antonis.lempesis
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
1
Fork 1
Code Issues Pull Requests Projects Releases Wiki Activity

Scholexplorer Datasource Aggregation: 

- Added collectedfrom in the inverse relation generated
Relation resolution:
- increased number of partitions in workflow.xml
- using classid instead of classname to build the pid-dnetId mapping
This commit is contained in:
Sandro La Bruzzo 2021-10-26 17:51:20 +02:00
parent aafdffa6b3
commit 4acfa8fa2e
3 changed files with 9 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/collection/CollectionUtils.scala
View File

@ -34,6 +34,12 @@ object CollectionUtils {
inverse.setRelType(currentRel.getRelType) inverse.setRelType(currentRel.getRelType)
inverse.setSubRelType(currentRel.getSubReltype) inverse.setSubRelType(currentRel.getSubReltype)
inverse.setRelClass(currentRel.getInverseRelClass) inverse.setRelClass(currentRel.getInverseRelClass)
inverse.setCollectedfrom(r.getCollectedfrom)
inverse.setDataInfo(r.getDataInfo)
inverse.setProperties(r.getProperties)
inverse.setLastupdatetimestamp(r.getLastupdatetimestamp)
inverse.setValidated(r.getValidated)
inverse.setValidationDate(r.getValidationDate)
return List(r, inverse) return List(r, inverse)
} }
} }

4
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/resolution/SparkResolveRelation.scala
View File

@ -104,14 +104,14 @@ object SparkResolveRelation {
JObject(pids) <- json \\ "instance" \ "pid" JObject(pids) <- json \\ "instance" \ "pid"
JField("value", JString(pidValue)) <- pids JField("value", JString(pidValue)) <- pids
JField("qualifier", JObject(qualifier)) <- pids JField("qualifier", JObject(qualifier)) <- pids
JField("classname", JString(pidType)) <- qualifier JField("classid", JString(pidType)) <- qualifier
} yield (pidValue, pidType) } yield (pidValue, pidType)
val alternateIds: List[(String, String)] = for { val alternateIds: List[(String, String)] = for {
JObject(pids) <- json \\ "alternateIdentifier" JObject(pids) <- json \\ "alternateIdentifier"
JField("value", JString(pidValue)) <- pids JField("value", JString(pidValue)) <- pids
JField("qualifier", JObject(qualifier)) <- pids JField("qualifier", JObject(qualifier)) <- pids
JField("classname", JString(pidType)) <- qualifier JField("classid", JString(pidType)) <- qualifier
} yield (pidValue, pidType) } yield (pidValue, pidType)
(id, result ::: alternateIds) (id, result ::: alternateIds)

2
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/resolution/oozie_app/workflow.xml
View File

@ -24,7 +24,7 @@
--executor-cores=${sparkExecutorCores} --executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory} --driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners} --conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.shuffle.partitions=3000 --conf spark.sql.shuffle.partitions=8000
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}