sourcePath
the source path
baseURL
the baseURL from where to reach the community APIs
startFrom
undelete
${jobTracker}
${nameNode}
oozie.action.sharelib.for.spark
${oozieActionShareLibForSpark2}
${wf:conf('startFrom') eq 'undelete'}
Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]
yarn
cluster
Prepare-Community-Result-Organization
eu.dnetlib.dhp.resulttocommunityfromorganization.PrepareResultCommunitySet
dhp-enrichment-${projectVersion}.jar
--executor-cores=6
--executor-memory=5G
--conf spark.executor.memoryOverhead=3g
--conf spark.sql.shuffle.partitions=3284
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
--sourcePath${sourcePath}/relation
--outputPath${workingDir}/communityorganization/preparedInfo/resultCommunityList
--hive_metastore_uris${hive_metastore_uris}
--baseURL${baseURL}
yarn
cluster
community2resultfromorganization
eu.dnetlib.dhp.resulttocommunityfromorganization.SparkResultToCommunityFromOrganizationJob
dhp-enrichment-${projectVersion}.jar
--executor-cores=6
--executor-memory=5G
--conf spark.executor.memoryOverhead=3g
--conf spark.sql.shuffle.partitions=3284
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
--preparedInfoPath${workingDir}/communityorganization/preparedInfo/resultCommunityList
--sourcePath${sourcePath}/
--outputPath${workingDir}/communityorganization/resulttocommunityfromorganization/
yarn
cluster
community2resultfromorganization - move results
eu.dnetlib.dhp.MoveResult
dhp-enrichment-${projectVersion}.jar
--executor-cores=6
--executor-memory=5G
--conf spark.executor.memoryOverhead=3g
--conf spark.sql.shuffle.partitions=3284
--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.maxExecutors=${spark2MaxExecutors}
--sourcePath${workingDir}/communityorganization/resulttocommunityfromorganization/
--outputPath${sourcePath}/