sourcePath
the source path
blacklist
The list of institutional repositories that should not be used for the propagation
${jobTracker}
${nameNode}
oozie.action.sharelib.for.spark
${oozieActionShareLibForSpark2}
Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]
yarn
cluster
PrepareResultOrganizationAssociation
eu.dnetlib.dhp.resulttoorganizationfrominstrepo.PrepareResultInstRepoAssociation
dhp-enrichment-${projectVersion}.jar
--executor-cores=${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}${spark2EventLogDir}
--sourcePath${sourcePath}
--workingPath${workingDir}/affiliationInstRepo
--blacklist${blacklist}
--hive_metastore_uris${hive_metastore_uris}
yarn
cluster
resultToOrganizationFromInstRepoPropagationForPublications
eu.dnetlib.dhp.resulttoorganizationfrominstrepo.SparkResultToOrganizationFromIstRepoJob
dhp-enrichment-${projectVersion}.jar
--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.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
--sourcePath${sourcePath}/publication
--outputPath${workingDir}/affiliationInstRepo/publication/relation
--datasourceOrganizationPath${workingDir}/affiliationInstRepo/preparedInfo/datasourceOrganization
--alreadyLinkedPath${workingDir}/affiliationInstRepo/preparedInfo/alreadyLinked
--hive_metastore_uris${hive_metastore_uris}
--resultTableNameeu.dnetlib.dhp.schema.oaf.Publication
yarn
cluster
resultToOrganizationFromInstRepoPropagationForDataset
eu.dnetlib.dhp.resulttoorganizationfrominstrepo.SparkResultToOrganizationFromIstRepoJob
dhp-enrichment-${projectVersion}.jar
--executor-cores=${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}${spark2EventLogDir}
--conf spark.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
--sourcePath${sourcePath}/dataset
--outputPath${workingDir}/affiliationInstRepo/dataset/relation
--datasourceOrganizationPath${workingDir}/affiliationInstRepo/preparedInfo/datasourceOrganization
--alreadyLinkedPath${workingDir}/affiliationInstRepo/preparedInfo/alreadyLinked
--hive_metastore_uris${hive_metastore_uris}
--resultTableNameeu.dnetlib.dhp.schema.oaf.Dataset
yarn
cluster
resultToOrganizationFromInstRepoPropagationForORP
eu.dnetlib.dhp.resulttoorganizationfrominstrepo.SparkResultToOrganizationFromIstRepoJob
dhp-enrichment-${projectVersion}.jar
--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.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
--sourcePath${sourcePath}/otherresearchproduct
--outputPath${workingDir}/affiliationInstRepo/otherresearchproduct/relation
--datasourceOrganizationPath${workingDir}/affiliationInstRepo/preparedInfo/datasourceOrganization
--alreadyLinkedPath${workingDir}/affiliationInstRepo/preparedInfo/alreadyLinked
--hive_metastore_uris${hive_metastore_uris}
--resultTableNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct
yarn
cluster
resultToOrganizationFromInstRepoPropagationForSoftware
eu.dnetlib.dhp.resulttoorganizationfrominstrepo.SparkResultToOrganizationFromIstRepoJob
dhp-enrichment-${projectVersion}.jar
--executor-cores=${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}${spark2EventLogDir}
--conf spark.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
--sourcePath${sourcePath}/software
--outputPath${workingDir}/affiliationInstRepo/software/relation
--datasourceOrganizationPath${workingDir}/affiliationInstRepo/preparedInfo/datasourceOrganization
--alreadyLinkedPath${workingDir}/affiliationInstRepo/preparedInfo/alreadyLinked
--hive_metastore_uris${hive_metastore_uris}
--resultTableNameeu.dnetlib.dhp.schema.oaf.Software
yarn
cluster
append new relations
eu.dnetlib.dhp.resulttoorganizationfrominstrepo.AppendNewRelations
dhp-enrichment-${projectVersion}.jar
--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.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
--outputPath${sourcePath}/relation
--sourcePath${workingDir}/affiliationInstRepo/