sourcePath
the source path
whitelist
the white list
allowedtypes
the allowed types
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
PrepareDatasourceCountryAssociation
eu.dnetlib.dhp.countrypropagation.PrepareDatasourceCountryAssociation
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}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=3840
--sourcePath${sourcePath}
--whitelist${whitelist}
--allowedtypes${allowedtypes}
--outputPath${workingDir}/country/preparedInfo
yarn
cluster
prepareResultCountry-Publication
eu.dnetlib.dhp.countrypropagation.PrepareResultCountrySet
dhp-enrichment-${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.speculation=false
--conf spark.hadoop.mapreduce.map.speculative=false
--conf spark.hadoop.mapreduce.reduce.speculative=false
--conf spark.sql.shuffle.partitions=3840
--sourcePath${sourcePath}/publication
--outputPath${workingDir}/country/publication
--workingPath${workingDir}/country/workingP
--resultTableNameeu.dnetlib.dhp.schema.oaf.Publication
--preparedInfoPath${workingDir}/country/preparedInfo
yarn
cluster
prepareResultCountry-Dataset
eu.dnetlib.dhp.countrypropagation.PrepareResultCountrySet
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}${spark2EventLogDir}
--conf spark.speculation=false
--conf spark.hadoop.mapreduce.map.speculative=false
--conf spark.hadoop.mapreduce.reduce.speculative=false
--conf spark.sql.shuffle.partitions=3840
--sourcePath${sourcePath}/dataset
--outputPath${workingDir}/country/dataset
--workingPath${workingDir}/country/workingD
--resultTableNameeu.dnetlib.dhp.schema.oaf.Dataset
--preparedInfoPath${workingDir}/country/preparedInfo
yarn
cluster
prepareResultCountry-ORP
eu.dnetlib.dhp.countrypropagation.PrepareResultCountrySet
dhp-enrichment-${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.speculation=false
--conf spark.hadoop.mapreduce.map.speculative=false
--conf spark.hadoop.mapreduce.reduce.speculative=false
--conf spark.sql.shuffle.partitions=3840
--sourcePath${sourcePath}/otherresearchproduct
--outputPath${workingDir}/country/otherresearchproduct
--workingPath${workingDir}/country/workingO
--resultTableNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct
--preparedInfoPath${workingDir}/country/preparedInfo
yarn
cluster
prepareResultCountry-Software
eu.dnetlib.dhp.countrypropagation.PrepareResultCountrySet
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}${spark2EventLogDir}
--conf spark.speculation=false
--conf spark.hadoop.mapreduce.map.speculative=false
--conf spark.hadoop.mapreduce.reduce.speculative=false
--conf spark.sql.shuffle.partitions=3840
--sourcePath${sourcePath}/software
--outputPath${workingDir}/country/software
--workingPath${workingDir}/country/workingS
--resultTableNameeu.dnetlib.dhp.schema.oaf.Software
--preparedInfoPath${workingDir}/country/preparedInfo
yarn
cluster
countryPropagationForPublications
eu.dnetlib.dhp.countrypropagation.SparkCountryPropagationJob
dhp-enrichment-${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.speculation=false
--conf spark.hadoop.mapreduce.map.speculative=false
--conf spark.hadoop.mapreduce.reduce.speculative=false
--conf spark.sql.shuffle.partitions=7680
--sourcePath${sourcePath}/publication
--preparedInfoPath${workingDir}/country/publication
--resultTableNameeu.dnetlib.dhp.schema.oaf.Publication
--outputPath${workingDir}/country/country/publication
yarn
cluster
countryPropagationForDataset
eu.dnetlib.dhp.countrypropagation.SparkCountryPropagationJob
dhp-enrichment-${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.speculation=false
--conf spark.hadoop.mapreduce.map.speculative=false
--conf spark.hadoop.mapreduce.reduce.speculative=false
--conf spark.sql.shuffle.partitions=3840
--sourcePath${sourcePath}/dataset
--preparedInfoPath${workingDir}/country/dataset
--resultTableNameeu.dnetlib.dhp.schema.oaf.Dataset
--outputPath${workingDir}/country/country/dataset
yarn
cluster
countryPropagationForORP
eu.dnetlib.dhp.countrypropagation.SparkCountryPropagationJob
dhp-enrichment-${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.speculation=false
--conf spark.hadoop.mapreduce.map.speculative=false
--conf spark.hadoop.mapreduce.reduce.speculative=false
--conf spark.sql.shuffle.partitions=3840
--sourcePath${sourcePath}/otherresearchproduct
--preparedInfoPath${workingDir}/country/otherresearchproduct
--resultTableNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct
--outputPath${workingDir}/country/country/otherresearchproduct
yarn
cluster
countryPropagationForSoftware
eu.dnetlib.dhp.countrypropagation.SparkCountryPropagationJob
dhp-enrichment-${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.speculation=false
--conf spark.hadoop.mapreduce.map.speculative=false
--conf spark.hadoop.mapreduce.reduce.speculative=false
--conf spark.sql.shuffle.partitions=3840
--sourcePath${sourcePath}/software
--preparedInfoPath${workingDir}/country/software
--resultTableNameeu.dnetlib.dhp.schema.oaf.Software
--outputPath${workingDir}/country/country/software
yarn
cluster
community2resultfromorganization - move results
eu.dnetlib.dhp.MoveResult
dhp-enrichment-${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}/country/country/
--outputPath${sourcePath}/
${wf:conf('startFrom') eq 'undelete'}