graphInputPath
the graph root input path
outputPath
the graph root output path
sparkDriverMemory
memory for driver process
sparkExecutorMemory
memory for individual executor
sparkExecutorCores
number of cores used by single executor
oozieActionShareLibForSpark2
oozie action sharelib for spark 2.*
spark2ExtraListeners
com.cloudera.spark.lineage.NavigatorAppListener
spark 2.* extra listeners classname
spark2SqlQueryExecutionListeners
com.cloudera.spark.lineage.NavigatorQueryListener
spark 2.* sql query execution listeners classname
spark2YarnHistoryServerAddress
spark 2.* yarn history server address
spark2EventLogDir
spark 2.* event log dir location
Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]
yarn
cluster
group graph entities and relations
eu.dnetlib.dhp.oa.graph.groupbyid.GroupEntitiesAndRelationsSparkJob
dhp-graph-mapper-${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.sql.shuffle.partitions=7680
--graphInputPath${graphInputPath}
--outputPath${workingDir}/grouped_entities
yarn
cluster
Dispatch publications
eu.dnetlib.dhp.oa.graph.groupbyid.DispatchEntitiesSparkJob
dhp-graph-mapper-${projectVersion}.jar
--executor-cores=${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}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=7680
--entitiesPath${workingDir}/grouped_entities
--outputPath${outputPath}/publication
--graphTableClassNameeu.dnetlib.dhp.schema.oaf.Publication
yarn
cluster
Dispatch datasets
eu.dnetlib.dhp.oa.graph.groupbyid.DispatchEntitiesSparkJob
dhp-graph-mapper-${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.sql.shuffle.partitions=7680
--entitiesPath${workingDir}/grouped_entities
--outputPath${outputPath}/dataset
--graphTableClassNameeu.dnetlib.dhp.schema.oaf.Dataset
yarn
cluster
Dispatch softwares
eu.dnetlib.dhp.oa.graph.groupbyid.DispatchEntitiesSparkJob
dhp-graph-mapper-${projectVersion}.jar
--executor-cores=${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}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=7680
--entitiesPath${workingDir}/grouped_entities
--outputPath${outputPath}/software
--graphTableClassNameeu.dnetlib.dhp.schema.oaf.Software
yarn
cluster
Dispatch otherresearchproducts
eu.dnetlib.dhp.oa.graph.groupbyid.DispatchEntitiesSparkJob
dhp-graph-mapper-${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.sql.shuffle.partitions=7680
--entitiesPath${workingDir}/grouped_entities
--outputPath${outputPath}/otherresearchproduct
--graphTableClassNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct
yarn
cluster
Dispatch datasources
eu.dnetlib.dhp.oa.graph.groupbyid.DispatchEntitiesSparkJob
dhp-graph-mapper-${projectVersion}.jar
--executor-cores=${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}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=7680
--entitiesPath${workingDir}/grouped_entities
--outputPath${outputPath}/datasource
--graphTableClassNameeu.dnetlib.dhp.schema.oaf.Datasource
yarn
cluster
Dispatch organizations
eu.dnetlib.dhp.oa.graph.groupbyid.DispatchEntitiesSparkJob
dhp-graph-mapper-${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.sql.shuffle.partitions=7680
--entitiesPath${workingDir}/grouped_entities
--outputPath${outputPath}/organization
--graphTableClassNameeu.dnetlib.dhp.schema.oaf.Organization
yarn
cluster
Dispatch project
eu.dnetlib.dhp.oa.graph.groupbyid.DispatchEntitiesSparkJob
dhp-graph-mapper-${projectVersion}.jar
--executor-cores=${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}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=7680
--entitiesPath${workingDir}/grouped_entities
--outputPath${outputPath}/project
--graphTableClassNameeu.dnetlib.dhp.schema.oaf.Project
yarn
cluster
Dispatch relations
eu.dnetlib.dhp.oa.graph.groupbyid.DispatchEntitiesSparkJob
dhp-graph-mapper-${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.sql.shuffle.partitions=7680
--entitiesPath${workingDir}/grouped_entities
--outputPath${outputPath}/relation
--graphTableClassNameeu.dnetlib.dhp.schema.oaf.Relation