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

91 lines
3.6 KiB
XML

<workflow-app name="OpenCitations Integration" xmlns="uri:oozie:workflow:0.5">
<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>${oozieActionShareLibForSpark2}</value>
</property>
</configuration>
</global>
<start to="resume_from"/>
<decision name="resume_from">
<switch>
<case to="download">${wf:conf('resumeFrom') eq 'DownloadDump'}</case>
<case to="extract">${wf:conf('resumeFrom') eq 'ExtractContent'}</case>
<default to="create_actionset"/> <!-- first action to be done when downloadDump is to be performed -->
</switch>
</decision>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="download">
<shell xmlns="uri:oozie:shell-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>mapred.job.queue.name</name>
<value>${queueName}</value>
</property>
</configuration>
<exec>download.sh</exec>
<argument>${filelist}</argument>
<argument>${workingPath}/Original</argument>
<env-var>HADOOP_USER_NAME=${wf:user()}</env-var>
<file>download.sh</file>
<capture-output/>
</shell>
<ok to="extract"/>
<error to="Kill"/>
</action>
<action name="extract">
<java>
<main-class>eu.dnetlib.dhp.actionmanager.opencitations.GetOpenCitationsRefs</main-class>
<arg>--hdfsNameNode</arg><arg>${nameNode}</arg>
<arg>--inputFile</arg><arg>${inputFile}</arg>
<arg>--workingPath</arg><arg>${workingPath}</arg>
</java>
<ok to="create_actionset"/>
<error to="Kill"/>
</action>
<action name="create_actionset">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Produces the AS for OC</name>
<class>eu.dnetlib.dhp.actionmanager.opencitations.CreateActionSetSparkJob</class>
<jar>dhp-aggregation-${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=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--inputPath</arg><arg>${workingPath}/COCI</arg>
<arg>--outputPath</arg><arg>${outputPath}</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>