Compare commits
188 Commits
@ -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;
|
||||
}
|
||||
|
||||
}
|
@ -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;
|
||||
}
|
||||
}
|
||||
|
||||
}
|
@ -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
@ -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;
|
||||
}
|
||||
|
||||
}
|
@ -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;
|
||||
}
|
||||
}
|
@ -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>> {
|
||||
}
|
@ -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() {
|
||||
}
|
||||
|
||||
}
|
@ -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);
|
||||
}
|
||||
}
|
@ -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;
|
||||
}
|
||||
}
|
||||
|
||||
}
|
@ -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);
|
||||
}
|
||||
}
|
@ -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;
|
||||
}
|
||||
}
|
@ -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;
|
||||
}
|
||||
}
|
@ -0,0 +1,87 @@
|
||||
|
||||
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;
|
||||
}
|
||||
|
||||
if (left.getResulttype() == null || left.getResulttype().getClassid() == null) {
|
||||
if (right.getResulttype() == null || right.getResulttype().getClassid() == null) {
|
||||
return 0;
|
||||
}
|
||||
return 1;
|
||||
} else if (right.getResulttype() == null || right.getResulttype().getClassid() == null) {
|
||||
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<>());
|
||||
}
|
||||
}
|
@ -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());
|
||||
}
|
||||
}
|
@ -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);
|
||||
}
|
||||
|
||||
}
|
@ -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, true);
|
||||
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, true);
|
||||
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, true);
|
||||
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);
|
||||
}
|
||||
|
||||
}
|
@ -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
@ -0,0 +1 @@
|
||||
{"id":"50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f","pid":[{"qualifier":{"classid":"scp-number"},"value":"79953761260"}]}
|
@ -0,0 +1 @@
|
||||
{"id":"50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f","pid":[]}
|
@ -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
@ -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"
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
@ -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"
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
@ -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"
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
@ -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"
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
@ -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"
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
@ -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 }
|
@ -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 }
|
@ -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"]
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
|
@ -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"
|
||||
}
|
||||
]
|
||||
}
|
@ -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"
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
@ -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"
|
||||
}
|
||||
]
|
||||
}
|
@ -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
@ -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
|
||||
}
|
||||
|
||||
}
|
@ -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());
|
||||
}
|
||||
}
|
||||
}
|
@ -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);
|
||||
}
|
||||
|
||||
}
|
@ -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);
|
||||
|
||||
}
|
||||
|
||||
}
|
@ -0,0 +1,196 @@
|
||||
|
||||
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));
|
||||
|
||||
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))
|
||||
.union(relations)
|
||||
.mapToPair(
|
||||
aa -> new Tuple2<>(new Text(aa.getClazz().getCanonicalName()),
|
||||
new Text(OBJECT_MAPPER.writeValueAsString(aa))))
|
||||
.saveAsHadoopFile(
|
||||
outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class);
|
||||
|
||||
}
|
||||
|
||||
private static Result createResult(TransformativeAgreementModel value) {
|
||||
Result r = new Result();
|
||||
r
|
||||
.setId(
|
||||
"50|doi_________::"
|
||||
+ IdentifierFactory
|
||||
.md5(PidCleaner.normalizePidValue(PidType.doi.toString(), value.getDoi())));
|
||||
r.setTransformativeAgreement(value.getAgreement());
|
||||
Country country = new Country();
|
||||
country.setClassid(value.getCountry());
|
||||
country.setClassname(value.getCountry());
|
||||
country
|
||||
.setDataInfo(
|
||||
OafMapperUtils
|
||||
.dataInfo(
|
||||
false, ModelConstants.SYSIMPORT_ACTIONSET, false, false,
|
||||
OafMapperUtils
|
||||
.qualifier(
|
||||
"openapc::transformativeagreement",
|
||||
"Harvested from Trnasformative Agreement file from OpenAPC",
|
||||
ModelConstants.DNET_PROVENANCE_ACTIONS, ModelConstants.DNET_PROVENANCE_ACTIONS),
|
||||
"0.9"));
|
||||
country.setSchemeid(ModelConstants.DNET_COUNTRY_TYPE);
|
||||
country.setSchemename(ModelConstants.DNET_COUNTRY_TYPE);
|
||||
r.setCountry(Arrays.asList(country));
|
||||
return r;
|
||||
}
|
||||
|
||||
private static List<Relation> createRelation(TransformativeAgreementModel value) {
|
||||
|
||||
List<Relation> relationList = new ArrayList<>();
|
||||
|
||||
if (value.getAgreement().startsWith("IReL")) {
|
||||
String paper;
|
||||
|
||||
paper = "50|doi_________::"
|
||||
+ IdentifierFactory
|
||||
.md5(PidCleaner.normalizePidValue(PidType.doi.toString(), value.getDoi()));
|
||||
|
||||
relationList
|
||||
.add(
|
||||
getRelation(
|
||||
paper,
|
||||
IREL_PROJECT, ModelConstants.IS_PRODUCED_BY));
|
||||
|
||||
relationList.add(getRelation(IREL_PROJECT, paper, ModelConstants.PRODUCES));
|
||||
}
|
||||
return relationList;
|
||||
}
|
||||
|
||||
public static Relation getRelation(
|
||||
String source,
|
||||
String target,
|
||||
String relClass) {
|
||||
|
||||
return OafMapperUtils
|
||||
.getRelation(
|
||||
source,
|
||||
target,
|
||||
ModelConstants.RESULT_PROJECT,
|
||||
ModelConstants.OUTCOME,
|
||||
relClass,
|
||||
Arrays
|
||||
.asList(
|
||||
OafMapperUtils.keyValue(ModelConstants.OPEN_APC_ID, ModelConstants.OPEN_APC_NAME)),
|
||||
OafMapperUtils
|
||||
.dataInfo(
|
||||
false, null, false, false,
|
||||
OafMapperUtils
|
||||
.qualifier(
|
||||
TRANSFORMATIVE_AGREEMENT, "Transformative Agreement",
|
||||
ModelConstants.DNET_PROVENANCE_ACTIONS, ModelConstants.DNET_PROVENANCE_ACTIONS),
|
||||
"0.9"),
|
||||
null);
|
||||
}
|
||||
|
||||
}
|
@ -0,0 +1,51 @@
|
||||
|
||||
package eu.dnetlib.dhp.actionmanager.transformativeagreement.model;
|
||||
|
||||
import java.io.Serializable;
|
||||
|
||||
import com.fasterxml.jackson.annotation.JsonIgnoreProperties;
|
||||
|
||||
/**
|
||||
* @author miriam.baglioni
|
||||
* @Date 18/12/23
|
||||
*/
|
||||
@JsonIgnoreProperties(ignoreUnknown = true)
|
||||
|
||||
public class TransformativeAgreementModel implements Serializable {
|
||||
private String institution;
|
||||
private String doi;
|
||||
private String agreement;
|
||||
private String country;
|
||||
|
||||
public String getCountry() {
|
||||
return country;
|
||||
}
|
||||
|
||||
public void setCountry(String country) {
|
||||
this.country = country;
|
||||
}
|
||||
|
||||
public String getInstitution() {
|
||||
return institution;
|
||||
}
|
||||
|
||||
public void setInstitution(String institution) {
|
||||
this.institution = institution;
|
||||
}
|
||||
|
||||
public String getDoi() {
|
||||
return doi;
|
||||
}
|
||||
|
||||
public void setDoi(String doi) {
|
||||
this.doi = doi;
|
||||
}
|
||||
|
||||
public String getAgreement() {
|
||||
return agreement;
|
||||
}
|
||||
|
||||
public void setAgreement(String agreement) {
|
||||
this.agreement = agreement;
|
||||
}
|
||||
}
|
@ -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;
|
||||
}
|
||||
}
|
@ -0,0 +1,232 @@
|
||||
|
||||
package eu.dnetlib.dhp.actionmanager.webcrawl;
|
||||
|
||||
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
|
||||
|
||||
import java.io.Serializable;
|
||||
import java.util.*;
|
||||
import java.util.stream.Collectors;
|
||||
|
||||
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.function.FlatMapFunction;
|
||||
import org.apache.spark.sql.*;
|
||||
import org.apache.spark.sql.types.StructType;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
|
||||
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||
|
||||
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.utils.IdentifierFactory;
|
||||
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
|
||||
import eu.dnetlib.dhp.schema.oaf.utils.PidCleaner;
|
||||
import eu.dnetlib.dhp.schema.oaf.utils.PidType;
|
||||
import scala.Tuple2;
|
||||
|
||||
/**
|
||||
* @author miriam.baglioni
|
||||
* @Date 18/04/24
|
||||
*/
|
||||
public class CreateActionSetFromWebEntries implements Serializable {
|
||||
private static final Logger log = LoggerFactory.getLogger(CreateActionSetFromWebEntries.class);
|
||||
private static final String DOI_PREFIX = "50|doi_________::";
|
||||
|
||||
private static final String ROR_PREFIX = "20|ror_________::";
|
||||
|
||||
private static final String PMID_PREFIX = "50|pmid________::";
|
||||
|
||||
private static final String PMCID_PREFIX = "50|pmc_________::";
|
||||
private static final String WEB_CRAWL_ID = "10|openaire____::fb98a192f6a055ba495ef414c330834b";
|
||||
private static final String WEB_CRAWL_NAME = "Web Crawl";
|
||||
public static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
|
||||
|
||||
public static void main(String[] args) throws Exception {
|
||||
String jsonConfiguration = IOUtils
|
||||
.toString(
|
||||
CreateActionSetFromWebEntries.class
|
||||
.getResourceAsStream(
|
||||
"/eu/dnetlib/dhp/actionmanager/webcrawl/as_parameters.json"));
|
||||
|
||||
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
|
||||
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);
|
||||
|
||||
});
|
||||
}
|
||||
|
||||
public static void createActionSet(SparkSession spark, String inputPath,
|
||||
String outputPath) {
|
||||
|
||||
final Dataset<Row> dataset = readWebCrawl(spark, inputPath)
|
||||
.filter("publication_year <= 2020 or country_code=='IE'")
|
||||
.drop("publication_year");
|
||||
|
||||
dataset.flatMap((FlatMapFunction<Row, Relation>) row -> {
|
||||
List<Relation> ret = new ArrayList<>();
|
||||
final String ror = ROR_PREFIX
|
||||
+ IdentifierFactory.md5(PidCleaner.normalizePidValue("ROR", row.getAs("ror")));
|
||||
ret.addAll(createAffiliationRelationPairDOI(row.getAs("doi"), ror));
|
||||
ret.addAll(createAffiliationRelationPairPMID(row.getAs("pmid"), ror));
|
||||
ret.addAll(createAffiliationRelationPairPMCID(row.getAs("pmcid"), ror));
|
||||
|
||||
return ret
|
||||
.iterator();
|
||||
}, Encoders.bean(Relation.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);
|
||||
|
||||
}
|
||||
|
||||
private static Dataset<Row> readWebCrawl(SparkSession spark, String inputPath) {
|
||||
StructType webInfo = StructType
|
||||
.fromDDL(
|
||||
"`id` STRING , `doi` STRING, `ids` STRUCT<`pmid` :STRING, `pmcid`: STRING >, `publication_year` STRING, "
|
||||
+
|
||||
"`authorships` ARRAY<STRUCT <`institutions`: ARRAY <STRUCT <`ror`: STRING, `country_code` :STRING>>>>");
|
||||
|
||||
return spark
|
||||
.read()
|
||||
.schema(webInfo)
|
||||
.json(inputPath)
|
||||
.withColumn(
|
||||
"authors", functions
|
||||
.explode(
|
||||
functions.col("authorships")))
|
||||
.selectExpr("id", "doi", "ids", "publication_year", "authors.institutions as institutions")
|
||||
.withColumn(
|
||||
"institution", functions
|
||||
.explode(
|
||||
functions.col("institutions")))
|
||||
.selectExpr(
|
||||
"id", "doi", "ids.pmcid as pmcid", "ids.pmid as pmid", "institution.ror as ror",
|
||||
"institution.country_code as country_code", "publication_year")
|
||||
.distinct();
|
||||
|
||||
}
|
||||
|
||||
private static List<Relation> createAffiliationRelationPairPMCID(String pmcid, String ror) {
|
||||
if (pmcid == null)
|
||||
return new ArrayList<>();
|
||||
|
||||
return createAffiliatioRelationPair(
|
||||
PMCID_PREFIX
|
||||
+ IdentifierFactory
|
||||
.md5(PidCleaner.normalizePidValue(PidType.pmc.toString(), removeResolver("PMC", pmcid))),
|
||||
ror);
|
||||
}
|
||||
|
||||
private static List<Relation> createAffiliationRelationPairPMID(String pmid, String ror) {
|
||||
if (pmid == null)
|
||||
return new ArrayList<>();
|
||||
|
||||
return createAffiliatioRelationPair(
|
||||
PMID_PREFIX
|
||||
+ IdentifierFactory
|
||||
.md5(PidCleaner.normalizePidValue(PidType.pmid.toString(), removeResolver("PMID", pmid))),
|
||||
ror);
|
||||
}
|
||||
|
||||
private static String removeResolver(String pidType, String pid) {
|
||||
switch (pidType) {
|
||||
case "PMID":
|
||||
return pid.substring(33);
|
||||
case "PMC":
|
||||
return "PMC" + pid.substring(43);
|
||||
case "DOI":
|
||||
return pid.substring(16);
|
||||
}
|
||||
|
||||
throw new RuntimeException();
|
||||
|
||||
}
|
||||
|
||||
private static List<Relation> createAffiliationRelationPairDOI(String doi, String ror) {
|
||||
if (doi == null)
|
||||
return new ArrayList<>();
|
||||
|
||||
return createAffiliatioRelationPair(
|
||||
DOI_PREFIX
|
||||
+ IdentifierFactory
|
||||
.md5(PidCleaner.normalizePidValue(PidType.doi.toString(), removeResolver("DOI", doi))),
|
||||
ror);
|
||||
|
||||
}
|
||||
|
||||
private static List<Relation> createAffiliatioRelationPair(String resultId, String orgId) {
|
||||
ArrayList<Relation> newRelations = new ArrayList();
|
||||
|
||||
newRelations
|
||||
.add(
|
||||
OafMapperUtils
|
||||
.getRelation(
|
||||
orgId, resultId, ModelConstants.RESULT_ORGANIZATION, ModelConstants.AFFILIATION,
|
||||
ModelConstants.IS_AUTHOR_INSTITUTION_OF,
|
||||
Arrays
|
||||
.asList(
|
||||
OafMapperUtils.keyValue(WEB_CRAWL_ID, WEB_CRAWL_NAME)),
|
||||
OafMapperUtils
|
||||
.dataInfo(
|
||||
false, null, false, false,
|
||||
OafMapperUtils
|
||||
.qualifier(
|
||||
"sysimport:crasswalk:webcrawl", "Imported from Webcrawl",
|
||||
ModelConstants.DNET_PROVENANCE_ACTIONS, ModelConstants.DNET_PROVENANCE_ACTIONS),
|
||||
"0.9"),
|
||||
null));
|
||||
|
||||
newRelations
|
||||
.add(
|
||||
OafMapperUtils
|
||||
.getRelation(
|
||||
resultId, orgId, ModelConstants.RESULT_ORGANIZATION, ModelConstants.AFFILIATION,
|
||||
ModelConstants.HAS_AUTHOR_INSTITUTION,
|
||||
Arrays
|
||||
.asList(
|
||||
OafMapperUtils.keyValue(WEB_CRAWL_ID, WEB_CRAWL_NAME)),
|
||||
OafMapperUtils
|
||||
.dataInfo(
|
||||
false, null, false, false,
|
||||
OafMapperUtils
|
||||
.qualifier(
|
||||
"sysimport:crasswalk:webcrawl", "Imported from Webcrawl",
|
||||
ModelConstants.DNET_PROVENANCE_ACTIONS, ModelConstants.DNET_PROVENANCE_ACTIONS),
|
||||
"0.9"),
|
||||
null));
|
||||
|
||||
return newRelations;
|
||||
|
||||
}
|
||||
|
||||
}
|
@ -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);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
}
|
@ -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();
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
}
|
@ -0,0 +1,171 @@
|
||||
|
||||
package eu.dnetlib.dhp.collection.plugin.base;
|
||||
|
||||
import java.io.BufferedInputStream;
|
||||
import java.io.ByteArrayInputStream;
|
||||
import java.io.InputStream;
|
||||
import java.io.StringWriter;
|
||||
import java.util.Iterator;
|
||||
import java.util.concurrent.BlockingQueue;
|
||||
import java.util.concurrent.LinkedBlockingQueue;
|
||||
|
||||
import javax.xml.stream.XMLEventReader;
|
||||
import javax.xml.stream.XMLEventWriter;
|
||||
import javax.xml.stream.XMLInputFactory;
|
||||
import javax.xml.stream.XMLOutputFactory;
|
||||
import javax.xml.stream.events.EndElement;
|
||||
import javax.xml.stream.events.StartElement;
|
||||
import javax.xml.stream.events.XMLEvent;
|
||||
|
||||
import org.apache.commons.compress.archivers.tar.TarArchiveEntry;
|
||||
import org.apache.commons.compress.archivers.tar.TarArchiveInputStream;
|
||||
import org.apache.commons.compress.compressors.CompressorInputStream;
|
||||
import org.apache.commons.compress.compressors.CompressorStreamFactory;
|
||||
import org.apache.commons.io.IOUtils;
|
||||
import org.apache.hadoop.fs.FileSystem;
|
||||
import org.apache.hadoop.fs.Path;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
|
||||
import eu.dnetlib.dhp.common.aggregation.AggregatorReport;
|
||||
|
||||
public class BaseCollectorIterator implements Iterator<String> {
|
||||
|
||||
private String nextElement;
|
||||
|
||||
private final BlockingQueue<String> queue = new LinkedBlockingQueue<>(100);
|
||||
|
||||
private static final Logger log = LoggerFactory.getLogger(BaseCollectorIterator.class);
|
||||
|
||||
private static final String END_ELEM = "__END__";
|
||||
|
||||
public BaseCollectorIterator(final FileSystem fs, final Path filePath, final AggregatorReport report) {
|
||||
new Thread(() -> importHadoopFile(fs, filePath, report)).start();
|
||||
try {
|
||||
this.nextElement = this.queue.take();
|
||||
} catch (final InterruptedException e) {
|
||||
throw new RuntimeException(e);
|
||||
}
|
||||
}
|
||||
|
||||
protected BaseCollectorIterator(final String resourcePath, final AggregatorReport report) {
|
||||
new Thread(() -> importTestFile(resourcePath, report)).start();
|
||||
try {
|
||||
this.nextElement = this.queue.take();
|
||||
} catch (final InterruptedException e) {
|
||||
throw new RuntimeException(e);
|
||||
}
|
||||
}
|
||||
|
||||
@Override
|
||||
public synchronized boolean hasNext() {
|
||||
return (this.nextElement != null) & !END_ELEM.equals(this.nextElement);
|
||||
}
|
||||
|
||||
@Override
|
||||
public synchronized String next() {
|
||||
try {
|
||||
return END_ELEM.equals(this.nextElement) ? null : this.nextElement;
|
||||
} finally {
|
||||
try {
|
||||
this.nextElement = this.queue.take();
|
||||
} catch (final InterruptedException e) {
|
||||
throw new RuntimeException(e);
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
private void importHadoopFile(final FileSystem fs, final Path filePath, final AggregatorReport report) {
|
||||
log.info("I start to read the TAR stream");
|
||||
|
||||
try (InputStream origInputStream = fs.open(filePath);
|
||||
final TarArchiveInputStream tarInputStream = new TarArchiveInputStream(origInputStream)) {
|
||||
importTarStream(tarInputStream, report);
|
||||
} catch (final Throwable e) {
|
||||
throw new RuntimeException("Error processing BASE records", e);
|
||||
}
|
||||
}
|
||||
|
||||
private void importTestFile(final String resourcePath, final AggregatorReport report) {
|
||||
try (final InputStream origInputStream = BaseCollectorIterator.class.getResourceAsStream(resourcePath);
|
||||
final TarArchiveInputStream tarInputStream = new TarArchiveInputStream(origInputStream)) {
|
||||
importTarStream(tarInputStream, report);
|
||||
} catch (final Throwable e) {
|
||||
throw new RuntimeException("Error processing BASE records", e);
|
||||
}
|
||||
}
|
||||
|
||||
private void importTarStream(final TarArchiveInputStream tarInputStream, final AggregatorReport report) {
|
||||
long count = 0;
|
||||
|
||||
final XMLInputFactory xmlInputFactory = XMLInputFactory.newInstance();
|
||||
final XMLOutputFactory xmlOutputFactory = XMLOutputFactory.newInstance();
|
||||
|
||||
try {
|
||||
TarArchiveEntry entry;
|
||||
while ((entry = (TarArchiveEntry) tarInputStream.getNextEntry()) != null) {
|
||||
final String name = entry.getName();
|
||||
|
||||
if (!entry.isDirectory() && name.contains("ListRecords") && name.endsWith(".bz2")) {
|
||||
|
||||
log.info("Processing file (BZIP): " + name);
|
||||
|
||||
final byte[] bzipData = new byte[(int) entry.getSize()];
|
||||
IOUtils.readFully(tarInputStream, bzipData);
|
||||
|
||||
try (InputStream bzipIs = new ByteArrayInputStream(bzipData);
|
||||
final BufferedInputStream bzipBis = new BufferedInputStream(bzipIs);
|
||||
final CompressorInputStream bzipInput = new CompressorStreamFactory()
|
||||
.createCompressorInputStream(bzipBis)) {
|
||||
|
||||
final XMLEventReader reader = xmlInputFactory.createXMLEventReader(bzipInput);
|
||||
|
||||
XMLEventWriter eventWriter = null;
|
||||
StringWriter xmlWriter = null;
|
||||
|
||||
while (reader.hasNext()) {
|
||||
final XMLEvent nextEvent = reader.nextEvent();
|
||||
|
||||
if (nextEvent.isStartElement()) {
|
||||
final StartElement startElement = nextEvent.asStartElement();
|
||||
if ("record".equals(startElement.getName().getLocalPart())) {
|
||||
xmlWriter = new StringWriter();
|
||||
eventWriter = xmlOutputFactory.createXMLEventWriter(xmlWriter);
|
||||
}
|
||||
}
|
||||
|
||||
if (eventWriter != null) {
|
||||
eventWriter.add(nextEvent);
|
||||
}
|
||||
|
||||
if (nextEvent.isEndElement()) {
|
||||
final EndElement endElement = nextEvent.asEndElement();
|
||||
if ("record".equals(endElement.getName().getLocalPart())) {
|
||||
eventWriter.flush();
|
||||
eventWriter.close();
|
||||
|
||||
this.queue.put(xmlWriter.toString());
|
||||
|
||||
eventWriter = null;
|
||||
xmlWriter = null;
|
||||
count++;
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
this.queue.put(END_ELEM); // TO INDICATE THE END OF THE QUEUE
|
||||
} catch (final Throwable e) {
|
||||
log.error("Error processing BASE records", e);
|
||||
report.put(e.getClass().getName(), e.getMessage());
|
||||
throw new RuntimeException("Error processing BASE records", e);
|
||||
} finally {
|
||||
log.info("Total records (written in queue): " + count);
|
||||
}
|
||||
}
|
||||
|
||||
}
|
@ -0,0 +1,159 @@
|
||||
|
||||
package eu.dnetlib.dhp.collection.plugin.base;
|
||||
|
||||
import java.io.IOException;
|
||||
import java.sql.SQLException;
|
||||
import java.util.HashSet;
|
||||
import java.util.Iterator;
|
||||
import java.util.Optional;
|
||||
import java.util.Set;
|
||||
import java.util.Spliterator;
|
||||
import java.util.Spliterators;
|
||||
import java.util.stream.Stream;
|
||||
import java.util.stream.StreamSupport;
|
||||
|
||||
import org.apache.commons.io.IOUtils;
|
||||
import org.apache.commons.lang3.StringUtils;
|
||||
import org.apache.hadoop.fs.FileSystem;
|
||||
import org.apache.hadoop.fs.Path;
|
||||
import org.dom4j.Document;
|
||||
import org.dom4j.DocumentException;
|
||||
import org.dom4j.DocumentHelper;
|
||||
import org.dom4j.Node;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
|
||||
import eu.dnetlib.dhp.collection.ApiDescriptor;
|
||||
import eu.dnetlib.dhp.collection.plugin.CollectorPlugin;
|
||||
import eu.dnetlib.dhp.collection.plugin.file.AbstractSplittedRecordPlugin;
|
||||
import eu.dnetlib.dhp.common.DbClient;
|
||||
import eu.dnetlib.dhp.common.aggregation.AggregatorReport;
|
||||
import eu.dnetlib.dhp.common.collection.CollectorException;
|
||||
|
||||
public class BaseCollectorPlugin implements CollectorPlugin {
|
||||
|
||||
private final FileSystem fs;
|
||||
|
||||
private static final Logger log = LoggerFactory.getLogger(AbstractSplittedRecordPlugin.class);
|
||||
|
||||
// MAPPING AND FILTERING ARE DEFINED HERE:
|
||||
// https://docs.google.com/document/d/1Aj-ZAV11b44MCrAAUCPiS2TUlXb6PnJEu1utCMAcCOU/edit
|
||||
|
||||
public BaseCollectorPlugin(final FileSystem fs) {
|
||||
this.fs = fs;
|
||||
}
|
||||
|
||||
@Override
|
||||
public Stream<String> collect(final ApiDescriptor api, final AggregatorReport report) throws CollectorException {
|
||||
// the path of the dump file on HDFS
|
||||
// http://oai.base-search.net/initial_load/base_oaipmh_dump-current.tar
|
||||
// it could be downloaded from iis-cdh5-test-gw.ocean.icm.edu.pl and then copied on HDFS
|
||||
final Path filePath = Optional
|
||||
.ofNullable(api.getBaseUrl())
|
||||
.map(Path::new)
|
||||
.orElseThrow(() -> new CollectorException("missing baseUrl"));
|
||||
|
||||
// get the parameters for the connection to the OpenAIRE database.
|
||||
// the database is used to obtain the list of the datasources that the plugin will collect
|
||||
final String dbUrl = api.getParams().get("dbUrl");
|
||||
final String dbUser = api.getParams().get("dbUser");
|
||||
final String dbPassword = api.getParams().get("dbPassword");
|
||||
|
||||
// the types(comma separated, empty value for all) that the plugin will collect,
|
||||
// the types should be expressed in the format of the normalized types of BASE (for example 1,121,...)
|
||||
final String acceptedNormTypesString = api.getParams().get("acceptedNormTypes");
|
||||
|
||||
log.info("baseUrl: {}", filePath);
|
||||
log.info("dbUrl: {}", dbUrl);
|
||||
log.info("dbUser: {}", dbUser);
|
||||
log.info("dbPassword: {}", "***");
|
||||
log.info("acceptedNormTypes: {}", acceptedNormTypesString);
|
||||
|
||||
try {
|
||||
if (!this.fs.exists(filePath)) {
|
||||
throw new CollectorException("path does not exist: " + filePath);
|
||||
}
|
||||
} catch (final Throwable e) {
|
||||
throw new CollectorException(e);
|
||||
}
|
||||
|
||||
final Set<String> acceptedOpendoarIds = findAcceptedOpendoarIds(dbUrl, dbUser, dbPassword);
|
||||
|
||||
final Set<String> acceptedNormTypes = new HashSet<>();
|
||||
if (StringUtils.isNotBlank(acceptedNormTypesString)) {
|
||||
for (final String s : StringUtils.split(acceptedNormTypesString, ",")) {
|
||||
if (StringUtils.isNotBlank(s)) {
|
||||
acceptedNormTypes.add(s.trim());
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
final Iterator<String> iterator = new BaseCollectorIterator(this.fs, filePath, report);
|
||||
final Spliterator<String> spliterator = Spliterators.spliteratorUnknownSize(iterator, Spliterator.ORDERED);
|
||||
return StreamSupport
|
||||
.stream(spliterator, false)
|
||||
.filter(doc -> filterXml(doc, acceptedOpendoarIds, acceptedNormTypes));
|
||||
}
|
||||
|
||||
private Set<String> findAcceptedOpendoarIds(final String dbUrl, final String dbUser, final String dbPassword)
|
||||
throws CollectorException {
|
||||
final Set<String> accepted = new HashSet<>();
|
||||
|
||||
try (final DbClient dbClient = new DbClient(dbUrl, dbUser, dbPassword)) {
|
||||
|
||||
final String sql = IOUtils
|
||||
.toString(
|
||||
getClass().getResourceAsStream("/eu/dnetlib/dhp/collection/plugin/base/sql/opendoar-accepted.sql"));
|
||||
|
||||
dbClient.processResults(sql, row -> {
|
||||
try {
|
||||
final String dsId = row.getString("id");
|
||||
log.info("Accepted Datasource: " + dsId);
|
||||
accepted.add(dsId);
|
||||
} catch (final SQLException e) {
|
||||
log.error("Error in SQL", e);
|
||||
throw new RuntimeException("Error in SQL", e);
|
||||
}
|
||||
});
|
||||
|
||||
} catch (final IOException e) {
|
||||
log.error("Error accessong SQL", e);
|
||||
throw new CollectorException("Error accessong SQL", e);
|
||||
}
|
||||
|
||||
log.info("Accepted Datasources (TOTAL): " + accepted.size());
|
||||
|
||||
return accepted;
|
||||
}
|
||||
|
||||
protected static boolean filterXml(final String xml,
|
||||
final Set<String> acceptedOpendoarIds,
|
||||
final Set<String> acceptedNormTypes) {
|
||||
try {
|
||||
|
||||
final Document doc = DocumentHelper.parseText(xml);
|
||||
|
||||
final String id = doc.valueOf("//*[local-name()='collection']/@opendoar_id").trim();
|
||||
|
||||
if (StringUtils.isBlank(id) || !acceptedOpendoarIds.contains("opendoar____::" + id)) {
|
||||
return false;
|
||||
}
|
||||
|
||||
if (acceptedNormTypes.isEmpty()) {
|
||||
return true;
|
||||
}
|
||||
|
||||
for (final Object s : doc.selectNodes("//*[local-name()='typenorm']")) {
|
||||
if (acceptedNormTypes.contains(((Node) s).getText().trim())) {
|
||||
return true;
|
||||
}
|
||||
}
|
||||
|
||||
return false;
|
||||
} catch (final DocumentException e) {
|
||||
log.error("Error parsing document", e);
|
||||
throw new RuntimeException("Error parsing document", e);
|
||||
}
|
||||
}
|
||||
|
||||
}
|
@ -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
|
||||
}
|
||||
]
|
@ -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>
|
@ -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>
|
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in New Issue