implemented branch workflow to import datacite and crossref in scholexplorer

This commit is contained in:
Sandro La Bruzzo 2021-07-08 21:20:19 +02:00
parent 8a034e46e1
commit cd17e19044
5 changed files with 175 additions and 1 deletions

View File

@ -0,0 +1,46 @@
package eu.dnetlib.dhp.actionmanager.datacite
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup
import eu.dnetlib.dhp.schema.mdstore.MetadataRecord
import eu.dnetlib.dhp.schema.oaf.{Oaf, Result}
import eu.dnetlib.dhp.utils.ISLookupClientFactory
import org.apache.spark.SparkConf
import org.apache.spark.sql.{Dataset, Encoder, Encoders, SaveMode, SparkSession}
import org.slf4j.{Logger, LoggerFactory}
import scala.io.Source
object FilterCrossrefEntitiesSpark {
val log: Logger = LoggerFactory.getLogger(getClass.getClass)
def main(args: Array[String]): Unit = {
val conf = new SparkConf
val parser = new ArgumentApplicationParser(Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/dhp/actionmanager/datacite/filter_crossref_param.json")).mkString)
parser.parseArgument(args)
val master = parser.get("master")
val sourcePath = parser.get("sourcePath")
log.info("sourcePath: {}", sourcePath)
val targetPath = parser.get("targetPath")
log.info("targetPath: {}", targetPath)
val spark: SparkSession = SparkSession.builder().config(conf)
.appName(getClass.getSimpleName)
.master(master)
.getOrCreate()
implicit val oafEncoder: Encoder[Oaf] = Encoders.kryo[Oaf]
implicit val resEncoder: Encoder[Result] = Encoders.kryo[Result]
val d:Dataset[Oaf]= spark.read.load(sourcePath).as[Oaf]
d.filter(r => r.isInstanceOf[Result]).map(r => r.asInstanceOf[Result]).write.mode(SaveMode.Overwrite).save(targetPath)
}
}

View File

@ -0,0 +1,21 @@
[
{
"paramName": "s",
"paramLongName": "sourcePath",
"paramDescription": "the source mdstore path",
"paramRequired": true
},
{
"paramName": "t",
"paramLongName": "targetPath",
"paramDescription": "the target mdstore path",
"paramRequired": true
},
{
"paramName": "m",
"paramLongName": "master",
"paramDescription": "the master name",
"paramRequired": true
}
]

View File

@ -0,0 +1,23 @@
<configuration>
<property>
<name>jobTracker</name>
<value>yarnRM</value>
</property>
<property>
<name>nameNode</name>
<value>hdfs://nameservice1</value>
</property>
<property>
<name>oozie.use.system.libpath</name>
<value>true</value>
</property>
<property>
<name>oozie.action.sharelib.for.spark</name>
<value>spark2</value>
</property>
<property>
<name>oozie.launcher.mapreduce.user.classpath.first</name>
<value>true</value>
</property>
</configuration>

View File

@ -0,0 +1,84 @@
<workflow-app name="Generate_Datacite_and_Crossref_dump_for_Scholexplorer" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>datacitePath</name>
<description>the path of Datacite spark dataset</description>
</property>
<property>
<name>isLookupUrl</name>
<description>The IS lookUp service endopoint</description>
</property>
<property>
<name>crossrefPath</name>
<description>the path of Crossref spark dataset</description>
</property>
<property>
<name>targetPath</name>
<description>the path of Crossref spark dataset</description>
</property>
</parameters>
<start to="ImportDatacite"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="ImportDatacite">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>ImportDatacite</name>
<class>eu.dnetlib.dhp.actionmanager.datacite.GenerateDataciteDatasetSpark</class>
<jar>dhp-aggregation-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.sql.shuffle.partitions=3840
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${datacitePath}</arg>
<arg>--targetPath</arg><arg>${targetPath}/datacite_oaf</arg>
<arg>--isLookupUrl</arg><arg>${isLookupUrl}</arg>
<arg>--exportLinks</arg><arg>true</arg>
<arg>--master</arg><arg>yarn-cluster</arg>
</spark>
<ok to="FilterCrossrefEntities"/>
<error to="Kill"/>
</action>
<action name="FilterCrossrefEntities">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>FilterCrossrefEntities</name>
<class>eu.dnetlib.dhp.actionmanager.datacite.FilterCrossrefEntitiesSpark</class>
<jar>dhp-aggregation-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.sql.shuffle.partitions=3840
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${crossrefPath}</arg>
<arg>--targetPath</arg><arg>${targetPath}/crossref_oaf</arg>
<arg>--master</arg><arg>yarn-cluster</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>

View File

@ -10,7 +10,7 @@
</property>
</parameters>
<start to="CreateScholix"/>
<start to="ExtractEntities"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>