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

58 lines
2.3 KiB
XML

<workflow-app name="Download_Transform_Pubmed_Workflow" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>baselineWorkingPath</name>
<description>the Baseline Working Path</description>
</property>
<property>
<name>isLookupUrl</name>
<description>The IS lookUp service endopoint</description>
</property>
<property>
<name>targetPath</name>
<description>The target path</description>
</property>
<property>
<name>skipUpdate</name>
<value>false</value>
<description>The request block size</description>
</property>
</parameters>
<start to="ConvertDataset"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="ConvertDataset">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Convert Baseline to OAF Dataset</name>
<class>eu.dnetllib.dhp.sx.bio.ebi.SparkCreateBaselineDataFrame</class>
<jar>dhp-aggregation-${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>${baselineWorkingPath}</arg>
<arg>--targetPath</arg><arg>${targetPath}</arg>
<arg>--master</arg><arg>yarn</arg>
<arg>--isLookupUrl</arg><arg>${isLookupUrl}</arg>
<arg>--hdfsServerUri</arg><arg>${nameNode}</arg>
<arg>--skipUpdate</arg><arg>${skipUpdate}</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>