dnet-hadoop/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/bulktag/oozie_app/workflow.xml

89 lines
3.0 KiB
XML

<workflow-app name="bulk_tagging" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>sourcePath</name>
<description>the source path</description>
</property>
<property>
<name>pathMap</name>
<description>the json path associated to each selection field</description>
</property>
<property>
<name>baseURL</name>
<description>The URL to access the community APIs</description>
</property>
<property>
<name>startFrom></name>
<value>undelete</value>
</property>
</parameters>
<global>
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>oozie.action.sharelib.for.spark</name>
<value>${oozieActionShareLibForSpark2}</value>
</property>
</configuration>
</global>
<start to="startFrom"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<decision name="startFrom">
<switch>
<case to="exec_bulktag">${wf:conf('startFrom') eq 'undelete'}</case>
<default to="reset_outputpath"/>
</switch>
</decision>
<action name="reset_outputpath">
<fs>
<delete path="${workingDir}"/>
<mkdir path="${workingDir}"/>
</fs>
<ok to="exec_bulktag"/>
<error to="Kill"/>
</action>
<action name="exec_bulktag">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>bulkTagging</name>
<class>eu.dnetlib.dhp.bulktag.SparkBulkTagJob</class>
<jar>dhp-enrichment-${projectVersion}.jar</jar>
<spark-opts>
--num-executors=${sparkExecutorNumber}
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.executor.memoryOverhead=${memoryOverhead}
--conf spark.sql.shuffle.partitions=${partitions}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/</arg>
<arg>--outputPath</arg><arg>${workingDir}/bulktag/</arg>
<arg>--pathMap</arg><arg>${pathMap}</arg>
<arg>--baseURL</arg><arg>${baseURL}</arg>
<arg>--nameNode</arg><arg>${nameNode}</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>