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

89 lines
3.6 KiB
XML

<workflow-app name="Index Scholexplorer Infospace" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>sourcePath</name>
<description>the sourcePath of the json RDDs</description>
</property>
<property>
<name>index</name>
<description>the index name</description>
</property>
<property>
<name>esCluster</name>
<description>the Index cluster</description>
</property>
</parameters>
<start to="DropAndCreateIndex"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="DropAndCreateIndex">
<java>
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<main-class>eu.dnetlib.dhp.sx.provision.DropAndCreateESIndex</main-class>
<arg>-i</arg><arg>${index}</arg>
<arg>-c</arg><arg>${esCluster}</arg>
</java>
<ok to="indexSummary"/>
<error to="Kill"/>
</action>
<action name="indexSummary">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Index summary</name>
<class>eu.dnetlib.dhp.sx.provision.SparkIndexCollectionOnES</class>
<jar>dhp-graph-provision-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--conf spark.dynamicAllocation.maxExecutors="8"
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--master</arg><arg>yarn</arg>
<arg>--sourcePath</arg><arg>${sourcePath}/summaries_json</arg>
<arg>--index</arg><arg>${index}_object</arg>
<arg>--idPath</arg><arg>id</arg>
<arg>--cluster</arg><arg>${esCluster}</arg>
</spark>
<ok to="indexScholix"/>
<error to="Kill"/>
</action>
<action name="indexScholix">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Index summary</name>
<class>eu.dnetlib.dhp.sx.provision.SparkIndexCollectionOnES</class>
<jar>dhp-graph-provision-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--conf spark.dynamicAllocation.maxExecutors="8"
--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>--master</arg><arg>yarn</arg>
<arg>--sourcePath</arg><arg>${sourcePath}/scholix_json</arg>
<arg>--index</arg><arg>${index}_scholix</arg>
<arg>--idPath</arg><arg>identifier</arg>
<arg>--cluster</arg><arg>${esCluster}</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>