dnet-hadoop/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/sx/pubmed/oozie_app/workflow.xml

41 lines
1.6 KiB
XML

<workflow-app name="Transform_Pubmed_Workflow" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>baselineWorkingPath</name>
<description>the Baseline Working Path</description>
</property>
</parameters>
<start to="ConvertDataset"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="ConvertDataset">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Convert Baseline to Dataset</name>
<class>eu.dnetlib.dhp.sx.ebi.SparkCreateBaselineDataFrame</class>
<jar>dhp-graph-mapper-${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>--workingPath</arg><arg>${baselineWorkingPath}</arg>
<arg>--master</arg><arg>yarn</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>