forked from D-Net/dnet-hadoop
62 lines
2.3 KiB
XML
62 lines
2.3 KiB
XML
<workflow-app name="Resolve Relation" xmlns="uri:oozie:workflow:0.5">
|
|
<parameters>
|
|
<property>
|
|
<name>entityPath</name>
|
|
<description>the path of deduplicate Entities</description>
|
|
</property>
|
|
<property>
|
|
<name>relationPath</name>
|
|
<description>the path of relation unresolved</description>
|
|
</property>
|
|
<property>
|
|
<name>targetPath</name>
|
|
<description>the path of relation unresolved</description>
|
|
</property>
|
|
|
|
</parameters>
|
|
|
|
<start to="DropRelFolder"/>
|
|
|
|
<kill name="Kill">
|
|
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
|
</kill>
|
|
|
|
|
|
<action name="DropRelFolder">
|
|
<fs>
|
|
<delete path='${targetPath}/relation'/>
|
|
<delete path='${targetPath}/relation_resolved'/>
|
|
<delete path='${targetPath}/resolvedSource'/>
|
|
<delete path='${targetPath}/resolvedPid'/>
|
|
|
|
</fs>
|
|
<ok to="ResolveRelations"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
<action name="ResolveRelations">
|
|
<spark xmlns="uri:oozie:spark-action:0.2">
|
|
<master>yarn</master>
|
|
<mode>cluster</mode>
|
|
<name>Resolve Relations in raw graph</name>
|
|
<class>eu.dnetlib.dhp.sx.graph.SparkResolveRelation</class>
|
|
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
|
|
<spark-opts>
|
|
--executor-memory=${sparkExecutorMemory}
|
|
--executor-cores=${sparkExecutorCores}
|
|
--driver-memory=${sparkDriverMemory}
|
|
--conf spark.extraListeners=${spark2ExtraListeners}
|
|
--conf spark.sql.shuffle.partitions=3000
|
|
--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>--relationPath</arg><arg>${relationPath}</arg>
|
|
<arg>--workingPath</arg><arg>${targetPath}</arg>
|
|
<arg>--entityPath</arg><arg>${entityPath}</arg>
|
|
</spark>
|
|
<ok to="End"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
<end name="End"/>
|
|
</workflow-app> |