Merge branch 'beta' into dump
commit
e9157c67aa
@ -1,4 +1,4 @@
|
||||
package eu.dnetllib.dhp.sx.bio
|
||||
package eu.dnetlib.dhp.sx.bio
|
||||
|
||||
import eu.dnetlib.dhp.schema.common.ModelConstants
|
||||
import eu.dnetlib.dhp.schema.oaf.utils.{GraphCleaningFunctions, OafMapperUtils}
|
||||
@ -1,10 +1,10 @@
|
||||
package eu.dnetllib.dhp.sx.bio.ebi
|
||||
package eu.dnetlib.dhp.sx.bio.ebi
|
||||
|
||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser
|
||||
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup
|
||||
import eu.dnetlib.dhp.schema.oaf.Result
|
||||
import eu.dnetlib.dhp.sx.bio.pubmed.{PMArticle, PMAuthor, PMJournal, PMParser, PubMedToOaf}
|
||||
import eu.dnetlib.dhp.utils.ISLookupClientFactory
|
||||
import eu.dnetllib.dhp.sx.bio.pubmed.{PMArticle, PMAuthor, PMJournal, PMParser, PubMedToOaf}
|
||||
import org.apache.commons.io.IOUtils
|
||||
import org.apache.hadoop.conf.Configuration
|
||||
import org.apache.hadoop.fs.{FSDataOutputStream, FileSystem, Path}
|
||||
@ -1,8 +1,9 @@
|
||||
package eu.dnetllib.dhp.sx.bio.ebi
|
||||
package eu.dnetlib.dhp.sx.bio.ebi
|
||||
|
||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser
|
||||
import eu.dnetllib.dhp.sx.bio.BioDBToOAF.EBILinkItem
|
||||
import eu.dnetllib.dhp.sx.bio.pubmed.{PMArticle, PMAuthor, PMJournal}
|
||||
import eu.dnetlib.dhp.sx.bio.pubmed.{PMArticle, PMAuthor, PMJournal}
|
||||
import eu.dnetlib.dhp.sx.bio.BioDBToOAF.EBILinkItem
|
||||
import eu.dnetlib.dhp.sx.bio.pubmed.PMJournal
|
||||
import org.apache.commons.io.IOUtils
|
||||
import org.apache.http.client.config.RequestConfig
|
||||
import org.apache.http.client.methods.HttpGet
|
||||
@ -1,9 +1,10 @@
|
||||
package eu.dnetllib.dhp.sx.bio.ebi
|
||||
package eu.dnetlib.dhp.sx.bio.ebi
|
||||
|
||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser
|
||||
import eu.dnetlib.dhp.schema.oaf.Oaf
|
||||
import eu.dnetllib.dhp.sx.bio.BioDBToOAF
|
||||
import eu.dnetllib.dhp.sx.bio.BioDBToOAF.EBILinkItem
|
||||
import eu.dnetlib.dhp.sx.bio.BioDBToOAF
|
||||
import eu.dnetlib.dhp.sx.bio.BioDBToOAF.EBILinkItem
|
||||
import BioDBToOAF.EBILinkItem
|
||||
import org.apache.commons.io.IOUtils
|
||||
import org.apache.spark.SparkConf
|
||||
import org.apache.spark.sql._
|
||||
@ -1,5 +1,5 @@
|
||||
|
||||
package eu.dnetllib.dhp.sx.bio.pubmed;
|
||||
package eu.dnetlib.dhp.sx.bio.pubmed;
|
||||
|
||||
import java.io.Serializable;
|
||||
import java.util.ArrayList;
|
||||
@ -1,5 +1,5 @@
|
||||
|
||||
package eu.dnetllib.dhp.sx.bio.pubmed;
|
||||
package eu.dnetlib.dhp.sx.bio.pubmed;
|
||||
|
||||
import java.io.Serializable;
|
||||
|
||||
@ -1,5 +1,5 @@
|
||||
|
||||
package eu.dnetllib.dhp.sx.bio.pubmed;
|
||||
package eu.dnetlib.dhp.sx.bio.pubmed;
|
||||
|
||||
public class PMGrant {
|
||||
|
||||
@ -1,5 +1,5 @@
|
||||
|
||||
package eu.dnetllib.dhp.sx.bio.pubmed;
|
||||
package eu.dnetlib.dhp.sx.bio.pubmed;
|
||||
|
||||
import java.io.Serializable;
|
||||
|
||||
@ -1,4 +1,4 @@
|
||||
package eu.dnetllib.dhp.sx.bio.pubmed
|
||||
package eu.dnetlib.dhp.sx.bio.pubmed
|
||||
|
||||
import scala.xml.MetaData
|
||||
import scala.xml.pull.{EvElemEnd, EvElemStart, EvText, XMLEventReader}
|
||||
@ -1,5 +1,5 @@
|
||||
|
||||
package eu.dnetllib.dhp.sx.bio.pubmed;
|
||||
package eu.dnetlib.dhp.sx.bio.pubmed;
|
||||
|
||||
public class PMSubject {
|
||||
private String value;
|
||||
@ -1,4 +1,4 @@
|
||||
package eu.dnetllib.dhp.sx.bio.pubmed
|
||||
package eu.dnetlib.dhp.sx.bio.pubmed
|
||||
|
||||
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup
|
||||
import eu.dnetlib.dhp.schema.common.ModelConstants
|
||||
@ -0,0 +1,51 @@
|
||||
<workflow-app name="Transform_BioEntity_Workflow" xmlns="uri:oozie:workflow:0.5">
|
||||
<parameters>
|
||||
<property>
|
||||
<name>sourcePath</name>
|
||||
<description>the PDB Database Working Path</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>database</name>
|
||||
<description>the PDB Database Working Path</description>
|
||||
</property>
|
||||
|
||||
<property>
|
||||
<name>targetPath</name>
|
||||
<description>the Target Working dir path</description>
|
||||
</property>
|
||||
</parameters>
|
||||
|
||||
<start to="ConvertDB"/>
|
||||
|
||||
<kill name="Kill">
|
||||
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
||||
</kill>
|
||||
|
||||
<action name="ConvertDB">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Convert Bio DB to OAF Dataset</name>
|
||||
<class>eu.dnetlib.dhp.sx.bio.SparkTransformBioDatabaseToOAF</class>
|
||||
<jar>dhp-aggregation-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--executor-memory=${sparkExecutorMemory}
|
||||
--executor-cores=${sparkExecutorCores}
|
||||
--driver-memory=${sparkDriverMemory}
|
||||
--conf spark.extraListeners=${spark2ExtraListeners}
|
||||
--conf spark.sql.shuffle.partitions=2000
|
||||
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
||||
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||||
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
||||
</spark-opts>
|
||||
<arg>--master</arg><arg>yarn</arg>
|
||||
<arg>--dbPath</arg><arg>${sourcePath}</arg>
|
||||
<arg>--database</arg><arg>${database}</arg>
|
||||
<arg>--targetPath</arg><arg>${targetPath}</arg>
|
||||
</spark>
|
||||
<ok to="End"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
<end name="End"/>
|
||||
|
||||
</workflow-app>
|
||||
@ -1,10 +1,10 @@
|
||||
package eu.dnetllib.dhp.sx.bio
|
||||
package eu.dnetlib.dhp.sx.bio
|
||||
|
||||
import com.fasterxml.jackson.databind.{DeserializationFeature, ObjectMapper, SerializationFeature}
|
||||
import eu.dnetlib.dhp.aggregation.AbstractVocabularyTest
|
||||
import eu.dnetlib.dhp.schema.oaf.{Oaf, Relation, Result}
|
||||
import eu.dnetllib.dhp.sx.bio.BioDBToOAF.ScholixResolved
|
||||
import eu.dnetllib.dhp.sx.bio.pubmed.{PMArticle, PMParser, PubMedToOaf}
|
||||
import eu.dnetlib.dhp.sx.bio.BioDBToOAF.ScholixResolved
|
||||
import eu.dnetlib.dhp.sx.bio.pubmed.{PMArticle, PMParser, PubMedToOaf}
|
||||
import org.json4s.DefaultFormats
|
||||
import org.json4s.JsonAST.{JField, JObject, JString}
|
||||
import org.json4s.jackson.JsonMethods.parse
|
||||
@ -0,0 +1,134 @@
|
||||
|
||||
package eu.dnetlib.dhp.oa.graph.raw;
|
||||
|
||||
import com.clearspring.analytics.util.Lists;
|
||||
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
||||
import eu.dnetlib.dhp.common.HdfsSupport;
|
||||
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup;
|
||||
import eu.dnetlib.dhp.oa.graph.raw.common.AbstractMigrationApplication;
|
||||
import eu.dnetlib.dhp.schema.common.EntityType;
|
||||
import eu.dnetlib.dhp.schema.common.ModelSupport;
|
||||
import eu.dnetlib.dhp.schema.oaf.Oaf;
|
||||
import eu.dnetlib.dhp.schema.oaf.Relation;
|
||||
import eu.dnetlib.dhp.utils.ISLookupClientFactory;
|
||||
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
|
||||
import org.apache.commons.io.IOUtils;
|
||||
import org.apache.spark.SparkConf;
|
||||
import org.apache.spark.api.java.JavaSparkContext;
|
||||
import org.apache.spark.api.java.function.FilterFunction;
|
||||
import org.apache.spark.api.java.function.FlatMapFunction;
|
||||
import org.apache.spark.api.java.function.MapFunction;
|
||||
import org.apache.spark.sql.Dataset;
|
||||
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 java.util.*;
|
||||
|
||||
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
|
||||
|
||||
public class CopyHdfsOafApplication extends AbstractMigrationApplication {
|
||||
|
||||
private static final Logger log = LoggerFactory.getLogger(CopyHdfsOafApplication.class);
|
||||
|
||||
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
|
||||
|
||||
public static void main(final String[] args) throws Exception {
|
||||
final ArgumentApplicationParser parser = new ArgumentApplicationParser(
|
||||
IOUtils
|
||||
.toString(
|
||||
CopyHdfsOafApplication.class
|
||||
.getResourceAsStream("/eu/dnetlib/dhp/oa/graph/copy_hdfs_oaf_parameters.json")));
|
||||
parser.parseArgument(args);
|
||||
|
||||
final Boolean isSparkSessionManaged = Optional
|
||||
.ofNullable(parser.get("isSparkSessionManaged"))
|
||||
.map(Boolean::valueOf)
|
||||
.orElse(Boolean.TRUE);
|
||||
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
|
||||
|
||||
final String mdstoreManagerUrl = parser.get("mdstoreManagerUrl");
|
||||
log.info("mdstoreManagerUrl: {}", mdstoreManagerUrl);
|
||||
|
||||
final String mdFormat = parser.get("mdFormat");
|
||||
log.info("mdFormat: {}", mdFormat);
|
||||
|
||||
final String mdLayout = parser.get("mdLayout");
|
||||
log.info("mdLayout: {}", mdLayout);
|
||||
|
||||
final String mdInterpretation = parser.get("mdInterpretation");
|
||||
log.info("mdInterpretation: {}", mdInterpretation);
|
||||
|
||||
final String hdfsPath = parser.get("hdfsPath");
|
||||
log.info("hdfsPath: {}", hdfsPath);
|
||||
|
||||
final String isLookupUrl = parser.get("isLookupUrl");
|
||||
log.info("isLookupUrl: {}", isLookupUrl);
|
||||
|
||||
final ISLookUpService isLookupService = ISLookupClientFactory.getLookUpService(isLookupUrl);
|
||||
final VocabularyGroup vocs = VocabularyGroup.loadVocsFromIS(isLookupService);
|
||||
|
||||
final Set<String> paths = mdstorePaths(mdstoreManagerUrl, mdFormat, mdLayout, mdInterpretation);
|
||||
|
||||
final SparkConf conf = new SparkConf();
|
||||
runWithSparkSession(conf, isSparkSessionManaged, spark -> processPaths(spark, vocs, hdfsPath, paths));
|
||||
}
|
||||
|
||||
public static void processPaths(final SparkSession spark,
|
||||
final VocabularyGroup vocs,
|
||||
final String outputPath,
|
||||
final Set<String> paths) {
|
||||
|
||||
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
|
||||
|
||||
log.info("Found {} mdstores", paths.size());
|
||||
paths.forEach(log::info);
|
||||
|
||||
final String[] validPaths = paths
|
||||
.stream()
|
||||
.filter(p -> HdfsSupport.exists(p, sc.hadoopConfiguration()))
|
||||
.toArray(String[]::new);
|
||||
log.info("Non empty mdstores {}", validPaths.length);
|
||||
|
||||
if (validPaths.length > 0) {
|
||||
// load the dataset
|
||||
Dataset<Oaf> oaf = spark
|
||||
.read()
|
||||
.load(validPaths)
|
||||
.as(Encoders.kryo(Oaf.class));
|
||||
|
||||
// dispatch each entity type individually in the respective graph subdirectory in append mode
|
||||
for(Map.Entry<String, Class> e : ModelSupport.oafTypes.entrySet()) {
|
||||
oaf
|
||||
.filter((FilterFunction<Oaf>) o -> o.getClass().getSimpleName().toLowerCase().equals(e.getKey()))
|
||||
.map((MapFunction<Oaf, String>) OBJECT_MAPPER::writeValueAsString, Encoders.bean(e.getValue()))
|
||||
.write()
|
||||
.option("compression", "gzip")
|
||||
.mode(SaveMode.Append)
|
||||
.text(outputPath + "/" + e.getKey());
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
private static Relation getInverse(Relation rel, VocabularyGroup vocs) {
|
||||
final Relation inverse = new Relation();
|
||||
|
||||
inverse.setProperties(rel.getProperties());
|
||||
inverse.setValidated(rel.getValidated());
|
||||
inverse.setValidationDate(rel.getValidationDate());
|
||||
inverse.setCollectedfrom(rel.getCollectedfrom());
|
||||
inverse.setDataInfo(rel.getDataInfo());
|
||||
inverse.setLastupdatetimestamp(rel.getLastupdatetimestamp());
|
||||
|
||||
inverse.setSource(rel.getTarget());
|
||||
inverse.setTarget(rel.getSource());
|
||||
inverse.setRelType(rel.getRelType());
|
||||
inverse.setSubRelType(rel.getSubRelType());
|
||||
|
||||
return inverse;
|
||||
}
|
||||
|
||||
}
|
||||
@ -0,0 +1,38 @@
|
||||
[
|
||||
{
|
||||
"paramName": "p",
|
||||
"paramLongName": "hdfsPath",
|
||||
"paramDescription": "the path where storing the sequential file",
|
||||
"paramRequired": true
|
||||
},
|
||||
{
|
||||
"paramName": "u",
|
||||
"paramLongName": "mdstoreManagerUrl",
|
||||
"paramDescription": "the MdstoreManager url",
|
||||
"paramRequired": true
|
||||
},
|
||||
{
|
||||
"paramName": "f",
|
||||
"paramLongName": "mdFormat",
|
||||
"paramDescription": "metadata format",
|
||||
"paramRequired": true
|
||||
},
|
||||
{
|
||||
"paramName": "l",
|
||||
"paramLongName": "mdLayout",
|
||||
"paramDescription": "metadata layout",
|
||||
"paramRequired": true
|
||||
},
|
||||
{
|
||||
"paramName": "i",
|
||||
"paramLongName": "mdInterpretation",
|
||||
"paramDescription": "metadata interpretation",
|
||||
"paramRequired": true
|
||||
},
|
||||
{
|
||||
"paramName": "isu",
|
||||
"paramLongName": "isLookupUrl",
|
||||
"paramDescription": "the url of the ISLookupService",
|
||||
"paramRequired": true
|
||||
}
|
||||
]
|
||||
@ -1,177 +0,0 @@
|
||||
<workflow-app name="Transform_BioEntity_Workflow" xmlns="uri:oozie:workflow:0.5">
|
||||
<parameters>
|
||||
<property>
|
||||
<name>PDBPath</name>
|
||||
<description>the PDB Database Working Path</description>
|
||||
</property>
|
||||
|
||||
<property>
|
||||
<name>UNIPROTDBPath</name>
|
||||
<description>the UNIPROT Database Working Path</description>
|
||||
</property>
|
||||
|
||||
<property>
|
||||
<name>EBIDataset</name>
|
||||
<description>the EBI Links Dataset Path</description>
|
||||
</property>
|
||||
|
||||
<property>
|
||||
<name>ScholixResolvedDBPath</name>
|
||||
<description>the Scholix Resolved Dataset Path</description>
|
||||
</property>
|
||||
|
||||
<property>
|
||||
<name>CrossrefLinksPath</name>
|
||||
<description>the CrossrefLinks Path</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>targetPath</name>
|
||||
<description>the Target Working dir path</description>
|
||||
</property>
|
||||
</parameters>
|
||||
|
||||
<start to="ConvertPDB"/>
|
||||
|
||||
<kill name="Kill">
|
||||
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
||||
</kill>
|
||||
|
||||
<action name="ConvertPDB">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Convert PDB to OAF Dataset</name>
|
||||
<class>eu.dnetlib.dhp.sx.graph.bio.SparkTransformBioDatabaseToOAF</class>
|
||||
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--executor-memory=${sparkExecutorMemory}
|
||||
--executor-cores=${sparkExecutorCores}
|
||||
--driver-memory=${sparkDriverMemory}
|
||||
--conf spark.extraListeners=${spark2ExtraListeners}
|
||||
--conf spark.sql.shuffle.partitions=2000
|
||||
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
||||
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||||
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
||||
</spark-opts>
|
||||
<arg>--master</arg><arg>yarn</arg>
|
||||
<arg>--dbPath</arg><arg>${PDBPath}</arg>
|
||||
<arg>--database</arg><arg>PDB</arg>
|
||||
<arg>--targetPath</arg><arg>${targetPath}/pdb_OAF</arg>
|
||||
</spark>
|
||||
<ok to="ConvertUNIPROT"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
|
||||
<action name="ConvertUNIPROT">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Convert UNIPROT to OAF Dataset</name>
|
||||
<class>eu.dnetlib.dhp.sx.graph.bio.SparkTransformBioDatabaseToOAF</class>
|
||||
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--executor-memory=${sparkExecutorMemory}
|
||||
--executor-cores=${sparkExecutorCores}
|
||||
--driver-memory=${sparkDriverMemory}
|
||||
--conf spark.extraListeners=${spark2ExtraListeners}
|
||||
--conf spark.sql.shuffle.partitions=2000
|
||||
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
||||
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||||
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
||||
</spark-opts>
|
||||
<arg>--master</arg><arg>yarn</arg>
|
||||
<arg>--dbPath</arg><arg>${UNIPROTDBPath}</arg>
|
||||
<arg>--database</arg><arg>UNIPROT</arg>
|
||||
<arg>--targetPath</arg><arg>${targetPath}/uniprot_OAF</arg>
|
||||
</spark>
|
||||
<ok to="ConvertEBILinks"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
|
||||
<action name="ConvertEBILinks">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Convert EBI Links to OAF Dataset</name>
|
||||
<class>eu.dnetlib.dhp.sx.graph.ebi.SparkEBILinksToOaf</class>
|
||||
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--executor-memory=${sparkExecutorMemory}
|
||||
--executor-cores=${sparkExecutorCores}
|
||||
--driver-memory=${sparkDriverMemory}
|
||||
--conf spark.extraListeners=${spark2ExtraListeners}
|
||||
--conf spark.sql.shuffle.partitions=2000
|
||||
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
||||
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||||
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
||||
</spark-opts>
|
||||
<arg>--master</arg><arg>yarn</arg>
|
||||
<arg>--sourcePath</arg><arg>${EBIDataset}</arg>
|
||||
<arg>--targetPath</arg><arg>${targetPath}/ebi_OAF</arg>
|
||||
</spark>
|
||||
<ok to="ConvertScholixResolved"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
|
||||
<action name="ConvertScholixResolved">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Convert Scholix to OAF Dataset</name>
|
||||
<class>eu.dnetlib.dhp.sx.graph.bio.SparkTransformBioDatabaseToOAF</class>
|
||||
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--executor-memory=${sparkExecutorMemory}
|
||||
--executor-cores=${sparkExecutorCores}
|
||||
--driver-memory=${sparkDriverMemory}
|
||||
--conf spark.extraListeners=${spark2ExtraListeners}
|
||||
--conf spark.sql.shuffle.partitions=2000
|
||||
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
||||
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||||
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
||||
</spark-opts>
|
||||
<arg>--master</arg><arg>yarn</arg>
|
||||
<arg>--dbPath</arg><arg>${ScholixResolvedDBPath}</arg>
|
||||
<arg>--database</arg><arg>SCHOLIX</arg>
|
||||
<arg>--targetPath</arg><arg>${targetPath}/scholix_resolved_OAF</arg>
|
||||
</spark>
|
||||
<ok to="ConvertCrossrefLinks"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
|
||||
<action name="ConvertCrossrefLinks">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Convert Crossref Links to OAF Dataset</name>
|
||||
<class>eu.dnetlib.dhp.sx.graph.bio.SparkTransformBioDatabaseToOAF</class>
|
||||
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--executor-memory=${sparkExecutorMemory}
|
||||
--executor-cores=${sparkExecutorCores}
|
||||
--driver-memory=${sparkDriverMemory}
|
||||
--conf spark.extraListeners=${spark2ExtraListeners}
|
||||
--conf spark.sql.shuffle.partitions=2000
|
||||
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
||||
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||||
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
||||
</spark-opts>
|
||||
<arg>--master</arg><arg>yarn</arg>
|
||||
<arg>--dbPath</arg><arg>${CrossrefLinksPath}</arg>
|
||||
<arg>--database</arg><arg>CROSSREF_LINKS</arg>
|
||||
<arg>--targetPath</arg><arg>${targetPath}/crossref_unresolved_relation_OAF</arg>
|
||||
</spark>
|
||||
<ok to="End"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
|
||||
|
||||
|
||||
<end name="End"/>
|
||||
|
||||
</workflow-app>
|
||||
Loading…
Reference in New Issue