patch of mdstore records
parent
ad56a44fda
commit
e9f2b6037c
@ -0,0 +1,157 @@
|
||||
<workflow-app name="Test Import of Hdfs Stores" xmlns="uri:oozie:workflow:0.5">
|
||||
|
||||
<parameters>
|
||||
<property>
|
||||
<name>graphOutputPath</name>
|
||||
<description>the target path to store raw graph</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>contentPath</name>
|
||||
<description>path location to store (or reuse) content from the aggregator</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>mdstoreManagerUrl</name>
|
||||
<description>the address of the Mdstore Manager</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>isLookupUrl</name>
|
||||
<description>the address of the lookUp service</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>sparkDriverMemory</name>
|
||||
<description>memory for driver process</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>sparkExecutorMemory</name>
|
||||
<description>memory for individual executor</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>sparkExecutorCores</name>
|
||||
<description>number of cores used by single executor</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>oozieActionShareLibForSpark2</name>
|
||||
<description>oozie action sharelib for spark 2.*</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>spark2ExtraListeners</name>
|
||||
<value>com.cloudera.spark.lineage.NavigatorAppListener</value>
|
||||
<description>spark 2.* extra listeners classname</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>spark2SqlQueryExecutionListeners</name>
|
||||
<value>com.cloudera.spark.lineage.NavigatorQueryListener</value>
|
||||
<description>spark 2.* sql query execution listeners classname</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>spark2YarnHistoryServerAddress</name>
|
||||
<description>spark 2.* yarn history server address</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>spark2EventLogDir</name>
|
||||
<description>spark 2.* event log dir location</description>
|
||||
</property>
|
||||
</parameters>
|
||||
|
||||
<global>
|
||||
<job-tracker>${jobTracker}</job-tracker>
|
||||
<name-node>${nameNode}</name-node>
|
||||
<configuration>
|
||||
<property>
|
||||
<name>mapreduce.job.queuename</name>
|
||||
<value>${queueName}</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>oozie.launcher.mapred.job.queue.name</name>
|
||||
<value>${oozieLauncherQueueName}</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>oozie.action.sharelib.for.spark</name>
|
||||
<value>${oozieActionShareLibForSpark2}</value>
|
||||
</property>
|
||||
</configuration>
|
||||
</global>
|
||||
|
||||
<start to="ImportODF_hdfs"/>
|
||||
|
||||
<kill name="Kill">
|
||||
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
||||
</kill>
|
||||
|
||||
<action name="ImportODF_hdfs">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>ImportODF_hdfs</name>
|
||||
<class>eu.dnetlib.dhp.oa.graph.raw.MigrateHdfsMdstoresApplication</class>
|
||||
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--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}${spark2EventLogDir}
|
||||
</spark-opts>
|
||||
<arg>--hdfsPath</arg><arg>${contentPath}/odf_records_hdfs</arg>
|
||||
<arg>--mdstoreManagerUrl</arg><arg>${mdstoreManagerUrl}</arg>
|
||||
<arg>--mdFormat</arg><arg>ODF</arg>
|
||||
<arg>--mdLayout</arg><arg>store</arg>
|
||||
<arg>--mdInterpretation</arg><arg>cleaned</arg>
|
||||
</spark>
|
||||
<ok to="GenerateEntities"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<action name="GenerateEntities">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>GenerateEntities</name>
|
||||
<class>eu.dnetlib.dhp.oa.graph.raw.GenerateEntitiesApplication</class>
|
||||
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--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}${spark2EventLogDir}
|
||||
</spark-opts>
|
||||
<arg>--sourcePaths</arg><arg>${contentPath}/odf_records_hdfs</arg>
|
||||
<arg>--targetPath</arg><arg>${workingDir}/entities</arg>
|
||||
<arg>--isLookupUrl</arg><arg>${isLookupUrl}</arg>
|
||||
<arg>--shouldHashId</arg><arg>${shouldHashId}</arg>
|
||||
</spark>
|
||||
<ok to="GenerateGraph"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<action name="GenerateGraph">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>GenerateGraph</name>
|
||||
<class>eu.dnetlib.dhp.oa.graph.raw.DispatchEntitiesApplication</class>
|
||||
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--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}${spark2EventLogDir}
|
||||
--conf spark.sql.shuffle.partitions=7680
|
||||
</spark-opts>
|
||||
<arg>--sourcePath</arg><arg>${workingDir}/entities</arg>
|
||||
<arg>--graphRawPath</arg><arg>${workingDir}/graph_raw</arg>
|
||||
</spark>
|
||||
<ok to="End"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<end name="End"/>
|
||||
</workflow-app>
|
@ -0,0 +1,77 @@
|
||||
<record xmlns:oaf="http://namespace.openaire.eu/oaf"
|
||||
xmlns:oai="http://www.openarchives.org/OAI/2.0/"
|
||||
xmlns:datacite="http://datacite.org/schema/kernel-3"
|
||||
xmlns:dr="http://www.driver-repository.eu/namespace/dr"
|
||||
xmlns:dri="http://www.driver-repository.eu/namespace/dri">
|
||||
<header xmlns="http://www.openarchives.org/OAI/2.0/">
|
||||
<identifier>df76e73f-0483-49a4-a9bb-63f2f985574a</identifier>
|
||||
<datestamp>2020-09-30T08:17:54Z</datestamp>
|
||||
<setSpec>eudat-b2find</setSpec>
|
||||
<dr:dateOfTransformation>2021-05-20T13:43:52.888Z</dr:dateOfTransformation>
|
||||
<dri:objIdentifier>test________::92fe3efa47883b2f3401e6a4bd92e9d7</dri:objIdentifier>
|
||||
<dri:dateOfCollection>2020-05-21T05:26:15.93Z</dri:dateOfCollection>
|
||||
<dri:dateOfTransformation>2020-08-01T11:06:26.977Z</dri:dateOfTransformation>
|
||||
</header>
|
||||
<metadata>
|
||||
<resource xmlns="http://datacite.org/schema/kernel-4"
|
||||
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
|
||||
xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.3/metadata.xsd">
|
||||
<creators>
|
||||
<creator>
|
||||
<creatorName>Museum Sønderjylland</creatorName>
|
||||
</creator>
|
||||
</creators>
|
||||
<titles>
|
||||
<title>200202-124 Hjelmvrå</title>
|
||||
</titles>
|
||||
<descriptions>
|
||||
<description descriptionType="Abstract">This record describes
|
||||
ancient sites and monuments as well archaeological excavations
|
||||
undertaken by Danish museums. Excerpt of the Danish description of
|
||||
events: 1995-04-26: Ved en besigtigelse ud for stedet fandt Nørgård
|
||||
en større mængde skår i skovens udkant, liggende i nogle
|
||||
drængrøfter1995-04-26: Leif Nørgård, der er leder af Sønderjyllands
|
||||
Amatørarkæologer, havde ved en samtale med en tidligere ansat på
|
||||
motorvejsprojektet gennem Sønderjylland fået at vide, at man på
|
||||
dette sted havde fundet "urner".1995-04-26: Ved en besigtigelse ud
|
||||
for stedet fandt Nørgård en større mængde skår i skovens udkant,
|
||||
liggende i nogle drængrøfter1995-04-26: Leif Nørgård, der er leder
|
||||
af Sønderjyllands Amatørarkæologer, havde ved en samtale med en
|
||||
tidligere ansat på motorvejsprojektet gennem Sønderjylland fået at
|
||||
vide, at man på dette sted havde fundet "urner".</description>
|
||||
</descriptions>
|
||||
<geoLocations>
|
||||
<geoLocation>
|
||||
<geoLocationPlace>(9.376 LON, 55.220 LAT)</geoLocationPlace>
|
||||
</geoLocation>
|
||||
</geoLocations>
|
||||
<subjects>
|
||||
<subject>Enkeltfund</subject>
|
||||
<subject>Settlement</subject>
|
||||
<subject>Single find</subject>
|
||||
<subject>Archaeology</subject>
|
||||
</subjects>
|
||||
<alternateIdentifiers
|
||||
xmlns="http://datacite.org/schema/kernel-3">
|
||||
<alternateIdentifier
|
||||
xmlns="http://datacite.org/schema/kernel-4"
|
||||
alternateIdentifierType="URL">http://www.kulturarv.dk/fundogfortidsminder/Lokalitet/136540/</alternateIdentifier>
|
||||
</alternateIdentifiers>
|
||||
<publicationYear>2020</publicationYear>
|
||||
<publisher>Slots- og Kulturstyrelsen (www.slks.dk)</publisher>
|
||||
<language>Danish</language>
|
||||
<rightsList>
|
||||
<rights>Public</rights>
|
||||
</rightsList>
|
||||
<resourceType resourceTypeGeneral="Other">Dataset</resourceType>
|
||||
</resource>
|
||||
<dr:CobjCategory type="dataset">0021</dr:CobjCategory>
|
||||
<oaf:dateAccepted>2020-01-01</oaf:dateAccepted>
|
||||
<oaf:accessrights>UNKNOWN</oaf:accessrights>
|
||||
<oaf:language>Danish</oaf:language>
|
||||
<oaf:hostedBy name="B2FIND"
|
||||
id="re3data_____::r3d100012377" />
|
||||
<oaf:collectedFrom name="B2FIND"
|
||||
id="re3data_____::r3d100012377" />
|
||||
</metadata>
|
||||
</record>
|
Loading…
Reference in New Issue