85 lines
3.2 KiB
XML
85 lines
3.2 KiB
XML
<workflow-app name="Create Raw Graph Step 1: extract Entities in raw graph" xmlns="uri:oozie:workflow:0.5">
|
|
<parameters>
|
|
<property>
|
|
<name>sourcePath</name>
|
|
<description>the working dir base path</description>
|
|
</property>
|
|
<property>
|
|
<name>targetPath</name>
|
|
<description>the graph Raw base path</description>
|
|
</property>
|
|
</parameters>
|
|
|
|
<start to="ExtractEntities"/>
|
|
|
|
<kill name="Kill">
|
|
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
|
</kill>
|
|
|
|
<action name="ExtractEntities">
|
|
<spark xmlns="uri:oozie:spark-action:0.2">
|
|
<master>yarn</master>
|
|
<mode>cluster</mode>
|
|
<name>Extract entities in raw graph</name>
|
|
<class>eu.dnetlib.dhp.sx.graph.SparkCreateInputGraph</class>
|
|
<jar>dhp-graph-mapper-${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>--master</arg><arg>yarn</arg>
|
|
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
|
|
<arg>--targetPath</arg><arg>${targetPath}</arg>
|
|
</spark>
|
|
<ok to="DropDedupPath"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
|
|
<action name="DropDedupPath">
|
|
<fs>
|
|
<delete path='${targetPath}/dedup'/>
|
|
<mkdir path='${targetPath}/dedup/'/>
|
|
</fs>
|
|
<ok to="GenerateInputGraphForDedup"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
|
|
<action name="GenerateInputGraphForDedup">
|
|
<spark xmlns="uri:oozie:spark-action:0.2">
|
|
<master>yarn</master>
|
|
<mode>cluster</mode>
|
|
<name>Generate Input Graph for deduplication</name>
|
|
<class>eu.dnetlib.dhp.sx.graph.SparkConvertDatasetToJsonRDD</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}${spark2EventLogDir}
|
|
</spark-opts>
|
|
<arg>--master</arg><arg>yarn</arg>
|
|
<arg>--sourcePath</arg><arg>${targetPath}/preprocess</arg>
|
|
<arg>--targetPath</arg><arg>${targetPath}/dedup</arg>
|
|
</spark>
|
|
<ok to="End"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<end name="End"/>
|
|
</workflow-app> |