lsmyrnaios
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
0
Fork 0
Code Pull Requests Activity

person table directory produced by the workflows raw_all and merge graphs

This commit is contained in:
Claudio Atzori 2024-10-30 11:25:17 +01:00
parent a877c76d70
commit a42c8b7c85
2 changed files with 55 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/merge/oozie_app/workflow.xml
View File

@ -68,6 +68,7 @@
<path start="merge_datasource"/> <path start="merge_datasource"/>
<path start="merge_organization"/> <path start="merge_organization"/>
<path start="merge_project"/> <path start="merge_project"/>
<path start="merge_person"/>
<path start="merge_relation"/> <path start="merge_relation"/>
</fork> </fork>
@ -260,6 +261,33 @@
<error to="Kill"/> <error to="Kill"/>
</action> </action>
<action name="merge_person">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Merge person</name>
<class>eu.dnetlib.dhp.oa.graph.merge.MergeGraphTableSparkJob</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=7680
</spark-opts>
<arg>--betaInputPath</arg><arg>${betaInputGraphPath}/person</arg>
<arg>--prodInputPath</arg><arg>${prodInputGraphPath}/person</arg>
<arg>--outputPath</arg><arg>${graphOutputPath}/person</arg>
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Person</arg>
<arg>--priority</arg><arg>${priority}</arg>
</spark>
<ok to="wait_merge"/>
<error to="Kill"/>
</action>
<action name="merge_relation"> <action name="merge_relation">
<spark xmlns="uri:oozie:spark-action:0.2"> <spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master> <master>yarn</master>

27
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/raw_all/oozie_app/workflow.xml
View File

@ -649,6 +649,7 @@
<path start="merge_claims_datasource"/> <path start="merge_claims_datasource"/>
<path start="merge_claims_organization"/> <path start="merge_claims_organization"/>
<path start="merge_claims_project"/> <path start="merge_claims_project"/>
<path start="merge_claims_person"/>
<path start="merge_claims_relation"/> <path start="merge_claims_relation"/>
</fork> </fork>
@ -860,6 +861,32 @@
<error to="Kill"/> <error to="Kill"/>
</action> </action>
<action name="merge_claims_person">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>MergeClaims_person</name>
<class>eu.dnetlib.dhp.oa.graph.raw.MergeClaimsApplication</class>
<jar>dhp-graph-mapper-${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}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=200
</spark-opts>
<arg>--rawGraphPath</arg><arg>${workingDir}/graph_raw</arg>
<arg>--claimsGraphPath</arg><arg>${workingDir}/graph_claims</arg>
<arg>--outputRawGaphPath</arg><arg>${graphOutputPath}</arg>
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Person</arg>
</spark>
<ok to="wait_merge"/>
<error to="Kill"/>
</action>
<join name="wait_merge" to="decisionPatchRelations"/> <join name="wait_merge" to="decisionPatchRelations"/>
<decision name="decisionPatchRelations"> <decision name="decisionPatchRelations">