forked from D-Net/dnet-hadoop
Merge branch 'beta' into FOSNew
This commit is contained in:
commit
9a5b134ddf
|
@ -145,105 +145,6 @@ public class AuthorMerger {
|
||||||
return null;
|
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) {
|
public static String pidToComparableString(StructuredProperty pid) {
|
||||||
final String classid = pid.getQualifier().getClassid() != null ? pid.getQualifier().getClassid().toLowerCase()
|
final String classid = pid.getQualifier().getClassid() != null ? pid.getQualifier().getClassid().toLowerCase()
|
||||||
: "";
|
: "";
|
||||||
|
|
|
@ -1,24 +1,6 @@
|
||||||
|
|
||||||
package eu.dnetlib.dhp.oa.merge;
|
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.application.ArgumentApplicationParser;
|
||||||
import eu.dnetlib.dhp.common.HdfsSupport;
|
import eu.dnetlib.dhp.common.HdfsSupport;
|
||||||
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup;
|
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.common.ModelSupport;
|
||||||
import eu.dnetlib.dhp.schema.oaf.OafEntity;
|
import eu.dnetlib.dhp.schema.oaf.OafEntity;
|
||||||
import eu.dnetlib.dhp.schema.oaf.utils.GraphCleaningFunctions;
|
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.dhp.utils.ISLookupClientFactory;
|
||||||
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpException;
|
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpException;
|
||||||
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
|
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 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
|
* Groups the graph content by entity identifier to ensure ID uniqueness
|
||||||
*/
|
*/
|
||||||
|
@ -135,7 +134,7 @@ public class GroupEntitiesSparkJob {
|
||||||
.applyCoarVocabularies(entity, vocs),
|
.applyCoarVocabularies(entity, vocs),
|
||||||
OAFENTITY_KRYO_ENC)
|
OAFENTITY_KRYO_ENC)
|
||||||
.groupByKey((MapFunction<OafEntity, String>) OafEntity::getId, Encoders.STRING())
|
.groupByKey((MapFunction<OafEntity, String>) OafEntity::getId, Encoders.STRING())
|
||||||
.reduceGroups((ReduceFunction<OafEntity>) OafMapperUtils::mergeEntities)
|
.reduceGroups((ReduceFunction<OafEntity>) MergeUtils::checkedMerge)
|
||||||
.map(
|
.map(
|
||||||
(MapFunction<Tuple2<String, OafEntity>, Tuple2<String, OafEntity>>) t -> new Tuple2<>(
|
(MapFunction<Tuple2<String, OafEntity>, Tuple2<String, OafEntity>>) t -> new Tuple2<>(
|
||||||
t._2().getClass().getName(), t._2()),
|
t._2().getClass().getName(), t._2()),
|
||||||
|
|
|
@ -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());
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
}
|
|
@ -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);
|
||||||
|
}
|
||||||
|
|
||||||
|
}
|
|
@ -14,7 +14,6 @@ import java.util.stream.Collectors;
|
||||||
import org.apache.commons.lang3.StringUtils;
|
import org.apache.commons.lang3.StringUtils;
|
||||||
|
|
||||||
import eu.dnetlib.dhp.schema.common.AccessRightComparator;
|
import eu.dnetlib.dhp.schema.common.AccessRightComparator;
|
||||||
import eu.dnetlib.dhp.schema.common.ModelSupport;
|
|
||||||
import eu.dnetlib.dhp.schema.oaf.*;
|
import eu.dnetlib.dhp.schema.oaf.*;
|
||||||
|
|
||||||
public class OafMapperUtils {
|
public class OafMapperUtils {
|
||||||
|
@ -22,65 +21,6 @@ public class OafMapperUtils {
|
||||||
private 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) {
|
public static KeyValue keyValue(final String k, final String v) {
|
||||||
final KeyValue kv = new KeyValue();
|
final KeyValue kv = new KeyValue();
|
||||||
kv.setKey(k);
|
kv.setKey(k);
|
||||||
|
|
|
@ -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);
|
||||||
|
}
|
||||||
|
|
||||||
|
}
|
|
@ -149,7 +149,7 @@ class OafMapperUtilsTest {
|
||||||
void testDate() {
|
void testDate() {
|
||||||
final String date = GraphCleaningFunctions.cleanDate("23-FEB-1998");
|
final String date = GraphCleaningFunctions.cleanDate("23-FEB-1998");
|
||||||
assertNotNull(date);
|
assertNotNull(date);
|
||||||
System.out.println(date);
|
assertEquals("1998-02-23", date);
|
||||||
}
|
}
|
||||||
|
|
||||||
@Test
|
@Test
|
||||||
|
@ -166,8 +166,8 @@ class OafMapperUtilsTest {
|
||||||
|
|
||||||
assertEquals(
|
assertEquals(
|
||||||
ModelConstants.PUBLICATION_RESULTTYPE_CLASSID,
|
ModelConstants.PUBLICATION_RESULTTYPE_CLASSID,
|
||||||
OafMapperUtils
|
MergeUtils
|
||||||
.mergeResults(p1, d2)
|
.mergeResult(p1, d2)
|
||||||
.getResulttype()
|
.getResulttype()
|
||||||
.getClassid());
|
.getClassid());
|
||||||
|
|
||||||
|
@ -178,8 +178,8 @@ class OafMapperUtilsTest {
|
||||||
|
|
||||||
assertEquals(
|
assertEquals(
|
||||||
ModelConstants.DATASET_RESULTTYPE_CLASSID,
|
ModelConstants.DATASET_RESULTTYPE_CLASSID,
|
||||||
OafMapperUtils
|
MergeUtils
|
||||||
.mergeResults(p2, d1)
|
.mergeResult(p2, d1)
|
||||||
.getResulttype()
|
.getResulttype()
|
||||||
.getClassid());
|
.getClassid());
|
||||||
}
|
}
|
||||||
|
@ -192,7 +192,7 @@ class OafMapperUtilsTest {
|
||||||
assertEquals(1, d2.getCollectedfrom().size());
|
assertEquals(1, d2.getCollectedfrom().size());
|
||||||
assertTrue(cfId(d2.getCollectedfrom()).contains(ModelConstants.ZENODO_OD_ID));
|
assertTrue(cfId(d2.getCollectedfrom()).contains(ModelConstants.ZENODO_OD_ID));
|
||||||
|
|
||||||
Result res = OafMapperUtils.mergeResults(d1, d2);
|
Result res = MergeUtils.mergeResult(d1, d2);
|
||||||
|
|
||||||
assertEquals(d2, res);
|
assertEquals(d2, res);
|
||||||
|
|
||||||
|
|
|
@ -1,14 +1,13 @@
|
||||||
|
|
||||||
package eu.dnetlib.dhp.actionmanager.promote;
|
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 java.util.function.BiFunction;
|
||||||
|
|
||||||
import eu.dnetlib.dhp.common.FunctionalInterfaceSupport.SerializableSupplier;
|
import static eu.dnetlib.dhp.schema.common.ModelSupport.isSubClass;
|
||||||
import eu.dnetlib.dhp.schema.oaf.Oaf;
|
|
||||||
import eu.dnetlib.dhp.schema.oaf.OafEntity;
|
|
||||||
import eu.dnetlib.dhp.schema.oaf.Relation;
|
|
||||||
|
|
||||||
/** OAF model merging support. */
|
/** OAF model merging support. */
|
||||||
public class MergeAndGet {
|
public class MergeAndGet {
|
||||||
|
@ -46,20 +45,7 @@ public class MergeAndGet {
|
||||||
}
|
}
|
||||||
|
|
||||||
private static <G extends Oaf, A extends Oaf> G mergeFromAndGet(G x, A y) {
|
private static <G extends Oaf, A extends Oaf> G mergeFromAndGet(G x, A y) {
|
||||||
if (isSubClass(x, Relation.class) && isSubClass(y, Relation.class)) {
|
return (G) MergeUtils.merge(x, y);
|
||||||
((Relation) x).mergeFrom((Relation) y);
|
|
||||||
return x;
|
|
||||||
} else if (isSubClass(x, OafEntity.class)
|
|
||||||
&& isSubClass(y, OafEntity.class)
|
|
||||||
&& isSubClass(x, y)) {
|
|
||||||
((OafEntity) x).mergeFrom((OafEntity) y);
|
|
||||||
return x;
|
|
||||||
}
|
|
||||||
throw new RuntimeException(
|
|
||||||
String
|
|
||||||
.format(
|
|
||||||
"MERGE_FROM_AND_GET incompatible types: %s, %s",
|
|
||||||
x.getClass().getCanonicalName(), y.getClass().getCanonicalName()));
|
|
||||||
}
|
}
|
||||||
|
|
||||||
@SuppressWarnings("unchecked")
|
@SuppressWarnings("unchecked")
|
||||||
|
|
|
@ -64,6 +64,9 @@ public class PrepareAffiliationRelations implements Serializable {
|
||||||
final String pubmedInputPath = parser.get("pubmedInputPath");
|
final String pubmedInputPath = parser.get("pubmedInputPath");
|
||||||
log.info("pubmedInputPath: {}", pubmedInputPath);
|
log.info("pubmedInputPath: {}", pubmedInputPath);
|
||||||
|
|
||||||
|
final String openapcInputPath = parser.get("openapcInputPath");
|
||||||
|
log.info("openapcInputPath: {}", openapcInputPath);
|
||||||
|
|
||||||
final String outputPath = parser.get("outputPath");
|
final String outputPath = parser.get("outputPath");
|
||||||
log.info("outputPath: {}", outputPath);
|
log.info("outputPath: {}", outputPath);
|
||||||
|
|
||||||
|
@ -85,8 +88,14 @@ public class PrepareAffiliationRelations implements Serializable {
|
||||||
JavaPairRDD<Text, Text> pubmedRelations = prepareAffiliationRelations(
|
JavaPairRDD<Text, Text> pubmedRelations = prepareAffiliationRelations(
|
||||||
spark, pubmedInputPath, collectedFromPubmed);
|
spark, pubmedInputPath, collectedFromPubmed);
|
||||||
|
|
||||||
|
List<KeyValue> collectedFromOpenAPC = OafMapperUtils
|
||||||
|
.listKeyValues(ModelConstants.OPEN_APC_ID, "OpenAPC");
|
||||||
|
JavaPairRDD<Text, Text> openAPCRelations = prepareAffiliationRelations(
|
||||||
|
spark, openapcInputPath, collectedFromOpenAPC);
|
||||||
|
|
||||||
crossrefRelations
|
crossrefRelations
|
||||||
.union(pubmedRelations)
|
.union(pubmedRelations)
|
||||||
|
.union(openAPCRelations)
|
||||||
.saveAsHadoopFile(
|
.saveAsHadoopFile(
|
||||||
outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class);
|
outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class);
|
||||||
|
|
||||||
|
|
|
@ -95,7 +95,7 @@ public class SparkAtomicActionScoreJob implements Serializable {
|
||||||
|
|
||||||
return projectScores.map((MapFunction<BipProjectModel, Project>) bipProjectScores -> {
|
return projectScores.map((MapFunction<BipProjectModel, Project>) bipProjectScores -> {
|
||||||
Project project = new Project();
|
Project project = new Project();
|
||||||
project.setId(bipProjectScores.getProjectId());
|
//project.setId(bipProjectScores.getProjectId());
|
||||||
project.setMeasures(bipProjectScores.toMeasures());
|
project.setMeasures(bipProjectScores.toMeasures());
|
||||||
return project;
|
return project;
|
||||||
}, Encoders.bean(Project.class))
|
}, Encoders.bean(Project.class))
|
||||||
|
|
|
@ -34,6 +34,11 @@ public class BipProjectModel {
|
||||||
|
|
||||||
String totalCitationCount;
|
String totalCitationCount;
|
||||||
|
|
||||||
|
public String getProjectId() {
|
||||||
|
return projectId;
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
// each project bip measure has exactly one value, hence one key-value pair
|
// each project bip measure has exactly one value, hence one key-value pair
|
||||||
private Measure createMeasure(String measureId, String measureValue) {
|
private Measure createMeasure(String measureId, String measureValue) {
|
||||||
|
|
||||||
|
|
|
@ -1,12 +1,20 @@
|
||||||
|
|
||||||
package eu.dnetlib.dhp.actionmanager.project;
|
package eu.dnetlib.dhp.actionmanager.project;
|
||||||
|
|
||||||
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
|
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||||
|
import eu.dnetlib.dhp.actionmanager.project.utils.model.CSVProgramme;
|
||||||
import java.util.Arrays;
|
import eu.dnetlib.dhp.actionmanager.project.utils.model.CSVProject;
|
||||||
import java.util.Objects;
|
import eu.dnetlib.dhp.actionmanager.project.utils.model.JsonTopic;
|
||||||
import java.util.Optional;
|
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.commons.io.IOUtils;
|
||||||
import org.apache.hadoop.io.Text;
|
import org.apache.hadoop.io.Text;
|
||||||
import org.apache.hadoop.mapred.SequenceFileOutputFormat;
|
import org.apache.hadoop.mapred.SequenceFileOutputFormat;
|
||||||
|
@ -18,24 +26,14 @@ import org.apache.spark.sql.Encoders;
|
||||||
import org.apache.spark.sql.SparkSession;
|
import org.apache.spark.sql.SparkSession;
|
||||||
import org.slf4j.Logger;
|
import org.slf4j.Logger;
|
||||||
import org.slf4j.LoggerFactory;
|
import org.slf4j.LoggerFactory;
|
||||||
|
|
||||||
import com.fasterxml.jackson.databind.ObjectMapper;
|
|
||||||
|
|
||||||
import eu.dnetlib.dhp.actionmanager.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 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
|
* 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,
|
(MapFunction<Project, String>) OafEntity::getId,
|
||||||
Encoders.STRING())
|
Encoders.STRING())
|
||||||
.mapGroups((MapGroupsFunction<String, Project, Project>) (s, it) -> {
|
.mapGroups((MapGroupsFunction<String, Project, Project>) (s, it) -> {
|
||||||
Project first = it.next();
|
Project merge = it.next();
|
||||||
it.forEachRemaining(first::mergeFrom);
|
while (it.hasNext()) {
|
||||||
return first;
|
merge = MergeUtils.mergeProject(merge, it.next());
|
||||||
|
}
|
||||||
|
return merge;
|
||||||
}, Encoders.bean(Project.class))
|
}, Encoders.bean(Project.class))
|
||||||
.toJavaRDD()
|
.toJavaRDD()
|
||||||
.map(p -> new AtomicAction(Project.class, p))
|
.map(p -> new AtomicAction(Project.class, p))
|
||||||
|
|
|
@ -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);
|
||||||
|
}
|
||||||
|
|
||||||
|
}
|
|
@ -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;
|
||||||
|
}
|
||||||
|
}
|
|
@ -19,6 +19,7 @@ import org.slf4j.LoggerFactory;
|
||||||
import eu.dnetlib.dhp.aggregation.common.ReporterCallback;
|
import eu.dnetlib.dhp.aggregation.common.ReporterCallback;
|
||||||
import eu.dnetlib.dhp.aggregation.common.ReportingJob;
|
import eu.dnetlib.dhp.aggregation.common.ReportingJob;
|
||||||
import eu.dnetlib.dhp.collection.plugin.CollectorPlugin;
|
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.FileCollectorPlugin;
|
||||||
import eu.dnetlib.dhp.collection.plugin.file.FileGZipCollectorPlugin;
|
import eu.dnetlib.dhp.collection.plugin.file.FileGZipCollectorPlugin;
|
||||||
import eu.dnetlib.dhp.collection.plugin.mongodb.MDStoreCollectorPlugin;
|
import eu.dnetlib.dhp.collection.plugin.mongodb.MDStoreCollectorPlugin;
|
||||||
|
@ -120,6 +121,8 @@ public class CollectorWorker extends ReportingJob {
|
||||||
return new FileCollectorPlugin(fileSystem);
|
return new FileCollectorPlugin(fileSystem);
|
||||||
case fileGzip:
|
case fileGzip:
|
||||||
return new FileGZipCollectorPlugin(fileSystem);
|
return new FileGZipCollectorPlugin(fileSystem);
|
||||||
|
case baseDump:
|
||||||
|
return new BaseCollectorPlugin(this.fileSystem);
|
||||||
case other:
|
case other:
|
||||||
final CollectorPlugin.NAME.OTHER_NAME plugin = Optional
|
final CollectorPlugin.NAME.OTHER_NAME plugin = Optional
|
||||||
.ofNullable(api.getParams().get("other_plugin_type"))
|
.ofNullable(api.getParams().get("other_plugin_type"))
|
||||||
|
|
|
@ -10,7 +10,8 @@ import eu.dnetlib.dhp.common.collection.CollectorException;
|
||||||
public interface CollectorPlugin {
|
public interface CollectorPlugin {
|
||||||
|
|
||||||
enum NAME {
|
enum NAME {
|
||||||
oai, other, rest_json2xml, file, fileGzip;
|
|
||||||
|
oai, other, rest_json2xml, file, fileGzip, baseDump;
|
||||||
|
|
||||||
public enum OTHER_NAME {
|
public enum OTHER_NAME {
|
||||||
mdstore_mongodb_dump, mdstore_mongodb
|
mdstore_mongodb_dump, mdstore_mongodb
|
||||||
|
|
|
@ -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);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
}
|
|
@ -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);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
}
|
|
@ -48,7 +48,7 @@ public class XSLTTransformationFunction implements MapFunction<MetadataRecord, M
|
||||||
@Override
|
@Override
|
||||||
public MetadataRecord call(MetadataRecord value) {
|
public MetadataRecord call(MetadataRecord value) {
|
||||||
aggregationCounter.getTotalItems().add(1);
|
aggregationCounter.getTotalItems().add(1);
|
||||||
try {
|
|
||||||
Processor processor = new Processor(false);
|
Processor processor = new Processor(false);
|
||||||
|
|
||||||
processor.registerExtensionFunction(cleanFunction);
|
processor.registerExtensionFunction(cleanFunction);
|
||||||
|
@ -60,11 +60,18 @@ public class XSLTTransformationFunction implements MapFunction<MetadataRecord, M
|
||||||
comp.setParameter(datasourceIDParam, new XdmAtomicValue(value.getProvenance().getDatasourceId()));
|
comp.setParameter(datasourceIDParam, new XdmAtomicValue(value.getProvenance().getDatasourceId()));
|
||||||
QName datasourceNameParam = new QName(DATASOURCE_NAME_PARAM);
|
QName datasourceNameParam = new QName(DATASOURCE_NAME_PARAM);
|
||||||
comp.setParameter(datasourceNameParam, new XdmAtomicValue(value.getProvenance().getDatasourceName()));
|
comp.setParameter(datasourceNameParam, new XdmAtomicValue(value.getProvenance().getDatasourceName()));
|
||||||
XsltExecutable xslt = comp
|
XsltExecutable xslt;
|
||||||
|
XdmNode source;
|
||||||
|
try {
|
||||||
|
xslt = comp
|
||||||
.compile(new StreamSource(IOUtils.toInputStream(transformationRule, StandardCharsets.UTF_8)));
|
.compile(new StreamSource(IOUtils.toInputStream(transformationRule, StandardCharsets.UTF_8)));
|
||||||
XdmNode source = processor
|
source = processor
|
||||||
.newDocumentBuilder()
|
.newDocumentBuilder()
|
||||||
.build(new StreamSource(IOUtils.toInputStream(value.getBody(), StandardCharsets.UTF_8)));
|
.build(new StreamSource(IOUtils.toInputStream(value.getBody(), StandardCharsets.UTF_8)));
|
||||||
|
} catch (Throwable e) {
|
||||||
|
throw new RuntimeException("Error on parsing xslt", e);
|
||||||
|
}
|
||||||
|
try {
|
||||||
XsltTransformer trans = xslt.load();
|
XsltTransformer trans = xslt.load();
|
||||||
trans.setInitialContextNode(source);
|
trans.setInitialContextNode(source);
|
||||||
final StringWriter output = new StringWriter();
|
final StringWriter output = new StringWriter();
|
||||||
|
|
|
@ -17,6 +17,12 @@
|
||||||
"paramDescription": "the path to get the input data from Pubmed",
|
"paramDescription": "the path to get the input data from Pubmed",
|
||||||
"paramRequired": true
|
"paramRequired": true
|
||||||
},
|
},
|
||||||
|
{
|
||||||
|
"paramName": "oip",
|
||||||
|
"paramLongName": "openapcInputPath",
|
||||||
|
"paramDescription": "the path to get the input data from OpenAPC",
|
||||||
|
"paramRequired": true
|
||||||
|
},
|
||||||
{
|
{
|
||||||
"paramName": "o",
|
"paramName": "o",
|
||||||
"paramLongName": "outputPath",
|
"paramLongName": "outputPath",
|
||||||
|
|
|
@ -31,6 +31,7 @@ spark2SqlQueryExecutionListeners=com.cloudera.spark.lineage.NavigatorQueryListen
|
||||||
# The following is needed as a property of a workflow
|
# The following is needed as a property of a workflow
|
||||||
oozie.wf.application.path=${oozieTopWfApplicationPath}
|
oozie.wf.application.path=${oozieTopWfApplicationPath}
|
||||||
|
|
||||||
crossrefInputPath=/data/bip-affiliations/data.json
|
crossrefInputPath=/data/bip-affiliations/crossref-data.json
|
||||||
pubmedInputPath=/data/bip-affiliations/pubmed-data.json
|
pubmedInputPath=/data/bip-affiliations/pubmed-data.json
|
||||||
|
openapcInputPath=/data/bip-affiliations/openapc-data.json
|
||||||
outputPath=/tmp/crossref-affiliations-output-v5
|
outputPath=/tmp/crossref-affiliations-output-v5
|
||||||
|
|
|
@ -9,6 +9,10 @@
|
||||||
<name>pubmedInputPath</name>
|
<name>pubmedInputPath</name>
|
||||||
<description>the path where to find the inferred affiliation relations from Pubmed</description>
|
<description>the path where to find the inferred affiliation relations from Pubmed</description>
|
||||||
</property>
|
</property>
|
||||||
|
<property>
|
||||||
|
<name>openapcInputPath</name>
|
||||||
|
<description>the path where to find the inferred affiliation relations from OpenAPC</description>
|
||||||
|
</property>
|
||||||
<property>
|
<property>
|
||||||
<name>outputPath</name>
|
<name>outputPath</name>
|
||||||
<description>the path where to store the actionset</description>
|
<description>the path where to store the actionset</description>
|
||||||
|
@ -102,6 +106,7 @@
|
||||||
</spark-opts>
|
</spark-opts>
|
||||||
<arg>--crossrefInputPath</arg><arg>${crossrefInputPath}</arg>
|
<arg>--crossrefInputPath</arg><arg>${crossrefInputPath}</arg>
|
||||||
<arg>--pubmedInputPath</arg><arg>${pubmedInputPath}</arg>
|
<arg>--pubmedInputPath</arg><arg>${pubmedInputPath}</arg>
|
||||||
|
<arg>--openapcInputPath</arg><arg>${openapcInputPath}</arg>
|
||||||
<arg>--outputPath</arg><arg>${outputPath}</arg>
|
<arg>--outputPath</arg><arg>${outputPath}</arg>
|
||||||
</spark>
|
</spark>
|
||||||
<ok to="End"/>
|
<ok to="End"/>
|
||||||
|
|
|
@ -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
|
||||||
|
}
|
||||||
|
]
|
|
@ -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
|
||||||
|
}
|
||||||
|
]
|
||||||
|
|
||||||
|
|
||||||
|
|
|
@ -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>
|
|
@ -0,0 +1,2 @@
|
||||||
|
#!/bin/bash
|
||||||
|
curl -L $1 | hdfs dfs -put - $2
|
|
@ -0,0 +1,82 @@
|
||||||
|
<workflow-app name="Transfomative Agreement Integration" xmlns="uri:oozie:workflow:0.5">
|
||||||
|
|
||||||
|
<global>
|
||||||
|
<job-tracker>${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>
|
|
@ -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;
|
|
@ -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%'
|
||||||
|
);
|
|
@ -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;
|
|
@ -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>
|
||||||
|
|
||||||
|
|
|
@ -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>
|
|
@ -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>
|
|
@ -78,10 +78,6 @@ public class PrepareAffiliationRelationsTest {
|
||||||
.getResource("/eu/dnetlib/dhp/actionmanager/bipaffiliations/doi_to_ror.json")
|
.getResource("/eu/dnetlib/dhp/actionmanager/bipaffiliations/doi_to_ror.json")
|
||||||
.getPath();
|
.getPath();
|
||||||
|
|
||||||
String pubmedAffiliationRelationsPath = getClass()
|
|
||||||
.getResource("/eu/dnetlib/dhp/actionmanager/bipaffiliations/doi_to_ror.json")
|
|
||||||
.getPath();
|
|
||||||
|
|
||||||
String outputPath = workingDir.toString() + "/actionSet";
|
String outputPath = workingDir.toString() + "/actionSet";
|
||||||
|
|
||||||
PrepareAffiliationRelations
|
PrepareAffiliationRelations
|
||||||
|
@ -89,7 +85,8 @@ public class PrepareAffiliationRelationsTest {
|
||||||
new String[] {
|
new String[] {
|
||||||
"-isSparkSessionManaged", Boolean.FALSE.toString(),
|
"-isSparkSessionManaged", Boolean.FALSE.toString(),
|
||||||
"-crossrefInputPath", crossrefAffiliationRelationPath,
|
"-crossrefInputPath", crossrefAffiliationRelationPath,
|
||||||
"-pubmedInputPath", pubmedAffiliationRelationsPath,
|
"-pubmedInputPath", crossrefAffiliationRelationPath,
|
||||||
|
"-openapcInputPath", crossrefAffiliationRelationPath,
|
||||||
"-outputPath", outputPath
|
"-outputPath", outputPath
|
||||||
});
|
});
|
||||||
|
|
||||||
|
@ -106,7 +103,7 @@ public class PrepareAffiliationRelationsTest {
|
||||||
// );
|
// );
|
||||||
// }
|
// }
|
||||||
// count the number of relations
|
// 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<Relation> dataset = spark.createDataset(tmp.rdd(), Encoders.bean(Relation.class));
|
||||||
dataset.createOrReplaceTempView("result");
|
dataset.createOrReplaceTempView("result");
|
||||||
|
@ -117,7 +114,7 @@ public class PrepareAffiliationRelationsTest {
|
||||||
// verify that we have equal number of bi-directional relations
|
// verify that we have equal number of bi-directional relations
|
||||||
Assertions
|
Assertions
|
||||||
.assertEquals(
|
.assertEquals(
|
||||||
20, execVerification
|
30, execVerification
|
||||||
.filter(
|
.filter(
|
||||||
"relClass='" + ModelConstants.HAS_AUTHOR_INSTITUTION + "'")
|
"relClass='" + ModelConstants.HAS_AUTHOR_INSTITUTION + "'")
|
||||||
.collectAsList()
|
.collectAsList()
|
||||||
|
@ -125,7 +122,7 @@ public class PrepareAffiliationRelationsTest {
|
||||||
|
|
||||||
Assertions
|
Assertions
|
||||||
.assertEquals(
|
.assertEquals(
|
||||||
20, execVerification
|
30, execVerification
|
||||||
.filter(
|
.filter(
|
||||||
"relClass='" + ModelConstants.IS_AUTHOR_INSTITUTION_OF + "'")
|
"relClass='" + ModelConstants.IS_AUTHOR_INSTITUTION_OF + "'")
|
||||||
.collectAsList()
|
.collectAsList()
|
||||||
|
|
|
@ -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()));
|
||||||
|
|
||||||
|
}
|
||||||
|
}
|
|
@ -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;
|
||||||
|
}
|
||||||
|
|
||||||
|
}
|
|
@ -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);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
}
|
|
@ -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));
|
||||||
|
|
||||||
|
}
|
||||||
|
|
||||||
|
}
|
|
@ -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;
|
||||||
|
}
|
||||||
|
|
||||||
|
}
|
|
@ -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);
|
||||||
|
}
|
||||||
|
|
||||||
|
}
|
|
@ -3,6 +3,7 @@ package eu.dnetlib.dhp.transformation;
|
||||||
|
|
||||||
import static eu.dnetlib.dhp.common.Constants.MDSTORE_DATA_PATH;
|
import static eu.dnetlib.dhp.common.Constants.MDSTORE_DATA_PATH;
|
||||||
import static org.junit.jupiter.api.Assertions.assertEquals;
|
import static org.junit.jupiter.api.Assertions.assertEquals;
|
||||||
|
import static org.junit.jupiter.api.Assertions.assertThrows;
|
||||||
|
|
||||||
import java.io.IOException;
|
import java.io.IOException;
|
||||||
import java.nio.file.Path;
|
import java.nio.file.Path;
|
||||||
|
@ -279,6 +280,19 @@ class TransformationJobTest extends AbstractVocabularyTest {
|
||||||
// TODO Create significant Assert
|
// TODO Create significant Assert
|
||||||
}
|
}
|
||||||
|
|
||||||
|
@Test
|
||||||
|
public void testInvalidXSLT() throws Exception{
|
||||||
|
final MetadataRecord mr = new MetadataRecord();
|
||||||
|
|
||||||
|
mr.setProvenance(new Provenance("openaire____::cnr_explora", "CNR ExploRA", "cnr_________"));
|
||||||
|
mr.setBody(IOUtils.toString(getClass().getResourceAsStream("/eu/dnetlib/dhp/transform/input_cnr_explora.xml")));
|
||||||
|
// We Load the XSLT transformation Rule from the classpath
|
||||||
|
final XSLTTransformationFunction tr = loadTransformationRule("/eu/dnetlib/dhp/transform/invalid.xslt");
|
||||||
|
|
||||||
|
assertThrows(RuntimeException.class,()->tr.call(mr));
|
||||||
|
|
||||||
|
}
|
||||||
|
|
||||||
private XSLTTransformationFunction loadTransformationRule(final String path) throws Exception {
|
private XSLTTransformationFunction loadTransformationRule(final String path) throws Exception {
|
||||||
final String trValue = IOUtils.toString(this.getClass().getResourceAsStream(path));
|
final String trValue = IOUtils.toString(this.getClass().getResourceAsStream(path));
|
||||||
final LongAccumulator la = new LongAccumulator();
|
final LongAccumulator la = new LongAccumulator();
|
||||||
|
|
File diff suppressed because it is too large
Load Diff
Binary file not shown.
|
@ -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>
|
|
@ -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>
|
|
@ -0,0 +1,185 @@
|
||||||
|
<xsl:stylesheet
|
||||||
|
xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
|
||||||
|
xmlns:oaire="http://namespace.openaire.eu/schema/oaire/"
|
||||||
|
xmlns:vocabulary="http://eu/dnetlib/transform/clean"
|
||||||
|
xmlns:dateCleaner="http://eu/dnetlib/transform/dateISO"
|
||||||
|
xmlns:oaf="http://namespace.openaire.eu/oaf"
|
||||||
|
xmlns:oai="http://www.openarchives.org/OAI/2.0/"
|
||||||
|
xmlns:datacite="http://datacite.org/schema/kernel-4"
|
||||||
|
xmlns:dri="http://www.driver-repository.eu/namespace/dri"
|
||||||
|
xmlns:xs="http://www.w3.org/2001/XMLSchema"
|
||||||
|
xmlns:dr="http://www.driver-repository.eu/namespace/dr"
|
||||||
|
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
|
||||||
|
xmlns:dc="http://purl.org/dc/elements/1.1/"
|
||||||
|
exclude-result-prefixes="xsl vocabulary dateCleaner" 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()" />
|
||||||
|
asdf;klamsdof'sdn &
|
||||||
|
<xsl:template match="/asdfasdf asdf&">
|
||||||
|
c:format'" />
|
||||||
|
</xsl:call-template>
|
||||||
|
<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( //dc:language, '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[not(starts-with(.,'info:cnr-pdr'))]" />
|
||||||
|
<xsl:with-param name="targetElement" select="'dc:relation'" />
|
||||||
|
</xsl:call-template>
|
||||||
|
|
||||||
|
<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>
|
||||||
|
|
||||||
|
<oaf:accessrights>
|
||||||
|
<xsl:value-of select="vocabulary:clean( //dc:rights, 'dnet:access_modes')" />
|
||||||
|
</oaf:accessrights>
|
||||||
|
|
||||||
|
<xsl:variable name="varCobjCategory" select="vocabulary:clean( //dc:type, 'dnet:publication_resource')" />
|
||||||
|
<xsl:variable name="varSuperType" select="vocabulary:clean( $varCobjCategory, 'dnet:result_typologies')" />
|
||||||
|
<dr:CobjCategory type="{$varSuperType}"><xsl:value-of select="$varCobjCategory" /></dr:CobjCategory>
|
||||||
|
|
||||||
|
|
||||||
|
<xsl:variable name="varRefereedConvt" select="for $i in (//dc:type, //dc:description, //oai:setSpec) return vocabulary:clean( normalize-space($i), 'dnet:review_levels')" />
|
||||||
|
<xsl:variable name="varRefereedIdntf" select="(//*[string(node-name(.)) = 'dc:identifier' and matches(lower-case(.), '(^|.*[\.\-_/\s\(\)%\d#])pre[\.\-_/\s\(\)%\d#]?prints?([\.\-_/\s\(\)%\d#].*)?$')][count(//dc:identifier) = 1]/'0002', //*[string(node-name(.)) = 'dc:identifier' and matches(lower-case(.), '(^|.*[\.\-_/\s\(\)%\d#])refereed([\.\-_/\s\(\)\d%\d#].*)?$')]/'0001', //*[string(node-name(.)) = 'dc:identifier' and matches(lower-case(.), '.*-peer-reviewed-(fulltext-)?article-.*')]/'0001')" />
|
||||||
|
<xsl:variable name="varRefereedSourc" select="//*[string(node-name(.)) = ('dc:source', 'dc:publisher') and matches(lower-case(.), '^(.*\s)?pre[\s\-_]*prints?([\s\.,].*)?$')]/'0002'" />
|
||||||
|
<xsl:variable name="varRefereedDescr" select="(//dc:description[matches(lower-case(.), '.*(this\s*book|this\s*volume|it)\s*constitutes\s*the\s*(thoroughly\s*)?refereed') or matches(lower-case(.), '.*peer[\.\-_/\s\(\)]?review\s*under\s*responsibility\s*of.*') or matches(lower-case(.), '(this|a)\s*(article|preprint)\s*(has\s*been\s*)?(peer[\-\s]*)?reviewed\s*and\s*recommended\s*by\s*peer[\-\s]*community')]/'0001', //dc:description[matches(., '^version\s*(préliminaire.*|preliminary.*|0$)')]/'0002')" />
|
||||||
|
<xsl:variable name="varRefereedTitle" select="(//dc:title[matches(lower-case(.), '.*\[.*peer[\s\-\._]*review\s*:.*\]\s*$')]/'0001', //dc:title[matches(lower-case(.), '.*\(\s*pre[\s\-\._]*prints?\s*\)\s*$')]/'0002')" />
|
||||||
|
<xsl:variable name="varRefereedSubjt" select="(//dc:subject[matches(lower-case(.), '^\s*refereed\s*$')][//oaf:datasourceprefix = 'narcis______']/'0001', //dc:subject[matches(lower-case(.), '^\s*no[nt].{0,3}refereed\s*$')][//oaf:datasourceprefix = 'narcis______']/'0002')" />
|
||||||
|
<xsl:variable name="varRefereed" select="($varRefereedConvt, $varRefereedIdntf, $varRefereedSourc, $varRefereedDescr, $varRefereedTitle, $varRefereedSubjt)" />
|
||||||
|
<xsl:choose>
|
||||||
|
<xsl:when test="count($varRefereed[. = '0001']) > 0">
|
||||||
|
<oaf:refereed>
|
||||||
|
<xsl:value-of select="'0001'" />
|
||||||
|
</oaf:refereed>
|
||||||
|
</xsl:when>
|
||||||
|
<xsl:when test="count($varRefereed[. = '0002']) > 0">
|
||||||
|
<oaf:refereed>
|
||||||
|
<xsl:value-of select="'0002'" />
|
||||||
|
</oaf:refereed>
|
||||||
|
</xsl:when>
|
||||||
|
</xsl:choose>
|
||||||
|
|
||||||
|
<oaf:dateAccepted>
|
||||||
|
<xsl:value-of select="dateCleaner:dateISO( //dc:date[1] )" />
|
||||||
|
</oaf:dateAccepted>
|
||||||
|
|
||||||
|
<xsl:if test="//dc:relation[starts-with(., 'http')] and //dc:rights[.='info:eu-repo/semantics/openAccess']">
|
||||||
|
<oaf:fulltext>
|
||||||
|
<xsl:value-of select="//dc:relation[starts-with(., 'http')]" />
|
||||||
|
</oaf:fulltext>
|
||||||
|
</xsl:if>
|
||||||
|
|
||||||
|
<oaf:hostedBy name="{$varOfficialName}" id="{$varDataSourceId}" />
|
||||||
|
<oaf:collectedFrom name="{$varOfficialName}" id="{$varDataSourceId}" />
|
||||||
|
|
||||||
|
<xsl:variable name="varKnownFileEndings" select="('.bmp', '.doc', '.docx', '.epub', '.flv', '.jpeg', '.jpg', '.m4v', '.mp4', '.mpg', '.odp', '.pdf', '.png', '.ppt', '.tiv', '.txt', '.xls', '.xlsx', '.zip')" />
|
||||||
|
<xsl:variable name="varIdDoi" select="distinct-values((//dc:identifier[starts-with(., '10.')][matches(., '(10[.][0-9]{4,}[^\s/>]*/[^\s>]+)')], //dc:identifier[starts-with(., 'http') and (contains(., '://dx.doi.org/10.') or contains(., '://doi.org/10.'))]/substring-after(., 'doi.org/'), //dc:identifier[starts-with(lower-case(.), 'doi:10.')]/substring-after(lower-case(.), 'doi:')))" />
|
||||||
|
<xsl:for-each select="$varIdDoi">
|
||||||
|
<oaf:identifier identifierType="doi">
|
||||||
|
<xsl:value-of select="." />
|
||||||
|
</oaf:identifier>
|
||||||
|
</xsl:for-each>
|
||||||
|
|
||||||
|
<xsl:variable name="varIdHdl" select="distinct-values(//dc:identifier[starts-with(., 'http') and contains(., '://hdl.handle.net/')]/substring-after(., 'hdl.handle.net/'))" />
|
||||||
|
<xsl:for-each select="$varIdHdl" >
|
||||||
|
<oaf:identifier identifierType="handle">
|
||||||
|
<xsl:value-of select="." />
|
||||||
|
</oaf:identifier>
|
||||||
|
</xsl:for-each>
|
||||||
|
|
||||||
|
<xsl:variable name="varIdUrn" select="distinct-values(//dc:identifier[starts-with(., 'urn:nbn:nl:') or starts-with(., 'URN:NBN:NL:')])" />
|
||||||
|
<xsl:for-each select="$varIdUrn">
|
||||||
|
<oaf:identifier identifierType="urn">
|
||||||
|
<xsl:value-of select="." />
|
||||||
|
</oaf:identifier>
|
||||||
|
</xsl:for-each>
|
||||||
|
|
||||||
|
<xsl:variable name="varOrigBaseUrl" select="//*[local-name() = 'about']/*[local-name() = 'provenance']//*[local-name() = 'originDescription' and not(./*[local-name() = 'originDescription'])]/*[local-name() = 'baseURL']" />
|
||||||
|
<xsl:variable name="varIdLdpg" select="distinct-values(//dc:identifier[(contains(substring-after(., '://'), '/') and contains($varOrigBaseUrl, substring-before(substring-after(., '://'), '/'))) or (contains(substring-after(., '://'), ':') and contains($varOrigBaseUrl, substring-before(substring-after(., '://'), ':')))][not(replace(lower-case(.), '.*(\.[a-z]*)$', '$1') = $varKnownFileEndings)])" />
|
||||||
|
<xsl:for-each select="$varIdLdpg">
|
||||||
|
<oaf:identifier identifierType="landingPage">
|
||||||
|
<xsl:value-of select="." />
|
||||||
|
</oaf:identifier>
|
||||||
|
</xsl:for-each>
|
||||||
|
|
||||||
|
<xsl:variable name="varIdUrl" select="distinct-values(//dc:identifier[starts-with(., 'http')][not(contains(., '://dx.doi.org/') or contains(., '://doi.org/') or contains(., '://hdl.handle.net/'))][count(index-of($varIdLdpg, .)) = 0])" />
|
||||||
|
<xsl:for-each select="$varIdUrl">
|
||||||
|
<oaf:identifier identifierType="url">
|
||||||
|
<xsl:value-of select="." />
|
||||||
|
</oaf:identifier>
|
||||||
|
</xsl:for-each>
|
||||||
|
|
||||||
|
<xsl:for-each select="//oai:setSpec">
|
||||||
|
<xsl:variable name="rorDsId" select="vocabulary:clean(., 'cnr:institutes')" />
|
||||||
|
<xsl:if test="contains($rorDsId, '/ror.org/')">
|
||||||
|
<oaf:relation relType="resultOrganization" subRelType="affiliation" relClass="hasAuthorInstitution">
|
||||||
|
<xsl:value-of select="concat('ror_________::', $rorDsId)" />
|
||||||
|
</oaf:relation>
|
||||||
|
</xsl:if>
|
||||||
|
</xsl:for-each>
|
||||||
|
|
||||||
|
</metadata>
|
||||||
|
|
||||||
|
<xsl:copy-of select="//*[local-name() = 'about']" />
|
||||||
|
</record>
|
||||||
|
</xsl:template>
|
||||||
|
|
||||||
|
|
||||||
|
<xsl:template name="allElements">
|
||||||
|
<xsl:param name="sourceElement" />
|
||||||
|
<xsl:param name="targetElement" />
|
||||||
|
|
||||||
|
<xsl:for-each select="$sourceElement">
|
||||||
|
<xsl:element name="{$targetElement}">
|
||||||
|
<xsl:value-of select="normalize-space(.)" />
|
||||||
|
</xsl:element>
|
||||||
|
</xsl:for-each>
|
||||||
|
</xsl:template>
|
||||||
|
|
||||||
|
<xsl:template match="//*[local-name() = 'header']">
|
||||||
|
<xsl:copy>
|
||||||
|
<xsl:apply-templates select="node()|@*" />
|
||||||
|
<xsl:element name="dr:dateOfTransformation">
|
||||||
|
<xsl:value-of select="$transDate" />
|
||||||
|
</xsl:element>
|
||||||
|
</xsl:copy>
|
||||||
|
</xsl:template>
|
||||||
|
|
||||||
|
<xsl:template match="node()|@*">
|
||||||
|
<xsl:copy>
|
||||||
|
<xsl:apply-templates select="node()|@*" />
|
||||||
|
</xsl:copy>
|
||||||
|
</xsl:template>
|
||||||
|
|
||||||
|
</xsl:stylesheet>
|
|
@ -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 @=@ https://ror.org/0263zy895 @=@ SCITEC - Istituto di Scienze e Tecnologie Chimiche \"Giulio Natta\"
|
||||||
cnr:institutes @=@ __CDS133__ @=@ CDS133
|
cnr:institutes @=@ __CDS133__ @=@ CDS133
|
||||||
cnr:institutes @=@ __CDS133__ @=@ STEMS - Istituto di Scienze e Tecnologie per l'Energia e la Mobilità Sostenibili
|
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
|
||||||
|
|
|
@ -1210,4 +1210,29 @@ cnr:institutes @=@ cnr:institutes @=@ __CDS130__ @=@ __CDS130__
|
||||||
cnr:institutes @=@ cnr:institutes @=@ __CDS131__ @=@ __CDS131__
|
cnr:institutes @=@ cnr:institutes @=@ __CDS131__ @=@ __CDS131__
|
||||||
cnr:institutes @=@ cnr:institutes @=@ https://ror.org/0263zy895 @=@ https://ror.org/0263zy895
|
cnr:institutes @=@ cnr:institutes @=@ https://ror.org/0263zy895 @=@ https://ror.org/0263zy895
|
||||||
cnr:institutes @=@ cnr:institutes @=@ __CDS133__ @=@ __CDS133__
|
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
|
|
@ -4,6 +4,7 @@ package eu.dnetlib.dhp.oa.dedup;
|
||||||
import java.util.*;
|
import java.util.*;
|
||||||
import java.util.stream.Stream;
|
import java.util.stream.Stream;
|
||||||
|
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.utils.MergeUtils;
|
||||||
import org.apache.commons.beanutils.BeanUtils;
|
import org.apache.commons.beanutils.BeanUtils;
|
||||||
import org.apache.commons.lang3.StringUtils;
|
import org.apache.commons.lang3.StringUtils;
|
||||||
import org.apache.spark.api.java.function.FlatMapFunction;
|
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.dedup.model.Identifier;
|
||||||
import eu.dnetlib.dhp.oa.merge.AuthorMerger;
|
import eu.dnetlib.dhp.oa.merge.AuthorMerger;
|
||||||
import eu.dnetlib.dhp.schema.common.ModelSupport;
|
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.Author;
|
||||||
import eu.dnetlib.dhp.schema.oaf.DataInfo;
|
import eu.dnetlib.dhp.schema.oaf.DataInfo;
|
||||||
import eu.dnetlib.dhp.schema.oaf.OafEntity;
|
import eu.dnetlib.dhp.schema.oaf.OafEntity;
|
||||||
|
@ -172,7 +174,7 @@ public class DedupRecordFactory {
|
||||||
entity = swap;
|
entity = swap;
|
||||||
}
|
}
|
||||||
|
|
||||||
entity.mergeFrom(duplicate);
|
entity = MergeUtils.checkedMerge(entity, duplicate);
|
||||||
|
|
||||||
if (ModelSupport.isSubClass(duplicate, Result.class)) {
|
if (ModelSupport.isSubClass(duplicate, Result.class)) {
|
||||||
Result re = (Result) entity;
|
Result re = (Result) entity;
|
||||||
|
|
|
@ -3,6 +3,7 @@ package eu.dnetlib.dhp.oa.dedup;
|
||||||
|
|
||||||
import static org.apache.spark.sql.functions.col;
|
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.commons.io.IOUtils;
|
||||||
import org.apache.spark.SparkConf;
|
import org.apache.spark.SparkConf;
|
||||||
import org.apache.spark.api.java.function.MapFunction;
|
import org.apache.spark.api.java.function.MapFunction;
|
||||||
|
@ -127,10 +128,8 @@ public class SparkPropagateRelation extends AbstractSparkAction {
|
||||||
(MapFunction<Relation, String>) r -> String
|
(MapFunction<Relation, String>) r -> String
|
||||||
.join(" ", r.getSource(), r.getTarget(), r.getRelType(), r.getSubRelType(), r.getRelClass()),
|
.join(" ", r.getSource(), r.getTarget(), r.getRelType(), r.getSubRelType(), r.getRelClass()),
|
||||||
Encoders.STRING())
|
Encoders.STRING())
|
||||||
.reduceGroups((ReduceFunction<Relation>) (b, a) -> {
|
.reduceGroups((ReduceFunction<Relation>) MergeUtils::mergeRelation
|
||||||
b.mergeFrom(a);
|
)
|
||||||
return b;
|
|
||||||
})
|
|
||||||
.map((MapFunction<Tuple2<String, Relation>, Relation>) Tuple2::_2, REL_BEAN_ENC);
|
.map((MapFunction<Tuple2<String, Relation>, Relation>) Tuple2::_2, REL_BEAN_ENC);
|
||||||
|
|
||||||
final String outputRelationPath = graphOutputPath + "/relation";
|
final String outputRelationPath = graphOutputPath + "/relation";
|
||||||
|
|
|
@ -3,17 +3,18 @@ package eu.dnetlib.doiboost
|
||||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser
|
import eu.dnetlib.dhp.application.ArgumentApplicationParser
|
||||||
import eu.dnetlib.dhp.oa.merge.AuthorMerger
|
import eu.dnetlib.dhp.oa.merge.AuthorMerger
|
||||||
import eu.dnetlib.dhp.schema.common.ModelConstants
|
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.dhp.schema.oaf.{Organization, Publication, Relation, Dataset => OafDataset}
|
||||||
import eu.dnetlib.doiboost.mag.ConversionUtil
|
import eu.dnetlib.doiboost.mag.ConversionUtil
|
||||||
import org.apache.commons.io.IOUtils
|
import org.apache.commons.io.IOUtils
|
||||||
import org.apache.spark.SparkConf
|
import org.apache.spark.SparkConf
|
||||||
import org.apache.spark.sql.expressions.Aggregator
|
|
||||||
import org.apache.spark.sql.functions.col
|
import org.apache.spark.sql.functions.col
|
||||||
import org.apache.spark.sql._
|
import org.apache.spark.sql._
|
||||||
import org.json4s.DefaultFormats
|
import org.json4s.DefaultFormats
|
||||||
import org.json4s.JsonAST.{JField, JObject, JString}
|
import org.json4s.JsonAST.{JField, JObject, JString}
|
||||||
import org.json4s.jackson.JsonMethods.parse
|
import org.json4s.jackson.JsonMethods.parse
|
||||||
import org.slf4j.{Logger, LoggerFactory}
|
import org.slf4j.{Logger, LoggerFactory}
|
||||||
|
|
||||||
import scala.collection.JavaConverters._
|
import scala.collection.JavaConverters._
|
||||||
|
|
||||||
object SparkGenerateDoiBoost {
|
object SparkGenerateDoiBoost {
|
||||||
|
@ -78,8 +79,10 @@ object SparkGenerateDoiBoost {
|
||||||
if (item._2 != null) {
|
if (item._2 != null) {
|
||||||
val otherPub = item._2._2
|
val otherPub = item._2._2
|
||||||
if (otherPub != null) {
|
if (otherPub != null) {
|
||||||
crossrefPub.mergeFrom(otherPub)
|
val mergedAuthor = AuthorMerger.mergeAuthor(crossrefPub.getAuthor, otherPub.getAuthor)
|
||||||
crossrefPub.setAuthor(AuthorMerger.mergeAuthor(crossrefPub.getAuthor, otherPub.getAuthor))
|
val res = MergeUtils.mergePublication(crossrefPub, otherPub)
|
||||||
|
res.setAuthor(mergedAuthor);
|
||||||
|
return res
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
crossrefPub
|
crossrefPub
|
||||||
|
@ -130,14 +133,13 @@ object SparkGenerateDoiBoost {
|
||||||
// So we have to merge
|
// So we have to merge
|
||||||
val b1 = left._2
|
val b1 = left._2
|
||||||
val b2 = right._2
|
val b2 = right._2
|
||||||
b1.mergeFrom(b2)
|
|
||||||
b1.mergeOAFDataInfo(b2)
|
|
||||||
val authors = AuthorMerger.mergeAuthor(b1.getAuthor, b2.getAuthor)
|
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)
|
if (b2.getId != null && b2.getId.nonEmpty)
|
||||||
b1.setId(b2.getId)
|
merged.setId(b2.getId)
|
||||||
//Return publication Merged
|
//Return publication Merged
|
||||||
(b1.getId, b1)
|
(merged.getId, merged)
|
||||||
}
|
}
|
||||||
} else {
|
} else {
|
||||||
// Left is Null so we return right
|
// Left is Null so we return right
|
||||||
|
|
|
@ -1,8 +1,8 @@
|
||||||
package eu.dnetlib.doiboost.mag
|
package eu.dnetlib.doiboost.mag
|
||||||
|
|
||||||
import eu.dnetlib.dhp.schema.common.ModelConstants
|
import eu.dnetlib.dhp.schema.common.ModelConstants
|
||||||
import eu.dnetlib.dhp.schema.oaf.utils.IdentifierFactory
|
import eu.dnetlib.dhp.schema.oaf.utils.{IdentifierFactory, MergeUtils}
|
||||||
import eu.dnetlib.dhp.schema.oaf.{Instance, Journal, Publication, StructuredProperty, Subject}
|
import eu.dnetlib.dhp.schema.oaf.{Instance, Journal, Publication, Subject}
|
||||||
import eu.dnetlib.doiboost.DoiBoostMappingUtil
|
import eu.dnetlib.doiboost.DoiBoostMappingUtil
|
||||||
import eu.dnetlib.doiboost.DoiBoostMappingUtil._
|
import eu.dnetlib.doiboost.DoiBoostMappingUtil._
|
||||||
import org.json4s
|
import org.json4s
|
||||||
|
@ -142,8 +142,7 @@ case object ConversionUtil {
|
||||||
|
|
||||||
def mergePublication(a: Publication, b: Publication): Publication = {
|
def mergePublication(a: Publication, b: Publication): Publication = {
|
||||||
if ((a != null) && (b != null)) {
|
if ((a != null) && (b != null)) {
|
||||||
a.mergeFrom(b)
|
MergeUtils.mergePublication(a, b)
|
||||||
a
|
|
||||||
} else {
|
} else {
|
||||||
if (a == null) b else a
|
if (a == null) b else a
|
||||||
}
|
}
|
||||||
|
|
|
@ -0,0 +1,39 @@
|
||||||
|
|
||||||
|
package eu.dnetlib.dhp.bulktag.actions;
|
||||||
|
|
||||||
|
import java.io.Serializable;
|
||||||
|
import java.util.List;
|
||||||
|
|
||||||
|
/**
|
||||||
|
* @author miriam.baglioni
|
||||||
|
* @Date 22/01/24
|
||||||
|
*/
|
||||||
|
public class Action implements Serializable {
|
||||||
|
private String clazz;
|
||||||
|
private String method;
|
||||||
|
private List<Parameters> params;
|
||||||
|
|
||||||
|
public String getClazz() {
|
||||||
|
return clazz;
|
||||||
|
}
|
||||||
|
|
||||||
|
public void setClazz(String clazz) {
|
||||||
|
this.clazz = clazz;
|
||||||
|
}
|
||||||
|
|
||||||
|
public String getMethod() {
|
||||||
|
return method;
|
||||||
|
}
|
||||||
|
|
||||||
|
public void setMethod(String method) {
|
||||||
|
this.method = method;
|
||||||
|
}
|
||||||
|
|
||||||
|
public List<Parameters> getParams() {
|
||||||
|
return params;
|
||||||
|
}
|
||||||
|
|
||||||
|
public void setParams(List<Parameters> params) {
|
||||||
|
this.params = params;
|
||||||
|
}
|
||||||
|
}
|
|
@ -0,0 +1,45 @@
|
||||||
|
|
||||||
|
package eu.dnetlib.dhp.bulktag.actions;
|
||||||
|
|
||||||
|
import java.io.Serializable;
|
||||||
|
|
||||||
|
/**
|
||||||
|
* @author miriam.baglioni
|
||||||
|
* @Date 19/01/24
|
||||||
|
*/
|
||||||
|
public class ExecSubstringAction implements Serializable {
|
||||||
|
|
||||||
|
private String value;
|
||||||
|
private String from;
|
||||||
|
private String to;
|
||||||
|
|
||||||
|
public String getValue() {
|
||||||
|
return value;
|
||||||
|
}
|
||||||
|
|
||||||
|
public void setValue(String value) {
|
||||||
|
this.value = value;
|
||||||
|
}
|
||||||
|
|
||||||
|
public String getFrom() {
|
||||||
|
return from;
|
||||||
|
}
|
||||||
|
|
||||||
|
public void setFrom(String from) {
|
||||||
|
this.from = from;
|
||||||
|
}
|
||||||
|
|
||||||
|
public String getTo() {
|
||||||
|
return to;
|
||||||
|
}
|
||||||
|
|
||||||
|
public void setTo(String to) {
|
||||||
|
this.to = to;
|
||||||
|
}
|
||||||
|
|
||||||
|
public String execSubstring() {
|
||||||
|
|
||||||
|
return this.value.substring(Integer.valueOf(this.from), Integer.valueOf(this.to));
|
||||||
|
|
||||||
|
}
|
||||||
|
}
|
|
@ -0,0 +1,30 @@
|
||||||
|
|
||||||
|
package eu.dnetlib.dhp.bulktag.actions;
|
||||||
|
|
||||||
|
import java.io.Serializable;
|
||||||
|
|
||||||
|
/**
|
||||||
|
* @author miriam.baglioni
|
||||||
|
* @Date 22/01/24
|
||||||
|
*/
|
||||||
|
public class MapModel implements Serializable {
|
||||||
|
|
||||||
|
private String path;
|
||||||
|
private Action action;
|
||||||
|
|
||||||
|
public String getPath() {
|
||||||
|
return path;
|
||||||
|
}
|
||||||
|
|
||||||
|
public void setPath(String path) {
|
||||||
|
this.path = path;
|
||||||
|
}
|
||||||
|
|
||||||
|
public Action getAction() {
|
||||||
|
return action;
|
||||||
|
}
|
||||||
|
|
||||||
|
public void setAction(Action action) {
|
||||||
|
this.action = action;
|
||||||
|
}
|
||||||
|
}
|
|
@ -0,0 +1,29 @@
|
||||||
|
|
||||||
|
package eu.dnetlib.dhp.bulktag.actions;
|
||||||
|
|
||||||
|
import java.io.Serializable;
|
||||||
|
|
||||||
|
/**
|
||||||
|
* @author miriam.baglioni
|
||||||
|
* @Date 22/01/24
|
||||||
|
*/
|
||||||
|
public class Parameters implements Serializable {
|
||||||
|
private String paramName;
|
||||||
|
private String paramValue;
|
||||||
|
|
||||||
|
public String getParamName() {
|
||||||
|
return paramName;
|
||||||
|
}
|
||||||
|
|
||||||
|
public void setParamName(String paramName) {
|
||||||
|
this.paramName = paramName;
|
||||||
|
}
|
||||||
|
|
||||||
|
public String getParamValue() {
|
||||||
|
return paramValue;
|
||||||
|
}
|
||||||
|
|
||||||
|
public void setParamValue(String paramValue) {
|
||||||
|
this.paramValue = paramValue;
|
||||||
|
}
|
||||||
|
}
|
|
@ -4,7 +4,9 @@ package eu.dnetlib.dhp.bulktag.community;
|
||||||
import java.io.Serializable;
|
import java.io.Serializable;
|
||||||
import java.util.HashMap;
|
import java.util.HashMap;
|
||||||
|
|
||||||
public class ProtoMap extends HashMap<String, String> implements Serializable {
|
import eu.dnetlib.dhp.bulktag.actions.MapModel;
|
||||||
|
|
||||||
|
public class ProtoMap extends HashMap<String, MapModel> implements Serializable {
|
||||||
|
|
||||||
public ProtoMap() {
|
public ProtoMap() {
|
||||||
super();
|
super();
|
||||||
|
|
|
@ -5,6 +5,8 @@ import static eu.dnetlib.dhp.bulktag.community.TaggingConstants.*;
|
||||||
import static eu.dnetlib.dhp.schema.common.ModelConstants.*;
|
import static eu.dnetlib.dhp.schema.common.ModelConstants.*;
|
||||||
|
|
||||||
import java.io.Serializable;
|
import java.io.Serializable;
|
||||||
|
import java.lang.reflect.InvocationTargetException;
|
||||||
|
import java.lang.reflect.Method;
|
||||||
import java.util.*;
|
import java.util.*;
|
||||||
import java.util.stream.Collectors;
|
import java.util.stream.Collectors;
|
||||||
|
|
||||||
|
@ -15,7 +17,10 @@ import org.slf4j.LoggerFactory;
|
||||||
import com.google.gson.Gson;
|
import com.google.gson.Gson;
|
||||||
import com.jayway.jsonpath.DocumentContext;
|
import com.jayway.jsonpath.DocumentContext;
|
||||||
import com.jayway.jsonpath.JsonPath;
|
import com.jayway.jsonpath.JsonPath;
|
||||||
|
import com.jayway.jsonpath.PathNotFoundException;
|
||||||
|
|
||||||
|
import eu.dnetlib.dhp.bulktag.actions.MapModel;
|
||||||
|
import eu.dnetlib.dhp.bulktag.actions.Parameters;
|
||||||
import eu.dnetlib.dhp.bulktag.eosc.EoscIFTag;
|
import eu.dnetlib.dhp.bulktag.eosc.EoscIFTag;
|
||||||
import eu.dnetlib.dhp.schema.oaf.*;
|
import eu.dnetlib.dhp.schema.oaf.*;
|
||||||
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
|
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
|
||||||
|
@ -35,27 +40,59 @@ public class ResultTagger implements Serializable {
|
||||||
return (tmp != clist.size());
|
return (tmp != clist.size());
|
||||||
}
|
}
|
||||||
|
|
||||||
private Map<String, List<String>> getParamMap(final Result result, Map<String, String> params) {
|
private Map<String, List<String>> getParamMap(final Result result, Map<String, MapModel> params)
|
||||||
|
throws NoSuchMethodException, InvocationTargetException {
|
||||||
Map<String, List<String>> param = new HashMap<>();
|
Map<String, List<String>> param = new HashMap<>();
|
||||||
String json = new Gson().toJson(result, Result.class);
|
String json = new Gson().toJson(result, Result.class);
|
||||||
DocumentContext jsonContext = JsonPath.parse(json);
|
DocumentContext jsonContext = JsonPath.parse(json);
|
||||||
|
|
||||||
if (params == null) {
|
if (params == null) {
|
||||||
params = new HashMap<>();
|
params = new HashMap<>();
|
||||||
}
|
}
|
||||||
for (String key : params.keySet()) {
|
for (String key : params.keySet()) {
|
||||||
|
MapModel mapModel = params.get(key);
|
||||||
|
|
||||||
try {
|
try {
|
||||||
param.put(key, jsonContext.read(params.get(key)));
|
String path = mapModel.getPath();
|
||||||
} catch (com.jayway.jsonpath.PathNotFoundException e) {
|
Object obj = jsonContext.read(path);
|
||||||
|
List<String> pathValue;
|
||||||
|
if (obj instanceof java.lang.String)
|
||||||
|
pathValue = Arrays.asList((String) obj);
|
||||||
|
else
|
||||||
|
pathValue = (List<String>) obj;
|
||||||
|
if (Optional.ofNullable(mapModel.getAction()).isPresent()) {
|
||||||
|
Class<?> c = Class.forName(mapModel.getAction().getClazz());
|
||||||
|
Object class_instance = c.newInstance();
|
||||||
|
Method setField = c.getMethod("setValue", String.class);
|
||||||
|
setField.invoke(class_instance, pathValue.get(0));
|
||||||
|
for (Parameters p : mapModel.getAction().getParams()) {
|
||||||
|
setField = c.getMethod("set" + p.getParamName(), String.class);
|
||||||
|
setField.invoke(class_instance, p.getParamValue());
|
||||||
|
}
|
||||||
|
|
||||||
|
param
|
||||||
|
.put(
|
||||||
|
key, Arrays
|
||||||
|
.asList((String) c.getMethod(mapModel.getAction().getMethod()).invoke(class_instance)));
|
||||||
|
|
||||||
|
}
|
||||||
|
|
||||||
|
else {
|
||||||
|
param.put(key, pathValue);
|
||||||
|
}
|
||||||
|
|
||||||
|
} catch (PathNotFoundException | ClassNotFoundException | InstantiationException
|
||||||
|
| IllegalAccessException e) {
|
||||||
param.put(key, new ArrayList<>());
|
param.put(key, new ArrayList<>());
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
return param;
|
return param;
|
||||||
|
|
||||||
}
|
}
|
||||||
|
|
||||||
public <R extends Result> R enrichContextCriteria(
|
public <R extends Result> R enrichContextCriteria(
|
||||||
final R result, final CommunityConfiguration conf, final Map<String, String> criteria) {
|
final R result, final CommunityConfiguration conf, final Map<String, MapModel> criteria)
|
||||||
|
throws InvocationTargetException, NoSuchMethodException {
|
||||||
final Map<String, List<String>> param = getParamMap(result, criteria);
|
|
||||||
|
|
||||||
// Verify if the entity is deletedbyinference. In case verify if to clean the context list
|
// Verify if the entity is deletedbyinference. In case verify if to clean the context list
|
||||||
// from all the zenodo communities
|
// from all the zenodo communities
|
||||||
|
@ -64,6 +101,8 @@ public class ResultTagger implements Serializable {
|
||||||
return result;
|
return result;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
final Map<String, List<String>> param = getParamMap(result, criteria);
|
||||||
|
|
||||||
// Execute the EOSCTag for the services
|
// Execute the EOSCTag for the services
|
||||||
switch (result.getResulttype().getClassid()) {
|
switch (result.getResulttype().getClassid()) {
|
||||||
case PUBLICATION_RESULTTYPE_CLASSID:
|
case PUBLICATION_RESULTTYPE_CLASSID:
|
||||||
|
|
|
@ -0,0 +1,34 @@
|
||||||
|
|
||||||
|
package eu.dnetlib.dhp.bulktag.criteria;
|
||||||
|
|
||||||
|
import java.io.Serializable;
|
||||||
|
|
||||||
|
/**
|
||||||
|
* @author miriam.baglioni
|
||||||
|
* @Date 11/11/22
|
||||||
|
*/
|
||||||
|
@VerbClass("greater_than")
|
||||||
|
public class GreatThanVerb implements Selection, Serializable {
|
||||||
|
|
||||||
|
private String param;
|
||||||
|
|
||||||
|
public GreatThanVerb() {
|
||||||
|
}
|
||||||
|
|
||||||
|
public GreatThanVerb(final String param) {
|
||||||
|
this.param = param;
|
||||||
|
}
|
||||||
|
|
||||||
|
@Override
|
||||||
|
public boolean apply(String value) {
|
||||||
|
return value.compareTo(param) > 0;
|
||||||
|
}
|
||||||
|
|
||||||
|
public String getParam() {
|
||||||
|
return param;
|
||||||
|
}
|
||||||
|
|
||||||
|
public void setParam(String param) {
|
||||||
|
this.param = param;
|
||||||
|
}
|
||||||
|
}
|
|
@ -0,0 +1,34 @@
|
||||||
|
|
||||||
|
package eu.dnetlib.dhp.bulktag.criteria;
|
||||||
|
|
||||||
|
import java.io.Serializable;
|
||||||
|
|
||||||
|
/**
|
||||||
|
* @author miriam.baglioni
|
||||||
|
* @Date 11/11/22
|
||||||
|
*/
|
||||||
|
@VerbClass("lesser_than")
|
||||||
|
public class LessThanVerb implements Selection, Serializable {
|
||||||
|
|
||||||
|
private String param;
|
||||||
|
|
||||||
|
public LessThanVerb() {
|
||||||
|
}
|
||||||
|
|
||||||
|
public LessThanVerb(final String param) {
|
||||||
|
this.param = param;
|
||||||
|
}
|
||||||
|
|
||||||
|
@Override
|
||||||
|
public boolean apply(String value) {
|
||||||
|
return value.compareTo(param) < 0;
|
||||||
|
}
|
||||||
|
|
||||||
|
public String getParam() {
|
||||||
|
return param;
|
||||||
|
}
|
||||||
|
|
||||||
|
public void setParam(String param) {
|
||||||
|
this.param = param;
|
||||||
|
}
|
||||||
|
}
|
|
@ -149,7 +149,7 @@ public class SparkResultToCommunityFromOrganizationJob {
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
// res.setContext(propagatedContexts);
|
// res.setContext(propagatedContexts);
|
||||||
// ret.mergeFrom(res);
|
// return MergeUtils.mergeResult(ret, res);
|
||||||
}
|
}
|
||||||
return ret;
|
return ret;
|
||||||
};
|
};
|
||||||
|
|
|
@ -13,6 +13,7 @@ import java.util.List;
|
||||||
import java.util.Optional;
|
import java.util.Optional;
|
||||||
import java.util.stream.Collectors;
|
import java.util.stream.Collectors;
|
||||||
|
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.utils.MergeUtils;
|
||||||
import org.apache.commons.io.IOUtils;
|
import org.apache.commons.io.IOUtils;
|
||||||
import org.apache.spark.SparkConf;
|
import org.apache.spark.SparkConf;
|
||||||
import org.apache.spark.api.java.function.MapFunction;
|
import org.apache.spark.api.java.function.MapFunction;
|
||||||
|
@ -24,8 +25,6 @@ import org.slf4j.Logger;
|
||||||
import org.slf4j.LoggerFactory;
|
import org.slf4j.LoggerFactory;
|
||||||
|
|
||||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
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.ModelConstants;
|
||||||
import eu.dnetlib.dhp.schema.common.ModelSupport;
|
import eu.dnetlib.dhp.schema.common.ModelSupport;
|
||||||
import eu.dnetlib.dhp.schema.oaf.Context;
|
import eu.dnetlib.dhp.schema.oaf.Context;
|
||||||
|
@ -162,7 +161,7 @@ public class SparkResultToCommunityFromProject implements Serializable {
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
res.setContext(propagatedContexts);
|
res.setContext(propagatedContexts);
|
||||||
ret.mergeFrom(res);
|
return MergeUtils.checkedMerge(ret, res);
|
||||||
}
|
}
|
||||||
return ret;
|
return ret;
|
||||||
};
|
};
|
||||||
|
|
|
@ -13,6 +13,7 @@ import org.apache.commons.io.IOUtils;
|
||||||
import org.apache.spark.SparkConf;
|
import org.apache.spark.SparkConf;
|
||||||
import org.apache.spark.api.java.JavaRDD;
|
import org.apache.spark.api.java.JavaRDD;
|
||||||
import org.apache.spark.api.java.JavaSparkContext;
|
import org.apache.spark.api.java.JavaSparkContext;
|
||||||
|
import org.apache.spark.api.java.function.FilterFunction;
|
||||||
import org.apache.spark.sql.Encoders;
|
import org.apache.spark.sql.Encoders;
|
||||||
import org.apache.spark.sql.Row;
|
import org.apache.spark.sql.Row;
|
||||||
import org.apache.spark.sql.SparkSession;
|
import org.apache.spark.sql.SparkSession;
|
||||||
|
@ -31,18 +32,26 @@ public class BulkTagJobTest {
|
||||||
|
|
||||||
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
|
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
|
||||||
|
|
||||||
public static final String pathMap = "{ \"author\" : \"$['author'][*]['fullname']\","
|
public static final String pathMap = "{\"author\":{\"path\":\"$['author'][*]['fullname']\"}," +
|
||||||
+ " \"title\" : \"$['title'][*]['value']\","
|
" \"title\":{\"path\":\"$['title'][*]['value']\"}, " +
|
||||||
+ " \"orcid\" : \"$['author'][*]['pid'][*][?(@['key']=='ORCID')]['value']\","
|
" \"orcid\":{\"path\":\"$['author'][*]['pid'][*][?(@['qualifier']['classid']=='orcid')]['value']\"} , " +
|
||||||
+ " \"contributor\" : \"$['contributor'][*]['value']\","
|
" \"orcid_pending\":{\"path\":\"$['author'][*]['pid'][*][?(@['qualifier']['classid']=='orcid_pending')]['value']\"} ,"
|
||||||
+ " \"description\" : \"$['description'][*]['value']\", "
|
+
|
||||||
+ " \"subject\" :\"$['subject'][*]['value']\" , " +
|
"\"contributor\" : {\"path\":\"$['contributor'][*]['value']\"}," +
|
||||||
"\"fos\" : \"$['subject'][?(@['qualifier']['classid']=='FOS')].value\"," +
|
" \"description\" : {\"path\":\"$['description'][*]['value']\"}," +
|
||||||
"\"sdg\" : \"$['subject'][?(@['qualifier']['classid']=='SDG')].value\"," +
|
" \"subject\" :{\"path\":\"$['subject'][*]['value']\"}, " +
|
||||||
"\"hostedby\" : \"$['instance'][*]['hostedby']['key']\" , " +
|
" \"fos\" : {\"path\":\"$['subject'][?(@['qualifier']['classid']=='FOS')].value\"} , " +
|
||||||
"\"collectedfrom\" : \"$['instance'][*]['collectedfrom']['key']\"," +
|
"\"sdg\" : {\"path\":\"$['subject'][?(@['qualifier']['classid']=='SDG')].value\"}," +
|
||||||
"\"publisher\":\"$['publisher'].value\"," +
|
"\"journal\":{\"path\":\"$['journal'].name\"}," +
|
||||||
"\"publicationyear\":\"$['dateofacceptance'].value\"} ";
|
"\"hostedby\":{\"path\":\"$['instance'][*]['hostedby']['key']\"}," +
|
||||||
|
"\"collectedfrom\":{\"path\":\"$['instance'][*]['collectedfrom']['key']\"}," +
|
||||||
|
"\"publisher\":{\"path\":\"$['publisher'].value\"}," +
|
||||||
|
"\"publicationyear\":{\"path\":\"$['dateofacceptance'].value\", " +
|
||||||
|
" \"action\":{\"clazz\":\"eu.dnetlib.dhp.bulktag.actions.ExecSubstringAction\"," +
|
||||||
|
"\"method\":\"execSubstring\"," +
|
||||||
|
"\"params\":[" +
|
||||||
|
"{\"paramName\":\"From\", \"paramValue\":0}, " +
|
||||||
|
"{\"paramName\":\"To\",\"paramValue\":4}]}}}";
|
||||||
|
|
||||||
private static SparkSession spark;
|
private static SparkSession spark;
|
||||||
|
|
||||||
|
@ -1600,4 +1609,94 @@ public class BulkTagJobTest {
|
||||||
Assertions.assertEquals(0, spark.sql(query).count());
|
Assertions.assertEquals(0, spark.sql(query).count());
|
||||||
}
|
}
|
||||||
|
|
||||||
|
@Test
|
||||||
|
void pubdateTest() throws Exception {
|
||||||
|
|
||||||
|
final String pathMap = BulkTagJobTest.pathMap;
|
||||||
|
SparkBulkTagJob
|
||||||
|
.main(
|
||||||
|
new String[] {
|
||||||
|
"-isSparkSessionManaged", Boolean.FALSE.toString(),
|
||||||
|
"-sourcePath",
|
||||||
|
getClass().getResource("/eu/dnetlib/dhp/bulktag/sample/dataset/publicationyear/").getPath(),
|
||||||
|
"-taggingConf",
|
||||||
|
IOUtils
|
||||||
|
.toString(
|
||||||
|
BulkTagJobTest.class
|
||||||
|
.getResourceAsStream(
|
||||||
|
"/eu/dnetlib/dhp/bulktag/communityconfiguration/tagging_conf_publicationdate.xml")),
|
||||||
|
"-outputPath", workingDir.toString() + "/",
|
||||||
|
"-pathMap", pathMap
|
||||||
|
});
|
||||||
|
|
||||||
|
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
|
||||||
|
|
||||||
|
JavaRDD<Dataset> tmp = sc
|
||||||
|
.textFile(workingDir.toString() + "/dataset")
|
||||||
|
.map(item -> OBJECT_MAPPER.readValue(item, Dataset.class));
|
||||||
|
|
||||||
|
Assertions.assertEquals(10, tmp.count());
|
||||||
|
org.apache.spark.sql.Dataset<Dataset> verificationDataset = spark
|
||||||
|
.createDataset(tmp.rdd(), Encoders.bean(Dataset.class));
|
||||||
|
|
||||||
|
verificationDataset.createOrReplaceTempView("dataset");
|
||||||
|
|
||||||
|
String query = "select id, MyT.id community, MyD.provenanceaction.classid "
|
||||||
|
+ "from dataset "
|
||||||
|
+ "lateral view explode(context) c as MyT "
|
||||||
|
+ "lateral view explode(MyT.datainfo) d as MyD "
|
||||||
|
+ "where MyD.inferenceprovenance = 'bulktagging'";
|
||||||
|
|
||||||
|
org.apache.spark.sql.Dataset<Row> queryResult = spark.sql(query);
|
||||||
|
queryResult.show(false);
|
||||||
|
Assertions.assertEquals(5, queryResult.count());
|
||||||
|
|
||||||
|
Assertions
|
||||||
|
.assertEquals(
|
||||||
|
1,
|
||||||
|
queryResult
|
||||||
|
.filter(
|
||||||
|
(FilterFunction<Row>) r -> r
|
||||||
|
.getAs("id")
|
||||||
|
.equals("50|od______3989::02dd5d2c222191b0b9bd4f33c8e96529"))
|
||||||
|
.count());
|
||||||
|
Assertions
|
||||||
|
.assertEquals(
|
||||||
|
1,
|
||||||
|
queryResult
|
||||||
|
.filter(
|
||||||
|
(FilterFunction<Row>) r -> r
|
||||||
|
.getAs("id")
|
||||||
|
.equals("50|od______3989::2f4f3c820c450bd08dac08d07cc82dcf"))
|
||||||
|
.count());
|
||||||
|
Assertions
|
||||||
|
.assertEquals(
|
||||||
|
1,
|
||||||
|
queryResult
|
||||||
|
.filter(
|
||||||
|
(FilterFunction<Row>) r -> r
|
||||||
|
.getAs("id")
|
||||||
|
.equals("50|od______3989::7fcbe3a03280663cddebfd3cb9203177"))
|
||||||
|
.count());
|
||||||
|
Assertions
|
||||||
|
.assertEquals(
|
||||||
|
1,
|
||||||
|
queryResult
|
||||||
|
.filter(
|
||||||
|
(FilterFunction<Row>) r -> r
|
||||||
|
.getAs("id")
|
||||||
|
.equals("50|od______3989::d791339867bec6d3eb2104deeb4e4961"))
|
||||||
|
.count());
|
||||||
|
Assertions
|
||||||
|
.assertEquals(
|
||||||
|
1,
|
||||||
|
queryResult
|
||||||
|
.filter(
|
||||||
|
(FilterFunction<Row>) r -> r
|
||||||
|
.getAs("id")
|
||||||
|
.equals("50|od______3989::d90d3a1f64ad264b5ebed8a35b280343"))
|
||||||
|
.count());
|
||||||
|
|
||||||
|
}
|
||||||
|
|
||||||
}
|
}
|
||||||
|
|
File diff suppressed because it is too large
Load Diff
File diff suppressed because one or more lines are too long
|
@ -7,6 +7,7 @@ import java.util.*;
|
||||||
import java.util.stream.Collectors;
|
import java.util.stream.Collectors;
|
||||||
import java.util.stream.Stream;
|
import java.util.stream.Stream;
|
||||||
|
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.utils.MergeUtils;
|
||||||
import org.apache.commons.io.IOUtils;
|
import org.apache.commons.io.IOUtils;
|
||||||
import org.apache.spark.SparkConf;
|
import org.apache.spark.SparkConf;
|
||||||
import org.apache.spark.api.java.function.FilterFunction;
|
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.ModelConstants;
|
||||||
import eu.dnetlib.dhp.schema.common.ModelSupport;
|
import eu.dnetlib.dhp.schema.common.ModelSupport;
|
||||||
import eu.dnetlib.dhp.schema.oaf.*;
|
import eu.dnetlib.dhp.schema.oaf.*;
|
||||||
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
|
|
||||||
import scala.Tuple2;
|
import scala.Tuple2;
|
||||||
|
|
||||||
/**
|
/**
|
||||||
|
@ -248,11 +248,11 @@ public class MergeGraphTableSparkJob {
|
||||||
private T mergeAndGet(T b, T a) {
|
private T mergeAndGet(T b, T a) {
|
||||||
if (Objects.nonNull(a) && Objects.nonNull(b)) {
|
if (Objects.nonNull(a) && Objects.nonNull(b)) {
|
||||||
if (ModelSupport.isSubClass(a, OafEntity.class) && ModelSupport.isSubClass(b, OafEntity.class)) {
|
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) {
|
if (a instanceof Relation && b instanceof Relation) {
|
||||||
((Relation) a).mergeFrom(b);
|
((Relation) a).mergeFrom(b);
|
||||||
return a;
|
return (T) MergeUtils.mergeRelation((Relation)a, (Relation) b);
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
return Objects.isNull(a) ? b : a;
|
return Objects.isNull(a) ? b : a;
|
||||||
|
|
|
@ -1,14 +1,16 @@
|
||||||
|
|
||||||
package eu.dnetlib.dhp.oa.graph.raw;
|
package eu.dnetlib.dhp.oa.graph.raw;
|
||||||
|
|
||||||
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
|
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||||
|
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
||||||
import java.util.Arrays;
|
import eu.dnetlib.dhp.common.HdfsSupport;
|
||||||
import java.util.List;
|
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup;
|
||||||
import java.util.Objects;
|
import eu.dnetlib.dhp.oa.graph.raw.common.AbstractMigrationApplication;
|
||||||
import java.util.Optional;
|
import eu.dnetlib.dhp.schema.common.ModelSupport;
|
||||||
import java.util.stream.Collectors;
|
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.io.IOUtils;
|
||||||
import org.apache.commons.lang3.StringUtils;
|
import org.apache.commons.lang3.StringUtils;
|
||||||
import org.apache.hadoop.io.Text;
|
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.SparkConf;
|
||||||
import org.apache.spark.api.java.JavaRDD;
|
import org.apache.spark.api.java.JavaRDD;
|
||||||
import org.apache.spark.api.java.JavaSparkContext;
|
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.apache.spark.sql.SparkSession;
|
||||||
import org.dom4j.DocumentException;
|
|
||||||
import org.slf4j.Logger;
|
import org.slf4j.Logger;
|
||||||
import org.slf4j.LoggerFactory;
|
import org.slf4j.LoggerFactory;
|
||||||
|
|
||||||
import com.fasterxml.jackson.databind.ObjectMapper;
|
|
||||||
|
|
||||||
import eu.dnetlib.dhp.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 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 {
|
public class GenerateEntitiesApplication extends AbstractMigrationApplication {
|
||||||
|
|
||||||
private static final Logger log = LoggerFactory.getLogger(GenerateEntitiesApplication.class);
|
private static final Logger log = LoggerFactory.getLogger(GenerateEntitiesApplication.class);
|
||||||
|
@ -137,7 +130,7 @@ public class GenerateEntitiesApplication extends AbstractMigrationApplication {
|
||||||
save(
|
save(
|
||||||
inputRdd
|
inputRdd
|
||||||
.mapToPair(oaf -> new Tuple2<>(ModelSupport.idFn().apply(oaf), oaf))
|
.mapToPair(oaf -> new Tuple2<>(ModelSupport.idFn().apply(oaf), oaf))
|
||||||
.reduceByKey(OafMapperUtils::merge)
|
.reduceByKey(MergeUtils::merge)
|
||||||
.map(Tuple2::_2),
|
.map(Tuple2::_2),
|
||||||
targetPath);
|
targetPath);
|
||||||
break;
|
break;
|
||||||
|
|
|
@ -12,6 +12,16 @@
|
||||||
<name>targetPath</name>
|
<name>targetPath</name>
|
||||||
<description>the output path of the graph enriched</description>
|
<description>the output path of the graph enriched</description>
|
||||||
</property>
|
</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>
|
</parameters>
|
||||||
|
|
||||||
<start to="EnrichGraph"/>
|
<start to="EnrichGraph"/>
|
||||||
|
@ -31,8 +41,8 @@
|
||||||
--executor-memory=${sparkExecutorMemory}
|
--executor-memory=${sparkExecutorMemory}
|
||||||
--executor-cores=${sparkExecutorCores}
|
--executor-cores=${sparkExecutorCores}
|
||||||
--driver-memory=${sparkDriverMemory}
|
--driver-memory=${sparkDriverMemory}
|
||||||
--conf spark.executor.memoryOverhead=2g
|
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
|
||||||
--conf spark.sql.shuffle.partitions=3000
|
--conf spark.sql.shuffle.partitions=5000
|
||||||
--conf spark.extraListeners=${spark2ExtraListeners}
|
--conf spark.extraListeners=${spark2ExtraListeners}
|
||||||
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
||||||
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||||||
|
|
|
@ -1,40 +0,0 @@
|
||||||
package eu.dnetlib.dhp.enrich.orcid
|
|
||||||
|
|
||||||
import eu.dnetlib.dhp.schema.common.ModelConstants
|
|
||||||
import eu.dnetlib.dhp.schema.oaf.{Author, Publication}
|
|
||||||
import eu.dnetlib.dhp.schema.sx.OafUtils
|
|
||||||
import org.apache.spark.sql.Row
|
|
||||||
|
|
||||||
import scala.collection.JavaConverters._
|
|
||||||
|
|
||||||
object AuthorEnricher extends Serializable {
|
|
||||||
|
|
||||||
def createAuthor(givenName: String, familyName: String, orcid: String): Author = {
|
|
||||||
val a = new Author
|
|
||||||
a.setName(givenName)
|
|
||||||
a.setSurname(familyName)
|
|
||||||
a.setFullname(s"$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)
|
|
||||||
//
|
|
||||||
//
|
|
||||||
//
|
|
||||||
// }
|
|
||||||
|
|
||||||
}
|
|
|
@ -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
|
||||||
|
}
|
||||||
|
|
||||||
|
}
|
|
@ -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)
|
||||||
|
}
|
||||||
|
}
|
|
@ -1,14 +1,39 @@
|
||||||
package eu.dnetlib.dhp.enrich.orcid
|
package eu.dnetlib.dhp.enrich.orcid
|
||||||
|
|
||||||
import eu.dnetlib.dhp.application.AbstractScalaApplication
|
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.common.ModelSupport
|
||||||
import eu.dnetlib.dhp.schema.oaf.{OtherResearchProduct, Publication, Result, Software}
|
import eu.dnetlib.dhp.schema.oaf._
|
||||||
import org.apache.spark.sql.functions._
|
|
||||||
import org.apache.spark.sql._
|
import org.apache.spark.sql._
|
||||||
|
import org.apache.spark.sql.functions._
|
||||||
import org.slf4j.{Logger, LoggerFactory}
|
import org.slf4j.{Logger, LoggerFactory}
|
||||||
|
|
||||||
|
import scala.beans.BeanProperty
|
||||||
import scala.collection.JavaConverters._
|
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)
|
class SparkEnrichGraphWithOrcidAuthors(propertyPath: String, args: Array[String], log: Logger)
|
||||||
extends AbstractScalaApplication(propertyPath, args, 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'")
|
log.info(s"orcidPath is '$orcidPath'")
|
||||||
val targetPath = parser.get("targetPath")
|
val targetPath = parser.get("targetPath")
|
||||||
log.info(s"targetPath is '$targetPath'")
|
log.info(s"targetPath is '$targetPath'")
|
||||||
val orcidPublication: Dataset[Row] = generateOrcidTable(spark, orcidPath)
|
|
||||||
// ModelSupport.entityTypes.entrySet().asScala.filter(k => k.getKey.getClass isInstance(Result))
|
|
||||||
|
|
||||||
enrichResult(
|
createTemporaryData(graphPath, orcidPath, targetPath)
|
||||||
spark,
|
analisys(targetPath)
|
||||||
s"$graphPath/publication",
|
generateGraph(graphPath, targetPath)
|
||||||
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"$targetPath/otherresearchproduct",
|
|
||||||
Encoders.bean(classOf[OtherResearchProduct])
|
|
||||||
)
|
|
||||||
}
|
}
|
||||||
|
|
||||||
private def enrichResult[T <: Result](
|
private def generateGraph(graphPath: String, targetPath: String): Unit = {
|
||||||
spark: SparkSession,
|
|
||||||
graphPath: String,
|
|
||||||
orcidPublication: Dataset[Row],
|
|
||||||
outputPath: String,
|
|
||||||
enc: Encoder[T]
|
|
||||||
): Unit = {
|
|
||||||
|
|
||||||
val entities = spark.read
|
ModelSupport.entityTypes.asScala
|
||||||
|
.filter(e => ModelSupport.isResult(e._1))
|
||||||
|
.foreach(e => {
|
||||||
|
val resultType = e._1.name()
|
||||||
|
val enc = Encoders.bean(e._2)
|
||||||
|
|
||||||
|
val matched = spark.read
|
||||||
|
.schema(Encoders.bean(classOf[ORCIDAuthorEnricherResult]).schema)
|
||||||
|
.parquet(s"${targetPath}/${resultType}_matched")
|
||||||
|
.selectExpr("id", "enriched_author")
|
||||||
|
|
||||||
|
spark.read
|
||||||
.schema(enc.schema)
|
.schema(enc.schema)
|
||||||
.json(graphPath)
|
.json(s"$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/$resultType")
|
||||||
.select(col("id"), col("datainfo"), col("instance"))
|
.select(col("id"), col("datainfo"), col("instance"))
|
||||||
.where("datainfo.deletedbyinference != true")
|
.where("datainfo.deletedbyinference != true")
|
||||||
.drop("datainfo")
|
.drop("datainfo")
|
||||||
.withColumn("instances", explode(col("instance")))
|
.withColumn("instances", explode(col("instance")))
|
||||||
.withColumn("pids", explode(col("instances.pid")))
|
.withColumn("pids", explode(col("instances.pid")))
|
||||||
.select(
|
.select(
|
||||||
col("pids.qualifier.classid").alias("pid_schema"),
|
lower(col("pids.qualifier.classid")).alias("pid_schema"),
|
||||||
col("pids.value").alias("pid_value"),
|
lower(col("pids.value")).alias("pid_value"),
|
||||||
col("id").alias("dnet_id")
|
col("id")
|
||||||
)
|
)
|
||||||
|
|
||||||
val orcidDnet = orcidPublication
|
val orcidDnet = orcidWorksWithAuthors
|
||||||
.join(
|
.join(
|
||||||
entities,
|
oaEntities,
|
||||||
lower(col("schema")).equalTo(lower(col("pid_schema"))) &&
|
Seq("pid_schema", "pid_value"),
|
||||||
lower(col("value")).equalTo(lower(col("pid_value"))),
|
|
||||||
"inner"
|
"inner"
|
||||||
)
|
)
|
||||||
.groupBy(col("dnet_id"))
|
.groupBy(col("id"))
|
||||||
.agg(collect_set(orcidPublication("author")).alias("orcid_authors"))
|
.agg(collect_set(col("author")).alias("orcid_authors"))
|
||||||
.select("dnet_id", "orcid_authors")
|
.select("id", "orcid_authors")
|
||||||
.cache()
|
|
||||||
orcidDnet.count()
|
val result =
|
||||||
val result = spark.read.schema(enc.schema).json(graphPath).as[T](enc)
|
spark.read.schema(enc.schema).json(s"$graphPath/$resultType").selectExpr("id", "author as graph_authors")
|
||||||
|
|
||||||
result
|
result
|
||||||
.joinWith(orcidDnet, result("id").equalTo(orcidDnet("dnet_id")), "left")
|
.join(orcidDnet, Seq("id"))
|
||||||
.map {
|
|
||||||
case (r: T, null) =>
|
|
||||||
r
|
|
||||||
case (p: T, r: Row) =>
|
|
||||||
p.setAuthor(AuthorMerger.enrichOrcid(p.getAuthor, AuthorEnricher.toOAFAuthor(r)))
|
|
||||||
p
|
|
||||||
}(enc)
|
|
||||||
.write
|
.write
|
||||||
.mode(SaveMode.Overwrite)
|
.mode(SaveMode.Overwrite)
|
||||||
.option("compression", "gzip")
|
.option("compression", "gzip")
|
||||||
.json(outputPath)
|
.parquet(s"$targetPath/${resultType}_unmatched")
|
||||||
|
})
|
||||||
|
|
||||||
|
orcidWorksWithAuthors.unpersist()
|
||||||
}
|
}
|
||||||
|
|
||||||
private def generateOrcidTable(spark: SparkSession, inputPath: String): Dataset[Row] = {
|
private def analisys(targetPath: String): Unit = {
|
||||||
val orcidAuthors =
|
ModelSupport.entityTypes.asScala
|
||||||
spark.read.load(s"$inputPath/Authors").select("orcid", "familyName", "givenName", "creditName", "otherNames")
|
.filter(e => ModelSupport.isResult(e._1))
|
||||||
val orcidWorks = spark.read
|
.foreach(e => {
|
||||||
.load(s"$inputPath/Works")
|
val resultType = e._1.name()
|
||||||
.select(col("orcid"), explode(col("pids")).alias("identifier"))
|
|
||||||
.where(
|
spark.read
|
||||||
"identifier.schema IN('doi','pmid','pmc','arxiv','handle')"
|
.parquet(s"$targetPath/${resultType}_unmatched")
|
||||||
)
|
.where("size(graph_authors) > 0")
|
||||||
val orcidPublication = orcidAuthors
|
.as[MatchData](Encoders.bean(classOf[MatchData]))
|
||||||
.join(orcidWorks, orcidAuthors("orcid").equalTo(orcidWorks("orcid")))
|
.map(md => {
|
||||||
.select(
|
ORCIDAuthorEnricher.enrichOrcid(md.id, md.graph_authors, md.orcid_authors)
|
||||||
col("identifier.schema").alias("schema"),
|
})(Encoders.bean(classOf[ORCIDAuthorEnricherResult]))
|
||||||
col("identifier.value").alias("value"),
|
.write
|
||||||
struct(orcidAuthors("orcid").alias("orcid"), col("givenName"), col("familyName")).alias("author")
|
.option("compression", "gzip")
|
||||||
)
|
.mode("overwrite")
|
||||||
orcidPublication.cache()
|
.parquet(s"$targetPath/${resultType}_matched")
|
||||||
|
})
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
|
@ -3,6 +3,7 @@ package eu.dnetlib.dhp.oa.graph.resolution
|
||||||
import com.fasterxml.jackson.databind.ObjectMapper
|
import com.fasterxml.jackson.databind.ObjectMapper
|
||||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser
|
import eu.dnetlib.dhp.application.ArgumentApplicationParser
|
||||||
import eu.dnetlib.dhp.schema.common.EntityType
|
import eu.dnetlib.dhp.schema.common.EntityType
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.utils.MergeUtils
|
||||||
import eu.dnetlib.dhp.schema.oaf.{Dataset => OafDataset, _}
|
import eu.dnetlib.dhp.schema.oaf.{Dataset => OafDataset, _}
|
||||||
import org.apache.commons.io.IOUtils
|
import org.apache.commons.io.IOUtils
|
||||||
import org.apache.hadoop.fs.{FileSystem, Path}
|
import org.apache.hadoop.fs.{FileSystem, Path}
|
||||||
|
@ -118,15 +119,12 @@ object SparkResolveEntities {
|
||||||
currentEntityDataset
|
currentEntityDataset
|
||||||
.joinWith(re, currentEntityDataset("_1").equalTo(re("_1")), "left")
|
.joinWith(re, currentEntityDataset("_1").equalTo(re("_1")), "left")
|
||||||
.map(k => {
|
.map(k => {
|
||||||
|
|
||||||
val a = k._1
|
val a = k._1
|
||||||
val b = k._2
|
val b = k._2
|
||||||
if (b == null)
|
if (b == null)
|
||||||
a._2
|
a._2
|
||||||
else {
|
else
|
||||||
a._2.mergeFrom(b._2)
|
MergeUtils.mergeResult(a._2, b._2)
|
||||||
a._2
|
|
||||||
}
|
|
||||||
})
|
})
|
||||||
.map(r => mapper.writeValueAsString(r))(Encoders.STRING)
|
.map(r => mapper.writeValueAsString(r))(Encoders.STRING)
|
||||||
.write
|
.write
|
||||||
|
|
|
@ -1,6 +1,7 @@
|
||||||
package eu.dnetlib.dhp.sx.graph
|
package eu.dnetlib.dhp.sx.graph
|
||||||
|
|
||||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser
|
import eu.dnetlib.dhp.application.ArgumentApplicationParser
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.utils.MergeUtils
|
||||||
import eu.dnetlib.dhp.schema.oaf.{Dataset => OafDataset, _}
|
import eu.dnetlib.dhp.schema.oaf.{Dataset => OafDataset, _}
|
||||||
import org.apache.commons.io.IOUtils
|
import org.apache.commons.io.IOUtils
|
||||||
import org.apache.spark.SparkConf
|
import org.apache.spark.SparkConf
|
||||||
|
@ -130,10 +131,7 @@ object SparkCreateInputGraph {
|
||||||
val ds: Dataset[T] = spark.read.load(sourcePath).as[T]
|
val ds: Dataset[T] = spark.read.load(sourcePath).as[T]
|
||||||
|
|
||||||
ds.groupByKey(_.getId)
|
ds.groupByKey(_.getId)
|
||||||
.reduceGroups { (x: T, y: T) =>
|
.reduceGroups { (x: T, y: T) => MergeUtils.merge(x, y).asInstanceOf[T] }
|
||||||
x.mergeFrom(y)
|
|
||||||
x
|
|
||||||
}
|
|
||||||
.map(_._2)
|
.map(_._2)
|
||||||
.write
|
.write
|
||||||
.mode(SaveMode.Overwrite)
|
.mode(SaveMode.Overwrite)
|
||||||
|
|
|
@ -1,10 +1,9 @@
|
||||||
|
|
||||||
package eu.dnetlib.oa.merge;
|
package eu.dnetlib.dhp.enrich.orcid;
|
||||||
|
|
||||||
import static org.junit.jupiter.api.Assertions.*;
|
|
||||||
|
|
||||||
import java.io.BufferedReader;
|
import java.io.BufferedReader;
|
||||||
import java.io.InputStreamReader;
|
import java.io.InputStreamReader;
|
||||||
|
import java.util.Collections;
|
||||||
import java.util.List;
|
import java.util.List;
|
||||||
import java.util.Objects;
|
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.core.type.TypeReference;
|
||||||
import com.fasterxml.jackson.databind.ObjectMapper;
|
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||||
|
|
||||||
import eu.dnetlib.dhp.oa.merge.AuthorMerger;
|
|
||||||
import eu.dnetlib.dhp.schema.oaf.Author;
|
import eu.dnetlib.dhp.schema.oaf.Author;
|
||||||
|
|
||||||
public class AuthorMergerTest {
|
public class ORCIDAuthorEnricherTest {
|
||||||
|
|
||||||
@Test
|
@Test
|
||||||
public void testEnrcichAuthor() throws Exception {
|
public void testEnrcichAuthor() throws Exception {
|
||||||
|
@ -26,12 +24,13 @@ public class AuthorMergerTest {
|
||||||
BufferedReader pr = new BufferedReader(new InputStreamReader(
|
BufferedReader pr = new BufferedReader(new InputStreamReader(
|
||||||
Objects
|
Objects
|
||||||
.requireNonNull(
|
.requireNonNull(
|
||||||
AuthorMergerTest.class
|
ORCIDAuthorEnricherTest.class
|
||||||
.getResourceAsStream("/eu/dnetlib/dhp/oa/merge/authors_publication_sample.json"))));
|
.getResourceAsStream("/eu/dnetlib/dhp/enrich/orcid/authors_publication_sample.json"))));
|
||||||
BufferedReader or = new BufferedReader(new InputStreamReader(
|
BufferedReader or = new BufferedReader(new InputStreamReader(
|
||||||
Objects
|
Objects
|
||||||
.requireNonNull(
|
.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>>() {
|
TypeReference<List<Author>> aclass = new TypeReference<List<Author>>() {
|
||||||
};
|
};
|
||||||
|
@ -67,7 +66,8 @@ public class AuthorMergerTest {
|
||||||
long start = System.currentTimeMillis();
|
long start = System.currentTimeMillis();
|
||||||
|
|
||||||
// final List<Author> enrichedList = AuthorMerger.enrichOrcid(publicationAuthors, orcidAuthors);
|
// 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
|
long enrichedAuthorWithPid = enrichedList
|
||||||
.stream()
|
.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);
|
|
||||||
|
|
||||||
}
|
|
||||||
|
|
||||||
}
|
}
|
|
@ -1,13 +1,12 @@
|
||||||
|
|
||||||
package eu.dnetlib.dhp.oa.graph.raw;
|
package eu.dnetlib.dhp.oa.graph.raw;
|
||||||
|
|
||||||
import static org.junit.jupiter.api.Assertions.assertEquals;
|
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup;
|
||||||
import static org.junit.jupiter.api.Assertions.assertTrue;
|
import eu.dnetlib.dhp.schema.common.ModelConstants;
|
||||||
import static org.mockito.Mockito.lenient;
|
import eu.dnetlib.dhp.schema.oaf.*;
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.utils.MergeUtils;
|
||||||
import java.io.IOException;
|
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpException;
|
||||||
import java.util.List;
|
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
|
||||||
|
|
||||||
import org.apache.commons.io.IOUtils;
|
import org.apache.commons.io.IOUtils;
|
||||||
import org.dom4j.DocumentException;
|
import org.dom4j.DocumentException;
|
||||||
import org.junit.jupiter.api.BeforeEach;
|
import org.junit.jupiter.api.BeforeEach;
|
||||||
|
@ -16,13 +15,12 @@ import org.junit.jupiter.api.extension.ExtendWith;
|
||||||
import org.mockito.Mock;
|
import org.mockito.Mock;
|
||||||
import org.mockito.junit.jupiter.MockitoExtension;
|
import org.mockito.junit.jupiter.MockitoExtension;
|
||||||
|
|
||||||
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup;
|
import java.io.IOException;
|
||||||
import eu.dnetlib.dhp.oa.graph.clean.GraphCleaningFunctionsTest;
|
import java.util.List;
|
||||||
import eu.dnetlib.dhp.schema.common.ModelConstants;
|
|
||||||
import eu.dnetlib.dhp.schema.oaf.*;
|
import static org.junit.jupiter.api.Assertions.assertEquals;
|
||||||
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
|
import static org.junit.jupiter.api.Assertions.assertTrue;
|
||||||
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpException;
|
import static org.mockito.Mockito.lenient;
|
||||||
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
|
|
||||||
|
|
||||||
@ExtendWith(MockitoExtension.class)
|
@ExtendWith(MockitoExtension.class)
|
||||||
class GenerateEntitiesApplicationTest {
|
class GenerateEntitiesApplicationTest {
|
||||||
|
@ -72,7 +70,7 @@ class GenerateEntitiesApplicationTest {
|
||||||
|
|
||||||
protected <T extends Result> void verifyMerge(Result publication, Result dataset, Class<T> clazz,
|
protected <T extends Result> void verifyMerge(Result publication, Result dataset, Class<T> clazz,
|
||||||
String resultType) {
|
String resultType) {
|
||||||
final Result merge = OafMapperUtils.mergeResults(publication, dataset);
|
final Result merge = MergeUtils.mergeResult(publication, dataset);
|
||||||
assertTrue(clazz.isAssignableFrom(merge.getClass()));
|
assertTrue(clazz.isAssignableFrom(merge.getClass()));
|
||||||
assertEquals(resultType, merge.getResulttype().getClassid());
|
assertEquals(resultType, merge.getResulttype().getClassid());
|
||||||
}
|
}
|
||||||
|
|
|
@ -0,0 +1,35 @@
|
||||||
|
package eu.dnetlib.dhp.enrich.orcid
|
||||||
|
|
||||||
|
import eu.dnetlib.dhp.enrich.orcid.ORCIDAuthorMatchers.matchOrderedTokenAndAbbreviations
|
||||||
|
import org.junit.jupiter.api.Assertions.{assertFalse, assertTrue}
|
||||||
|
import org.junit.jupiter.api.Test
|
||||||
|
|
||||||
|
class ORCIDAuthorMatchersTest {
|
||||||
|
|
||||||
|
@Test def testShortNames(): Unit = {
|
||||||
|
assertTrue(matchOrderedTokenAndAbbreviations("Lasagni Mariozzi Federico", "Lasagni F. Mariozzi"))
|
||||||
|
}
|
||||||
|
|
||||||
|
@Test def testInvertedNames(): Unit = {
|
||||||
|
assertTrue(matchOrderedTokenAndAbbreviations("Andrea, Paolo Marcello", "Marcello Paolo, Andrea"))
|
||||||
|
}
|
||||||
|
|
||||||
|
@Test def testHomonymy(): Unit = {
|
||||||
|
assertTrue(matchOrderedTokenAndAbbreviations("Jang Myung Lee", "J Lee"))
|
||||||
|
}
|
||||||
|
|
||||||
|
@Test def testAmbiguousShortNames(): Unit = {
|
||||||
|
assertFalse(matchOrderedTokenAndAbbreviations("P. Mariozzi", "M. Paolozzi"))
|
||||||
|
}
|
||||||
|
|
||||||
|
@Test def testNonMatches(): Unit = {
|
||||||
|
assertFalse(matchOrderedTokenAndAbbreviations("Giovanni Paolozzi", "Francesco Paolozzi"))
|
||||||
|
assertFalse(matchOrderedTokenAndAbbreviations("G. Paolozzi", "F. Paolozzi"))
|
||||||
|
}
|
||||||
|
|
||||||
|
@Test def testChineseNames(): Unit = {
|
||||||
|
assertTrue(matchOrderedTokenAndAbbreviations("孙林 Sun Lin", "Sun Lin"))
|
||||||
|
// assertTrue(AuthorsMatchRevised.compare("孙林 Sun Lin", "孙林")); // not yet implemented
|
||||||
|
}
|
||||||
|
|
||||||
|
}
|
2
pom.xml
2
pom.xml
|
@ -888,7 +888,7 @@
|
||||||
<mockito-core.version>3.3.3</mockito-core.version>
|
<mockito-core.version>3.3.3</mockito-core.version>
|
||||||
<mongodb.driver.version>3.4.2</mongodb.driver.version>
|
<mongodb.driver.version>3.4.2</mongodb.driver.version>
|
||||||
<vtd.version>[2.12,3.0)</vtd.version>
|
<vtd.version>[2.12,3.0)</vtd.version>
|
||||||
<dhp-schemas.version>[4.17.2]</dhp-schemas.version>
|
<dhp-schemas.version>[5.17.3]</dhp-schemas.version>
|
||||||
<dnet-actionmanager-api.version>[4.0.3]</dnet-actionmanager-api.version>
|
<dnet-actionmanager-api.version>[4.0.3]</dnet-actionmanager-api.version>
|
||||||
<dnet-actionmanager-common.version>[6.0.5]</dnet-actionmanager-common.version>
|
<dnet-actionmanager-common.version>[6.0.5]</dnet-actionmanager-common.version>
|
||||||
<dnet-openaire-broker-common.version>[3.1.6]</dnet-openaire-broker-common.version>
|
<dnet-openaire-broker-common.version>[3.1.6]</dnet-openaire-broker-common.version>
|
||||||
|
|
Loading…
Reference in New Issue