forked from D-Net/dnet-hadoop
81 lines
3.1 KiB
XML
81 lines
3.1 KiB
XML
<workflow-app name="download_ORCID_DUMP" xmlns="uri:oozie:workflow:0.5">
|
|
<parameters>
|
|
<property>
|
|
<name>targetPath</name>
|
|
<description>the path to store the original ORCID dump</description>
|
|
</property>
|
|
<property>
|
|
<name>apiURL</name>
|
|
<description>The figshare API URL to retrieve the list file to download</description>
|
|
</property>
|
|
</parameters>
|
|
|
|
<start to="generateTables"/>
|
|
|
|
<kill name="Kill">
|
|
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
|
</kill>
|
|
|
|
<action name="DownloadDUMP">
|
|
<java>
|
|
<configuration>
|
|
<property>
|
|
<name>oozie.launcher.mapreduce.user.classpath.first</name>
|
|
<value>true</value>
|
|
</property>
|
|
</configuration>
|
|
<main-class>eu.dnetlib.dhp.collection.orcid.DownloadORCIDDumpApplication</main-class>
|
|
<arg>--namenode</arg><arg>${nameNode}</arg>
|
|
<arg>--targetPath</arg><arg>${targetPath}</arg>
|
|
<arg>--apiURL</arg><arg>${apiURL}</arg>
|
|
</java>
|
|
<ok to="extractDump"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
|
|
<action name="extractDump">
|
|
<java>
|
|
<configuration>
|
|
<property>
|
|
<name>oozie.launcher.mapreduce.user.classpath.first</name>
|
|
<value>true</value>
|
|
</property>
|
|
</configuration>
|
|
|
|
<main-class>eu.dnetlib.dhp.collection.orcid.ExtractORCIDDump</main-class>
|
|
<java-opts> -Xmx6g </java-opts>
|
|
<arg>--namenode</arg><arg>${nameNode}</arg>
|
|
<arg>--sourcePath</arg><arg>${targetPath}</arg>
|
|
<arg>--targetPath</arg><arg>${targetPath}/extracted</arg>
|
|
</java>
|
|
<ok to="generateTables"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
|
|
<action name="generateTables">
|
|
<spark xmlns="uri:oozie:spark-action:0.2">
|
|
<master>yarn</master>
|
|
<mode>cluster</mode>
|
|
<name>Generate ORCID Tables</name>
|
|
<class>eu.dnetlib.dhp.collection.orcid.SparkGenerateORCIDTable</class>
|
|
<jar>dhp-aggregation-${projectVersion}.jar</jar>
|
|
<spark-opts>
|
|
--executor-memory=${sparkExecutorMemory}
|
|
--executor-cores=${sparkExecutorCores}
|
|
--driver-memory=${sparkDriverMemory}
|
|
--conf spark.executor.memoryOverhead=2g
|
|
--conf spark.sql.shuffle.partitions=3000
|
|
--conf spark.extraListeners=${spark2ExtraListeners}
|
|
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
|
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
|
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
|
</spark-opts>
|
|
<arg>--sourcePath</arg><arg>${targetPath}/extracted</arg>
|
|
<arg>--targetPath</arg><arg>${targetPath}/tables</arg>
|
|
<arg>--master</arg><arg>yarn</arg>
|
|
</spark>
|
|
<ok to="End"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
<end name="End"/>
|
|
</workflow-app> |