:CobjCategory type="publication">0001</dr:CobjCategory>
</xsl:when>
<!-- Journal/Newspaper -->
<xsl:when test="//base_dc:typenorm = '12'">
<dr:CobjCategory type="publication">0043</dr:CobjCategory>
</xsl:when>
<!-- Report -->
<xsl:when test="//base_dc:typenorm = '14'">
<dr:CobjCategory type="publication">0017</dr:CobjCategory>
</xsl:when>
<!-- Review -->
<xsl:when test="//base_dc:typenorm = '15'">
<dr:CobjCategory type="publication">0015</dr:CobjCategory>
</xsl:when>
<!-- Lecture -->
<xsl:when test="//base_dc:typenorm = '17'">
<dr:CobjCategory type="publication">0010</dr:CobjCategory>
</xsl:when>
<!-- Bachelor's thesis -->
<xsl:when test="//base_dc:typenorm = '181'">
<dr:CobjCategory type="publication">0008</dr:CobjCategory>
</xsl:when>
<!-- Master's thesis -->
<xsl:when test="//base_dc:typenorm = '182'">
<dr:CobjCategory type="publication">0007</dr:CobjCategory>
</xsl:when>
<!-- Doctoral and postdoctoral thesis -->
<xsl:when test="//base_dc:typenorm = '183'">
<dr:CobjCategory type="publication">0006</dr:CobjCategory>
</xsl:when>
<!-- Thesis -->
<xsl:when test="//base_dc:typenorm = '18'">
<dr:CobjCategory type="publication">0044</dr:CobjCategory>
</xsl:when>
<!-- Patent -->
<xsl:when test="//base_dc:typenorm = '1A'">
<dr:CobjCategory type="publication">0019</dr:CobjCategory>
</xsl:when>
<!-- Text -->
<xsl:when test="//base_dc:typenorm = '1'">
<dr:CobjCategory type="publication">0001</dr:CobjCategory>
</xsl:when>
<!-- Software -->
<xsl:when test="//base_dc:typenorm = '6'">
<dr:CobjCategory type="software">0029</dr:CobjCategory>
</xsl:when>
<!-- Dataset -->
<xsl:when test="//base_dc:typenorm = '7'">
<dr:CobjCategory type="dataset">0021</dr:CobjCategory>
</xsl:when>
<!-- Still image -->
<xsl:when test="//base_dc:typenorm = '51'">
<dr:CobjCategory type="other">0025</dr:CobjCategory>
</xsl:when>
<!-- Moving image/Video -->
<xsl:when test="//base_dc:typenorm = '52'">
<dr:CobjCategory type="other">0024</dr:CobjCategory>
</xsl:when>
<!-- Image/Video -->
<xsl:when test="//base_dc:typenorm = '5'">
<dr:CobjCategory type="other">0033</dr:CobjCategory>
</xsl:when>
<!-- Audio -->
<xsl:when test="//base_dc:typenorm = '4'">
<dr:CobjCategory type="other">0030</dr:CobjCategory>
</xsl:when>
<!-- Musical notation -->
<xsl:when test="//base_dc:typenorm = '2'">
<dr:CobjCategory type="other">0020</dr:CobjCategory>
</xsl:when>
<!-- Map -->
<xsl:when test="//base_dc:typenorm = '3'">
<dr:CobjCategory type="other">0020</dr:CobjCategory>
</xsl:when>
<!-- Other non-article -->
<xsl:when test="//base_dc:typenorm = '122'">
<dr:CobjCategory type="publication">0038</dr:CobjCategory>
</xsl:when>
<!-- Course material -->
<xsl:when test="//base_dc:typenorm = '16'">
<dr:CobjCategory type="publication">0038</dr:CobjCategory>
</xsl:when>
<!-- Manuscript -->
<xsl:when test="//base_dc:typenorm = '19'">
<dr:CobjCategory type="publication">0038</dr:CobjCategory>
</xsl:when>
<!-- Conference object -->
<xsl:when test="//base_dc:typenorm = '13'">
<dr:CobjCategory type="publication">0004</dr:CobjCategory>
</xsl:when>
<!-- Unknown -->
<xsl:when test="//base_dc:typenorm = 'F'">
<dr:CobjCategory type="other">0000</dr:CobjCategory>
</xsl:when>
<xsl:otherwise>
<dr:CobjCategory type="other">0000</dr:CobjCategory>
</xsl:otherwise>
</xsl:choose>
<oaf:accessrights>
<xsl:choose>
<xsl:when test="//base_dc:oa[.='0']">CLOSED</xsl:when>
<xsl:when test="//base_dc:oa[.='1']">OPEN</xsl:when>
<xsl:when test="//base_dc:oa[.='2']">UNKNOWN</xsl:when>
<xsl:when test="//base_dc:rightsnorm">
<xsl:value-of select="vocabulary:clean(//base_dc:rightsnorm, 'dnet:access_modes')" />
</xsl:when>
<xsl:when test="//dc:rights">
<xsl:value-of select="vocabulary:clean( //dc:rights, 'dnet:access_modes')" />
</xsl:when>
<xsl:otherwise>UNKNOWN</xsl:otherwise>
</xsl:choose>
</oaf:accessrights>
<xsl:for-each select="//base_dc:doi">
<oaf:identifier identifierType="doi">
<xsl:value-of select="." />
</oaf:identifier>
</xsl:for-each>
<xsl:for-each
select="distinct-values(//dc:identifier[starts-with(., 'http') and ( not(contains(., '://dx.doi.org/') or contains(., '://doi.org/') or contains(., '://hdl.handle.net/')))])">
<oaf:identifier identifierType="url">
<xsl:value-of select="." />
</oaf:identifier>
</xsl:for-each>
<xsl:for-each select="distinct-values(//dc:identifier[starts-with(., 'http') and contains(., '://hdl.handle.net/')]/substring-after(., 'hdl.handle.net/'))">
<oaf:identifier identifierType="handle">
<xsl:value-of select="." />
</oaf:identifier>
</xsl:for-each>
<xsl:for-each select="distinct-values(//dc:identifier[starts-with(., 'urn:nbn:nl:') or starts-with(., 'URN:NBN:NL:')])">
<oaf:identifier identifierType='urn'>
<xsl:value-of select="." />
</oaf:identifier>
</xsl:for-each>
<oaf:identifier identifierType="oai-original">
<xsl:value-of
select="//oai:header/oai:identifier" />
</oaf:identifier>
<oaf:hostedBy>
<xsl:attribute name="name">
<xsl:value-of select="//base_dc:collname" />
</xsl:attribute>
<xsl:attribute name="id">
<xsl:value-of select="concat('opendoar____::', //base_dc:collection/@opendoar_id)" />
</xsl:attribute>
</oaf:hostedBy>
<oaf:collectedFrom>
<xsl:attribute name="name">
<xsl:value-of select="$varOfficialName" />
</xsl:attribute>
<xsl:attribute name="id">
<xsl:value-of select="$varDataSourceId" />
</xsl:attribute>
</oaf:collectedFrom>
<oaf:dateAccepted>
<xsl:value-of select="dateCleaner:dateISO( //dc:date[1] )" />
</oaf:dateAccepted>
<xsl:if test="//base_dc:oa[.='1']">
<xsl:for-each select="//dc:relation[starts-with(., 'http')]">
<oaf:fulltext>
<xsl:value-of select="normalize-space(.)" />
</oaf:fulltext>
</xsl:for-each>
</xsl:if>
<xsl:for-each select="//base_dc:collection/@ror_id">
<oaf:relation relType="resultOrganization" subRelType="affiliation" relClass="hasAuthorInstitution" targetType="organization">
<xsl:choose>
<xsl:when test="contains(.,'https://ror.org/')">
<xsl:value-of select="concat('ror_________::', normalize-space(.))" />
</xsl:when>
<xsl:otherwise>
<xsl:value-of select="concat('ror_________::https://ror.org/', normalize-space(.))" />
</xsl:otherwise>
</xsl:choose>
</oaf:relation>
</xsl:for-each>
</metadata>
<xsl:copy-of select="//*[local-name() = 'about']" />
</record>
</xsl:template>
<xsl:template match="//*[local-name() = 'header']">
<xsl:if test="//oai:header/@status='deleted'">
<xsl:call-template name="terminate" />
</xsl:if>
<xsl:copy>
<xsl:apply-templates select="node()|@*" />
<xsl:element name="dr:dateOfTransformation">
<xsl:value-of select="$transDate" />
</xsl:element>
</xsl:copy>
</xsl:template>
<xsl:template match="node()|@*">
<xsl:copy>
<xsl:apply-templates select="node()|@*" />
</xsl:copy>
</xsl:template>
</xsl:stylesheet>
</CODE>
</SCRIPT>
</CONFIGURATION>
<STATUS />
<SECURITY_PARAMETERS />
</BODY>
</RESOURCE_PROFILE>

120
dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/collection/orcid/SparkApplyUpdate.scala Normal file
View File

@ -0,0 +1,120 @@
package eu.dnetlib.dhp.collection.orcid
import eu.dnetlib.dhp.application.AbstractScalaApplication
import org.apache.spark.sql.{DataFrame, SaveMode, SparkSession}
import org.slf4j.{Logger, LoggerFactory}
class SparkApplyUpdate(propertyPath: String, args: Array[String], log: Logger)
extends AbstractScalaApplication(propertyPath, args, log: Logger) {
/** Here all the spark applications runs this method
* where the whole logic of the spark node is defined
*/
override def run(): Unit = {
val graphPath: String = parser.get("graphPath")
log.info("found parameters graphPath: {}", graphPath)
val updatePath: String = parser.get("updatePath")
log.info("found parameters updatePath: {}", updatePath)
val targetPath: String = parser.get("targetPath")
log.info("found parameters targetPath: {}", targetPath)
applyTableUpdate(spark, graphPath, updatePath, targetPath)
checkUpdate(spark, graphPath, targetPath)
moveTable(spark, graphPath, targetPath)
}
private def moveTable(spark: SparkSession, graphPath: String, updatePath: String): Unit = {
spark.read
.load(s"$updatePath/Authors")
.repartition(1000)
.write
.mode(SaveMode.Overwrite)
.save(s"$graphPath/Authors")
spark.read
.load(s"$updatePath/Works")
.repartition(1000)
.write
.mode(SaveMode.Overwrite)
.save(s"$graphPath/Works")
spark.read
.load(s"$updatePath/Employments")
.repartition(1000)
.write
.mode(SaveMode.Overwrite)
.save(s"$graphPath/Employments")
}
private def updateDataset(
inputDataset: DataFrame,
idUpdate: DataFrame,
updateDataframe: DataFrame,
targetPath: String
): Unit = {
inputDataset
.join(idUpdate, inputDataset("orcid").equalTo(idUpdate("orcid")), "leftanti")
.select(inputDataset("*"))
.unionByName(updateDataframe)
.write
.mode(SaveMode.Overwrite)
.save(targetPath)
}
private def checkUpdate(spark: SparkSession, graphPath: String, updatePath: String): Unit = {
val totalOriginalAuthors = spark.read.load(s"$graphPath/Authors").count
val totalOriginalWorks = spark.read.load(s"$graphPath/Works").count
val totalOriginalEmployments = spark.read.load(s"$graphPath/Employments").count
val totalUpdateAuthors = spark.read.load(s"$updatePath/Authors").count
val totalUpdateWorks = spark.read.load(s"$updatePath/Works").count
val totalUpdateEmployments = spark.read.load(s"$updatePath/Employments").count
log.info("totalOriginalAuthors: {}", totalOriginalAuthors)
log.info("totalOriginalWorks: {}", totalOriginalWorks)
log.info("totalOriginalEmployments: {}", totalOriginalEmployments)
log.info("totalUpdateAuthors: {}", totalUpdateAuthors)
log.info("totalUpdateWorks: {}", totalUpdateWorks)
log.info("totalUpdateEmployments: {}", totalUpdateEmployments)
if (
totalUpdateAuthors < totalOriginalAuthors || totalUpdateEmployments < totalOriginalEmployments || totalUpdateWorks < totalOriginalWorks
)
throw new RuntimeException("The updated Graph contains less elements of the original one")
}
private def applyTableUpdate(spark: SparkSession, graphPath: String, updatePath: String, targetPath: String): Unit = {
val orcidIDUpdate = spark.read.load(s"$updatePath/Authors").select("orcid")
updateDataset(
spark.read.load(s"$graphPath/Authors"),
orcidIDUpdate,
spark.read.load(s"$updatePath/Authors"),
s"$targetPath/Authors"
)
updateDataset(
spark.read.load(s"$graphPath/Employments"),
orcidIDUpdate,
spark.read.load(s"$updatePath/Employments"),
s"$targetPath/Employments"
)
updateDataset(
spark.read.load(s"$graphPath/Works"),
orcidIDUpdate,
spark.read.load(s"$updatePath/Works"),
s"$targetPath/Works"
)
}
}
object SparkApplyUpdate {
val log: Logger = LoggerFactory.getLogger(SparkGenerateORCIDTable.getClass)
def main(args: Array[String]): Unit = {
new SparkApplyUpdate("/eu/dnetlib/dhp/collection/orcid/apply_orcid_table_parameter.json", args, log)
.initialize()
.run()
}
}

59
dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/collection/orcid/SparkGenerateORCIDTable.scala
View File

@ -6,6 +6,7 @@ import org.apache.hadoop.io.Text
import org.apache.spark.SparkContext
import org.apache.spark.sql.{Encoder, Encoders, SaveMode, SparkSession}
import org.slf4j.{Logger, LoggerFactory}
import scala.collection.JavaConverters._
class SparkGenerateORCIDTable(propertyPath: String, args: Array[String], log: Logger)
extends AbstractScalaApplication(propertyPath, args, log: Logger) {
@ -18,12 +19,16 @@ class SparkGenerateORCIDTable(propertyPath: String, args: Array[String], log: Lo
log.info("found parameters sourcePath: {}", sourcePath)
val targetPath: String = parser.get("targetPath")
log.info("found parameters targetPath: {}", targetPath)
extractORCIDTable(spark, sourcePath, targetPath)
extractORCIDEmploymentsTable(spark, sourcePath, targetPath)
extractORCIDWorksTable(spark, sourcePath, targetPath)
val fromUpdate = "true".equals(parser.get("fromUpdate"))
val sourceSummaryPath = if (fromUpdate) s"$sourcePath/summary*" else sourcePath
val sourceEmploymentsPath = if (fromUpdate) s"$sourcePath/employments*" else sourcePath
val sourceWorksPath = if (fromUpdate) s"$sourcePath/works*" else sourcePath
extractORCIDTable(spark, sourceSummaryPath, targetPath, fromUpdate)
extractORCIDEmploymentsTable(spark, sourceEmploymentsPath, targetPath, fromUpdate)
extractORCIDWorksTable(spark, sourceWorksPath, targetPath, fromUpdate)
}
def extractORCIDTable(spark: SparkSession, sourcePath: String, targetPath: String): Unit = {
def extractORCIDTable(spark: SparkSession, sourcePath: String, targetPath: String, skipFilterByKey: Boolean): Unit = {
val sc: SparkContext = spark.sparkContext
import spark.implicits._
val df = sc
@ -32,8 +37,8 @@ class SparkGenerateORCIDTable(propertyPath: String, args: Array[String], log: Lo
.toDF
.as[(String, String)]
implicit val orcidAuthor: Encoder[Author] = Encoders.bean(classOf[Author])
// implicit val orcidPID:Encoder[Pid] = Encoders.bean(classOf[Pid])
df.filter(r => r._1.contains("summaries"))
val newDf = if (!skipFilterByKey) df.filter(r => r._1.contains("summaries")) else df
newDf
.map { r =>
val p = new OrcidParser
p.parseSummary(r._2)
@ -44,7 +49,12 @@ class SparkGenerateORCIDTable(propertyPath: String, args: Array[String], log: Lo
.save(s"$targetPath/Authors")
}
def extractORCIDWorksTable(spark: SparkSession, sourcePath: String, targetPath: String): Unit = {
def extractORCIDWorksTable(
spark: SparkSession,
sourcePath: String,
targetPath: String,
skipFilterByKey: Boolean
): Unit = {
val sc: SparkContext = spark.sparkContext
import spark.implicits._
val df = sc
@ -53,7 +63,19 @@ class SparkGenerateORCIDTable(propertyPath: String, args: Array[String], log: Lo
.toDF
.as[(String, String)]
implicit val orcidWorkAuthor: Encoder[Work] = Encoders.bean(classOf[Work])
implicit val orcidPID: Encoder[Pid] = Encoders.bean(classOf[Pid])
//We are in the case of parsing ORCID UPDATE
if (skipFilterByKey) {
df.flatMap { r =>
val p = new OrcidParser
p.parseWorks(r._2).asScala
}.filter(p => p != null)
.write
.mode(SaveMode.Overwrite)
.save(s"$targetPath/Works")
}
//We are in the case of parsing ORCID DUMP
else {
df.filter(r => r._1.contains("works"))
.map { r =>
val p = new OrcidParser
@ -64,8 +86,14 @@ class SparkGenerateORCIDTable(propertyPath: String, args: Array[String], log: Lo
.mode(SaveMode.Overwrite)
.save(s"$targetPath/Works")
}
}
def extractORCIDEmploymentsTable(spark: SparkSession, sourcePath: String, targetPath: String): Unit = {
def extractORCIDEmploymentsTable(
spark: SparkSession,
sourcePath: String,
targetPath: String,
skipFilterByKey: Boolean
): Unit = {
val sc: SparkContext = spark.sparkContext
import spark.implicits._
val df = sc
@ -74,7 +102,17 @@ class SparkGenerateORCIDTable(propertyPath: String, args: Array[String], log: Lo
.toDF
.as[(String, String)]
implicit val orcidEmploymentAuthor: Encoder[Employment] = Encoders.bean(classOf[Employment])
implicit val orcidPID: Encoder[Pid] = Encoders.bean(classOf[Pid])
if (skipFilterByKey) {
df.flatMap { r =>
val p = new OrcidParser
p.parseEmployments(r._2).asScala
}.filter(p => p != null)
.write
.mode(SaveMode.Overwrite)
.save(s"$targetPath/Employments")
}
//We are in the case of parsing ORCID DUMP
else {
df.filter(r => r._1.contains("employments"))
.map { r =>
val p = new OrcidParser
@ -85,6 +123,7 @@ class SparkGenerateORCIDTable(propertyPath: String, args: Array[String], log: Lo
.mode(SaveMode.Overwrite)
.save(s"$targetPath/Employments")
}
}
}
object SparkGenerateORCIDTable {

13
dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/actionmanager/bipaffiliations/PrepareAffiliationRelationsTest.java
View File

@ -78,10 +78,6 @@ public class PrepareAffiliationRelationsTest {
.getResource("/eu/dnetlib/dhp/actionmanager/bipaffiliations/doi_to_ror.json")
.getPath();
String pubmedAffiliationRelationsPath = getClass()
.getResource("/eu/dnetlib/dhp/actionmanager/bipaffiliations/doi_to_ror.json")
.getPath();
String outputPath = workingDir.toString() + "/actionSet";
PrepareAffiliationRelations
@ -89,7 +85,8 @@ public class PrepareAffiliationRelationsTest {
new String[] {
"-isSparkSessionManaged", Boolean.FALSE.toString(),
"-crossrefInputPath", crossrefAffiliationRelationPath,
"-pubmedInputPath", pubmedAffiliationRelationsPath,
"-pubmedInputPath", crossrefAffiliationRelationPath,
"-openapcInputPath", crossrefAffiliationRelationPath,
"-outputPath", outputPath
});
@ -106,7 +103,7 @@ public class PrepareAffiliationRelationsTest {
// );
// }
// count the number of relations
assertEquals(40, tmp.count());
assertEquals(60, tmp.count());
Dataset<Relation> dataset = spark.createDataset(tmp.rdd(), Encoders.bean(Relation.class));
dataset.createOrReplaceTempView("result");
@ -117,7 +114,7 @@ public class PrepareAffiliationRelationsTest {
// verify that we have equal number of bi-directional relations
Assertions
.assertEquals(
20, execVerification
30, execVerification
.filter(
"relClass='" + ModelConstants.HAS_AUTHOR_INSTITUTION + "'")
.collectAsList()
@ -125,7 +122,7 @@ public class PrepareAffiliationRelationsTest {
Assertions
.assertEquals(
20, execVerification
30, execVerification
.filter(
"relClass='" + ModelConstants.IS_AUTHOR_INSTITUTION_OF + "'")
.collectAsList()

324
dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/actionmanager/transformativeagreement/CreateTAActionSetTest.java Normal file
View File

@ -0,0 +1,324 @@
package eu.dnetlib.dhp.actionmanager.transformativeagreement;
import static org.junit.jupiter.api.Assertions.assertEquals;
import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Path;
import org.apache.commons.io.FileUtils;
import org.apache.hadoop.io.Text;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.sql.SparkSession;
import org.junit.jupiter.api.AfterAll;
import org.junit.jupiter.api.BeforeAll;
import org.junit.jupiter.api.Test;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.actionmanager.opencitations.CreateActionSetSparkJob;
import eu.dnetlib.dhp.actionmanager.opencitations.CreateOpenCitationsASTest;
import eu.dnetlib.dhp.schema.action.AtomicAction;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.Relation;
import eu.dnetlib.dhp.schema.oaf.utils.CleaningFunctions;
import eu.dnetlib.dhp.schema.oaf.utils.IdentifierFactory;
/**
* @author miriam.baglioni
* @Date 13/02/24
*/
public class CreateTAActionSetTest {
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
private static SparkSession spark;
private static Path workingDir;
private static final Logger log = LoggerFactory
.getLogger(CreateOpenCitationsASTest.class);
@BeforeAll
public static void beforeAll() throws IOException {
workingDir = Files
.createTempDirectory(CreateTAActionSetTest.class.getSimpleName());
log.info("using work dir {}", workingDir);
SparkConf conf = new SparkConf();
conf.setAppName(CreateTAActionSetTest.class.getSimpleName());
conf.setMaster("local[*]");
conf.set("spark.driver.host", "localhost");
conf.set("hive.metastore.local", "true");
conf.set("spark.ui.enabled", "false");
conf.set("spark.sql.warehouse.dir", workingDir.toString());
conf.set("hive.metastore.warehouse.dir", workingDir.resolve("warehouse").toString());
spark = SparkSession
.builder()
.appName(CreateTAActionSetTest.class.getSimpleName())
.config(conf)
.getOrCreate();
}
@AfterAll
public static void afterAll() throws IOException {
FileUtils.deleteDirectory(workingDir.toFile());
spark.stop();
}
@Test
void createActionSet() throws Exception {
String inputPath = getClass()
.getResource(
"/eu/dnetlib/dhp/actionmanager/transformativeagreement/facts.json")
.getPath();
eu.dnetlib.dhp.actionmanager.transformativeagreement.CreateActionSetSparkJob
.main(
new String[] {
"-isSparkSessionManaged",
Boolean.FALSE.toString(),
"-inputPath",
inputPath,
"-outputPath",
workingDir.toString() + "/actionSet1"
});
}
@Test
void testNumberofRelations2() throws Exception {
String inputPath = getClass()
.getResource(
"/eu/dnetlib/dhp/actionmanager/opencitations/COCI")
.getPath();
eu.dnetlib.dhp.actionmanager.opencitations.CreateActionSetSparkJob
.main(
new String[] {
"-isSparkSessionManaged",
Boolean.FALSE.toString(),
"-inputPath",
inputPath,
"-outputPath",
workingDir.toString() + "/actionSet2"
});
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
JavaRDD<Relation> tmp = sc
.sequenceFile(workingDir.toString() + "/actionSet2", Text.class, Text.class)
.map(value -> OBJECT_MAPPER.readValue(value._2().toString(), AtomicAction.class))
.map(aa -> ((Relation) aa.getPayload()));
assertEquals(23, tmp.count());
// tmp.foreach(r -> System.out.println(OBJECT_MAPPER.writeValueAsString(r)));
}
@Test
void testRelationsCollectedFrom() throws Exception {
String inputPath = getClass()
.getResource(
"/eu/dnetlib/dhp/actionmanager/opencitations/COCI")
.getPath();
eu.dnetlib.dhp.actionmanager.opencitations.CreateActionSetSparkJob
.main(
new String[] {
"-isSparkSessionManaged",
Boolean.FALSE.toString(),
"-inputPath",
inputPath,
"-outputPath",
workingDir.toString() + "/actionSet3"
});
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
JavaRDD<Relation> tmp = sc
.sequenceFile(workingDir.toString() + "/actionSet3", Text.class, Text.class)
.map(value -> OBJECT_MAPPER.readValue(value._2().toString(), AtomicAction.class))
.map(aa -> ((Relation) aa.getPayload()));
tmp.foreach(r -> {
assertEquals(ModelConstants.OPENOCITATIONS_NAME, r.getCollectedfrom().get(0).getValue());
assertEquals(ModelConstants.OPENOCITATIONS_ID, r.getCollectedfrom().get(0).getKey());
});
}
@Test
void testRelationsDataInfo() throws Exception {
String inputPath = getClass()
.getResource(
"/eu/dnetlib/dhp/actionmanager/opencitations/COCI")
.getPath();
eu.dnetlib.dhp.actionmanager.opencitations.CreateActionSetSparkJob
.main(
new String[] {
"-isSparkSessionManaged",
Boolean.FALSE.toString(),
"-inputPath",
inputPath,
"-outputPath",
workingDir.toString() + "/actionSet4"
});
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
JavaRDD<Relation> tmp = sc
.sequenceFile(workingDir.toString() + "/actionSet4", Text.class, Text.class)
.map(value -> OBJECT_MAPPER.readValue(value._2().toString(), AtomicAction.class))
.map(aa -> ((Relation) aa.getPayload()));
tmp.foreach(r -> {
assertEquals(false, r.getDataInfo().getInferred());
assertEquals(false, r.getDataInfo().getDeletedbyinference());
assertEquals("0.91", r.getDataInfo().getTrust());
assertEquals(
eu.dnetlib.dhp.actionmanager.opencitations.CreateActionSetSparkJob.OPENCITATIONS_CLASSID,
r.getDataInfo().getProvenanceaction().getClassid());
assertEquals(
eu.dnetlib.dhp.actionmanager.opencitations.CreateActionSetSparkJob.OPENCITATIONS_CLASSNAME,
r.getDataInfo().getProvenanceaction().getClassname());
assertEquals(ModelConstants.DNET_PROVENANCE_ACTIONS, r.getDataInfo().getProvenanceaction().getSchemeid());
assertEquals(ModelConstants.DNET_PROVENANCE_ACTIONS, r.getDataInfo().getProvenanceaction().getSchemename());
});
}
@Test
void testRelationsSemantics() throws Exception {
String inputPath = getClass()
.getResource(
"/eu/dnetlib/dhp/actionmanager/opencitations/COCI")
.getPath();
eu.dnetlib.dhp.actionmanager.opencitations.CreateActionSetSparkJob
.main(
new String[] {
"-isSparkSessionManaged",
Boolean.FALSE.toString(),
"-inputPath",
inputPath,
"-outputPath",
workingDir.toString() + "/actionSet5"
});
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
JavaRDD<Relation> tmp = sc
.sequenceFile(workingDir.toString() + "/actionSet5", Text.class, Text.class)
.map(value -> OBJECT_MAPPER.readValue(value._2().toString(), AtomicAction.class))
.map(aa -> ((Relation) aa.getPayload()));
tmp.foreach(r -> {
assertEquals("citation", r.getSubRelType());
assertEquals("resultResult", r.getRelType());
});
assertEquals(23, tmp.filter(r -> r.getRelClass().equals("Cites")).count());
assertEquals(0, tmp.filter(r -> r.getRelClass().equals("IsCitedBy")).count());
}
@Test
void testRelationsSourceTargetPrefix() throws Exception {
String inputPath = getClass()
.getResource(
"/eu/dnetlib/dhp/actionmanager/opencitations/COCI")
.getPath();
eu.dnetlib.dhp.actionmanager.opencitations.CreateActionSetSparkJob
.main(
new String[] {
"-isSparkSessionManaged",
Boolean.FALSE.toString(),
"-inputPath",
inputPath,
"-outputPath",
workingDir.toString() + "/actionSet6"
});
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
JavaRDD<Relation> tmp = sc
.sequenceFile(workingDir.toString() + "/actionSet6", Text.class, Text.class)
.map(value -> OBJECT_MAPPER.readValue(value._2().toString(), AtomicAction.class))
.map(aa -> ((Relation) aa.getPayload()));
tmp.foreach(r -> {
assertEquals("50|doi_________::", r.getSource().substring(0, 17));
assertEquals("50|doi_________::", r.getTarget().substring(0, 17));
});
}
@Test
void testRelationsSourceTargetCouple() throws Exception {
final String doi1 = "50|doi_________::"
+ IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", "10.1007/s10854-015-3684-x"));
final String doi2 = "50|doi_________::"
+ IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", "10.1111/j.1551-2916.2008.02408.x"));
final String doi3 = "50|doi_________::"
+ IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", "10.1007/s10854-014-2114-9"));
final String doi4 = "50|doi_________::"
+ IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", "10.1016/j.ceramint.2013.09.069"));
final String doi5 = "50|doi_________::"
+ IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", "10.1007/s10854-009-9913-4"));
final String doi6 = "50|doi_________::"
+ IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", "10.1016/0038-1098(72)90370-5"));
String inputPath = getClass()
.getResource(
"/eu/dnetlib/dhp/actionmanager/opencitations/COCI")
.getPath();
CreateActionSetSparkJob
.main(
new String[] {
"-isSparkSessionManaged",
Boolean.FALSE.toString(),
"-inputPath",
inputPath,
"-outputPath",
workingDir.toString() + "/actionSet7"
});
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
JavaRDD<Relation> tmp = sc
.sequenceFile(workingDir.toString() + "/actionSet7", Text.class, Text.class)
.map(value -> OBJECT_MAPPER.readValue(value._2().toString(), AtomicAction.class))
.map(aa -> ((Relation) aa.getPayload()));
JavaRDD<Relation> check = tmp.filter(r -> r.getSource().equals(doi1) || r.getTarget().equals(doi1));
assertEquals(5, check.count());
// check.foreach(r -> {
// if (r.getSource().equals(doi2) || r.getSource().equals(doi3) || r.getSource().equals(doi4) ||
// r.getSource().equals(doi5) || r.getSource().equals(doi6)) {
// assertEquals(ModelConstants.IS_CITED_BY, r.getRelClass());
// assertEquals(doi1, r.getTarget());
// }
// });
assertEquals(5, check.filter(r -> r.getSource().equals(doi1)).count());
check.filter(r -> r.getSource().equals(doi1)).foreach(r -> assertEquals(ModelConstants.CITES, r.getRelClass()));
}
}

35
dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/collection/orcid/DownloadORCIDTest.java
View File

@ -2,6 +2,7 @@
package eu.dnetlib.dhp.collection.orcid;
import java.io.IOException;
import java.net.URI;
import java.util.Arrays;
import java.util.List;
import java.util.Objects;
@ -9,7 +10,12 @@ import java.util.Objects;
import org.apache.commons.io.IOUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.LocalFileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.SequenceFile;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.compress.CompressionCodec;
import org.apache.hadoop.io.compress.CompressionCodecFactory;
import org.apache.spark.SparkContext;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.sql.Encoders;
@ -27,6 +33,7 @@ import com.ximpleware.XPathParseException;
import eu.dnetlib.dhp.collection.orcid.model.Author;
import eu.dnetlib.dhp.collection.orcid.model.ORCIDItem;
import eu.dnetlib.dhp.collection.orcid.model.Work;
import eu.dnetlib.dhp.parser.utility.VtdException;
public class DownloadORCIDTest {
@ -82,6 +89,34 @@ public class DownloadORCIDTest {
});
}
@Test
public void testParsingOrcidUpdateEmployments() throws Exception {
final String xml = IOUtils
.toString(
Objects
.requireNonNull(
getClass().getResourceAsStream("/eu/dnetlib/dhp/collection/orcid/update_employments.xml")));
final OrcidParser parser = new OrcidParser();
final ObjectMapper mapper = new ObjectMapper();
System.out.println(mapper.writeValueAsString(parser.parseEmployments(xml)));
}
@Test
public void testParsingOrcidUpdateWorks() throws Exception {
final String xml = IOUtils
.toString(
Objects
.requireNonNull(
getClass().getResourceAsStream("/eu/dnetlib/dhp/collection/orcid/update_work.xml")));
final OrcidParser parser = new OrcidParser();
final List<Work> works = parser.parseWorks(xml);
final ObjectMapper mapper = new ObjectMapper();
System.out.println(mapper.writeValueAsString(works));
}
@Test
public void testParsingEmployments() throws Exception {

38
dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/collection/plugin/base/BaseCollectionInfo.java Normal file
View File

@ -0,0 +1,38 @@
package eu.dnetlib.dhp.collection.plugin.base;
import java.io.Serializable;
public class BaseCollectionInfo implements Serializable {
private static final long serialVersionUID = 5766333937429419647L;
private String id;
private String opendoarId;
private String rorId;
public String getId() {
return this.id;
}
public void setId(final String id) {
this.id = id;
}
public String getOpendoarId() {
return this.opendoarId;
}
public void setOpendoarId(final String opendoarId) {
this.opendoarId = opendoarId;
}
public String getRorId() {
return this.rorId;
}
public void setRorId(final String rorId) {
this.rorId = rorId;
}
}

184
dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/collection/plugin/base/BaseCollectorIteratorTest.java Normal file
View File

@ -0,0 +1,184 @@
package eu.dnetlib.dhp.collection.plugin.base;
import static org.junit.jupiter.api.Assertions.assertEquals;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.HashSet;
import java.util.LinkedHashSet;
import java.util.List;
import java.util.Map;
import java.util.Map.Entry;
import java.util.Set;
import java.util.concurrent.atomic.AtomicInteger;
import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.StringUtils;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.SparkSession;
import org.dom4j.Attribute;
import org.dom4j.Document;
import org.dom4j.DocumentException;
import org.dom4j.DocumentHelper;
import org.dom4j.Element;
import org.dom4j.Node;
import org.junit.jupiter.api.Disabled;
import org.junit.jupiter.api.Test;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.common.aggregation.AggregatorReport;
@Disabled
public class BaseCollectorIteratorTest {
@Test
void testImportFile() throws Exception {
long count = 0;
final BaseCollectorIterator iterator = new BaseCollectorIterator("base-sample.tar", new AggregatorReport());
final Map<String, Map<String, String>> collections = new HashMap<>();
final Map<String, AtomicInteger> fields = new HashMap<>();
final Set<String> types = new HashSet<>();
while (iterator.hasNext()) {
final Document record = DocumentHelper.parseText(iterator.next());
count++;
if ((count % 1000) == 0) {
System.out.println("# Read records: " + count);
}
// System.out.println(record.asXML());
for (final Object o : record.selectNodes("//*|//@*")) {
final String path = ((Node) o).getPath();
if (fields.containsKey(path)) {
fields.get(path).incrementAndGet();
} else {
fields.put(path, new AtomicInteger(1));
}
if (o instanceof Element) {
final Element n = (Element) o;
if ("collection".equals(n.getName())) {
final String collName = n.getText().trim();
if (StringUtils.isNotBlank(collName) && !collections.containsKey(collName)) {
final Map<String, String> collAttrs = new HashMap<>();
for (final Object ao : n.attributes()) {
collAttrs.put(((Attribute) ao).getName(), ((Attribute) ao).getValue());
}
collections.put(collName, collAttrs);
}
} else if ("type".equals(n.getName())) {
types.add(n.getText().trim());
}
}
}
}
final ObjectMapper mapper = new ObjectMapper();
for (final Entry<String, Map<String, String>> e : collections.entrySet()) {
System.out.println(e.getKey() + ": " + mapper.writeValueAsString(e.getValue()));
}
for (final Entry<String, AtomicInteger> e : fields.entrySet()) {
System.out.println(e.getKey() + ": " + e.getValue().get());
}
System.out.println("TYPES: ");
for (final String s : types) {
System.out.println(s);
}
assertEquals(30000, count);
}
@Test
public void testParquet() throws Exception {
final String xml = IOUtils.toString(getClass().getResourceAsStream("record.xml"));
final SparkSession spark = SparkSession.builder().master("local[*]").getOrCreate();
final List<BaseRecordInfo> ls = new ArrayList<>();
for (int i = 0; i < 10; i++) {
ls.add(extractInfo(xml));
}
final JavaRDD<BaseRecordInfo> rdd = JavaSparkContext
.fromSparkContext(spark.sparkContext())
.parallelize(ls);
final Dataset<BaseRecordInfo> df = spark
.createDataset(rdd.rdd(), Encoders.bean(BaseRecordInfo.class));
df.printSchema();
df.show(false);
}
private BaseRecordInfo extractInfo(final String s) {
try {
final Document record = DocumentHelper.parseText(s);
final BaseRecordInfo info = new BaseRecordInfo();
final Set<String> paths = new LinkedHashSet<>();
final Set<String> types = new LinkedHashSet<>();
final List<BaseCollectionInfo> colls = new ArrayList<>();
for (final Object o : record.selectNodes("//*|//@*")) {
paths.add(((Node) o).getPath());
if (o instanceof Element) {
final Element n = (Element) o;
final String nodeName = n.getName();
if ("collection".equals(nodeName)) {
final String collName = n.getText().trim();
if (StringUtils.isNotBlank(collName)) {
final BaseCollectionInfo coll = new BaseCollectionInfo();
coll.setId(collName);
coll.setOpendoarId(n.valueOf("@opendoar_id").trim());
coll.setRorId(n.valueOf("@ror_id").trim());
colls.add(coll);
}
} else if ("type".equals(nodeName)) {
types.add("TYPE: " + n.getText().trim());
} else if ("typenorm".equals(nodeName)) {
types.add("TYPE_NORM: " + n.getText().trim());
}
}
}
info.setId(record.valueOf("//*[local-name() = 'header']/*[local-name() = 'identifier']").trim());
info.getTypes().addAll(types);
info.getPaths().addAll(paths);
info.setCollections(colls);
return info;
} catch (final DocumentException e) {
throw new RuntimeException(e);
}
}
}

32
dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/collection/plugin/base/BaseCollectorPluginTest.java Normal file
View File

@ -0,0 +1,32 @@
package eu.dnetlib.dhp.collection.plugin.base;
import static org.junit.jupiter.api.Assertions.assertFalse;
import static org.junit.jupiter.api.Assertions.assertTrue;
import java.util.Arrays;
import java.util.HashSet;
import java.util.Set;
import org.apache.commons.io.IOUtils;
import org.junit.jupiter.api.Test;
class BaseCollectorPluginTest {
@Test
void testFilterXml() throws Exception {
final String xml = IOUtils.toString(getClass().getResourceAsStream("record.xml"));
final Set<String> validIds = new HashSet<>(Arrays.asList("opendoar____::1234", "opendoar____::4567"));
final Set<String> validTypes = new HashSet<>(Arrays.asList("1", "121"));
final Set<String> validTypes2 = new HashSet<>(Arrays.asList("1", "11"));
assertTrue(BaseCollectorPlugin.filterXml(xml, validIds, validTypes));
assertTrue(BaseCollectorPlugin.filterXml(xml, validIds, new HashSet<>()));
assertFalse(BaseCollectorPlugin.filterXml(xml, new HashSet<>(), validTypes));
assertFalse(BaseCollectorPlugin.filterXml(xml, validIds, validTypes2));
}
}

49
dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/collection/plugin/base/BaseRecordInfo.java Normal file
View File

@ -0,0 +1,49 @@
package eu.dnetlib.dhp.collection.plugin.base;
import java.io.Serializable;
import java.util.ArrayList;
import java.util.List;
public class BaseRecordInfo implements Serializable {
private static final long serialVersionUID = -8848232018350074593L;
private String id;
private List<BaseCollectionInfo> collections = new ArrayList<>();
private List<String> paths = new ArrayList<>();
private List<String> types = new ArrayList<>();
public String getId() {
return this.id;
}
public void setId(final String id) {
this.id = id;
}
public List<String> getPaths() {
return this.paths;
}
public void setPaths(final List<String> paths) {
this.paths = paths;
}
public List<String> getTypes() {
return this.types;
}
public void setTypes(final List<String> types) {
this.types = types;
}
public List<BaseCollectionInfo> getCollections() {
return this.collections;
}
public void setCollections(final List<BaseCollectionInfo> collections) {
this.collections = collections;
}
}

94
dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/collection/plugin/base/BaseTransfomationTest.java Normal file
View File

@ -0,0 +1,94 @@
package eu.dnetlib.dhp.collection.plugin.base;
import static org.junit.jupiter.api.Assertions.assertThrows;
import java.io.IOException;
import org.apache.commons.io.IOUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.util.LongAccumulator;
import org.dom4j.io.SAXReader;
import org.junit.jupiter.api.BeforeEach;
import org.junit.jupiter.api.Test;
import org.junit.jupiter.api.extension.ExtendWith;
import org.mockito.junit.jupiter.MockitoExtension;
import eu.dnetlib.dhp.aggregation.AbstractVocabularyTest;
import eu.dnetlib.dhp.aggregation.common.AggregationCounter;
import eu.dnetlib.dhp.schema.mdstore.MetadataRecord;
import eu.dnetlib.dhp.schema.mdstore.Provenance;
import eu.dnetlib.dhp.transformation.xslt.XSLTTransformationFunction;
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpException;
// @Disabled
@ExtendWith(MockitoExtension.class)
public class BaseTransfomationTest extends AbstractVocabularyTest {
private SparkConf sparkConf;
@BeforeEach
public void setUp() throws IOException, ISLookUpException {
setUpVocabulary();
this.sparkConf = new SparkConf();
this.sparkConf.setMaster("local[*]");
this.sparkConf.set("spark.driver.host", "localhost");
this.sparkConf.set("spark.ui.enabled", "false");
}
@Test
void testBase2ODF() throws Exception {
final MetadataRecord mr = new MetadataRecord();
mr.setProvenance(new Provenance("DSID", "DSNAME", "PREFIX"));
mr.setBody(IOUtils.toString(getClass().getResourceAsStream("record.xml")));
final XSLTTransformationFunction tr = loadTransformationRule("xml/base2odf.transformationRule.xml");
final MetadataRecord result = tr.call(mr);
System.out.println(result.getBody());
}
@Test
void testBase2OAF() throws Exception {
final MetadataRecord mr = new MetadataRecord();
mr.setProvenance(new Provenance("DSID", "DSNAME", "PREFIX"));
mr.setBody(IOUtils.toString(getClass().getResourceAsStream("record.xml")));
final XSLTTransformationFunction tr = loadTransformationRule("xml/base2oaf.transformationRule.xml");
final MetadataRecord result = tr.call(mr);
System.out.println(result.getBody());
}
@Test
void testBase2ODF_wrong_date() throws Exception {
final MetadataRecord mr = new MetadataRecord();
mr.setProvenance(new Provenance("DSID", "DSNAME", "PREFIX"));
mr.setBody(IOUtils.toString(getClass().getResourceAsStream("record_wrong_1.xml")));
final XSLTTransformationFunction tr = loadTransformationRule("xml/base2oaf.transformationRule.xml");
assertThrows(NullPointerException.class, () -> {
final MetadataRecord result = tr.call(mr);
System.out.println(result.getBody());
});
}
private XSLTTransformationFunction loadTransformationRule(final String path) throws Exception {
final String xslt = new SAXReader()
.read(this.getClass().getResourceAsStream(path))
.selectSingleNode("//CODE/*")
.asXML();
final LongAccumulator la = new LongAccumulator();
return new XSLTTransformationFunction(new AggregationCounter(la, la, la), xslt, 0, this.vocabularies);
}
}

3
dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/collection/plugin/rest/RestIteratorTest.java
View File

@ -9,6 +9,7 @@ import org.junit.jupiter.api.Test;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import eu.dnetlib.dhp.common.collection.CollectorException;
import eu.dnetlib.dhp.common.collection.HttpClientParams;
/**
@ -37,7 +38,7 @@ public class RestIteratorTest {
@Disabled
@Test
public void test() {
public void test() throws CollectorException {
HttpClientParams clientParams = new HttpClientParams();

48
dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/collection/plugin/utils/JsonUtilsTest.java Normal file
View File

@ -0,0 +1,48 @@
package eu.dnetlib.dhp.collection.plugin.utils;
import static org.junit.jupiter.api.Assertions.assertEquals;
import org.junit.jupiter.api.Test;
class JsonUtilsTest {
static private String wrapped(String xml) {
return "<?xml version=\"1.0\" encoding=\"UTF-8\"?><recordWrap>" + xml + "</recordWrap>";
}
@Test
void keyStartWithDigit() {
assertEquals(
wrapped("<m_100><n_200v>null</n_200v></m_100>"),
JsonUtils.convertToXML("{\"100\" : {\"200v\" : null}}"));
}
@Test
void keyStartWithSpecialchars() {
assertEquals(
wrapped("<_parent><_nest1><_nest2>null</_nest2></_nest1></_parent>"),
JsonUtils.convertToXML("{\" parent\" : {\"-nest1\" : {\".nest2\" : null}}}"));
}
@Test
void encodeArray() {
assertEquals(
wrapped("<_parent.child>1</_parent.child><_parent.child>2</_parent.child>"),
JsonUtils.convertToXML("{\" parent.child\":[1, 2]}"));
}
@Test
void arrayOfObjects() {
assertEquals(
wrapped("<parent><id>1</id></parent><parent><id>2</id></parent>"),
JsonUtils.convertToXML("{\"parent\": [{\"id\": 1}, {\"id\": 2}]}"));
}
@Test
void removeControlCharacters() {
assertEquals(
wrapped("<m_100><n_200v>Test</n_200v></m_100>"),
JsonUtils.convertToXML("{\"100\" : {\"200v\" : \"\\u0000\\u000cTest\"}}"));
}
}

96499
dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/transformativeagreement/facts.json Normal file
View File

File diff suppressed because it is too large Load Diff

966
dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/collection/orcid/summary2.xml Normal file
View File

@ -0,0 +1,966 @@
<record:record path="/0000-0001-6816-8350" xmlns:internal="http://www.orcid.org/ns/internal" xmlns:education="http://www.orcid.org/ns/education" xmlns:distinction="http://www.orcid.org/ns/distinction" xmlns:deprecated="http://www.orcid.org/ns/deprecated" xmlns:other-name="http://www.orcid.org/ns/other-name" xmlns:membership="http://www.orcid.org/ns/membership" xmlns:error="http://www.orcid.org/ns/error" xmlns:common="http://www.orcid.org/ns/common" xmlns:record="http://www.orcid.org/ns/record" xmlns:personal-details="http://www.orcid.org/ns/personal-details" xmlns:keyword="http://www.orcid.org/ns/keyword" xmlns:email="http://www.orcid.org/ns/email" xmlns:external-identifier="http://www.orcid.org/ns/external-identifier" xmlns:funding="http://www.orcid.org/ns/funding" xmlns:preferences="http://www.orcid.org/ns/preferences" xmlns:address="http://www.orcid.org/ns/address" xmlns:invited-position="http://www.orcid.org/ns/invited-position" xmlns:work="http://www.orcid.org/ns/work" xmlns:history="http://www.orcid.org/ns/history" xmlns:employment="http://www.orcid.org/ns/employment" xmlns:qualification="http://www.orcid.org/ns/qualification" xmlns:service="http://www.orcid.org/ns/service" xmlns:person="http://www.orcid.org/ns/person" xmlns:activities="http://www.orcid.org/ns/activities" xmlns:researcher-url="http://www.orcid.org/ns/researcher-url" xmlns:peer-review="http://www.orcid.org/ns/peer-review" xmlns:bulk="http://www.orcid.org/ns/bulk" xmlns:research-resource="http://www.orcid.org/ns/research-resource">
<common:orcid-identifier>
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
<common:path>0000-0001-6816-8350</common:path>
<common:host>orcid.org</common:host>
</common:orcid-identifier>
<preferences:preferences>
<preferences:locale>en</preferences:locale>
</preferences:preferences>
<history:history>
<history:creation-method>Direct</history:creation-method>
<history:submission-date>2016-01-06T05:08:45.720Z</history:submission-date>
<common:last-modified-date>2024-01-02T20:07:05.186Z</common:last-modified-date>
<history:claimed>true</history:claimed>
<history:verified-email>true</history:verified-email>
<history:verified-primary-email>true</history:verified-primary-email>
</history:history>
<person:person path="/0000-0001-6816-8350/person">
<common:last-modified-date>2023-12-02T13:32:05.269Z</common:last-modified-date>
<other-name:other-names path="/0000-0001-6816-8350/other-names"/>
<researcher-url:researcher-urls path="/0000-0001-6816-8350/researcher-urls">
<common:last-modified-date>2016-02-09T09:18:18.417Z</common:last-modified-date>
<researcher-url:researcher-url put-code="633431" visibility="public" path="/0000-0001-6816-8350/researcher-urls/633431" display-index="0">
<common:created-date>2016-02-09T09:18:18.416Z</common:created-date>
<common:last-modified-date>2016-02-09T09:18:18.417Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
<common:path>0000-0001-6816-8350</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
</common:source>
<researcher-url:url-name>Dr Michael Muchiri</researcher-url:url-name>
<researcher-url:url>http://www.rmit.edu.au/contact/staff-contacts/academic-staff/m/muchiri-dr-michael</researcher-url:url>
</researcher-url:researcher-url>
</researcher-url:researcher-urls>
<email:emails path="/0000-0001-6816-8350/email"/>
<address:addresses path="/0000-0001-6816-8350/address">
<common:last-modified-date>2023-12-02T13:32:05.269Z</common:last-modified-date>
<address:address put-code="897528" visibility="public" path="/0000-0001-6816-8350/address/897528" display-index="2">
<common:created-date>2018-02-13T02:32:04.094Z</common:created-date>
<common:last-modified-date>2023-12-02T13:32:05.269Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
<common:path>0000-0001-6816-8350</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
</common:source>
<address:country>AU</address:country>
</address:address>
<address:address put-code="3191142" visibility="public" path="/0000-0001-6816-8350/address/3191142" display-index="1">
<common:created-date>2023-12-02T13:32:05.260Z</common:created-date>
<common:last-modified-date>2023-12-02T13:32:05.260Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
<common:path>0000-0001-6816-8350</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
</common:source>
<address:country>SA</address:country>
</address:address>
</address:addresses>
<keyword:keywords path="/0000-0001-6816-8350/keywords">
<common:last-modified-date>2023-12-02T13:31:16.269Z</common:last-modified-date>
<keyword:keyword put-code="368304" visibility="public" path="/0000-0001-6816-8350/keywords/368304" display-index="4">
<common:created-date>2016-02-09T09:16:44.001Z</common:created-date>
<common:last-modified-date>2023-12-02T13:31:16.269Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
<common:path>0000-0001-6816-8350</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
</common:source>
<keyword:content>Organizational Behavior</keyword:content>
</keyword:keyword>
<keyword:keyword put-code="368303" visibility="public" path="/0000-0001-6816-8350/keywords/368303" display-index="3">
<common:created-date>2016-02-09T09:16:27.374Z</common:created-date>
<common:last-modified-date>2023-12-02T13:31:16.269Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
<common:path>0000-0001-6816-8350</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
</common:source>
<keyword:content>Organizational Leadership</keyword:content>
</keyword:keyword>
<keyword:keyword put-code="368306" visibility="public" path="/0000-0001-6816-8350/keywords/368306" display-index="2">
<common:created-date>2016-02-09T09:17:08.998Z</common:created-date>
<common:last-modified-date>2023-12-02T13:31:16.269Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
<common:path>0000-0001-6816-8350</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
</common:source>
<keyword:content>Organizational performance</keyword:content>
</keyword:keyword>
<keyword:keyword put-code="3590814" visibility="public" path="/0000-0001-6816-8350/keywords/3590814" display-index="1">
<common:created-date>2023-12-02T13:31:16.259Z</common:created-date>
<common:last-modified-date>2023-12-02T13:31:16.259Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
<common:path>0000-0001-6816-8350</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
</common:source>
<keyword:content>Thriving at work</keyword:content>
</keyword:keyword>
</keyword:keywords>
<external-identifier:external-identifiers path="/0000-0001-6816-8350/external-identifiers">
<common:last-modified-date>2018-04-10T00:49:55.386Z</common:last-modified-date>
<external-identifier:external-identifier put-code="998076" visibility="public" path="/0000-0001-6816-8350/external-identifiers/998076" display-index="0">
<common:created-date>2018-04-10T00:49:55.385Z</common:created-date>
<common:last-modified-date>2018-04-10T00:49:55.386Z</common:last-modified-date>
<common:source>
<common:source-client-id>
<common:uri>https://orcid.org/client/0000-0003-1377-5676</common:uri>
<common:path>0000-0003-1377-5676</common:path>
<common:host>orcid.org</common:host>
</common:source-client-id>
<common:source-name>ResearcherID</common:source-name>
<common:assertion-origin-orcid>
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
<common:path>0000-0001-6816-8350</common:path>
<common:host>orcid.org</common:host>
</common:assertion-origin-orcid>
</common:source>
<common:external-id-type>ResearcherID</common:external-id-type>
<common:external-id-value>D-1929-2018</common:external-id-value>
<common:external-id-url>http://www.researcherid.com/rid/D-1929-2018</common:external-id-url>
<common:external-id-relationship>self</common:external-id-relationship>
</external-identifier:external-identifier>
</external-identifier:external-identifiers>
</person:person>
<activities:activities-summary path="/0000-0001-6816-8350/activities">
<common:last-modified-date>2023-12-02T13:28:26.051Z</common:last-modified-date>
<activities:distinctions path="/0000-0001-6816-8350/distinctions"/>
<activities:educations path="/0000-0001-6816-8350/educations">
<common:last-modified-date>2018-02-13T02:33:38.225Z</common:last-modified-date>
<activities:affiliation-group>
<common:last-modified-date>2016-02-09T06:55:21.838Z</common:last-modified-date>
<common:external-ids/>
<education:education-summary put-code="1549986" display-index="0" path="/0000-0001-6816-8350/education/1549986" visibility="public">
<common:created-date>2016-02-09T06:54:39.199Z</common:created-date>
<common:last-modified-date>2016-02-09T06:55:21.838Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
<common:path>0000-0001-6816-8350</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
</common:source>
<common:department-name>Management</common:department-name>
<common:role-title>PhD</common:role-title>
<common:start-date>
<common:year>2021</common:year>
</common:start-date>
<common:end-date>
<common:year>2022</common:year>
<common:month>02</common:month>
<common:day>12</common:day>
</common:end-date>
<common:start-date>
<common:year>2003</common:year>
<common:month>03</common:month>
</common:start-date>
<common:end-date>
<common:year>2007</common:year>
<common:month>03</common:month>
</common:end-date>
<common:organization>
<common:name>University of New England</common:name>
<common:address>
<common:city>Armidale</common:city>
<common:region>NSW</common:region>
<common:country>AU</common:country>
</common:address>
<common:disambiguated-organization>
<common:disambiguated-organization-identifier>1319</common:disambiguated-organization-identifier>
<common:disambiguation-source>RINGGOLD</common:disambiguation-source>
</common:disambiguated-organization>
</common:organization>
</education:education-summary>
</activities:affiliation-group>
<activities:affiliation-group>
<common:last-modified-date>2018-02-13T02:33:38.225Z</common:last-modified-date>
<common:external-ids/>
<education:education-summary put-code="1549990" display-index="0" path="/0000-0001-6816-8350/education/1549990" visibility="public">
<common:created-date>2016-02-09T06:57:04.181Z</common:created-date>
<common:last-modified-date>2018-02-13T02:33:38.225Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
<common:path>0000-0001-6816-8350</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
</common:source>
<common:department-name>Psychology</common:department-name>
<common:role-title>Master of Science (Industrial and Organizational) Psychology</common:role-title>
<common:start-date>
<common:year>1998</common:year>
<common:month>01</common:month>
</common:start-date>
<common:end-date>
<common:year>2000</common:year>
<common:month>01</common:month>
</common:end-date>
<common:organization>
<common:name>Universitas Gadjah Mada</common:name>
<common:address>
<common:city>Yogyakarta</common:city>
<common:region>Daerah Istimewa Yogyakart</common:region>
<common:country>ID</common:country>
</common:address>
<common:disambiguated-organization>
<common:disambiguated-organization-identifier>59166</common:disambiguated-organization-identifier>
<common:disambiguation-source>RINGGOLD</common:disambiguation-source>
</common:disambiguated-organization>
</common:organization>
</education:education-summary>
</activities:affiliation-group>
<activities:affiliation-group>
<common:last-modified-date>2018-02-13T02:33:35.821Z</common:last-modified-date>
<common:external-ids/>
<education:education-summary put-code="1549998" display-index="0" path="/0000-0001-6816-8350/education/1549998" visibility="public">
<common:created-date>2016-02-09T06:58:59.869Z</common:created-date>
<common:last-modified-date>2018-02-13T02:33:35.821Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
<common:path>0000-0001-6816-8350</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
</common:source>
<common:department-name>Education</common:department-name>
<common:role-title>Bachelor of Education (Honors)</common:role-title>
<common:start-date>
<common:year>1988</common:year>
<common:month>03</common:month>
</common:start-date>
<common:end-date>
<common:year>1991</common:year>
<common:month>03</common:month>
</common:end-date>
<common:organization>
<common:name>Kenyatta University</common:name>
<common:address>
<common:city>Nairobi</common:city>
<common:region>Nairobi</common:region>
<common:country>KE</common:country>
</common:address>
<common:disambiguated-organization>
<common:disambiguated-organization-identifier>107864</common:disambiguated-organization-identifier>
<common:disambiguation-source>RINGGOLD</common:disambiguation-source>
</common:disambiguated-organization>
</common:organization>
</education:education-summary>
</activities:affiliation-group>
</activities:educations>
<activities:employments path="/0000-0001-6816-8350/employments">
<common:last-modified-date>2023-12-02T13:28:26.051Z</common:last-modified-date>
<activities:affiliation-group>
<common:last-modified-date>2023-12-02T13:28:26.051Z</common:last-modified-date>
<common:external-ids/>
<employment:employment-summary put-code="21884863" display-index="1" path="/0000-0001-6816-8350/employment/21884863" visibility="public">
<common:created-date>2023-12-02T13:28:26.051Z</common:created-date>
<common:last-modified-date>2023-12-02T13:28:26.051Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
<common:path>0000-0001-6816-8350</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
</common:source>
<common:department-name>Management</common:department-name>
<common:role-title>Associate Professor in Management</common:role-title>
<common:start-date>
<common:year>2023</common:year>
<common:month>08</common:month>
<common:day>20</common:day>
</common:start-date>
<common:organization>
<common:name>Alfaisal University</common:name>
<common:address>
<common:city>Riyadh</common:city>
<common:country>SA</common:country>
</common:address>
<common:disambiguated-organization>
<common:disambiguated-organization-identifier>https://ror.org/00cdrtq48</common:disambiguated-organization-identifier>
<common:disambiguation-source>ROR</common:disambiguation-source>
</common:disambiguated-organization>
</common:organization>
<common:url>https://faculty.alfaisal.edu/user/mmuchiri</common:url>
</employment:employment-summary>
</activities:affiliation-group>
<activities:affiliation-group>
<common:last-modified-date>2016-02-09T07:00:06.052Z</common:last-modified-date>
<common:external-ids/>
<employment:employment-summary put-code="1550002" display-index="0" path="/0000-0001-6816-8350/employment/1550002" visibility="public">
<common:created-date>2016-02-09T07:00:06.052Z</common:created-date>
<common:last-modified-date>2016-02-09T07:00:06.052Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
<common:path>0000-0001-6816-8350</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
</common:source>
<common:department-name>Management</common:department-name>
<common:role-title>Senior Lecturer</common:role-title>
<common:start-date>
<common:year>2014</common:year>
<common:month>02</common:month>
</common:start-date>
<common:organization>
<common:name>RMIT University</common:name>
<common:address>
<common:city>Melbourne</common:city>
<common:region>VIC</common:region>
<common:country>AU</common:country>
</common:address>
<common:disambiguated-organization>
<common:disambiguated-organization-identifier>5376</common:disambiguated-organization-identifier>
<common:disambiguation-source>RINGGOLD</common:disambiguation-source>
</common:disambiguated-organization>
</common:organization>
</employment:employment-summary>
</activities:affiliation-group>
<activities:affiliation-group>
<common:last-modified-date>2016-02-09T07:01:08.398Z</common:last-modified-date>
<common:external-ids/>
<employment:employment-summary put-code="1550007" display-index="0" path="/0000-0001-6816-8350/employment/1550007" visibility="public">
<common:created-date>2016-02-09T07:01:08.398Z</common:created-date>
<common:last-modified-date>2016-02-09T07:01:08.398Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
<common:path>0000-0001-6816-8350</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
</common:source>
<common:department-name>Management</common:department-name>
<common:role-title>Senior Lecturer in Human Resource Management</common:role-title>
<common:start-date>
<common:year>2010</common:year>
<common:month>01</common:month>
</common:start-date>
<common:end-date>
<common:year>2014</common:year>
<common:month>02</common:month>
</common:end-date>
<common:organization>
<common:name>Central Queensland University</common:name>
<common:address>
<common:city>Rockhampton</common:city>
<common:region>QLD</common:region>
<common:country>AU</common:country>
</common:address>
<common:disambiguated-organization>
<common:disambiguated-organization-identifier>273488</common:disambiguated-organization-identifier>
<common:disambiguation-source>RINGGOLD</common:disambiguation-source>
</common:disambiguated-organization>
</common:organization>
</employment:employment-summary>
</activities:affiliation-group>
<activities:affiliation-group>
<common:last-modified-date>2016-02-09T07:01:47.814Z</common:last-modified-date>
<common:external-ids/>
<employment:employment-summary put-code="1550010" display-index="0" path="/0000-0001-6816-8350/employment/1550010" visibility="public">
<common:created-date>2016-02-09T07:01:47.814Z</common:created-date>
<common:last-modified-date>2016-02-09T07:01:47.814Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
<common:path>0000-0001-6816-8350</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
</common:source>
<common:department-name>Management</common:department-name>
<common:role-title>Lecturer in Management</common:role-title>
<common:start-date>
<common:year>2007</common:year>
<common:month>01</common:month>
</common:start-date>
<common:end-date>
<common:year>2010</common:year>
<common:month>01</common:month>
</common:end-date>
<common:organization>
<common:name>Central Queensland University</common:name>
<common:address>
<common:city>Rockhampton</common:city>
<common:region>QLD</common:region>
<common:country>AU</common:country>
</common:address>
<common:disambiguated-organization>
<common:disambiguated-organization-identifier>273488</common:disambiguated-organization-identifier>
<common:disambiguation-source>RINGGOLD</common:disambiguation-source>
</common:disambiguated-organization>
</common:organization>
</employment:employment-summary>
</activities:affiliation-group>
<activities:affiliation-group>
<common:last-modified-date>2018-02-13T02:33:13.213Z</common:last-modified-date>
<common:external-ids/>
<employment:employment-summary put-code="1550017" display-index="0" path="/0000-0001-6816-8350/employment/1550017" visibility="public">
<common:created-date>2016-02-09T07:03:42.180Z</common:created-date>
<common:last-modified-date>2018-02-13T02:33:13.213Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
<common:path>0000-0001-6816-8350</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
</common:source>
<common:department-name>Human Resource Development Division</common:department-name>
<common:role-title>Chief Human Resource Development Officer</common:role-title>
<common:start-date>
<common:year>2005</common:year>
<common:month>01</common:month>
</common:start-date>
<common:end-date>
<common:year>2007</common:year>
<common:month>01</common:month>
</common:end-date>
<common:organization>
<common:name>Government of Kenya Directorate of Personnel Management</common:name>
<common:address>
<common:city>Nairobi</common:city>
<common:region>Nairobi</common:region>
<common:country>KE</common:country>
</common:address>
<common:disambiguated-organization>
<common:disambiguated-organization-identifier>360256</common:disambiguated-organization-identifier>
<common:disambiguation-source>RINGGOLD</common:disambiguation-source>
</common:disambiguated-organization>
</common:organization>
</employment:employment-summary>
</activities:affiliation-group>
<activities:affiliation-group>
<common:last-modified-date>2016-02-09T07:05:02.300Z</common:last-modified-date>
<common:external-ids/>
<employment:employment-summary put-code="1550020" display-index="0" path="/0000-0001-6816-8350/employment/1550020" visibility="public">
<common:created-date>2016-02-09T07:05:02.300Z</common:created-date>
<common:last-modified-date>2016-02-09T07:05:02.300Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
<common:path>0000-0001-6816-8350</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
</common:source>
<common:department-name>Human Resource Development Division</common:department-name>
<common:role-title>Human Resource Development Officer</common:role-title>
<common:start-date>
<common:year>2001</common:year>
<common:month>01</common:month>
</common:start-date>
<common:end-date>
<common:year>2005</common:year>
<common:month>01</common:month>
</common:end-date>
<common:organization>
<common:name>Government of Kenya Directorate of Personnel Management</common:name>
<common:address>
<common:city>Nairobi</common:city>
<common:region>Nairobi</common:region>
<common:country>KE</common:country>
</common:address>
<common:disambiguated-organization>
<common:disambiguated-organization-identifier>360256</common:disambiguated-organization-identifier>
<common:disambiguation-source>RINGGOLD</common:disambiguation-source>
</common:disambiguated-organization>
</common:organization>
</employment:employment-summary>
</activities:affiliation-group>
<activities:affiliation-group>
<common:last-modified-date>2016-02-09T07:36:52.398Z</common:last-modified-date>
<common:external-ids/>
<employment:employment-summary put-code="1550050" display-index="0" path="/0000-0001-6816-8350/employment/1550050" visibility="public">
<common:created-date>2016-02-09T07:36:52.398Z</common:created-date>
<common:last-modified-date>2016-02-09T07:36:52.398Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
<common:path>0000-0001-6816-8350</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
</common:source>
<common:department-name>Public Sector Management Technical Assistance Project</common:department-name>
<common:role-title>Project Coordinator for Development Learning Centre</common:role-title>
<common:start-date>
<common:year>2002</common:year>
<common:month>08</common:month>
</common:start-date>
<common:end-date>
<common:year>2003</common:year>
<common:month>03</common:month>
</common:end-date>
<common:organization>
<common:name>Government of Kenya Directorate of Personnel Management</common:name>
<common:address>
<common:city>Nairobi</common:city>
<common:region>Nairobi</common:region>
<common:country>KE</common:country>
</common:address>
<common:disambiguated-organization>
<common:disambiguated-organization-identifier>360256</common:disambiguated-organization-identifier>
<common:disambiguation-source>RINGGOLD</common:disambiguation-source>
</common:disambiguated-organization>
</common:organization>
</employment:employment-summary>
</activities:affiliation-group>
</activities:employments>
<activities:fundings path="/0000-0001-6816-8350/fundings">
<common:last-modified-date>2016-02-09T09:05:27.100Z</common:last-modified-date>
<activities:group>
<common:last-modified-date>2016-02-09T09:05:27.100Z</common:last-modified-date>
<common:external-ids/>
<funding:funding-summary put-code="150520" path="/0000-0001-6816-8350/funding/150520" visibility="public" display-index="6">
<common:created-date>2016-02-09T09:05:27.100Z</common:created-date>
<common:last-modified-date>2016-02-09T09:05:27.100Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
<common:path>0000-0001-6816-8350</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
</common:source>
<funding:title>
<common:title>A cross-country examination of Employee Wellbeing, Leadership, High Performance Work Systems and Innovative Behaviours</common:title>
</funding:title>
<funding:type>grant</funding:type>
<common:start-date>
<common:year>2016</common:year>
<common:month>01</common:month>
</common:start-date>
<common:end-date>
<common:year>2016</common:year>
<common:month>12</common:month>
</common:end-date>
<common:organization>
<common:name>RMIT University</common:name>
<common:address>
<common:city>VIC</common:city>
<common:region>VIC</common:region>
<common:country>AU</common:country>
</common:address>
<common:disambiguated-organization>
<common:disambiguated-organization-identifier>http://dx.doi.org/10.13039/501100001780</common:disambiguated-organization-identifier>
<common:disambiguation-source>FUNDREF</common:disambiguation-source>
</common:disambiguated-organization>
</common:organization>
</funding:funding-summary>
</activities:group>
<activities:group>
<common:last-modified-date>2016-02-09T09:03:51.641Z</common:last-modified-date>
<common:external-ids/>
<funding:funding-summary put-code="150518" path="/0000-0001-6816-8350/funding/150518" visibility="public" display-index="5">
<common:created-date>2016-02-09T09:03:51.641Z</common:created-date>
<common:last-modified-date>2016-02-09T09:03:51.641Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
<common:path>0000-0001-6816-8350</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
</common:source>
<funding:title>
<common:title>Leading Safe and Thriving Organisations: An Investigation of the Relationships between Leadership, Thriving Behaviour, Authentic Followership and Safety Climate in an Australian Multinational Enterprise</common:title>
</funding:title>
<funding:type>grant</funding:type>
<common:start-date>
<common:year>2015</common:year>
<common:month>01</common:month>
</common:start-date>
<common:end-date>
<common:year>2015</common:year>
<common:month>12</common:month>
</common:end-date>
<common:organization>
<common:name>RMIT University</common:name>
<common:address>
<common:city>VIC</common:city>
<common:region>VIC</common:region>
<common:country>AU</common:country>
</common:address>
<common:disambiguated-organization>
<common:disambiguated-organization-identifier>http://dx.doi.org/10.13039/501100001780</common:disambiguated-organization-identifier>
<common:disambiguation-source>FUNDREF</common:disambiguation-source>
</common:disambiguated-organization>
</common:organization>
</funding:funding-summary>
</activities:group>
<activities:group>
<common:last-modified-date>2016-02-09T09:02:28.297Z</common:last-modified-date>
<common:external-ids/>
<funding:funding-summary put-code="150516" path="/0000-0001-6816-8350/funding/150516" visibility="public" display-index="4">
<common:created-date>2016-02-09T09:02:28.297Z</common:created-date>
<common:last-modified-date>2016-02-09T09:02:28.297Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
<common:path>0000-0001-6816-8350</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
</common:source>
<funding:title>
<common:title>A multilevel, cross-country examination of leadership, followership and innovative behaviours in Australia and Indonesia. </common:title>
</funding:title>
<funding:type>grant</funding:type>
<common:start-date>
<common:year>2015</common:year>
<common:month>01</common:month>
</common:start-date>
<common:end-date>
<common:year>2015</common:year>
<common:month>12</common:month>
</common:end-date>
<common:organization>
<common:name>RMIT University</common:name>
<common:address>
<common:city>VIC</common:city>
<common:region>VIC</common:region>
<common:country>AU</common:country>
</common:address>
<common:disambiguated-organization>
<common:disambiguated-organization-identifier>http://dx.doi.org/10.13039/501100001780</common:disambiguated-organization-identifier>
<common:disambiguation-source>FUNDREF</common:disambiguation-source>
</common:disambiguated-organization>
</common:organization>
</funding:funding-summary>
</activities:group>
<activities:group>
<common:last-modified-date>2016-02-09T09:00:51.749Z</common:last-modified-date>
<common:external-ids/>
<funding:funding-summary put-code="150514" path="/0000-0001-6816-8350/funding/150514" visibility="public" display-index="3">
<common:created-date>2016-02-09T09:00:51.749Z</common:created-date>
<common:last-modified-date>2016-02-09T09:00:51.749Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
<common:path>0000-0001-6816-8350</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
</common:source>
<funding:title>
<common:title>Workplace safety and positive leadership: Exploring relationships between leader behaviours, organisational climate, safety climate, safety citizenship behaviours and innovative behaviours within city councils in Victoria </common:title>
</funding:title>
<funding:type>grant</funding:type>
<common:start-date>
<common:year>2014</common:year>
<common:month>01</common:month>
</common:start-date>
<common:end-date>
<common:year>2014</common:year>
<common:month>12</common:month>
</common:end-date>
<common:organization>
<common:name>RMIT University</common:name>
<common:address>
<common:city>VIC</common:city>
<common:region>VIC</common:region>
<common:country>AU</common:country>
</common:address>
<common:disambiguated-organization>
<common:disambiguated-organization-identifier>http://dx.doi.org/10.13039/501100001780</common:disambiguated-organization-identifier>
<common:disambiguation-source>FUNDREF</common:disambiguation-source>
</common:disambiguated-organization>
</common:organization>
</funding:funding-summary>
</activities:group>
<activities:group>
<common:last-modified-date>2016-02-09T07:46:44.919Z</common:last-modified-date>
<common:external-ids/>
<funding:funding-summary put-code="150485" path="/0000-0001-6816-8350/funding/150485" visibility="public" display-index="0">
<common:created-date>2016-02-09T07:46:44.919Z</common:created-date>
<common:last-modified-date>2016-02-09T07:46:44.919Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
<common:path>0000-0001-6816-8350</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
</common:source>
<funding:title>
<common:title>Sustainable Business Model for Central Queensland Regional Information Systems.</common:title>
</funding:title>
<funding:type>grant</funding:type>
<common:start-date>
<common:year>2008</common:year>
<common:month>01</common:month>
</common:start-date>
<common:end-date>
<common:year>2008</common:year>
<common:month>12</common:month>
</common:end-date>
<common:organization>
<common:name>Department of Local Government, Planning, Sport and Recreation, Queensland, Australia </common:name>
<common:address>
<common:city>Rockhampton</common:city>
<common:region>Central Queensland</common:region>
<common:country>AU</common:country>
</common:address>
</common:organization>
</funding:funding-summary>
</activities:group>
</activities:fundings>
<activities:invited-positions path="/0000-0001-6816-8350/invited-positions"/>
<activities:memberships path="/0000-0001-6816-8350/memberships"/>
<activities:peer-reviews path="/0000-0001-6816-8350/peer-reviews">
<common:last-modified-date>2023-05-31T05:53:44.542Z</common:last-modified-date>
<activities:group>
<common:last-modified-date>2023-05-31T05:53:44.542Z</common:last-modified-date>
<common:external-ids>
<common:external-id>
<common:external-id-type>peer-review</common:external-id-type>
<common:external-id-value>issn:0167-4544</common:external-id-value>
</common:external-id>
</common:external-ids>
<activities:peer-review-group>
<common:last-modified-date>2023-02-28T06:51:52.426Z</common:last-modified-date>
<common:external-ids>
<common:external-id>
<common:external-id-type>source-work-id</common:external-id-type>
<common:external-id-value>c9bdf086-cfee-4cd9-bcfb-268cc5423248</common:external-id-value>
<common:external-id-normalized transient="true">c9bdf086-cfee-4cd9-bcfb-268cc5423248</common:external-id-normalized>
<common:external-id-url></common:external-id-url>
<common:external-id-relationship>self</common:external-id-relationship>
</common:external-id>
</common:external-ids>
<peer-review:peer-review-summary put-code="8741329" path="/0000-0001-6816-8350/peer-review/8741329" visibility="public" display-index="0">
<common:created-date>2023-02-28T06:51:52.426Z</common:created-date>
<common:last-modified-date>2023-02-28T06:51:52.426Z</common:last-modified-date>
<common:source>
<common:source-client-id>
<common:uri>https://orcid.org/client/APP-945VYTN20C7BZXYT</common:uri>
<common:path>APP-945VYTN20C7BZXYT</common:path>
<common:host>orcid.org</common:host>
</common:source-client-id>
<common:source-name>Springer Nature @ Editorial Manager</common:source-name>
</common:source>
<peer-review:reviewer-role>reviewer</peer-review:reviewer-role>
<common:external-ids>
<common:external-id>
<common:external-id-type>source-work-id</common:external-id-type>
<common:external-id-value>c9bdf086-cfee-4cd9-bcfb-268cc5423248</common:external-id-value>
<common:external-id-normalized transient="true">c9bdf086-cfee-4cd9-bcfb-268cc5423248</common:external-id-normalized>
<common:external-id-url></common:external-id-url>
<common:external-id-relationship>self</common:external-id-relationship>
</common:external-id>
</common:external-ids>
<peer-review:review-type>review</peer-review:review-type>
<peer-review:completion-date>
<common:year>2023</common:year>
</peer-review:completion-date>
<peer-review:review-group-id>issn:0167-4544</peer-review:review-group-id>
<peer-review:convening-organization>
<common:name>Springer Nature</common:name>
<common:address>
<common:city>New York</common:city>
<common:country>US</common:country>
</common:address>
<common:disambiguated-organization>
<common:disambiguated-organization-identifier>grid.467660.5</common:disambiguated-organization-identifier>
<common:disambiguation-source>GRID</common:disambiguation-source>
</common:disambiguated-organization>
</peer-review:convening-organization>
</peer-review:peer-review-summary>
</activities:peer-review-group>
<activities:peer-review-group>
<common:last-modified-date>2023-05-31T05:53:44.542Z</common:last-modified-date>
<common:external-ids>
<common:external-id>
<common:external-id-type>source-work-id</common:external-id-type>
<common:external-id-value>c442840b-5807-459d-802a-303d8ba4e25e</common:external-id-value>
<common:external-id-normalized transient="true">c442840b-5807-459d-802a-303d8ba4e25e</common:external-id-normalized>
<common:external-id-url></common:external-id-url>
<common:external-id-relationship>self</common:external-id-relationship>
</common:external-id>
</common:external-ids>
<peer-review:peer-review-summary put-code="9680570" path="/0000-0001-6816-8350/peer-review/9680570" visibility="public" display-index="0">
<common:created-date>2023-05-31T05:53:44.542Z</common:created-date>
<common:last-modified-date>2023-05-31T05:53:44.542Z</common:last-modified-date>
<common:source>
<common:source-client-id>
<common:uri>https://orcid.org/client/APP-945VYTN20C7BZXYT</common:uri>
<common:path>APP-945VYTN20C7BZXYT</common:path>
<common:host>orcid.org</common:host>
</common:source-client-id>
<common:source-name>Springer Nature @ Editorial Manager</common:source-name>
</common:source>
<peer-review:reviewer-role>reviewer</peer-review:reviewer-role>
<common:external-ids>
<common:external-id>
<common:external-id-type>source-work-id</common:external-id-type>
<common:external-id-value>c442840b-5807-459d-802a-303d8ba4e25e</common:external-id-value>
<common:external-id-normalized transient="true">c442840b-5807-459d-802a-303d8ba4e25e</common:external-id-normalized>
<common:external-id-url></common:external-id-url>
<common:external-id-relationship>self</common:external-id-relationship>
</common:external-id>
</common:external-ids>
<peer-review:review-type>review</peer-review:review-type>
<peer-review:completion-date>
<common:year>2023</common:year>
</peer-review:completion-date>
<peer-review:review-group-id>issn:0167-4544</peer-review:review-group-id>
<peer-review:convening-organization>
<common:name>Springer Nature</common:name>
<common:address>
<common:city>New York</common:city>
<common:country>US</common:country>
</common:address>
<common:disambiguated-organization>
<common:disambiguated-organization-identifier>grid.467660.5</common:disambiguated-organization-identifier>
<common:disambiguation-source>GRID</common:disambiguation-source>
</common:disambiguated-organization>
</peer-review:convening-organization>
</peer-review:peer-review-summary>
</activities:peer-review-group>
</activities:group>
</activities:peer-reviews>
<activities:qualifications path="/0000-0001-6816-8350/qualifications"/>
<activities:research-resources path="/0000-0001-6816-8350/research-resources"/>
<activities:services path="/0000-0001-6816-8350/services"/>
<activities:works path="/0000-0001-6816-8350/works">
<common:last-modified-date>2023-06-02T20:12:00.338Z</common:last-modified-date>
<activities:group>
<common:last-modified-date>2023-06-02T20:12:00.338Z</common:last-modified-date>
<common:external-ids>
<common:external-id>
<common:external-id-type>doi</common:external-id-type>
<common:external-id-value>10.4337/9781800881945.00020</common:external-id-value>
<common:external-id-normalized transient="true">10.4337/9781800881945.00020</common:external-id-normalized>
<common:external-id-url>https://doi.org/10.4337/9781800881945.00020</common:external-id-url>
<common:external-id-relationship>self</common:external-id-relationship>
</common:external-id>
</common:external-ids>
<work:work-summary put-code="134891279" path="/0000-0001-6816-8350/work/134891279" visibility="public" display-index="0">
<common:created-date>2023-05-11T21:05:54.188Z</common:created-date>
<common:last-modified-date>2023-06-02T20:12:00.338Z</common:last-modified-date>
<common:source>
<common:source-client-id>
<common:uri>https://orcid.org/client/0000-0001-9884-1913</common:uri>
<common:path>0000-0001-9884-1913</common:path>
<common:host>orcid.org</common:host>
</common:source-client-id>
<common:source-name>Crossref</common:source-name>
</common:source>
<work:title>
<common:title>Ethical leadership as workplace innovation and enabler for employee commitment and innovative work behaviours in Vietnam</common:title>
</work:title>
<common:external-ids>
<common:external-id>
<common:external-id-type>doi</common:external-id-type>
<common:external-id-value>10.4337/9781800881945.00020</common:external-id-value>
<common:external-id-normalized transient="true">10.4337/9781800881945.00020</common:external-id-normalized>
<common:external-id-url>https://doi.org/10.4337/9781800881945.00020</common:external-id-url>
<common:external-id-relationship>self</common:external-id-relationship>
</common:external-id>
</common:external-ids>
<common:url>https://doi.org/10.4337/9781800881945.00020</common:url>
<work:type>book-chapter</work:type>
<common:publication-date>
<common:year>2023</common:year>
<common:month>05</common:month>
<common:day>26</common:day>
</common:publication-date>
</work:work-summary>
</activities:group>
<activities:group>
<common:last-modified-date>2023-03-01T11:30:31.972Z</common:last-modified-date>
<common:external-ids>
<common:external-id>
<common:external-id-type>doi</common:external-id-type>
<common:external-id-value>10.1007/s10551-022-05081-6</common:external-id-value>
<common:external-id-normalized transient="true">10.1007/s10551-022-05081-6</common:external-id-normalized>
<common:external-id-url>https://doi.org/10.1007/s10551-022-05081-6</common:external-id-url>
<common:external-id-relationship>self</common:external-id-relationship>
</common:external-id>
</common:external-ids>
<work:work-summary put-code="110048777" path="/0000-0001-6816-8350/work/110048777" visibility="public" display-index="0">
<common:created-date>2022-03-18T03:36:55.927Z</common:created-date>
<common:last-modified-date>2023-03-01T11:30:31.972Z</common:last-modified-date>
<common:source>
<common:source-client-id>
<common:uri>https://orcid.org/client/0000-0001-9884-1913</common:uri>
<common:path>0000-0001-9884-1913</common:path>
<common:host>orcid.org</common:host>
</common:source-client-id>
<common:source-name>Crossref</common:source-name>
</common:source>
<work:title>
<common:title>Unethical Leadership: Review, Synthesis and Directions for Future Research</common:title>
</work:title>
<common:external-ids>
<common:external-id>
<common:external-id-type>doi</common:external-id-type>
<common:external-id-value>10.1007/s10551-022-05081-6</common:external-id-value>
<common:external-id-normalized transient="true">10.1007/s10551-022-05081-6</common:external-id-normalized>
<common:external-id-url>https://doi.org/10.1007/s10551-022-05081-6</common:external-id-url>
<common:external-id-relationship>self</common:external-id-relationship>
</common:external-id>
</common:external-ids>
<common:url>https://doi.org/10.1007/s10551-022-05081-6</common:url>
<work:type>journal-article</work:type>
<common:publication-date>
<common:year>2023</common:year>
<common:month>03</common:month>
</common:publication-date>
<work:journal-title>Journal of Business Ethics</work:journal-title>
</work:work-summary>
</activities:group>
<activities:group>
<common:last-modified-date>2022-05-28T18:16:16.575Z</common:last-modified-date>
<common:external-ids>
<common:external-id>
<common:external-id-type>doi</common:external-id-type>
<common:external-id-value>10.1017/jmo.2019.33</common:external-id-value>
<common:external-id-normalized transient="true">10.1017/jmo.2019.33</common:external-id-normalized>
<common:external-id-url>https://doi.org/10.1017/jmo.2019.33</common:external-id-url>
<common:external-id-relationship>self</common:external-id-relationship>
</common:external-id>
</common:external-ids>
<work:work-summary put-code="57272180" path="/0000-0001-6816-8350/work/57272180" visibility="public" display-index="0">
<common:created-date>2019-05-10T07:23:14.608Z</common:created-date>
<common:last-modified-date>2022-05-28T18:16:16.575Z</common:last-modified-date>
<common:source>
<common:source-client-id>
<common:uri>https://orcid.org/client/0000-0001-9884-1913</common:uri>
<common:path>0000-0001-9884-1913</common:path>
<common:host>orcid.org</common:host>
</common:source-client-id>
<common:source-name>Crossref</common:source-name>
</common:source>
<work:title>
<common:title>And now for something completely different: Reframing social processes of leadership theory using positive organisational behaviour</common:title>
</work:title>
<common:external-ids>
<common:external-id>
<common:external-id-type>doi</common:external-id-type>
<common:external-id-value>10.1017/jmo.2019.33</common:external-id-value>
<common:external-id-normalized transient="true">10.1017/jmo.2019.33</common:external-id-normalized>
<common:external-id-url>https://doi.org/10.1017/jmo.2019.33</common:external-id-url>
<common:external-id-relationship>self</common:external-id-relationship>
</common:external-id>
</common:external-ids>
<common:url>https://doi.org/10.1017/jmo.2019.33</common:url>
<work:type>journal-article</work:type>
<common:publication-date>
<common:year>2019</common:year>
<common:month>05</common:month>
<common:day>09</common:day>
</common:publication-date>
<work:journal-title>Journal of Management &amp; Organization</work:journal-title>
</work:work-summary>
</activities:group>
</activities:works>
</activities:activities-summary>
</record:record>

60
dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/collection/orcid/update_employments.xml Normal file
View File

@ -0,0 +1,60 @@
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<activities:employments path="/0000-0002-0456-1185/employments" xmlns:internal="http://www.orcid.org/ns/internal" xmlns:education="http://www.orcid.org/ns/education" xmlns:distinction="http://www.orcid.org/ns/distinction" xmlns:deprecated="http://www.orcid.org/ns/deprecated" xmlns:other-name="http://www.orcid.org/ns/other-name" xmlns:membership="http://www.orcid.org/ns/membership" xmlns:error="http://www.orcid.org/ns/error" xmlns:common="http://www.orcid.org/ns/common" xmlns:record="http://www.orcid.org/ns/record" xmlns:personal-details="http://www.orcid.org/ns/personal-details" xmlns:keyword="http://www.orcid.org/ns/keyword" xmlns:email="http://www.orcid.org/ns/email" xmlns:external-identifier="http://www.orcid.org/ns/external-identifier" xmlns:funding="http://www.orcid.org/ns/funding" xmlns:preferences="http://www.orcid.org/ns/preferences" xmlns:address="http://www.orcid.org/ns/address" xmlns:invited-position="http://www.orcid.org/ns/invited-position" xmlns:work="http://www.orcid.org/ns/work" xmlns:history="http://www.orcid.org/ns/history" xmlns:employment="http://www.orcid.org/ns/employment" xmlns:qualification="http://www.orcid.org/ns/qualification" xmlns:service="http://www.orcid.org/ns/service" xmlns:person="http://www.orcid.org/ns/person" xmlns:activities="http://www.orcid.org/ns/activities" xmlns:researcher-url="http://www.orcid.org/ns/researcher-url" xmlns:peer-review="http://www.orcid.org/ns/peer-review" xmlns:bulk="http://www.orcid.org/ns/bulk" xmlns:research-resource="http://www.orcid.org/ns/research-resource">
<common:last-modified-date>2024-01-07T23:59:38.869Z</common:last-modified-date>
<activities:affiliation-group>
<common:last-modified-date>2024-01-07T23:59:38.869Z</common:last-modified-date>
<common:external-ids/>
<employment:employment-summary put-code="22127142" display-index="0" path="/0000-0002-0456-1185/employment/22127142" visibility="public">
<common:created-date>2024-01-07T23:59:38.869Z</common:created-date>
<common:last-modified-date>2024-01-07T23:59:38.869Z</common:last-modified-date>
<common:source>
<common:source-client-id>
<common:uri>https://orcid.org/client/APP-N0TAO4G9BBK9PWHT</common:uri>
<common:path>APP-N0TAO4G9BBK9PWHT</common:path>
<common:host>orcid.org</common:host>
</common:source-client-id>
<common:source-name>Tampere University</common:source-name>
</common:source>
<common:organization>
<common:name>Tampere University</common:name>
<common:address>
<common:city>Tampere</common:city>
<common:country>FI</common:country>
</common:address>
<common:disambiguated-organization>
<common:disambiguated-organization-identifier>https://ror.org/033003e23</common:disambiguated-organization-identifier>
<common:disambiguation-source>ROR</common:disambiguation-source>
</common:disambiguated-organization>
</common:organization>
</employment:employment-summary>
</activities:affiliation-group>
<activities:affiliation-group>
<common:last-modified-date>2019-01-03T17:00:05.658Z</common:last-modified-date>
<common:external-ids/>
<employment:employment-summary put-code="3291239" display-index="1" path="/0000-0002-0456-1185/employment/3291239" visibility="public">
<common:created-date>2017-02-26T04:46:20.917Z</common:created-date>
<common:last-modified-date>2019-01-03T17:00:05.658Z</common:last-modified-date>
<common:source>
<common:source-orcid>
<common:uri>https://orcid.org/0000-0002-0456-1185</common:uri>
<common:path>0000-0002-0456-1185</common:path>
<common:host>orcid.org</common:host>
</common:source-orcid>
<common:source-name>Tiina Manninen</common:source-name>
</common:source>
<common:department-name> Faculty of Medicine and Health Technology</common:department-name>
<common:role-title>Academy Research Fellow</common:role-title>
<common:organization>
<common:name>Tampere University</common:name>
<common:address>
<common:city>Tampere</common:city>
<common:country>FI</common:country>
</common:address>
<common:disambiguated-organization>
<common:disambiguated-organization-identifier>7839</common:disambiguated-organization-identifier>
<common:disambiguation-source>RINGGOLD</common:disambiguation-source>
</common:disambiguated-organization>
</common:organization>
</employment:employment-summary>
</activities:affiliation-group>
</activities:employments>

6234
dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/collection/orcid/update_work.xml Normal file
View File

File diff suppressed because it is too large Load Diff

BIN
dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/collection/plugin/base/base-sample.tar Normal file
View File

Binary file not shown.

58
dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/collection/plugin/base/record.xml Normal file
View File

@ -0,0 +1,58 @@
<record>
<header xmlns="http://www.openarchives.org/OAI/2.0/">
<identifier>ftdoajarticles:oai:doaj.org/article:e2d5b5126b2d4e479933cc7f9a9ae0c1</identifier>
<datestamp>2022-12-31T11:48:55Z</datestamp>
</header>
<metadata xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:base_dc="http://oai.base-search.net/base_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:dc="http://purl.org/dc/elements/1.1/">
<base_dc:dc xsi:schemaLocation="http://oai.base-search.net/base_dc/ http://oai.base-search.net/base_dc/base_dc.xsd">
<base_dc:global_id>ftdoajarticles:oai:doaj.org/article:e2d5b5126b2d4e479933cc7f9a9ae0c1</base_dc:global_id>
<base_dc:continent>cww</base_dc:continent>
<base_dc:country>org</base_dc:country>
<base_dc:collection opendoar_id="1234" ror_id="ror1234">ftdoajarticles</base_dc:collection>
<base_dc:collname>TEST REPO</base_dc:collname>
<dc:title>Assessment of cultural heritage: the legislative and methodological framework of Russian Federation</dc:title>
<dc:creator>ALBU, Svetlana</dc:creator>
<dc:creator>LEȘAN, Anna</dc:creator>
<dc:subject>architectural heritage</dc:subject>
<dc:subject>evaluation of architectural heritage</dc:subject>
<dc:subject>types of values</dc:subject>
<dc:subject>experience of russian federation</dc:subject>
<dc:subject>Social Sciences</dc:subject>
<dc:subject>H</dc:subject>
<dc:description>Architectural heritage is the real estate inheritance by population of a country becoming an extremely valuable and specific category, preserving and capitalizing on those assets requires considerable effort. The state does not have sufficient means to maintain and preserve cultural heritage, as a result it is included in the civil circuit. The transfer of property right or of some partial rights over the architectural patrimony is accompanied by the necessity to estimate the value of goods. In this article, the authors examine the experience of Russian Federation (one of the largest countries with a huge architectural heritage) on the legislative framework of architectural and methodological heritage of architectural heritage assessment. The particularities of cultural assets valuation compared to other categories of real estate are examined, as well as the methodological aspects (types of values, methods applied in valuation, approaches according to the purpose of valuation) regarding the valuation of real estate with architectural value in Russian Federation.</dc:description>
<dc:publisher>Technical University of Moldova</dc:publisher>
<dc:date>2020-09-01T00:00:00Z</dc:date>
<base_dc:year>2020</base_dc:year>
<dc:type>article</dc:type>
<base_dc:typenorm>121</base_dc:typenorm>
<dc:identifier>https://doi.org/10.5281/zenodo.3971988</dc:identifier>
<dc:identifier>https://doaj.org/article/e2d5b5126b2d4e479933cc7f9a9ae0c1</dc:identifier>
<base_dc:link>https://doi.org/10.5281/zenodo.3971988</base_dc:link>
<dc:source>Journal of Social Sciences, Vol 3, Iss 3, Pp 134-143 (2020)</dc:source>
<dc:language>EN</dc:language>
<dc:language>FR</dc:language>
<dc:language>RO</dc:language>
<dc:relation>http://ibn.idsi.md/sites/default/files/imag_file/JSS-3-2020_134-143.pdf</dc:relation>
<dc:relation>https://doaj.org/toc/2587-3490</dc:relation>
<dc:relation>https://doaj.org/toc/2587-3504</dc:relation>
<dc:relation>doi:10.5281/zenodo.3971988</dc:relation>
<dc:relation>2587-3490</dc:relation>
<dc:relation>2587-3504</dc:relation>
<dc:relation>https://doaj.org/article/e2d5b5126b2d4e479933cc7f9a9ae0c1</dc:relation>
<base_dc:autoclasscode type="ddc">720</base_dc:autoclasscode>
<base_dc:authod_id>
<base_dc:creator_name>ALBU, Svetlana</base_dc:creator_name>
<base_dc:creator_id>https://orcid.org/0000-0002-8648-950X</base_dc:creator_id>
</base_dc:authod_id>
<base_dc:authod_id>
<base_dc:creator_name>LEȘAN, Anna</base_dc:creator_name>
<base_dc:creator_id>https://orcid.org/0000-0003-3284-0525</base_dc:creator_id>
</base_dc:authod_id>
<base_dc:doi>https://doi.org/10.5281/zenodo.3971988</base_dc:doi>
<base_dc:oa>1</base_dc:oa>
<base_dc:lang>eng</base_dc:lang>
<base_dc:lang>fre</base_dc:lang>
<base_dc:lang>rum</base_dc:lang>
</base_dc:dc>
</metadata>
</record>

36
dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/collection/plugin/base/record_wrong_1.xml Normal file
View File

@ -0,0 +1,36 @@
<?xml version="1.0" encoding="UTF-8"?>
<record>
<header xmlns="http://www.openarchives.org/OAI/2.0/">
<identifier>ftunivminnesdc:oai:conservancy.umn.edu:11299/109914</identifier>
<datestamp>2023-07-18T20:05:40Z</datestamp>
</header>
<metadata xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:base_dc="http://oai.base-search.net/base_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:dc="http://purl.org/dc/elements/1.1/">
<base_dc:dc xsi:schemaLocation="http://oai.base-search.net/base_dc/ http://oai.base-search.net/base_dc/base_dc.xsd">
<base_dc:global_id>ftunivminnesdc:oai:conservancy.umn.edu:11299/109914</base_dc:global_id>
<base_dc:continent>cna</base_dc:continent>
<base_dc:country>us</base_dc:country>
<base_dc:collection opendoar_id="1008">ftunivminnesdc</base_dc:collection>
<base_dc:collname>University of Minnesota Digital Conservancy</base_dc:collname>
<dc:title>An Experimental Investigation of the influence of an air bubble layer on radiated noise and surface pressure fluctuations in a turbulent boundary layer</dc:title>
<dc:creator>Killen, John M.</dc:creator>
<dc:subject>Boundary layer noise</dc:subject>
<dc:subject>Kinetic energy dissipation</dc:subject>
<dc:subject>Air bubble layer</dc:subject>
<dc:subject>Maximum stable bubble size</dc:subject>
<dc:subject>bubble noise spectra</dc:subject>
<dc:description>between the noise spectra of a layer of air bubbles in a turbulent flow and' a maximum stable bubble size which can exist in the same flow. An air bubbie layer with individual bubble sizes greater than a maximum stable size was introduced into the boundary layer of water flowing along a smooth flat plate. It was found that the maximum stable bubble size was related to the turbulent kinetic energy dissipation as had been previously shown by other investigators ; Office of Naval Research Arlington, Virginia 22217</dc:description>
<dc:date>1981-09-31T21:42:52Z</dc:date>
<base_dc:year>1981</base_dc:year>
<dc:type>Report</dc:type>
<base_dc:typenorm>14</base_dc:typenorm>
<dc:identifier>http://purl.umn.edu/109914</dc:identifier>
<base_dc:link>http://purl.umn.edu/109914</base_dc:link>
<dc:language>en_US</dc:language>
<dc:relation>Project Reports</dc:relation>
<dc:relation>202</dc:relation>
<dc:relation>http://purl.umn.edu/109914</dc:relation>
<base_dc:oa>2</base_dc:oa>
<base_dc:lang>eng</base_dc:lang>
</base_dc:dc>
</metadata>
</record>

26
dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/synonyms.txt
View File

@ -1497,3 +1497,29 @@ cnr:institutes @=@ https://ror.org/0263zy895 @=@ CDS132
cnr:institutes @=@ https://ror.org/0263zy895 @=@ SCITEC - Istituto di Scienze e Tecnologie Chimiche \"Giulio Natta\"
cnr:institutes @=@ __CDS133__ @=@ CDS133
cnr:institutes @=@ __CDS133__ @=@ STEMS - Istituto di Scienze e Tecnologie per l'Energia e la Mobilità Sostenibili
base:normalized_types @=@ Text @=@ 1
base:normalized_types @=@ Book @=@ 11
base:normalized_types @=@ Book part @=@ 111
base:normalized_types @=@ Journal/Newspaper @=@ 12
base:normalized_types @=@ Article contribution @=@ 121
base:normalized_types @=@ Other non-article @=@ 122
base:normalized_types @=@ Conference object @=@ 13
base:normalized_types @=@ Report @=@ 14
base:normalized_types @=@ Review @=@ 15
base:normalized_types @=@ Course material @=@ 16
base:normalized_types @=@ Lecture @=@ 17
base:normalized_types @=@ Thesis @=@ 18
base:normalized_types @=@ Bachelor's thesis @=@ 181
base:normalized_types @=@ Master's thesis @=@ 182
base:normalized_types @=@ Doctoral and postdoctoral thesis @=@ 183
base:normalized_types @=@ Manuscript @=@ 19
base:normalized_types @=@ Patent @=@ 1A
base:normalized_types @=@ Musical notation @=@ 2
base:normalized_types @=@ Map @=@ 3
base:normalized_types @=@ Audio @=@ 4
base:normalized_types @=@ Image/Video @=@ 5
base:normalized_types @=@ Still image @=@ 51
base:normalized_types @=@ Moving image/Video @=@ 52
base:normalized_types @=@ Software @=@ 6
base:normalized_types @=@ Dataset @=@ 7
base:normalized_types @=@ Unknown @=@ F

27
dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/transform/terms.txt
View File

@ -1210,4 +1210,29 @@ cnr:institutes @=@ cnr:institutes @=@ __CDS130__ @=@ __CDS130__
cnr:institutes @=@ cnr:institutes @=@ __CDS131__ @=@ __CDS131__
cnr:institutes @=@ cnr:institutes @=@ https://ror.org/0263zy895 @=@ https://ror.org/0263zy895
cnr:institutes @=@ cnr:institutes @=@ __CDS133__ @=@ __CDS133__
base:normalized_types @=@ base:normalized_types @=@ Text @=@ Text
base:normalized_types @=@ base:normalized_types @=@ Book @=@ Book
base:normalized_types @=@ base:normalized_types @=@ Book part @=@ Book part
base:normalized_types @=@ base:normalized_types @=@ Journal/Newspaper @=@ Journal/Newspaper
base:normalized_types @=@ base:normalized_types @=@ Article contribution @=@ Article contribution
base:normalized_types @=@ base:normalized_types @=@ Other non-article @=@ Other non-article
base:normalized_types @=@ base:normalized_types @=@ Conference object @=@ Conference object
base:normalized_types @=@ base:normalized_types @=@ Report @=@ Report
base:normalized_types @=@ base:normalized_types @=@ Review @=@ Review
base:normalized_types @=@ base:normalized_types @=@ Course material @=@ Course material
base:normalized_types @=@ base:normalized_types @=@ Lecture @=@ Lecture
base:normalized_types @=@ base:normalized_types @=@ Thesis @=@ Thesis
base:normalized_types @=@ base:normalized_types @=@ Bachelor's thesis @=@ Bachelor's thesis
base:normalized_types @=@ base:normalized_types @=@ Master's thesis @=@ Master's thesis
base:normalized_types @=@ base:normalized_types @=@ Doctoral and postdoctoral thesis @=@ Doctoral and postdoctoral thesis
base:normalized_types @=@ base:normalized_types @=@ Manuscript @=@ Manuscript
base:normalized_types @=@ base:normalized_types @=@ Patent @=@ Patent
base:normalized_types @=@ base:normalized_types @=@ Musical notation @=@ Musical notation
base:normalized_types @=@ base:normalized_types @=@ Map @=@ Map
base:normalized_types @=@ base:normalized_types @=@ Audio @=@ Audio
base:normalized_types @=@ base:normalized_types @=@ Image/Video @=@ Image/Video
base:normalized_types @=@ base:normalized_types @=@ Still image @=@ Still image
base:normalized_types @=@ base:normalized_types @=@ Moving image/Video @=@ Moving image/Video
base:normalized_types @=@ base:normalized_types @=@ Software @=@ Software
base:normalized_types @=@ base:normalized_types @=@ Dataset @=@ Dataset
base:normalized_types @=@ base:normalized_types @=@ Unknown @=@ Unknown

35
dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/DedupRecordFactory.java
View File

@ -4,6 +4,7 @@ package eu.dnetlib.dhp.oa.dedup;
import java.util.*;
import java.util.stream.Stream;
import eu.dnetlib.dhp.schema.oaf.utils.MergeUtils;
import org.apache.commons.beanutils.BeanUtils;
import org.apache.commons.lang3.StringUtils;
import org.apache.spark.api.java.function.FlatMapFunction;
@ -14,6 +15,7 @@ import org.apache.spark.sql.*;
import eu.dnetlib.dhp.oa.dedup.model.Identifier;
import eu.dnetlib.dhp.oa.merge.AuthorMerger;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.utils.MergeUtils;
import eu.dnetlib.dhp.schema.oaf.Author;
import eu.dnetlib.dhp.schema.oaf.DataInfo;
import eu.dnetlib.dhp.schema.oaf.OafEntity;
@ -122,10 +124,20 @@ public class DedupRecordFactory {
}
return Stream
.concat(Stream.of(agg.getDedupId()), agg.aliases.stream())
.map(id -> {
.concat(
Stream
.of(agg.getDedupId())
.map(id -> createDedupOafEntity(id, agg.entity, dataInfo, ts)),
agg.aliases
.stream()
.map(id -> createMergedDedupAliasOafEntity(id, agg.entity, dataInfo, ts)))
.iterator();
}, beanEncoder);
}
private static OafEntity createDedupOafEntity(String id, OafEntity base, DataInfo dataInfo, long ts) {
try {
OafEntity res = (OafEntity) BeanUtils.cloneBean(agg.entity);
OafEntity res = (OafEntity) BeanUtils.cloneBean(base);
res.setId(id);
res.setDataInfo(dataInfo);
res.setLastupdatetimestamp(ts);
@ -133,9 +145,18 @@ public class DedupRecordFactory {
} catch (Exception e) {
throw new RuntimeException(e);
}
})
.iterator();
}, beanEncoder);
}
private static OafEntity createMergedDedupAliasOafEntity(String id, OafEntity base, DataInfo dataInfo, long ts) {
try {
OafEntity res = createDedupOafEntity(id, base, dataInfo, ts);
DataInfo ds = (DataInfo) BeanUtils.cloneBean(dataInfo);
ds.setDeletedbyinference(true);
res.setDataInfo(ds);
return res;
} catch (Exception e) {
throw new RuntimeException(e);
}
}
private static OafEntity reduceEntity(OafEntity entity, OafEntity duplicate) {
@ -153,7 +174,7 @@ public class DedupRecordFactory {
entity = swap;
}
entity.mergeFrom(duplicate);
entity = MergeUtils.checkedMerge(entity, duplicate);
if (ModelSupport.isSubClass(duplicate, Result.class)) {
Result re = (Result) entity;

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

@ -3,6 +3,7 @@ package eu.dnetlib.dhp.oa.dedup;
import static org.apache.spark.sql.functions.col;
import eu.dnetlib.dhp.schema.oaf.utils.MergeUtils;
import org.apache.commons.io.IOUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.MapFunction;
@ -127,10 +128,8 @@ public class SparkPropagateRelation extends AbstractSparkAction {
(MapFunction<Relation, String>) r -> String
.join(" ", r.getSource(), r.getTarget(), r.getRelType(), r.getSubRelType(), r.getRelClass()),
Encoders.STRING())
.reduceGroups((ReduceFunction<Relation>) (b, a) -> {
b.mergeFrom(a);
return b;
})
.reduceGroups((ReduceFunction<Relation>) MergeUtils::mergeRelation
)
.map((MapFunction<Tuple2<String, Relation>, Relation>) Tuple2::_2, REL_BEAN_ENC);
final String outputRelationPath = graphOutputPath + "/relation";

18
dhp-workflows/dhp-doiboost/src/main/scala/eu/dnetlib/doiboost/SparkGenerateDoiBoost.scala
View File

@ -3,17 +3,18 @@ package eu.dnetlib.doiboost
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.oa.merge.AuthorMerger
import eu.dnetlib.dhp.schema.common.ModelConstants
import eu.dnetlib.dhp.schema.oaf.utils.MergeUtils
import eu.dnetlib.dhp.schema.oaf.{Organization, Publication, Relation, Dataset => OafDataset}
import eu.dnetlib.doiboost.mag.ConversionUtil
import org.apache.commons.io.IOUtils
import org.apache.spark.SparkConf
import org.apache.spark.sql.expressions.Aggregator
import org.apache.spark.sql.functions.col
import org.apache.spark.sql._
import org.json4s.DefaultFormats
import org.json4s.JsonAST.{JField, JObject, JString}
import org.json4s.jackson.JsonMethods.parse
import org.slf4j.{Logger, LoggerFactory}
import scala.collection.JavaConverters._
object SparkGenerateDoiBoost {
@ -78,8 +79,10 @@ object SparkGenerateDoiBoost {
if (item._2 != null) {
val otherPub = item._2._2
if (otherPub != null) {
crossrefPub.mergeFrom(otherPub)
crossrefPub.setAuthor(AuthorMerger.mergeAuthor(crossrefPub.getAuthor, otherPub.getAuthor))
val mergedAuthor = AuthorMerger.mergeAuthor(crossrefPub.getAuthor, otherPub.getAuthor)
val res = MergeUtils.mergePublication(crossrefPub, otherPub)
res.setAuthor(mergedAuthor);
return res
}
}
crossrefPub
@ -130,14 +133,13 @@ object SparkGenerateDoiBoost {
// So we have to merge
val b1 = left._2
val b2 = right._2
b1.mergeFrom(b2)
b1.mergeOAFDataInfo(b2)
val authors = AuthorMerger.mergeAuthor(b1.getAuthor, b2.getAuthor)
b1.setAuthor(authors)
val merged = MergeUtils.mergePublication(b1, b2);
merged.setAuthor(authors)
if (b2.getId != null && b2.getId.nonEmpty)
b1.setId(b2.getId)
merged.setId(b2.getId)
//Return publication Merged
(b1.getId, b1)
(merged.getId, merged)
}
} else {
// Left is Null so we return right

7
dhp-workflows/dhp-doiboost/src/main/scala/eu/dnetlib/doiboost/mag/MagDataModel.scala
View File

@ -1,8 +1,8 @@
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, Subject}
import eu.dnetlib.dhp.schema.oaf.utils.{IdentifierFactory, MergeUtils}
import eu.dnetlib.dhp.schema.oaf.{Instance, Journal, Publication, Subject}
import eu.dnetlib.doiboost.DoiBoostMappingUtil
import eu.dnetlib.doiboost.DoiBoostMappingUtil._
import org.json4s
@ -142,8 +142,7 @@ case object ConversionUtil {
def mergePublication(a: Publication, b: Publication): Publication = {
if ((a != null) && (b != null)) {
a.mergeFrom(b)
a
MergeUtils.mergePublication(a, b)
} else {
if (a == null) b else a
}

11
dhp-workflows/dhp-doiboost/src/test/scala/eu/dnetlib/dhp/doiboost/crossref/CrossrefMappingTest.scala
View File

@ -23,10 +23,15 @@ class CrossrefMappingTest {
val mapper = new ObjectMapper()
@Test
def testMissingAuthorParser():Unit = {
val json: String = Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/crossref/s41567-022-01757-y.json")).mkString
def testMissingAuthorParser(): Unit = {
val json: String = Source
.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/crossref/s41567-022-01757-y.json"))
.mkString
val result = Crossref2Oaf.convert(json)
result.filter(o => o.isInstanceOf[Publication]).map(p=> p.asInstanceOf[Publication]).foreach(p =>assertTrue(p.getAuthor.size()>0))
result
.filter(o => o.isInstanceOf[Publication])
.map(p => p.asInstanceOf[Publication])
.foreach(p => assertTrue(p.getAuthor.size() > 0))
}
@Test

2
dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromorganization/SparkResultToCommunityFromOrganizationJob.java
View File

@ -149,7 +149,7 @@ public class SparkResultToCommunityFromOrganizationJob {
}
}
// res.setContext(propagatedContexts);
// ret.mergeFrom(res);
// return MergeUtils.mergeResult(ret, res);
}
return ret;
};

5
dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/SparkResultToCommunityFromProject.java
View File

@ -13,6 +13,7 @@ import java.util.List;
import java.util.Optional;
import java.util.stream.Collectors;
import eu.dnetlib.dhp.schema.oaf.utils.MergeUtils;
import org.apache.commons.io.IOUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.MapFunction;
@ -24,8 +25,6 @@ import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.resulttocommunityfromorganization.ResultCommunityList;
import eu.dnetlib.dhp.resulttocommunityfromorganization.SparkResultToCommunityFromOrganizationJob;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.Context;
@ -162,7 +161,7 @@ public class SparkResultToCommunityFromProject implements Serializable {
}
}
res.setContext(propagatedContexts);
ret.mergeFrom(res);
return MergeUtils.checkedMerge(ret, res);
}
return ret;
};

6
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/merge/MergeGraphTableSparkJob.java
View File

@ -7,6 +7,7 @@ import java.util.*;
import java.util.stream.Collectors;
import java.util.stream.Stream;
import eu.dnetlib.dhp.schema.oaf.utils.MergeUtils;
import org.apache.commons.io.IOUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.FilterFunction;
@ -24,7 +25,6 @@ import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.*;
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
import scala.Tuple2;
/**
@ -248,11 +248,11 @@ public class MergeGraphTableSparkJob {
private T mergeAndGet(T b, T a) {
if (Objects.nonNull(a) && Objects.nonNull(b)) {
if (ModelSupport.isSubClass(a, OafEntity.class) && ModelSupport.isSubClass(b, OafEntity.class)) {
return (T) OafMapperUtils.mergeEntities((OafEntity) b, (OafEntity) a);
return (T) MergeUtils.merge(b, a);
}
if (a instanceof Relation && b instanceof Relation) {
((Relation) a).mergeFrom(b);
return a;
return (T) MergeUtils.mergeRelation((Relation)a, (Relation) b);
}
}
return Objects.isNull(a) ? b : a;

43
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/raw/GenerateEntitiesApplication.java
View File

@ -1,14 +1,16 @@
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 com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup;
import eu.dnetlib.dhp.oa.graph.raw.common.AbstractMigrationApplication;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.*;
import eu.dnetlib.dhp.schema.oaf.utils.MergeUtils;
import eu.dnetlib.dhp.utils.ISLookupClientFactory;
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.StringUtils;
import org.apache.hadoop.io.Text;
@ -16,27 +18,18 @@ 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;
import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup;
import eu.dnetlib.dhp.oa.graph.raw.common.AbstractMigrationApplication;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.*;
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
import eu.dnetlib.dhp.utils.ISLookupClientFactory;
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
import scala.Tuple2;
import java.util.Arrays;
import java.util.List;
import java.util.Objects;
import java.util.Optional;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
public class GenerateEntitiesApplication extends AbstractMigrationApplication {
private static final Logger log = LoggerFactory.getLogger(GenerateEntitiesApplication.class);
@ -137,7 +130,7 @@ public class GenerateEntitiesApplication extends AbstractMigrationApplication {
save(
inputRdd
.mapToPair(oaf -> new Tuple2<>(ModelSupport.idFn().apply(oaf), oaf))
.reduceByKey(OafMapperUtils::merge)
.reduceByKey(MergeUtils::merge)
.map(Tuple2::_2),
targetPath);
break;

2
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/raw/MigrateDbEntitiesApplication.java
View File

@ -317,7 +317,7 @@ public class MigrateDbEntitiesApplication extends AbstractMigrationApplication i
listKeyValues(
createOpenaireId(10, rs.getString("collectedfromid"), true),
rs.getString("collectedfromname")));
p.setPid(new ArrayList<>());
p.setPid(prepareListOfStructProps(rs.getArray("pid"), info));
p.setDateofcollection(asString(rs.getDate("dateofcollection")));
p.setDateoftransformation(asString(rs.getDate("dateoftransformation")));
p.setExtraInfo(new ArrayList<>()); // Values not present in the DB

22
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/raw/OdfToOafMapper.java
View File

@ -238,11 +238,23 @@ public class OdfToOafMapper extends AbstractMdRecordToOafMapper {
(Element) doc
.selectSingleNode(
"//*[local-name()='metadata']/*[local-name() = 'resource']/*[local-name() = 'resourceType']"))
.map(element -> {
final String resourceTypeURI = element.attributeValue("uri");
final String resourceTypeAnyURI = element.attributeValue("anyURI");
final String resourceTypeTxt = element.getText();
final String resourceTypeGeneral = element.attributeValue("resourceTypeGeneral");
.map(e -> {
final String resourceTypeURI = Optional
.ofNullable(e.attributeValue("uri"))
.filter(StringUtils::isNotBlank)
.orElse(null);
final String resourceTypeAnyURI = Optional
.ofNullable(e.attributeValue("anyURI"))
.filter(StringUtils::isNotBlank)
.orElse(null);
final String resourceTypeTxt = Optional
.ofNullable(e.getText())
.filter(StringUtils::isNotBlank)
.orElse(null);
final String resourceTypeGeneral = Optional
.ofNullable(e.attributeValue("resourceTypeGeneral"))
.filter(StringUtils::isNotBlank)
.orElse(null);
return ObjectUtils
.firstNonNull(resourceTypeURI, resourceTypeAnyURI, resourceTypeTxt, resourceTypeGeneral);

22
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/enrich/orcid/oozie_app/workflow.xml
View File

@ -12,6 +12,16 @@
<name>targetPath</name>
<description>the output path of the graph enriched</description>
</property>
<property>
<name>spark2ExtraListeners</name>
<value>com.cloudera.spark.lineage.NavigatorAppListener</value>
<description>spark 2.* extra listeners classname</description>
</property>
<property>
<name>spark2SqlQueryExecutionListeners</name>
<value>com.cloudera.spark.lineage.NavigatorQueryListener</value>
<description>spark 2.* sql query execution listeners classname</description>
</property>
</parameters>
<start to="EnrichGraph"/>
@ -31,8 +41,8 @@
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.executor.memoryOverhead=2g
--conf spark.sql.shuffle.partitions=3000
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
--conf spark.sql.shuffle.partitions=5000
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
@ -49,10 +59,10 @@
<action name="reset_outputpath">
<fs>
<delete path="${graphPath}/datasource"/>
<delete path="${graphPath}/organization"/>
<delete path="${graphPath}/project"/>
<delete path="${graphPath}/relation"/>
<delete path="${targetPath}/datasource"/>
<delete path="${targetPath}/organization"/>
<delete path="${targetPath}/project"/>
<delete path="${targetPath}/relation"/>
</fs>
<ok to="copy_datasource"/>
<error to="Kill"/>

2
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/sql/queryProjects.sql
View File

@ -33,7 +33,7 @@ SELECT
dc.officialname AS collectedfromname,
p.contracttype || '@@@' || p.contracttypescheme AS contracttype,
p.provenanceactionclass || '@@@' || p.provenanceactionscheme AS provenanceaction,
array_agg(DISTINCT i.pid || '###' || i.issuertype) AS pid,
array_remove(array_agg(DISTINCT i.pid || '###' || i.issuertype || '@@@' || i.issuertype), NULL) AS pid,,
array_agg(DISTINCT s.name || '###' || s.semanticclass || '@@@' || s.semanticscheme) AS subjects,
array_agg(DISTINCT fp.path) AS fundingtree

2
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/sql/queryProjects_production.sql
View File

@ -33,7 +33,7 @@ SELECT
dc.officialname AS collectedfromname,
p.contracttypeclass || '@@@' || p.contracttypescheme AS contracttype,
p.provenanceactionclass || '@@@' || p.provenanceactionscheme AS provenanceaction,
array_agg(DISTINCT i.pid || '###' || i.issuertype) AS pid,
array_remove(array_agg(DISTINCT i.pid || '###' || i.issuertype || '@@@' || i.issuertype), NULL) AS pid,
array_agg(DISTINCT s.name || '###' || s.semanticclass || '@@@' || s.semanticscheme) AS subjects,
array_agg(DISTINCT fp.path) AS fundingtree
FROM projects p

40
dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/enrich/orcid/AuthorEnricher.scala
View File

@ -1,40 +0,0 @@
package eu.dnetlib.dhp.enrich.orcid
import eu.dnetlib.dhp.schema.common.ModelConstants
import eu.dnetlib.dhp.schema.oaf.{Author, Publication}
import eu.dnetlib.dhp.schema.sx.OafUtils
import org.apache.spark.sql.Row
import scala.collection.JavaConverters._
object AuthorEnricher extends Serializable {
def createAuthor(givenName: String, familyName: String, orcid: String): Author = {
val a = new Author
a.setName(givenName)
a.setSurname(familyName)
a.setFullname(s"$givenName $familyName")
val pid = OafUtils.createSP(orcid, ModelConstants.ORCID, ModelConstants.ORCID)
pid.setDataInfo(OafUtils.generateDataInfo())
pid.getDataInfo.setProvenanceaction(OafUtils.createQualifier("ORCID_ENRICHMENT", "ORCID_ENRICHMENT"))
a.setPid(List(pid).asJava)
a
}
def toOAFAuthor(r: Row): java.util.List[Author] = {
r.getList[Row](1)
.asScala
.map(s => createAuthor(s.getAs[String]("givenName"), s.getAs[String]("familyName"), s.getAs[String]("orcid")))
.toList
.asJava
}
// def enrichAuthor(p:Publication,r:Row): Unit = {
// val k:Map[String, OAuthor] =r.getList[Row](1).asScala.map(s => (s.getAs[String]("orcid"), OAuthor(s.getAs[String]("givenName") ,s.getAs[String]("familyName") ))).groupBy(_._1).mapValues(_.map(_._2).head)
// println(k)
//
//
//
// }
}

128
dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/enrich/orcid/ORCIDAuthorEnricher.scala Normal file
View File

@ -0,0 +1,128 @@
package eu.dnetlib.dhp.enrich.orcid
import eu.dnetlib.dhp.schema.common.ModelConstants
import eu.dnetlib.dhp.schema.oaf.{Author, StructuredProperty}
import eu.dnetlib.dhp.schema.sx.OafUtils
import java.util
import scala.beans.BeanProperty
import scala.collection.JavaConverters._
import scala.util.control.Breaks.{break, breakable}
case class ORCIDAuthorEnricherResult(
@BeanProperty var id: String,
@BeanProperty var enriched_author: java.util.List[Author],
@BeanProperty var author_matched: java.util.List[MatchedAuthors],
@BeanProperty var author_unmatched: java.util.List[Author],
@BeanProperty var orcid_unmatched: java.util.List[OrcidAutor]
)
object ORCIDAuthorEnricher extends Serializable {
def enrichOrcid(
id: String,
graph_authors: java.util.List[Author],
orcid_authors: java.util.List[OrcidAutor]
): ORCIDAuthorEnricherResult = {
// Author enriching strategy:
// 1) create a copy of graph author list in unmatched_authors
// 2) find best match in unmatched_authors, remove it from unmatched_authors and enrich it so
// that the enrichment is reflected in graph_authors (they share author instances)
// 3) repeat (2) till the end of the list and then with different matching algorithms that have decreasing
// trust in their output
// At the end unmatched_authors will contain authors not matched with any of the matching algos
val unmatched_authors = new util.ArrayList[Author](graph_authors)
val matches = {
// Look after exact fullname match, reconstruct ORCID fullname as givenName + familyName
extractAndEnrichMatches(
unmatched_authors,
orcid_authors,
(author, orcid) =>
ORCIDAuthorMatchers.matchEqualsIgnoreCase(author.getFullname, orcid.givenName + " " + orcid.familyName),
"fullName"
) ++
// Look after exact reversed fullname match, reconstruct ORCID fullname as familyName + givenName
extractAndEnrichMatches(
unmatched_authors,
orcid_authors,
(author, orcid) =>
ORCIDAuthorMatchers.matchEqualsIgnoreCase(author.getFullname, orcid.familyName + " " + orcid.givenName),
"reversedFullName"
) ++
// split author names in tokens, order the tokens, then check for matches of full tokens or abbreviations
extractAndEnrichMatches(
unmatched_authors,
orcid_authors,
(author, orcid) =>
ORCIDAuthorMatchers
.matchOrderedTokenAndAbbreviations(author.getFullname, orcid.givenName + " " + orcid.familyName),
"orderedTokens"
) ++
// look after exact matches of ORCID creditName
extractAndEnrichMatches(
unmatched_authors,
orcid_authors,
(author, orcid) => ORCIDAuthorMatchers.matchEqualsIgnoreCase(author.getFullname, orcid.creditName),
"creditName"
) ++
// look after exact matches in ORCID otherNames
extractAndEnrichMatches(
unmatched_authors,
orcid_authors,
(author, orcid) =>
orcid.otherNames != null && ORCIDAuthorMatchers.matchOtherNames(author.getFullname, orcid.otherNames.asScala),
"otherNames"
)
}
ORCIDAuthorEnricherResult(id, graph_authors, matches.asJava, unmatched_authors, orcid_authors)
}
private def extractAndEnrichMatches(
graph_authors: java.util.List[Author],
orcid_authors: java.util.List[OrcidAutor],
matchingFunc: (Author, OrcidAutor) => Boolean,
matchName: String
) = {
val matched = scala.collection.mutable.ArrayBuffer.empty[MatchedAuthors]
if (graph_authors != null && !graph_authors.isEmpty) {
val ait = graph_authors.iterator
while (ait.hasNext) {
val author = ait.next()
val oit = orcid_authors.iterator
breakable {
while (oit.hasNext) {
val orcid = oit.next()
if (matchingFunc(author, orcid)) {
ait.remove()
oit.remove()
matched += MatchedAuthors(author, orcid, matchName)
if (author.getPid == null) {
author.setPid(new util.ArrayList[StructuredProperty]())
}
val orcidPID = OafUtils.createSP(orcid.orcid, ModelConstants.ORCID, ModelConstants.ORCID)
orcidPID.setDataInfo(OafUtils.generateDataInfo())
orcidPID.getDataInfo.setProvenanceaction(
OafUtils.createQualifier("ORCID_ENRICHMENT", "ORCID_ENRICHMENT")
)
author.getPid.add(orcidPID)
break()
}
}
}
}
}
matched
}
}

65
dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/enrich/orcid/ORCIDAuthorMatchers.scala Normal file
View File

@ -0,0 +1,65 @@
package eu.dnetlib.dhp.enrich.orcid
import java.util.Locale
import java.util.regex.Pattern
object ORCIDAuthorMatchers {
val SPLIT_REGEX = Pattern.compile("[\\s,\\.]+")
val WORD_DIFF = 2
def matchEqualsIgnoreCase(a1: String, a2: String): Boolean = {
if (a1 == null || a2 == null)
false
else
a1 == a2 || a1.toLowerCase(Locale.ROOT).equals(a2.toLowerCase(Locale.ROOT))
}
def matchOtherNames(fullName: String, otherNames: Seq[String]): Boolean = {
if (otherNames != null) {
otherNames.exists(matchEqualsIgnoreCase(fullName, _))
} else {
false
}
}
def matchOrderedTokenAndAbbreviations(a1: String, a2: String): Boolean = {
val p1: Array[String] = SPLIT_REGEX.split(a1.trim.toLowerCase(Locale.ROOT)).filter(_.nonEmpty).sorted
val p2: Array[String] = SPLIT_REGEX.split(a2.trim.toLowerCase(Locale.ROOT)).filter(_.nonEmpty).sorted
if (p1.length < 2 || p2.length < 2) return false
if (Math.abs(p1.length - p2.length) > WORD_DIFF) return false // use alternative comparison algo
var p1Idx: Int = 0
var p2Idx: Int = 0
var shortMatches: Int = 0
var longMatches: Int = 0
while (p1Idx < p1.length && p2Idx < p2.length) {
val e1: String = p1(p1Idx)
val c1: Char = e1.charAt(0)
val e2: String = p2(p2Idx)
val c2: Char = e2.charAt(0)
if (c1 < c2) p1Idx += 1
else if (c1 > c2) p2Idx += 1
else {
var res: Boolean = false
if (e1.length != 1 && e2.length != 1) {
res = e1 == e2
longMatches += 1
} else {
res = true
shortMatches += 1
}
if (res) {
p1Idx += 1
p2Idx += 1
} else {
val diff: Int = e1.compareTo(e2)
if (diff < 0) p1Idx += 1
else if (diff > 0) p2Idx += 1
}
}
}
longMatches > 0 && (shortMatches + longMatches) == Math.min(p1.length, p2.length)
}
}

212
dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/enrich/orcid/SparkEnrichGraphWithOrcidAuthors.scala
View File

@ -1,14 +1,39 @@
package eu.dnetlib.dhp.enrich.orcid
import eu.dnetlib.dhp.application.AbstractScalaApplication
import eu.dnetlib.dhp.oa.merge.AuthorMerger
import eu.dnetlib.dhp.schema.common.ModelSupport
import eu.dnetlib.dhp.schema.oaf.{OtherResearchProduct, Publication, Result, Software}
import org.apache.spark.sql.functions._
import eu.dnetlib.dhp.schema.oaf._
import org.apache.spark.sql._
import org.apache.spark.sql.functions._
import org.slf4j.{Logger, LoggerFactory}
import scala.beans.BeanProperty
import scala.collection.JavaConverters._
case class OrcidAutor(
@BeanProperty var orcid: String,
@BeanProperty var familyName: String,
@BeanProperty var givenName: String,
@BeanProperty var creditName: String,
@BeanProperty var otherNames: java.util.List[String]
) {
def this() = this("null", "null", "null", "null", null)
}
case class MatchData(
@BeanProperty var id: String,
@BeanProperty var graph_authors: java.util.List[Author],
@BeanProperty var orcid_authors: java.util.List[OrcidAutor]
) {
def this() = this("null", null, null)
}
case class MatchedAuthors(
@BeanProperty var author: Author,
@BeanProperty var orcid: OrcidAutor,
@BeanProperty var `type`: String
)
class SparkEnrichGraphWithOrcidAuthors(propertyPath: String, args: Array[String], log: Logger)
extends AbstractScalaApplication(propertyPath, args, log: Logger) {
@ -22,107 +47,132 @@ class SparkEnrichGraphWithOrcidAuthors(propertyPath: String, args: Array[String]
log.info(s"orcidPath is '$orcidPath'")
val targetPath = parser.get("targetPath")
log.info(s"targetPath is '$targetPath'")
val orcidPublication: Dataset[Row] = generateOrcidTable(spark, orcidPath)
// ModelSupport.entityTypes.entrySet().asScala.filter(k => k.getKey.getClass isInstance(Result))
enrichResult(
spark,
s"$graphPath/publication",
orcidPublication,
s"$targetPath/publication",
Encoders.bean(classOf[Publication])
)
enrichResult(
spark,
s"$graphPath/dataset",
orcidPublication,
s"$targetPath/dataset",
Encoders.bean(classOf[eu.dnetlib.dhp.schema.oaf.Dataset])
)
enrichResult(
spark,
s"$graphPath/software",
orcidPublication,
s"$targetPath/software",
Encoders.bean(classOf[Software])
)
enrichResult(
spark,
s"$graphPath/otherresearchproduct",
orcidPublication,
s"$targetPath/otherresearchproduct",
Encoders.bean(classOf[OtherResearchProduct])
)
createTemporaryData(graphPath, orcidPath, targetPath)
analisys(targetPath)
generateGraph(graphPath, targetPath)
}
private def enrichResult[T <: Result](
spark: SparkSession,
graphPath: String,
orcidPublication: Dataset[Row],
outputPath: String,
enc: Encoder[T]
): Unit = {
private def generateGraph(graphPath: String, targetPath: String): Unit = {
val entities = spark.read
ModelSupport.entityTypes.asScala
.filter(e => ModelSupport.isResult(e._1))
.foreach(e => {
val resultType = e._1.name()
val enc = Encoders.bean(e._2)
val matched = spark.read
.schema(Encoders.bean(classOf[ORCIDAuthorEnricherResult]).schema)
.parquet(s"${targetPath}/${resultType}_matched")
.selectExpr("id", "enriched_author")
spark.read
.schema(enc.schema)
.json(graphPath)
.json(s"$graphPath/$resultType")
.join(matched, Seq("id"), "left")
.withColumn(
"author",
when(size(col("enriched_author")).gt(0), col("enriched_author"))
.otherwise(col("author"))
)
.drop("enriched_author")
.write
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(s"${targetPath}/${resultType}")
})
}
private def createTemporaryData(graphPath: String, orcidPath: String, targetPath: String): Unit = {
val orcidAuthors =
spark.read.load(s"$orcidPath/Authors").select("orcid", "familyName", "givenName", "creditName", "otherNames")
val orcidWorks = spark.read
.load(s"$orcidPath/Works")
.select(col("orcid"), explode(col("pids")).alias("identifier"))
.where(
"identifier.schema IN('doi','pmid','pmc','arxiv','handle')" // scopus eid ?
)
val orcidWorksWithAuthors = orcidAuthors
.join(orcidWorks, Seq("orcid"))
.select(
lower(col("identifier.schema")).alias("pid_schema"),
lower(col("identifier.value")).alias("pid_value"),
struct(
col("orcid"),
col("givenName"),
col("familyName"),
col("creditName"),
col("otherNames")
).alias("author")
)
.cache()
ModelSupport.entityTypes.asScala
.filter(e => ModelSupport.isResult(e._1))
.foreach(e => {
val resultType = e._1.name()
val enc = Encoders.bean(e._2)
val oaEntities = spark.read
.schema(enc.schema)
.json(s"$graphPath/$resultType")
.select(col("id"), col("datainfo"), col("instance"))
.where("datainfo.deletedbyinference != true")
.drop("datainfo")
.withColumn("instances", explode(col("instance")))
.withColumn("pids", explode(col("instances.pid")))
.select(
col("pids.qualifier.classid").alias("pid_schema"),
col("pids.value").alias("pid_value"),
col("id").alias("dnet_id")
lower(col("pids.qualifier.classid")).alias("pid_schema"),
lower(col("pids.value")).alias("pid_value"),
col("id")
)
val orcidDnet = orcidPublication
val orcidDnet = orcidWorksWithAuthors
.join(
entities,
lower(col("schema")).equalTo(lower(col("pid_schema"))) &&
lower(col("value")).equalTo(lower(col("pid_value"))),
oaEntities,
Seq("pid_schema", "pid_value"),
"inner"
)
.groupBy(col("dnet_id"))
.agg(collect_set(orcidPublication("author")).alias("orcid_authors"))
.select("dnet_id", "orcid_authors")
.cache()
orcidDnet.count()
val result = spark.read.schema(enc.schema).json(graphPath).as[T](enc)
.groupBy(col("id"))
.agg(collect_set(col("author")).alias("orcid_authors"))
.select("id", "orcid_authors")
val result =
spark.read.schema(enc.schema).json(s"$graphPath/$resultType").selectExpr("id", "author as graph_authors")
result
.joinWith(orcidDnet, result("id").equalTo(orcidDnet("dnet_id")), "left")
.map {
case (r: T, null) =>
r
case (p: T, r: Row) =>
p.setAuthor(AuthorMerger.enrichOrcid(p.getAuthor, AuthorEnricher.toOAFAuthor(r)))
p
}(enc)
.join(orcidDnet, Seq("id"))
.write
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(outputPath)
.parquet(s"$targetPath/${resultType}_unmatched")
})
orcidWorksWithAuthors.unpersist()
}
private def generateOrcidTable(spark: SparkSession, inputPath: String): Dataset[Row] = {
val orcidAuthors =
spark.read.load(s"$inputPath/Authors").select("orcid", "familyName", "givenName", "creditName", "otherNames")
val orcidWorks = spark.read
.load(s"$inputPath/Works")
.select(col("orcid"), explode(col("pids")).alias("identifier"))
.where(
"identifier.schema IN('doi','pmid','pmc','arxiv','handle')"
)
val orcidPublication = orcidAuthors
.join(orcidWorks, orcidAuthors("orcid").equalTo(orcidWorks("orcid")))
.select(
col("identifier.schema").alias("schema"),
col("identifier.value").alias("value"),
struct(orcidAuthors("orcid").alias("orcid"), col("givenName"), col("familyName")).alias("author")
)
orcidPublication.cache()
private def analisys(targetPath: String): Unit = {
ModelSupport.entityTypes.asScala
.filter(e => ModelSupport.isResult(e._1))
.foreach(e => {
val resultType = e._1.name()
spark.read
.parquet(s"$targetPath/${resultType}_unmatched")
.where("size(graph_authors) > 0")
.as[MatchData](Encoders.bean(classOf[MatchData]))
.map(md => {
ORCIDAuthorEnricher.enrichOrcid(md.id, md.graph_authors, md.orcid_authors)
})(Encoders.bean(classOf[ORCIDAuthorEnricherResult]))
.write
.option("compression", "gzip")
.mode("overwrite")
.parquet(s"$targetPath/${resultType}_matched")
})
}
}

4
dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/oa/graph/raw/CopyHdfsOafSparkApplication.scala
View File

@ -93,8 +93,8 @@ object CopyHdfsOafSparkApplication {
hasSource != null && hasTarget != null
} else {
val hasId = (json \ "id").extractOrElse[String](null)
val resultType = (json \ "resulttype" \ "classid").extractOrElse[String](null)
hasId != null && oafType.equalsIgnoreCase(resultType)
val resultType = (json \ "resulttype" \ "classid").extractOrElse[String]("")
hasId != null && oafType.startsWith(resultType)
}
}

8
dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/oa/graph/resolution/SparkResolveEntities.scala
View File

@ -3,6 +3,7 @@ package eu.dnetlib.dhp.oa.graph.resolution
import com.fasterxml.jackson.databind.ObjectMapper
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.schema.common.EntityType
import eu.dnetlib.dhp.schema.oaf.utils.MergeUtils
import eu.dnetlib.dhp.schema.oaf.{Dataset => OafDataset, _}
import org.apache.commons.io.IOUtils
import org.apache.hadoop.fs.{FileSystem, Path}
@ -118,15 +119,12 @@ object SparkResolveEntities {
currentEntityDataset
.joinWith(re, currentEntityDataset("_1").equalTo(re("_1")), "left")
.map(k => {
val a = k._1
val b = k._2
if (b == null)
a._2
else {
a._2.mergeFrom(b._2)
a._2
}
else
MergeUtils.mergeResult(a._2, b._2)
})
.map(r => mapper.writeValueAsString(r))(Encoders.STRING)
.write

6
dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/sx/graph/SparkCreateInputGraph.scala
View File

@ -1,6 +1,7 @@
package eu.dnetlib.dhp.sx.graph
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.schema.oaf.utils.MergeUtils
import eu.dnetlib.dhp.schema.oaf.{Dataset => OafDataset, _}
import org.apache.commons.io.IOUtils
import org.apache.spark.SparkConf
@ -130,10 +131,7 @@ object SparkCreateInputGraph {
val ds: Dataset[T] = spark.read.load(sourcePath).as[T]
ds.groupByKey(_.getId)
.reduceGroups { (x: T, y: T) =>
x.mergeFrom(y)
x
}
.reduceGroups { (x: T, y: T) => MergeUtils.merge(x, y).asInstanceOf[T] }
.map(_._2)
.write
.mode(SaveMode.Overwrite)

38
dhp-common/src/test/java/eu/dnetlib/oa/merge/AuthorMergerTest.java → dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/enrich/orcid/ORCIDAuthorEnricherTest.java
View File

@ -1,10 +1,9 @@
package eu.dnetlib.oa.merge;
import static org.junit.jupiter.api.Assertions.*;
package eu.dnetlib.dhp.enrich.orcid;
import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.util.Collections;
import java.util.List;
import java.util.Objects;
@ -14,10 +13,9 @@ import org.junit.platform.commons.util.StringUtils;
import com.fasterxml.jackson.core.type.TypeReference;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.oa.merge.AuthorMerger;
import eu.dnetlib.dhp.schema.oaf.Author;
public class AuthorMergerTest {
public class ORCIDAuthorEnricherTest {
@Test
public void testEnrcichAuthor() throws Exception {
@ -26,12 +24,13 @@ public class AuthorMergerTest {
BufferedReader pr = new BufferedReader(new InputStreamReader(
Objects
.requireNonNull(
AuthorMergerTest.class
.getResourceAsStream("/eu/dnetlib/dhp/oa/merge/authors_publication_sample.json"))));
ORCIDAuthorEnricherTest.class
.getResourceAsStream("/eu/dnetlib/dhp/enrich/orcid/authors_publication_sample.json"))));
BufferedReader or = new BufferedReader(new InputStreamReader(
Objects
.requireNonNull(
AuthorMergerTest.class.getResourceAsStream("/eu/dnetlib/dhp/oa/merge/authors_orcid_sample.json"))));
ORCIDAuthorEnricherTest.class
.getResourceAsStream("/eu/dnetlib/dhp/enrich/orcid/authors_orcid_sample.json"))));
TypeReference<List<Author>> aclass = new TypeReference<List<Author>>() {
};
@ -67,7 +66,8 @@ public class AuthorMergerTest {
long start = System.currentTimeMillis();
// final List<Author> enrichedList = AuthorMerger.enrichOrcid(publicationAuthors, orcidAuthors);
final List<Author> enrichedList = AuthorMerger.enrichOrcid(publicationAuthors, orcidAuthors);
final List<Author> enrichedList = Collections.emptyList(); // SparkEnrichGraphWithOrcidAuthors.enrichOrcid(publicationAuthors,
// orcidAuthors);
long enrichedAuthorWithPid = enrichedList
.stream()
@ -91,24 +91,4 @@ public class AuthorMergerTest {
}
}
@Test
public void checkSimilarityTest() {
final Author left = new Author();
left.setName("Anand");
left.setSurname("Rachna");
left.setFullname("Anand, Rachna");
System.out.println(AuthorMerger.normalizeFullName(left.getFullname()));
final Author right = new Author();
right.setName("Rachna");
right.setSurname("Anand");
right.setFullname("Rachna, Anand");
// System.out.println(AuthorMerger.normalize(right.getFullname()));
boolean same = AuthorMerger.checkORCIDSimilarity(left, right);
assertTrue(same);
}
}

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