WIP: using common definitions from ModelConstants
commit
879e8cc7ef
@ -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>
|
@ -0,0 +1,46 @@
|
||||
<workflow-app name="Datacite_to_ActionSet_Workflow" xmlns="uri:oozie:workflow:0.5">
|
||||
<parameters>
|
||||
<property>
|
||||
<name>sourcePath</name>
|
||||
<description>the working path of Datacite stores</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>outputPath</name>
|
||||
<description>the path of Datacite ActionSet</description>
|
||||
</property>
|
||||
</parameters>
|
||||
|
||||
<start to="ExportDataset"/>
|
||||
|
||||
<kill name="Kill">
|
||||
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
||||
</kill>
|
||||
|
||||
|
||||
<action name="ExportDataset">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn-cluster</master>
|
||||
<mode>cluster</mode>
|
||||
<name>ExportDataset</name>
|
||||
<class>eu.dnetlib.dhp.actionmanager.datacite.ExportActionSetJobNode</class>
|
||||
<jar>dhp-aggregation-${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>${sourcePath}</arg>
|
||||
<arg>--targetPath</arg><arg>${outputPath}</arg>
|
||||
<arg>--master</arg><arg>yarn-cluster</arg>
|
||||
</spark>
|
||||
<ok to="End"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<end name="End"/>
|
||||
</workflow-app>
|
@ -0,0 +1,35 @@
|
||||
package eu.dnetlib.dhp.actionmanager.datacite
|
||||
|
||||
import com.fasterxml.jackson.databind.ObjectMapper
|
||||
import eu.dnetlib.dhp.aggregation.AbstractVocabularyTest
|
||||
import eu.dnetlib.dhp.schema.oaf.Oaf
|
||||
import org.junit.jupiter.api.extension.ExtendWith
|
||||
import org.junit.jupiter.api.{BeforeEach, Test}
|
||||
import org.mockito.junit.jupiter.MockitoExtension
|
||||
|
||||
import scala.io.Source
|
||||
|
||||
@ExtendWith(Array(classOf[MockitoExtension]))
|
||||
class DataciteToOAFTest extends AbstractVocabularyTest{
|
||||
|
||||
|
||||
@BeforeEach
|
||||
def setUp() :Unit = {
|
||||
println("Called Method")
|
||||
super.setUpVocabulary()
|
||||
}
|
||||
|
||||
@Test
|
||||
def testMapping() :Unit = {
|
||||
val record =Source.fromInputStream(getClass.getResourceAsStream("record.json")).mkString
|
||||
|
||||
|
||||
|
||||
val mapper = new ObjectMapper()
|
||||
val res:List[Oaf] =DataciteToOAFTransformation.generateOAF(record, 0L,0L, vocabularies )
|
||||
println (mapper.writeValueAsString(res.head))
|
||||
|
||||
|
||||
}
|
||||
|
||||
}
|
File diff suppressed because one or more lines are too long
Loading…
Reference in New Issue