1
0
Fork 0

Merge branch 'master' of code-repo.d4science.org:D-Net/dnet-hadoop

This commit is contained in:
Miriam Baglioni 2020-05-14 10:34:17 +02:00
commit e7eb4f377e
33 changed files with 499 additions and 329 deletions

View File

@ -1,4 +1,4 @@
<workflow-app name="blacklisting" xmlns="uri:oozie:workflow:0.5">
<workflow-app name="blacklist_relations" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>postgresURL</name>
@ -102,7 +102,7 @@
<error to="Kill"/>
</action>
<action name="copy_projects">
<action name="copy_project">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
@ -113,7 +113,7 @@
<error to="Kill"/>
</action>
<action name="copy_datasources">
<action name="copy_datasource">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>

View File

@ -29,31 +29,32 @@ public class EventFactory {
"yyyy-MM-dd"
};
public static Event newBrokerEvent(final Result source, final Result target, final UpdateInfo<?> updateInfo) {
public static Event newBrokerEvent(final UpdateInfo<?> updateInfo) {
final long now = new Date().getTime();
final Event res = new Event();
final Map<String, Object> map = createMapFromResult(target, source, updateInfo);
final Map<String, Object> map = createMapFromResult(updateInfo);
final String payload = createPayload(target, updateInfo);
final String payload = createPayload(updateInfo);
final String eventId = calculateEventId(
updateInfo.getTopic(), target.getOriginalId().get(0), updateInfo.getHighlightValueAsString());
updateInfo.getTopicPath(), updateInfo.getTarget().getOriginalId().get(0),
updateInfo.getHighlightValueAsString());
res.setEventId(eventId);
res.setProducerId(PRODUCER_ID);
res.setPayload(payload);
res.setMap(map);
res.setTopic(updateInfo.getTopic());
res.setTopic(updateInfo.getTopicPath());
res.setCreationDate(now);
res.setExpiryDate(calculateExpiryDate(now));
res.setInstantMessage(false);
return res;
}
private static String createPayload(final Result result, final UpdateInfo<?> updateInfo) {
private static String createPayload(final UpdateInfo<?> updateInfo) {
final OpenAireEventPayload payload = new OpenAireEventPayload();
// TODO
@ -62,32 +63,34 @@ public class EventFactory {
return payload.toJSON();
}
private static Map<String, Object> createMapFromResult(final Result oaf, final Result source,
final UpdateInfo<?> updateInfo) {
private static Map<String, Object> createMapFromResult(final UpdateInfo<?> updateInfo) {
final Map<String, Object> map = new HashMap<>();
final List<KeyValue> collectedFrom = oaf.getCollectedfrom();
final Result source = updateInfo.getSource();
final Result target = updateInfo.getTarget();
final List<KeyValue> collectedFrom = target.getCollectedfrom();
if (collectedFrom.size() == 1) {
map.put("target_datasource_id", collectedFrom.get(0).getKey());
map.put("target_datasource_name", collectedFrom.get(0).getValue());
}
final List<String> ids = oaf.getOriginalId();
final List<String> ids = target.getOriginalId();
if (ids.size() > 0) {
map.put("target_publication_id", ids.get(0));
}
final List<StructuredProperty> titles = oaf.getTitle();
final List<StructuredProperty> titles = target.getTitle();
if (titles.size() > 0) {
map.put("target_publication_title", titles.get(0));
}
final long date = parseDateTolong(oaf.getDateofacceptance().getValue());
final long date = parseDateTolong(target.getDateofacceptance().getValue());
if (date > 0) {
map.put("target_dateofacceptance", date);
}
final List<StructuredProperty> subjects = oaf.getSubject();
final List<StructuredProperty> subjects = target.getSubject();
if (subjects.size() > 0) {
map
.put(
@ -95,7 +98,7 @@ public class EventFactory {
subjects.stream().map(StructuredProperty::getValue).collect(Collectors.toList()));
}
final List<Author> authors = oaf.getAuthor();
final List<Author> authors = target.getAuthor();
if (authors.size() > 0) {
map
.put(

View File

@ -0,0 +1,52 @@
package eu.dnetlib.dhp.broker.model;
public enum Topic {
// ENRICHMENT MISSING
ENRICH_MISSING_OA_VERSION("ENRICH/MISSING/OPENACCESS_VERSION"), ENRICH_MISSING_ABSTRACT(
"ENRICH/MISSING/ABSTRACT"), ENRICH_MISSING_PUBLICATION_DATE(
"ENRICH/MISSING/PUBLICATION_DATE"), ENRICH_MISSING_PID(
"ENRICH/MISSING/PID"), ENRICH_MISSING_PROJECT("ENRICH/MISSING/PROJECT"), ENRICH_MISSING_SOFTWARE(
"ENRICH/MISSING/SOFTWARE"), ENRICH_MISSING_SUBJECT_MESHEUROPMC(
"ENRICH/MISSING/SUBJECT/MESHEUROPMC"), ENRICH_MISSING_SUBJECT_ARXIV(
"ENRICH/MISSING/SUBJECT/ARXIV"), ENRICH_MISSING_SUBJECT_JEL(
"ENRICH/MISSING/SUBJECT/JEL"), ENRICH_MISSING_SUBJECT_DDC(
"ENRICH/MISSING/SUBJECT/DDC"), ENRICH_MISSING_SUBJECT_ACM(
"ENRICH/MISSING/SUBJECT/ACM"), ENRICH_MISSING_SUBJECT_RVK(
"ENRICH/MISSING/SUBJECT/RVK"), ENRICH_MISSING_AUTHOR_ORCID(
"ENRICH/MISSING/AUTHOR/ORCID"),
// ENRICHMENT MORE
ENRICH_MORE_PID("ENRICH/MORE/PID"), ENRICH_MORE_OA_VERSION("ENRICH/MORE/OPENACCESS_VERSION"), ENRICH_MORE_ABSTRACT(
"ENRICH/MORE/ABSTRACT"), ENRICH_MORE_PUBLICATION_DATE("ENRICH/MORE/PUBLICATION_DATE"), ENRICH_MORE_PROJECT(
"ENRICH/MORE/PROJECT"), ENRICH_MORE_SUBJECT_MESHEUROPMC(
"ENRICH/MORE/SUBJECT/MESHEUROPMC"), ENRICH_MORE_SUBJECT_ARXIV(
"ENRICH/MORE/SUBJECT/ARXIV"), ENRICH_MORE_SUBJECT_JEL(
"ENRICH/MORE/SUBJECT/JEL"), ENRICH_MORE_SUBJECT_DDC(
"ENRICH/MORE/SUBJECT/DDC"), ENRICH_MORE_SUBJECT_ACM(
"ENRICH/MORE/SUBJECT/ACM"), ENRICH_MORE_SUBJECT_RVK("ENRICH/MORE/SUBJECT/RVK"),
// ADDITION
ADD_BY_PROJECT("ADD/BY_PROJECT");
Topic(final String path) {
this.path = path;
}
protected String path;
public String getPath() {
return this.path;
}
public static Topic fromPath(final String path) {
for (final Topic t : Topic.values()) {
if (t.getPath().equals(path)) {
return t;
}
}
return null;
}
}

View File

@ -14,8 +14,6 @@ import org.apache.spark.sql.SparkSession;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.broker.model.Event;
import eu.dnetlib.dhp.broker.model.EventFactory;
@ -30,6 +28,7 @@ import eu.dnetlib.dhp.broker.oa.util.EnrichMoreOpenAccess;
import eu.dnetlib.dhp.broker.oa.util.EnrichMorePid;
import eu.dnetlib.dhp.broker.oa.util.EnrichMoreSubject;
import eu.dnetlib.dhp.broker.oa.util.UpdateInfo;
import eu.dnetlib.dhp.broker.oa.util.UpdateMatcher;
import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.schema.oaf.Result;
@ -37,7 +36,16 @@ public class GenerateEventsApplication {
private static final Logger log = LoggerFactory.getLogger(GenerateEventsApplication.class);
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
private static final UpdateMatcher<?> enrichMissingAbstract = new EnrichMissingAbstract();
private static final UpdateMatcher<?> enrichMissingAuthorOrcid = new EnrichMissingAuthorOrcid();
private static final UpdateMatcher<?> enrichMissingOpenAccess = new EnrichMissingOpenAccess();
private static final UpdateMatcher<?> enrichMissingPid = new EnrichMissingPid();
private static final UpdateMatcher<?> enrichMissingProject = new EnrichMissingProject();
private static final UpdateMatcher<?> enrichMissingPublicationDate = new EnrichMissingPublicationDate();
private static final UpdateMatcher<?> enrichMissingSubject = new EnrichMissingSubject();
private static final UpdateMatcher<?> enrichMoreOpenAccess = new EnrichMoreOpenAccess();
private static final UpdateMatcher<?> enrichMorePid = new EnrichMorePid();
private static final UpdateMatcher<?> enrichMoreSubject = new EnrichMoreSubject();
public static void main(final String[] args) throws Exception {
final ArgumentApplicationParser parser = new ArgumentApplicationParser(
@ -76,37 +84,22 @@ public class GenerateEventsApplication {
}
private List<Event> generateEvents(final Result... children) {
final List<Event> list = new ArrayList<>();
final List<UpdateInfo<?>> list = new ArrayList<>();
for (final Result source : children) {
for (final Result target : children) {
if (source != target) {
list
.addAll(
findUpdates(source, target)
.stream()
.map(info -> EventFactory.newBrokerEvent(source, target, info))
.collect(Collectors.toList()));
}
}
for (final Result target : children) {
list.addAll(enrichMissingAbstract.searchUpdatesForRecord(target, children));
list.addAll(enrichMissingAuthorOrcid.searchUpdatesForRecord(target, children));
list.addAll(enrichMissingOpenAccess.searchUpdatesForRecord(target, children));
list.addAll(enrichMissingPid.searchUpdatesForRecord(target, children));
list.addAll(enrichMissingProject.searchUpdatesForRecord(target, children));
list.addAll(enrichMissingPublicationDate.searchUpdatesForRecord(target, children));
list.addAll(enrichMissingSubject.searchUpdatesForRecord(target, children));
list.addAll(enrichMoreOpenAccess.searchUpdatesForRecord(target, children));
list.addAll(enrichMorePid.searchUpdatesForRecord(target, children));
list.addAll(enrichMoreSubject.searchUpdatesForRecord(target, children));
}
return list;
}
private List<UpdateInfo<?>> findUpdates(final Result source, final Result target) {
final List<UpdateInfo<?>> list = new ArrayList<>();
list.addAll(EnrichMissingAbstract.findUpdates(source, target));
list.addAll(EnrichMissingAuthorOrcid.findUpdates(source, target));
list.addAll(EnrichMissingOpenAccess.findUpdates(source, target));
list.addAll(EnrichMissingPid.findUpdates(source, target));
list.addAll(EnrichMissingProject.findUpdates(source, target));
list.addAll(EnrichMissingPublicationDate.findUpdates(source, target));
list.addAll(EnrichMissingSubject.findUpdates(source, target));
list.addAll(EnrichMoreOpenAccess.findUpdates(source, target));
list.addAll(EnrichMorePid.findUpdates(source, target));
list.addAll(EnrichMoreSubject.findUpdates(source, target));
return list;
return list.stream().map(EventFactory::newBrokerEvent).collect(Collectors.toList());
}
}

View File

@ -1,31 +1,35 @@
package eu.dnetlib.dhp.broker.oa.util;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
import eu.dnetlib.broker.objects.OpenAireEventPayload;
import eu.dnetlib.dhp.broker.model.Topic;
import eu.dnetlib.dhp.schema.oaf.Result;
public class EnrichMissingAbstract extends UpdateInfo<String> {
public class EnrichMissingAbstract extends UpdateMatcher<String> {
public static List<EnrichMissingAbstract> findUpdates(final Result source, final Result target) {
// return Arrays.asList(new EnrichMissingAbstract("xxxxxxx", 0.9f));
return Arrays.asList();
}
private EnrichMissingAbstract(final String highlightValue, final float trust) {
super("ENRICH/MISSING/ABSTRACT", highlightValue, trust);
public EnrichMissingAbstract() {
super(false);
}
@Override
public void compileHighlight(final OpenAireEventPayload payload) {
payload.getHighlight().getAbstracts().add(getHighlightValue());
protected List<UpdateInfo<String>> findUpdates(final Result source, final Result target) {
if (isMissing(target.getDescription()) && !isMissing(source.getDescription())) {
return Arrays.asList(generateUpdateInfo(source.getDescription().get(0).getValue(), source, target));
}
return new ArrayList<>();
}
@Override
public String getHighlightValueAsString() {
return getHighlightValue();
public UpdateInfo<String> generateUpdateInfo(final String highlightValue, final Result source,
final Result target) {
return new UpdateInfo<>(
Topic.ENRICH_MISSING_ABSTRACT,
highlightValue, source, target,
(p, s) -> p.getAbstracts().add(s),
s -> s);
}
}

View File

@ -4,28 +4,30 @@ package eu.dnetlib.dhp.broker.oa.util;
import java.util.Arrays;
import java.util.List;
import eu.dnetlib.broker.objects.OpenAireEventPayload;
import org.apache.commons.lang3.tuple.Pair;
import eu.dnetlib.dhp.broker.model.Topic;
import eu.dnetlib.dhp.schema.oaf.Result;
public class EnrichMissingAuthorOrcid extends UpdateInfo<String> {
public class EnrichMissingAuthorOrcid extends UpdateMatcher<Pair<String, String>> {
public static List<EnrichMissingAuthorOrcid> findUpdates(final Result source, final Result target) {
public EnrichMissingAuthorOrcid() {
super(true);
}
@Override
protected List<UpdateInfo<Pair<String, String>>> findUpdates(final Result source, final Result target) {
// return Arrays.asList(new EnrichMissingAbstract("xxxxxxx", 0.9f));
return Arrays.asList();
}
private EnrichMissingAuthorOrcid(final String highlightValue, final float trust) {
super("ENRICH/MISSING/AUTHOR/ORCID", highlightValue, trust);
}
@Override
public void compileHighlight(final OpenAireEventPayload payload) {
// TODO
public UpdateInfo<Pair<String, String>> generateUpdateInfo(final Pair<String, String> highlightValue,
final Result source, final Result target) {
return new UpdateInfo<>(
Topic.ENRICH_MISSING_AUTHOR_ORCID,
highlightValue, source, target,
(p, pair) -> p.getCreators().add(pair.getLeft() + " - ORCID: " + pair.getRight()),
pair -> pair.getLeft() + "::" + pair.getRight());
}
@Override
public String getHighlightValueAsString() {
return getHighlightValue();
}
}

View File

@ -5,28 +5,29 @@ import java.util.Arrays;
import java.util.List;
import eu.dnetlib.broker.objects.Instance;
import eu.dnetlib.broker.objects.OpenAireEventPayload;
import eu.dnetlib.dhp.broker.model.Topic;
import eu.dnetlib.dhp.schema.oaf.Result;
public class EnrichMissingOpenAccess extends UpdateInfo<Instance> {
public class EnrichMissingOpenAccess extends UpdateMatcher<Instance> {
public EnrichMissingOpenAccess() {
super(true);
}
@Override
protected List<UpdateInfo<Instance>> findUpdates(final Result source, final Result target) {
public static List<EnrichMissingOpenAccess> findUpdates(final Result source, final Result target) {
// return Arrays.asList(new EnrichMissingAbstract("xxxxxxx", 0.9f));
return Arrays.asList();
}
private EnrichMissingOpenAccess(final Instance highlightValue, final float trust) {
super("ENRICH/MISSING/OPENACCESS_VERSION", highlightValue, trust);
}
@Override
public void compileHighlight(final OpenAireEventPayload payload) {
payload.getHighlight().getInstances().add(getHighlightValue());
}
@Override
public String getHighlightValueAsString() {
return getHighlightValue().getUrl();
public UpdateInfo<Instance> generateUpdateInfo(final Instance highlightValue, final Result source,
final Result target) {
return new UpdateInfo<>(
Topic.ENRICH_MISSING_OA_VERSION,
highlightValue, source, target,
(p, i) -> p.getInstances().add(i),
Instance::getUrl);
}
}

View File

@ -4,29 +4,29 @@ package eu.dnetlib.dhp.broker.oa.util;
import java.util.Arrays;
import java.util.List;
import eu.dnetlib.broker.objects.OpenAireEventPayload;
import eu.dnetlib.broker.objects.Pid;
import eu.dnetlib.dhp.broker.model.Topic;
import eu.dnetlib.dhp.schema.oaf.Result;
public class EnrichMissingPid extends UpdateInfo<Pid> {
public class EnrichMissingPid extends UpdateMatcher<Pid> {
public static List<EnrichMissingPid> findUpdates(final Result source, final Result target) {
public EnrichMissingPid() {
super(true);
}
@Override
protected List<UpdateInfo<Pid>> findUpdates(final Result source, final Result target) {
// return Arrays.asList(new EnrichMissingAbstract("xxxxxxx", 0.9f));
return Arrays.asList();
}
private EnrichMissingPid(final Pid highlightValue, final float trust) {
super("ENRICH/MISSING/PID", highlightValue, trust);
}
@Override
public void compileHighlight(final OpenAireEventPayload payload) {
payload.getHighlight().getPids().add(getHighlightValue());
}
@Override
public String getHighlightValueAsString() {
return getHighlightValue().getType() + "::" + getHighlightValue().getValue();
public UpdateInfo<Pid> generateUpdateInfo(final Pid highlightValue, final Result source, final Result target) {
return new UpdateInfo<>(
Topic.ENRICH_MISSING_PID,
highlightValue, source, target,
(p, pid) -> p.getPids().add(pid),
pid -> pid.getType() + "::" + pid.getValue());
}
}

View File

@ -4,30 +4,30 @@ package eu.dnetlib.dhp.broker.oa.util;
import java.util.Arrays;
import java.util.List;
import eu.dnetlib.broker.objects.OpenAireEventPayload;
import eu.dnetlib.broker.objects.Project;
import eu.dnetlib.dhp.broker.model.Topic;
import eu.dnetlib.dhp.schema.oaf.Result;
public class EnrichMissingProject extends UpdateInfo<Project> {
public class EnrichMissingProject extends UpdateMatcher<Project> {
public static List<EnrichMissingProject> findUpdates(final Result source, final Result target) {
public EnrichMissingProject() {
super(true);
}
@Override
protected List<UpdateInfo<Project>> findUpdates(final Result source, final Result target) {
// return Arrays.asList(new EnrichMissingAbstract("xxxxxxx", 0.9f));
return Arrays.asList();
}
private EnrichMissingProject(final Project highlightValue, final float trust) {
super("ENRICH/MISSING/PROJECT", highlightValue, trust);
}
@Override
public void compileHighlight(final OpenAireEventPayload payload) {
payload.getHighlight().getProjects().add(getHighlightValue());
}
@Override
public String getHighlightValueAsString() {
return getHighlightValue().getFunder() + "::" + getHighlightValue().getFundingProgram()
+ getHighlightValue().getCode();
public UpdateInfo<Project> generateUpdateInfo(final Project highlightValue, final Result source,
final Result target) {
return new UpdateInfo<>(
Topic.ENRICH_MISSING_PROJECT,
highlightValue, source, target,
(p, prj) -> p.getProjects().add(prj),
prj -> prj.getFunder() + "::" + prj.getFundingProgram() + prj.getCode());
}
}

View File

@ -4,28 +4,29 @@ package eu.dnetlib.dhp.broker.oa.util;
import java.util.Arrays;
import java.util.List;
import eu.dnetlib.broker.objects.OpenAireEventPayload;
import eu.dnetlib.dhp.broker.model.Topic;
import eu.dnetlib.dhp.schema.oaf.Result;
public class EnrichMissingPublicationDate extends UpdateInfo<String> {
public class EnrichMissingPublicationDate extends UpdateMatcher<String> {
public static List<EnrichMissingPublicationDate> findUpdates(final Result source, final Result target) {
public EnrichMissingPublicationDate() {
super(false);
}
@Override
protected List<UpdateInfo<String>> findUpdates(final Result source, final Result target) {
// return Arrays.asList(new EnrichMissingAbstract("xxxxxxx", 0.9f));
return Arrays.asList();
}
private EnrichMissingPublicationDate(final String highlightValue, final float trust) {
super("ENRICH/MISSING/PUBLICATION_DATE", highlightValue, trust);
}
@Override
public void compileHighlight(final OpenAireEventPayload payload) {
payload.getHighlight().setPublicationdate(getHighlightValue());
}
@Override
public String getHighlightValueAsString() {
return getHighlightValue();
public UpdateInfo<String> generateUpdateInfo(final String highlightValue, final Result source,
final Result target) {
return new UpdateInfo<>(
Topic.ENRICH_MISSING_PUBLICATION_DATE,
highlightValue, source, target,
(p, date) -> p.setPublicationdate(date),
s -> s);
}
}

View File

@ -4,12 +4,19 @@ package eu.dnetlib.dhp.broker.oa.util;
import java.util.Arrays;
import java.util.List;
import eu.dnetlib.broker.objects.OpenAireEventPayload;
import org.apache.commons.lang3.tuple.Pair;
import eu.dnetlib.dhp.broker.model.Topic;
import eu.dnetlib.dhp.schema.oaf.Result;
public class EnrichMissingSubject extends UpdateInfo<String> {
public class EnrichMissingSubject extends UpdateMatcher<Pair<String, String>> {
public static List<EnrichMissingSubject> findUpdates(final Result source, final Result target) {
public EnrichMissingSubject() {
super(true);
}
@Override
protected List<UpdateInfo<Pair<String, String>>> findUpdates(final Result source, final Result target) {
// MESHEUROPMC
// ARXIV
// JEL
@ -19,18 +26,15 @@ public class EnrichMissingSubject extends UpdateInfo<String> {
return Arrays.asList();
}
private EnrichMissingSubject(final String subjectClassification, final String highlightValue, final float trust) {
super("ENRICH/MISSING/SUBJECT/" + subjectClassification, highlightValue, trust);
}
@Override
public void compileHighlight(final OpenAireEventPayload payload) {
payload.getHighlight().getSubjects().add(getHighlightValue());
}
public UpdateInfo<Pair<String, String>> generateUpdateInfo(final Pair<String, String> highlightValue,
final Result source, final Result target) {
@Override
public String getHighlightValueAsString() {
return getHighlightValue();
return new UpdateInfo<>(
Topic.fromPath("ENRICH/MISSING/SUBJECT/" + highlightValue.getLeft()),
highlightValue, source, target,
(p, pair) -> p.getSubjects().add(pair.getRight()),
pair -> pair.getLeft() + "::" + pair.getRight());
}
}

View File

@ -5,28 +5,29 @@ import java.util.Arrays;
import java.util.List;
import eu.dnetlib.broker.objects.Instance;
import eu.dnetlib.broker.objects.OpenAireEventPayload;
import eu.dnetlib.dhp.broker.model.Topic;
import eu.dnetlib.dhp.schema.oaf.Result;
public class EnrichMoreOpenAccess extends UpdateInfo<Instance> {
public class EnrichMoreOpenAccess extends UpdateMatcher<Instance> {
public static List<EnrichMoreOpenAccess> findUpdates(final Result source, final Result target) {
public EnrichMoreOpenAccess() {
super(true);
}
@Override
protected List<UpdateInfo<Instance>> findUpdates(final Result source, final Result target) {
// return Arrays.asList(new EnrichMissingAbstract("xxxxxxx", 0.9f));
return Arrays.asList();
}
private EnrichMoreOpenAccess(final Instance highlightValue, final float trust) {
super("ENRICH/MORE/OPENACCESS_VERSION", highlightValue, trust);
}
@Override
public void compileHighlight(final OpenAireEventPayload payload) {
payload.getHighlight().getInstances().add(getHighlightValue());
}
@Override
public String getHighlightValueAsString() {
return getHighlightValue().getUrl();
public UpdateInfo<Instance> generateUpdateInfo(final Instance highlightValue, final Result source,
final Result target) {
return new UpdateInfo<>(
Topic.ENRICH_MORE_OA_VERSION,
highlightValue, source, target,
(p, i) -> p.getInstances().add(i),
Instance::getUrl);
}
}

View File

@ -4,29 +4,29 @@ package eu.dnetlib.dhp.broker.oa.util;
import java.util.Arrays;
import java.util.List;
import eu.dnetlib.broker.objects.OpenAireEventPayload;
import eu.dnetlib.broker.objects.Pid;
import eu.dnetlib.dhp.broker.model.Topic;
import eu.dnetlib.dhp.schema.oaf.Result;
public class EnrichMorePid extends UpdateInfo<Pid> {
public class EnrichMorePid extends UpdateMatcher<Pid> {
public static List<EnrichMorePid> findUpdates(final Result source, final Result target) {
public EnrichMorePid() {
super(true);
}
@Override
protected List<UpdateInfo<Pid>> findUpdates(final Result source, final Result target) {
// return Arrays.asList(new EnrichMissingAbstract("xxxxxxx", 0.9f));
return Arrays.asList();
}
private EnrichMorePid(final Pid highlightValue, final float trust) {
super("ENRICH/MORE/PID", highlightValue, trust);
}
@Override
public void compileHighlight(final OpenAireEventPayload payload) {
payload.getHighlight().getPids().add(getHighlightValue());
}
@Override
public String getHighlightValueAsString() {
return getHighlightValue().getType() + "::" + getHighlightValue().getValue();
public UpdateInfo<Pid> generateUpdateInfo(final Pid highlightValue, final Result source, final Result target) {
return new UpdateInfo<>(
Topic.ENRICH_MORE_PID,
highlightValue, source, target,
(p, pid) -> p.getPids().add(pid),
pid -> pid.getType() + "::" + pid.getValue());
}
}

View File

@ -4,12 +4,19 @@ package eu.dnetlib.dhp.broker.oa.util;
import java.util.Arrays;
import java.util.List;
import eu.dnetlib.broker.objects.OpenAireEventPayload;
import org.apache.commons.lang3.tuple.Pair;
import eu.dnetlib.dhp.broker.model.Topic;
import eu.dnetlib.dhp.schema.oaf.Result;
public class EnrichMoreSubject extends UpdateInfo<String> {
public class EnrichMoreSubject extends UpdateMatcher<Pair<String, String>> {
public static List<EnrichMoreSubject> findUpdates(final Result source, final Result target) {
public EnrichMoreSubject() {
super(true);
}
@Override
protected List<UpdateInfo<Pair<String, String>>> findUpdates(final Result source, final Result target) {
// MESHEUROPMC
// ARXIV
// JEL
@ -19,18 +26,15 @@ public class EnrichMoreSubject extends UpdateInfo<String> {
return Arrays.asList();
}
private EnrichMoreSubject(final String subjectClassification, final String highlightValue, final float trust) {
super("ENRICH/MORE/SUBJECT/" + subjectClassification, highlightValue, trust);
}
@Override
public void compileHighlight(final OpenAireEventPayload payload) {
payload.getHighlight().getSubjects().add(getHighlightValue());
}
public UpdateInfo<Pair<String, String>> generateUpdateInfo(final Pair<String, String> highlightValue,
final Result source, final Result target) {
@Override
public String getHighlightValueAsString() {
return getHighlightValue();
return new UpdateInfo<>(
Topic.fromPath("ENRICH/MORE/SUBJECT/" + highlightValue.getLeft()),
highlightValue, source, target,
(p, pair) -> p.getSubjects().add(pair.getRight()),
pair -> pair.getLeft() + "::" + pair.getRight());
}
}

View File

@ -1,36 +1,77 @@
package eu.dnetlib.dhp.broker.oa.util;
import java.util.function.BiConsumer;
import java.util.function.Function;
import eu.dnetlib.broker.objects.OpenAireEventPayload;
import eu.dnetlib.broker.objects.Publication;
import eu.dnetlib.dhp.broker.model.Topic;
import eu.dnetlib.dhp.schema.oaf.Result;
public abstract class UpdateInfo<T> {
public final class UpdateInfo<T> {
private final String topic;
private final Topic topic;
private final T highlightValue;
private final Result source;
private final Result target;
private final BiConsumer<Publication, T> compileHighlight;
private final Function<T, String> highlightToString;
private final float trust;
protected UpdateInfo(final String topic, final T highlightValue, final float trust) {
protected UpdateInfo(final Topic topic, final T highlightValue, final Result source, final Result target,
final BiConsumer<Publication, T> compileHighlight,
final Function<T, String> highlightToString) {
this.topic = topic;
this.highlightValue = highlightValue;
this.trust = trust;
this.source = source;
this.target = target;
this.compileHighlight = compileHighlight;
this.highlightToString = highlightToString;
this.trust = calculateTrust(source, target);
}
public T getHighlightValue() {
return highlightValue;
}
public Result getSource() {
return source;
}
public Result getTarget() {
return target;
}
private float calculateTrust(final Result source, final Result target) {
// TODO
return 0.9f;
}
protected Topic getTopic() {
return topic;
}
public String getTopicPath() {
return topic.getPath();
}
public float getTrust() {
return trust;
}
public String getTopic() {
return topic;
public void compileHighlight(final OpenAireEventPayload payload) {
compileHighlight.accept(payload.getHighlight(), getHighlightValue());
}
abstract public void compileHighlight(OpenAireEventPayload payload);
abstract public String getHighlightValueAsString();
public String getHighlightValueAsString() {
return highlightToString.apply(getHighlightValue());
}
}

View File

@ -0,0 +1,63 @@
package eu.dnetlib.dhp.broker.oa.util;
import java.util.Arrays;
import java.util.Collection;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import org.apache.commons.codec.digest.DigestUtils;
import org.apache.commons.lang3.StringUtils;
import eu.dnetlib.dhp.schema.oaf.Field;
import eu.dnetlib.dhp.schema.oaf.Result;
public abstract class UpdateMatcher<T> {
private final boolean multipleUpdate;
public UpdateMatcher(final boolean multipleUpdate) {
this.multipleUpdate = multipleUpdate;
}
public Collection<UpdateInfo<T>> searchUpdatesForRecord(final Result res, final Result... others) {
final Map<String, UpdateInfo<T>> infoMap = new HashMap<>();
for (final Result source : others) {
if (source != res) {
for (final UpdateInfo<T> info : findUpdates(source, res)) {
final String s = DigestUtils.md5Hex(info.getHighlightValueAsString());
if (!infoMap.containsKey(s) || infoMap.get(s).getTrust() < info.getTrust()) {
} else {
infoMap.put(s, info);
}
}
}
}
final Collection<UpdateInfo<T>> values = infoMap.values();
if (values.isEmpty() || multipleUpdate) {
return values;
} else {
final UpdateInfo<T> v = values
.stream()
.sorted((o1, o2) -> Float.compare(o1.getTrust(), o2.getTrust()))
.findFirst()
.get();
return Arrays.asList(v);
}
}
protected abstract List<UpdateInfo<T>> findUpdates(Result source, Result target);
protected abstract UpdateInfo<T> generateUpdateInfo(final T highlightValue, final Result source,
final Result target);
protected static boolean isMissing(final List<Field<String>> list) {
return list == null || list.isEmpty() || StringUtils.isBlank(list.get(0).getValue());
}
}

View File

@ -1,6 +1,7 @@
package eu.dnetlib.dhp.bulktag;
import static eu.dnetlib.dhp.PropagationConstant.removeOutputDir;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import java.util.Optional;
@ -84,6 +85,7 @@ public class SparkBulkTagJob {
conf,
isSparkSessionManaged,
spark -> {
removeOutputDir(spark, outputPath);
execBulkTag(spark, inputPath, outputPath, protoMappingParams, resultClazz, cc);
});
}

View File

@ -69,13 +69,16 @@ public class SparkCountryPropagationJob {
runWithSparkSession(
conf,
isSparkSessionManaged,
spark -> execPropagation(
spark,
sourcePath,
preparedInfoPath,
outputPath,
resultClazz,
saveGraph));
spark -> {
removeOutputDir(spark, outputPath);
execPropagation(
spark,
sourcePath,
preparedInfoPath,
outputPath,
resultClazz,
saveGraph);
});
}
private static <R extends Result> void execPropagation(

View File

@ -74,9 +74,7 @@ public class PrepareResultOrcidAssociationStep1 {
conf,
isSparkSessionManaged,
spark -> {
if (isTest(parser)) {
removeOutputDir(spark, outputPath);
}
removeOutputDir(spark, outputPath);
prepareInfo(
spark, inputRelationPath, inputResultPath, outputResultPath, resultClazz, allowedsemrel);
});

View File

@ -50,9 +50,7 @@ public class PrepareResultOrcidAssociationStep2 {
conf,
isSparkSessionManaged,
spark -> {
if (isTest(parser)) {
removeOutputDir(spark, outputPath);
}
removeOutputDir(spark, outputPath);
mergeInfo(spark, inputPath, outputPath);
});
}

View File

@ -70,11 +70,10 @@ public class SparkOrcidToResultFromSemRelJob {
conf,
isSparkSessionManaged,
spark -> {
if (isTest(parser)) {
removeOutputDir(spark, outputPath);
}
if (saveGraph)
removeOutputDir(spark, outputPath);
if (saveGraph) {
execPropagation(spark, possibleUpdates, inputPath, outputPath, resultClazz);
}
});
}

View File

@ -60,6 +60,8 @@ public class PrepareProjectResultsAssociation {
conf,
isSparkSessionManaged,
spark -> {
removeOutputDir(spark, potentialUpdatePath);
removeOutputDir(spark, alreadyLinkedPath);
prepareResultProjProjectResults(
spark,
inputPath,

View File

@ -55,9 +55,7 @@ public class PrepareResultCommunitySet {
conf,
isSparkSessionManaged,
spark -> {
if (isTest(parser)) {
removeOutputDir(spark, outputPath);
}
removeOutputDir(spark, outputPath);
prepareInfo(spark, inputPath, outputPath, organizationMap);
});
}

View File

@ -68,11 +68,10 @@ public class SparkResultToCommunityFromOrganizationJob {
conf,
isSparkSessionManaged,
spark -> {
if (isTest(parser)) {
removeOutputDir(spark, outputPath);
}
if (saveGraph)
removeOutputDir(spark, outputPath);
if (saveGraph) {
execPropagation(spark, inputPath, outputPath, resultClazz, possibleupdatespath);
}
});
}

View File

@ -58,30 +58,15 @@ public class PrepareResultInstRepoAssociation {
isSparkSessionManaged,
spark -> {
readNeededResources(spark, inputPath);
removeOutputDir(spark, datasourceOrganizationPath);
prepareDatasourceOrganization(spark, datasourceOrganizationPath);
removeOutputDir(spark, alreadyLinkedPath);
prepareAlreadyLinkedAssociation(spark, alreadyLinkedPath);
});
}
private static void prepareAlreadyLinkedAssociation(
SparkSession spark, String alreadyLinkedPath) {
String query = "Select source resultId, collect_set(target) organizationSet "
+ "from relation "
+ "where datainfo.deletedbyinference = false "
+ "and relClass = '"
+ RELATION_RESULT_ORGANIZATION_REL_CLASS
+ "' "
+ "group by source";
spark
.sql(query)
.as(Encoders.bean(ResultOrganizationSet.class))
// TODO retry to stick with datasets
.toJavaRDD()
.map(r -> OBJECT_MAPPER.writeValueAsString(r))
.saveAsTextFile(alreadyLinkedPath, GzipCodec.class);
}
private static void readNeededResources(SparkSession spark, String inputPath) {
Dataset<Datasource> datasource = readPath(spark, inputPath + "/datasource", Datasource.class);
datasource.createOrReplaceTempView("datasource");
@ -119,4 +104,24 @@ public class PrepareResultInstRepoAssociation {
.option("compression", "gzip")
.json(datasourceOrganizationPath);
}
private static void prepareAlreadyLinkedAssociation(
SparkSession spark, String alreadyLinkedPath) {
String query = "Select source resultId, collect_set(target) organizationSet "
+ "from relation "
+ "where datainfo.deletedbyinference = false "
+ "and relClass = '"
+ RELATION_RESULT_ORGANIZATION_REL_CLASS
+ "' "
+ "group by source";
spark
.sql(query)
.as(Encoders.bean(ResultOrganizationSet.class))
// TODO retry to stick with datasets
.toJavaRDD()
.map(r -> OBJECT_MAPPER.writeValueAsString(r))
.saveAsTextFile(alreadyLinkedPath, GzipCodec.class);
}
}

View File

@ -83,10 +83,8 @@ public class SparkResultToOrganizationFromIstRepoJob {
conf,
isSparkSessionManaged,
spark -> {
if (isTest(parser)) {
removeOutputDir(spark, outputPath);
}
if (saveGraph)
removeOutputDir(spark, outputPath);
if (saveGraph) {
execPropagation(
spark,
datasourceorganization,
@ -94,6 +92,7 @@ public class SparkResultToOrganizationFromIstRepoJob {
inputPath,
outputPath,
resultClazz);
}
});
}

View File

@ -18,6 +18,17 @@
</property>
</parameters>
<global>
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>oozie.action.sharelib.for.spark</name>
<value>${oozieActionShareLibForSpark2}</value>
</property>
</configuration>
</global>
<start to="reset_outputpath"/>
<kill name="Kill">
@ -42,8 +53,6 @@
<action name="copy_relation">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/relation</arg>
<arg>${nameNode}/${outputPath}/relation</arg>
</distcp>
@ -53,8 +62,6 @@
<action name="copy_organization">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/organization</arg>
<arg>${nameNode}/${outputPath}/organization</arg>
</distcp>
@ -64,8 +71,6 @@
<action name="copy_projects">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/project</arg>
<arg>${nameNode}/${outputPath}/project</arg>
</distcp>
@ -75,8 +80,6 @@
<action name="copy_datasources">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/datasource</arg>
<arg>${nameNode}/${outputPath}/datasource</arg>
</distcp>
@ -95,8 +98,6 @@
<action name="join_bulktag_publication">
<spark xmlns="uri:oozie:spark-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>bulkTagging-publication</name>
@ -124,8 +125,6 @@
<action name="join_bulktag_dataset">
<spark xmlns="uri:oozie:spark-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>bulkTagging-dataset</name>
@ -153,8 +152,6 @@
<action name="join_bulktag_otherresearchproduct">
<spark xmlns="uri:oozie:spark-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>bulkTagging-orp</name>
@ -182,8 +179,6 @@
<action name="join_bulktag_software">
<spark xmlns="uri:oozie:spark-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>bulkTagging-software</name>

View File

@ -19,6 +19,17 @@
</parameters>
<global>
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>oozie.action.sharelib.for.spark</name>
<value>${oozieActionShareLibForSpark2}</value>
</property>
</configuration>
</global>
<start to="reset_outputpath"/>
<kill name="Kill">
@ -43,8 +54,6 @@
<action name="copy_relation">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/relation</arg>
<arg>${nameNode}/${outputPath}/relation</arg>
</distcp>
@ -54,18 +63,15 @@
<action name="copy_organization">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/organization</arg>
<arg>${nameNode}/${outputPath}/organization</arg>
</distcp>
<ok to="copy_wait"/>
<error to="Kill"/>
</action>
<action name="copy_projects">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/project</arg>
<arg>${nameNode}/${outputPath}/project</arg>
</distcp>
@ -75,8 +81,6 @@
<action name="copy_datasources">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/datasource</arg>
<arg>${nameNode}/${outputPath}/datasource</arg>
</distcp>

View File

@ -57,6 +57,7 @@
<ok to="copy_wait"/>
<error to="Kill"/>
</action>
<action name="copy_projects">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
@ -81,7 +82,6 @@
<join name="copy_wait" to="fork_prepare_assoc_step1"/>
<fork name="fork_prepare_assoc_step1">
<path start="join_prepare_publication"/>
<path start="join_prepare_dataset"/>
@ -230,8 +230,8 @@
</spark>
<ok to="fork-join-exec-propagation"/>
<error to="Kill"/>
</action>
<fork name="fork-join-exec-propagation">
<path start="join_propagate_publication"/>
<path start="join_propagate_dataset"/>
@ -271,6 +271,7 @@
<ok to="wait2"/>
<error to="Kill"/>
</action>
<action name="join_propagate_dataset">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
@ -302,6 +303,7 @@
<ok to="wait2"/>
<error to="Kill"/>
</action>
<action name="join_propagate_otherresearchproduct">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
@ -333,6 +335,7 @@
<ok to="wait2"/>
<error to="Kill"/>
</action>
<action name="join_propagate_software">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>

View File

@ -14,6 +14,17 @@
</property>
</parameters>
<global>
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>oozie.action.sharelib.for.spark</name>
<value>${oozieActionShareLibForSpark2}</value>
</property>
</configuration>
</global>
<start to="reset_outputpath"/>
<kill name="Kill">
@ -42,8 +53,6 @@
<action name="copy_relation">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/relation</arg>
<arg>${nameNode}/${outputPath}/relation</arg>
</distcp>
@ -53,8 +62,6 @@
<action name="copy_publication">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/publication</arg>
<arg>${nameNode}/${outputPath}/publication</arg>
</distcp>
@ -64,8 +71,6 @@
<action name="copy_dataset">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/dataset</arg>
<arg>${nameNode}/${outputPath}/dataset</arg>
</distcp>
@ -75,8 +80,6 @@
<action name="copy_orp">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/otherresearchproduct</arg>
<arg>${nameNode}/${outputPath}/otherresearchproduct</arg>
</distcp>
@ -86,28 +89,24 @@
<action name="copy_software">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/software</arg>
<arg>${nameNode}/${outputPath}/software</arg>
</distcp>
<ok to="wait"/>
<error to="Kill"/>
</action>
<action name="copy_organization">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/organization</arg>
<arg>${nameNode}/${outputPath}/organization</arg>
</distcp>
<ok to="wait"/>
<error to="Kill"/>
</action>
<action name="copy_projects">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/project</arg>
<arg>${nameNode}/${outputPath}/project</arg>
</distcp>
@ -117,8 +116,6 @@
<action name="copy_datasources">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/datasource</arg>
<arg>${nameNode}/${outputPath}/datasource</arg>
</distcp>

View File

@ -14,6 +14,17 @@
</property>
</parameters>
<global>
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>oozie.action.sharelib.for.spark</name>
<value>${oozieActionShareLibForSpark2}</value>
</property>
</configuration>
</global>
<start to="reset_outputpath"/>
<kill name="Kill">
@ -38,8 +49,6 @@
<action name="copy_relation">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/relation</arg>
<arg>${nameNode}/${outputPath}/relation</arg>
</distcp>
@ -49,8 +58,6 @@
<action name="copy_organization">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/organization</arg>
<arg>${nameNode}/${outputPath}/organization</arg>
</distcp>
@ -60,8 +67,6 @@
<action name="copy_projects">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/project</arg>
<arg>${nameNode}/${outputPath}/project</arg>
</distcp>
@ -71,8 +76,6 @@
<action name="copy_datasources">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/datasource</arg>
<arg>${nameNode}/${outputPath}/datasource</arg>
</distcp>
@ -101,8 +104,8 @@
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/relation</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--outputPath</arg><arg>${workingDir}/preparedInfo/resultCommunityList</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--organizationtoresultcommunitymap</arg><arg>${organizationtoresultcommunitymap}</arg>
</spark>
<ok to="fork-join-exec-propagation"/>
@ -136,9 +139,9 @@
</spark-opts>
<arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo/resultCommunityList</arg>
<arg>--sourcePath</arg><arg>${sourcePath}/publication</arg>
<arg>--outputPath</arg><arg>${outputPath}/publication</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
<arg>--outputPath</arg><arg>${outputPath}/publication</arg>
<arg>--saveGraph</arg><arg>${saveGraph}</arg>
</spark>
<ok to="wait2"/>
@ -165,9 +168,9 @@
</spark-opts>
<arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo/resultCommunityList</arg>
<arg>--sourcePath</arg><arg>${sourcePath}/dataset</arg>
<arg>--outputPath</arg><arg>${outputPath}/dataset</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
<arg>--outputPath</arg><arg>${outputPath}/dataset</arg>
<arg>--saveGraph</arg><arg>${saveGraph}</arg>
</spark>
<ok to="wait2"/>
@ -194,9 +197,9 @@
</spark-opts>
<arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo/resultCommunityList</arg>
<arg>--sourcePath</arg><arg>${sourcePath}/otherresearchproduct</arg>
<arg>--outputPath</arg><arg>${outputPath}/otherresearchproduct</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
<arg>--outputPath</arg><arg>${outputPath}/otherresearchproduct</arg>
<arg>--saveGraph</arg><arg>${saveGraph}</arg>
</spark>
<ok to="wait2"/>
@ -223,9 +226,9 @@
</spark-opts>
<arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo/resultCommunityList</arg>
<arg>--sourcePath</arg><arg>${sourcePath}/software</arg>
<arg>--outputPath</arg><arg>${outputPath}/software</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
<arg>--outputPath</arg><arg>${outputPath}/software</arg>
<arg>--saveGraph</arg><arg>${saveGraph}</arg>
</spark>
<ok to="wait2"/>

View File

@ -10,6 +10,17 @@
</property>
</parameters>
<global>
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>oozie.action.sharelib.for.spark</name>
<value>${oozieActionShareLibForSpark2}</value>
</property>
</configuration>
</global>
<start to="reset_outputpath"/>
<kill name="Kill">
@ -38,8 +49,6 @@
<action name="copy_relation">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/relation</arg>
<arg>${nameNode}/${outputPath}/relation</arg>
</distcp>
@ -49,8 +58,6 @@
<action name="copy_publication">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/publication</arg>
<arg>${nameNode}/${outputPath}/publication</arg>
</distcp>
@ -60,8 +67,6 @@
<action name="copy_dataset">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/dataset</arg>
<arg>${nameNode}/${outputPath}/dataset</arg>
</distcp>
@ -71,8 +76,6 @@
<action name="copy_orp">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/otherresearchproduct</arg>
<arg>${nameNode}/${outputPath}/otherresearchproduct</arg>
</distcp>
@ -82,8 +85,6 @@
<action name="copy_software">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/software</arg>
<arg>${nameNode}/${outputPath}/software</arg>
</distcp>
@ -93,8 +94,6 @@
<action name="copy_organization">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/organization</arg>
<arg>${nameNode}/${outputPath}/organization</arg>
</distcp>
@ -104,8 +103,6 @@
<action name="copy_projects">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/project</arg>
<arg>${nameNode}/${outputPath}/project</arg>
</distcp>
@ -115,8 +112,6 @@
<action name="copy_datasources">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/datasource</arg>
<arg>${nameNode}/${outputPath}/datasource</arg>
</distcp>
@ -125,6 +120,7 @@
</action>
<join name="wait" to="prepare_result_organization_association"/>
<action name="prepare_result_organization_association">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
@ -176,12 +172,12 @@
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/publication</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--saveGraph</arg><arg>${saveGraph}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
<arg>--outputPath</arg><arg>${outputPath}/relation</arg>
<arg>--datasourceOrganizationPath</arg><arg>${workingDir}/preparedInfo/datasourceOrganization</arg>
<arg>--alreadyLinkedPath</arg><arg>${workingDir}/preparedInfo/alreadyLinked</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--saveGraph</arg><arg>${saveGraph}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
</spark>
<ok to="wait2"/>
<error to="Kill"/>
@ -206,12 +202,12 @@
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/dataset</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--saveGraph</arg><arg>${saveGraph}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
<arg>--outputPath</arg><arg>${outputPath}/relation</arg>
<arg>--datasourceOrganizationPath</arg><arg>${workingDir}/preparedInfo/datasourceOrganization</arg>
<arg>--alreadyLinkedPath</arg><arg>${workingDir}/preparedInfo/alreadyLinked</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--saveGraph</arg><arg>${saveGraph}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
</spark>
<ok to="wait2"/>
<error to="Kill"/>
@ -236,12 +232,12 @@
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/otherresearchproduct</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--saveGraph</arg><arg>${saveGraph}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
<arg>--outputPath</arg><arg>${outputPath}/relation</arg>
<arg>--datasourceOrganizationPath</arg><arg>${workingDir}/preparedInfo/datasourceOrganization</arg>
<arg>--alreadyLinkedPath</arg><arg>${workingDir}/preparedInfo/alreadyLinked</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--saveGraph</arg><arg>${saveGraph}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
</spark>
<ok to="wait2"/>
<error to="Kill"/>
@ -266,12 +262,12 @@
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/software</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--saveGraph</arg><arg>${saveGraph}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
<arg>--outputPath</arg><arg>${outputPath}/relation</arg>
<arg>--datasourceOrganizationPath</arg><arg>${workingDir}/preparedInfo/datasourceOrganization</arg>
<arg>--alreadyLinkedPath</arg><arg>${workingDir}/preparedInfo/alreadyLinked</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--saveGraph</arg><arg>${saveGraph}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
</spark>
<ok to="wait2"/>
<error to="Kill"/>

View File

@ -127,7 +127,6 @@ public abstract class AbstractMdRecordToOafMapper {
final List<Oaf> oafs = new ArrayList<>();
switch (type.toLowerCase()) {
case "":
case "publication":
final Publication p = new Publication();
populateResultFields(p, doc, collectedFrom, hostedBy, info, lastUpdateTimestamp);
@ -138,7 +137,7 @@ public abstract class AbstractMdRecordToOafMapper {
case "dataset":
final Dataset d = new Dataset();
populateResultFields(d, doc, collectedFrom, hostedBy, info, lastUpdateTimestamp);
d.setResulttype(PUBLICATION_DEFAULT_RESULTTYPE);
d.setResulttype(DATASET_DEFAULT_RESULTTYPE);
d.setStoragedate(prepareDatasetStorageDate(doc, info));
d.setDevice(prepareDatasetDevice(doc, info));
d.setSize(prepareDatasetSize(doc, info));
@ -158,6 +157,7 @@ public abstract class AbstractMdRecordToOafMapper {
s.setProgrammingLanguage(prepareSoftwareProgrammingLanguage(doc, info));
oafs.add(s);
break;
case "":
case "otherresearchproducts":
default:
final OtherResearchProduct o = new OtherResearchProduct();