Changed the code for the production of the dump for FCT

This commit is contained in:
Miriam Baglioni 2023-04-05 19:00:10 +02:00
parent 80d51cea56
commit 43e9286db2
3 changed files with 395 additions and 147 deletions

View File

@ -66,7 +66,7 @@ public class MakeTar implements Serializable {
String pathString = p.toString();
String entity = pathString.substring(pathString.lastIndexOf("/") + 1);
MakeTarArchive.tarMaxSize(fileSystem, pathString, outputPath + "/" + entity, entity, gBperSplit);
MakeTarArchive.tarMaxSize(fileSystem, pathString, outputPath + "/" + entity, entity, gBperSplit, true);
}
}

View File

@ -17,6 +17,8 @@ import org.apache.spark.sql.SparkSession;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.oa.graph.dump.Constants;
import eu.dnetlib.dhp.oa.graph.dump.ResultMapper;
@ -83,7 +85,7 @@ public class SparkResultLinkedToProject implements Serializable {
private static <R extends Result> void writeResultsLinkedToProjects(String communityMapPath, SparkSession spark,
Class<R> inputClazz,
String inputPath, String outputPath, String resultProjectsPath) {
ObjectMapper mapper = new ObjectMapper();
Dataset<R> results = Utils
.readPath(spark, inputPath, inputClazz)
.filter(
@ -102,10 +104,11 @@ public class SparkResultLinkedToProject implements Serializable {
cr.setProjects(t2._2().getProjectsList());
return cr;
}, Encoders.bean(CommunityResult.class))
.map((MapFunction<CommunityResult, String>) cr -> mapper.writeValueAsString(cr), Encoders.STRING())
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(outputPath);
.text(outputPath);
}
}

View File

@ -264,11 +264,124 @@
<decision name="dumpModel">
<switch>
<case to="prepareResultProject">${wf:conf('mapAs') eq "community"}</case>
<case to="fork_dump_community">${wf:conf('mapAs') eq "community"}</case>
<default to="fork_dump_otherentities"/>
</switch>
</decision>
<fork name="fork_dump_community">
<path start="dump_publication"/>
<path start="dump_dataset"/>
<path start="dump_orp"/>
<path start="dump_software"/>
</fork>
<action name="dump_publication">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Dump table publication for community/funder related products</name>
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkDumpCommunityProducts</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}/dump/publication</arg>
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
<arg>--dumpType</arg><arg>community</arg>
</spark>
<ok to="join_dump_comm"/>
<error to="Kill"/>
</action>
<action name="dump_dataset">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Dump table dataset for community/funder related products</name>
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkDumpCommunityProducts</class>
<jar>dump-${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>${workingDir}/dump/dataset</arg>
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
</spark>
<ok to="join_dump_comm"/>
<error to="Kill"/>
</action>
<action name="dump_orp">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Dump table ORP for community related products</name>
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkDumpCommunityProducts</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}/dump/otherresearchproduct</arg>
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
</spark>
<ok to="join_dump_comm"/>
<error to="Kill"/>
</action>
<action name="dump_software">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Dump table software for community related products</name>
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkDumpCommunityProducts</class>
<jar>dump-${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>${workingDir}/dump/software</arg>
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
</spark>
<ok to="join_dump_comm"/>
<error to="Kill"/>
</action>
<join name="join_dump_comm" to="prepareResultProject"/>
<action name="prepareResultProject">
<spark xmlns="uri:oozie:spark-action:0.2">
@ -290,155 +403,287 @@
<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"/>
<ok to="fork_extendWithProject"/>
<error to="Kill"/>
</action>
<fork name="fork_extendWithProject">
<path start="extend_publication"/>
<path start="extend_dataset"/>
<path start="extend_orp"/>
<path start="extend_software"/>
</fork>
<action name="extend_publication">
<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.community.SparkUpdateProjectInfo</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>${workingDir}/dump/publication</arg>
<arg>--outputPath</arg><arg>${outputPath}/dump/publication</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo</arg>
</spark>
<ok to="join_extend"/>
<error to="Kill"/>
</action>
<action name="extend_dataset">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Extend dumped dataset with information about project</name>
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkUpdateProjectInfo</class>
<jar>dump-${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/dataset</arg>
<arg>--outputPath</arg><arg>${outputPath}/dump/dataset</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo</arg>
</spark>
<ok to="join_extend"/>
<error to="Kill"/>
</action>
<action name="extend_orp">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Extend dumped ORP with information about project</name>
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkUpdateProjectInfo</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>${workingDir}/dump/otherresearchproduct</arg>
<arg>--outputPath</arg><arg>${outputPath}/dump/otherresearchproduct</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo</arg>
</spark>
<ok to="join_extend"/>
<error to="Kill"/>
</action>
<action name="extend_software">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Extend dumped software with information about project</name>
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkUpdateProjectInfo</class>
<jar>dhp-graph-dump-${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/software</arg>
<arg>--outputPath</arg><arg>${outputPath}/dump/software</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo</arg>
</spark>
<ok to="join_extend"/>
<error to="Kill"/>
</action>
<join name="join_extend" to="End"/>
<!-- <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-${projectVersion}.jar</jar>-->
<!-- <spark-opts>-->
<!-- &#45;&#45;executor-memory=${sparkExecutorMemory}-->
<!-- &#45;&#45;executor-cores=${sparkExecutorCores}-->
<!-- &#45;&#45;driver-memory=${sparkDriverMemory}-->
<!-- &#45;&#45;conf spark.extraListeners=${spark2ExtraListeners}-->
<!-- &#45;&#45;conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}-->
<!-- &#45;&#45;conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}-->
<!-- &#45;&#45;conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}-->
<!-- &#45;&#45;conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}-->
<!-- </spark-opts>-->
<!-- <arg>&#45;&#45;sourcePath</arg><arg>${outputPath}/original</arg>-->
<!-- <arg>&#45;&#45;outputPath</arg><arg>${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-${projectVersion}.jar</jar>-->
<!-- <spark-opts>-->
<!-- &#45;&#45;executor-memory=${sparkExecutorMemory}-->
<!-- &#45;&#45;executor-cores=${sparkExecutorCores}-->
<!-- &#45;&#45;driver-memory=${sparkDriverMemory}-->
<!-- &#45;&#45;conf spark.extraListeners=${spark2ExtraListeners}-->
<!-- &#45;&#45;conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}-->
<!-- &#45;&#45;conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}-->
<!-- &#45;&#45;conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}-->
<!-- &#45;&#45;conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}-->
<!-- </spark-opts>-->
<!-- <arg>&#45;&#45;sourcePath</arg><arg>${outputPath}/original/publication</arg>-->
<!-- <arg>&#45;&#45;resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>-->
<!-- <arg>&#45;&#45;outputPath</arg><arg>${workingDir}/result/publication</arg>-->
<!-- <arg>&#45;&#45;graphPath</arg><arg>${workingDir}/preparedInfo</arg>-->
<!-- <arg>&#45;&#45;communityMapPath</arg><arg>${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-${projectVersion}.jar</jar>-->
<!-- <spark-opts>-->
<!-- &#45;&#45;executor-memory=${sparkExecutorMemory}-->
<!-- &#45;&#45;executor-cores=${sparkExecutorCores}-->
<!-- &#45;&#45;driver-memory=${sparkDriverMemory}-->
<!-- &#45;&#45;conf spark.extraListeners=${spark2ExtraListeners}-->
<!-- &#45;&#45;conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}-->
<!-- &#45;&#45;conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}-->
<!-- &#45;&#45;conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}-->
<!-- &#45;&#45;conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}-->
<!-- </spark-opts>-->
<!-- <arg>&#45;&#45;sourcePath</arg><arg>${outputPath}/original/dataset</arg>-->
<!-- <arg>&#45;&#45;resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>-->
<!-- <arg>&#45;&#45;outputPath</arg><arg>${workingDir}/result/dataset</arg>-->
<!-- <arg>&#45;&#45;graphPath</arg><arg>${workingDir}/preparedInfo</arg>-->
<!-- <arg>&#45;&#45;communityMapPath</arg><arg>${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-${projectVersion}.jar</jar>-->
<!-- <spark-opts>-->
<!-- &#45;&#45;executor-memory=${sparkExecutorMemory}-->
<!-- &#45;&#45;executor-cores=${sparkExecutorCores}-->
<!-- &#45;&#45;driver-memory=${sparkDriverMemory}-->
<!-- &#45;&#45;conf spark.extraListeners=${spark2ExtraListeners}-->
<!-- &#45;&#45;conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}-->
<!-- &#45;&#45;conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}-->
<!-- &#45;&#45;conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}-->
<!-- &#45;&#45;conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}-->
<!-- </spark-opts>-->
<!-- <arg>&#45;&#45;sourcePath</arg><arg>${outputPath}/original/otherresearchproduct</arg>-->
<!-- <arg>&#45;&#45;resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>-->
<!-- <arg>&#45;&#45;outputPath</arg><arg>${workingDir}/result/otherresearchproduct</arg>-->
<!-- <arg>&#45;&#45;graphPath</arg><arg>${workingDir}/preparedInfo</arg>-->
<!-- <arg>&#45;&#45;communityMapPath</arg><arg>${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-${projectVersion}.jar</jar>-->
<!-- <spark-opts>-->
<!-- &#45;&#45;executor-memory=${sparkExecutorMemory}-->
<!-- &#45;&#45;executor-cores=${sparkExecutorCores}-->
<!-- &#45;&#45;driver-memory=${sparkDriverMemory}-->
<!-- &#45;&#45;conf spark.extraListeners=${spark2ExtraListeners}-->
<!-- &#45;&#45;conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}-->
<!-- &#45;&#45;conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}-->
<!-- &#45;&#45;conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}-->
<!-- &#45;&#45;conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}-->
<!-- </spark-opts>-->
<!-- <arg>&#45;&#45;sourcePath</arg><arg>${outputPath}/original/software</arg>-->
<!-- <arg>&#45;&#45;resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>-->
<!-- <arg>&#45;&#45;outputPath</arg><arg>${workingDir}/result/software</arg>-->
<!-- <arg>&#45;&#45;graphPath</arg><arg>${workingDir}/preparedInfo</arg>-->
<!-- <arg>&#45;&#45;communityMapPath</arg><arg>${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-${projectVersion}.jar</jar>-->
<!-- <spark-opts>-->
<!-- &#45;&#45;executor-memory=${sparkExecutorMemory}-->
<!-- &#45;&#45;executor-cores=${sparkExecutorCores}-->
<!-- &#45;&#45;driver-memory=${sparkDriverMemory}-->
<!-- &#45;&#45;conf spark.extraListeners=${spark2ExtraListeners}-->
<!-- &#45;&#45;conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}-->
<!-- &#45;&#45;conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}-->
<!-- &#45;&#45;conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}-->
<!-- &#45;&#45;conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}-->
<!-- </spark-opts>-->
<!-- <arg>&#45;&#45;sourcePath</arg><arg>${workingDir}/result</arg>-->
<!-- <arg>&#45;&#45;outputPath</arg><arg>${outputPath}/dumpSubsetCommunityModel</arg>-->
<!-- </spark>-->
<!-- <ok to="End"/>-->
<!-- <error to="Kill"/>-->
<!-- </action>-->
<fork name="fork_dump_otherentities">
<path start="dump_organization"/>