apiDescription
A json encoding of the API Description class
dataSourceInfo
A json encoding of the Datasource Info
identifierPath
An xpath to retrieve the metadata identifier for the generation of DNet Identifier
metadataEncoding
The type of the metadata XML/JSON
timestamp
The timestamp of the collection date
workflowId
The identifier of the workflow
mdStoreID
The identifier of the mdStore
mdStoreManagerURI
The URI of the MDStore Manager
dnetMessageManagerURL
The URI of the Dnet Message Manager
collectionMode
Should be REFRESH or INCREMENTAL
${jobTracker}
${nameNode}
Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]
${wf:conf('collectionMode') eq 'REFRESH'}
${wf:conf('collectionMode') eq 'INCREMENTAL'}
eu.dnetlib.dhp.aggregation.mdstore.MDStoreActionNode
--actionREAD_LOCK
--mdStoreID${mdStoreID}
--mdStoreManagerURI${mdStoreManagerURI}
eu.dnetlib.dhp.aggregation.mdstore.MDStoreActionNode
--actionNEW_VERSION
--mdStoreID${mdStoreID}
--mdStoreManagerURI${mdStoreManagerURI}
eu.dnetlib.dhp.collection.worker.CollectorWorkerApplication
--apidescriptor${apiDescription}
--namenode${nameNode}
--workflowId${workflowId}
--dnetMessageManagerURL${dnetMessageManagerURL}
--mdStoreVersion${wf:actionData('StartTransaction')['mdStoreVersion']}
--maxNumberOfRetry${maxNumberOfRetry}
--retryDelay${retryDelay}
--connectTimeOut${connectTimeOut}
--readTimeOut${readTimeOut}
eu.dnetlib.dhp.collection.worker.CollectorWorkerReporter
--mdStoreVersion${wf:actionData('StartTransaction')['mdStoreVersion']}
--namenode${nameNode}
yarn
cluster
Generate Native MetadataStore
eu.dnetlib.dhp.collection.GenerateNativeStoreSparkJob
dhp-aggregation-${projectVersion}.jar
--executor-memory=${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}${spark2EventLogDir}
--encoding${metadataEncoding}
--dateOfCollection${timestamp}
--provenance${dataSourceInfo}
--xpath${identifierPath}
--mdStoreVersion${wf:actionData('StartTransaction')['mdStoreVersion']}
--readMdStoreVersion${wf:actionData('BeginRead')['mdStoreReadLockVersion']}
${wf:conf('collectionMode') eq 'REFRESH'}
${wf:conf('collectionMode') eq 'INCREMENTAL'}
eu.dnetlib.dhp.aggregation.mdstore.MDStoreActionNode
--actionREAD_UNLOCK
--mdStoreManagerURI${mdStoreManagerURI}
--readMDStoreId${wf:actionData('BeginRead')['mdStoreReadLockVersion']}
eu.dnetlib.dhp.aggregation.mdstore.MDStoreActionNode
--actionCOMMIT
--namenode${nameNode}
--mdStoreVersion${wf:actionData('StartTransaction')['mdStoreVersion']}
--mdStoreManagerURI${mdStoreManagerURI}
${wf:conf('collectionMode') eq 'REFRESH'}
${wf:conf('collectionMode') eq 'INCREMENTAL'}
eu.dnetlib.dhp.aggregation.mdstore.MDStoreActionNode
--actionREAD_UNLOCK
--mdStoreManagerURI${mdStoreManagerURI}
--readMDStoreId${wf:actionData('BeginRead')['mdStoreReadLockVersion']}
eu.dnetlib.dhp.aggregation.mdstore.MDStoreActionNode
--actionROLLBACK
--mdStoreVersion${wf:actionData('StartTransaction')['mdStoreVersion']}
--mdStoreManagerURI${mdStoreManagerURI}