D-Net
/
dhp-graph-dump
4
0
Fork 0
Code Issues Pull Requests 1 Projects Releases Wiki Activity

change dipendency from the workflow (leftover with old library name

This commit is contained in:
Miriam Baglioni 2023-03-30 10:29:00 +02:00
parent dc5e79dc64
commit 80d51cea56
1 changed files with 184 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

188
dump/src/main/resources/eu/dnetlib/dhp/oa/graph/dump/wf/subworkflows/subset/oozie_app/workflow.xml
View File

@ -20,7 +20,10 @@
<name>selectionCriteria</name>
<description>the selection criteria used to select the results</description>
</property>
<property>
<name>mapAs</name>
<description>It specifies the type of model for the dump (community - complete)</description>
</property>
<property>
<name>hiveDbName</name>
<description>the target hive database name</description>
@ -231,8 +234,6 @@
<join name="join_dump" to="select_subset"/>
<action name="select_subset">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
@ -256,10 +257,189 @@
<arg>--removeSet</arg><arg>${removeSet}</arg>
</spark>
<ok to="fork_dump_otherentities"/>
<ok to="dumpModel"/>
<error to="Kill"/>
</action>
<decision name="dumpModel">
<switch>
<case to="prepareResultProject">${wf:conf('mapAs') eq "community"}</case>
<default to="fork_dump_otherentities"/>
</switch>
</decision>
<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.community.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>${outputPath}/original</arg>
<arg>--outputPath</arg><arg>${workingDir}/preparedInfo</arg>
</spark>
<ok to="fork_result_linked_to_projects"/>
<error to="Kill"/>
</action>
<fork name="fork_result_linked_to_projects">
<path start="select_publication_linked_to_projects"/>
<path start="select_dataset_linked_to_projects"/>
<path start="select_orp_linked_to_project"/>
<path start="select_software_linked_to_projects"/>
</fork>
<action name="select_publication_linked_to_projects">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Dump funder results </name>
<class>eu.dnetlib.dhp.oa.graph.dump.funderresults.SparkResultLinkedToProject</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>${outputPath}/original/publication</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
<arg>--outputPath</arg><arg>${workingDir}/result/publication</arg>
<arg>--graphPath</arg><arg>${workingDir}/preparedInfo</arg>
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
</spark>
<ok to="join_link"/>
<error to="Kill"/>
</action>
<action name="select_dataset_linked_to_projects">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Dump funder results </name>
<class>eu.dnetlib.dhp.oa.graph.dump.funderresults.SparkResultLinkedToProject</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>${outputPath}/original/dataset</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
<arg>--outputPath</arg><arg>${workingDir}/result/dataset</arg>
<arg>--graphPath</arg><arg>${workingDir}/preparedInfo</arg>
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
</spark>
<ok to="join_link"/>
<error to="Kill"/>
</action>
<action name="select_orp_linked_to_project">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Dump funder results </name>
<class>eu.dnetlib.dhp.oa.graph.dump.funderresults.SparkResultLinkedToProject</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>${outputPath}/original/otherresearchproduct</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
<arg>--outputPath</arg><arg>${workingDir}/result/otherresearchproduct</arg>
<arg>--graphPath</arg><arg>${workingDir}/preparedInfo</arg>
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
</spark>
<ok to="join_link"/>
<error to="Kill"/>
</action>
<action name="select_software_linked_to_projects">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Dump funder results </name>
<class>eu.dnetlib.dhp.oa.graph.dump.funderresults.SparkResultLinkedToProject</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>${outputPath}/original/software</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
<arg>--outputPath</arg><arg>${workingDir}/result/software</arg>
<arg>--graphPath</arg><arg>${workingDir}/preparedInfo</arg>
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
</spark>
<ok to="join_link"/>
<error to="Kill"/>
</action>
<join name="join_link" to="dump_funder_results"/>
<action name="dump_funder_results">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Dump funder results </name>
<class>eu.dnetlib.dhp.oa.graph.dump.funderresults.SparkDumpFunderResults</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>${workingDir}/result</arg>
<arg>--outputPath</arg><arg>${outputPath}/dumpSubsetCommunityModel</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<fork name="fork_dump_otherentities">
<path start="dump_organization"/>
<path start="dump_project"/>