292 lines
14 KiB
XML
292 lines
14 KiB
XML
<workflow-app name="dump_graph_for_eosc" xmlns="uri:oozie:workflow:0.5">
|
|
<parameters>
|
|
<property>
|
|
<name>sourcePath</name>
|
|
<description>the source path</description>
|
|
</property>
|
|
<property>
|
|
<name>outputPath</name>
|
|
<description>the output path</description>
|
|
</property>
|
|
<property>
|
|
<name>accessToken</name>
|
|
<description>the access token used for the deposition in Zenodo</description>
|
|
</property>
|
|
<property>
|
|
<name>connectionUrl</name>
|
|
<description>the connection url for Zenodo</description>
|
|
</property>
|
|
<property>
|
|
<name>metadata</name>
|
|
<description> the metadata associated to the deposition</description>
|
|
</property>
|
|
<property>
|
|
<name>depositionType</name>
|
|
<description>the type of deposition we want to perform. "new" for brand new deposition, "version" for a new version of a published deposition (in this case the concept record id must be provided), "upload" to upload content to an open deposition for which we already have the deposition id (in this case the deposition id should be provided)</description>
|
|
</property>
|
|
<property>
|
|
<name>conceptRecordId</name>
|
|
<description>for new version, the id of the record for the old deposition</description>
|
|
</property>
|
|
<property>
|
|
<name>depositionId</name>
|
|
<description>the depositionId of a deposition open that has to be added content</description>
|
|
</property>
|
|
<property>
|
|
<name>sparkDriverMemory</name>
|
|
<description>memory for driver process</description>
|
|
</property>
|
|
<property>
|
|
<name>sparkExecutorMemory</name>
|
|
<description>memory for individual executor</description>
|
|
</property>
|
|
<property>
|
|
<name>sparkExecutorCores</name>
|
|
<description>number of cores used by single executor</description>
|
|
</property>
|
|
<property>
|
|
<name>oozieActionShareLibForSpark2</name>
|
|
<description>oozie action sharelib for spark 2.*</description>
|
|
</property>
|
|
<property>
|
|
<name>spark2ExtraListeners</name>
|
|
<value>com.cloudera.spark.lineage.NavigatorAppListener</value>
|
|
<description>spark 2.* extra listeners classname</description>
|
|
</property>
|
|
<property>
|
|
<name>spark2SqlQueryExecutionListeners</name>
|
|
<value>com.cloudera.spark.lineage.NavigatorQueryListener</value>
|
|
<description>spark 2.* sql query execution listeners classname</description>
|
|
</property>
|
|
<property>
|
|
<name>spark2YarnHistoryServerAddress</name>
|
|
<description>spark 2.* yarn history server address</description>
|
|
</property>
|
|
<property>
|
|
<name>spark2EventLogDir</name>
|
|
<description>spark 2.* event log dir location</description>
|
|
</property>
|
|
</parameters>
|
|
<global>
|
|
<job-tracker>${jobTracker}</job-tracker>
|
|
<name-node>${nameNode}</name-node>
|
|
<configuration>
|
|
<property>
|
|
<name>mapreduce.job.queuename</name>
|
|
<value>${queueName}</value>
|
|
</property>
|
|
<property>
|
|
<name>oozie.launcher.mapred.job.queue.name</name>
|
|
<value>${oozieLauncherQueueName}</value>
|
|
</property>
|
|
<property>
|
|
<name>oozie.action.sharelib.for.spark</name>
|
|
<value>${oozieActionShareLibForSpark2}</value>
|
|
</property>
|
|
</configuration>
|
|
</global>
|
|
<start to="save_community_map"/>
|
|
<kill name="Kill">
|
|
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
|
</kill>
|
|
|
|
<action name="save_community_map">
|
|
<java>
|
|
<main-class>eu.dnetlib.dhp.oa.graph.dump.eosc.SaveCommunityMap</main-class>
|
|
<arg>--outputPath</arg><arg>${workingDir}/communityMap</arg>
|
|
<arg>--nameNode</arg><arg>${nameNode}</arg>
|
|
<arg>--isLookUpUrl</arg><arg>${isLookUpUrl}</arg>
|
|
</java>
|
|
<ok to="get_ds_master_duplicate"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
<action name="get_ds_master_duplicate">
|
|
<java>
|
|
<main-class>eu.dnetlib.dhp.oa.graph.dump.eosc.EoscMasterDuplicate</main-class>
|
|
<arg>--postgresUrl</arg><arg>${postgresURL}</arg>
|
|
<arg>--postgresUser</arg><arg>${postgresUser}</arg>
|
|
<arg>--postgresPassword</arg><arg>${postgresPassword}</arg>
|
|
<arg>--hdfsPath</arg><arg>${workingDir}/masterduplicate</arg>
|
|
<arg>--hdfsNameNode</arg><arg>${nameNode}</arg>
|
|
</java>
|
|
<ok to="dump_eosc_result"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
|
|
<action name="dump_eosc_result">
|
|
<spark xmlns="uri:oozie:spark-action:0.2">
|
|
<master>yarn</master>
|
|
<mode>cluster</mode>
|
|
<name>Dump Publication For EOSC </name>
|
|
<class>eu.dnetlib.dhp.oa.graph.dump.eosc.SelectEoscResults</class>
|
|
<jar>dump-${projectVersion}.jar</jar>
|
|
<spark-opts>
|
|
--executor-memory=${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}${spark2EventLogDir}
|
|
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
|
|
</spark-opts>
|
|
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
|
|
<arg>--outputPath</arg><arg>${workingDir}/dump</arg>
|
|
<arg>--communityMapPath</arg><arg>${workingDir}/communityMap</arg>
|
|
<arg>--eoscDatasourceIdsPath</arg><arg>${workingDir}/masterduplicate</arg>
|
|
</spark>
|
|
<ok to="extend_result_with_affiliation"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
<action name="extend_result_with_affiliation">
|
|
<spark xmlns="uri:oozie:spark-action:0.2">
|
|
<master>yarn</master>
|
|
<mode>cluster</mode>
|
|
<name>Extend Dump Publication For EOSC with affiliations </name>
|
|
<class>eu.dnetlib.dhp.oa.graph.dump.eosc.ExtendEoscResultWithOrganization</class>
|
|
<jar>dump-${projectVersion}.jar</jar>
|
|
<spark-opts>
|
|
--executor-memory=${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}${spark2EventLogDir}
|
|
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
|
|
</spark-opts>
|
|
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
|
|
<arg>--workingPath</arg><arg>${workingDir}/dump</arg>
|
|
</spark>
|
|
<ok to="prepareResultProject"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
|
|
<action name="prepareResultProject">
|
|
<spark xmlns="uri:oozie:spark-action:0.2">
|
|
<master>yarn</master>
|
|
<mode>cluster</mode>
|
|
<name>Prepare association result subset of project info</name>
|
|
<class>eu.dnetlib.dhp.oa.graph.dump.eosc.SparkPrepareResultProject</class>
|
|
<jar>dump-${projectVersion}.jar</jar>
|
|
<spark-opts>
|
|
--executor-memory=${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}${spark2EventLogDir}
|
|
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
|
|
</spark-opts>
|
|
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
|
|
<arg>--outputPath</arg><arg>${workingDir}/preparedInfo</arg>
|
|
</spark>
|
|
<ok to="extend_result_with_projects"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
|
|
<action name="extend_result_with_projects">
|
|
<spark xmlns="uri:oozie:spark-action:0.2">
|
|
<master>yarn</master>
|
|
<mode>cluster</mode>
|
|
<name>Extend dumped publications with information about project</name>
|
|
<class>eu.dnetlib.dhp.oa.graph.dump.eosc.ExtendEoscResultWithProject</class>
|
|
<jar>dump-${projectVersion}.jar</jar>
|
|
<spark-opts>
|
|
--executor-memory=${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}${spark2EventLogDir}
|
|
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
|
|
</spark-opts>
|
|
<arg>--sourcePath</arg><arg>${workingDir}/dump/affiliation</arg>
|
|
<arg>--outputPath</arg><arg>${workingDir}/dump/project</arg>
|
|
<arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo</arg>
|
|
<arg>--dumpType</arg><arg>eosc</arg>
|
|
</spark>
|
|
<ok to="select_relation"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
|
|
<action name="select_relation">
|
|
<spark xmlns="uri:oozie:spark-action:0.2">
|
|
<master>yarn</master>
|
|
<mode>cluster</mode>
|
|
<name>Select the set of relations between the results in the selected set</name>
|
|
<class>eu.dnetlib.dhp.oa.graph.dump.eosc.SparkSelectRelation</class>
|
|
<jar>dump-${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}
|
|
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
|
|
</spark-opts>
|
|
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
|
|
<arg>--outputPath</arg><arg>${workingDir}/dump</arg>
|
|
<arg>--removeSet</arg><arg>${removeSet}</arg>
|
|
</spark>
|
|
<ok to="extend_result_with_relation"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
|
|
<action name="extend_result_with_relation">
|
|
<spark xmlns="uri:oozie:spark-action:0.2">
|
|
<master>yarn</master>
|
|
<mode>cluster</mode>
|
|
<name>Extends the publication adding the relations of which the publication is the source node</name>
|
|
<class>eu.dnetlib.dhp.oa.graph.dump.eosc.ExtendEoscResultWithRelation</class>
|
|
<jar>dump-${projectVersion}.jar</jar>
|
|
<spark-opts>
|
|
--executor-memory=${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}${spark2EventLogDir}
|
|
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
|
|
</spark-opts>
|
|
<arg>--relationPath</arg><arg>${workingDir}/dump/relation</arg>
|
|
<arg>--resultPath</arg><arg>${workingDir}/dump/project</arg>
|
|
<arg>--outputPath</arg><arg>${outputPath}/dump</arg>
|
|
</spark>
|
|
<ok to="make_archive"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
|
|
<action name="make_archive">
|
|
<java>
|
|
<main-class>eu.dnetlib.dhp.oa.graph.dump.MakeTar</main-class>
|
|
<arg>--hdfsPath</arg><arg>${outputPath}/tar</arg>
|
|
<arg>--nameNode</arg><arg>${nameNode}</arg>
|
|
<arg>--sourcePath</arg><arg>${outputPath}/dump</arg>
|
|
</java>
|
|
<ok to="send_zenodo"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
|
|
<action name="send_zenodo">
|
|
<java>
|
|
<main-class>eu.dnetlib.dhp.oa.graph.dump.SendToZenodoHDFS</main-class>
|
|
<arg>--hdfsPath</arg><arg>${outputPath}/tar</arg>
|
|
<arg>--nameNode</arg><arg>${nameNode}</arg>
|
|
<arg>--accessToken</arg><arg>${accessToken}</arg>
|
|
<arg>--connectionUrl</arg><arg>${connectionUrl}</arg>
|
|
<arg>--metadata</arg><arg>${metadata}</arg>
|
|
<arg>--conceptRecordId</arg><arg>${conceptRecordId}</arg>
|
|
<arg>--depositionType</arg><arg>${depositionType}</arg>
|
|
<arg>--depositionId</arg><arg>${depositionId}</arg>
|
|
</java>
|
|
<ok to="End"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
<end name="End"/>
|
|
</workflow-app> |