sourcePath
the source path
sparkDriverMemory
memory for driver process
sparkExecutorMemory
memory for individual executor
sparkExecutorCores
number of cores used by single executor
isLookupUrl
the isLookup service endpoint
protoMap
the json path associated to each selection field
Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]
${jobTracker}
${nameNode}
${nameNode}/${sourcePath}/relation
${nameNode}/${workingDir}/relation
${jobTracker}
${nameNode}
yarn-cluster
cluster
bulkTagging
eu.dnetlib.dhp.SparkBulkTagJob
dhp-bulktag-${projectVersion}.jar
--num-executors=${sparkExecutorNumber}
--executor-memory=${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}${spark2EventLogDir}
--sourcePath${sourcePath}/publication
--resultTableNameeu.dnetlib.dhp.schema.oaf.Publication
--outputPath${workingDir}/publication
--proto_map${protoMap}
--isLookupUrl${isLookupUrl}
${jobTracker}
${nameNode}
yarn-cluster
cluster
bulkTagging
eu.dnetlib.dhp.SparkBulkTagJob
dhp-bulktag-${projectVersion}.jar
--num-executors=${sparkExecutorNumber}
--executor-memory=${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}${spark2EventLogDir}
--sourcePath${sourcePath}/dataset
--resultTableNameeu.dnetlib.dhp.schema.oaf.Dataset
--outputPath${workingDir}/dataset
--proto_map${protoMap}
--isLookupUrl${isLookupUrl}
${jobTracker}
${nameNode}
yarn-cluster
cluster
bulkTagging
eu.dnetlib.dhp.SparkBulkTagJob
dhp-bulktag-${projectVersion}.jar
--num-executors=${sparkExecutorNumber}
--executor-memory=${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}${spark2EventLogDir}
--sourcePath${sourcePath}/otherresearchproduct
--resultTableNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct
--outputPath${workingDir}/otherresearchproduct
--proto_map${protoMap}
--isLookupUrl${isLookupUrl}
${jobTracker}
${nameNode}
yarn-cluster
cluster
bulkTagging
eu.dnetlib.dhp.SparkBulkTagJob
dhp-bulktag-${projectVersion}.jar
--num-executors=${sparkExecutorNumber}
--executor-memory=${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}${spark2EventLogDir}
--sourcePath${sourcePath}/software
--resultTableNameeu.dnetlib.dhp.schema.oaf.Software
--outputPath${workingDir}/software
--proto_map${protoMap}
--isLookupUrl${isLookupUrl}