110 lines
5.1 KiB
XML
110 lines
5.1 KiB
XML
<workflow-app name="affiliation_from_semrel_propagation" xmlns="uri:oozie:workflow:0.5">
|
|
<parameters>
|
|
<property>
|
|
<name>sourcePath</name>
|
|
<description>the source path</description>
|
|
</property>
|
|
<!-- <property>-->
|
|
<!-- <name>outputPath</name>-->
|
|
<!-- <description>sets the outputPath</description>-->
|
|
<!-- </property>-->
|
|
</parameters>
|
|
|
|
<global>
|
|
<job-tracker>${jobTracker}</job-tracker>
|
|
<name-node>${nameNode}</name-node>
|
|
<configuration>
|
|
<property>
|
|
<name>oozie.action.sharelib.for.spark</name>
|
|
<value>${oozieActionShareLibForSpark2}</value>
|
|
</property>
|
|
</configuration>
|
|
</global>
|
|
|
|
<start to="prepare_info"/>
|
|
|
|
<kill name="Kill">
|
|
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
|
</kill>
|
|
|
|
<!-- <decision name="resume_from">-->
|
|
<!-- <switch>-->
|
|
<!-- <case to="prepare_info">${wf:conf('resumeFrom') eq 'PrepareInfo'}</case>-->
|
|
<!-- <default to="reset_outputpath"/> <!– first action to be done when downloadDump is to be performed –>-->
|
|
<!-- </switch>-->
|
|
<!-- </decision>-->
|
|
|
|
<!-- <action name="reset_outputpath">-->
|
|
<!-- <fs>-->
|
|
<!-- <delete path="${outputPath}"/>-->
|
|
<!-- <mkdir path="${outputPath}"/>-->
|
|
<!-- </fs>-->
|
|
<!-- <ok to="prepare_info"/>-->
|
|
<!-- <error to="Kill"/>-->
|
|
<!-- </action>-->
|
|
|
|
|
|
<action name="prepare_info">
|
|
<spark xmlns="uri:oozie:spark-action:0.2">
|
|
<master>yarn</master>
|
|
<mode>cluster</mode>
|
|
<name>PrepareResultOrganizationAssociation</name>
|
|
<class>eu.dnetlib.dhp.resulttoorganizationfromsemrel.PrepareInfo</class>
|
|
<jar>dhp-enrichment-${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}
|
|
</spark-opts>
|
|
<arg>--graphPath</arg><arg>${sourcePath}</arg>
|
|
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
|
|
<arg>--leavesPath</arg><arg>${workingDir}/affiliationSemanticRelation/preparedInfo/leavesPath</arg>
|
|
<arg>--childParentPath</arg><arg>${workingDir}/affiliationSemanticRelation/preparedInfo/childParentPath</arg>
|
|
<arg>--resultOrgPath</arg><arg>${workingDir}/affiliationSemanticRelation/preparedInfo/resultOrgPath</arg>
|
|
<arg>--relationPath</arg><arg>${workingDir}/affiliationSemanticRelation/preparedInfo/relation</arg>
|
|
</spark>
|
|
<ok to="apply_resulttoorganization_propagation"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
|
|
<action name="apply_resulttoorganization_propagation">
|
|
<spark xmlns="uri:oozie:spark-action:0.2">
|
|
<master>yarn</master>
|
|
<mode>cluster</mode>
|
|
<name>resultToOrganizationFromSemRel</name>
|
|
<class>eu.dnetlib.dhp.resulttoorganizationfromsemrel.SparkResultToOrganizationFromSemRel</class>
|
|
<jar>dhp-enrichment-${projectVersion}.jar</jar>
|
|
<spark-opts>
|
|
--executor-cores=${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}${spark2EventLogDir}
|
|
--conf spark.dynamicAllocation.enabled=true
|
|
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
|
|
--conf spark.sql.shuffle.partitions=3840
|
|
</spark-opts>
|
|
<arg>--relationPath</arg><arg>${workingDir}/affiliationSemanticRelation/preparedInfo/relation</arg>
|
|
<arg>--outputPath</arg><arg>${sourcePath}</arg>
|
|
<arg>--leavesPath</arg><arg>${workingDir}/affiliationSemanticRelation/preparedInfo/leavesPath</arg>
|
|
<arg>--childParentPath</arg><arg>${workingDir}/affiliationSemanticRelation/preparedInfo/childParentPath</arg>
|
|
<arg>--resultOrgPath</arg><arg>${workingDir}/affiliationSemanticRelation/preparedInfo/resultOrgPath</arg>
|
|
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
|
|
<arg>--workingDir</arg><arg>${workingDir}/affiliationSemanticRelation/working</arg>
|
|
<arg>--iterations</arg><arg>${iterations}</arg>
|
|
</spark>
|
|
<ok to="End"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
|
|
|
|
|
|
<end name="End"/>
|
|
|
|
</workflow-app> |