dnet-hadoop/dhp-workflows/dhp-doiboost/src/main/resources/eu/dnetlib/dhp/doiboost/orcid_updates_download/oozie_app/workflow.xml

64 lines
2.3 KiB
XML

<workflow-app name="Orcid Updates Download" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>workingPath</name>
<description>the working dir base path</description>
</property>
<property>
<name>token</name>
<description>access token</description>
</property>
<property>
<name>shell_cmd</name>
<value>wget -O /tmp/last_modified.csv.tar http://74804fb637bd8e2fba5b-e0a029c2f87486cddec3b416996a6057.r3.cf1.rackcdn.com/last_modified.csv.tar ; hdfs dfs -copyFromLocal /tmp/last_modified.csv.tar /data/orcid_activities_2020/last_modified.csv.tar ; rm -f /tmp/last_modified.csv.tar
</value>
<description>the shell command that downloads the lambda file from orcid containing last orcid update informations</description>
</property>
</parameters>
<start to="ResetWorkingPath"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="ResetWorkingPath">
<fs>
<delete path='${workingPath}/downloads'/>
<mkdir path='${workingPath}/downloads'/>
</fs>
<ok to="DownloadLambdaFile"/>
<error to="Kill"/>
</action>
<action name="DownloadLambdaFile">
<shell xmlns="uri:oozie:shell-action:0.1">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<exec>bash</exec>
<argument>-c</argument>
<argument>${shell_cmd}</argument>
<capture-output/>
</shell>
<ok to="End"/>
<error to="Kill"/>
</action>
<action name="DownloadOrcidData">
<java>
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<main-class>eu.dnetlib.doiboost.orcid.OrcidDownloader</main-class>
<arg>-d</arg><arg>${workingPathOrcid}/</arg>
<arg>-n</arg><arg>${nameNode}</arg>
<arg>-f</arg><arg>last_modified.csv</arg>
<arg>-o</arg><arg>download/</arg>
<arg>-t</arg><arg>${token}</arg>
</java>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>