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

64 lines
2.2 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>${oozieActionShareLibForSpark2}</value>
</property>
</configuration>
</global>
<start to="download"/>
<kill name="Kill">
<message>Action failed, error message[${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>${queueName}</value>
</property>
</configuration>
<exec>download.sh</exec>
<argument>${url}</argument>
<argument>${crossrefDumpPath}</argument>
<argument>${crossrefdumpfilename}</argument>
<argument>${crossrefdumptoken}</argument>
<env-var>HADOOP_USER_NAME=${wf:user()}</env-var>
<file>download.sh</file>
<capture-output/>
</shell>
<ok to="ImportCrossRef"/>
<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>${workingDir}/OpenCitations</arg>
</java>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>