enrichment steps #38

Merged
claudio.atzori merged 334 commits from miriam.baglioni/dnet-hadoop:master into enrichment_wfs 2020-08-11 16:40:26 +02:00
2 changed files with 59 additions and 0 deletions
Showing only changes of commit 5d46ec7d5f - Show all commits

View File

@ -0,0 +1,18 @@
<configuration>
<property>
<name>jobTracker</name>
<value>yarnRM</value>
</property>
<property>
<name>nameNode</name>
<value>hdfs://nameservice1</value>
</property>
<property>
<name>oozie.action.sharelib.for.java</name>
<value>spark2</value>
</property>
<property>
<name>oozie.launcher.mapreduce.user.classpath.first</name>
<value>true</value>
</property>
</configuration>

View File

@ -0,0 +1,41 @@
<workflow-app name="import Crossref from index into HDFS" 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}/output'/>
<mkdir path='${workingPath}/output'/>
</fs>
<ok to="ImportOrcidSummary"/>
<error to="Kill"/>
</action>
<action name="ImportOrcidSummary">
<java>
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<main-class>eu.dnetlib.doiboost.orcid.OrcidDSManager</main-class>
<arg>-d</arg><arg>${workingPath}/</arg>
<arg>-n</arg><arg>${nameNode}</arg>
<arg>-f</arg><arg>ORCID_2019_summaries.tar.gz</arg>
<arg>-o</arg><arg>output/</arg>
</java>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>