forked from D-Net/dnet-hadoop
40 lines
1.3 KiB
XML
40 lines
1.3 KiB
XML
|
<workflow-app name="Extract Orcid XML Authors From Summaries" xmlns="uri:oozie:workflow:0.5">
|
||
|
<parameters>
|
||
|
<property>
|
||
|
<name>workingPath</name>
|
||
|
<description>the working dir base path</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}/xml/authors'/>
|
||
|
<mkdir path='${workingPath}/xml/authors'/>
|
||
|
</fs>
|
||
|
<ok to="ExtractXMLAuthorsSummaries"/>
|
||
|
<error to="Kill"/>
|
||
|
</action>
|
||
|
|
||
|
<action name="ExtractXMLAuthorsSummaries">
|
||
|
<java>
|
||
|
<job-tracker>${jobTracker}</job-tracker>
|
||
|
<name-node>${nameNode}</name-node>
|
||
|
<main-class>eu.dnetlib.doiboost.orcid.ExtractXMLSummariesData</main-class>
|
||
|
<arg>-w</arg><arg>${workingPath}/</arg>
|
||
|
<arg>-n</arg><arg>${nameNode}</arg>
|
||
|
<arg>-f</arg><arg>ORCID_2020_10_summaries.tar.gz</arg>
|
||
|
<arg>-o</arg><arg>xml/authors/</arg>
|
||
|
</java>
|
||
|
<ok to="End"/>
|
||
|
<error to="Kill"/>
|
||
|
</action>
|
||
|
|
||
|
<end name="End"/>
|
||
|
</workflow-app>
|