101 lines
4.1 KiB
XML
101 lines
4.1 KiB
XML
<workflow-app name="Software-Heritage-Integration-Workflow" xmlns="uri:oozie:workflow:0.5">
|
|
<!-- <parameters>-->
|
|
<!-- <property>-->
|
|
<!-- <name>apiDescription</name>-->
|
|
<!-- <description>A json encoding of the API Description class</description>-->
|
|
<!-- </property>-->
|
|
<!-- <property>-->
|
|
<!-- <name>dataSourceInfo</name>-->
|
|
<!-- <description>A json encoding of the Datasource Info</description>-->
|
|
<!-- </property>-->
|
|
<!-- <property>-->
|
|
<!-- <name>identifierPath</name>-->
|
|
<!-- <description>An xpath to retrieve the metadata identifier for the generation of DNet Identifier </description>-->
|
|
<!-- </property>-->
|
|
<!-- <property>-->
|
|
<!-- <name>metadataEncoding</name>-->
|
|
<!-- <description> The type of the metadata XML/JSON</description>-->
|
|
<!-- </property>-->
|
|
<!-- <property>-->
|
|
<!-- <name>timestamp</name>-->
|
|
<!-- <description>The timestamp of the collection date</description>-->
|
|
<!-- </property>-->
|
|
<!-- <property>-->
|
|
<!-- <name>workflowId</name>-->
|
|
<!-- <description>The identifier of the workflow</description>-->
|
|
<!-- </property>-->
|
|
<!-- <property>-->
|
|
<!-- <name>mdStoreID</name>-->
|
|
<!-- <description>The identifier of the mdStore</description>-->
|
|
<!-- </property>-->
|
|
<!-- <property>-->
|
|
<!-- <name>mdStoreManagerURI</name>-->
|
|
<!-- <description>The URI of the MDStore Manager</description>-->
|
|
<!-- </property>-->
|
|
|
|
<!-- <property>-->
|
|
<!-- <name>dnetMessageManagerURL</name>-->
|
|
<!-- <description>The URI of the Dnet Message Manager</description>-->
|
|
<!-- </property>-->
|
|
<!-- <property>-->
|
|
<!-- <name>collectionMode</name>-->
|
|
<!-- <description>Should be REFRESH or INCREMENTAL</description>-->
|
|
<!-- </property>-->
|
|
|
|
<!-- <property>-->
|
|
<!-- <name>collection_java_xmx</name>-->
|
|
<!-- <value>-Xmx200m</value>-->
|
|
<!-- <description>Used to configure the heap size for the map JVM process. Should be 80% of mapreduce.map.memory.mb.</description>-->
|
|
<!-- </property>-->
|
|
|
|
|
|
<!-- </parameters>-->
|
|
|
|
<global>
|
|
<job-tracker>${jobTracker}</job-tracker>
|
|
<name-node>${nameNode}</name-node>
|
|
</global>
|
|
|
|
<start to="startFrom"/>
|
|
|
|
<kill name="Kill">
|
|
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
|
</kill>
|
|
|
|
<decision name="startFrom">
|
|
<switch>
|
|
<case to="collect-software-repository-urls">${wf:conf('startFrom') eq 'collect-software-repository-urls'}</case>
|
|
<default to="collect-software-repository-urls"/>
|
|
</switch>
|
|
</decision>
|
|
|
|
<action name="collect-software-repository-urls">
|
|
<spark xmlns="uri:oozie:spark-action:0.2">
|
|
<master>yarn</master>
|
|
<mode>cluster</mode>
|
|
<name>Collect software repository URLs</name>
|
|
<class>eu.dnetlib.dhp.swh.CollectSoftwareRepositoryURLs</class>
|
|
<jar>dhp-swh-${projectVersion}.jar</jar>
|
|
<spark-opts>
|
|
--executor-memory=${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}${spark2EventLogDir}
|
|
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
|
|
</spark-opts>
|
|
|
|
<arg>--softwareCodeRepositoryURLs</arg><arg>${softwareCodeRepositoryURLs}</arg>
|
|
<arg>--hiveDbName</arg><arg>${hiveDbName}</arg>
|
|
<arg>--hiveMetastoreUris</arg><arg>${hiveMetastoreUris}</arg>
|
|
|
|
</spark>
|
|
<ok to="End"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
|
|
<end name="End"/>
|
|
|
|
</workflow-app> |