dnet-hadoop/dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/bipaffiliations/oozie_app/workflow.xml

123 lines
5.0 KiB
XML

<workflow-app name="BipAffiliations" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>crossrefInputPath</name>
<description>the path where to find the inferred affiliation relations from Crossref</description>
</property>
<property>
<name>pubmedInputPath</name>
<description>the path where to find the inferred affiliation relations from Pubmed</description>
</property>
<property>
<name>openapcInputPath</name>
<description>the path where to find the inferred affiliation relations from OpenAPC</description>
</property>
<property>
<name>dataciteInputPath</name>
<description>the path where to find the inferred affiliation relations from Datacite</description>
</property>
<property>
<name>outputPath</name>
<description>the path where to store the actionset</description>
</property>
<property>
<name>sparkDriverMemory</name>
<description>memory for driver process</description>
</property>
<property>
<name>sparkExecutorMemory</name>
<description>memory for individual executor</description>
</property>
<property>
<name>sparkExecutorCores</name>
<description>number of cores used by single executor</description>
</property>
<property>
<name>oozieActionShareLibForSpark2</name>
<description>oozie action sharelib for spark 2.*</description>
</property>
<property>
<name>spark2ExtraListeners</name>
<value>com.cloudera.spark.lineage.NavigatorAppListener</value>
<description>spark 2.* extra listeners classname</description>
</property>
<property>
<name>spark2SqlQueryExecutionListeners</name>
<value>com.cloudera.spark.lineage.NavigatorQueryListener</value>
<description>spark 2.* sql query execution listeners classname</description>
</property>
<property>
<name>spark2YarnHistoryServerAddress</name>
<description>spark 2.* yarn history server address</description>
</property>
<property>
<name>spark2EventLogDir</name>
<description>spark 2.* event log dir location</description>
</property>
</parameters>
<global>
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>mapreduce.job.queuename</name>
<value>${queueName}</value>
</property>
<property>
<name>oozie.launcher.mapred.job.queue.name</name>
<value>${oozieLauncherQueueName}</value>
</property>
<property>
<name>oozie.action.sharelib.for.spark</name>
<value>${oozieActionShareLibForSpark2}</value>
</property>
</configuration>
</global>
<start to="deleteoutputpath"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="deleteoutputpath">
<fs>
<delete path="${outputPath}"/>
<mkdir path="${outputPath}"/>
<delete path="${workingDir}"/>
<mkdir path="${workingDir}"/>
</fs>
<ok to="atomicactions"/>
<error to="Kill"/>
</action>
<action name="atomicactions">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Produces the atomic action with the inferred by BIP! affiliation relations (from Crossref and Pubmed)</name>
<class>eu.dnetlib.dhp.actionmanager.bipaffiliations.PrepareAffiliationRelations</class>
<jar>dhp-aggregation-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--crossrefInputPath</arg><arg>${crossrefInputPath}</arg>
<arg>--pubmedInputPath</arg><arg>${pubmedInputPath}</arg>
<arg>--openapcInputPath</arg><arg>${openapcInputPath}</arg>
<arg>--dataciteInputPath</arg><arg>${dataciteInputPath}</arg>
<arg>--outputPath</arg><arg>${outputPath}</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>