dnet-hadoop/dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/ror/oozie_app/workflow.xml

55 lines
2.0 KiB
XML

<workflow-app name="Update_ROR_action_set" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>rorJsonInputPath</name>
<description>the path of the json</description>
</property>
<property>
<name>rorActionSetPath</name>
<description>path where to store the action set</description>
</property>
</parameters>
<start to="deleteoutputpath"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="deleteoutputpath">
<fs>
<delete path="${rorActionSetPath}"/>
<mkdir path="${rorActionSetPath}"/>
<delete path="${workingDir}"/>
<mkdir path="${workingDir}"/>
</fs>
<ok to="processRorFile"/>
<error to="Kill"/>
</action>
<action name="processRorFile">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>ProcessRorFile</name>
<class>eu.dnetlib.dhp.actionmanager.ror.GenerateRorActionSetJob</class>
<jar>dhp-aggregation-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--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.shuffle.partitions=3840
</spark-opts>
<arg>--inputPath</arg><arg>${rorJsonInputPath}</arg>
<arg>--outputPath</arg><arg>${rorActionSetPath}</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>