inputPath the source path hiveDbName the target hive database name hiveJdbcUrl hive server jdbc url hiveMetastoreUris hive server metastore URIs 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 sparkSqlWarehouseDir spark 2.* db directory location ${jobTracker} ${nameNode} mapreduce.job.queuename ${queueName} oozie.launcher.mapred.job.queue.name ${oozieLauncherQueueName} oozie.action.sharelib.for.spark ${oozieActionShareLibForSpark2} Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] hive.metastore.uris ${hiveMetastoreUris} ${hiveJdbcUrl}/${hiveDbName} hiveDbName=${hiveDbName} yarn cluster Import table publication eu.dnetlib.dhp.oa.graph.hive.GraphHiveTableImporterJob dhp-graph-mapper-${projectVersion}.jar --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} --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir} --inputPath${inputPath}/publication --hiveDbName${hiveDbName} --classNameeu.dnetlib.dhp.schema.oaf.Publication --hiveMetastoreUris${hiveMetastoreUris} yarn cluster Import table dataset eu.dnetlib.dhp.oa.graph.hive.GraphHiveTableImporterJob dhp-graph-mapper-${projectVersion}.jar --executor-memory=${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}${spark2EventLogDir} --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir} --inputPath${inputPath}/dataset --hiveDbName${hiveDbName} --classNameeu.dnetlib.dhp.schema.oaf.Dataset --hiveMetastoreUris${hiveMetastoreUris} yarn cluster Import table otherresearchproduct eu.dnetlib.dhp.oa.graph.hive.GraphHiveTableImporterJob dhp-graph-mapper-${projectVersion}.jar --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} --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir} --inputPath${inputPath}/otherresearchproduct --hiveDbName${hiveDbName} --classNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct --hiveMetastoreUris${hiveMetastoreUris} yarn cluster Import table software eu.dnetlib.dhp.oa.graph.hive.GraphHiveTableImporterJob dhp-graph-mapper-${projectVersion}.jar --executor-memory=${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}${spark2EventLogDir} --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir} --inputPath${inputPath}/software --hiveDbName${hiveDbName} --classNameeu.dnetlib.dhp.schema.oaf.Software --hiveMetastoreUris${hiveMetastoreUris} yarn cluster Import table datasource eu.dnetlib.dhp.oa.graph.hive.GraphHiveTableImporterJob dhp-graph-mapper-${projectVersion}.jar --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} --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir} --inputPath${inputPath}/datasource --hiveDbName${hiveDbName} --classNameeu.dnetlib.dhp.schema.oaf.Datasource --hiveMetastoreUris${hiveMetastoreUris} yarn cluster Import table organization eu.dnetlib.dhp.oa.graph.hive.GraphHiveTableImporterJob dhp-graph-mapper-${projectVersion}.jar --executor-memory=${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}${spark2EventLogDir} --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir} --inputPath${inputPath}/organization --hiveDbName${hiveDbName} --classNameeu.dnetlib.dhp.schema.oaf.Organization --hiveMetastoreUris${hiveMetastoreUris} yarn cluster Import table project eu.dnetlib.dhp.oa.graph.hive.GraphHiveTableImporterJob dhp-graph-mapper-${projectVersion}.jar --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} --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir} --inputPath${inputPath}/project --hiveDbName${hiveDbName} --classNameeu.dnetlib.dhp.schema.oaf.Project --hiveMetastoreUris${hiveMetastoreUris} --numPartitions100 yarn cluster Import table project eu.dnetlib.dhp.oa.graph.hive.GraphHiveTableImporterJob dhp-graph-mapper-${projectVersion}.jar --executor-memory=${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}${spark2EventLogDir} --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir} --inputPath${inputPath}/relation --hiveDbName${hiveDbName} --classNameeu.dnetlib.dhp.schema.oaf.Relation --hiveMetastoreUris${hiveMetastoreUris} hive.metastore.uris ${hiveMetastoreUris} ${hiveJdbcUrl}/${hiveDbName} hiveDbName=${hiveDbName}