andreas.czerniak
/
BrBETA_dnet-hadoop
forked from D-Net/dnet-hadoop
1
1
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[raw_all] patching relation identifier phase to be run at the end, i.e. includes also claimed relations

This commit is contained in:
Claudio Atzori 2021-07-29 13:03:16 +02:00
parent f83dd70e1c
commit e725c88ebb
1 changed files with 37 additions and 38 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

75
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/raw_all/oozie_app/workflow.xml
View File

@ -548,42 +548,7 @@
<error to="Kill"/> <error to="Kill"/>
</action> </action>
<join name="wait_graphs" to="patchRelations"/> <join name="wait_graphs" to="fork_merge_claims"/>
<decision name="decisionPatchRelations">
<switch>
<case to="patchRelations">
${(shouldPatchRelations eq "true") and
(fs:exists(concat(concat(wf:conf('nameNode'),'/'),wf:conf('idMappingPath'))) eq "true")}
</case>
<default to="fork_merge_claims"/>
</switch>
</decision>
<action name="patchRelations">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>PatchRelations</name>
<class>eu.dnetlib.dhp.oa.graph.raw.PatchRelationsApplication</class>
<jar>dhp-graph-mapper-${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}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=7680
</spark-opts>
<arg>--graphBasePath</arg><arg>${workingDir}/graph_raw</arg>
<arg>--workingDir</arg><arg>${workingDir}/patch_relations</arg>
<arg>--idMappingPath</arg><arg>${idMappingPath}</arg>
</spark>
<ok to="fork_merge_claims"/>
<error to="Kill"/>
</action>
<fork name="fork_merge_claims"> <fork name="fork_merge_claims">
<path start="merge_claims_publication"/> <path start="merge_claims_publication"/>
@ -596,7 +561,6 @@
<path start="merge_claims_relation"/> <path start="merge_claims_relation"/>
</fork> </fork>
<action name="merge_claims_publication"> <action name="merge_claims_publication">
<spark xmlns="uri:oozie:spark-action:0.2"> <spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master> <master>yarn</master>
@ -805,7 +769,42 @@
<error to="Kill"/> <error to="Kill"/>
</action> </action>
<join name="wait_merge" to="End"/> <join name="wait_merge" to="decisionPatchRelations"/>
<decision name="decisionPatchRelations">
<switch>
<case to="patchRelations">
${(shouldPatchRelations eq "true") and
(fs:exists(concat(concat(wf:conf('nameNode'),'/'),wf:conf('idMappingPath'))) eq "true")}
</case>
<default to="End"/>
</switch>
</decision>
<action name="patchRelations">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>PatchRelations</name>
<class>eu.dnetlib.dhp.oa.graph.raw.PatchRelationsApplication</class>
<jar>dhp-graph-mapper-${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}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=7680
</spark-opts>
<arg>--graphBasePath</arg><arg>${graphOutputPath}</arg>
<arg>--workingDir</arg><arg>${workingDir}/patch_relations</arg>
<arg>--idMappingPath</arg><arg>${idMappingPath}</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/> <end name="End"/>
</workflow-app> </workflow-app>