forked from D-Net/dnet-hadoop
New properties for the orcid to result propagation through semantic relation
This commit is contained in:
parent
b50166b9ad
commit
3a4ccb26c0
|
|
@ -0,0 +1,20 @@
|
||||||
|
[
|
||||||
|
{
|
||||||
|
"paramName":"mt",
|
||||||
|
"paramLongName":"master",
|
||||||
|
"paramDescription": "should be local or yarn",
|
||||||
|
"paramRequired": true
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"paramName":"s",
|
||||||
|
"paramLongName":"sourcePath",
|
||||||
|
"paramDescription": "the path of the sequencial file to read",
|
||||||
|
"paramRequired": true
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"paramName":"as",
|
||||||
|
"paramLongName":"allowedsemrels",
|
||||||
|
"paramDescription": "the allowed sematinc relations for propagation",
|
||||||
|
"paramRequired": true
|
||||||
|
}
|
||||||
|
]
|
||||||
|
|
@ -0,0 +1,18 @@
|
||||||
|
<configuration>
|
||||||
|
<property>
|
||||||
|
<name>jobTracker</name>
|
||||||
|
<value>yarnRM</value>
|
||||||
|
</property>
|
||||||
|
<property>
|
||||||
|
<name>nameNode</name>
|
||||||
|
<value>hdfs://nameservice1</value>
|
||||||
|
</property>
|
||||||
|
<property>
|
||||||
|
<name>oozie.use.system.libpath</name>
|
||||||
|
<value>true</value>
|
||||||
|
</property>
|
||||||
|
<property>
|
||||||
|
<name>oozie.action.sharelib.for.spark</name>
|
||||||
|
<value>spark2</value>
|
||||||
|
</property>
|
||||||
|
</configuration>
|
||||||
|
|
@ -0,0 +1,55 @@
|
||||||
|
<workflow-app name="orcid_to_result_from_semrel_propagation" xmlns="uri:oozie:workflow:0.5">
|
||||||
|
<parameters>
|
||||||
|
<property>
|
||||||
|
<name>sourcePath</name>
|
||||||
|
<description>the source path</description>
|
||||||
|
</property>
|
||||||
|
<property>
|
||||||
|
<name>allowedsemrels</name>
|
||||||
|
<description>the semantic relationships allowed for propagation</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>
|
||||||
|
</parameters>
|
||||||
|
|
||||||
|
<start to="OrcidToResultFromSemRelPropagation"/>
|
||||||
|
|
||||||
|
<kill name="Kill">
|
||||||
|
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
||||||
|
</kill>
|
||||||
|
|
||||||
|
<action name="OrcidToResultFromSemRelPropagation">
|
||||||
|
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||||
|
<job-tracker>${jobTracker}</job-tracker>
|
||||||
|
<name-node>${nameNode}</name-node>
|
||||||
|
<master>yarn-cluster</master>
|
||||||
|
<mode>cluster</mode>
|
||||||
|
<name>AffiliatioPropagation</name>
|
||||||
|
<class>eu.dnetlib.dhp.resulttoorganizationfrominstrepo.SparkResultToOrganizationFromIstRepoJob</class>
|
||||||
|
<jar>dhp-propagation-${projectVersion}.jar</jar>
|
||||||
|
<spark-opts>--executor-memory ${sparkExecutorMemory}
|
||||||
|
--executor-cores ${sparkExecutorCores}
|
||||||
|
--driver-memory=${sparkDriverMemory}
|
||||||
|
--conf spark.extraListeners="com.cloudera.spark.lineage.NavigatorAppListener"
|
||||||
|
--conf spark.sql.queryExecutionListeners="com.cloudera.spark.lineage.NavigatorQueryListener"
|
||||||
|
</spark-opts>
|
||||||
|
<arg>-mt</arg> <arg>yarn-cluster</arg>
|
||||||
|
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
|
||||||
|
<arg>--allowedsemrels</arg><arg>${allowedsemrels}</arg>
|
||||||
|
</spark>
|
||||||
|
<ok to="End"/>
|
||||||
|
<error to="Kill"/>
|
||||||
|
</action>
|
||||||
|
|
||||||
|
<end name="End"/>
|
||||||
|
</workflow-app>
|
||||||
|
|
@ -0,0 +1,20 @@
|
||||||
|
[
|
||||||
|
{
|
||||||
|
"paramName":"mt",
|
||||||
|
"paramLongName":"master",
|
||||||
|
"paramDescription": "should be local or yarn",
|
||||||
|
"paramRequired": true
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"paramName":"s",
|
||||||
|
"paramLongName":"sourcePath",
|
||||||
|
"paramDescription": "the path of the sequencial file to read",
|
||||||
|
"paramRequired": true
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"paramName":"as",
|
||||||
|
"paramLongName":"allowedsemrels",
|
||||||
|
"paramDescription": "the allowed sematinc relations for propagation",
|
||||||
|
"paramRequired": true
|
||||||
|
}
|
||||||
|
]
|
||||||
|
|
@ -0,0 +1,18 @@
|
||||||
|
<configuration>
|
||||||
|
<property>
|
||||||
|
<name>jobTracker</name>
|
||||||
|
<value>yarnRM</value>
|
||||||
|
</property>
|
||||||
|
<property>
|
||||||
|
<name>nameNode</name>
|
||||||
|
<value>hdfs://nameservice1</value>
|
||||||
|
</property>
|
||||||
|
<property>
|
||||||
|
<name>oozie.use.system.libpath</name>
|
||||||
|
<value>true</value>
|
||||||
|
</property>
|
||||||
|
<property>
|
||||||
|
<name>oozie.action.sharelib.for.spark</name>
|
||||||
|
<value>spark2</value>
|
||||||
|
</property>
|
||||||
|
</configuration>
|
||||||
|
|
@ -0,0 +1,55 @@
|
||||||
|
<workflow-app name="result_to_community_from_semrel_propagation" xmlns="uri:oozie:workflow:0.5">
|
||||||
|
<parameters>
|
||||||
|
<property>
|
||||||
|
<name>sourcePath</name>
|
||||||
|
<description>the source path</description>
|
||||||
|
</property>
|
||||||
|
<property>
|
||||||
|
<name>allowedsemrels</name>
|
||||||
|
<description>the semantic relationships allowed for propagation</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>
|
||||||
|
</parameters>
|
||||||
|
|
||||||
|
<start to="ResultToCommunityFromSemRelPropagation"/>
|
||||||
|
|
||||||
|
<kill name="Kill">
|
||||||
|
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
||||||
|
</kill>
|
||||||
|
|
||||||
|
<action name="ResultToCommunityFromSemRelPropagation">
|
||||||
|
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||||
|
<job-tracker>${jobTracker}</job-tracker>
|
||||||
|
<name-node>${nameNode}</name-node>
|
||||||
|
<master>yarn-cluster</master>
|
||||||
|
<mode>cluster</mode>
|
||||||
|
<name>AffiliatioPropagation</name>
|
||||||
|
<class>eu.dnetlib.dhp.resulttoorganizationfrominstrepo.SparkResultToOrganizationFromIstRepoJob</class>
|
||||||
|
<jar>dhp-propagation-${projectVersion}.jar</jar>
|
||||||
|
<spark-opts>--executor-memory ${sparkExecutorMemory}
|
||||||
|
--executor-cores ${sparkExecutorCores}
|
||||||
|
--driver-memory=${sparkDriverMemory}
|
||||||
|
--conf spark.extraListeners="com.cloudera.spark.lineage.NavigatorAppListener"
|
||||||
|
--conf spark.sql.queryExecutionListeners="com.cloudera.spark.lineage.NavigatorQueryListener"
|
||||||
|
</spark-opts>
|
||||||
|
<arg>-mt</arg> <arg>yarn-cluster</arg>
|
||||||
|
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
|
||||||
|
<arg>--allowedsemrels</arg><arg>${allowedsemrels}</arg>
|
||||||
|
</spark>
|
||||||
|
<ok to="End"/>
|
||||||
|
<error to="Kill"/>
|
||||||
|
</action>
|
||||||
|
|
||||||
|
<end name="End"/>
|
||||||
|
</workflow-app>
|
||||||
Loading…
Reference in New Issue