removed old datacite oozie workflow

This commit is contained in:
Sandro La Bruzzo 2021-10-20 17:19:47 +02:00
parent ae4e99a471
commit ab3a99d3e9
6 changed files with 0 additions and 280 deletions

View File

@ -1,23 +0,0 @@
<configuration>
<property>
<name>jobTracker</name>
<value>yarnRM</value>
</property>
<property>
<name>nameNode</name>
<value>hdfs://nameservice1</value>
</property>
<property>
<name>oozie.use.system.libpath</name>
<value>true</value>
</property>
<property>
<name>oozie.action.sharelib.for.spark</name>
<value>spark2</value>
</property>
<property>
<name>oozie.launcher.mapreduce.user.classpath.first</name>
<value>true</value>
</property>
</configuration>

View File

@ -1,46 +0,0 @@
<workflow-app name="Datacite_to_ActionSet_Workflow" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>sourcePath</name>
<description>the working path of Datacite stores</description>
</property>
<property>
<name>outputPath</name>
<description>the path of Datacite ActionSet</description>
</property>
</parameters>
<start to="ExportDataset"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="ExportDataset">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>ExportDataset</name>
<class>eu.dnetlib.dhp.actionmanager.datacite.ExportActionSetJobNode</class>
<jar>dhp-aggregation-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.sql.shuffle.partitions=3840
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--targetPath</arg><arg>${outputPath}</arg>
<arg>--master</arg><arg>yarn-cluster</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>

View File

@ -1,23 +0,0 @@
<configuration>
<property>
<name>jobTracker</name>
<value>yarnRM</value>
</property>
<property>
<name>nameNode</name>
<value>hdfs://nameservice1</value>
</property>
<property>
<name>oozie.use.system.libpath</name>
<value>true</value>
</property>
<property>
<name>oozie.action.sharelib.for.spark</name>
<value>spark2</value>
</property>
<property>
<name>oozie.launcher.mapreduce.user.classpath.first</name>
<value>true</value>
</property>
</configuration>

View File

@ -1,81 +0,0 @@
<workflow-app name="Import_Datacite_and_transform_to_OAF" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>mainPath</name>
<description>the working path of Datacite stores</description>
</property>
<property>
<name>isLookupUrl</name>
<description>The IS lookUp service endopoint</description>
</property>
<property>
<name>blocksize</name>
<value>100</value>
<description>The request block size</description>
</property>
</parameters>
<start to="ImportDatacite"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="ImportDatacite">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>ImportDatacite</name>
<class>eu.dnetlib.dhp.actionmanager.datacite.ImportDatacite</class>
<jar>dhp-aggregation-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--targetPath</arg><arg>${mainPath}/datacite_update</arg>
<arg>--dataciteDumpPath</arg><arg>${mainPath}/datacite_dump</arg>
<arg>--namenode</arg><arg>${nameNode}</arg>
<arg>--master</arg><arg>yarn-cluster</arg>
<arg>--blocksize</arg><arg>${blocksize}</arg>
</spark>
<ok to="TransformJob"/>
<error to="Kill"/>
</action>
<action name="TransformJob">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>TransformJob</name>
<class>eu.dnetlib.dhp.actionmanager.datacite.GenerateDataciteDatasetSpark</class>
<jar>dhp-aggregation-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.sql.shuffle.partitions=3840
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${mainPath}/datacite_dump</arg>
<arg>--targetPath</arg><arg>${mainPath}/datacite_oaf</arg>
<arg>--isLookupUrl</arg><arg>${isLookupUrl}</arg>
<arg>--exportLinks</arg><arg>false</arg>
<arg>--master</arg><arg>yarn-cluster</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>

View File

@ -1,23 +0,0 @@
<configuration>
<property>
<name>jobTracker</name>
<value>yarnRM</value>
</property>
<property>
<name>nameNode</name>
<value>hdfs://nameservice1</value>
</property>
<property>
<name>oozie.use.system.libpath</name>
<value>true</value>
</property>
<property>
<name>oozie.action.sharelib.for.spark</name>
<value>spark2</value>
</property>
<property>
<name>oozie.launcher.mapreduce.user.classpath.first</name>
<value>true</value>
</property>
</configuration>

View File

@ -1,84 +0,0 @@
<workflow-app name="Generate_Datacite_and_Crossref_dump_for_Scholexplorer" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>datacitePath</name>
<description>the path of Datacite spark dataset</description>
</property>
<property>
<name>isLookupUrl</name>
<description>The IS lookUp service endopoint</description>
</property>
<property>
<name>crossrefPath</name>
<description>the path of Crossref spark dataset</description>
</property>
<property>
<name>targetPath</name>
<description>the path of Crossref spark dataset</description>
</property>
</parameters>
<start to="ImportDatacite"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="ImportDatacite">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>ImportDatacite</name>
<class>eu.dnetlib.dhp.actionmanager.datacite.GenerateDataciteDatasetSpark</class>
<jar>dhp-aggregation-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.sql.shuffle.partitions=3840
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${datacitePath}</arg>
<arg>--targetPath</arg><arg>${targetPath}/datacite_oaf</arg>
<arg>--isLookupUrl</arg><arg>${isLookupUrl}</arg>
<arg>--exportLinks</arg><arg>true</arg>
<arg>--master</arg><arg>yarn-cluster</arg>
</spark>
<ok to="FilterCrossrefEntities"/>
<error to="Kill"/>
</action>
<action name="FilterCrossrefEntities">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>FilterCrossrefEntities</name>
<class>eu.dnetlib.dhp.actionmanager.datacite.FilterCrossrefEntitiesSpark</class>
<jar>dhp-aggregation-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.sql.shuffle.partitions=3840
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${crossrefPath}</arg>
<arg>--targetPath</arg><arg>${targetPath}/crossref_oaf</arg>
<arg>--master</arg><arg>yarn-cluster</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>