D-Net
/
dnet-hadoop
14
5
Fork 11
Code Issues 14 Pull Requests 13 Projects 2 Releases 2 Wiki Activity

master #11

Manually merged
claudio.atzori merged 275 commits from :master into enrichment_wfs 2020-05-11 15:14:56 +02:00
Conversation 1 Commits 275 Files Changed 156 +1 -41
2 changed files with 1 additions and 41 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files
Showing only changes of commit 5e1bd67680 - Show all commits

6
dhp-workflows/dhp-propagation/src/main/resources/eu/dnetlib/dhp/projecttoresult/input_projecttoresult_parameters.json
View File

@ -1,10 +1,4 @@
[
{
"paramName":"s",
"paramLongName":"sourcePath",
"paramDescription": "the path of the sequencial file to read",
"paramRequired": true
},
{
"paramName":"h",
"paramLongName":"hive_metastore_uris",

36
dhp-workflows/dhp-propagation/src/main/resources/eu/dnetlib/dhp/projecttoresult/oozie_app/workflow.xml
View File

@ -31,7 +31,6 @@
</parameters>
<start to="reset-outputpath"/>
<!--<start to="prepare_project_results_association"/>-->
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
@ -98,7 +97,7 @@
--conf spark.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/relation</arg>
<!-- <arg>&#45;&#45;sourcePath</arg><arg>${sourcePath}/relation</arg>-->
<arg>--writeUpdate</arg><arg>${writeUpdate}</arg>
<arg>--saveGraph</arg><arg>${saveGraph}</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
@ -110,38 +109,5 @@
<error to="Kill"/>
</action>
<action name="ProjectPropagation">
<spark xmlns="uri:oozie:spark-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>ProjectToResultPropagation</name>
<class>eu.dnetlib.dhp.projecttoresult.SparkResultToProjectThroughSemRelJob2</class>
<jar>dhp-propagation-${projectVersion}.jar</jar>
<spark-opts>
--num-executors=${sparkExecutorNumber}
--executor-memory=${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}${spark2EventLogDir}
--conf spark.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--allowedsemrels</arg><arg>${allowedsemrels}</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--writeUpdate</arg><arg>${writeUpdate}</arg>
<arg>--saveGraph</arg><arg>${saveGraph}</arg>
<arg>--potentialUpdatePath</arg><arg>${workingDir}/projecttoresult_propagation/preparedInfo/potentialUpdates</arg>
<arg>--alreadyLinkedPath</arg><arg>${workingDir}/projecttoresult_propagation/preparedInfo/alreadyLinked</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>