Merge remote-tracking branch 'upstream/beta' into beta

This commit is contained in:
Antonis Lempesis 2024-04-19 15:28:28 +03:00
commit b52a5a753b
289 changed files with 132815 additions and 3580 deletions

View File

@ -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()
: ""; : "";

View File

@ -14,7 +14,7 @@ import java.util.stream.Collectors;
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;
import org.apache.spark.api.java.function.ReduceFunction; import org.apache.spark.api.java.function.MapGroupsFunction;
import org.apache.spark.sql.*; import org.apache.spark.sql.*;
import org.slf4j.Logger; import org.slf4j.Logger;
import org.slf4j.LoggerFactory; import org.slf4j.LoggerFactory;
@ -26,7 +26,7 @@ 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;
@ -135,10 +135,10 @@ 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) .mapGroups((MapGroupsFunction<String, OafEntity, OafEntity>) MergeUtils::mergeGroup, OAFENTITY_KRYO_ENC)
.map( .map(
(MapFunction<Tuple2<String, OafEntity>, Tuple2<String, OafEntity>>) t -> new Tuple2<>( (MapFunction<OafEntity, Tuple2<String, OafEntity>>) t -> new Tuple2<>(
t._2().getClass().getName(), t._2()), t.getClass().getName(), t),
Encoders.tuple(Encoders.STRING(), OAFENTITY_KRYO_ENC)); Encoders.tuple(Encoders.STRING(), OAFENTITY_KRYO_ENC));
// pivot on "_1" (classname of the entity) // pivot on "_1" (classname of the entity)

View File

@ -0,0 +1,76 @@
package eu.dnetlib.dhp.schema.oaf.utils;
import java.util.HashSet;
import java.util.Objects;
import java.util.Optional;
import java.util.Set;
import org.apache.commons.lang3.StringUtils;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
public class CleaningFunctions {
public static final String DOI_PREFIX_REGEX = "(^10\\.|\\/10\\.)";
public static final String DOI_PREFIX = "10.";
public static final Set<String> PID_BLACKLIST = new HashSet<>();
static {
PID_BLACKLIST.add("none");
PID_BLACKLIST.add("na");
}
public CleaningFunctions() {
}
/**
* Utility method that filter PID values on a per-type basis.
* @param s the PID whose value will be checked.
* @return false if the pid matches the filter criteria, true otherwise.
*/
public static boolean pidFilter(StructuredProperty s) {
final String pidValue = s.getValue();
if (Objects.isNull(s.getQualifier()) ||
StringUtils.isBlank(pidValue) ||
StringUtils.isBlank(pidValue.replaceAll("(?:\\n|\\r|\\t|\\s)", ""))) {
return false;
}
if (CleaningFunctions.PID_BLACKLIST.contains(pidValue)) {
return false;
}
return !PidBlacklistProvider.getBlacklist(s.getQualifier().getClassid()).contains(pidValue);
}
/**
* Utility method that normalises PID values on a per-type basis.
* @param pid the PID whose value will be normalised.
* @return the PID containing the normalised value.
*/
public static StructuredProperty normalizePidValue(StructuredProperty pid) {
pid
.setValue(
normalizePidValue(
pid.getQualifier().getClassid(),
pid.getValue()));
return pid;
}
public static String normalizePidValue(String pidType, String pidValue) {
String value = Optional
.ofNullable(pidValue)
.map(String::trim)
.orElseThrow(() -> new IllegalArgumentException("PID value cannot be empty"));
switch (pidType) {
// TODO add cleaning for more PID types as needed
case "doi":
return value.toLowerCase().replaceFirst(DOI_PREFIX_REGEX, DOI_PREFIX);
}
return value;
}
}

View File

@ -1,6 +1,8 @@
package eu.dnetlib.dhp.schema.oaf.utils; package eu.dnetlib.dhp.schema.oaf.utils;
import org.apache.commons.lang3.StringUtils;
public class DoiCleaningRule { public class DoiCleaningRule {
public static String clean(final String doi) { public static String clean(final String doi) {
@ -11,4 +13,26 @@ public class DoiCleaningRule {
.replaceFirst(CleaningFunctions.DOI_PREFIX_REGEX, CleaningFunctions.DOI_PREFIX); .replaceFirst(CleaningFunctions.DOI_PREFIX_REGEX, CleaningFunctions.DOI_PREFIX);
} }
public static String normalizeDoi(final String input) {
if (input == null)
return null;
final String replaced = input
.replaceAll("\\n|\\r|\\t|\\s", "")
.toLowerCase()
.replaceFirst(CleaningFunctions.DOI_PREFIX_REGEX, CleaningFunctions.DOI_PREFIX);
if (StringUtils.isEmpty(replaced))
return null;
if (!replaced.contains("10."))
return null;
final String ret = replaced.substring(replaced.indexOf("10."));
if (!ret.startsWith(CleaningFunctions.DOI_PREFIX))
return null;
return ret;
}
} }

View File

@ -92,6 +92,8 @@ public class GraphCleaningFunctions extends CleaningFunctions {
INVALID_AUTHOR_NAMES.add("null anonymous"); INVALID_AUTHOR_NAMES.add("null anonymous");
INVALID_AUTHOR_NAMES.add("unbekannt"); INVALID_AUTHOR_NAMES.add("unbekannt");
INVALID_AUTHOR_NAMES.add("unknown"); INVALID_AUTHOR_NAMES.add("unknown");
INVALID_AUTHOR_NAMES.add("autor, Sin");
INVALID_AUTHOR_NAMES.add("Desconocido / Inconnu,");
INVALID_URL_HOSTS.add("creativecommons.org"); INVALID_URL_HOSTS.add("creativecommons.org");
INVALID_URL_HOSTS.add("www.academia.edu"); INVALID_URL_HOSTS.add("www.academia.edu");
@ -312,7 +314,8 @@ public class GraphCleaningFunctions extends CleaningFunctions {
} }
if (value instanceof Datasource) { if (value instanceof Datasource) {
// nothing to evaluate here final Datasource d = (Datasource) value;
return Objects.nonNull(d.getOfficialname()) && StringUtils.isNotBlank(d.getOfficialname().getValue());
} else if (value instanceof Project) { } else if (value instanceof Project) {
final Project p = (Project) value; final Project p = (Project) value;
return Objects.nonNull(p.getCode()) && StringUtils.isNotBlank(p.getCode().getValue()); return Objects.nonNull(p.getCode()) && StringUtils.isNotBlank(p.getCode().getValue());
@ -505,6 +508,8 @@ public class GraphCleaningFunctions extends CleaningFunctions {
.filter(Objects::nonNull) .filter(Objects::nonNull)
.filter(sp -> StringUtils.isNotBlank(sp.getValue())) .filter(sp -> StringUtils.isNotBlank(sp.getValue()))
.map(GraphCleaningFunctions::cleanValue) .map(GraphCleaningFunctions::cleanValue)
.sorted((s1, s2) -> s2.getValue().length() - s1.getValue().length())
.limit(ModelHardLimits.MAX_ABSTRACTS)
.collect(Collectors.toList())); .collect(Collectors.toList()));
} }
if (Objects.isNull(r.getResourcetype()) || StringUtils.isBlank(r.getResourcetype().getClassid())) { if (Objects.isNull(r.getResourcetype()) || StringUtils.isBlank(r.getResourcetype().getClassid())) {

View File

@ -0,0 +1,294 @@
package eu.dnetlib.dhp.schema.oaf.utils;
import static com.google.common.base.Preconditions.checkArgument;
import static eu.dnetlib.dhp.schema.common.ModelConstants.*;
import java.io.Serializable;
import java.nio.charset.StandardCharsets;
import java.security.MessageDigest;
import java.util.*;
import java.util.function.Function;
import java.util.stream.Collectors;
import java.util.stream.Stream;
import org.apache.commons.codec.binary.Hex;
import org.apache.commons.lang3.StringUtils;
import com.google.common.collect.HashBiMap;
import com.google.common.collect.Maps;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.*;
/**
* Factory class for OpenAIRE identifiers in the Graph
*/
public class IdentifierFactory implements Serializable {
public static final String ID_SEPARATOR = "::";
public static final String ID_PREFIX_SEPARATOR = "|";
public static final int ID_PREFIX_LEN = 12;
/**
* Declares the associations PID_TYPE -> [DATASOURCE ID, NAME] considered authoritative for that PID_TYPE.
* The id of the record (source_::id) will be rewritten as pidType_::id)
*/
public static final Map<PidType, HashBiMap<String, String>> PID_AUTHORITY = Maps.newHashMap();
static {
PID_AUTHORITY.put(PidType.doi, HashBiMap.create());
PID_AUTHORITY.get(PidType.doi).put(CROSSREF_ID, "Crossref");
PID_AUTHORITY.get(PidType.doi).put(DATACITE_ID, "Datacite");
PID_AUTHORITY.get(PidType.doi).put(ZENODO_OD_ID, "ZENODO");
PID_AUTHORITY.get(PidType.doi).put(ZENODO_R3_ID, "Zenodo");
PID_AUTHORITY.put(PidType.pmc, HashBiMap.create());
PID_AUTHORITY.get(PidType.pmc).put(EUROPE_PUBMED_CENTRAL_ID, "Europe PubMed Central");
PID_AUTHORITY.get(PidType.pmc).put(PUBMED_CENTRAL_ID, "PubMed Central");
PID_AUTHORITY.put(PidType.pmid, HashBiMap.create());
PID_AUTHORITY.get(PidType.pmid).put(EUROPE_PUBMED_CENTRAL_ID, "Europe PubMed Central");
PID_AUTHORITY.get(PidType.pmid).put(PUBMED_CENTRAL_ID, "PubMed Central");
PID_AUTHORITY.put(PidType.arXiv, HashBiMap.create());
PID_AUTHORITY.get(PidType.arXiv).put(ARXIV_ID, "arXiv.org e-Print Archive");
PID_AUTHORITY.put(PidType.w3id, HashBiMap.create());
PID_AUTHORITY.get(PidType.w3id).put(ROHUB_ID, "ROHub");
}
/**
* Declares the associations PID_TYPE -> [DATASOURCE ID, PID SUBSTRING] considered as delegated authority for that
* PID_TYPE. Example, Zenodo is delegated to forge DOIs that contain the 'zenodo' word.
*
* If a record with the same id (same pid) comes from 2 data sources, the one coming from a delegated source wins. E.g. Zenodo records win over those from Datacite.
* See also https://code-repo.d4science.org/D-Net/dnet-hadoop/pulls/187 and the class dhp-common/src/main/java/eu/dnetlib/dhp/schema/oaf/utils/OafMapperUtils.java
*/
public static final Map<PidType, Map<String, String>> DELEGATED_PID_AUTHORITY = Maps.newHashMap();
static {
DELEGATED_PID_AUTHORITY.put(PidType.doi, new HashMap<>());
DELEGATED_PID_AUTHORITY.get(PidType.doi).put(ZENODO_OD_ID, "zenodo");
DELEGATED_PID_AUTHORITY.get(PidType.doi).put(ZENODO_R3_ID, "zenodo");
DELEGATED_PID_AUTHORITY.put(PidType.w3id, new HashMap<>());
DELEGATED_PID_AUTHORITY.get(PidType.w3id).put(ROHUB_ID, "ro-id");
}
/**
* Declares the associations PID_TYPE -> [DATASOURCE ID, NAME] whose records are considered enrichment for the graph.
* Their OpenAIRE ID is built from the declared PID type. Are merged with their corresponding record, identified by
* the same OpenAIRE id.
*/
public static final Map<PidType, HashBiMap<String, String>> ENRICHMENT_PROVIDER = Maps.newHashMap();
static {
ENRICHMENT_PROVIDER.put(PidType.doi, HashBiMap.create());
ENRICHMENT_PROVIDER.get(PidType.doi).put(OPEN_APC_ID, OPEN_APC_NAME);
}
public static Set<String> delegatedAuthorityDatasourceIds() {
return DELEGATED_PID_AUTHORITY
.values()
.stream()
.flatMap(m -> m.keySet().stream())
.collect(Collectors.toCollection(HashSet::new));
}
public static List<StructuredProperty> getPids(List<StructuredProperty> pid, KeyValue collectedFrom) {
return pidFromInstance(pid, collectedFrom, true).distinct().collect(Collectors.toList());
}
public static <T extends Result> String createDOIBoostIdentifier(T entity) {
if (entity == null)
return null;
StructuredProperty pid = null;
if (entity.getPid() != null) {
pid = entity
.getPid()
.stream()
.filter(Objects::nonNull)
.filter(s -> s.getQualifier() != null && "doi".equalsIgnoreCase(s.getQualifier().getClassid()))
.filter(CleaningFunctions::pidFilter)
.findAny()
.orElse(null);
} else {
if (entity.getInstance() != null) {
pid = entity
.getInstance()
.stream()
.filter(i -> i.getPid() != null)
.flatMap(i -> i.getPid().stream())
.filter(CleaningFunctions::pidFilter)
.findAny()
.orElse(null);
}
}
if (pid != null)
return idFromPid(entity, pid, true);
return null;
}
/**
* Creates an identifier from the most relevant PID (if available) provided by a known PID authority in the given
* entity T. Returns entity.id when none of the PIDs meet the selection criteria is available.
*
* @param entity the entity providing PIDs and a default ID.
* @param <T> the specific entity type. Currently Organization and Result subclasses are supported.
* @param md5 indicates whether should hash the PID value or not.
* @return an identifier from the most relevant PID, entity.id otherwise
*/
public static <T extends OafEntity> String createIdentifier(T entity, boolean md5) {
checkArgument(StringUtils.isNoneBlank(entity.getId()), "missing entity identifier");
final Map<String, Set<StructuredProperty>> pids = extractPids(entity);
return pids
.values()
.stream()
.flatMap(Set::stream)
.min(new PidComparator<>(entity))
.map(
min -> Optional
.ofNullable(pids.get(min.getQualifier().getClassid()))
.map(
p -> p
.stream()
.sorted(new PidValueComparator())
.findFirst()
.map(s -> idFromPid(entity, s, md5))
.orElseGet(entity::getId))
.orElseGet(entity::getId))
.orElseGet(entity::getId);
}
private static <T extends OafEntity> Map<String, Set<StructuredProperty>> extractPids(T entity) {
if (entity instanceof Result) {
return Optional
.ofNullable(((Result) entity).getInstance())
.map(IdentifierFactory::mapPids)
.orElse(new HashMap<>());
} else {
return entity
.getPid()
.stream()
.map(CleaningFunctions::normalizePidValue)
.filter(CleaningFunctions::pidFilter)
.collect(
Collectors
.groupingBy(
p -> p.getQualifier().getClassid(),
Collectors.mapping(p -> p, Collectors.toCollection(HashSet::new))));
}
}
private static Map<String, Set<StructuredProperty>> mapPids(List<Instance> instance) {
return instance
.stream()
.map(i -> pidFromInstance(i.getPid(), i.getCollectedfrom(), false))
.flatMap(Function.identity())
.collect(
Collectors
.groupingBy(
p -> p.getQualifier().getClassid(),
Collectors.mapping(p -> p, Collectors.toCollection(HashSet::new))));
}
private static Stream<StructuredProperty> pidFromInstance(List<StructuredProperty> pid, KeyValue collectedFrom,
boolean mapHandles) {
return Optional
.ofNullable(pid)
.map(
pp -> pp
.stream()
// filter away PIDs provided by a DS that is not considered an authority for the
// given PID Type
.filter(p -> shouldFilterPidByCriteria(collectedFrom, p, mapHandles))
.map(CleaningFunctions::normalizePidValue)
.filter(p -> isNotFromDelegatedAuthority(collectedFrom, p))
.filter(CleaningFunctions::pidFilter))
.orElse(Stream.empty());
}
private static boolean shouldFilterPidByCriteria(KeyValue collectedFrom, StructuredProperty p, boolean mapHandles) {
final PidType pType = PidType.tryValueOf(p.getQualifier().getClassid());
if (Objects.isNull(collectedFrom)) {
return false;
}
boolean isEnrich = Optional
.ofNullable(ENRICHMENT_PROVIDER.get(pType))
.map(
enrich -> enrich.containsKey(collectedFrom.getKey())
|| enrich.containsValue(collectedFrom.getValue()))
.orElse(false);
boolean isAuthority = Optional
.ofNullable(PID_AUTHORITY.get(pType))
.map(
authorities -> authorities.containsKey(collectedFrom.getKey())
|| authorities.containsValue(collectedFrom.getValue()))
.orElse(false);
return (mapHandles && pType.equals(PidType.handle)) || isEnrich || isAuthority;
}
private static boolean isNotFromDelegatedAuthority(KeyValue collectedFrom, StructuredProperty p) {
final PidType pType = PidType.tryValueOf(p.getQualifier().getClassid());
final Map<String, String> da = DELEGATED_PID_AUTHORITY.get(pType);
if (Objects.isNull(da)) {
return true;
}
if (!da.containsKey(collectedFrom.getKey())) {
return true;
}
return StringUtils.contains(p.getValue(), da.get(collectedFrom.getKey()));
}
/**
* @see {@link IdentifierFactory#createIdentifier(OafEntity, boolean)}
*/
public static <T extends OafEntity> String createIdentifier(T entity) {
return createIdentifier(entity, true);
}
private static <T extends OafEntity> String idFromPid(T entity, StructuredProperty s, boolean md5) {
return idFromPid(ModelSupport.getIdPrefix(entity.getClass()), s.getQualifier().getClassid(), s.getValue(), md5);
}
public static String idFromPid(String numericPrefix, String pidType, String pidValue, boolean md5) {
return new StringBuilder()
.append(numericPrefix)
.append(ID_PREFIX_SEPARATOR)
.append(createPrefix(pidType))
.append(ID_SEPARATOR)
.append(md5 ? md5(pidValue) : pidValue)
.toString();
}
// create the prefix (length = 12)
private static String createPrefix(String pidType) {
StringBuilder prefix = new StringBuilder(StringUtils.left(pidType, ID_PREFIX_LEN));
while (prefix.length() < ID_PREFIX_LEN) {
prefix.append("_");
}
return prefix.substring(0, ID_PREFIX_LEN);
}
public static String md5(final String s) {
try {
final MessageDigest md = MessageDigest.getInstance("MD5");
md.update(s.getBytes(StandardCharsets.UTF_8));
return new String(Hex.encodeHex(md.digest()));
} catch (final Exception e) {
return null;
}
}
}

View File

@ -0,0 +1,78 @@
package eu.dnetlib.dhp.schema.oaf.utils;
import java.util.Comparator;
import java.util.HashSet;
import java.util.Optional;
import java.util.stream.Collectors;
//
// 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;
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());
}
}
}

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,27 @@
package eu.dnetlib.dhp.schema.oaf.utils;
public class ModelHardLimits {
private ModelHardLimits() {
}
public static final String LAYOUT = "index";
public static final String INTERPRETATION = "openaire";
public static final String SEPARATOR = "-";
public static final int MAX_EXTERNAL_ENTITIES = 50;
public static final int MAX_AUTHORS = 200;
public static final int MAX_AUTHOR_FULLNAME_LENGTH = 1000;
public static final int MAX_TITLE_LENGTH = 5000;
public static final int MAX_TITLES = 10;
public static final int MAX_ABSTRACTS = 10;
public static final int MAX_ABSTRACT_LENGTH = 150000;
public static final int MAX_RELATED_ABSTRACT_LENGTH = 500;
public static final int MAX_INSTANCES = 10;
public static String getCollectionName(String format) {
return format + SEPARATOR + LAYOUT + SEPARATOR + INTERPRETATION;
}
}

View File

@ -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);

View File

@ -0,0 +1,46 @@
package eu.dnetlib.dhp.schema.oaf.utils;
import java.util.Comparator;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
public class OrganizationPidComparator implements Comparator<StructuredProperty> {
@Override
public int compare(StructuredProperty left, StructuredProperty right) {
if (left == null) {
return right == null ? 0 : -1;
} else if (right == null) {
return 1;
}
PidType lClass = PidType.tryValueOf(left.getQualifier().getClassid());
PidType rClass = PidType.tryValueOf(right.getQualifier().getClassid());
if (lClass.equals(rClass))
return 0;
if (lClass.equals(PidType.openorgs))
return -1;
if (rClass.equals(PidType.openorgs))
return 1;
if (lClass.equals(PidType.GRID))
return -1;
if (rClass.equals(PidType.GRID))
return 1;
if (lClass.equals(PidType.mag_id))
return -1;
if (rClass.equals(PidType.mag_id))
return 1;
if (lClass.equals(PidType.urn))
return -1;
if (rClass.equals(PidType.urn))
return 1;
return 0;
}
}

View File

@ -0,0 +1,8 @@
package eu.dnetlib.dhp.schema.oaf.utils;
import java.util.HashMap;
import java.util.HashSet;
public class PidBlacklist extends HashMap<String, HashSet<String>> {
}

View File

@ -0,0 +1,40 @@
package eu.dnetlib.dhp.schema.oaf.utils;
import java.io.IOException;
import java.util.HashSet;
import java.util.Optional;
import java.util.Set;
import org.apache.commons.io.IOUtils;
import com.fasterxml.jackson.databind.ObjectMapper;
public class PidBlacklistProvider {
private static final PidBlacklist blacklist;
static {
try {
String json = IOUtils.toString(IdentifierFactory.class.getResourceAsStream("pid_blacklist.json"));
blacklist = new ObjectMapper().readValue(json, PidBlacklist.class);
} catch (IOException e) {
throw new RuntimeException(e);
}
}
public static PidBlacklist getBlacklist() {
return blacklist;
}
public static Set<String> getBlacklist(String pidType) {
return Optional
.ofNullable(getBlacklist().get(pidType))
.orElse(new HashSet<>());
}
private PidBlacklistProvider() {
}
}

View File

@ -0,0 +1,48 @@
package eu.dnetlib.dhp.schema.oaf.utils;
import java.util.Comparator;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.OafEntity;
import eu.dnetlib.dhp.schema.oaf.Organization;
import eu.dnetlib.dhp.schema.oaf.Result;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
public class PidComparator<T extends OafEntity> implements Comparator<StructuredProperty> {
private final T entity;
public PidComparator(T entity) {
this.entity = entity;
}
@Override
public int compare(StructuredProperty left, StructuredProperty right) {
if (left == null && right == null)
return 0;
if (left == null)
return 1;
if (right == null)
return -1;
if (ModelSupport.isSubClass(entity, Result.class)) {
return compareResultPids(left, right);
}
if (ModelSupport.isSubClass(entity, Organization.class)) {
return compareOrganizationtPids(left, right);
}
// Else (but unlikely), lexicographical ordering will do.
return left.getQualifier().getClassid().compareTo(right.getQualifier().getClassid());
}
private int compareResultPids(StructuredProperty left, StructuredProperty right) {
return new ResultPidComparator().compare(left, right);
}
private int compareOrganizationtPids(StructuredProperty left, StructuredProperty right) {
return new OrganizationPidComparator().compare(left, right);
}
}

View File

@ -0,0 +1,79 @@
package eu.dnetlib.dhp.schema.oaf.utils;
import org.apache.commons.lang3.EnumUtils;
public enum PidType {
/**
* The DOI syntax shall be made up of a DOI prefix and a DOI suffix separated by a forward slash.
*
* There is no defined limit on the length of the DOI name, or of the DOI prefix or DOI suffix.
*
* The DOI name is case-insensitive and can incorporate any printable characters from the legal graphic characters
* of Unicode. Further constraints on character use (e.g. use of language-specific alphanumeric characters) can be
* defined for an application by the ISO 26324 Registration Authority.
*
*
* DOI prefix: The DOI prefix shall be composed of a directory indicator followed by a registrant code.
* These two components shall be separated by a full stop (period). The directory indicator shall be "10" and
* distinguishes the entire set of character strings (prefix and suffix) as digital object identifiers within the
* resolution system.
*
* Registrant code: The second element of the DOI prefix shall be the registrant code. The registrant code is a
* unique string assigned to a registrant.
*
* DOI suffix: The DOI suffix shall consist of a character string of any length chosen by the registrant.
* Each suffix shall be unique to the prefix element that precedes it. The unique suffix can be a sequential number,
* or it might incorporate an identifier generated from or based on another system used by the registrant
* (e.g. ISAN, ISBN, ISRC, ISSN, ISTC, ISNI; in such cases, a preferred construction for such a suffix can be
* specified, as in Example 1).
*
* Source: https://www.doi.org/doi_handbook/2_Numbering.html#2.2
*/
doi,
/**
* PubMed Unique Identifier (PMID)
*
* This field is a 1-to-8 digit accession number with no leading zeros. It is present on all records and is the
* accession number for managing and disseminating records. PMIDs are not reused after records are deleted.
*
* Beginning in February 2012 PMIDs include extensions following a decimal point to account for article versions
* (e.g., 21804956.2). All citations are considered version 1 until replaced. The extended PMID is not displayed
* on the MEDLINE format.
*
* View the citation in abstract format in PubMed to access additional versions when available (see the article in
* the Jan-Feb 2012 NLM Technical Bulletin).
*
* Source: https://www.nlm.nih.gov/bsd/mms/medlineelements.html#pmid
*/
pmid,
/**
* This field contains the unique identifier for the cited article in PubMed Central. The identifier begins with the
* prefix PMC.
*
* Source: https://www.nlm.nih.gov/bsd/mms/medlineelements.html#pmc
*/
pmc, handle, arXiv, nct, pdb, w3id,
// Organization
openorgs, ROR, GRID, PIC, ISNI, Wikidata, FundRef, corda, corda_h2020, mag_id, urn,
// Used by dedup
undefined, original;
public static boolean isValid(String type) {
return EnumUtils.isValidEnum(PidType.class, type);
}
public static PidType tryValueOf(String s) {
try {
return PidType.valueOf(s);
} catch (Exception e) {
return PidType.original;
}
}
}

View File

@ -0,0 +1,33 @@
package eu.dnetlib.dhp.schema.oaf.utils;
import java.util.Comparator;
import java.util.Optional;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
public class PidValueComparator implements Comparator<StructuredProperty> {
@Override
public int compare(StructuredProperty left, StructuredProperty right) {
if (left == null && right == null)
return 0;
if (left == null)
return 1;
if (right == null)
return -1;
StructuredProperty l = CleaningFunctions.normalizePidValue(left);
StructuredProperty r = CleaningFunctions.normalizePidValue(right);
return Optional
.ofNullable(l.getValue())
.map(
lv -> Optional
.ofNullable(r.getValue())
.map(rv -> lv.compareTo(rv))
.orElse(-1))
.orElse(1);
}
}

View File

@ -0,0 +1,46 @@
package eu.dnetlib.dhp.schema.oaf.utils;
import java.util.Comparator;
import eu.dnetlib.dhp.schema.oaf.Qualifier;
/**
* Comparator for sorting the values from the dnet:review_levels vocabulary, implements the following ordering
*
* peerReviewed (0001) > nonPeerReviewed (0002) > UNKNOWN (0000)
*/
public class RefereedComparator implements Comparator<Qualifier> {
@Override
public int compare(Qualifier left, Qualifier right) {
if (left == null || left.getClassid() == null) {
return (right == null || right.getClassid() == null) ? 0 : -1;
} else if (right == null || right.getClassid() == null) {
return 1;
}
String lClass = left.getClassid();
String rClass = right.getClassid();
if (lClass.equals(rClass))
return 0;
if ("0001".equals(lClass))
return -1;
if ("0001".equals(rClass))
return 1;
if ("0002".equals(lClass))
return -1;
if ("0002".equals(rClass))
return 1;
if ("0000".equals(lClass))
return -1;
if ("0000".equals(rClass))
return 1;
return 0;
}
}

View File

@ -0,0 +1,56 @@
package eu.dnetlib.dhp.schema.oaf.utils;
import java.util.Comparator;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
public class ResultPidComparator implements Comparator<StructuredProperty> {
@Override
public int compare(StructuredProperty left, StructuredProperty right) {
PidType lClass = PidType.tryValueOf(left.getQualifier().getClassid());
PidType rClass = PidType.tryValueOf(right.getQualifier().getClassid());
if (lClass.equals(rClass))
return 0;
if (lClass.equals(PidType.doi))
return -1;
if (rClass.equals(PidType.doi))
return 1;
if (lClass.equals(PidType.pmid))
return -1;
if (rClass.equals(PidType.pmid))
return 1;
if (lClass.equals(PidType.pmc))
return -1;
if (rClass.equals(PidType.pmc))
return 1;
if (lClass.equals(PidType.handle))
return -1;
if (rClass.equals(PidType.handle))
return 1;
if (lClass.equals(PidType.arXiv))
return -1;
if (rClass.equals(PidType.arXiv))
return 1;
if (lClass.equals(PidType.nct))
return -1;
if (rClass.equals(PidType.nct))
return 1;
if (lClass.equals(PidType.pdb))
return -1;
if (rClass.equals(PidType.pdb))
return 1;
return 0;
}
}

View File

@ -0,0 +1,78 @@
package eu.dnetlib.dhp.schema.oaf.utils;
import static eu.dnetlib.dhp.schema.common.ModelConstants.CROSSREF_ID;
import java.util.Comparator;
import java.util.HashSet;
import java.util.Optional;
import java.util.stream.Collectors;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.KeyValue;
import eu.dnetlib.dhp.schema.oaf.Result;
public class ResultTypeComparator implements Comparator<Result> {
public static final ResultTypeComparator INSTANCE = new ResultTypeComparator();
@Override
public int compare(Result left, Result right) {
if (left == null && right == null)
return 0;
if (left == null)
return 1;
if (right == null)
return -1;
HashSet<String> lCf = getCollectedFromIds(left);
HashSet<String> rCf = getCollectedFromIds(right);
if (lCf.contains(CROSSREF_ID) && !rCf.contains(CROSSREF_ID)) {
return -1;
}
if (!lCf.contains(CROSSREF_ID) && rCf.contains(CROSSREF_ID)) {
return 1;
}
String lClass = left.getResulttype().getClassid();
String rClass = right.getResulttype().getClassid();
if (!lClass.equals(rClass)) {
if (lClass.equals(ModelConstants.PUBLICATION_RESULTTYPE_CLASSID))
return -1;
if (rClass.equals(ModelConstants.PUBLICATION_RESULTTYPE_CLASSID))
return 1;
if (lClass.equals(ModelConstants.DATASET_RESULTTYPE_CLASSID))
return -1;
if (rClass.equals(ModelConstants.DATASET_RESULTTYPE_CLASSID))
return 1;
if (lClass.equals(ModelConstants.SOFTWARE_RESULTTYPE_CLASSID))
return -1;
if (rClass.equals(ModelConstants.SOFTWARE_RESULTTYPE_CLASSID))
return 1;
if (lClass.equals(ModelConstants.ORP_RESULTTYPE_CLASSID))
return -1;
if (rClass.equals(ModelConstants.ORP_RESULTTYPE_CLASSID))
return 1;
}
// Else (but unlikely), lexicographical ordering will do.
return lClass.compareTo(rClass);
}
protected HashSet<String> getCollectedFromIds(Result left) {
return Optional
.ofNullable(left.getCollectedfrom())
.map(
cf -> cf
.stream()
.map(KeyValue::getKey)
.collect(Collectors.toCollection(HashSet::new)))
.orElse(new HashSet<>());
}
}

View File

@ -1,5 +1,8 @@
package eu.dnetlib.dhp.application package eu.dnetlib.dhp.application
import eu.dnetlib.dhp.common.Constants
import eu.dnetlib.dhp.utils.DHPUtils.writeHdfsFile
import scala.io.Source import scala.io.Source
/** This is the main Interface SparkApplication /** This is the main Interface SparkApplication
@ -70,4 +73,13 @@ abstract class AbstractScalaApplication(
.getOrCreate() .getOrCreate()
} }
def reportTotalSize(targetPath: String, outputBasePath: String): Unit = {
val total_items = spark.read.text(targetPath).count()
writeHdfsFile(
spark.sparkContext.hadoopConfiguration,
s"$total_items",
outputBasePath + Constants.MDSTORE_SIZE_PATH
)
}
} }

View File

@ -0,0 +1,21 @@
package eu.dnetlib.dhp.schema.oaf.utils;
import java.util.Set;
import org.junit.jupiter.api.Assertions;
import org.junit.jupiter.api.Test;
class BlackListProviderTest {
@Test
void blackListTest() {
Assertions.assertNotNull(PidBlacklistProvider.getBlacklist());
Assertions.assertNotNull(PidBlacklistProvider.getBlacklist().get("doi"));
Assertions.assertTrue(PidBlacklistProvider.getBlacklist().get("doi").size() > 0);
final Set<String> xxx = PidBlacklistProvider.getBlacklist("xxx");
Assertions.assertNotNull(xxx);
Assertions.assertEquals(0, xxx.size());
}
}

View File

@ -0,0 +1,87 @@
package eu.dnetlib.dhp.schema.oaf.utils;
import static org.junit.jupiter.api.Assertions.assertEquals;
import static org.junit.jupiter.api.Assertions.assertNotNull;
import java.io.IOException;
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.oaf.Publication;
class IdentifierFactoryTest {
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper()
.configure(DeserializationFeature.FAIL_ON_UNKNOWN_PROPERTIES, false);
@Test
void testCreateIdentifierForPublication() throws IOException {
verifyIdentifier(
"publication_doi1.json", "50|doi_________::79dbc7a2a56dc1532659f9038843256e", true);
verifyIdentifier(
"publication_doi2.json", "50|doi_________::79dbc7a2a56dc1532659f9038843256e", true);
verifyIdentifier(
"publication_doi3.json", "50|pmc_________::94e4cb08c93f8733b48e2445d04002ac", true);
verifyIdentifier(
"publication_doi4.json", "50|od______2852::38861c44e6052a8d49f59a4c39ba5e66", true);
verifyIdentifier(
"publication_doi5.json", "50|doi_________::3bef95c0ca26dd55451fc8839ea69d27", true);
verifyIdentifier(
"publication_pmc1.json", "50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f", true);
verifyIdentifier(
"publication_pmc2.json", "50|pmc_________::94e4cb08c93f8733b48e2445d04002ac", true);
verifyIdentifier(
"publication_openapc.json", "50|doi_________::79dbc7a2a56dc1532659f9038843256e", true);
final String defaultID = "50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f";
verifyIdentifier("publication_3.json", defaultID, true);
verifyIdentifier("publication_4.json", defaultID, true);
verifyIdentifier("publication_5.json", defaultID, true);
}
@Test
void testCreateIdentifierForPublicationNoHash() throws IOException {
verifyIdentifier("publication_doi1.json", "50|doi_________::10.1016/j.cmet.2010.03.013", false);
verifyIdentifier("publication_doi2.json", "50|doi_________::10.1016/j.cmet.2010.03.013", false);
verifyIdentifier("publication_pmc1.json", "50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f", false);
verifyIdentifier(
"publication_urn1.json", "50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f", false);
final String defaultID = "50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f";
verifyIdentifier("publication_3.json", defaultID, false);
verifyIdentifier("publication_4.json", defaultID, false);
verifyIdentifier("publication_5.json", defaultID, false);
}
@Test
void testCreateIdentifierForROHub() throws IOException {
verifyIdentifier(
"orp-rohub.json", "50|w3id________::afc7592914ae190a50570db90f55f9c2", true);
}
protected void verifyIdentifier(String filename, String expectedID, boolean md5) throws IOException {
final String json = IOUtils.toString(getClass().getResourceAsStream(filename));
final Publication pub = OBJECT_MAPPER.readValue(json, Publication.class);
String id = IdentifierFactory.createIdentifier(pub, md5);
System.out.println(id);
assertNotNull(id);
assertEquals(expectedID, id);
}
}

View File

@ -0,0 +1,130 @@
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.lang.reflect.InvocationTargetException;
import java.util.HashSet;
import java.util.List;
import java.util.stream.Collectors;
import org.apache.commons.beanutils.BeanUtils;
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 com.google.common.collect.Lists;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.*;
public class MergeUtilsTest {
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper()
.configure(DeserializationFeature.FAIL_ON_UNKNOWN_PROPERTIES, false);
@Test
void testMergePubs_new() throws IOException {
Publication pt = read("publication_test.json", Publication.class);
Publication p1 = read("publication_test.json", Publication.class);
assertEquals(1, pt.getCollectedfrom().size());
assertEquals(ModelConstants.CROSSREF_ID, pt.getCollectedfrom().get(0).getKey());
Instance i = new Instance();
i.setUrl(Lists.newArrayList("https://..."));
p1.getInstance().add(i);
Publication ptp1 = MergeUtils.mergePublication(pt, p1);
assertNotNull(ptp1.getInstance());
assertEquals(2, ptp1.getInstance().size());
}
@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);
}
}

View File

@ -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());
@ -178,10 +178,10 @@ class OafMapperUtilsTest {
assertEquals( assertEquals(
ModelConstants.DATASET_RESULTTYPE_CLASSID, ModelConstants.DATASET_RESULTTYPE_CLASSID,
OafMapperUtils ((Result) MergeUtils
.mergeResults(p2, d1) .merge(p2, d1))
.getResulttype() .getResulttype()
.getClassid()); .getClassid());
} }
@Test @Test
@ -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);

View File

@ -0,0 +1,12 @@
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0000/ra.v2i3.114::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.91019644836e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.0"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"4.65008652949e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0000/ra.v2i3.114"}]}]}
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0001/(aj).v3i6.458::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.91019644836e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.0"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"4.01810569717e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0001/(aj).v3i6.458"}]}]}
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0001/1587::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.91019644836e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.0"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.39172290649e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0001/1587"}]}]}
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0001/462::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"6.33235333753e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.36"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.00285265116e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0001/462"}]}]}
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0001/731::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.91019644836e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.0"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"4.01810569717e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0001/731"}]}]}
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0001/ijllis.v9i4.2066.g2482::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.91019644836e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.0"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"8.48190886761e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0001/ijllis.v9i4.2066.g2482"}]}]}
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0118/alfahim.v3i1.140::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.91019644836e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.0"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"9.88840807598e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0118/alfahim.v3i1.140"}]}]}
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0166/fk2.stagefigshare.6442896.v3::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.91019644836e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.0"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"7.28336930301e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0166/fk2.stagefigshare.6442896.v3"}]}]}
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0301/jttb.v2i1.64::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.91019644836e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.0"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"7.28336930301e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0301/jttb.v2i1.64"}]}]}
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0809/seruni.v1i1.567::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.91019644836e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.0"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"2.62959564033e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0809/seruni.v1i1.567"}]}]}
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0809/seruni.v2i1.765::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"9.40178571921e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.0559872"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"3.67659957614e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0809/seruni.v2i1.765"}]}]}
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0901/jkip.v7i3.485::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.91019644836e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.0"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"6.26204125721e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0901/jkip.v7i3.485"}]}]}

File diff suppressed because one or more lines are too long

View File

@ -0,0 +1 @@
{"id":"50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f","pid":[{"qualifier":{"classid":"scp-number"},"value":"79953761260"}]}

View File

@ -0,0 +1 @@
{"id":"50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f","pid":[]}

View File

@ -0,0 +1 @@
{"id":"50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f"}

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

View File

@ -0,0 +1,33 @@
{
"id": "50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f",
"instance": [
{
"collectedfrom": {
"key": "10|openaire____::081b82f96300b6a6e3d282bad31cb6e2",
"value": "Crossref"
},
"pid": [
{
"qualifier": {"classid": "doi"},
"value": "10.1016/j.cmet.2010.03.013"
}
]
},
{
"pid": [
{
"qualifier": {"classid": "urn"},
"value": "urn:nbn:nl:ui:29-f3ed5f9e-edf6-457e-8848-61b58a4075e2"
},
{
"qualifier": {"classid": "scp-number"},
"value": "79953761260"
},
{
"qualifier": {"classid": "pmc"},
"value": "21459329"
}
]
}
]
}

View File

@ -0,0 +1,37 @@
{
"id": "50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f",
"instance": [
{
"collectedfrom": {
"key": "10|openaire____::081b82f96300b6a6e3d282bad31cb6e2",
"value": "Crossref"
},
"pid": [
{
"qualifier": {"classid": "doi"},
"value": "10.1016/j.cmet.2010.03.013"
}
]
},
{
"collectedfrom": {
"key": "10|opendoar____::8b6dd7db9af49e67306feb59a8bdc52c",
"value": "Europe PubMed Central"
},
"pid": [
{
"qualifier": {"classid": "urn"},
"value": "urn:nbn:nl:ui:29-f3ed5f9e-edf6-457e-8848-61b58a4075e2"
},
{
"qualifier": {"classid": "scp-number"},
"value": "79953761260"
},
{
"qualifier": {"classid": "pmc"},
"value": "21459329"
}
]
}
]
}

View File

@ -0,0 +1,37 @@
{
"id": "50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f",
"instance": [
{
"collectedfrom": {
"key": "10|opendoar____::358aee4cc897452c00244351e4d91f69",
"value": "Zenodo"
},
"pid": [
{
"qualifier": {"classid": "doi"},
"value": "10.1016/j.cmet.2010.03.013"
}
]
},
{
"collectedfrom": {
"key": "10|opendoar____::8b6dd7db9af49e67306feb59a8bdc52c",
"value": "Europe PubMed Central"
},
"pid": [
{
"qualifier": {"classid": "urn"},
"value": "urn:nbn:nl:ui:29-f3ed5f9e-edf6-457e-8848-61b58a4075e2"
},
{
"qualifier": {"classid": "scp-number"},
"value": "79953761260"
},
{
"qualifier": {"classid": "pmc"},
"value": "21459329"
}
]
}
]
}

View File

@ -0,0 +1,37 @@
{
"id": "50|od______2852::38861c44e6052a8d49f59a4c39ba5e66",
"instance": [
{
"collectedfrom": {
"key": "10|opendoar____::358aee4cc897452c00244351e4d91f69",
"value": "Zenodo"
},
"pid": [
{
"qualifier": {"classid": "doi"},
"value": "10.1016/j.cmet.2010.03.013"
},
{
"qualifier": {"classid": "handle"},
"value": "11012/83840"
}
]
},
{
"collectedfrom": {
"key": "10|opendoar____::2852",
"value": "Digital library of Brno University of Technology"
},
"pid": [
{
"qualifier": {"classid": "pmc"},
"value": "21459329"
},
{
"qualifier": {"classid": "handle"},
"value": "11012/83840"
}
]
}
]
}

View File

@ -0,0 +1,37 @@
{
"id": "50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f",
"instance": [
{
"collectedfrom": {
"key": "10|opendoar____::358aee4cc897452c00244351e4d91f69",
"value": "Zenodo"
},
"pid": [
{
"qualifier": {"classid": "doi"},
"value": "10.5281/zenodo.5121485"
}
]
},
{
"collectedfrom": {
"key": "10|opendoar____::8b6dd7db9af49e67306feb59a8bdc52c",
"value": "Europe PubMed Central"
},
"pid": [
{
"qualifier": {"classid": "urn"},
"value": "urn:nbn:nl:ui:29-f3ed5f9e-edf6-457e-8848-61b58a4075e2"
},
{
"qualifier": {"classid": "scp-number"},
"value": "79953761260"
},
{
"qualifier": {"classid": "pmc"},
"value": "21459329"
}
]
}
]
}

View File

@ -0,0 +1,3 @@
{"id":"50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f", "resulttype" : { "classid" : "publication" }, "pid":[{"qualifier":{"classid":"doi"},"value":"10.1016/j.cmet.2011.03.013"},{"qualifier":{"classid":"urn"},"value":"urn:nbn:nl:ui:29-f3ed5f9e-edf6-457e-8848-61b58a4075e2"},{"qualifier":{"classid":"scp-number"},"value":"79953761260"},{"qualifier":{"classid":"pmc"},"value":"21459329"}], "collectedfrom" : [ { "key" : "10|openaire____::081b82f96300b6a6e3d282bad31cb6e2", "value" : "Crossref"} ], "isGreen": null, "openAccessColor": "gold", "isInDiamondJournal": null, "publiclyFunded": null}
{"id":"50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1g", "resulttype" : { "classid" : "publication" }, "isGreen": true, "openAccessColor": "gold", "isInDiamondJournal": true, "publiclyFunded": false }
{"id":"50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1h", "resulttype" : { "classid" : "publication" }, "isGreen": false, "openAccessColor": null, "isInDiamondJournal": true, "publiclyFunded": false }

View File

@ -0,0 +1,3 @@
{"id":"50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f", "resulttype" : { "classid" : "publication" }, "pid":[{"qualifier":{"classid":"doi"},"value":"10.1016/j.cmet.2011.03.013"},{"qualifier":{"classid":"urn"},"value":"urn:nbn:nl:ui:29-f3ed5f9e-edf6-457e-8848-61b58a4075e2"},{"qualifier":{"classid":"scp-number"},"value":"79953761260"},{"qualifier":{"classid":"pmc"},"value":"21459329"}], "collectedfrom" : [ { "key" : "10|openaire____::081b82f96300b6a6e3d282bad31cb6e2", "value" : "Crossref"} ], "isGreen": null, "openAccessColor": "gold", "isInDiamondJournal": null, "publiclyFunded": null}
{"id":"50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1g", "resulttype" : { "classid" : "publication" }, "isGreen": true, "openAccessColor": "bronze", "isInDiamondJournal": true, "publiclyFunded": false }
{"id":"50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1h", "resulttype" : { "classid" : "publication" }, "isGreen": false, "openAccessColor": null, "isInDiamondJournal": true, "publiclyFunded": false }

View File

@ -0,0 +1,31 @@
{
"id": "50|openapc_____::000023f9cb6e3a247c764daec4273cbc",
"resuttype": {
"classid": "publication"
},
"instance": [
{
"collectedfrom": {
"key": "10|apc_________::e2b1600b229fc30663c8a1f662debddf",
"value": "OpenAPC Global Initiative"
},
"pid": [
{
"qualifier": {"classid": "doi"},
"value": "10.1016/j.cmet.2010.03.013"
},
{
"qualifier": {"classid": "pmc"},
"value": "21459329"
},
{
"qualifier": {"classid": "pmid"},
"value": "25811027"
}
],
"url":["https://doi.org/10.1155/2015/439379"]
}
]
}

View File

@ -0,0 +1,17 @@
{
"id": "50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f",
"pid": [
{
"qualifier": {"classid": "urn"},
"value": "urn:nbn:nl:ui:29-f3ed5f9e-edf6-457e-8848-61b58a4075e2"
},
{
"qualifier": {"classid": "scp-number"},
"value": "79953761260"
},
{
"qualifier": {"classid": "pmc"},
"value": "21459329"
}
]
}

View File

@ -0,0 +1,21 @@
{
"id":"50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f",
"instance": [
{
"collectedfrom": {
"key": "10|opendoar____::8b6dd7db9af49e67306feb59a8bdc52c",
"value": "Europe PubMed Central"
},
"pid": [
{
"qualifier": {"classid": "doi"},
"value": "10.1016/j.cmet.2010.03.013"
},
{
"qualifier":{"classid":"pmc"},
"value":"21459329"
}
]
}
]
}

View File

@ -0,0 +1,428 @@
{
"author": [
{
"affiliation": null,
"fullname": "Deymier, Ghislaine",
"name": "Ghislaine",
"pid": [],
"rank": 1,
"surname": "Deymier"
},
{
"affiliation": null,
"fullname": "Gaschet, Frédéric",
"name": "Frédéric",
"pid": [],
"rank": 2,
"surname": "Gaschet"
},
{
"affiliation": null,
"fullname": "Pouyanne, Guillaume",
"name": "Guillaume",
"pid": [],
"rank": 3,
"surname": "Pouyanne"
}
],
"bestaccessright": {
"classid": "OPEN",
"classname": "Open Access",
"schemeid": "dnet:access_modes",
"schemename": "dnet:access_modes"
},
"collectedfrom": [
{
"key" : "10|openaire____::081b82f96300b6a6e3d282bad31cb6e2",
"value" : "Crossref"
}
],
"context": [],
"contributor": [],
"country": [],
"coverage": [],
"dataInfo": {
"deletedbyinference": false,
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "sysimport:crosswalk:repository",
"classname": "Harvested",
"schemeid": "dnet:provenanceActions",
"schemename": "dnet:provenanceActions"
},
"trust": "0.9"
},
"dateofacceptance": {
"dataInfo": {
"deletedbyinference": false,
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "sysimport:crosswalk:repository",
"classname": "Harvested",
"schemeid": "dnet:provenanceActions",
"schemename": "dnet:provenanceActions"
},
"trust": "0.9"
},
"value": "2013-11-30"
},
"dateofcollection": "2024-02-28T00:22:13+0000",
"dateoftransformation": "2024-03-06T08:43:13.253Z",
"description": [
{
"dataInfo": {
"deletedbyinference": false,
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "sysimport:crosswalk:repository",
"classname": "Harvested",
"schemeid": "dnet:provenanceActions",
"schemename": "dnet:provenanceActions"
},
"trust": "0.9"
},
"value": "For analyzing the reciprocal interaction between urban sprawl and car use, research has first focused on the link between urban density and mobility. By looking for a reduction in energy consumption, cities have favoured a compact planning development. Then reflection has broadened from the simple density to the wider, multi-dimensional concept of urban form. This controversy has led to a renewal of analysis in term of the costs of urban growth, notably by comparing the costs of \"compact\" and \"sprawled\" development. The idea is to compare the mobility costs of different urban forms. However, most often because of a lack of data, such studies are scarce. This paper suggests an innovative method to compute mobility costs at an infra-urban scale : The Spatialized Travel Account (STA). It is based on the CERTU's travel account methodology at a metropolitan scale. It puts forward an accurate estimate of the mobility costs for each transport mode (individual and public) and for each type of payer (households, firms, local authorities...). In order to test the relationships between mobility costs and urban form, we link the computed costs to morphological characteristics of infra-urban zones, taking in account sociodemographic characteristics of households."
},
{
"dataInfo": {
"deletedbyinference": false,
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "sysimport:crosswalk:repository",
"classname": "Harvested",
"schemeid": "dnet:provenanceActions",
"schemename": "dnet:provenanceActions"
},
"trust": "0.9"
},
"value": "L'interaction réciproque entre étalement urbain et usage de l'automobile a conduit la recherche à se focaliser sur le lien entre les densités urbaines et la mobilité. En cherchant à réduire leur consommation d'énergie pour les transports, et donc leurs émissions de Gaz à Effet de Serre, les villes ont alors cherché à planifier la \" ville compacte \", privilégiant notamment la reconstruction de la ville sur elle-même et la densification. Par la suite, la réflexion s'est élargie de la simple densité à la notion de forme urbaine et à toutes ses dimensions. Cette controverse devait conduire à un renouveau des analyses en termes de coûts de la croissance urbaine : le débat reste vif, encore aujourd'hui, sur les coûts comparés de la ville étalée et de la ville compacte. Plus largement, il s'agit d'explorer les coûts des différentes formes urbaines en termes de mobilité. Malgré cela, généralement pour des raisons de disponibilité de données, les études sur le sujet restent extrêmement rares. Cet article propose un outil novateur pour mesurer les coûts de la mobilité à l'échelle intraurbaine : le Compte Déplacements Territorialisé (CDT). Il s'inspire de la méthode développée par le CERTU pour l'établissement des Comptes Déplacements Voyageurs à l'échelle métropolitaine. Le CDT propose, pour chacune des zones de l'agglomération, une estimation précise de l'ensemble des coûts liés aux déplacements de personnes, ventilés par mode de transport (individuels et collectifs) et par type de financeurs (ménages, entreprises, collectivités territoriales, etc.). Nous proposons une application de cette méthode à la controverse sur le lien entre forme urbaine et coûts de la mobilité. Les coûts sont reliés aux caractéristiques morphologiques des zones (en termes de densité et de diversité, notamment), en prenant soin de contrôler les facteurs socio-économiques qui influent traditionnellement sur les comportements de mobilité (taille du ménage, revenu, etc.)."
}
],
"eoscifguidelines": [],
"externalReference": [],
"extraInfo": [],
"format": [
{
"dataInfo": {
"deletedbyinference": false,
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "sysimport:crosswalk:repository",
"classname": "Harvested",
"schemeid": "dnet:provenanceActions",
"schemename": "dnet:provenanceActions"
},
"trust": "0.9"
},
"value": "application/pdf"
}
],
"fulltext": [],
"id": "50|06cdd3ff4700::4826ac62a11a957fe332e2c291dcfcca",
"instance": [
{
"accessright": {
"classid": "OPEN",
"classname": "Open Access",
"schemeid": "dnet:access_modes",
"schemename": "dnet:access_modes"
},
"alternateIdentifier": [
{
"dataInfo": {
"deletedbyinference": false,
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "sysimport:crosswalk:repository",
"classname": "Harvested",
"schemeid": "dnet:provenanceActions",
"schemename": "dnet:provenanceActions"
},
"trust": "0.9"
},
"qualifier": {
"classid": "doi",
"classname": "Digital Object Identifier",
"schemeid": "dnet:pid_types",
"schemename": "dnet:pid_types"
},
"value": "10.46298/cst.12132"
}
],
"collectedfrom": {
"key": "10|openaire____::6824b298c96ba906a3e6a70593affbf5",
"value": "Episciences"
},
"dateofacceptance": {
"dataInfo": {
"deletedbyinference": false,
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "sysimport:crosswalk:repository",
"classname": "Harvested",
"schemeid": "dnet:provenanceActions",
"schemename": "dnet:provenanceActions"
},
"trust": "0.9"
},
"value": "2013-11-30"
},
"hostedby": {
"key": "10|openaire____::6824b298c96ba906a3e6a70593affbf5",
"value": "Episciences"
},
"instanceTypeMapping": [
{
"originalType": "http://purl.org/coar/resource_type/c_6501",
"typeCode": "http://purl.org/coar/resource_type/c_6501",
"typeLabel": "journal article",
"vocabularyName": "openaire::coar_resource_types_3_1"
},
{
"originalType": "http://purl.org/coar/resource_type/c_6501",
"typeCode": "Article",
"typeLabel": "Article",
"vocabularyName": "openaire::user_resource_types"
}
],
"instancetype": {
"classid": "0001",
"classname": "Article",
"schemeid": "dnet:publication_resource",
"schemename": "dnet:publication_resource"
},
"license": {
"dataInfo": {
"deletedbyinference": false,
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "sysimport:crosswalk:repository",
"classname": "Harvested",
"schemeid": "dnet:provenanceActions",
"schemename": "dnet:provenanceActions"
},
"trust": "0.9"
},
"value": "CC BY NC SA"
},
"pid": [],
"refereed": {
"classid": "0002",
"classname": "nonPeerReviewed",
"schemeid": "dnet:review_levels",
"schemename": "dnet:review_levels"
},
"url": [
"https://doi.org/10.46298/cst.12132",
"https://cst.episciences.org/12132"
]
}
],
"language": {
"classid": "fra/fre",
"classname": "French",
"schemeid": "dnet:languages",
"schemename": "dnet:languages"
},
"lastupdatetimestamp": 1710636106633,
"metaResourceType": {
"classid": "Research Literature",
"classname": "Research Literature",
"schemeid": "openaire::meta_resource_types",
"schemename": "openaire::meta_resource_types"
},
"originalId": [
"oai:episciences.org:cst:12132",
"50|06cdd3ff4700::4826ac62a11a957fe332e2c291dcfcca"
],
"pid": [],
"publisher": {
"dataInfo": {
"deletedbyinference": false,
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "sysimport:crosswalk:repository",
"classname": "Harvested",
"schemeid": "dnet:provenanceActions",
"schemename": "dnet:provenanceActions"
},
"trust": "0.9"
},
"value": "episciences.org"
},
"relevantdate": [
{
"dataInfo": {
"deletedbyinference": false,
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "sysimport:crosswalk:repository",
"classname": "Harvested",
"schemeid": "dnet:provenanceActions",
"schemename": "dnet:provenanceActions"
},
"trust": "0.9"
},
"qualifier": {
"classid": "Accepted",
"classname": "Accepted",
"schemeid": "dnet:dataCite_date",
"schemename": "dnet:dataCite_date"
},
"value": "2024-02-11"
},
{
"dataInfo": {
"deletedbyinference": false,
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "sysimport:crosswalk:repository",
"classname": "Harvested",
"schemeid": "dnet:provenanceActions",
"schemename": "dnet:provenanceActions"
},
"trust": "0.9"
},
"qualifier": {
"classid": "issued",
"classname": "issued",
"schemeid": "dnet:dataCite_date",
"schemename": "dnet:dataCite_date"
},
"value": "2013-11-30"
},
{
"dataInfo": {
"deletedbyinference": false,
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "sysimport:crosswalk:repository",
"classname": "Harvested",
"schemeid": "dnet:provenanceActions",
"schemename": "dnet:provenanceActions"
},
"trust": "0.9"
},
"qualifier": {
"classid": "available",
"classname": "available",
"schemeid": "dnet:dataCite_date",
"schemename": "dnet:dataCite_date"
},
"value": "2013-11-30"
}
],
"resourcetype": {
"classid": "journal article",
"classname": "journal article",
"schemeid": "dnet:dataCite_resource",
"schemename": "dnet:dataCite_resource"
},
"resulttype": {
"classid": "publication",
"classname": "publication",
"schemeid": "dnet:result_typologies",
"schemename": "dnet:result_typologies"
},
"source": [],
"subject": [
{
"dataInfo": {
"deletedbyinference": false,
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "sysimport:crosswalk:repository",
"classname": "Harvested",
"schemeid": "dnet:provenanceActions",
"schemename": "dnet:provenanceActions"
},
"trust": "0.9"
},
"qualifier": {
"classid": "keyword",
"classname": "keyword",
"schemeid": "dnet:subject_classification_typologies",
"schemename": "dnet:subject_classification_typologies"
},
"value": "JEL: H - Public Economics/H.H7 - State and Local Government • Intergovernmental Relations/H.H7.H72 - State and Local Budget and Expenditures"
},
{
"dataInfo": {
"deletedbyinference": false,
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "sysimport:crosswalk:repository",
"classname": "Harvested",
"schemeid": "dnet:provenanceActions",
"schemename": "dnet:provenanceActions"
},
"trust": "0.9"
},
"qualifier": {
"classid": "keyword",
"classname": "keyword",
"schemeid": "dnet:subject_classification_typologies",
"schemename": "dnet:subject_classification_typologies"
},
"value": "Local public finance"
},
{
"dataInfo": {
"deletedbyinference": false,
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "sysimport:crosswalk:repository",
"classname": "Harvested",
"schemeid": "dnet:provenanceActions",
"schemename": "dnet:provenanceActions"
},
"trust": "0.9"
},
"qualifier": {
"classid": "keyword",
"classname": "keyword",
"schemeid": "dnet:subject_classification_typologies",
"schemename": "dnet:subject_classification_typologies"
},
"value": "JEL: R - Urban, Rural, Regional, Real Estate, and Transportation Economics/R.R5 - Regional Government Analysis/R.R5.R51 - Finance in Urban and Rural Economies"
}
],
"title": [
{
"dataInfo": {
"deletedbyinference": false,
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "sysimport:crosswalk:repository",
"classname": "Harvested",
"schemeid": "dnet:provenanceActions",
"schemename": "dnet:provenanceActions"
},
"trust": "0.9"
},
"qualifier": {
"classid": "main title",
"classname": "main title",
"schemeid": "dnet:dataCite_title",
"schemename": "dnet:dataCite_title"
},
"value": "Urban form and the costs of daily mobility. The spatialized travel account tool and its application to the Bordeaux metropolitan area"
}
]
}

View File

@ -0,0 +1,23 @@
{
"id": "50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f",
"pid": [
{
"qualifier": {
"classid": "urn"
},
"value": "urn:nbn:nl:ui:29-f3ed5f9e-edf6-457e-8848-61b58a4075e2"
},
{
"qualifier": {
"classid": "scp-number"
},
"value": "79953761260"
},
{
"qualifier": {
"classid": "pmcid"
},
"value": "21459329"
}
]
}

File diff suppressed because one or more lines are too long

View File

@ -20,7 +20,7 @@ public class WordsStatsSuffixPrefixChain extends AbstractClusteringFunction {
return suffixPrefixChain(s, param("mod")); return suffixPrefixChain(s, param("mod"));
} }
private Collection<String> suffixPrefixChain(String s, int mod) { static Collection<String> suffixPrefixChain(String s, int mod) {
// create the list of words from the string (remove short words) // create the list of words from the string (remove short words)
List<String> wordsList = Arrays List<String> wordsList = Arrays
@ -38,7 +38,7 @@ public class WordsStatsSuffixPrefixChain extends AbstractClusteringFunction {
} }
private Collection<String> doSuffixPrefixChain(List<String> wordsList, String prefix) { static private Collection<String> doSuffixPrefixChain(List<String> wordsList, String prefix) {
Set<String> set = Sets.newLinkedHashSet(); Set<String> set = Sets.newLinkedHashSet();
switch (wordsList.size()) { switch (wordsList.size()) {
@ -80,12 +80,16 @@ public class WordsStatsSuffixPrefixChain extends AbstractClusteringFunction {
} }
private String suffix(String s, int len) { private static String suffix(String s, int len) {
return s.substring(s.length() - len); return s.substring(s.length() - len);
} }
private String prefix(String s, int len) { private static String prefix(String s, int len) {
return s.substring(0, len); return s.substring(0, len);
} }
static public void main(String[] args) {
String title = "MY LIFE AS A BOSON: THE STORY OF \"THE HIGGS\"".toLowerCase();
System.out.println(suffixPrefixChain(title, 10));
}
} }

View File

@ -1,16 +1,18 @@
package eu.dnetlib.pace.tree; package eu.dnetlib.pace.tree;
import java.util.List;
import java.util.Map;
import java.util.stream.Collectors;
import com.wcohen.ss.AbstractStringDistance; import com.wcohen.ss.AbstractStringDistance;
import eu.dnetlib.pace.config.Config; import eu.dnetlib.pace.config.Config;
import eu.dnetlib.pace.model.Person; import eu.dnetlib.pace.model.Person;
import eu.dnetlib.pace.tree.support.AbstractListComparator; import eu.dnetlib.pace.tree.support.AbstractListComparator;
import eu.dnetlib.pace.tree.support.ComparatorClass; import eu.dnetlib.pace.tree.support.ComparatorClass;
import eu.dnetlib.pace.util.AuthorMatchers;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;
import java.util.function.BiFunction;
import java.util.stream.Collectors;
@ComparatorClass("authorsMatch") @ComparatorClass("authorsMatch")
public class AuthorsMatch extends AbstractListComparator { public class AuthorsMatch extends AbstractListComparator {
@ -41,24 +43,36 @@ public class AuthorsMatch extends AbstractListComparator {
} }
@Override @Override
public double compare(final List<String> a, final List<String> b, final Config conf) { public double compare(final List<String> left, final List<String> right, final Config conf) {
if (a.isEmpty() || b.isEmpty()) if (left.isEmpty() || right.isEmpty())
return -1; return -1;
if (a.size() > SIZE_THRESHOLD || b.size() > SIZE_THRESHOLD) if (left.size() > SIZE_THRESHOLD || right.size() > SIZE_THRESHOLD)
return 1.0; return 1.0;
int maxMiss = Integer.MAX_VALUE;
List<Person> bList = b.stream().map(author -> new Person(author, false)).collect(Collectors.toList());
Double threshold = getDoubleParam("threshold"); Double threshold = getDoubleParam("threshold");
int maxMiss = Integer.MAX_VALUE;
if (threshold != null && threshold >= 0.0 && threshold <= 1.0 && a.size() == b.size()) { if (threshold != null && threshold >= 0.0 && threshold <= 1.0 && left.size() == right.size()) {
maxMiss = (int) Math.floor((1 - threshold) * Math.max(a.size(), b.size())); maxMiss = (int) Math.floor((1 - threshold) * Math.max(left.size(), right.size()));
} }
int common = 0; int common = 0;
List<String> a = new ArrayList<>(left);
List<String> b = new ArrayList<>(right);
common += AuthorMatchers
.removeMatches(a, b, (BiFunction<String, String, Object>) AuthorMatchers::matchEqualsIgnoreCase)
.size() / 2;
common += AuthorMatchers
.removeMatches(a, b, (BiFunction<String, String, Object>) AuthorMatchers::matchOrderedTokenAndAbbreviations)
.size() / 2;
List<Person> bList = b.stream().map(author -> new Person(author, false)).collect(Collectors.toList());
// compare each element of List1 with each element of List2 // compare each element of List1 with each element of List2
int alreadyMatched = common;
for (int i = 0; i < a.size(); i++) { for (int i = 0; i < a.size(); i++) {
Person p1 = new Person(a.get(i), false); Person p1 = new Person(a.get(i), false);
@ -123,13 +137,13 @@ public class AuthorsMatch extends AbstractListComparator {
} }
} }
if (i - common > maxMiss) { if (i - common - alreadyMatched > maxMiss) {
return 0.0; return 0.0;
} }
} }
// normalization factor to compute the score // normalization factor to compute the score
int normFactor = a.size() == b.size() ? a.size() : (a.size() + b.size() - common); int normFactor = left.size() == right.size() ? left.size() : (left.size() + right.size() - common);
if (TYPE.equals("percentage")) { if (TYPE.equals("percentage")) {
return (double) common / normFactor; return (double) common / normFactor;
@ -160,5 +174,4 @@ public class AuthorsMatch extends AbstractListComparator {
public String normalization(String s) { public String normalization(String s) {
return normalize(utf8(cleanup(s))); return normalize(utf8(cleanup(s)));
} }
} }

View File

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

View File

@ -0,0 +1,112 @@
package eu.dnetlib.pace.util
import java.util.Locale
import java.util.regex.Pattern
import scala.util.control.Breaks.{break, breakable}
object AuthorMatchers {
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
if (res)
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)
}
def removeMatches(
graph_authors: java.util.List[String],
orcid_authors: java.util.List[String],
matchingFunc: java.util.function.BiFunction[String,String,Boolean]
) : java.util.List[String] = {
removeMatches(graph_authors, orcid_authors, (a, b) => matchingFunc(a,b))
}
def removeMatches(
graph_authors: java.util.List[String],
orcid_authors: java.util.List[String],
matchingFunc: (String, String) => Boolean
) : java.util.List[String] = {
val matched = new java.util.ArrayList[String]()
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.add(author)
matched.add(orcid)
break()
}
}
}
}
}
matched
}
}

View File

@ -7,8 +7,7 @@ import java.util.function.BiFunction;
import eu.dnetlib.dhp.common.FunctionalInterfaceSupport.SerializableSupplier; import eu.dnetlib.dhp.common.FunctionalInterfaceSupport.SerializableSupplier;
import eu.dnetlib.dhp.schema.oaf.Oaf; import eu.dnetlib.dhp.schema.oaf.Oaf;
import eu.dnetlib.dhp.schema.oaf.OafEntity; import eu.dnetlib.dhp.schema.oaf.utils.MergeUtils;
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")

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

@ -8,6 +8,7 @@ import static org.mockito.Mockito.*;
import java.util.function.BiFunction; import java.util.function.BiFunction;
import org.junit.jupiter.api.Disabled;
import org.junit.jupiter.api.Nested; import org.junit.jupiter.api.Nested;
import org.junit.jupiter.api.Test; import org.junit.jupiter.api.Test;
@ -85,6 +86,7 @@ public class MergeAndGetTest {
} }
@Test @Test
@Disabled
void shouldBehaveProperlyForRelationAndRelation() { void shouldBehaveProperlyForRelationAndRelation() {
// given // given
Relation a = mock(Relation.class); Relation a = mock(Relation.class);
@ -96,7 +98,9 @@ public class MergeAndGetTest {
// then // then
Oaf x = fn.get().apply(a, b); Oaf x = fn.get().apply(a, b);
assertTrue(Relation.class.isAssignableFrom(x.getClass())); assertTrue(Relation.class.isAssignableFrom(x.getClass()));
verify(a).mergeFrom(b);
// TODO should be reimplemented
// verify(a).mergeFrom(b);
assertEquals(a, x); assertEquals(a, x);
} }
@ -145,6 +149,7 @@ public class MergeAndGetTest {
} }
@Test @Test
@Disabled
void shouldBehaveProperlyForOafEntityAndOafEntity() { void shouldBehaveProperlyForOafEntityAndOafEntity() {
// given // given
OafEntity a = mock(OafEntity.class); OafEntity a = mock(OafEntity.class);
@ -156,7 +161,9 @@ public class MergeAndGetTest {
// then // then
Oaf x = fn.get().apply(a, b); Oaf x = fn.get().apply(a, b);
assertTrue(OafEntity.class.isAssignableFrom(x.getClass())); assertTrue(OafEntity.class.isAssignableFrom(x.getClass()));
verify(a).mergeFrom(b);
// TODO should be reimplemented
// verify(a).mergeFrom(b);
assertEquals(a, x); assertEquals(a, x);
} }
} }

View File

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

View File

@ -64,6 +64,12 @@ 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 dataciteInputPath = parser.get("dataciteInputPath");
log.info("dataciteInputPath: {}", dataciteInputPath);
final String outputPath = parser.get("outputPath"); final String outputPath = parser.get("outputPath");
log.info("outputPath: {}", outputPath); log.info("outputPath: {}", outputPath);
@ -85,8 +91,20 @@ 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);
List<KeyValue> collectedFromDatacite = OafMapperUtils
.listKeyValues(ModelConstants.DATACITE_ID, "Datacite");
JavaPairRDD<Text, Text> dataciteRelations = prepareAffiliationRelations(
spark, dataciteInputPath, collectedFromDatacite);
crossrefRelations crossrefRelations
.union(pubmedRelations) .union(pubmedRelations)
.union(openAPCRelations)
.union(dataciteRelations)
.saveAsHadoopFile( .saveAsHadoopFile(
outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class); outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class);

View File

@ -34,6 +34,10 @@ 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) {

View File

@ -75,6 +75,7 @@ public class GetFOSSparkJob implements Serializable {
fosData.map((MapFunction<Row, FOSDataModel>) r -> { fosData.map((MapFunction<Row, FOSDataModel>) r -> {
FOSDataModel fosDataModel = new FOSDataModel(); FOSDataModel fosDataModel = new FOSDataModel();
fosDataModel.setDoi(r.getString(0).toLowerCase()); fosDataModel.setDoi(r.getString(0).toLowerCase());
fosDataModel.setOaid(r.getString(1).toLowerCase());
fosDataModel.setLevel1(r.getString(2)); fosDataModel.setLevel1(r.getString(2));
fosDataModel.setLevel2(r.getString(3)); fosDataModel.setLevel2(r.getString(3));
fosDataModel.setLevel3(r.getString(4)); fosDataModel.setLevel3(r.getString(4));

View File

@ -16,12 +16,14 @@ import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoders; import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.SaveMode; import org.apache.spark.sql.SaveMode;
import org.apache.spark.sql.SparkSession; import org.apache.spark.sql.SparkSession;
import org.jetbrains.annotations.NotNull;
import org.slf4j.Logger; import org.slf4j.Logger;
import org.slf4j.LoggerFactory; import org.slf4j.LoggerFactory;
import eu.dnetlib.dhp.actionmanager.createunresolvedentities.model.FOSDataModel; import eu.dnetlib.dhp.actionmanager.createunresolvedentities.model.FOSDataModel;
import eu.dnetlib.dhp.application.ArgumentApplicationParser; import eu.dnetlib.dhp.application.ArgumentApplicationParser;
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.oaf.Result; import eu.dnetlib.dhp.schema.oaf.Result;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty; import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
import eu.dnetlib.dhp.schema.oaf.Subject; import eu.dnetlib.dhp.schema.oaf.Subject;
@ -52,62 +54,90 @@ public class PrepareFOSSparkJob implements Serializable {
final String outputPath = parser.get("outputPath"); final String outputPath = parser.get("outputPath");
log.info("outputPath: {}", outputPath); log.info("outputPath: {}", outputPath);
final Boolean distributeDOI = Optional
.ofNullable(parser.get("distributeDoi"))
.map(Boolean::valueOf)
.orElse(Boolean.TRUE);
SparkConf conf = new SparkConf(); SparkConf conf = new SparkConf();
runWithSparkSession( runWithSparkSession(
conf, conf,
isSparkSessionManaged, isSparkSessionManaged,
spark -> { spark -> {
distributeFOSdois( if (distributeDOI)
spark, distributeFOSdois(
sourcePath, spark,
sourcePath,
outputPath); outputPath);
else
distributeFOSoaid(spark, sourcePath, outputPath);
}); });
} }
private static void distributeFOSoaid(SparkSession spark, String sourcePath, String outputPath) {
Dataset<FOSDataModel> fosDataset = readPath(spark, sourcePath, FOSDataModel.class);
fosDataset
.groupByKey((MapFunction<FOSDataModel, String>) v -> v.getOaid().toLowerCase(), Encoders.STRING())
.mapGroups((MapGroupsFunction<String, FOSDataModel, Result>) (k, it) -> {
return getResult(ModelSupport.getIdPrefix(Result.class) + "|" + k, it);
}, Encoders.bean(Result.class))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(outputPath + "/fos");
}
@NotNull
private static Result getResult(String k, Iterator<FOSDataModel> it) {
Result r = new Result();
FOSDataModel first = it.next();
r.setId(k);
HashSet<String> level1 = new HashSet<>();
HashSet<String> level2 = new HashSet<>();
HashSet<String> level3 = new HashSet<>();
HashSet<String> level4 = new HashSet<>();
addLevels(level1, level2, level3, level4, first);
it.forEachRemaining(v -> addLevels(level1, level2, level3, level4, v));
List<Subject> sbjs = new ArrayList<>();
level1
.forEach(l -> add(sbjs, getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID)));
level2
.forEach(l -> add(sbjs, getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID)));
level3
.forEach(
l -> add(sbjs, getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID, true)));
level4
.forEach(
l -> add(sbjs, getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID, true)));
r.setSubject(sbjs);
r
.setDataInfo(
OafMapperUtils
.dataInfo(
false, null, true,
false,
OafMapperUtils
.qualifier(
ModelConstants.PROVENANCE_ENRICH,
null,
ModelConstants.DNET_PROVENANCE_ACTIONS,
ModelConstants.DNET_PROVENANCE_ACTIONS),
null));
return r;
}
private static void distributeFOSdois(SparkSession spark, String sourcePath, String outputPath) { private static void distributeFOSdois(SparkSession spark, String sourcePath, String outputPath) {
Dataset<FOSDataModel> fosDataset = readPath(spark, sourcePath, FOSDataModel.class); Dataset<FOSDataModel> fosDataset = readPath(spark, sourcePath, FOSDataModel.class);
fosDataset fosDataset
.groupByKey((MapFunction<FOSDataModel, String>) v -> v.getDoi().toLowerCase(), Encoders.STRING()) .groupByKey((MapFunction<FOSDataModel, String>) v -> v.getDoi().toLowerCase(), Encoders.STRING())
.mapGroups((MapGroupsFunction<String, FOSDataModel, Result>) (k, it) -> { .mapGroups(
Result r = new Result(); (MapGroupsFunction<String, FOSDataModel, Result>) (k,
FOSDataModel first = it.next(); it) -> getResult(DHPUtils.generateUnresolvedIdentifier(k, DOI), it),
r.setId(DHPUtils.generateUnresolvedIdentifier(k, DOI)); Encoders.bean(Result.class))
HashSet<String> level1 = new HashSet<>();
HashSet<String> level2 = new HashSet<>();
HashSet<String> level3 = new HashSet<>();
HashSet<String> level4 = new HashSet<>();
addLevels(level1, level2, level3, level4, first);
it.forEachRemaining(v -> addLevels(level1, level2, level3, level4, v));
List<Subject> sbjs = new ArrayList<>();
level1
.forEach(l -> add(sbjs, getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID)));
level2
.forEach(l -> add(sbjs, getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID)));
level3
.forEach(
l -> add(sbjs, getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID, true)));
level4
.forEach(
l -> add(sbjs, getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID, true)));
r.setSubject(sbjs);
r
.setDataInfo(
OafMapperUtils
.dataInfo(
false, null, true,
false,
OafMapperUtils
.qualifier(
ModelConstants.PROVENANCE_ENRICH,
null,
ModelConstants.DNET_PROVENANCE_ACTIONS,
ModelConstants.DNET_PROVENANCE_ACTIONS),
null));
return r;
}, Encoders.bean(Result.class))
.write() .write()
.mode(SaveMode.Overwrite) .mode(SaveMode.Overwrite)
.option("compression", "gzip") .option("compression", "gzip")

View File

@ -0,0 +1,92 @@
package eu.dnetlib.dhp.actionmanager.fosnodoi;
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.JavaPairRDD;
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.opencitations.model.COCI;
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.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();
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/fosnodoi/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("sourcePath");
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) {
spark
.read()
.textFile(inputPath)
.map(
(MapFunction<String, Result>) value -> OBJECT_MAPPER.readValue(value, Result.class),
Encoders.bean(Result.class))
.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);
}
}

View File

@ -22,12 +22,14 @@ 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.core.JsonProcessingException;
import com.fasterxml.jackson.databind.ObjectMapper; import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.actionmanager.opencitations.model.COCI; import eu.dnetlib.dhp.actionmanager.opencitations.model.COCI;
import eu.dnetlib.dhp.application.ArgumentApplicationParser; import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.schema.action.AtomicAction; import eu.dnetlib.dhp.schema.action.AtomicAction;
import eu.dnetlib.dhp.schema.common.ModelConstants; import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.*; import eu.dnetlib.dhp.schema.oaf.*;
import eu.dnetlib.dhp.schema.oaf.utils.*; import eu.dnetlib.dhp.schema.oaf.utils.*;
import eu.dnetlib.dhp.utils.DHPUtils; import eu.dnetlib.dhp.utils.DHPUtils;
@ -37,16 +39,12 @@ public class CreateActionSetSparkJob implements Serializable {
public static final String OPENCITATIONS_CLASSID = "sysimport:crosswalk:opencitations"; public static final String OPENCITATIONS_CLASSID = "sysimport:crosswalk:opencitations";
public static final String OPENCITATIONS_CLASSNAME = "Imported from OpenCitations"; public static final String OPENCITATIONS_CLASSNAME = "Imported from OpenCitations";
// DOI-to-DOI citations
public static final String COCI = "COCI";
// PMID-to-PMID citations
public static final String POCI = "POCI";
private static final String DOI_PREFIX = "50|doi_________::"; private static final String DOI_PREFIX = "50|doi_________::";
private static final String PMID_PREFIX = "50|pmid________::"; private static final String PMID_PREFIX = "50|pmid________::";
private static final String ARXIV_PREFIX = "50|arXiv_______::";
private static final String PMCID_PREFIX = "50|pmcid_______::";
private static final String TRUST = "0.91"; private static final String TRUST = "0.91";
private static final Logger log = LoggerFactory.getLogger(CreateActionSetSparkJob.class); private static final Logger log = LoggerFactory.getLogger(CreateActionSetSparkJob.class);
@ -79,38 +77,30 @@ public class CreateActionSetSparkJob implements Serializable {
final String outputPath = parser.get("outputPath"); final String outputPath = parser.get("outputPath");
log.info("outputPath {}", outputPath); log.info("outputPath {}", outputPath);
final boolean shouldDuplicateRels = Optional
.ofNullable(parser.get("shouldDuplicateRels"))
.map(Boolean::valueOf)
.orElse(Boolean.FALSE);
SparkConf conf = new SparkConf(); SparkConf conf = new SparkConf();
runWithSparkSession( runWithSparkSession(
conf, conf,
isSparkSessionManaged, isSparkSessionManaged,
spark -> extractContent(spark, inputPath, outputPath, shouldDuplicateRels)); spark -> extractContent(spark, inputPath, outputPath));
} }
private static void extractContent(SparkSession spark, String inputPath, String outputPath, private static void extractContent(SparkSession spark, String inputPath, String outputPath) {
boolean shouldDuplicateRels) {
getTextTextJavaPairRDD(spark, inputPath, shouldDuplicateRels, COCI) getTextTextJavaPairRDD(spark, inputPath)
.union(getTextTextJavaPairRDD(spark, inputPath, shouldDuplicateRels, POCI))
.saveAsHadoopFile(outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class); .saveAsHadoopFile(outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class);
} }
private static JavaPairRDD<Text, Text> getTextTextJavaPairRDD(SparkSession spark, String inputPath, private static JavaPairRDD<Text, Text> getTextTextJavaPairRDD(SparkSession spark, String inputPath) {
boolean shouldDuplicateRels, String prefix) {
return spark return spark
.read() .read()
.textFile(inputPath + "/" + prefix + "/" + prefix + "_JSON/*") .textFile(inputPath)
.map( .map(
(MapFunction<String, COCI>) value -> OBJECT_MAPPER.readValue(value, COCI.class), (MapFunction<String, COCI>) value -> OBJECT_MAPPER.readValue(value, COCI.class),
Encoders.bean(COCI.class)) Encoders.bean(COCI.class))
.flatMap( .flatMap(
(FlatMapFunction<COCI, Relation>) value -> createRelation( (FlatMapFunction<COCI, Relation>) value -> createRelation(
value, shouldDuplicateRels, prefix) value)
.iterator(), .iterator(),
Encoders.bean(Relation.class)) Encoders.bean(Relation.class))
.filter((FilterFunction<Relation>) Objects::nonNull) .filter((FilterFunction<Relation>) Objects::nonNull)
@ -121,34 +111,68 @@ public class CreateActionSetSparkJob implements Serializable {
new Text(OBJECT_MAPPER.writeValueAsString(aa)))); new Text(OBJECT_MAPPER.writeValueAsString(aa))));
} }
private static List<Relation> createRelation(COCI value, boolean duplicate, String p) { private static List<Relation> createRelation(COCI value) throws JsonProcessingException {
List<Relation> relationList = new ArrayList<>(); List<Relation> relationList = new ArrayList<>();
String prefix;
String citing; String citing;
String cited; String cited;
switch (p) { switch (value.getCiting_pid()) {
case COCI: case "doi":
prefix = DOI_PREFIX; citing = DOI_PREFIX
citing = prefix
+ IdentifierFactory + IdentifierFactory
.md5(PidCleaner.normalizePidValue(PidType.doi.toString(), value.getCiting())); .md5(PidCleaner.normalizePidValue(PidType.doi.toString(), value.getCiting()));
cited = prefix break;
case "pmid":
citing = PMID_PREFIX
+ IdentifierFactory
.md5(PidCleaner.normalizePidValue(PidType.pmid.toString(), value.getCiting()));
break;
case "arxiv":
citing = ARXIV_PREFIX
+ IdentifierFactory
.md5(PidCleaner.normalizePidValue(PidType.arXiv.toString(), value.getCiting()));
break;
case "pmcid":
citing = PMCID_PREFIX
+ IdentifierFactory
.md5(PidCleaner.normalizePidValue(PidType.pmc.toString(), value.getCiting()));
break;
case "isbn":
case "issn":
return relationList;
default:
throw new IllegalStateException("Invalid prefix: " + new ObjectMapper().writeValueAsString(value));
}
switch (value.getCited_pid()) {
case "doi":
cited = DOI_PREFIX
+ IdentifierFactory + IdentifierFactory
.md5(PidCleaner.normalizePidValue(PidType.doi.toString(), value.getCited())); .md5(PidCleaner.normalizePidValue(PidType.doi.toString(), value.getCited()));
break; break;
case POCI: case "pmid":
prefix = PMID_PREFIX; cited = PMID_PREFIX
citing = prefix
+ IdentifierFactory
.md5(PidCleaner.normalizePidValue(PidType.pmid.toString(), value.getCiting()));
cited = prefix
+ IdentifierFactory + IdentifierFactory
.md5(PidCleaner.normalizePidValue(PidType.pmid.toString(), value.getCited())); .md5(PidCleaner.normalizePidValue(PidType.pmid.toString(), value.getCited()));
break; break;
case "arxiv":
cited = ARXIV_PREFIX
+ IdentifierFactory
.md5(PidCleaner.normalizePidValue(PidType.arXiv.toString(), value.getCited()));
break;
case "pmcid":
cited = PMCID_PREFIX
+ IdentifierFactory
.md5(PidCleaner.normalizePidValue(PidType.pmc.toString(), value.getCited()));
break;
case "isbn":
case "issn":
return relationList;
default: default:
throw new IllegalStateException("Invalid prefix: " + p); throw new IllegalStateException("Invalid prefix: " + new ObjectMapper().writeValueAsString(value));
} }
if (!citing.equals(cited)) { if (!citing.equals(cited)) {
@ -157,15 +181,6 @@ public class CreateActionSetSparkJob implements Serializable {
getRelation( getRelation(
citing, citing,
cited, ModelConstants.CITES)); cited, ModelConstants.CITES));
if (duplicate && value.getCiting().endsWith(".refs")) {
citing = prefix + IdentifierFactory
.md5(
CleaningFunctions
.normalizePidValue(
"doi", value.getCiting().substring(0, value.getCiting().indexOf(".refs"))));
relationList.add(getRelation(citing, cited, ModelConstants.CITES));
}
} }
return relationList; return relationList;

View File

@ -12,10 +12,7 @@ import java.util.zip.ZipInputStream;
import org.apache.commons.cli.ParseException; import org.apache.commons.cli.ParseException;
import org.apache.commons.io.IOUtils; import org.apache.commons.io.IOUtils;
import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream; import org.apache.hadoop.fs.*;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.slf4j.Logger; import org.slf4j.Logger;
import org.slf4j.LoggerFactory; import org.slf4j.LoggerFactory;
@ -37,17 +34,17 @@ public class GetOpenCitationsRefs implements Serializable {
parser.parseArgument(args); parser.parseArgument(args);
final String[] inputFile = parser.get("inputFile").split(";"); // final String[] inputFile = parser.get("inputFile").split(";");
log.info("inputFile {}", Arrays.asList(inputFile)); // log.info("inputFile {}", Arrays.asList(inputFile));
final String workingPath = parser.get("workingPath"); final String inputPath = parser.get("inputPath");
log.info("workingPath {}", workingPath); log.info("inputPath {}", inputPath);
final String hdfsNameNode = parser.get("hdfsNameNode"); final String hdfsNameNode = parser.get("hdfsNameNode");
log.info("hdfsNameNode {}", hdfsNameNode); log.info("hdfsNameNode {}", hdfsNameNode);
final String prefix = parser.get("prefix"); final String outputPath = parser.get("outputPath");
log.info("prefix {}", prefix); log.info("outputPath {}", outputPath);
Configuration conf = new Configuration(); Configuration conf = new Configuration();
conf.set("fs.defaultFS", hdfsNameNode); conf.set("fs.defaultFS", hdfsNameNode);
@ -56,41 +53,42 @@ public class GetOpenCitationsRefs implements Serializable {
GetOpenCitationsRefs ocr = new GetOpenCitationsRefs(); GetOpenCitationsRefs ocr = new GetOpenCitationsRefs();
for (String file : inputFile) { ocr.doExtract(inputPath, outputPath, fileSystem);
ocr.doExtract(workingPath + "/Original/" + file, workingPath, fileSystem, prefix);
}
} }
private void doExtract(String inputFile, String workingPath, FileSystem fileSystem, String prefix) private void doExtract(String inputPath, String outputPath, FileSystem fileSystem)
throws IOException { throws IOException {
final Path path = new Path(inputFile); RemoteIterator<LocatedFileStatus> fileStatusListIterator = fileSystem
.listFiles(
new Path(inputPath), true);
while (fileStatusListIterator.hasNext()) {
LocatedFileStatus fileStatus = fileStatusListIterator.next();
// do stuff with the file like ...
FSDataInputStream oc_zip = fileSystem.open(fileStatus.getPath());
try (ZipInputStream zis = new ZipInputStream(oc_zip)) {
ZipEntry entry = null;
while ((entry = zis.getNextEntry()) != null) {
FSDataInputStream oc_zip = fileSystem.open(path); if (!entry.isDirectory()) {
String fileName = entry.getName();
// fileName = fileName.substring(0, fileName.indexOf("T")) + "_" + count;
fileName = fileName.substring(0, fileName.lastIndexOf("."));
// count++;
try (
FSDataOutputStream out = fileSystem
.create(new Path(outputPath + "/" + fileName + ".gz"));
GZIPOutputStream gzipOs = new GZIPOutputStream(new BufferedOutputStream(out))) {
// int count = 1; IOUtils.copy(zis, gzipOs);
try (ZipInputStream zis = new ZipInputStream(oc_zip)) {
ZipEntry entry = null;
while ((entry = zis.getNextEntry()) != null) {
if (!entry.isDirectory()) {
String fileName = entry.getName();
// fileName = fileName.substring(0, fileName.indexOf("T")) + "_" + count;
fileName = fileName.substring(0, fileName.lastIndexOf("."));
// count++;
try (
FSDataOutputStream out = fileSystem
.create(new Path(workingPath + "/" + prefix + "/" + fileName + ".gz"));
GZIPOutputStream gzipOs = new GZIPOutputStream(new BufferedOutputStream(out))) {
IOUtils.copy(zis, gzipOs);
}
} }
} }
} }
} }
} }

View File

@ -0,0 +1,171 @@
package eu.dnetlib.dhp.actionmanager.opencitations;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import java.io.IOException;
import java.io.Serializable;
import java.util.Arrays;
import java.util.Objects;
import java.util.Optional;
import java.util.stream.Collectors;
import java.util.zip.ZipEntry;
import java.util.zip.ZipInputStream;
import org.apache.commons.cli.ParseException;
import org.apache.commons.io.IOUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.FlatMapFunction;
import org.apache.spark.api.java.function.ForeachFunction;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.sql.*;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.actionmanager.opencitations.model.COCI;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import scala.Tuple2;
/**
* @author miriam.baglioni
* @Date 29/02/24
*/
public class MapOCIdsInPids implements Serializable {
private static final Logger log = LoggerFactory.getLogger(CreateActionSetSparkJob.class);
private static final String DELIMITER = ",";
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
public static void main(final String[] args) throws IOException, ParseException {
final ArgumentApplicationParser parser = new ArgumentApplicationParser(
IOUtils
.toString(
Objects
.requireNonNull(
MapOCIdsInPids.class
.getResourceAsStream(
"/eu/dnetlib/dhp/actionmanager/opencitations/remap_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);
final String nameNode = parser.get("nameNode");
log.info("nameNode {}", nameNode);
unzipCorrespondenceFile(inputPath, nameNode);
SparkConf conf = new SparkConf();
runWithSparkSession(
conf,
isSparkSessionManaged,
spark -> mapIdentifiers(spark, inputPath, outputPath));
}
private static void unzipCorrespondenceFile(String inputPath, String hdfsNameNode) throws IOException {
Configuration conf = new Configuration();
conf.set("fs.defaultFS", hdfsNameNode);
final Path path = new Path(inputPath + "/correspondence/omid.zip");
FileSystem fileSystem = FileSystem.get(conf);
FSDataInputStream project_zip = fileSystem.open(path);
try (ZipInputStream zis = new ZipInputStream(project_zip)) {
ZipEntry entry = null;
while ((entry = zis.getNextEntry()) != null) {
if (!entry.isDirectory()) {
String fileName = entry.getName();
byte buffer[] = new byte[1024];
int count;
try (
FSDataOutputStream out = fileSystem
.create(new Path(inputPath + "/correspondence/omid.csv"))) {
while ((count = zis.read(buffer, 0, buffer.length)) != -1)
out.write(buffer, 0, count);
}
}
}
}
}
private static void mapIdentifiers(SparkSession spark, String inputPath, String outputPath) {
Dataset<COCI> coci = spark
.read()
.textFile(inputPath + "/JSON")
.map(
(MapFunction<String, COCI>) value -> OBJECT_MAPPER.readValue(value, COCI.class),
Encoders.bean(COCI.class));
Dataset<Tuple2<String, String>> correspondenceData = spark
.read()
.format("csv")
.option("sep", DELIMITER)
.option("inferSchema", "true")
.option("header", "true")
.option("quotes", "\"")
.load(inputPath + "/correspondence/omid.csv")
.repartition(5000)
.flatMap((FlatMapFunction<Row, Tuple2<String, String>>) r -> {
String ocIdentifier = r.getAs("omid");
String[] correspondentIdentifiers = ((String) r.getAs("id")).split(" ");
return Arrays
.stream(correspondentIdentifiers)
.map(ci -> new Tuple2<String, String>(ocIdentifier, ci))
.collect(Collectors.toList())
.iterator();
}, Encoders.tuple(Encoders.STRING(), Encoders.STRING()));
Dataset<COCI> mappedCitingDataset = coci
.joinWith(correspondenceData, coci.col("citing").equalTo(correspondenceData.col("_1")))
.map((MapFunction<Tuple2<COCI, Tuple2<String, String>>, COCI>) t2 -> {
String correspondent = t2._2()._2();
t2._1().setCiting_pid(correspondent.substring(0, correspondent.indexOf(":")));
t2._1().setCiting(correspondent.substring(correspondent.indexOf(":") + 1));
return t2._1();
}, Encoders.bean(COCI.class));
mappedCitingDataset
.joinWith(correspondenceData, mappedCitingDataset.col("cited").equalTo(correspondenceData.col("_1")))
.map((MapFunction<Tuple2<COCI, Tuple2<String, String>>, COCI>) t2 -> {
String correspondent = t2._2()._2();
t2._1().setCited_pid(correspondent.substring(0, correspondent.indexOf(":")));
t2._1().setCited(correspondent.substring(correspondent.indexOf(":") + 1));
return t2._1();
}, Encoders.bean(COCI.class))
.write()
.mode(SaveMode.Append)
.option("compression", "gzip")
.json(outputPath);
}
}

View File

@ -12,11 +12,9 @@ import java.util.Optional;
import org.apache.commons.io.IOUtils; import org.apache.commons.io.IOUtils;
import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem; import org.apache.hadoop.fs.*;
import org.apache.hadoop.fs.LocatedFileStatus;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.fs.RemoteIterator;
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.MapFunction; import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.sql.*; import org.apache.spark.sql.*;
import org.slf4j.Logger; import org.slf4j.Logger;
@ -42,19 +40,21 @@ public class ReadCOCI implements Serializable {
final String outputPath = parser.get("outputPath"); final String outputPath = parser.get("outputPath");
log.info("outputPath: {}", outputPath); log.info("outputPath: {}", outputPath);
final String[] inputFile = parser.get("inputFile").split(";"); final String hdfsNameNode = parser.get("hdfsNameNode");
log.info("inputFile {}", Arrays.asList(inputFile)); log.info("hdfsNameNode {}", hdfsNameNode);
Boolean isSparkSessionManaged = isSparkSessionManaged(parser); Boolean isSparkSessionManaged = isSparkSessionManaged(parser);
log.info("isSparkSessionManaged: {}", isSparkSessionManaged); log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
final String workingPath = parser.get("workingPath"); final String workingPath = parser.get("inputPath");
log.info("workingPath {}", workingPath); log.info("workingPath {}", workingPath);
final String format = parser.get("format");
log.info("format {}", format);
SparkConf sconf = new SparkConf(); SparkConf sconf = new SparkConf();
Configuration conf = new Configuration();
conf.set("fs.defaultFS", hdfsNameNode);
FileSystem fileSystem = FileSystem.get(conf);
final String delimiter = Optional final String delimiter = Optional
.ofNullable(parser.get("delimiter")) .ofNullable(parser.get("delimiter"))
.orElse(DEFAULT_DELIMITER); .orElse(DEFAULT_DELIMITER);
@ -66,20 +66,21 @@ public class ReadCOCI implements Serializable {
doRead( doRead(
spark, spark,
workingPath, workingPath,
inputFile, fileSystem,
outputPath, outputPath,
delimiter, delimiter);
format);
}); });
} }
private static void doRead(SparkSession spark, String workingPath, String[] inputFiles, private static void doRead(SparkSession spark, String workingPath, FileSystem fileSystem,
String outputPath, String outputPath,
String delimiter, String format) { String delimiter) throws IOException {
RemoteIterator<LocatedFileStatus> fileStatusListIterator = fileSystem
for (String inputFile : inputFiles) { .listFiles(
String pString = workingPath + "/" + inputFile + ".gz"; new Path(workingPath), true);
while (fileStatusListIterator.hasNext()) {
LocatedFileStatus fileStatus = fileStatusListIterator.next();
log.info("extracting file {}", fileStatus.getPath().toString());
Dataset<Row> cociData = spark Dataset<Row> cociData = spark
.read() .read()
.format("csv") .format("csv")
@ -87,26 +88,26 @@ public class ReadCOCI implements Serializable {
.option("inferSchema", "true") .option("inferSchema", "true")
.option("header", "true") .option("header", "true")
.option("quotes", "\"") .option("quotes", "\"")
.load(pString) .load(fileStatus.getPath().toString())
.repartition(100); .repartition(100);
cociData.map((MapFunction<Row, COCI>) row -> { cociData.map((MapFunction<Row, COCI>) row -> {
COCI coci = new COCI(); COCI coci = new COCI();
if (format.equals("COCI")) {
coci.setCiting(row.getString(1)); coci.setCiting(row.getString(1));
coci.setCited(row.getString(2)); coci.setCited(row.getString(2));
} else {
coci.setCiting(String.valueOf(row.getInt(1)));
coci.setCited(String.valueOf(row.getInt(2)));
}
coci.setOci(row.getString(0)); coci.setOci(row.getString(0));
return coci; return coci;
}, Encoders.bean(COCI.class)) }, Encoders.bean(COCI.class))
.filter((FilterFunction<COCI>) c -> c != null)
.write() .write()
.mode(SaveMode.Overwrite) .mode(SaveMode.Append)
.option("compression", "gzip") .option("compression", "gzip")
.json(outputPath + inputFile); .json(outputPath);
fileSystem.rename(fileStatus.getPath(), new Path("/tmp/miriam/OC/DONE"));
} }
} }

View File

@ -9,8 +9,10 @@ public class COCI implements Serializable {
private String oci; private String oci;
private String citing; private String citing;
private String citing_pid;
private String cited; private String cited;
private String cited_pid;
public String getOci() { public String getOci() {
return oci; return oci;
@ -25,6 +27,8 @@ public class COCI implements Serializable {
} }
public void setCiting(String citing) { public void setCiting(String citing) {
if (citing != null && citing.startsWith("omid:"))
citing = citing.substring(5);
this.citing = citing; this.citing = citing;
} }
@ -33,7 +37,24 @@ public class COCI implements Serializable {
} }
public void setCited(String cited) { public void setCited(String cited) {
if (cited != null && cited.startsWith("omid:"))
cited = cited.substring(5);
this.cited = cited; this.cited = cited;
} }
public String getCiting_pid() {
return citing_pid;
}
public void setCiting_pid(String citing_pid) {
this.citing_pid = citing_pid;
}
public String getCited_pid() {
return cited_pid;
}
public void setCited_pid(String cited_pid) {
this.cited_pid = cited_pid;
}
} }

View File

@ -23,7 +23,6 @@ import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.actionmanager.project.utils.model.CSVProgramme; 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.CSVProject;
import eu.dnetlib.dhp.actionmanager.project.utils.model.EXCELTopic;
import eu.dnetlib.dhp.actionmanager.project.utils.model.JsonTopic; import eu.dnetlib.dhp.actionmanager.project.utils.model.JsonTopic;
import eu.dnetlib.dhp.application.ArgumentApplicationParser; import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.HdfsSupport; import eu.dnetlib.dhp.common.HdfsSupport;
@ -33,6 +32,7 @@ import eu.dnetlib.dhp.schema.oaf.H2020Classification;
import eu.dnetlib.dhp.schema.oaf.H2020Programme; import eu.dnetlib.dhp.schema.oaf.H2020Programme;
import eu.dnetlib.dhp.schema.oaf.OafEntity; import eu.dnetlib.dhp.schema.oaf.OafEntity;
import eu.dnetlib.dhp.schema.oaf.Project; import eu.dnetlib.dhp.schema.oaf.Project;
import eu.dnetlib.dhp.schema.oaf.utils.MergeUtils;
import eu.dnetlib.dhp.utils.DHPUtils; import eu.dnetlib.dhp.utils.DHPUtils;
import scala.Tuple2; import scala.Tuple2;
@ -160,9 +160,11 @@ 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))

View File

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

View File

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

View File

@ -5,6 +5,7 @@ import static eu.dnetlib.dhp.actionmanager.Constants.*;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkHiveSession; import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkHiveSession;
import java.io.Serializable; import java.io.Serializable;
import java.util.ArrayList;
import java.util.Arrays; import java.util.Arrays;
import java.util.List; import java.util.List;
import java.util.Optional; import java.util.Optional;
@ -13,7 +14,9 @@ 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;
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.MapFunction; import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.api.java.function.MapGroupsFunction;
import org.apache.spark.sql.Dataset; import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoders; import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.SaveMode; import org.apache.spark.sql.SaveMode;
@ -68,18 +71,59 @@ public class SparkAtomicActionUsageJob implements Serializable {
final String workingPath = parser.get("workingPath"); final String workingPath = parser.get("workingPath");
final String datasourcePath = parser.get("datasourcePath");
runWithSparkHiveSession( runWithSparkHiveSession(
conf, conf,
isSparkSessionManaged, isSparkSessionManaged,
spark -> { spark -> {
removeOutputDir(spark, outputPath); removeOutputDir(spark, outputPath);
prepareData(dbname, spark, workingPath + "/usageDb", "usage_stats", "result_id"); prepareResultData(
dbname, spark, workingPath + "/usageDb",
"usage_stats",
"result_id",
"repository_id",
datasourcePath);
prepareData(dbname, spark, workingPath + "/projectDb", "project_stats", "id"); prepareData(dbname, spark, workingPath + "/projectDb", "project_stats", "id");
prepareData(dbname, spark, workingPath + "/datasourceDb", "datasource_stats", "repository_id"); prepareData(dbname, spark, workingPath + "/datasourceDb", "datasource_stats", "repository_id");
writeActionSet(spark, workingPath, outputPath); writeActionSet(spark, workingPath, outputPath);
}); });
} }
private static void prepareResultData(String dbname, SparkSession spark, String workingPath, String tableName,
String resultAttributeName, String datasourceAttributeName,
String datasourcePath) {
Dataset<UsageStatsResultModel> resultModel = spark
.sql(
String
.format(
"select %s as id, %s as datasourceId, sum(downloads) as downloads, sum(views) as views " +
"from %s.%s group by %s, %s",
resultAttributeName, datasourceAttributeName, dbname, tableName, resultAttributeName,
datasourceAttributeName))
.as(Encoders.bean(UsageStatsResultModel.class));
Dataset<Datasource> datasource = readPath(spark, datasourcePath, Datasource.class)
.filter((FilterFunction<Datasource>) d -> !d.getDataInfo().getDeletedbyinference())
.map((MapFunction<Datasource, Datasource>) d -> {
d.setId(d.getId().substring(3));
return d;
}, Encoders.bean(Datasource.class));
resultModel
.joinWith(datasource, resultModel.col("datasourceId").equalTo(datasource.col("id")), "left")
.map((MapFunction<Tuple2<UsageStatsResultModel, Datasource>, UsageStatsResultModel>) t2 -> {
UsageStatsResultModel usrm = t2._1();
if (Optional.ofNullable(t2._2()).isPresent())
usrm.setDatasourceId(usrm.getDatasourceId() + "||" + t2._2().getOfficialname().getValue());
else
usrm.setDatasourceId(usrm.getDatasourceId() + "||NO_MATCH_FOUND");
return usrm;
}, Encoders.bean(UsageStatsResultModel.class))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(workingPath);
}
private static void prepareData(String dbname, SparkSession spark, String workingPath, String tableName, private static void prepareData(String dbname, SparkSession spark, String workingPath, String tableName,
String attribute_name) { String attribute_name) {
spark spark
@ -115,15 +159,62 @@ public class SparkAtomicActionUsageJob implements Serializable {
} }
public static Measure newMeasureInstance(String id) {
Measure m = new Measure();
m.setId(id);
m.setUnit(new ArrayList<>());
return m;
}
private static Dataset<Result> getFinalIndicatorsResult(SparkSession spark, String inputPath) { private static Dataset<Result> getFinalIndicatorsResult(SparkSession spark, String inputPath) {
return readPath(spark, inputPath, UsageStatsModel.class) return readPath(spark, inputPath, UsageStatsResultModel.class)
.map((MapFunction<UsageStatsModel, Result>) usm -> { .groupByKey((MapFunction<UsageStatsResultModel, String>) usm -> usm.getId(), Encoders.STRING())
.mapGroups((MapGroupsFunction<String, UsageStatsResultModel, Result>) (k, it) -> {
Result r = new Result(); Result r = new Result();
r.setId("50|" + usm.getId()); r.setId("50|" + k);
r.setMeasures(getMeasure(usm.getDownloads(), usm.getViews())); // id = download or view and unit = list of key value pairs
Measure download = newMeasureInstance("downloads");
Measure view = newMeasureInstance("views");
UsageStatsResultModel first = it.next();
addCountForDatasource(download, first, view);
it.forEachRemaining(usm -> {
addCountForDatasource(download, usm, view);
});
r.setMeasures(Arrays.asList(download, view));
return r; return r;
}, Encoders.bean(Result.class)); }, Encoders.bean(Result.class))
// .map((MapFunction<UsageStatsResultModel, Result>) usm -> {
// Result r = new Result();
// r.setId("50|" + usm.getId());
// r.setMeasures(getMeasure(usm.getDownloads(), usm.getViews()));
// return r;
// }, Encoders.bean(Result.class));
;
}
private static void addCountForDatasource(Measure download, UsageStatsResultModel usm, Measure view) {
DataInfo dataInfo = OafMapperUtils
.dataInfo(
false,
UPDATE_DATA_INFO_TYPE,
true,
false,
OafMapperUtils
.qualifier(
UPDATE_MEASURE_USAGE_COUNTS_CLASS_ID,
UPDATE_CLASS_NAME,
ModelConstants.DNET_PROVENANCE_ACTIONS,
ModelConstants.DNET_PROVENANCE_ACTIONS),
"");
download
.getUnit()
.add(
OafMapperUtils
.newKeyValueInstance(usm.getDatasourceId(), String.valueOf(usm.getDownloads()), dataInfo));
view
.getUnit()
.add(OafMapperUtils.newKeyValueInstance(usm.getDatasourceId(), String.valueOf(usm.getViews()), dataInfo));
} }
private static Dataset<Project> getFinalIndicatorsProject(SparkSession spark, String inputPath) { private static Dataset<Project> getFinalIndicatorsProject(SparkSession spark, String inputPath) {

View File

@ -0,0 +1,18 @@
package eu.dnetlib.dhp.actionmanager.usagestats;
/**
* @author miriam.baglioni
* @Date 30/06/23
*/
public class UsageStatsResultModel extends UsageStatsModel {
private String datasourceId;
public String getDatasourceId() {
return datasourceId;
}
public void setDatasourceId(String datasourceId) {
this.datasourceId = datasourceId;
}
}

View File

@ -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"))

View File

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

View File

@ -0,0 +1,171 @@
package eu.dnetlib.dhp.collection.orcid;
import static eu.dnetlib.dhp.utils.DHPUtils.getHadoopConfiguration;
import java.io.*;
import java.net.HttpURLConnection;
import java.net.URL;
import java.util.ArrayList;
import java.util.List;
import java.util.Objects;
import java.util.concurrent.ArrayBlockingQueue;
import java.util.concurrent.BlockingQueue;
import org.apache.commons.compress.archivers.tar.TarArchiveEntry;
import org.apache.commons.compress.archivers.tar.TarArchiveInputStream;
import org.apache.commons.compress.compressors.gzip.GzipCompressorInputStream;
import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.StringUtils;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.SequenceFile;
import org.apache.hadoop.io.Text;
import org.apache.spark.sql.SparkSession;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.collection.HttpClientParams;
public class OrcidGetUpdatesFile {
private static Logger log = LoggerFactory.getLogger(OrcidGetUpdatesFile.class);
public static void main(String[] args) throws Exception {
ArgumentApplicationParser parser = new ArgumentApplicationParser(
IOUtils
.toString(
Objects
.requireNonNull(
OrcidGetUpdatesFile.class
.getResourceAsStream(
"/eu/dnetlib/dhp/collection/orcid/download_orcid_update_parameter.json")))
);
parser.parseArgument(args);
final String namenode = parser.get("namenode");
log.info("got variable namenode: {}", namenode);
final String master = parser.get("master");
log.info("got variable master: {}", master);
final String targetPath = parser.get("targetPath");
log.info("got variable targetPath: {}", targetPath);
final String apiURL = parser.get("apiURL");
log.info("got variable apiURL: {}", apiURL);
final String accessToken = parser.get("accessToken");
log.info("got variable accessToken: {}", accessToken);
final String graphPath = parser.get("graphPath");
log.info("got variable graphPath: {}", graphPath);
final SparkSession spark = SparkSession
.builder()
.appName(OrcidGetUpdatesFile.class.getName())
.master(master)
.getOrCreate();
final String latestDate = spark
.read()
.load(graphPath + "/Authors")
.selectExpr("max(lastModifiedDate)")
.first()
.getString(0);
log.info("latest date is {}", latestDate);
final FileSystem fileSystem = FileSystem.get(getHadoopConfiguration(namenode));
new OrcidGetUpdatesFile().readTar(fileSystem, accessToken, apiURL, targetPath, latestDate);
}
private SequenceFile.Writer createFile(Path aPath, FileSystem fileSystem) throws IOException {
return SequenceFile
.createWriter(
fileSystem.getConf(),
SequenceFile.Writer.file(aPath),
SequenceFile.Writer.keyClass(Text.class),
SequenceFile.Writer.valueClass(Text.class));
}
private ORCIDWorker createWorker(final String id, final String targetPath, final BlockingQueue<String> queue,
final String accessToken, FileSystem fileSystem) throws Exception {
return ORCIDWorker
.builder()
.withId(id)
.withEmployments(createFile(new Path(String.format("%s/employments_%s", targetPath, id)), fileSystem))
.withSummary(createFile(new Path(String.format("%s/summary_%s", targetPath, id)), fileSystem))
.withWorks(createFile(new Path(String.format("%s/works_%s", targetPath, id)), fileSystem))
.withAccessToken(accessToken)
.withBlockingQueue(queue)
.build();
}
public void readTar(FileSystem fileSystem, final String accessToken, final String apiURL, final String targetPath,
final String startDate) throws Exception {
final HttpURLConnection urlConn = (HttpURLConnection) new URL(apiURL).openConnection();
final HttpClientParams clientParams = new HttpClientParams();
urlConn.setInstanceFollowRedirects(false);
urlConn.setReadTimeout(clientParams.getReadTimeOut() * 1000);
urlConn.setConnectTimeout(clientParams.getConnectTimeOut() * 1000);
if (urlConn.getResponseCode() > 199 && urlConn.getResponseCode() < 300) {
InputStream input = urlConn.getInputStream();
Path hdfsWritePath = new Path("/tmp/orcid_updates.tar.gz");
final FSDataOutputStream fsDataOutputStream = fileSystem.create(hdfsWritePath, true);
IOUtils.copy(input, fsDataOutputStream);
fsDataOutputStream.flush();
fsDataOutputStream.close();
FSDataInputStream updateFile = fileSystem.open(hdfsWritePath);
TarArchiveInputStream tais = new TarArchiveInputStream(new GzipCompressorInputStream(
new BufferedInputStream(
updateFile.getWrappedStream())));
TarArchiveEntry entry;
BlockingQueue<String> queue = new ArrayBlockingQueue<String>(3000);
final List<ORCIDWorker> workers = new ArrayList<>();
for (int i = 0; i < 22; i++) {
workers.add(createWorker("" + i, targetPath, queue, accessToken, fileSystem));
}
workers.forEach(Thread::start);
while ((entry = tais.getNextTarEntry()) != null) {
if (entry.isFile()) {
BufferedReader br = new BufferedReader(new InputStreamReader(tais));
System.out.println(br.readLine());
br
.lines()
.map(l -> l.split(","))
.filter(s -> StringUtils.compare(s[3].substring(0, 10), startDate) > 0)
.map(s -> s[0])
.forEach(s -> {
try {
queue.put(s);
} catch (InterruptedException e) {
throw new RuntimeException(e);
}
});
}
}
for (int i = 0; i < 22; i++) {
queue.put(ORCIDWorker.JOB_COMPLETE);
}
for (ORCIDWorker worker : workers) {
worker.join();
}
}
}
}

View File

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

View File

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

View File

@ -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

View File

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

View File

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

View File

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

View File

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

View File

@ -48,23 +48,30 @@ 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);
Processor processor = new Processor(false);
processor.registerExtensionFunction(cleanFunction);
processor.registerExtensionFunction(new DateCleaner());
processor.registerExtensionFunction(new PersonCleaner());
final XsltCompiler comp = processor.newXsltCompiler();
QName datasourceIDParam = new QName(DATASOURCE_ID_PARAM);
comp.setParameter(datasourceIDParam, new XdmAtomicValue(value.getProvenance().getDatasourceId()));
QName datasourceNameParam = new QName(DATASOURCE_NAME_PARAM);
comp.setParameter(datasourceNameParam, new XdmAtomicValue(value.getProvenance().getDatasourceName()));
XsltExecutable xslt;
XdmNode source;
try { try {
Processor processor = new Processor(false); xslt = comp
processor.registerExtensionFunction(cleanFunction);
processor.registerExtensionFunction(new DateCleaner());
processor.registerExtensionFunction(new PersonCleaner());
final XsltCompiler comp = processor.newXsltCompiler();
QName datasourceIDParam = new QName(DATASOURCE_ID_PARAM);
comp.setParameter(datasourceIDParam, new XdmAtomicValue(value.getProvenance().getDatasourceId()));
QName datasourceNameParam = new QName(DATASOURCE_NAME_PARAM);
comp.setParameter(datasourceNameParam, new XdmAtomicValue(value.getProvenance().getDatasourceName()));
XsltExecutable 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();

View File

@ -17,6 +17,18 @@
"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": "dip",
"paramLongName": "dataciteInputPath",
"paramDescription": "the path to get the input data from Datacite",
"paramRequired": true
},
{ {
"paramName": "o", "paramName": "o",
"paramLongName": "outputPath", "paramLongName": "outputPath",

View File

@ -31,6 +31,9 @@ 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
dataciteInputPath=/data/bip-affiliations/datacite-data.json
outputPath=/tmp/crossref-affiliations-output-v5 outputPath=/tmp/crossref-affiliations-output-v5

View File

@ -9,6 +9,14 @@
<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>
<name>dataciteInputPath</name>
<description>the path where to find the inferred affiliation relations from Datacite</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 +110,9 @@
</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>${openapcInputPath}</arg>
<arg>--dataciteInputPath</arg><arg>${dataciteInputPath}</arg>
<arg>--outputPath</arg><arg>${outputPath}</arg> <arg>--outputPath</arg><arg>${outputPath}</arg>
</spark> </spark>
<ok to="End"/> <ok to="End"/>

View File

@ -16,5 +16,10 @@
"paramLongName": "outputPath", "paramLongName": "outputPath",
"paramDescription": "the path of the new ActionSet", "paramDescription": "the path of the new ActionSet",
"paramRequired": true "paramRequired": true
} }, {
"paramName": "fd",
"paramLongName": "distributeDoi",
"paramDescription": "the path of the new ActionSet",
"paramRequired": false
}
] ]

View File

@ -0,0 +1,20 @@
[
{
"paramName": "sp",
"paramLongName": "sourcePath",
"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
}
]

View File

@ -0,0 +1,30 @@
<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>hiveMetastoreUris</name>
<value>thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083</value>
</property>
<property>
<name>hiveJdbcUrl</name>
<value>jdbc:hive2://iis-cdh5-test-m3.ocean.icm.edu.pl:10000</value>
</property>
<property>
<name>hiveDbName</name>
<value>openaire</value>
</property>
<property>
<name>oozie.launcher.mapreduce.user.classpath.first</name>
<value>true</value>
</property>
</configuration>

View File

@ -0,0 +1,153 @@
<workflow-app name="FOS no doi" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>fosPath</name>
<description>the input path of the resources to be extended</description>
</property>
<property>
<name>outputPath</name>
<description>the path where to store the actionset</description>
</property>
<property>
<name>sparkDriverMemory</name>
<description>memory for driver process</description>
</property>
<property>
<name>sparkExecutorMemory</name>
<description>memory for individual executor</description>
</property>
<property>
<name>sparkExecutorCores</name>
<description>number of cores used by single executor</description>
</property>
<property>
<name>oozieActionShareLibForSpark2</name>
<description>oozie action sharelib for spark 2.*</description>
</property>
<property>
<name>spark2ExtraListeners</name>
<value>com.cloudera.spark.lineage.NavigatorAppListener</value>
<description>spark 2.* extra listeners classname</description>
</property>
<property>
<name>spark2SqlQueryExecutionListeners</name>
<value>com.cloudera.spark.lineage.NavigatorQueryListener</value>
<description>spark 2.* sql query execution listeners classname</description>
</property>
<property>
<name>spark2YarnHistoryServerAddress</name>
<description>spark 2.* yarn history server address</description>
</property>
<property>
<name>spark2EventLogDir</name>
<description>spark 2.* event log dir location</description>
</property>
</parameters>
<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>${oozieActionShareLibForSpark2}</value>
</property>
</configuration>
</global>
<start to="getFOS"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="getFOS">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Gets Data from FOS csv file</name>
<class>eu.dnetlib.dhp.actionmanager.createunresolvedentities.GetFOSSparkJob</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>--sourcePath</arg><arg>${fosPath}</arg>
<arg>--outputPath</arg><arg>${workingDir}/input/fos</arg>
<arg>--delimiter</arg><arg>${delimiter}</arg>
</spark>
<ok to="prepareFos"/>
<error to="Kill"/>
</action>
<action name="prepareFos">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Produces the results from FOS</name>
<class>eu.dnetlib.dhp.actionmanager.createunresolvedentities.PrepareFOSSparkJob</class>
<jar>dhp-aggregation-${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=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${workingDir}/input/fos</arg>
<arg>--outputPath</arg><arg>${workingDir}/prepared</arg>
<arg>--distributeDoi</arg><arg>false</arg>
</spark>
<ok to="produceActionSet"/>
<error to="Kill"/>
</action>
<action name="produceActionSet">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Save the action set grouping results with the same id</name>
<class>eu.dnetlib.dhp.actionmanager.fosnodoi.CreateActionSetSparkJob</class>
<jar>dhp-aggregation-${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=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${workingDir}/prepared/fos</arg>
<arg>--outputPath</arg><arg>${outputPath}</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>

View File

@ -1,13 +1,13 @@
[ [
{ {
"paramName": "if", "paramName": "ip",
"paramLongName": "inputFile", "paramLongName": "inputPath",
"paramDescription": "the zipped opencitations file", "paramDescription": "the zipped opencitations file",
"paramRequired": true "paramRequired": true
}, },
{ {
"paramName": "wp", "paramName": "op",
"paramLongName": "workingPath", "paramLongName": "outputPath",
"paramDescription": "the working path", "paramDescription": "the working path",
"paramRequired": true "paramRequired": true
}, },
@ -16,11 +16,5 @@
"paramLongName": "hdfsNameNode", "paramLongName": "hdfsNameNode",
"paramDescription": "the hdfs name node", "paramDescription": "the hdfs name node",
"paramRequired": true "paramRequired": true
},
{
"paramName": "p",
"paramLongName": "prefix",
"paramDescription": "COCI or POCI",
"paramRequired": true
} }
] ]

View File

@ -1,7 +1,7 @@
[ [
{ {
"paramName": "wp", "paramName": "ip",
"paramLongName": "workingPath", "paramLongName": "inputPath",
"paramDescription": "the zipped opencitations file", "paramDescription": "the zipped opencitations file",
"paramRequired": true "paramRequired": true
}, },
@ -24,15 +24,9 @@
"paramLongName": "outputPath", "paramLongName": "outputPath",
"paramDescription": "the hdfs name node", "paramDescription": "the hdfs name node",
"paramRequired": true "paramRequired": true
}, }, {
{ "paramName": "nn",
"paramName": "if", "paramLongName": "hdfsNameNode",
"paramLongName": "inputFile",
"paramDescription": "the hdfs name node",
"paramRequired": true
}, {
"paramName": "f",
"paramLongName": "format",
"paramDescription": "the hdfs name node", "paramDescription": "the hdfs name node",
"paramRequired": true "paramRequired": true
} }

View File

@ -27,7 +27,9 @@
<case to="download">${wf:conf('resumeFrom') eq 'DownloadDump'}</case> <case to="download">${wf:conf('resumeFrom') eq 'DownloadDump'}</case>
<case to="extract">${wf:conf('resumeFrom') eq 'ExtractContent'}</case> <case to="extract">${wf:conf('resumeFrom') eq 'ExtractContent'}</case>
<case to="read">${wf:conf('resumeFrom') eq 'ReadContent'}</case> <case to="read">${wf:conf('resumeFrom') eq 'ReadContent'}</case>
<default to="create_actionset"/> <!-- first action to be done when downloadDump is to be performed --> <case to="remap">${wf:conf('resumeFrom') eq 'MapContent'}</case>
<case to="create_actionset">${wf:conf('resumeFrom') eq 'CreateAS'}</case>
<default to="deleteoutputpath"/> <!-- first action to be done when downloadDump is to be performed -->
</switch> </switch>
</decision> </decision>
@ -35,6 +37,15 @@
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message> <message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill> </kill>
<action name="deleteoutputpath">
<fs>
<delete path='${inputPath}'/>
<mkdir path='${inputPath}'/>
</fs>
<ok to="download"/>
<error to="Kill"/>
</action>
<action name="download"> <action name="download">
<shell xmlns="uri:oozie:shell-action:0.2"> <shell xmlns="uri:oozie:shell-action:0.2">
<job-tracker>${jobTracker}</job-tracker> <job-tracker>${jobTracker}</job-tracker>
@ -47,7 +58,28 @@
</configuration> </configuration>
<exec>download.sh</exec> <exec>download.sh</exec>
<argument>${filelist}</argument> <argument>${filelist}</argument>
<argument>${workingPath}/${prefix}/Original</argument> <argument>${inputPath}/Original</argument>
<env-var>HADOOP_USER_NAME=${wf:user()}</env-var>
<file>download.sh</file>
<capture-output/>
</shell>
<ok to="download_correspondence"/>
<error to="Kill"/>
</action>
<!-- downloads the correspondence from the omid and the pid (doi, pmid etc)-->
<action name="download_correspondence">
<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>${queueName}</value>
</property>
</configuration>
<exec>download_corr.sh</exec>
<argument>${filecorrespondence}</argument>
<argument>${inputPath}/correspondence</argument>
<env-var>HADOOP_USER_NAME=${wf:user()}</env-var> <env-var>HADOOP_USER_NAME=${wf:user()}</env-var>
<file>download.sh</file> <file>download.sh</file>
<capture-output/> <capture-output/>
@ -60,9 +92,19 @@
<java> <java>
<main-class>eu.dnetlib.dhp.actionmanager.opencitations.GetOpenCitationsRefs</main-class> <main-class>eu.dnetlib.dhp.actionmanager.opencitations.GetOpenCitationsRefs</main-class>
<arg>--hdfsNameNode</arg><arg>${nameNode}</arg> <arg>--hdfsNameNode</arg><arg>${nameNode}</arg>
<arg>--inputFile</arg><arg>${inputFile}</arg> <arg>--inputPath</arg><arg>${inputPath}/Original</arg>
<arg>--workingPath</arg><arg>${workingPath}/${prefix}</arg> <arg>--outputPath</arg><arg>${inputPath}/Extracted</arg>
<arg>--prefix</arg><arg>${prefix}</arg> </java>
<ok to="read"/>
<error to="Kill"/>
</action>
<action name="extract_correspondence">
<java>
<main-class>eu.dnetlib.dhp.actionmanager.opencitations.GetOpenCitationsRefs</main-class>
<arg>--hdfsNameNode</arg><arg>${nameNode}</arg>
<arg>--inputPath</arg><arg>${inputPath}/correspondence</arg>
<arg>--outputPath</arg><arg>${inputPath}/correspondence_extracted</arg>
</java> </java>
<ok to="read"/> <ok to="read"/>
<error to="Kill"/> <error to="Kill"/>
@ -85,11 +127,35 @@
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir} --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts> </spark-opts>
<arg>--workingPath</arg><arg>${workingPath}/${prefix}/${prefix}</arg> <arg>--inputPath</arg><arg>${inputPath}/Extracted</arg>
<arg>--outputPath</arg><arg>${workingPath}/${prefix}/${prefix}_JSON/</arg> <arg>--outputPath</arg><arg>${inputPath}/JSON</arg>
<arg>--delimiter</arg><arg>${delimiter}</arg> <arg>--delimiter</arg><arg>${delimiter}</arg>
<arg>--inputFile</arg><arg>${inputFileCoci}</arg> <arg>--hdfsNameNode</arg><arg>${nameNode}</arg>
<arg>--format</arg><arg>${prefix}</arg> </spark>
<ok to="remap"/>
<error to="Kill"/>
</action>
<action name="remap">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Produces the AS for OC</name>
<class>eu.dnetlib.dhp.actionmanager.opencitations.MapOCIdsInPids</class>
<jar>dhp-aggregation-${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=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--inputPath</arg><arg>${inputPath}</arg>
<arg>--outputPath</arg><arg>${outputPathExtraction}</arg>
<arg>--nameNode</arg><arg>${nameNode}</arg>
</spark> </spark>
<ok to="create_actionset"/> <ok to="create_actionset"/>
<error to="Kill"/> <error to="Kill"/>
@ -112,7 +178,7 @@
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir} --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts> </spark-opts>
<arg>--inputPath</arg><arg>${workingPath}</arg> <arg>--inputPath</arg><arg>${outputPathExtraction}</arg>
<arg>--outputPath</arg><arg>${outputPath}</arg> <arg>--outputPath</arg><arg>${outputPath}</arg>
</spark> </spark>
<ok to="End"/> <ok to="End"/>

View File

@ -0,0 +1,25 @@
[
{
"paramName": "ip",
"paramLongName": "inputPath",
"paramDescription": "the zipped opencitations file",
"paramRequired": true
},
{
"paramName": "op",
"paramLongName": "outputPath",
"paramDescription": "the working path",
"paramRequired": true
},
{
"paramName": "issm",
"paramLongName": "isSparkSessionManged",
"paramDescription": "the hdfs name node",
"paramRequired": false
},{
"paramName": "nn",
"paramLongName": "nameNode",
"paramDescription": "the hdfs name node",
"paramRequired": true
}
]

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