[graph provision] added person to the graph2hive workflow

This commit is contained in:
Claudio Atzori 2024-08-05 09:35:07 +02:00
parent 975d44cac7
commit 0bf76f2a34
1 changed files with 30 additions and 0 deletions

View File

@ -102,6 +102,7 @@
<path start="import_datasource"/> <path start="import_datasource"/>
<path start="import_organization"/> <path start="import_organization"/>
<path start="import_project"/> <path start="import_project"/>
<path start="import_person"/>
<path start="import_relation"/> <path start="import_relation"/>
</fork> </fork>
@ -308,6 +309,35 @@
<error to="Kill"/> <error to="Kill"/>
</action> </action>
<action name="import_person">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Import table person</name>
<class>eu.dnetlib.dhp.oa.graph.hive.GraphHiveTableImporterJob</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
--conf spark.sql.shuffle.partitions=1000
</spark-opts>
<arg>--inputPath</arg><arg>${inputPath}/person</arg>
<arg>--hiveDbName</arg><arg>${hiveDbName}</arg>
<arg>--className</arg><arg>eu.dnetlib.dhp.schema.oaf.Person</arg>
<arg>--hiveMetastoreUris</arg><arg>${hiveMetastoreUris}</arg>
<arg>--numPartitions</arg><arg>1000</arg>
</spark>
<ok to="join_import"/>
<error to="Kill"/>
</action>
<action name="import_relation"> <action name="import_relation">
<spark xmlns="uri:oozie:spark-action:0.2"> <spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master> <master>yarn</master>