sourcePath
the source path
subjectlist
fos;sdg
the list of subject classid to propagate (split by ;)
allowedsemrels
IsSupplementedBy;IsSupplementTo;IsPreviousVersionOf;IsNewVersionOf;IsIdenticalTo;Obsoletes;IsObsoletedBy;IsVersionOf
the allowed semantics
outputPath
the output path
${jobTracker}
${nameNode}
oozie.action.sharelib.for.spark
${oozieActionShareLibForSpark2}
Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]
yarn
cluster
PrepareSubjectResultsAssociation
eu.dnetlib.dhp.subjecttoresultfromsemrel.PrepareResultResultStep1
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}
--allowedsemrels${allowedsemrels}
--subjectlist${subjectlist}
--resultTypepublication
--resultTableNameeu.dnetlib.dhp.schema.oaf.Publication
--outputPath${workingDir}/preparedInfo
yarn
cluster
PrepareSubjectResultsAssociation
eu.dnetlib.dhp.subjecttoresultfromsemrel.PrepareResultResultStep1
dhp-enrichment-${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${sourcePath}
--allowedsemrels${allowedsemrels}
--subjectlist${subjectlist}
--resultTypedataset
--resultTableNameeu.dnetlib.dhp.schema.oaf.Dataset
--outputPath${workingDir}/preparedInfo
yarn
cluster
PrepareSubjectResultsAssociation
eu.dnetlib.dhp.subjecttoresultfromsemrel.PrepareResultResultStep1
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}
--allowedsemrels${allowedsemrels}
--subjectlist${subjectlist}
--resultTypesoftware
--resultTableNameeu.dnetlib.dhp.schema.oaf.Software
--outputPath${workingDir}/preparedInfo
yarn
cluster
PrepareSubjectResultsAssociation
eu.dnetlib.dhp.subjecttoresultfromsemrel.PrepareResultResultStep1
dhp-enrichment-${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${sourcePath}
--allowedsemrels${allowedsemrels}
--subjectlist${subjectlist}
--resultTypeotherresearchproduct
--resultTableNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct
--outputPath${workingDir}/preparedInfo
yarn
cluster
SubjectToResultPropagation
eu.dnetlib.dhp.subjecttoresultfromsemrel.SparkSubjectPropagationStep2
dhp-enrichment-${projectVersion}.jar
--executor-cores=${sparkExecutorCores}
--executor-memory=8G
--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=${spark2MaxExecutors}
--conf spark.sql.shuffle.partitions=3840
--sourcePath${sourcePath}
--outputPath${outputPath}
--workingPath${workingDir}/working
--resultTableNameeu.dnetlib.dhp.schema.oaf.Publication
--resultTypepublication
--preparedPath${workingDir}/preparedInfo
yarn
cluster
SubjectToResultPropagation
eu.dnetlib.dhp.subjecttoresultfromsemrel.SparkSubjectPropagationStep2
dhp-enrichment-${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=${spark2MaxExecutors}
--conf spark.sql.shuffle.partitions=3840
--sourcePath${sourcePath}
--outputPath${outputPath}
--workingPath${workingDir}/working
--resultTableNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct
--resultTypeotherresearchproduct
--preparedPath${workingDir}/preparedInfo
yarn
cluster
SubjectToResultPropagation
eu.dnetlib.dhp.subjecttoresultfromsemrel.SparkSubjectPropagationStep2
dhp-enrichment-${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=${spark2MaxExecutors}
--conf spark.sql.shuffle.partitions=3840
--sourcePath${sourcePath}
--outputPath${outputPath}
--workingPath${workingDir}/working
--resultTableNameeu.dnetlib.dhp.schema.oaf.Dataset
--resultTypedataset
--preparedPath${workingDir}/preparedInfo
yarn
cluster
SubjectToResultPropagation
eu.dnetlib.dhp.subjecttoresultfromsemrel.SparkSubjectPropagationStep2
dhp-enrichment-${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=${spark2MaxExecutors}
--conf spark.sql.shuffle.partitions=3840
--sourcePath${sourcePath}
--outputPath${outputPath}
--workingPath${workingDir}/working
--resultTableNameeu.dnetlib.dhp.schema.oaf.Software
--resultTypesoftware
--preparedPath${workingDir}/preparedInfo