This commit is contained in:
Enrico Ottonello 2020-05-19 09:43:12 +02:00
commit ca722d4d18
77 changed files with 1880 additions and 803 deletions

View File

@ -13,6 +13,7 @@ public class ModelConstants {
public static final String DNET_DATA_CITE_DATE = "dnet:dataCite_date"; public static final String DNET_DATA_CITE_DATE = "dnet:dataCite_date";
public static final String DNET_DATA_CITE_RESOURCE = "dnet:dataCite_resource"; public static final String DNET_DATA_CITE_RESOURCE = "dnet:dataCite_resource";
public static final String DNET_PROVENANCE_ACTIONS = "dnet:provenanceActions"; public static final String DNET_PROVENANCE_ACTIONS = "dnet:provenanceActions";
public static final String DNET_COUNTRY_TYPE = "dnet:countries";
public static final String SYSIMPORT_CROSSWALK_REPOSITORY = "sysimport:crosswalk:repository"; public static final String SYSIMPORT_CROSSWALK_REPOSITORY = "sysimport:crosswalk:repository";
public static final String SYSIMPORT_CROSSWALK_ENTITYREGISTRY = "sysimport:crosswalk:entityregistry"; public static final String SYSIMPORT_CROSSWALK_ENTITYREGISTRY = "sysimport:crosswalk:entityregistry";
@ -49,6 +50,13 @@ public class ModelConstants {
public static final String HAS_PARTICIPANT = "hasParticipant"; public static final String HAS_PARTICIPANT = "hasParticipant";
public static final String IS_PARTICIPANT = "isParticipant"; public static final String IS_PARTICIPANT = "isParticipant";
public static final String RESULT_ORGANIZATION = "resultOrganization";
public static final String AFFILIATION = "affiliation";
public static final String IS_AUTHOR_INSTITUTION_OF = "isAuthorInstitutionOf";
public static final String HAS_AUTHOR_INSTITUTION = "hasAuthorInstitution";
public static final String MERGES = "merges";
public static final String UNKNOWN = "UNKNOWN"; public static final String UNKNOWN = "UNKNOWN";
public static final String NOT_AVAILABLE = "not available"; public static final String NOT_AVAILABLE = "not available";

View File

@ -1,10 +1,15 @@
package eu.dnetlib.dhp.schema.common; package eu.dnetlib.dhp.schema.common;
import static com.google.common.base.Preconditions.checkArgument;
import java.util.Map; import java.util.Map;
import java.util.Objects;
import java.util.Optional; import java.util.Optional;
import java.util.function.Function; import java.util.function.Function;
import org.apache.commons.lang3.StringUtils;
import com.google.common.collect.Maps; import com.google.common.collect.Maps;
import eu.dnetlib.dhp.schema.oaf.*; import eu.dnetlib.dhp.schema.oaf.*;
@ -379,6 +384,21 @@ public class ModelSupport {
entityMapping.get(EntityType.valueOf(targetType)).name()); entityMapping.get(EntityType.valueOf(targetType)).name());
} }
public static <T extends Oaf> String tableIdentifier(String dbName, String tableName) {
checkArgument(StringUtils.isNotBlank(dbName), "DB name cannot be empty");
checkArgument(StringUtils.isNotBlank(tableName), "table name cannot be empty");
return String.format("%s.%s", dbName, tableName);
}
public static <T extends Oaf> String tableIdentifier(String dbName, Class<T> clazz) {
checkArgument(Objects.nonNull(clazz), "clazz is needed to derive the table name, thus cannot be null");
return tableIdentifier(dbName, clazz.getSimpleName().toLowerCase());
}
public static <T extends Oaf> Function<T, String> idFn() { public static <T extends Oaf> Function<T, String> idFn() {
return x -> { return x -> {
if (isSubClass(x, Relation.class)) { if (isSubClass(x, Relation.class)) {

View File

@ -523,7 +523,9 @@ public class ProtoConverter implements Serializable {
} }
private static Context mapContext(ResultProtos.Result.Context context) { private static Context mapContext(ResultProtos.Result.Context context) {
if (context == null || StringUtils.isBlank(context.getId())) {
return null;
}
final Context entity = new Context(); final Context entity = new Context();
entity.setId(context.getId()); entity.setId(context.getId());
entity entity
@ -537,6 +539,10 @@ public class ProtoConverter implements Serializable {
} }
public static KeyValue mapKV(FieldTypeProtos.KeyValue kv) { public static KeyValue mapKV(FieldTypeProtos.KeyValue kv) {
if (kv == null || StringUtils.isBlank(kv.getKey()) & StringUtils.isBlank(kv.getValue())) {
return null;
}
final KeyValue keyValue = new KeyValue(); final KeyValue keyValue = new KeyValue();
keyValue.setKey(kv.getKey()); keyValue.setKey(kv.getKey());
keyValue.setValue(kv.getValue()); keyValue.setValue(kv.getValue());
@ -575,6 +581,10 @@ public class ProtoConverter implements Serializable {
} }
public static StructuredProperty mapStructuredProperty(FieldTypeProtos.StructuredProperty sp) { public static StructuredProperty mapStructuredProperty(FieldTypeProtos.StructuredProperty sp) {
if (sp == null | StringUtils.isBlank(sp.getValue())) {
return null;
}
final StructuredProperty structuredProperty = new StructuredProperty(); final StructuredProperty structuredProperty = new StructuredProperty();
structuredProperty.setValue(sp.getValue()); structuredProperty.setValue(sp.getValue());
structuredProperty.setQualifier(mapQualifier(sp.getQualifier())); structuredProperty.setQualifier(mapQualifier(sp.getQualifier()));
@ -611,6 +621,10 @@ public class ProtoConverter implements Serializable {
} }
public static Field<String> mapStringField(FieldTypeProtos.StringField s) { public static Field<String> mapStringField(FieldTypeProtos.StringField s) {
if (s == null || StringUtils.isBlank(s.getValue())) {
return null;
}
final Field<String> stringField = new Field<>(); final Field<String> stringField = new Field<>();
stringField.setValue(s.getValue()); stringField.setValue(s.getValue());
stringField.setDataInfo(mapDataInfo(s.getDataInfo())); stringField.setDataInfo(mapDataInfo(s.getDataInfo()));
@ -618,19 +632,16 @@ public class ProtoConverter implements Serializable {
} }
public static Field<Boolean> mapBoolField(FieldTypeProtos.BoolField b) { public static Field<Boolean> mapBoolField(FieldTypeProtos.BoolField b) {
if (b == null) {
return null;
}
final Field<Boolean> booleanField = new Field<>(); final Field<Boolean> booleanField = new Field<>();
booleanField.setValue(b.getValue()); booleanField.setValue(b.getValue());
booleanField.setDataInfo(mapDataInfo(b.getDataInfo())); booleanField.setDataInfo(mapDataInfo(b.getDataInfo()));
return booleanField; return booleanField;
} }
public static Field<Integer> mapIntField(FieldTypeProtos.IntField b) {
final Field<Integer> entity = new Field<>();
entity.setValue(b.getValue());
entity.setDataInfo(mapDataInfo(b.getDataInfo()));
return entity;
}
public static Journal mapJournal(FieldTypeProtos.Journal j) { public static Journal mapJournal(FieldTypeProtos.Journal j) {
final Journal journal = new Journal(); final Journal journal = new Journal();
journal.setConferencedate(j.getConferencedate()); journal.setConferencedate(j.getConferencedate());

View File

@ -18,6 +18,7 @@ import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.ObjectMapper; import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.application.ArgumentApplicationParser; import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.schema.oaf.Relation; import eu.dnetlib.dhp.schema.oaf.Relation;
public class PrepareMergedRelationJob { public class PrepareMergedRelationJob {
@ -56,6 +57,7 @@ public class PrepareMergedRelationJob {
conf, conf,
isSparkSessionManaged, isSparkSessionManaged,
spark -> { spark -> {
removeOutputDir(spark, outputPath);
selectMergesRelations( selectMergesRelations(
spark, spark,
inputPath, inputPath,
@ -84,4 +86,9 @@ public class PrepareMergedRelationJob {
(MapFunction<String, Relation>) value -> OBJECT_MAPPER.readValue(value, Relation.class), (MapFunction<String, Relation>) value -> OBJECT_MAPPER.readValue(value, Relation.class),
Encoders.bean(Relation.class)); Encoders.bean(Relation.class));
} }
private static void removeOutputDir(SparkSession spark, String path) {
HdfsSupport.remove(path, spark.sparkContext().hadoopConfiguration());
}
} }

View File

@ -18,6 +18,7 @@ import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.ObjectMapper; import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.application.ArgumentApplicationParser; import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.schema.oaf.Relation; import eu.dnetlib.dhp.schema.oaf.Relation;
import scala.Tuple2; import scala.Tuple2;
@ -62,6 +63,7 @@ public class SparkRemoveBlacklistedRelationJob {
conf, conf,
isSparkSessionManaged, isSparkSessionManaged,
spark -> { spark -> {
removeOutputDir(spark, outputPath);
removeBlacklistedRelations( removeBlacklistedRelations(
spark, spark,
blacklistPath, blacklistPath,
@ -69,7 +71,6 @@ public class SparkRemoveBlacklistedRelationJob {
outputPath, outputPath,
mergesPath); mergesPath);
}); });
} }
private static void removeBlacklistedRelations(SparkSession spark, String blacklistPath, String inputPath, private static void removeBlacklistedRelations(SparkSession spark, String blacklistPath, String inputPath,
@ -78,8 +79,6 @@ public class SparkRemoveBlacklistedRelationJob {
Dataset<Relation> inputRelation = readRelations(spark, inputPath); Dataset<Relation> inputRelation = readRelations(spark, inputPath);
Dataset<Relation> mergesRelation = readRelations(spark, mergesPath); Dataset<Relation> mergesRelation = readRelations(spark, mergesPath);
log.info("InputRelationCount: {}", inputRelation.count());
Dataset<Relation> dedupSource = blackListed Dataset<Relation> dedupSource = blackListed
.joinWith( .joinWith(
mergesRelation, blackListed.col("source").equalTo(mergesRelation.col("target")), mergesRelation, blackListed.col("source").equalTo(mergesRelation.col("target")),
@ -102,11 +101,6 @@ public class SparkRemoveBlacklistedRelationJob {
return c._1(); return c._1();
}, Encoders.bean(Relation.class)); }, Encoders.bean(Relation.class));
dedupBL
.write()
.mode(SaveMode.Overwrite)
.json(blacklistPath + "/deduped");
inputRelation inputRelation
.joinWith( .joinWith(
dedupBL, (inputRelation dedupBL, (inputRelation
@ -144,4 +138,8 @@ public class SparkRemoveBlacklistedRelationJob {
Encoders.bean(Relation.class)); Encoders.bean(Relation.class));
} }
private static void removeOutputDir(SparkSession spark, String path) {
HdfsSupport.remove(path, spark.sparkContext().hadoopConfiguration());
}
} }

View File

@ -22,6 +22,25 @@
</property> </property>
</parameters> </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>${oozieActionShareLibForSpark2}</value>
</property>
</configuration>
</global>
<start to="reset_outputpath"/> <start to="reset_outputpath"/>
<kill name="Kill"> <kill name="Kill">
@ -49,8 +68,6 @@
<action name="copy_publication"> <action name="copy_publication">
<distcp xmlns="uri:oozie:distcp-action:0.2"> <distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/publication</arg> <arg>${nameNode}/${sourcePath}/publication</arg>
<arg>${nameNode}/${outputPath}/publication</arg> <arg>${nameNode}/${outputPath}/publication</arg>
</distcp> </distcp>
@ -60,8 +77,6 @@
<action name="copy_dataset"> <action name="copy_dataset">
<distcp xmlns="uri:oozie:distcp-action:0.2"> <distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/dataset</arg> <arg>${nameNode}/${sourcePath}/dataset</arg>
<arg>${nameNode}/${outputPath}/dataset</arg> <arg>${nameNode}/${outputPath}/dataset</arg>
</distcp> </distcp>
@ -71,8 +86,6 @@
<action name="copy_orp"> <action name="copy_orp">
<distcp xmlns="uri:oozie:distcp-action:0.2"> <distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/otherresearchproduct</arg> <arg>${nameNode}/${sourcePath}/otherresearchproduct</arg>
<arg>${nameNode}/${outputPath}/otherresearchproduct</arg> <arg>${nameNode}/${outputPath}/otherresearchproduct</arg>
</distcp> </distcp>
@ -82,8 +95,6 @@
<action name="copy_software"> <action name="copy_software">
<distcp xmlns="uri:oozie:distcp-action:0.2"> <distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/software</arg> <arg>${nameNode}/${sourcePath}/software</arg>
<arg>${nameNode}/${outputPath}/software</arg> <arg>${nameNode}/${outputPath}/software</arg>
</distcp> </distcp>
@ -93,8 +104,6 @@
<action name="copy_organization"> <action name="copy_organization">
<distcp xmlns="uri:oozie:distcp-action:0.2"> <distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/organization</arg> <arg>${nameNode}/${sourcePath}/organization</arg>
<arg>${nameNode}/${outputPath}/organization</arg> <arg>${nameNode}/${outputPath}/organization</arg>
</distcp> </distcp>
@ -104,8 +113,6 @@
<action name="copy_project"> <action name="copy_project">
<distcp xmlns="uri:oozie:distcp-action:0.2"> <distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/project</arg> <arg>${nameNode}/${sourcePath}/project</arg>
<arg>${nameNode}/${outputPath}/project</arg> <arg>${nameNode}/${outputPath}/project</arg>
</distcp> </distcp>
@ -115,8 +122,6 @@
<action name="copy_datasource"> <action name="copy_datasource">
<distcp xmlns="uri:oozie:distcp-action:0.2"> <distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/datasource</arg> <arg>${nameNode}/${sourcePath}/datasource</arg>
<arg>${nameNode}/${outputPath}/datasource</arg> <arg>${nameNode}/${outputPath}/datasource</arg>
</distcp> </distcp>
@ -128,8 +133,6 @@
<action name="read_blacklist"> <action name="read_blacklist">
<java> <java>
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<main-class>eu.dnetlib.dhp.blacklist.ReadBlacklistFromDB</main-class> <main-class>eu.dnetlib.dhp.blacklist.ReadBlacklistFromDB</main-class>
<arg>--hdfsPath</arg><arg>${workingDir}/blacklist</arg> <arg>--hdfsPath</arg><arg>${workingDir}/blacklist</arg>
<arg>--hdfsNameNode</arg><arg>${nameNode}</arg> <arg>--hdfsNameNode</arg><arg>${nameNode}</arg>
@ -156,6 +159,7 @@
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=3840
</spark-opts> </spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/relation</arg> <arg>--sourcePath</arg><arg>${sourcePath}/relation</arg>
<arg>--outputPath</arg><arg>${workingDir}/mergesRelation</arg> <arg>--outputPath</arg><arg>${workingDir}/mergesRelation</arg>
@ -180,6 +184,7 @@
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=3840
</spark-opts> </spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/relation</arg> <arg>--sourcePath</arg><arg>${sourcePath}/relation</arg>
<arg>--outputPath</arg><arg>${outputPath}/relation</arg> <arg>--outputPath</arg><arg>${outputPath}/relation</arg>

View File

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

@ -14,21 +14,20 @@ import org.apache.spark.sql.SparkSession;
import org.slf4j.Logger; import org.slf4j.Logger;
import org.slf4j.LoggerFactory; import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.application.ArgumentApplicationParser; import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.broker.model.Event; import eu.dnetlib.dhp.broker.model.Event;
import eu.dnetlib.dhp.broker.model.EventFactory; import eu.dnetlib.dhp.broker.model.EventFactory;
import eu.dnetlib.dhp.broker.oa.util.EnrichMissingAbstract; import eu.dnetlib.dhp.broker.oa.matchers.EnrichMissingAbstract;
import eu.dnetlib.dhp.broker.oa.util.EnrichMissingAuthorOrcid; import eu.dnetlib.dhp.broker.oa.matchers.EnrichMissingAuthorOrcid;
import eu.dnetlib.dhp.broker.oa.util.EnrichMissingOpenAccess; import eu.dnetlib.dhp.broker.oa.matchers.EnrichMissingOpenAccess;
import eu.dnetlib.dhp.broker.oa.util.EnrichMissingPid; import eu.dnetlib.dhp.broker.oa.matchers.EnrichMissingPid;
import eu.dnetlib.dhp.broker.oa.util.EnrichMissingProject; import eu.dnetlib.dhp.broker.oa.matchers.EnrichMissingProject;
import eu.dnetlib.dhp.broker.oa.util.EnrichMissingPublicationDate; import eu.dnetlib.dhp.broker.oa.matchers.EnrichMissingPublicationDate;
import eu.dnetlib.dhp.broker.oa.util.EnrichMissingSubject; import eu.dnetlib.dhp.broker.oa.matchers.EnrichMissingSubject;
import eu.dnetlib.dhp.broker.oa.util.EnrichMoreOpenAccess; import eu.dnetlib.dhp.broker.oa.matchers.EnrichMoreOpenAccess;
import eu.dnetlib.dhp.broker.oa.util.EnrichMorePid; import eu.dnetlib.dhp.broker.oa.matchers.EnrichMorePid;
import eu.dnetlib.dhp.broker.oa.util.EnrichMoreSubject; import eu.dnetlib.dhp.broker.oa.matchers.EnrichMoreSubject;
import eu.dnetlib.dhp.broker.oa.matchers.UpdateMatcher;
import eu.dnetlib.dhp.broker.oa.util.UpdateInfo; import eu.dnetlib.dhp.broker.oa.util.UpdateInfo;
import eu.dnetlib.dhp.common.HdfsSupport; import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.schema.oaf.Result; 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 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 { public static void main(final String[] args) throws Exception {
final ArgumentApplicationParser parser = new ArgumentApplicationParser( final ArgumentApplicationParser parser = new ArgumentApplicationParser(
@ -76,37 +84,22 @@ public class GenerateEventsApplication {
} }
private List<Event> generateEvents(final Result... children) { 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) {
for (final Result target : children) { list.addAll(enrichMissingAbstract.searchUpdatesForRecord(target, children));
if (source != target) { list.addAll(enrichMissingAuthorOrcid.searchUpdatesForRecord(target, children));
list list.addAll(enrichMissingOpenAccess.searchUpdatesForRecord(target, children));
.addAll( list.addAll(enrichMissingPid.searchUpdatesForRecord(target, children));
findUpdates(source, target) list.addAll(enrichMissingProject.searchUpdatesForRecord(target, children));
.stream() list.addAll(enrichMissingPublicationDate.searchUpdatesForRecord(target, children));
.map(info -> EventFactory.newBrokerEvent(source, target, info)) list.addAll(enrichMissingSubject.searchUpdatesForRecord(target, children));
.collect(Collectors.toList())); list.addAll(enrichMoreOpenAccess.searchUpdatesForRecord(target, children));
} list.addAll(enrichMorePid.searchUpdatesForRecord(target, children));
} list.addAll(enrichMoreSubject.searchUpdatesForRecord(target, children));
} }
return list; return list.stream().map(EventFactory::newBrokerEvent).collect(Collectors.toList());
}
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;
} }
} }

View File

@ -0,0 +1,36 @@
package eu.dnetlib.dhp.broker.oa.matchers;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
import eu.dnetlib.dhp.broker.model.Topic;
import eu.dnetlib.dhp.broker.oa.util.UpdateInfo;
import eu.dnetlib.dhp.schema.oaf.Result;
public class EnrichMissingAbstract extends UpdateMatcher<String> {
public EnrichMissingAbstract() {
super(false);
}
@Override
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 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

@ -0,0 +1,34 @@
package eu.dnetlib.dhp.broker.oa.matchers;
import java.util.Arrays;
import java.util.List;
import org.apache.commons.lang3.tuple.Pair;
import eu.dnetlib.dhp.broker.model.Topic;
import eu.dnetlib.dhp.broker.oa.util.UpdateInfo;
import eu.dnetlib.dhp.schema.oaf.Result;
public class EnrichMissingAuthorOrcid extends UpdateMatcher<Pair<String, String>> {
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();
}
@Override
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());
}
}

View File

@ -0,0 +1,55 @@
package eu.dnetlib.dhp.broker.oa.matchers;
import java.util.Arrays;
import java.util.List;
import java.util.stream.Collectors;
import eu.dnetlib.broker.objects.Instance;
import eu.dnetlib.dhp.broker.model.Topic;
import eu.dnetlib.dhp.broker.oa.util.BrokerConstants;
import eu.dnetlib.dhp.broker.oa.util.ConversionUtils;
import eu.dnetlib.dhp.broker.oa.util.UpdateInfo;
import eu.dnetlib.dhp.schema.oaf.Result;
public class EnrichMissingOpenAccess extends UpdateMatcher<Instance> {
public EnrichMissingOpenAccess() {
super(true);
}
@Override
protected List<UpdateInfo<Instance>> findUpdates(final Result source, final Result target) {
final long count = target
.getInstance()
.stream()
.map(i -> i.getAccessright().getClassid())
.filter(right -> right.equals(BrokerConstants.OPEN_ACCESS))
.count();
if (count > 0) {
return Arrays.asList();
}
return source
.getInstance()
.stream()
.filter(i -> i.getAccessright().getClassid().equals(BrokerConstants.OPEN_ACCESS))
.map(ConversionUtils::oafInstanceToBrokerInstances)
.flatMap(s -> s)
.map(i -> generateUpdateInfo(i, source, target))
.collect(Collectors.toList());
}
@Override
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

@ -0,0 +1,45 @@
package eu.dnetlib.dhp.broker.oa.matchers;
import java.util.Arrays;
import java.util.List;
import java.util.stream.Collectors;
import eu.dnetlib.broker.objects.Pid;
import eu.dnetlib.dhp.broker.model.Topic;
import eu.dnetlib.dhp.broker.oa.util.ConversionUtils;
import eu.dnetlib.dhp.broker.oa.util.UpdateInfo;
import eu.dnetlib.dhp.schema.oaf.Result;
public class EnrichMissingPid extends UpdateMatcher<Pid> {
public EnrichMissingPid() {
super(true);
}
@Override
protected List<UpdateInfo<Pid>> findUpdates(final Result source, final Result target) {
final long count = target.getPid().size();
if (count > 0) {
return Arrays.asList();
}
return source
.getPid()
.stream()
.map(ConversionUtils::oafPidToBrokerPid)
.map(i -> generateUpdateInfo(i, source, target))
.collect(Collectors.toList());
}
@Override
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

@ -0,0 +1,35 @@
package eu.dnetlib.dhp.broker.oa.matchers;
import java.util.Arrays;
import java.util.List;
import eu.dnetlib.broker.objects.Project;
import eu.dnetlib.dhp.broker.model.Topic;
import eu.dnetlib.dhp.broker.oa.util.UpdateInfo;
import eu.dnetlib.dhp.schema.oaf.Result;
public class EnrichMissingProject extends UpdateMatcher<Project> {
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();
}
@Override
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

@ -0,0 +1,33 @@
package eu.dnetlib.dhp.broker.oa.matchers;
import java.util.Arrays;
import java.util.List;
import eu.dnetlib.dhp.broker.model.Topic;
import eu.dnetlib.dhp.broker.oa.util.UpdateInfo;
import eu.dnetlib.dhp.schema.oaf.Result;
public class EnrichMissingPublicationDate extends UpdateMatcher<String> {
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();
}
@Override
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

@ -0,0 +1,53 @@
package eu.dnetlib.dhp.broker.oa.matchers;
import java.util.List;
import java.util.Set;
import java.util.stream.Collectors;
import org.apache.commons.lang3.tuple.Pair;
import eu.dnetlib.dhp.broker.model.Topic;
import eu.dnetlib.dhp.broker.oa.util.ConversionUtils;
import eu.dnetlib.dhp.broker.oa.util.UpdateInfo;
import eu.dnetlib.dhp.schema.oaf.Qualifier;
import eu.dnetlib.dhp.schema.oaf.Result;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
public class EnrichMissingSubject extends UpdateMatcher<Pair<String, String>> {
public EnrichMissingSubject() {
super(true);
}
@Override
protected List<UpdateInfo<Pair<String, String>>> findUpdates(final Result source, final Result target) {
final Set<String> existingTypes = target
.getSubject()
.stream()
.map(StructuredProperty::getQualifier)
.map(Qualifier::getClassid)
.collect(Collectors.toSet());
return source
.getPid()
.stream()
.filter(pid -> !existingTypes.contains(pid.getQualifier().getClassid()))
.map(ConversionUtils::oafSubjectToPair)
.map(i -> generateUpdateInfo(i, source, target))
.collect(Collectors.toList());
}
@Override
public UpdateInfo<Pair<String, String>> generateUpdateInfo(final Pair<String, String> highlightValue,
final Result source,
final Result target) {
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

@ -0,0 +1,53 @@
package eu.dnetlib.dhp.broker.oa.matchers;
import java.util.List;
import java.util.Set;
import java.util.stream.Collectors;
import eu.dnetlib.broker.objects.Instance;
import eu.dnetlib.dhp.broker.model.Topic;
import eu.dnetlib.dhp.broker.oa.util.BrokerConstants;
import eu.dnetlib.dhp.broker.oa.util.ConversionUtils;
import eu.dnetlib.dhp.broker.oa.util.UpdateInfo;
import eu.dnetlib.dhp.schema.oaf.Result;
public class EnrichMoreOpenAccess extends UpdateMatcher<Instance> {
public EnrichMoreOpenAccess() {
super(true);
}
@Override
protected List<UpdateInfo<Instance>> findUpdates(final Result source, final Result target) {
final Set<String> urls = target
.getInstance()
.stream()
.filter(i -> i.getAccessright().getClassid().equals(BrokerConstants.OPEN_ACCESS))
.map(i -> i.getUrl())
.flatMap(List::stream)
.collect(Collectors.toSet());
return source
.getInstance()
.stream()
.filter(i -> i.getAccessright().getClassid().equals(BrokerConstants.OPEN_ACCESS))
.map(ConversionUtils::oafInstanceToBrokerInstances)
.flatMap(s -> s)
.filter(i -> !urls.contains(i.getUrl()))
.map(i -> generateUpdateInfo(i, source, target))
.collect(Collectors.toList());
}
@Override
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

@ -0,0 +1,46 @@
package eu.dnetlib.dhp.broker.oa.matchers;
import java.util.List;
import java.util.Set;
import java.util.stream.Collectors;
import eu.dnetlib.broker.objects.Pid;
import eu.dnetlib.dhp.broker.model.Topic;
import eu.dnetlib.dhp.broker.oa.util.ConversionUtils;
import eu.dnetlib.dhp.broker.oa.util.UpdateInfo;
import eu.dnetlib.dhp.schema.oaf.Result;
public class EnrichMorePid extends UpdateMatcher<Pid> {
public EnrichMorePid() {
super(true);
}
@Override
protected List<UpdateInfo<Pid>> findUpdates(final Result source, final Result target) {
final Set<String> existingPids = target
.getPid()
.stream()
.map(pid -> pid.getQualifier().getClassid() + "::" + pid.getValue())
.collect(Collectors.toSet());
return source
.getPid()
.stream()
.filter(pid -> !existingPids.contains(pid.getQualifier().getClassid() + "::" + pid.getValue()))
.map(ConversionUtils::oafPidToBrokerPid)
.map(i -> generateUpdateInfo(i, source, target))
.collect(Collectors.toList());
}
@Override
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

@ -0,0 +1,50 @@
package eu.dnetlib.dhp.broker.oa.matchers;
import java.util.List;
import java.util.Set;
import java.util.stream.Collectors;
import org.apache.commons.lang3.tuple.Pair;
import eu.dnetlib.dhp.broker.model.Topic;
import eu.dnetlib.dhp.broker.oa.util.ConversionUtils;
import eu.dnetlib.dhp.broker.oa.util.UpdateInfo;
import eu.dnetlib.dhp.schema.oaf.Result;
public class EnrichMoreSubject extends UpdateMatcher<Pair<String, String>> {
public EnrichMoreSubject() {
super(true);
}
@Override
protected List<UpdateInfo<Pair<String, String>>> findUpdates(final Result source, final Result target) {
final Set<String> existingSubjects = target
.getSubject()
.stream()
.map(pid -> pid.getQualifier().getClassid() + "::" + pid.getValue())
.collect(Collectors.toSet());
return source
.getPid()
.stream()
.filter(pid -> !existingSubjects.contains(pid.getQualifier().getClassid() + "::" + pid.getValue()))
.map(ConversionUtils::oafSubjectToPair)
.map(i -> generateUpdateInfo(i, source, target))
.collect(Collectors.toList());
}
@Override
public UpdateInfo<Pair<String, String>> generateUpdateInfo(final Pair<String, String> highlightValue,
final Result source,
final Result target) {
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

@ -0,0 +1,64 @@
package eu.dnetlib.dhp.broker.oa.matchers;
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.broker.oa.util.UpdateInfo;
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

@ -0,0 +1,7 @@
package eu.dnetlib.dhp.broker.oa.util;
public class BrokerConstants {
public final static String OPEN_ACCESS = "OPEN";
}

View File

@ -0,0 +1,36 @@
package eu.dnetlib.dhp.broker.oa.util;
import java.util.stream.Stream;
import org.apache.commons.lang3.tuple.Pair;
import eu.dnetlib.broker.objects.Instance;
import eu.dnetlib.broker.objects.Pid;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
public class ConversionUtils {
public static Stream<Instance> oafInstanceToBrokerInstances(final eu.dnetlib.dhp.schema.oaf.Instance i) {
return i.getUrl().stream().map(url -> {
final Instance r = new Instance();
r.setUrl(url);
r.setInstancetype(i.getInstancetype().getClassid());
r.setLicense(BrokerConstants.OPEN_ACCESS);
r.setHostedby(i.getHostedby().getValue());
return r;
});
}
public static Pid oafPidToBrokerPid(final StructuredProperty sp) {
final Pid pid = new Pid();
pid.setValue(sp.getValue());
pid.setType(sp.getQualifier().getClassid());
return pid;
}
public static final Pair<String, String> oafSubjectToPair(final StructuredProperty sp) {
return Pair.of(sp.getQualifier().getClassid(), sp.getValue());
}
}

View File

@ -1,31 +0,0 @@
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.schema.oaf.Result;
public class EnrichMissingAbstract extends UpdateInfo<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);
}
@Override
public void compileHighlight(final OpenAireEventPayload payload) {
payload.getHighlight().getAbstracts().add(getHighlightValue());
}
@Override
public String getHighlightValueAsString() {
return getHighlightValue();
}
}

View File

@ -1,31 +0,0 @@
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.schema.oaf.Result;
public class EnrichMissingAuthorOrcid extends UpdateInfo<String> {
public static List<EnrichMissingAuthorOrcid> 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
}
@Override
public String getHighlightValueAsString() {
return getHighlightValue();
}
}

View File

@ -1,32 +0,0 @@
package eu.dnetlib.dhp.broker.oa.util;
import java.util.Arrays;
import java.util.List;
import eu.dnetlib.broker.objects.Instance;
import eu.dnetlib.broker.objects.OpenAireEventPayload;
import eu.dnetlib.dhp.schema.oaf.Result;
public class EnrichMissingOpenAccess extends UpdateInfo<Instance> {
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();
}
}

View File

@ -1,32 +0,0 @@
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.schema.oaf.Result;
public class EnrichMissingPid extends UpdateInfo<Pid> {
public static List<EnrichMissingPid> 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();
}
}

View File

@ -1,33 +0,0 @@
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.schema.oaf.Result;
public class EnrichMissingProject extends UpdateInfo<Project> {
public static List<EnrichMissingProject> 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();
}
}

View File

@ -1,31 +0,0 @@
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.schema.oaf.Result;
public class EnrichMissingPublicationDate extends UpdateInfo<String> {
public static List<EnrichMissingPublicationDate> 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();
}
}

View File

@ -1,36 +0,0 @@
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.schema.oaf.Result;
public class EnrichMissingSubject extends UpdateInfo<String> {
public static List<EnrichMissingSubject> findUpdates(final Result source, final Result target) {
// MESHEUROPMC
// ARXIV
// JEL
// DDC
// ACM
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());
}
@Override
public String getHighlightValueAsString() {
return getHighlightValue();
}
}

View File

@ -1,32 +0,0 @@
package eu.dnetlib.dhp.broker.oa.util;
import java.util.Arrays;
import java.util.List;
import eu.dnetlib.broker.objects.Instance;
import eu.dnetlib.broker.objects.OpenAireEventPayload;
import eu.dnetlib.dhp.schema.oaf.Result;
public class EnrichMoreOpenAccess extends UpdateInfo<Instance> {
public static List<EnrichMoreOpenAccess> 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();
}
}

View File

@ -1,32 +0,0 @@
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.schema.oaf.Result;
public class EnrichMorePid extends UpdateInfo<Pid> {
public static List<EnrichMorePid> 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();
}
}

View File

@ -1,36 +0,0 @@
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.schema.oaf.Result;
public class EnrichMoreSubject extends UpdateInfo<String> {
public static List<EnrichMoreSubject> findUpdates(final Result source, final Result target) {
// MESHEUROPMC
// ARXIV
// JEL
// DDC
// ACM
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());
}
@Override
public String getHighlightValueAsString() {
return getHighlightValue();
}
}

View File

@ -1,36 +1,77 @@
package eu.dnetlib.dhp.broker.oa.util; 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.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 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; private final float trust;
protected UpdateInfo(final String topic, final T highlightValue, final float trust) { public 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.topic = topic;
this.highlightValue = highlightValue; 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() { public T getHighlightValue() {
return highlightValue; 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() { public float getTrust() {
return trust; return trust;
} }
public String getTopic() { public void compileHighlight(final OpenAireEventPayload payload) {
return topic; compileHighlight.accept(payload.getHighlight(), getHighlightValue());
} }
abstract public void compileHighlight(OpenAireEventPayload payload); public String getHighlightValueAsString() {
return highlightToString.apply(getHighlightValue());
abstract public String getHighlightValueAsString(); }
} }

View File

@ -129,6 +129,9 @@ public class DedupUtility {
.max(Comparator.comparing(Tuple2::_1)); .max(Comparator.comparing(Tuple2::_1));
if (simAuhtor.isPresent() && simAuhtor.get()._1() > THRESHOLD) { if (simAuhtor.isPresent() && simAuhtor.get()._1() > THRESHOLD) {
Author r = simAuhtor.get()._2(); Author r = simAuhtor.get()._2();
if (r.getPid() == null) {
r.setPid(new ArrayList<>());
}
r.getPid().add(a._1()); r.getPid().add(a._1());
} }
}); });

View File

@ -0,0 +1,104 @@
package eu.dnetlib.doiboost
import eu.dnetlib.dhp.schema.oaf.{DataInfo, Dataset, Field, KeyValue, Qualifier, Result, StructuredProperty}
import eu.dnetlib.dhp.utils.DHPUtils
object DoiBoostMappingUtil {
//STATIC STRING
val MAG = "microsoft"
val ORCID = "ORCID"
val CROSSREF = "Crossref"
val UNPAYWALL = "UnpayWall"
val GRID_AC = "grid.ac"
val WIKPEDIA = "wikpedia"
val doiBoostNSPREFIX = "doiboost____"
val OPENAIRE_PREFIX = "openaire____"
val SEPARATOR = "::"
val DNET_LANGUAGES = "dnet:languages"
val PID_TYPES = "dnet:pid_types"
def generateDataInfo(): DataInfo = {
val di = new DataInfo
di.setDeletedbyinference(false)
di.setInferred(false)
di.setInvisible(false)
di.setTrust("0.9")
di.setProvenanceaction(createQualifier("sysimport:actionset", "dnet:provenanceActions"))
di
}
def createSP(value: String, classId: String, schemeId: String): StructuredProperty = {
val sp = new StructuredProperty
sp.setQualifier(createQualifier(classId, schemeId))
sp.setValue(value)
sp
}
def createSP(value: String, classId: String, schemeId: String, dataInfo: DataInfo): StructuredProperty = {
val sp = new StructuredProperty
sp.setQualifier(createQualifier(classId, schemeId))
sp.setValue(value)
sp.setDataInfo(dataInfo)
sp
}
def createCrossrefCollectedFrom(): KeyValue = {
val cf = new KeyValue
cf.setValue(CROSSREF)
cf.setKey("10|" + OPENAIRE_PREFIX + SEPARATOR + DHPUtils.md5("crossref"))
cf
}
def generateIdentifier(oaf: Result, doi: String): String = {
val id = DHPUtils.md5(doi.toLowerCase)
if (oaf.isInstanceOf[Dataset])
return s"60|${doiBoostNSPREFIX}${SEPARATOR}${id}"
s"50|${doiBoostNSPREFIX}${SEPARATOR}${id}"
}
def createMAGCollectedFrom(): KeyValue = {
val cf = new KeyValue
cf.setValue(MAG)
cf.setKey("10|" + OPENAIRE_PREFIX + SEPARATOR + DHPUtils.md5(MAG))
cf
}
def createQualifier(clsName: String, clsValue: String, schName: String, schValue: String): Qualifier = {
val q = new Qualifier
q.setClassid(clsName)
q.setClassname(clsValue)
q.setSchemeid(schName)
q.setSchemename(schValue)
q
}
def createQualifier(cls: String, sch: String): Qualifier = {
createQualifier(cls, cls, sch, sch)
}
def asField[T](value: T): Field[T] = {
val tmp = new Field[T]
tmp.setValue(value)
tmp
}
}

View File

@ -14,6 +14,7 @@ import org.slf4j.{Logger, LoggerFactory}
import scala.collection.JavaConverters._ import scala.collection.JavaConverters._
import scala.collection.mutable import scala.collection.mutable
import scala.util.matching.Regex import scala.util.matching.Regex
import eu.dnetlib.doiboost.DoiBoostMappingUtil._
case class mappingAffiliation(name: String) {} case class mappingAffiliation(name: String) {}
@ -25,18 +26,7 @@ case class mappingFunder(name: String, DOI: Option[String], award: Option[List[S
case object Crossref2Oaf { case object Crossref2Oaf {
val logger: Logger = LoggerFactory.getLogger(Crossref2Oaf.getClass) val logger: Logger = LoggerFactory.getLogger(Crossref2Oaf.getClass)
//STATIC STRING
val MAG = "MAG"
val ORCID = "ORCID"
val CROSSREF = "Crossref"
val UNPAYWALL = "UnpayWall"
val GRID_AC = "grid.ac"
val WIKPEDIA = "wikpedia"
val doiBoostNSPREFIX = "doiboost____"
val OPENAIRE_PREFIX = "openaire____"
val SEPARATOR = "::"
val DNET_LANGUAGES = "dnet:languages"
val PID_TYPES = "dnet:pid_types"
val mappingCrossrefType = Map( val mappingCrossrefType = Map(
"book-section" -> "publication", "book-section" -> "publication",
@ -116,7 +106,7 @@ case object Crossref2Oaf {
result.setLastupdatetimestamp((json \ "indexed" \ "timestamp").extract[Long]) result.setLastupdatetimestamp((json \ "indexed" \ "timestamp").extract[Long])
result.setDateofcollection((json \ "indexed" \ "date-time").extract[String]) result.setDateofcollection((json \ "indexed" \ "date-time").extract[String])
result.setCollectedfrom(List(createCollectedFrom()).asJava) result.setCollectedfrom(List(createCrossrefCollectedFrom()).asJava)
// Publisher ( Name of work's publisher mapped into Result/Publisher) // Publisher ( Name of work's publisher mapped into Result/Publisher)
val publisher = (json \ "publisher").extractOrElse[String](null) val publisher = (json \ "publisher").extractOrElse[String](null)
@ -168,7 +158,7 @@ case object Crossref2Oaf {
result.setInstance(List(instance).asJava) result.setInstance(List(instance).asJava)
instance.setInstancetype(createQualifier(cobjCategory.substring(0, 4), cobjCategory.substring(5), "dnet:publication_resource", "dnet:publication_resource")) instance.setInstancetype(createQualifier(cobjCategory.substring(0, 4), cobjCategory.substring(5), "dnet:publication_resource", "dnet:publication_resource"))
instance.setCollectedfrom(createCollectedFrom()) instance.setCollectedfrom(createCrossrefCollectedFrom())
if (StringUtils.isNotBlank(issuedDate)) { if (StringUtils.isNotBlank(issuedDate)) {
instance.setDateofacceptance(asField(issuedDate)) instance.setDateofacceptance(asField(issuedDate))
} }
@ -215,7 +205,7 @@ case object Crossref2Oaf {
val funderList: List[mappingFunder] = (json \ "funder").extractOrElse[List[mappingFunder]](List()) val funderList: List[mappingFunder] = (json \ "funder").extractOrElse[List[mappingFunder]](List())
if (funderList.nonEmpty) { if (funderList.nonEmpty) {
resultList = resultList ::: mappingFunderToRelations(funderList, result.getId, createCollectedFrom(), result.getDataInfo, result.getLastupdatetimestamp) resultList = resultList ::: mappingFunderToRelations(funderList, result.getId, createCrossrefCollectedFrom(), result.getDataInfo, result.getLastupdatetimestamp)
} }
@ -416,71 +406,8 @@ case object Crossref2Oaf {
} }
def generateIdentifier(oaf: Result, doi: String): String = {
val id = DHPUtils.md5(doi.toLowerCase)
if (oaf.isInstanceOf[Dataset])
return s"60|${doiBoostNSPREFIX}${SEPARATOR}${id}"
s"50|${doiBoostNSPREFIX}${SEPARATOR}${id}"
}
def asField[T](value: T): Field[T] = {
val tmp = new Field[T]
tmp.setValue(value)
tmp
}
def generateDataInfo(): DataInfo = {
val di = new DataInfo
di.setDeletedbyinference(false)
di.setInferred(false)
di.setInvisible(false)
di.setTrust("0.9")
di.setProvenanceaction(createQualifier("sysimport:actionset", "dnet:provenanceActions"))
di
}
def createSP(value: String, classId: String, schemeId: String): StructuredProperty = {
val sp = new StructuredProperty
sp.setQualifier(createQualifier(classId, schemeId))
sp.setValue(value)
sp
}
def createSP(value: String, classId: String, schemeId: String, dataInfo: DataInfo): StructuredProperty = {
val sp = new StructuredProperty
sp.setQualifier(createQualifier(classId, schemeId))
sp.setValue(value)
sp.setDataInfo(dataInfo)
sp
}
def createCollectedFrom(): KeyValue = {
val cf = new KeyValue
cf.setValue(CROSSREF)
cf.setKey("10|" + OPENAIRE_PREFIX + SEPARATOR + DHPUtils.md5("crossref"))
cf
}
def createQualifier(clsName: String, clsValue: String, schName: String, schValue: String): Qualifier = {
val q = new Qualifier
q.setClassid(clsName)
q.setClassname(clsValue)
q.setSchemeid(schName)
q.setSchemename(schValue)
q
}
def createQualifier(cls: String, sch: String): Qualifier = {
createQualifier(cls, cls, sch, sch)
}
def generateItemFromType(objectType: String, objectSubType: String): Result = { def generateItemFromType(objectType: String, objectSubType: String): Result = {

View File

@ -1,52 +1,215 @@
package eu.dnetlib.doiboost.mag package eu.dnetlib.doiboost.mag
import eu.dnetlib.dhp.schema.oaf.{Instance, Journal, Publication}
import org.json4s import org.json4s
import org.json4s.DefaultFormats import org.json4s.DefaultFormats
import org.json4s.jackson.JsonMethods.parse import org.json4s.jackson.JsonMethods.parse
import eu.dnetlib.doiboost.DoiBoostMappingUtil._
import scala.collection.JavaConverters._
import scala.collection.mutable
import scala.util.matching.Regex
case class Papers(PaperId:Long, Rank:Integer, Doi:String, case class MagPapers(PaperId: Long, Rank: Integer, Doi: String,
DocType:String, PaperTitle:String, OriginalTitle:String, DocType: String, PaperTitle: String, OriginalTitle: String,
BookTitle:String, Year:Option[Integer], Date:Option[java.sql.Timestamp], Publisher:String, BookTitle: String, Year: Option[Integer], Date: Option[java.sql.Timestamp], Publisher: String,
JournalId:Option[Long], ConferenceSeriesId:Option[Long], ConferenceInstanceId:Option[Long], JournalId: Option[Long], ConferenceSeriesId: Option[Long], ConferenceInstanceId: Option[Long],
Volume:String, Issue:String, FirstPage:String, LastPage:String, Volume: String, Issue: String, FirstPage: String, LastPage: String,
ReferenceCount:Option[Long], CitationCount:Option[Long], EstimatedCitation:Option[Long], ReferenceCount: Option[Long], CitationCount: Option[Long], EstimatedCitation: Option[Long],
OriginalVenue:String, FamilyId:Option[Long], CreatedDate:java.sql.Timestamp) {} OriginalVenue: String, FamilyId: Option[Long], CreatedDate: java.sql.Timestamp) {}
case class PaperAbstract(PaperId:Long,IndexedAbstract:String) {} case class MagPaperAbstract(PaperId: Long, IndexedAbstract: String) {}
case class MagAuthor(AuthorId: Long, Rank: Option[Int], NormalizedName: Option[String], DisplayName: Option[String], LastKnownAffiliationId: Option[Long], PaperCount: Option[Long], CitationCount: Option[Long], CreatedDate: Option[java.sql.Timestamp]) {}
case class MagAffiliation(AffiliationId: Long, Rank: Int, NormalizedName: String, DisplayName: String, GridId: String, OfficialPage: String, WikiPage: String, PaperCount: Long, CitationCount: Long, Latitude: Option[Float], Longitude: Option[Float], CreatedDate: java.sql.Timestamp) {}
case class MagPaperAuthorAffiliation(PaperId: Long, AuthorId: Long, AffiliationId: Option[Long], AuthorSequenceNumber: Int, OriginalAuthor: String, OriginalAffiliation: String) {}
case class MagAuthorAffiliation(author: MagAuthor, affiliation:String)
case class MagPaperWithAuthorList(PaperId: Long, authors: List[MagAuthorAffiliation]) {}
case class MagPaperAuthorDenormalized(PaperId: Long, author: MagAuthor, affiliation:String) {}
case class MagPaperUrl(PaperId: Long, SourceType: Option[Int], SourceUrl: Option[String], LanguageCode: Option[String]) {}
case class MagUrl(PaperId: Long, instances: List[String])
case class MagJournal(JournalId: Long, Rank: Option[Int], NormalizedName: Option[String], DisplayName: Option[String], Issn: Option[String], Publisher: Option[String], Webpage: Option[String], PaperCount: Option[Long], CitationCount: Option[Long], CreatedDate: Option[java.sql.Timestamp]) {}
case object ConversionUtil { case object ConversionUtil {
def extractMagIdentifier(pids:mutable.Buffer[String]) :String ={
val magIDRegex: Regex = "^[0-9]+$".r
val s =pids.filter(p=> magIDRegex.findAllIn(p).hasNext)
if (s.nonEmpty)
def transformPaperAbstract(input:PaperAbstract) : PaperAbstract = { return s.head
PaperAbstract(input.PaperId, convertInvertedIndexString(input.IndexedAbstract)) null
} }
def convertInvertedIndexString(json_input:String) :String = { def addInstances(a: (Publication, MagUrl)): Publication = {
val pub = a._1
val urls = a._2
val i = new Instance
if (urls!= null) {
val l:List[String] = urls.instances.filter(k=>k.nonEmpty):::List(s"https://academic.microsoft.com/#/detail/${extractMagIdentifier(pub.getOriginalId.asScala)}")
i.setUrl(l.asJava)
}
else
i.setUrl(List(s"https://academic.microsoft.com/#/detail/${extractMagIdentifier(pub.getOriginalId.asScala)}").asJava)
i.setCollectedfrom(createMAGCollectedFrom())
pub.setInstance(List(i).asJava)
pub
}
def transformPaperAbstract(input: MagPaperAbstract): MagPaperAbstract = {
MagPaperAbstract(input.PaperId, convertInvertedIndexString(input.IndexedAbstract))
}
def createOAFFromJournalAuthorPaper(inputParams: ((MagPapers, MagJournal), MagPaperWithAuthorList)): Publication = {
val paper = inputParams._1._1
val journal = inputParams._1._2
val authors = inputParams._2
val pub = new Publication
pub.setPid(List(createSP(paper.Doi.toLowerCase, "doi", PID_TYPES)).asJava)
pub.setOriginalId(List(paper.PaperId.toString, paper.Doi.toLowerCase).asJava)
//Set identifier as {50|60} | doiboost____::md5(DOI)
pub.setId(generateIdentifier(pub, paper.Doi.toLowerCase))
val mainTitles = createSP(paper.PaperTitle, "main title", "dnet:dataCite_title")
val originalTitles = createSP(paper.OriginalTitle, "alternative title", "dnet:dataCite_title")
pub.setTitle(List(mainTitles, originalTitles).asJava)
pub.setSource(List(asField(paper.BookTitle)).asJava)
val authorsOAF = authors.authors.map { f: MagAuthorAffiliation =>
val a: eu.dnetlib.dhp.schema.oaf.Author = new eu.dnetlib.dhp.schema.oaf.Author
a.setFullname(f.author.DisplayName.get)
if(f.affiliation!= null)
a.setAffiliation(List(asField(f.affiliation)).asJava)
a.setPid(List(createSP(s"https://academic.microsoft.com/#/detail/${f.author.AuthorId}", "URL", PID_TYPES)).asJava)
a
}
pub.setAuthor(authorsOAF.asJava)
if (paper.Date != null && paper.Date.isDefined) {
pub.setDateofacceptance(asField(paper.Date.get.toString))
}
pub.setPublisher(asField(paper.Publisher))
if (journal != null && journal.DisplayName.isDefined) {
val j = new Journal
j.setName(journal.DisplayName.get)
j.setSp(paper.FirstPage)
j.setEp(paper.LastPage)
if (journal.Publisher.isDefined)
j.setEdition(journal.Publisher.get)
if (journal.Issn.isDefined)
j.setIssnPrinted(journal.Issn.get)
pub.setJournal(j)
}
pub
}
def createOAF(inputParams: ((MagPapers, MagPaperWithAuthorList), MagPaperAbstract)): Publication = {
val paper = inputParams._1._1
val authors = inputParams._1._2
val description = inputParams._2
val pub = new Publication
pub.setPid(List(createSP(paper.Doi.toLowerCase, "doi", PID_TYPES)).asJava)
pub.setOriginalId(List(paper.PaperId.toString, paper.Doi.toLowerCase).asJava)
//Set identifier as {50|60} | doiboost____::md5(DOI)
pub.setId(generateIdentifier(pub, paper.Doi.toLowerCase))
val mainTitles = createSP(paper.PaperTitle, "main title", "dnet:dataCite_title")
val originalTitles = createSP(paper.OriginalTitle, "alternative title", "dnet:dataCite_title")
pub.setTitle(List(mainTitles, originalTitles).asJava)
pub.setSource(List(asField(paper.BookTitle)).asJava)
if (description != null) {
pub.setDescription(List(asField(description.IndexedAbstract)).asJava)
}
val authorsOAF = authors.authors.map { f: MagAuthorAffiliation =>
val a: eu.dnetlib.dhp.schema.oaf.Author = new eu.dnetlib.dhp.schema.oaf.Author
a.setFullname(f.author.DisplayName.get)
if(f.affiliation!= null)
a.setAffiliation(List(asField(f.affiliation)).asJava)
a.setPid(List(createSP(s"https://academic.microsoft.com/#/detail/${f.author.AuthorId}", "URL", PID_TYPES)).asJava)
a
}
if (paper.Date != null) {
pub.setDateofacceptance(asField(paper.Date.toString))
}
pub.setAuthor(authorsOAF.asJava)
pub
}
def convertInvertedIndexString(json_input: String): String = {
implicit lazy val formats: DefaultFormats.type = org.json4s.DefaultFormats implicit lazy val formats: DefaultFormats.type = org.json4s.DefaultFormats
lazy val json: json4s.JValue = parse(json_input) lazy val json: json4s.JValue = parse(json_input)
val idl = (json \ "IndexLength").extract[Int] val idl = (json \ "IndexLength").extract[Int]
if (idl > 0) { if (idl > 0) {
val res = Array.ofDim[String](idl) val res = Array.ofDim[String](idl)
val iid = (json \ "InvertedIndex").extract[Map[String, List[Int]]] val iid = (json \ "InvertedIndex").extract[Map[String, List[Int]]]
for {(k:String,v:List[Int]) <- iid}{ for {(k: String, v: List[Int]) <- iid} {
v.foreach(item => res(item) = k) v.foreach(item => res(item) = k)
} }
(0 until idl).foreach(i => {
if (res(i) == null)
res(i) = ""
})
return res.mkString(" ") return res.mkString(" ")
} }
"" ""
} }

View File

@ -1,13 +1,17 @@
package eu.dnetlib.doiboost.mag package eu.dnetlib.doiboost.mag
import eu.dnetlib.dhp.application.ArgumentApplicationParser import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.schema.oaf.Publication
import eu.dnetlib.doiboost.DoiBoostMappingUtil.asField
import org.apache.commons.io.IOUtils import org.apache.commons.io.IOUtils
import org.apache.spark.SparkConf import org.apache.spark.SparkConf
import org.apache.spark.rdd.RDD import org.apache.spark.rdd.RDD
import org.apache.spark.sql.{Dataset, SaveMode, SparkSession} import org.apache.spark.sql.{Dataset, Encoder, Encoders, SaveMode, SparkSession}
import org.slf4j.{Logger, LoggerFactory} import org.slf4j.{Logger, LoggerFactory}
import org.apache.spark.sql.functions._ import org.apache.spark.sql.functions._
import scala.collection.JavaConverters._
object SparkPreProcessMAG { object SparkPreProcessMAG {
@ -23,15 +27,21 @@ object SparkPreProcessMAG {
.config(conf) .config(conf)
.appName(getClass.getSimpleName) .appName(getClass.getSimpleName)
.master(parser.get("master")).getOrCreate() .master(parser.get("master")).getOrCreate()
val sourcePath = parser.get("sourcePath")
import spark.implicits._ import spark.implicits._
implicit val mapEncoderPubs: Encoder[Publication] = org.apache.spark.sql.Encoders.kryo[Publication]
implicit val tupleForJoinEncoder = Encoders.tuple(Encoders.STRING, mapEncoderPubs)
logger.info("Phase 1) make uninque DOI in Papers:") logger.info("Phase 1) make uninque DOI in Papers:")
val d: Dataset[Papers] = spark.read.load(s"${parser.get("sourcePath")}/Papers").as[Papers] val d: Dataset[MagPapers] = spark.read.load(s"${parser.get("sourcePath")}/Papers").as[MagPapers]
// Filtering Papers with DOI, and since for the same DOI we have multiple version of item with different PapersId we get the last one // Filtering Papers with DOI, and since for the same DOI we have multiple version of item with different PapersId we get the last one
val result: RDD[Papers] = d.where(col("Doi").isNotNull).rdd.map { p: Papers => Tuple2(p.Doi, p) }.reduceByKey { case (p1: Papers, p2: Papers) => val result: RDD[MagPapers] = d.where(col("Doi").isNotNull).rdd.map { p: MagPapers => Tuple2(p.Doi, p) }.reduceByKey { case (p1: MagPapers, p2: MagPapers) =>
var r = if (p1 == null) p2 else p1 var r = if (p1 == null) p2 else p1
if (p1 != null && p2 != null) { if (p1 != null && p2 != null) {
if (p1.CreatedDate != null && p2.CreatedDate != null) { if (p1.CreatedDate != null && p2.CreatedDate != null) {
@ -46,16 +56,83 @@ object SparkPreProcessMAG {
r r
}.map(_._2) }.map(_._2)
val distinctPaper: Dataset[Papers] = spark.createDataset(result) val distinctPaper: Dataset[MagPapers] = spark.createDataset(result)
distinctPaper.write.mode(SaveMode.Overwrite).save(s"${parser.get("targetPath")}/Papers_distinct") distinctPaper.write.mode(SaveMode.Overwrite).save(s"${parser.get("targetPath")}/Papers_distinct")
logger.info(s"Total number of element: ${result.count()}") logger.info(s"Total number of element: ${result.count()}")
logger.info("Phase 2) convert InverdIndex Abastrac to string") logger.info("Phase 3) Group Author by PaperId")
val pa = spark.read.load(s"${parser.get("sourcePath")}/PaperAbstractsInvertedIndex").as[PaperAbstract] val authors = spark.read.load(s"$sourcePath/Authors").as[MagAuthor]
val affiliation =spark.read.load(s"$sourcePath/Affiliations").as[MagAffiliation]
val paperAuthorAffiliation =spark.read.load(s"$sourcePath/PaperAuthorAffiliations").as[MagPaperAuthorAffiliation]
paperAuthorAffiliation.joinWith(authors, paperAuthorAffiliation("AuthorId").equalTo(authors("AuthorId")))
.map{case (a:MagPaperAuthorAffiliation,b:MagAuthor )=> (a.AffiliationId,MagPaperAuthorDenormalized(a.PaperId, b, null)) }
.joinWith(affiliation, affiliation("AffiliationId").equalTo(col("_1")), "left")
.map(s => {
val mpa = s._1._2
val af = s._2
if (af!= null) {
MagPaperAuthorDenormalized(mpa.PaperId, mpa.author, af.DisplayName)
} else
mpa
}).groupBy("PaperId").agg(collect_list(struct($"author", $"affiliation")).as("authors"))
.write.mode(SaveMode.Overwrite).save(s"${parser.get("targetPath")}/merge_step_1_paper_authors")
logger.info("Phase 4) create First Version of publication Entity with Paper Journal and Authors")
val journals = spark.read.load(s"$sourcePath/Journals").as[MagJournal]
val papers =spark.read.load((s"${parser.get("targetPath")}/Papers_distinct")).as[MagPapers]
val paperWithAuthors = spark.read.load(s"${parser.get("targetPath")}/merge_step_1_paper_authors").as[MagPaperWithAuthorList]
val firstJoin =papers.joinWith(journals, papers("JournalId").equalTo(journals("JournalId")),"left")
firstJoin.joinWith(paperWithAuthors, firstJoin("_1.PaperId").equalTo(paperWithAuthors("PaperId")), "left")
.map { a: ((MagPapers, MagJournal), MagPaperWithAuthorList) => ConversionUtil.createOAFFromJournalAuthorPaper(a) }.write.mode(SaveMode.Overwrite).save(s"${parser.get("targetPath")}/merge_step_2")
var magPubs:Dataset[(String,Publication)] = spark.read.load(s"${parser.get("targetPath")}/merge_step_2").as[Publication].map(p => (ConversionUtil.extractMagIdentifier(p.getOriginalId.asScala), p)).as[(String,Publication)]
val paperUrlDataset = spark.read.load(s"$sourcePath/PaperUrls").as[MagPaperUrl].groupBy("PaperId").agg(collect_list(struct("sourceUrl")).as("instances")).as[MagUrl]
logger.info("Phase 5) enrich publication with URL and Instances")
magPubs.joinWith(paperUrlDataset, col("_1").equalTo(paperUrlDataset("PaperId")), "left")
.map{a:((String,Publication), MagUrl) => ConversionUtil.addInstances((a._1._2, a._2))}
.write.mode(SaveMode.Overwrite)
.save(s"${parser.get("targetPath")}/merge_step_3")
logger.info("Phase 6) Enrich Publication with description")
val pa = spark.read.load(s"${parser.get("sourcePath")}/PaperAbstractsInvertedIndex").as[MagPaperAbstract]
pa.map(ConversionUtil.transformPaperAbstract).write.mode(SaveMode.Overwrite).save(s"${parser.get("targetPath")}/PaperAbstract") pa.map(ConversionUtil.transformPaperAbstract).write.mode(SaveMode.Overwrite).save(s"${parser.get("targetPath")}/PaperAbstract")
val paperAbstract =spark.read.load((s"${parser.get("targetPath")}/PaperAbstract")).as[MagPaperAbstract]
distinctPaper.joinWith(pa, col("PaperId").eqia)
magPubs = spark.read.load(s"${parser.get("targetPath")}/merge_step_3").as[Publication].map(p => (ConversionUtil.extractMagIdentifier(p.getOriginalId.asScala), p)).as[(String,Publication)]
magPubs.joinWith(paperAbstract,col("_1").equalTo(paperAbstract("PaperId")), "left").map(p=>
{
val pub = p._1._2
val abst = p._2
if (abst!= null) {
pub.setDescription(List(asField(abst.IndexedAbstract)).asJava)
}
pub
}
).write.mode(SaveMode.Overwrite).save(s"${parser.get("targetPath")}/merge_step_4")
} }

View File

@ -72,6 +72,7 @@
--executor-memory=${sparkExecutorMemory} --executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores} --executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory} --driver-memory=${sparkDriverMemory}
--conf spark.sql.shuffle.partitions=3840
${sparkExtraOPT} ${sparkExtraOPT}
</spark-opts> </spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}</arg> <arg>--sourcePath</arg><arg>${sourcePath}</arg>

View File

@ -11,6 +11,10 @@
<name>queueName</name> <name>queueName</name>
<value>default</value> <value>default</value>
</property> </property>
<property>
<name>oozie.use.system.libpath</name>
<value>true</value>
</property>
<property> <property>
<name>oozie.action.sharelib.for.spark</name> <name>oozie.action.sharelib.for.spark</name>
<value>spark2</value> <value>spark2</value>

View File

@ -20,6 +20,10 @@
<name>sparkExecutorCores</name> <name>sparkExecutorCores</name>
<description>number of cores used by single executor</description> <description>number of cores used by single executor</description>
</property> </property>
<property>
<name>outputPath</name>
<description>the working dir base path</description>
</property>
</parameters> </parameters>
<start to="ResetWorkingPath"/> <start to="ResetWorkingPath"/>

View File

@ -1,10 +1,21 @@
package eu.dnetlib.doiboost.mag package eu.dnetlib.doiboost.mag
import org.codehaus.jackson.map.ObjectMapper import eu.dnetlib.dhp.schema.oaf.Publication
import org.apache.htrace.fasterxml.jackson.databind.SerializationFeature
import org.apache.spark.SparkConf
import org.apache.spark.api.java.function.MapFunction
import org.apache.spark.sql.{Dataset, Encoder, Encoders, SaveMode, SparkSession}
import org.codehaus.jackson.map.{ObjectMapper, SerializationConfig}
import org.junit.jupiter.api.Test import org.junit.jupiter.api.Test
import org.slf4j.{Logger, LoggerFactory} import org.slf4j.{Logger, LoggerFactory}
import org.junit.jupiter.api.Assertions._ import org.junit.jupiter.api.Assertions._
import org.apache.spark.sql.functions._
import scala.collection.JavaConverters._
import scala.io.Source import scala.io.Source
import scala.reflect.ClassTag
import scala.util.matching.Regex
class MAGMappingTest { class MAGMappingTest {
@ -13,14 +24,49 @@ class MAGMappingTest {
val mapper = new ObjectMapper() val mapper = new ObjectMapper()
//@Test @Test
def testMAGCSV(): Unit = { def testMAGCSV(): Unit = {
SparkPreProcessMAG.main("-m local[*] -s /data/doiboost/mag/datasets -t /data/doiboost/mag/datasets/preprocess".split(" ")) // SparkPreProcessMAG.main("-m local[*] -s /data/doiboost/mag/datasets -t /data/doiboost/mag/datasets/preprocess".split(" "))
val sparkConf: SparkConf = new SparkConf
val spark: SparkSession = SparkSession.builder()
.config(sparkConf)
.appName(getClass.getSimpleName)
.master("local[*]")
.getOrCreate()
import spark.implicits._
implicit val mapEncoderPubs: Encoder[Publication] = org.apache.spark.sql.Encoders.kryo[Publication]
implicit val longBarEncoder = Encoders.tuple(Encoders.STRING, mapEncoderPubs)
val sourcePath = "/data/doiboost/mag/input"
mapper.getSerializationConfig.enable(SerializationConfig.Feature.INDENT_OUTPUT)
val magOAF = spark.read.load("$sourcePath/merge_step_4").as[Publication]
println(magOAF.first().getOriginalId)
magOAF.map(k => (ConversionUtil.extractMagIdentifier(k.getOriginalId.asScala),k)).as[(String,Publication)].show()
println((ConversionUtil.extractMagIdentifier(magOAF.first().getOriginalId.asScala)))
val magIDRegex: Regex = "^[0-9]+$".r
println(magIDRegex.findFirstMatchIn("suca").isDefined)
} }
@Test @Test
def buildInvertedIndexTest() :Unit = { def buildInvertedIndexTest(): Unit = {
val json_input = Source.fromInputStream(getClass.getResourceAsStream("invertedIndex.json")).mkString val json_input = Source.fromInputStream(getClass.getResourceAsStream("invertedIndex.json")).mkString
val description = ConversionUtil.convertInvertedIndexString(json_input) val description = ConversionUtil.convertInvertedIndexString(json_input)
assertNotNull(description) assertNotNull(description)
@ -32,3 +78,5 @@ class MAGMappingTest {
} }

View File

@ -15,6 +15,8 @@ import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.application.ArgumentApplicationParser; import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.HdfsSupport; import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.resulttocommunityfromorganization.ResultCommunityList; import eu.dnetlib.dhp.resulttocommunityfromorganization.ResultCommunityList;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.*; import eu.dnetlib.dhp.schema.oaf.*;
public class PropagationConstant { public class PropagationConstant {
@ -24,10 +26,6 @@ public class PropagationConstant {
public static final String TRUE = "true"; public static final String TRUE = "true";
public static final String DNET_COUNTRY_SCHEMA = "dnet:countries";
public static final String DNET_SCHEMA_NAME = "dnet:provenanceActions";
public static final String DNET_SCHEMA_ID = "dnet:provenanceActions";
public static final String PROPAGATION_COUNTRY_INSTREPO_CLASS_ID = "country:instrepos"; public static final String PROPAGATION_COUNTRY_INSTREPO_CLASS_ID = "country:instrepos";
public static final String PROPAGATION_COUNTRY_INSTREPO_CLASS_NAME = "Propagation of country to result collected from datasources of type institutional repositories"; public static final String PROPAGATION_COUNTRY_INSTREPO_CLASS_NAME = "Propagation of country to result collected from datasources of type institutional repositories";
@ -46,22 +44,6 @@ public class PropagationConstant {
public static final String PROPAGATION_ORCID_TO_RESULT_FROM_SEM_REL_CLASS_ID = "authorpid:result"; public static final String PROPAGATION_ORCID_TO_RESULT_FROM_SEM_REL_CLASS_ID = "authorpid:result";
public static final String PROPAGATION_ORCID_TO_RESULT_FROM_SEM_REL_CLASS_NAME = "Propagation of authors pid to result through semantic relations"; public static final String PROPAGATION_ORCID_TO_RESULT_FROM_SEM_REL_CLASS_NAME = "Propagation of authors pid to result through semantic relations";
public static final String RELATION_DATASOURCE_ORGANIZATION_REL_CLASS = "isProvidedBy";
public static final String RELATION_RESULTORGANIZATION_REL_TYPE = "resultOrganization";
public static final String RELATION_RESULTORGANIZATION_SUBREL_TYPE = "affiliation";
public static final String RELATION_ORGANIZATION_RESULT_REL_CLASS = "isAuthorInstitutionOf";
public static final String RELATION_RESULT_ORGANIZATION_REL_CLASS = "hasAuthorInstitution";
public static final String RELATION_RESULTRESULT_REL_TYPE = "resultResult";
public static final String RELATION_RESULTPROJECT_REL_TYPE = "resultProject";
public static final String RELATION_RESULTPROJECT_SUBREL_TYPE = "outcome";
public static final String RELATION_RESULT_PROJECT_REL_CLASS = "isProducedBy";
public static final String RELATION_PROJECT_RESULT_REL_CLASS = "produces";
public static final String RELATION_REPRESENTATIVERESULT_RESULT_CLASS = "merges";
public static final String PROPAGATION_AUTHOR_PID = "ORCID"; public static final String PROPAGATION_AUTHOR_PID = "ORCID";
public static final ObjectMapper OBJECT_MAPPER = new ObjectMapper(); public static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
@ -76,8 +58,8 @@ public class PropagationConstant {
Country nc = new Country(); Country nc = new Country();
nc.setClassid(classid); nc.setClassid(classid);
nc.setClassname(classname); nc.setClassname(classname);
nc.setSchemename(DNET_COUNTRY_SCHEMA); nc.setSchemename(ModelConstants.DNET_COUNTRY_TYPE);
nc.setSchemeid(DNET_COUNTRY_SCHEMA); nc.setSchemeid(ModelConstants.DNET_COUNTRY_TYPE);
nc nc
.setDataInfo( .setDataInfo(
getDataInfo( getDataInfo(
@ -102,8 +84,8 @@ public class PropagationConstant {
Qualifier pa = new Qualifier(); Qualifier pa = new Qualifier();
pa.setClassid(inference_class_id); pa.setClassid(inference_class_id);
pa.setClassname(inference_class_name); pa.setClassname(inference_class_name);
pa.setSchemeid(DNET_SCHEMA_ID); pa.setSchemeid(ModelConstants.DNET_PID_TYPES);
pa.setSchemename(DNET_SCHEMA_NAME); pa.setSchemename(ModelConstants.DNET_PID_TYPES);
return pa; return pa;
} }

View File

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

View File

@ -21,6 +21,7 @@ import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.ObjectMapper; import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.application.ArgumentApplicationParser; import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.*; import eu.dnetlib.dhp.schema.oaf.*;
/** /**
@ -100,7 +101,7 @@ public class PrepareDatasourceCountryAssociation {
+ "JOIN ( SELECT source, target " + "JOIN ( SELECT source, target "
+ " FROM relation " + " FROM relation "
+ " WHERE relclass = '" + " WHERE relclass = '"
+ RELATION_DATASOURCE_ORGANIZATION_REL_CLASS + ModelConstants.IS_PROVIDED_BY
+ "' " + "' "
+ " AND datainfo.deletedbyinference = false ) rel " + " AND datainfo.deletedbyinference = false ) rel "
+ "ON d.id = rel.source " + "ON d.id = rel.source "

View File

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

View File

@ -74,9 +74,7 @@ public class PrepareResultOrcidAssociationStep1 {
conf, conf,
isSparkSessionManaged, isSparkSessionManaged,
spark -> { spark -> {
if (isTest(parser)) { removeOutputDir(spark, outputPath);
removeOutputDir(spark, outputPath);
}
prepareInfo( prepareInfo(
spark, inputRelationPath, inputResultPath, outputResultPath, resultClazz, allowedsemrel); spark, inputRelationPath, inputResultPath, outputResultPath, resultClazz, allowedsemrel);
}); });
@ -97,22 +95,22 @@ public class PrepareResultOrcidAssociationStep1 {
Dataset<R> result = readPath(spark, inputResultPath, resultClazz); Dataset<R> result = readPath(spark, inputResultPath, resultClazz);
result.createOrReplaceTempView("result"); result.createOrReplaceTempView("result");
String query = " select target resultId, author authorList" String query = "SELECT target resultId, author authorList"
+ " from (select id, collect_set(named_struct('name', name, 'surname', surname, 'fullname', fullname, 'orcid', orcid)) author " + " FROM (SELECT id, collect_set(named_struct('name', name, 'surname', surname, 'fullname', fullname, 'orcid', orcid)) author "
+ " from ( " + " FROM ( "
+ " select id, MyT.fullname, MyT.name, MyT.surname, MyP.value orcid " + " SELECT DISTINCT id, MyT.fullname, MyT.name, MyT.surname, MyP.value orcid "
+ " from result " + " FROM result "
+ " lateral view explode (author) a as MyT " + " LATERAL VIEW EXPLODE (author) a AS MyT "
+ " lateral view explode (MyT.pid) p as MyP " + " LATERAL VIEW EXPLODE (MyT.pid) p AS MyP "
+ " where MyP.qualifier.classid = 'ORCID') tmp " + " WHERE MyP.qualifier.classid = 'ORCID') tmp "
+ " group by id) r_t " + " GROUP BY id) r_t "
+ " join (" + " JOIN ("
+ " select source, target " + " SELECT source, target "
+ " from relation " + " FROM relation "
+ " where datainfo.deletedbyinference = false " + " WHERE datainfo.deletedbyinference = false "
+ getConstraintList(" relclass = '", allowedsemrel) + getConstraintList(" relclass = '", allowedsemrel)
+ ") rel_rel " + " ) rel_rel "
+ " on source = id"; + " ON source = id";
spark spark
.sql(query) .sql(query)
.as(Encoders.bean(ResultOrcidList.class)) .as(Encoders.bean(ResultOrcidList.class))

View File

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

View File

@ -70,11 +70,10 @@ public class SparkOrcidToResultFromSemRelJob {
conf, conf,
isSparkSessionManaged, isSparkSessionManaged,
spark -> { spark -> {
if (isTest(parser)) { removeOutputDir(spark, outputPath);
removeOutputDir(spark, outputPath); if (saveGraph) {
}
if (saveGraph)
execPropagation(spark, possibleUpdates, inputPath, outputPath, resultClazz); execPropagation(spark, possibleUpdates, inputPath, outputPath, resultClazz);
}
}); });
} }
@ -132,16 +131,16 @@ public class SparkOrcidToResultFromSemRelJob {
private static boolean enrichAuthor(AutoritativeAuthor autoritative_author, Author author) { private static boolean enrichAuthor(AutoritativeAuthor autoritative_author, Author author) {
boolean toaddpid = false; boolean toaddpid = false;
if (StringUtils.isNoneEmpty(autoritative_author.getSurname())) { if (StringUtils.isNotEmpty(autoritative_author.getSurname())) {
if (StringUtils.isNoneEmpty(author.getSurname())) { if (StringUtils.isNotEmpty(author.getSurname())) {
if (autoritative_author if (autoritative_author
.getSurname() .getSurname()
.trim() .trim()
.equalsIgnoreCase(author.getSurname().trim())) { .equalsIgnoreCase(author.getSurname().trim())) {
// have the same surname. Check the name // have the same surname. Check the name
if (StringUtils.isNoneEmpty(autoritative_author.getName())) { if (StringUtils.isNotEmpty(autoritative_author.getName())) {
if (StringUtils.isNoneEmpty(author.getName())) { if (StringUtils.isNotEmpty(author.getName())) {
if (autoritative_author if (autoritative_author
.getName() .getName()
.trim() .trim()
@ -150,12 +149,14 @@ public class SparkOrcidToResultFromSemRelJob {
} }
// they could be differently written (i.e. only the initials of the name // they could be differently written (i.e. only the initials of the name
// in one of the two // in one of the two
if (autoritative_author else {
.getName() if (autoritative_author
.trim() .getName()
.substring(0, 0) .trim()
.equalsIgnoreCase(author.getName().trim().substring(0, 0))) { .substring(0, 0)
toaddpid = true; .equalsIgnoreCase(author.getName().trim().substring(0, 0))) {
toaddpid = true;
}
} }
} }
} }

View File

@ -21,6 +21,7 @@ import com.google.gson.Gson;
import eu.dnetlib.dhp.application.ArgumentApplicationParser; import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.countrypropagation.PrepareDatasourceCountryAssociation; import eu.dnetlib.dhp.countrypropagation.PrepareDatasourceCountryAssociation;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.Relation; import eu.dnetlib.dhp.schema.oaf.Relation;
public class PrepareProjectResultsAssociation { public class PrepareProjectResultsAssociation {
@ -60,6 +61,8 @@ public class PrepareProjectResultsAssociation {
conf, conf,
isSparkSessionManaged, isSparkSessionManaged,
spark -> { spark -> {
removeOutputDir(spark, potentialUpdatePath);
removeOutputDir(spark, alreadyLinkedPath);
prepareResultProjProjectResults( prepareResultProjProjectResults(
spark, spark,
inputPath, inputPath,
@ -83,7 +86,7 @@ public class PrepareProjectResultsAssociation {
+ " FROM relation " + " FROM relation "
+ " WHERE datainfo.deletedbyinference = false " + " WHERE datainfo.deletedbyinference = false "
+ " AND relClass = '" + " AND relClass = '"
+ RELATION_RESULT_PROJECT_REL_CLASS + ModelConstants.IS_PRODUCED_BY
+ "'"; + "'";
Dataset<Row> resproj_relation = spark.sql(resproj_relation_query); Dataset<Row> resproj_relation = spark.sql(resproj_relation_query);

View File

@ -20,6 +20,7 @@ import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.application.ArgumentApplicationParser; import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.countrypropagation.PrepareDatasourceCountryAssociation; import eu.dnetlib.dhp.countrypropagation.PrepareDatasourceCountryAssociation;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.Relation; import eu.dnetlib.dhp.schema.oaf.Relation;
import scala.Tuple2; import scala.Tuple2;
@ -122,9 +123,9 @@ public class SparkResultToProjectThroughSemRelJob {
getRelation( getRelation(
resId, resId,
projectId, projectId,
RELATION_RESULT_PROJECT_REL_CLASS, ModelConstants.IS_PRODUCED_BY,
RELATION_RESULTPROJECT_REL_TYPE, ModelConstants.RESULT_PROJECT,
RELATION_RESULTPROJECT_SUBREL_TYPE, ModelConstants.OUTCOME,
PROPAGATION_DATA_INFO_TYPE, PROPAGATION_DATA_INFO_TYPE,
PROPAGATION_RELATION_RESULT_PROJECT_SEM_REL_CLASS_ID, PROPAGATION_RELATION_RESULT_PROJECT_SEM_REL_CLASS_ID,
PROPAGATION_RELATION_RESULT_PROJECT_SEM_REL_CLASS_NAME)); PROPAGATION_RELATION_RESULT_PROJECT_SEM_REL_CLASS_NAME));
@ -133,9 +134,9 @@ public class SparkResultToProjectThroughSemRelJob {
getRelation( getRelation(
projectId, projectId,
resId, resId,
RELATION_PROJECT_RESULT_REL_CLASS, ModelConstants.PRODUCES,
RELATION_RESULTPROJECT_REL_TYPE, ModelConstants.RESULT_PROJECT,
RELATION_RESULTPROJECT_SUBREL_TYPE, ModelConstants.OUTCOME,
PROPAGATION_DATA_INFO_TYPE, PROPAGATION_DATA_INFO_TYPE,
PROPAGATION_RELATION_RESULT_PROJECT_SEM_REL_CLASS_ID, PROPAGATION_RELATION_RESULT_PROJECT_SEM_REL_CLASS_ID,
PROPAGATION_RELATION_RESULT_PROJECT_SEM_REL_CLASS_NAME)); PROPAGATION_RELATION_RESULT_PROJECT_SEM_REL_CLASS_NAME));

View File

@ -17,6 +17,7 @@ import com.fasterxml.jackson.databind.ObjectMapper;
import com.google.gson.Gson; import com.google.gson.Gson;
import eu.dnetlib.dhp.application.ArgumentApplicationParser; import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.Relation; import eu.dnetlib.dhp.schema.oaf.Relation;
public class PrepareResultCommunitySet { public class PrepareResultCommunitySet {
@ -55,9 +56,7 @@ public class PrepareResultCommunitySet {
conf, conf,
isSparkSessionManaged, isSparkSessionManaged,
spark -> { spark -> {
if (isTest(parser)) { removeOutputDir(spark, outputPath);
removeOutputDir(spark, outputPath);
}
prepareInfo(spark, inputPath, outputPath, organizationMap); prepareInfo(spark, inputPath, outputPath, organizationMap);
}); });
} }
@ -76,13 +75,13 @@ public class PrepareResultCommunitySet {
+ " FROM relation " + " FROM relation "
+ " WHERE datainfo.deletedbyinference = false " + " WHERE datainfo.deletedbyinference = false "
+ " AND relClass = '" + " AND relClass = '"
+ RELATION_RESULT_ORGANIZATION_REL_CLASS + ModelConstants.HAS_AUTHOR_INSTITUTION
+ "') result_organization " + "') result_organization "
+ "LEFT JOIN (SELECT source, collect_set(target) org_set " + "LEFT JOIN (SELECT source, collect_set(target) org_set "
+ " FROM relation " + " FROM relation "
+ " WHERE datainfo.deletedbyinference = false " + " WHERE datainfo.deletedbyinference = false "
+ " AND relClass = '" + " AND relClass = '"
+ RELATION_REPRESENTATIVERESULT_RESULT_CLASS + ModelConstants.MERGES
+ "' " + "' "
+ " GROUP BY source) organization_organization " + " GROUP BY source) organization_organization "
+ "ON result_organization.target = organization_organization.source "; + "ON result_organization.target = organization_organization.source ";

View File

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

View File

@ -53,9 +53,7 @@ public class PrepareResultCommunitySetStep2 {
conf, conf,
isSparkSessionManaged, isSparkSessionManaged,
spark -> { spark -> {
if (isTest(parser)) { removeOutputDir(spark, outputPath);
removeOutputDir(spark, outputPath);
}
mergeInfo(spark, inputPath, outputPath); mergeInfo(spark, inputPath, outputPath);
}); });
} }

View File

@ -17,6 +17,7 @@ import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.ObjectMapper; import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.application.ArgumentApplicationParser; import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.Datasource; import eu.dnetlib.dhp.schema.oaf.Datasource;
import eu.dnetlib.dhp.schema.oaf.Organization; import eu.dnetlib.dhp.schema.oaf.Organization;
import eu.dnetlib.dhp.schema.oaf.Relation; import eu.dnetlib.dhp.schema.oaf.Relation;
@ -58,30 +59,15 @@ public class PrepareResultInstRepoAssociation {
isSparkSessionManaged, isSparkSessionManaged,
spark -> { spark -> {
readNeededResources(spark, inputPath); readNeededResources(spark, inputPath);
removeOutputDir(spark, datasourceOrganizationPath);
prepareDatasourceOrganization(spark, datasourceOrganizationPath); prepareDatasourceOrganization(spark, datasourceOrganizationPath);
removeOutputDir(spark, alreadyLinkedPath);
prepareAlreadyLinkedAssociation(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) { private static void readNeededResources(SparkSession spark, String inputPath) {
Dataset<Datasource> datasource = readPath(spark, inputPath + "/datasource", Datasource.class); Dataset<Datasource> datasource = readPath(spark, inputPath + "/datasource", Datasource.class);
datasource.createOrReplaceTempView("datasource"); datasource.createOrReplaceTempView("datasource");
@ -106,7 +92,7 @@ public class PrepareResultInstRepoAssociation {
+ "JOIN ( SELECT source, target " + "JOIN ( SELECT source, target "
+ "FROM relation " + "FROM relation "
+ "WHERE relclass = '" + "WHERE relclass = '"
+ RELATION_DATASOURCE_ORGANIZATION_REL_CLASS + ModelConstants.IS_PROVIDED_BY
+ "' " + "' "
+ "AND datainfo.deletedbyinference = false ) rel " + "AND datainfo.deletedbyinference = false ) rel "
+ "ON d.id = rel.source "; + "ON d.id = rel.source ";
@ -119,4 +105,24 @@ public class PrepareResultInstRepoAssociation {
.option("compression", "gzip") .option("compression", "gzip")
.json(datasourceOrganizationPath); .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 = '"
+ ModelConstants.HAS_AUTHOR_INSTITUTION
+ "' "
+ "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

@ -19,6 +19,7 @@ import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.ObjectMapper; import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.application.ArgumentApplicationParser; import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.*; import eu.dnetlib.dhp.schema.oaf.*;
import scala.Tuple2; import scala.Tuple2;
@ -83,10 +84,8 @@ public class SparkResultToOrganizationFromIstRepoJob {
conf, conf,
isSparkSessionManaged, isSparkSessionManaged,
spark -> { spark -> {
if (isTest(parser)) { // removeOutputDir(spark, outputPath);
removeOutputDir(spark, outputPath); if (saveGraph) {
}
if (saveGraph)
execPropagation( execPropagation(
spark, spark,
datasourceorganization, datasourceorganization,
@ -94,6 +93,7 @@ public class SparkResultToOrganizationFromIstRepoJob {
inputPath, inputPath,
outputPath, outputPath,
resultClazz); resultClazz);
}
}); });
} }
@ -151,9 +151,9 @@ public class SparkResultToOrganizationFromIstRepoJob {
getRelation( getRelation(
orgId, orgId,
resultId, resultId,
RELATION_ORGANIZATION_RESULT_REL_CLASS, ModelConstants.IS_AUTHOR_INSTITUTION_OF,
RELATION_RESULTORGANIZATION_REL_TYPE, ModelConstants.RESULT_ORGANIZATION,
RELATION_RESULTORGANIZATION_SUBREL_TYPE, ModelConstants.AFFILIATION,
PROPAGATION_DATA_INFO_TYPE, PROPAGATION_DATA_INFO_TYPE,
PROPAGATION_RELATION_RESULT_ORGANIZATION_INST_REPO_CLASS_ID, PROPAGATION_RELATION_RESULT_ORGANIZATION_INST_REPO_CLASS_ID,
PROPAGATION_RELATION_RESULT_ORGANIZATION_INST_REPO_CLASS_NAME)); PROPAGATION_RELATION_RESULT_ORGANIZATION_INST_REPO_CLASS_NAME));
@ -162,9 +162,9 @@ public class SparkResultToOrganizationFromIstRepoJob {
getRelation( getRelation(
resultId, resultId,
orgId, orgId,
RELATION_RESULT_ORGANIZATION_REL_CLASS, ModelConstants.HAS_AUTHOR_INSTITUTION,
RELATION_RESULTORGANIZATION_REL_TYPE, ModelConstants.RESULT_ORGANIZATION,
RELATION_RESULTORGANIZATION_SUBREL_TYPE, ModelConstants.AFFILIATION,
PROPAGATION_DATA_INFO_TYPE, PROPAGATION_DATA_INFO_TYPE,
PROPAGATION_RELATION_RESULT_ORGANIZATION_INST_REPO_CLASS_ID, PROPAGATION_RELATION_RESULT_ORGANIZATION_INST_REPO_CLASS_ID,
PROPAGATION_RELATION_RESULT_ORGANIZATION_INST_REPO_CLASS_NAME)); PROPAGATION_RELATION_RESULT_ORGANIZATION_INST_REPO_CLASS_NAME));

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

@ -0,0 +1,79 @@
package eu.dnetlib.dhp.oa.graph.hive;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkHiveSession;
import static eu.dnetlib.dhp.schema.common.ModelSupport.tableIdentifier;
import java.util.Optional;
import org.apache.commons.io.IOUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.SaveMode;
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.schema.oaf.Oaf;
public class GraphHiveTableImporterJob {
private static final Logger log = LoggerFactory.getLogger(GraphHiveTableImporterJob.class);
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
public static void main(String[] args) throws Exception {
final ArgumentApplicationParser parser = new ArgumentApplicationParser(
IOUtils
.toString(
GraphHiveTableImporterJob.class
.getResourceAsStream(
"/eu/dnetlib/dhp/oa/graph/hive_table_importer_parameters.json")));
parser.parseArgument(args);
Boolean isSparkSessionManaged = Optional
.ofNullable(parser.get("isSparkSessionManaged"))
.map(Boolean::valueOf)
.orElse(Boolean.TRUE);
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
String inputPath = parser.get("inputPath");
log.info("inputPath: {}", inputPath);
String hiveDbName = parser.get("hiveDbName");
log.info("hiveDbName: {}", hiveDbName);
final String className = parser.get("className");
log.info("className: {}", className);
Class<? extends Oaf> clazz = (Class<? extends Oaf>) Class.forName(className);
String hiveMetastoreUris = parser.get("hiveMetastoreUris");
log.info("hiveMetastoreUris: {}", hiveMetastoreUris);
SparkConf conf = new SparkConf();
conf.set("hive.metastore.uris", hiveMetastoreUris);
runWithSparkHiveSession(
conf, isSparkSessionManaged, spark -> loadGraphTable(spark, inputPath, hiveDbName, clazz));
}
// protected for testing
private static <T extends Oaf> void loadGraphTable(SparkSession spark, String inputPath, String hiveDbName,
Class<T> clazz) {
spark
.read()
.textFile(inputPath)
.map((MapFunction<String, T>) s -> OBJECT_MAPPER.readValue(s, clazz), Encoders.bean(clazz))
.write()
.mode(SaveMode.Overwrite)
.saveAsTable(tableIdentifier(hiveDbName, clazz));
}
}

View File

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

View File

@ -50,8 +50,7 @@ import eu.dnetlib.dhp.schema.oaf.Result;
import eu.dnetlib.dhp.schema.oaf.Software; import eu.dnetlib.dhp.schema.oaf.Software;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty; import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
public class MigrateDbEntitiesApplication extends AbstractMigrationApplication public class MigrateDbEntitiesApplication extends AbstractMigrationApplication implements Closeable {
implements Closeable {
private static final Log log = LogFactory.getLog(MigrateDbEntitiesApplication.class); private static final Log log = LogFactory.getLog(MigrateDbEntitiesApplication.class);
@ -128,9 +127,7 @@ public class MigrateDbEntitiesApplication extends AbstractMigrationApplication
} }
public List<Oaf> processDatasource(final ResultSet rs) { public List<Oaf> processDatasource(final ResultSet rs) {
try { try {
final DataInfo info = prepareDataInfo(rs); final DataInfo info = prepareDataInfo(rs);
final Datasource ds = new Datasource(); final Datasource ds = new Datasource();
@ -194,7 +191,6 @@ public class MigrateDbEntitiesApplication extends AbstractMigrationApplication
public List<Oaf> processProject(final ResultSet rs) { public List<Oaf> processProject(final ResultSet rs) {
try { try {
final DataInfo info = prepareDataInfo(rs); final DataInfo info = prepareDataInfo(rs);
final Project p = new Project(); final Project p = new Project();
@ -249,9 +245,7 @@ public class MigrateDbEntitiesApplication extends AbstractMigrationApplication
} }
public List<Oaf> processOrganization(final ResultSet rs) { public List<Oaf> processOrganization(final ResultSet rs) {
try { try {
final DataInfo info = prepareDataInfo(rs); final DataInfo info = prepareDataInfo(rs);
final Organization o = new Organization(); final Organization o = new Organization();
@ -370,14 +364,12 @@ public class MigrateDbEntitiesApplication extends AbstractMigrationApplication
final DataInfo info = dataInfo( final DataInfo info = dataInfo(
false, null, false, false, false, null, false, false,
qualifier(USER_CLAIM, USER_CLAIM, DNET_PROVENANCE_ACTIONS, DNET_PROVENANCE_ACTIONS), "0.9"); qualifier(USER_CLAIM, USER_CLAIM, DNET_PROVENANCE_ACTIONS, DNET_PROVENANCE_ACTIONS), "0.9");
final List<KeyValue> collectedFrom = listKeyValues( final List<KeyValue> collectedFrom = listKeyValues(
createOpenaireId(10, "infrastruct_::openaire", true), "OpenAIRE"); createOpenaireId(10, "infrastruct_::openaire", true), "OpenAIRE");
try { try {
if (rs.getString(SOURCE_TYPE).equals("context")) { if (rs.getString(SOURCE_TYPE).equals("context")) {
final Result r; final Result r;
@ -461,9 +453,12 @@ public class MigrateDbEntitiesApplication extends AbstractMigrationApplication
final Boolean inferred = rs.getBoolean("inferred"); final Boolean inferred = rs.getBoolean("inferred");
final String trust = rs.getString("trust"); final String trust = rs.getString("trust");
return dataInfo( return dataInfo(
deletedbyinference,
deletedbyinference, inferenceprovenance, inferred, false, ENTITYREGISTRY_PROVENANCE_ACTION, trust); inferenceprovenance,
inferred,
false,
ENTITYREGISTRY_PROVENANCE_ACTION,
trust);
} }
private Qualifier prepareQualifierSplitting(final String s) { private Qualifier prepareQualifierSplitting(final String s) {
@ -535,4 +530,5 @@ public class MigrateDbEntitiesApplication extends AbstractMigrationApplication
super.close(); super.close();
dbClient.close(); dbClient.close();
} }
} }

View File

@ -1,8 +1,7 @@
package eu.dnetlib.dhp.oa.graph.raw; package eu.dnetlib.dhp.oa.graph.raw;
import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.createOpenaireId; import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.*;
import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.field;
import static eu.dnetlib.dhp.schema.common.ModelConstants.*; import static eu.dnetlib.dhp.schema.common.ModelConstants.*;
import java.util.*; import java.util.*;
@ -10,11 +9,13 @@ import java.util.stream.Collectors;
import org.apache.commons.lang3.StringUtils; import org.apache.commons.lang3.StringUtils;
import org.dom4j.Document; import org.dom4j.Document;
import org.dom4j.Element;
import org.dom4j.Node; import org.dom4j.Node;
import com.google.common.collect.Lists; import com.google.common.collect.Lists;
import eu.dnetlib.dhp.oa.graph.raw.common.PacePerson; import eu.dnetlib.dhp.oa.graph.raw.common.PacePerson;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.*; import eu.dnetlib.dhp.schema.oaf.*;
public class OafToOafMapper extends AbstractMdRecordToOafMapper { public class OafToOafMapper extends AbstractMdRecordToOafMapper {
@ -28,15 +29,26 @@ public class OafToOafMapper extends AbstractMdRecordToOafMapper {
final List<Author> res = new ArrayList<>(); final List<Author> res = new ArrayList<>();
int pos = 1; int pos = 1;
for (final Object o : doc.selectNodes("//dc:creator")) { for (final Object o : doc.selectNodes("//dc:creator")) {
final Node n = (Node) o; final Element e = (Element) o;
final Author author = new Author(); final Author author = new Author();
author.setFullname(n.getText()); author.setFullname(e.getText());
author.setRank(pos++); author.setRank(pos++);
final PacePerson p = new PacePerson(n.getText(), false); final PacePerson p = new PacePerson(e.getText(), false);
if (p.isAccurate()) { if (p.isAccurate()) {
author.setName(p.getNormalisedFirstName()); author.setName(p.getNormalisedFirstName());
author.setSurname(p.getNormalisedSurname()); author.setSurname(p.getNormalisedSurname());
} }
final String pid = e.attributeValue("nameIdentifier");
final String pidType = e.attributeValue("nameIdentifierScheme");
author.setPid(new ArrayList<>());
if (StringUtils.isNotBlank(pid) && StringUtils.isNotBlank(pidType)) {
author
.getPid()
.add(structuredProperty(pid, qualifier(pidType, pidType, DNET_PID_TYPES, DNET_PID_TYPES), info));
}
res.add(author); res.add(author);
} }
return res; return res;

View File

@ -12,6 +12,7 @@ import org.apache.commons.lang3.StringUtils;
import org.dom4j.Document; import org.dom4j.Document;
import org.dom4j.Node; import org.dom4j.Node;
import eu.dnetlib.dhp.oa.graph.raw.common.PacePerson;
import eu.dnetlib.dhp.schema.common.ModelConstants; import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.Author; import eu.dnetlib.dhp.schema.oaf.Author;
import eu.dnetlib.dhp.schema.oaf.DataInfo; import eu.dnetlib.dhp.schema.oaf.DataInfo;
@ -44,20 +45,35 @@ public class OdfToOafMapper extends AbstractMdRecordToOafMapper {
for (final Object o : doc.selectNodes("//datacite:creator")) { for (final Object o : doc.selectNodes("//datacite:creator")) {
final Node n = (Node) o; final Node n = (Node) o;
final Author author = new Author(); final Author author = new Author();
author.setFullname(n.valueOf("./datacite:creatorName")); final String fullname = n.valueOf("./datacite:creatorName");
author.setName(n.valueOf("./datacite:givenName")); author.setFullname(fullname);
author.setSurname(n.valueOf("./datacite:familyName"));
author.setAffiliation(prepareListFields(doc, "./datacite:affiliation", info)); PacePerson pp = new PacePerson(fullname, false);
author.setPid(preparePids(doc, info)); final String name = n.valueOf("./datacite:givenName");
if (StringUtils.isBlank(name) & pp.isAccurate()) {
author.setName(pp.getNormalisedFirstName());
} else {
author.setName(name);
}
final String surname = n.valueOf("./datacite:familyName");
if (StringUtils.isBlank(surname) & pp.isAccurate()) {
author.setSurname(pp.getNormalisedSurname());
} else {
author.setSurname(surname);
}
author.setAffiliation(prepareListFields(n, "./datacite:affiliation", info));
author.setPid(preparePids(n, info));
author.setRank(pos++); author.setRank(pos++);
res.add(author); res.add(author);
} }
return res; return res;
} }
private List<StructuredProperty> preparePids(final Document doc, final DataInfo info) { private List<StructuredProperty> preparePids(final Node n, final DataInfo info) {
final List<StructuredProperty> res = new ArrayList<>(); final List<StructuredProperty> res = new ArrayList<>();
for (final Object o : doc.selectNodes("./datacite:nameIdentifier")) { for (final Object o : n.selectNodes("./datacite:nameIdentifier")) {
res res
.add( .add(
structuredProperty( structuredProperty(
@ -77,8 +93,6 @@ public class OdfToOafMapper extends AbstractMdRecordToOafMapper {
final KeyValue hostedby) { final KeyValue hostedby) {
final Instance instance = new Instance(); final Instance instance = new Instance();
final Set<String> url = new HashSet<>();
instance.setUrl(new ArrayList<>());
instance instance
.setInstancetype( .setInstancetype(
prepareQualifier( prepareQualifier(
@ -97,6 +111,7 @@ public class OdfToOafMapper extends AbstractMdRecordToOafMapper {
.setProcessingchargecurrency( .setProcessingchargecurrency(
field(doc.valueOf("//oaf:processingchargeamount/@currency"), info)); field(doc.valueOf("//oaf:processingchargeamount/@currency"), info));
final Set<String> url = new HashSet<>();
for (final Object o : doc.selectNodes("//datacite:alternateIdentifier[@alternateIdentifierType='URL']")) { for (final Object o : doc.selectNodes("//datacite:alternateIdentifier[@alternateIdentifierType='URL']")) {
url.add(((Node) o).getText().trim()); url.add(((Node) o).getText().trim());
} }
@ -109,7 +124,10 @@ public class OdfToOafMapper extends AbstractMdRecordToOafMapper {
for (final Object o : doc.selectNodes("//datacite:identifier[@identifierType='DOI']")) { for (final Object o : doc.selectNodes("//datacite:identifier[@identifierType='DOI']")) {
url.add(HTTP_DX_DOI_PREIFX + ((Node) o).getText().trim()); url.add(HTTP_DX_DOI_PREIFX + ((Node) o).getText().trim());
} }
instance.getUrl().addAll(url); if (!url.isEmpty()) {
instance.setUrl(new ArrayList<>());
instance.getUrl().addAll(url);
}
return Arrays.asList(instance); return Arrays.asList(instance);
} }

View File

@ -1,7 +1,6 @@
package eu.dnetlib.dhp.oa.graph.raw.common; package eu.dnetlib.dhp.oa.graph.raw.common;
import java.nio.charset.Charset;
import java.nio.charset.StandardCharsets; import java.nio.charset.StandardCharsets;
import java.text.Normalizer; import java.text.Normalizer;
import java.util.HashSet; import java.util.HashSet;

View File

@ -0,0 +1,2 @@
DROP DATABASE IF EXISTS ${hiveDbName} CASCADE;
CREATE DATABASE ${hiveDbName};

View File

@ -72,18 +72,45 @@
</configuration> </configuration>
</global> </global>
<start to="MapGraphAsHiveDB"/> <start to="reset_DB"/>
<kill name="Kill"> <kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message> <message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill> </kill>
<action name="MapGraphAsHiveDB"> <action name="reset_DB">
<hive2 xmlns="uri:oozie:hive2-action:0.1">
<configuration>
<property>
<name>hive.metastore.uris</name>
<value>${hiveMetastoreUris}</value>
</property>
</configuration>
<jdbc-url>${hiveJdbcUrl}/${hiveDbName}</jdbc-url>
<script>lib/scripts/reset_db.sql</script>
<param>hiveDbName=${hiveDbName}</param>
</hive2>
<ok to="fork_import"/>
<error to="Kill"/>
</action>
<fork name="fork_import">
<path start="import_publication"/>
<path start="import_dataset"/>
<path start="import_orp"/>
<path start="import_software"/>
<path start="import_datasource"/>
<path start="import_organization"/>
<path start="import_project"/>
<path start="import_relation"/>
</fork>
<action name="import_publication">
<spark xmlns="uri:oozie:spark-action:0.2"> <spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master> <master>yarn</master>
<mode>cluster</mode> <mode>cluster</mode>
<name>MapGraphAsHiveDB</name> <name>Import table publication</name>
<class>eu.dnetlib.dhp.oa.graph.hive.GraphHiveImporterJob</class> <class>eu.dnetlib.dhp.oa.graph.hive.GraphHiveTableImporterJob</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar> <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts> <spark-opts>
--executor-memory=${sparkExecutorMemory} --executor-memory=${sparkExecutorMemory}
@ -95,18 +122,201 @@
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir} --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts> </spark-opts>
<arg>--inputPath</arg><arg>${inputPath}</arg> <arg>--inputPath</arg><arg>${inputPath}/publication</arg>
<arg>--hiveDbName</arg><arg>${hiveDbName}</arg> <arg>--hiveDbName</arg><arg>${hiveDbName}</arg>
<arg>--className</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
<arg>--hiveMetastoreUris</arg><arg>${hiveMetastoreUris}</arg> <arg>--hiveMetastoreUris</arg><arg>${hiveMetastoreUris}</arg>
</spark> </spark>
<ok to="PostProcessing"/> <ok to="join_import"/>
<error to="Kill"/> <error to="Kill"/>
</action> </action>
<action name="import_dataset">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Import table dataset</name>
<class>eu.dnetlib.dhp.oa.graph.hive.GraphHiveTableImporterJob</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--inputPath</arg><arg>${inputPath}/dataset</arg>
<arg>--hiveDbName</arg><arg>${hiveDbName}</arg>
<arg>--className</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
<arg>--hiveMetastoreUris</arg><arg>${hiveMetastoreUris}</arg>
</spark>
<ok to="join_import"/>
<error to="Kill"/>
</action>
<action name="import_orp">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Import table otherresearchproduct</name>
<class>eu.dnetlib.dhp.oa.graph.hive.GraphHiveTableImporterJob</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--inputPath</arg><arg>${inputPath}/otherresearchproduct</arg>
<arg>--hiveDbName</arg><arg>${hiveDbName}</arg>
<arg>--className</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
<arg>--hiveMetastoreUris</arg><arg>${hiveMetastoreUris}</arg>
</spark>
<ok to="join_import"/>
<error to="Kill"/>
</action>
<action name="import_software">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Import table software</name>
<class>eu.dnetlib.dhp.oa.graph.hive.GraphHiveTableImporterJob</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--inputPath</arg><arg>${inputPath}/software</arg>
<arg>--hiveDbName</arg><arg>${hiveDbName}</arg>
<arg>--className</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
<arg>--hiveMetastoreUris</arg><arg>${hiveMetastoreUris}</arg>
</spark>
<ok to="join_import"/>
<error to="Kill"/>
</action>
<action name="import_datasource">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Import table datasource</name>
<class>eu.dnetlib.dhp.oa.graph.hive.GraphHiveTableImporterJob</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--inputPath</arg><arg>${inputPath}/datasource</arg>
<arg>--hiveDbName</arg><arg>${hiveDbName}</arg>
<arg>--className</arg><arg>eu.dnetlib.dhp.schema.oaf.Datasource</arg>
<arg>--hiveMetastoreUris</arg><arg>${hiveMetastoreUris}</arg>
</spark>
<ok to="join_import"/>
<error to="Kill"/>
</action>
<action name="import_organization">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Import table organization</name>
<class>eu.dnetlib.dhp.oa.graph.hive.GraphHiveTableImporterJob</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--inputPath</arg><arg>${inputPath}/organization</arg>
<arg>--hiveDbName</arg><arg>${hiveDbName}</arg>
<arg>--className</arg><arg>eu.dnetlib.dhp.schema.oaf.Organization</arg>
<arg>--hiveMetastoreUris</arg><arg>${hiveMetastoreUris}</arg>
</spark>
<ok to="join_import"/>
<error to="Kill"/>
</action>
<action name="import_project">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Import table project</name>
<class>eu.dnetlib.dhp.oa.graph.hive.GraphHiveTableImporterJob</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--inputPath</arg><arg>${inputPath}/project</arg>
<arg>--hiveDbName</arg><arg>${hiveDbName}</arg>
<arg>--className</arg><arg>eu.dnetlib.dhp.schema.oaf.Project</arg>
<arg>--hiveMetastoreUris</arg><arg>${hiveMetastoreUris}</arg>
</spark>
<ok to="join_import"/>
<error to="Kill"/>
</action>
<action name="import_relation">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Import table project</name>
<class>eu.dnetlib.dhp.oa.graph.hive.GraphHiveTableImporterJob</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--inputPath</arg><arg>${inputPath}/relation</arg>
<arg>--hiveDbName</arg><arg>${hiveDbName}</arg>
<arg>--className</arg><arg>eu.dnetlib.dhp.schema.oaf.Relation</arg>
<arg>--hiveMetastoreUris</arg><arg>${hiveMetastoreUris}</arg>
</spark>
<ok to="join_import"/>
<error to="Kill"/>
</action>
<join name="join_import" to="PostProcessing"/>
<action name="PostProcessing"> <action name="PostProcessing">
<hive2 xmlns="uri:oozie:hive2-action:0.1"> <hive2 xmlns="uri:oozie:hive2-action:0.1">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration> <configuration>
<property> <property>
<name>hive.metastore.uris</name> <name>hive.metastore.uris</name>
@ -122,4 +332,5 @@
</action> </action>
<end name="End"/> <end name="End"/>
</workflow-app> </workflow-app>

View File

@ -0,0 +1,26 @@
[
{
"paramName": "issm",
"paramLongName": "isSparkSessionManaged",
"paramDescription": "when true will stop SparkSession after job execution",
"paramRequired": false
},
{
"paramName": "in",
"paramLongName": "inputPath",
"paramDescription": "the path to the graph data dump to read",
"paramRequired": true
},
{
"paramName": "hmu",
"paramLongName": "hiveMetastoreUris",
"paramDescription": "the hive metastore uris",
"paramRequired": true
},
{
"paramName": "db",
"paramLongName": "hiveDbName",
"paramDescription": "the target hive database name",
"paramRequired": true
}
]

View File

@ -0,0 +1,32 @@
[
{
"paramName": "issm",
"paramLongName": "isSparkSessionManaged",
"paramDescription": "when true will stop SparkSession after job execution",
"paramRequired": false
},
{
"paramName": "in",
"paramLongName": "inputPath",
"paramDescription": "the path to the graph data dump to read",
"paramRequired": true
},
{
"paramName": "hmu",
"paramLongName": "hiveMetastoreUris",
"paramDescription": "the hive metastore uris",
"paramRequired": true
},
{
"paramName": "db",
"paramLongName": "hiveDbName",
"paramDescription": "the target hive database name",
"paramRequired": true
},
{
"paramName": "tn",
"paramLongName": "className",
"paramDescription": "the class modelling the target table",
"paramRequired": true
}
]

View File

@ -1,10 +0,0 @@
[
{"paramName":"is", "paramLongName":"isLookupUrl", "paramDescription": "URL of the isLookUp Service", "paramRequired": true},
{"paramName":"sn", "paramLongName":"sourceNameNode", "paramDescription": "nameNode of the source cluster", "paramRequired": true},
{"paramName":"tn", "paramLongName":"targetNameNode", "paramDescription": "namoNode of the target cluster", "paramRequired": true},
{"paramName":"w", "paramLongName":"workingDirectory", "paramDescription": "working directory", "paramRequired": true},
{"paramName":"nm", "paramLongName":"distcp_num_maps", "paramDescription": "maximum number of map tasks used in the distcp process", "paramRequired": true},
{"paramName":"mm", "paramLongName":"distcp_memory_mb", "paramDescription": "memory for distcp action copying actionsets from remote cluster", "paramRequired": true},
{"paramName":"tt", "paramLongName":"distcp_task_timeout", "paramDescription": "timeout for distcp copying actions from remote cluster", "paramRequired": true},
{"paramName":"tr", "paramLongName":"transform_only", "paramDescription": "activate tranform-only mode. Only apply transformation step", "paramRequired": true}
]

View File

@ -1,20 +0,0 @@
[
{
"paramName": "mt",
"paramLongName": "master",
"paramDescription": "should be local or yarn",
"paramRequired": true
},
{
"paramName": "is",
"paramLongName": "isLookupUrl",
"paramDescription": "URL of the isLookUp Service",
"paramRequired": true
},
{
"paramName": "i",
"paramLongName": "inputPaths",
"paramDescription": "URL of the isLookUp Service",
"paramRequired": true
}
]

View File

@ -10,6 +10,7 @@ import static org.mockito.Mockito.when;
import java.io.IOException; import java.io.IOException;
import java.util.List; import java.util.List;
import java.util.Map; import java.util.Map;
import java.util.Optional;
import org.apache.commons.io.IOUtils; import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.StringUtils; import org.apache.commons.lang3.StringUtils;
@ -19,11 +20,8 @@ import org.junit.jupiter.api.extension.ExtendWith;
import org.mockito.Mock; import org.mockito.Mock;
import org.mockito.junit.jupiter.MockitoExtension; import org.mockito.junit.jupiter.MockitoExtension;
import eu.dnetlib.dhp.schema.oaf.Dataset; import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.Oaf; import eu.dnetlib.dhp.schema.oaf.*;
import eu.dnetlib.dhp.schema.oaf.Publication;
import eu.dnetlib.dhp.schema.oaf.Relation;
import eu.dnetlib.dhp.schema.oaf.Software;
@ExtendWith(MockitoExtension.class) @ExtendWith(MockitoExtension.class)
public class MappersTest { public class MappersTest {
@ -54,7 +52,29 @@ public class MappersTest {
assertValidId(p.getId()); assertValidId(p.getId());
assertValidId(p.getCollectedfrom().get(0).getKey()); assertValidId(p.getCollectedfrom().get(0).getKey());
assertTrue(StringUtils.isNotBlank(p.getTitle().get(0).getValue())); assertTrue(StringUtils.isNotBlank(p.getTitle().get(0).getValue()));
assertTrue(p.getAuthor().size() > 0); assertTrue(p.getAuthor().size() > 0);
Optional<Author> author = p
.getAuthor()
.stream()
.filter(a -> a.getPid() != null && !a.getPid().isEmpty())
.findFirst();
assertTrue(author.isPresent());
StructuredProperty pid = author
.get()
.getPid()
.stream()
.findFirst()
.get();
assertEquals("0000-0001-6651-1178", pid.getValue());
assertEquals("ORCID", pid.getQualifier().getClassid());
assertEquals("ORCID", pid.getQualifier().getClassname());
assertEquals(ModelConstants.DNET_PID_TYPES, pid.getQualifier().getSchemeid());
assertEquals(ModelConstants.DNET_PID_TYPES, pid.getQualifier().getSchemename());
assertEquals("Votsi,Nefta", author.get().getFullname());
assertEquals("Votsi", author.get().getSurname());
assertEquals("Nefta", author.get().getName());
assertTrue(p.getSubject().size() > 0); assertTrue(p.getSubject().size() > 0);
assertTrue(StringUtils.isNotBlank(p.getJournal().getIssnOnline())); assertTrue(StringUtils.isNotBlank(p.getJournal().getIssnOnline()));
assertTrue(StringUtils.isNotBlank(p.getJournal().getName())); assertTrue(StringUtils.isNotBlank(p.getJournal().getName()));
@ -100,6 +120,38 @@ public class MappersTest {
assertValidId(d.getCollectedfrom().get(0).getKey()); assertValidId(d.getCollectedfrom().get(0).getKey());
assertTrue(StringUtils.isNotBlank(d.getTitle().get(0).getValue())); assertTrue(StringUtils.isNotBlank(d.getTitle().get(0).getValue()));
assertTrue(d.getAuthor().size() > 0); assertTrue(d.getAuthor().size() > 0);
Optional<Author> author = d
.getAuthor()
.stream()
.filter(a -> a.getPid() != null && !a.getPid().isEmpty())
.findFirst();
assertTrue(author.isPresent());
StructuredProperty pid = author
.get()
.getPid()
.stream()
.findFirst()
.get();
assertEquals("0000-0001-9074-1619", pid.getValue());
assertEquals("ORCID", pid.getQualifier().getClassid());
assertEquals("ORCID", pid.getQualifier().getClassname());
assertEquals(ModelConstants.DNET_PID_TYPES, pid.getQualifier().getSchemeid());
assertEquals(ModelConstants.DNET_PID_TYPES, pid.getQualifier().getSchemename());
assertEquals("Baracchini, Theo", author.get().getFullname());
assertEquals("Baracchini", author.get().getSurname());
assertEquals("Theo", author.get().getName());
assertEquals(1, author.get().getAffiliation().size());
Optional<Field<String>> opAff = author
.get()
.getAffiliation()
.stream()
.findFirst();
assertTrue(opAff.isPresent());
Field<String> affiliation = opAff.get();
assertEquals("ISTI-CNR", affiliation.getValue());
assertTrue(d.getSubject().size() > 0); assertTrue(d.getSubject().size() > 0);
assertTrue(d.getInstance().size() > 0); assertTrue(d.getInstance().size() > 0);
assertTrue(d.getContext().size() > 0); assertTrue(d.getContext().size() > 0);

View File

@ -19,7 +19,7 @@
<metadata xmlns="http://namespace.openaire.eu/"> <metadata xmlns="http://namespace.openaire.eu/">
<dc:title>Ecosystem Service capacity is higher in areas of multiple designation types</dc:title> <dc:title>Ecosystem Service capacity is higher in areas of multiple designation types</dc:title>
<dc:creator>Nikolaidou,Charitini</dc:creator> <dc:creator>Nikolaidou,Charitini</dc:creator>
<dc:creator>Votsi,Nefta</dc:creator> <dc:creator nameIdentifier="0000-0001-6651-1178" nameIdentifierScheme="ORCID">Votsi,Nefta</dc:creator>
<dc:creator>Sgardelis,Steanos</dc:creator> <dc:creator>Sgardelis,Steanos</dc:creator>
<dc:creator>Halley,John</dc:creator> <dc:creator>Halley,John</dc:creator>
<dc:creator>Pantis,John</dc:creator> <dc:creator>Pantis,John</dc:creator>

View File

@ -35,9 +35,10 @@
</creator> </creator>
<creator> <creator>
<creatorName>Baracchini, Theo</creatorName> <creatorName>Baracchini, Theo</creatorName>
<nameIdentifier nameIdentifierScheme="ORCID">0000-0001-9074-1619</nameIdentifier>
<givenName>Theo</givenName> <givenName>Theo</givenName>
<familyName>Baracchini</familyName> <familyName>Baracchini</familyName>
<affiliation>Physics of Aquatic Systems Laboratory (APHYS) Margaretha Kamprad Chair, ENAC, EPFL, Lausanne, 1015, Switzerland</affiliation> <affiliation>ISTI-CNR</affiliation>
</creator> </creator>
<creator> <creator>
<creatorName>Wüest, Alfred</creatorName> <creatorName>Wüest, Alfred</creatorName>