mdstoreInputPath
the path of the input MDStore
mdstoreOutputPath
the path of the cleaned mdstore
nativeInputPath
the path of the input MDStore
Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]
${wf:conf('resumeFrom') eq 'TransformJob'}
${wf:conf('resumeFrom') eq 'ExportDataset'}
yarn-cluster
cluster
ImportDatacite
eu.dnetlib.dhp.actionmanager.datacite.ImportDatacite
dhp-aggregation-${projectVersion}.jar
--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}
-t${nativeInputPath}
-d${mdstoreInputPath}
-n${nameNode}
--masteryarn-cluster
yarn-cluster
cluster
TransformJob
eu.dnetlib.dhp.actionmanager.datacite.GenerateDataciteDatasetSpark
dhp-aggregation-${projectVersion}.jar
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.sql.shuffle.partitions=3840
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--sourcePath${mdstoreInputPath}
--targetPath${mdstoreOutputPath}
--isLookupUrl${isLookupUrl}
-tr${isLookupUrl}
--masteryarn-cluster
yarn-cluster
cluster
ExportDataset
eu.dnetlib.dhp.actionmanager.datacite.ExportActionSetJobNode
dhp-aggregation-${projectVersion}.jar
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.sql.shuffle.partitions=3840
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--sourcePath${mdstoreOutputPath}
--targetPath${mdstoreOutputPath}_raw_AS
--masteryarn-cluster