graphOutputPath
the target path to store raw graph
reuseContent
false
should import content from the aggregator or reuse a previous version
contentPath
path location to store (or reuse) content from the aggregator
postgresURL
the postgres URL to access to the database
postgresUser
the user postgres
postgresPassword
the password postgres
mongoURL
mongoDB url, example: mongodb://[username:password@]host[:port]
mongoDb
mongo database
isLookupUrl
the address of the lookUp service
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
${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())}]
${wf:conf('reuseContent') eq false}
${wf:conf('reuseContent') eq true}
eu.dnetlib.dhp.oa.graph.raw.MigrateDbEntitiesApplication
--hdfsPath${contentPath}/db_claims
--postgresUrl${postgresURL}
--postgresUser${postgresUser}
--postgresPassword${postgresPassword}
--isLookupUrl${isLookupUrl}
--actionclaims
eu.dnetlib.dhp.oa.graph.raw.MigrateMongoMdstoresApplication
-p${contentPath}/odf_claims
-mongourl${mongoURL}
-mongodb${mongoDb}
-fODF
-lstore
-iclaim
eu.dnetlib.dhp.oa.graph.raw.MigrateMongoMdstoresApplication
-p${contentPath}/oaf_claims
-mongourl${mongoURL}
-mongodb${mongoDb}
-fOAF
-lstore
-iclaim
eu.dnetlib.dhp.oa.graph.raw.MigrateDbEntitiesApplication
--hdfsPath${contentPath}/db_records
--postgresUrl${postgresURL}
--postgresUser${postgresUser}
--postgresPassword${postgresPassword}
--isLookupUrl${isLookupUrl}
eu.dnetlib.dhp.oa.graph.raw.MigrateMongoMdstoresApplication
--hdfsPath${contentPath}/odf_records
--mongoBaseUrl${mongoURL}
--mongoDb${mongoDb}
--mdFormatODF
--mdLayoutstore
--mdInterpretationcleaned
eu.dnetlib.dhp.oa.graph.raw.MigrateMongoMdstoresApplication
--hdfsPath${contentPath}/oaf_records
--mongoBaseUrl${mongoURL}
--mongoDb${mongoDb}
--mdFormatOAF
--mdLayoutstore
--mdInterpretationcleaned
eu.dnetlib.dhp.oa.graph.raw.MigrateMongoMdstoresApplication
--hdfsPath${contentPath}/oaf_records_invisible
--mongoBaseUrl${mongoURL}
--mongoDb${mongoDb}
--mdFormatOAF
--mdLayoutstore
--mdInterpretationintersection
yarn
cluster
GenerateEntities_claim
eu.dnetlib.dhp.oa.graph.raw.GenerateEntitiesApplication
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}${spark2EventLogDir}
--sourcePaths${contentPath}/db_claims,${contentPath}/oaf_claims,${contentPath}/odf_claims,${contentPath}/oaf_records_invisible
--targetPath${workingDir}/entities_claim
--isLookupUrl${isLookupUrl}
yarn
cluster
GenerateGraph_claims
eu.dnetlib.dhp.oa.graph.raw.DispatchEntitiesApplication
dhp-graph-mapper-${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}${spark2EventLogDir}
--sourcePath${workingDir}/entities_claim
--graphRawPath${workingDir}/graph_claims
yarn
cluster
GenerateEntities
eu.dnetlib.dhp.oa.graph.raw.GenerateEntitiesApplication
dhp-graph-mapper-${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}${spark2EventLogDir}
--sourcePaths${contentPath}/db_records,${contentPath}/oaf_records,${contentPath}/odf_records
--targetPath${workingDir}/entities
--isLookupUrl${isLookupUrl}
yarn
cluster
GenerateGraph
eu.dnetlib.dhp.oa.graph.raw.DispatchEntitiesApplication
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}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=7680
--sourcePath${workingDir}/entities
--graphRawPath${workingDir}/graph_raw
yarn
cluster
MergeClaims_publication
eu.dnetlib.dhp.oa.graph.raw.MergeClaimsApplication
dhp-graph-mapper-${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}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=7680
--rawGraphPath${workingDir}/graph_raw
--claimsGraphPath${workingDir}/graph_claims
--outputRawGaphPath${graphOutputPath}
--graphTableClassNameeu.dnetlib.dhp.schema.oaf.Publication
yarn
cluster
MergeClaims_dataset
eu.dnetlib.dhp.oa.graph.raw.MergeClaimsApplication
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}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=7680
--rawGraphPath${workingDir}/graph_raw
--claimsGraphPath${workingDir}/graph_claims
--outputRawGaphPath${graphOutputPath}
--graphTableClassNameeu.dnetlib.dhp.schema.oaf.Dataset
yarn
cluster
MergeClaims_relation
eu.dnetlib.dhp.oa.graph.raw.MergeClaimsApplication
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}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=3840
--rawGraphPath${workingDir}/graph_raw
--claimsGraphPath${workingDir}/graph_claims
--outputRawGaphPath${graphOutputPath}
--graphTableClassNameeu.dnetlib.dhp.schema.oaf.Relation
yarn
cluster
MergeClaims_software
eu.dnetlib.dhp.oa.graph.raw.MergeClaimsApplication
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}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=1920
--rawGraphPath${workingDir}/graph_raw
--claimsGraphPath${workingDir}/graph_claims
--outputRawGaphPath${graphOutputPath}
--graphTableClassNameeu.dnetlib.dhp.schema.oaf.Software
yarn
cluster
MergeClaims_otherresearchproduct
eu.dnetlib.dhp.oa.graph.raw.MergeClaimsApplication
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}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=1920
--rawGraphPath${workingDir}/graph_raw
--claimsGraphPath${workingDir}/graph_claims
--outputRawGaphPath${graphOutputPath}
--graphTableClassNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct
yarn
cluster
MergeClaims_datasource
eu.dnetlib.dhp.oa.graph.raw.MergeClaimsApplication
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}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=200
--rawGraphPath${workingDir}/graph_raw
--claimsGraphPath${workingDir}/graph_claims
--outputRawGaphPath${graphOutputPath}
--graphTableClassNameeu.dnetlib.dhp.schema.oaf.Datasource
yarn
cluster
MergeClaims_organization
eu.dnetlib.dhp.oa.graph.raw.MergeClaimsApplication
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}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=200
--rawGraphPath${workingDir}/graph_raw
--claimsGraphPath${workingDir}/graph_claims
--outputRawGaphPath${graphOutputPath}
--graphTableClassNameeu.dnetlib.dhp.schema.oaf.Organization
yarn
cluster
MergeClaims_project
eu.dnetlib.dhp.oa.graph.raw.MergeClaimsApplication
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}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=200
--rawGraphPath${workingDir}/graph_raw
--claimsGraphPath${workingDir}/graph_claims
--outputRawGaphPath${graphOutputPath}
--graphTableClassNameeu.dnetlib.dhp.schema.oaf.Project