379 lines
18 KiB
XML
379 lines
18 KiB
XML
<workflow-app name="country_propagation" xmlns="uri:oozie:workflow:0.5">
|
|
<parameters>
|
|
<property>
|
|
<name>sourcePath</name>
|
|
<description>the source path</description>
|
|
</property>
|
|
<property>
|
|
<name>whitelist</name>
|
|
<description>the white list</description>
|
|
</property>
|
|
<property>
|
|
<name>allowedtypes</name>
|
|
<description>the allowed types</description>
|
|
</property>
|
|
<property>
|
|
<name>startFrom</name>
|
|
<value>undelete</value>
|
|
</property>
|
|
</parameters>
|
|
|
|
<global>
|
|
<job-tracker>${jobTracker}</job-tracker>
|
|
<name-node>${nameNode}</name-node>
|
|
<configuration>
|
|
<property>
|
|
<name>oozie.action.sharelib.for.spark</name>
|
|
<value>${oozieActionShareLibForSpark2}</value>
|
|
</property>
|
|
</configuration>
|
|
</global>
|
|
|
|
<start to="resumeFrom"/>
|
|
|
|
<decision name="resumeFrom">
|
|
<switch>
|
|
<case to="prepare_datasource_country_association">${wf:conf('startFrom') eq 'undelete'}</case>
|
|
|
|
<default to="reset_outputpath"/>
|
|
</switch>
|
|
</decision>
|
|
|
|
<kill name="Kill">
|
|
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
|
</kill>
|
|
|
|
<action name="reset_outputpath">
|
|
<fs>
|
|
<delete path="${workingDir}"/>
|
|
<mkdir path="${workingDir}"/>
|
|
</fs>
|
|
<ok to="prepare_datasource_country_association"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
|
|
|
|
<action name="prepare_datasource_country_association">
|
|
<spark xmlns="uri:oozie:spark-action:0.2">
|
|
<master>yarn</master>
|
|
<mode>cluster</mode>
|
|
<name>PrepareDatasourceCountryAssociation</name>
|
|
<class>eu.dnetlib.dhp.countrypropagation.PrepareDatasourceCountryAssociation</class>
|
|
<jar>dhp-enrichment-${projectVersion}.jar</jar>
|
|
<spark-opts>
|
|
--executor-cores=${sparkExecutorCores}
|
|
--executor-memory=${sparkExecutorMemory}
|
|
--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=3840
|
|
</spark-opts>
|
|
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
|
|
<arg>--whitelist</arg><arg>${whitelist}</arg>
|
|
<arg>--allowedtypes</arg><arg>${allowedtypes}</arg>
|
|
<arg>--outputPath</arg><arg>${workingDir}/country/preparedInfo</arg>
|
|
</spark>
|
|
<ok to="fork_prepare_result_country"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
|
|
<fork name="fork_prepare_result_country">
|
|
<path start="prepareresult_publication"/>
|
|
<path start="prepareresult_dataset"/>
|
|
<path start="prepareresult_otherresearchproduct"/>
|
|
<path start="prepareresult_software"/>
|
|
</fork>
|
|
|
|
<action name="prepareresult_publication">
|
|
<spark xmlns="uri:oozie:spark-action:0.2">
|
|
<master>yarn</master>
|
|
<mode>cluster</mode>
|
|
<name>prepareResultCountry-Publication</name>
|
|
<class>eu.dnetlib.dhp.countrypropagation.PrepareResultCountrySet</class>
|
|
<jar>dhp-enrichment-${projectVersion}.jar</jar>
|
|
<spark-opts>
|
|
--executor-cores=${sparkExecutorCores}
|
|
--executor-memory=${sparkExecutorMemory}
|
|
--driver-memory=${sparkDriverMemory}
|
|
--conf spark.extraListeners=${spark2ExtraListeners}
|
|
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
|
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
|
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
|
--conf spark.speculation=false
|
|
--conf spark.hadoop.mapreduce.map.speculative=false
|
|
--conf spark.hadoop.mapreduce.reduce.speculative=false
|
|
--conf spark.sql.shuffle.partitions=3840
|
|
</spark-opts>
|
|
<arg>--sourcePath</arg><arg>${sourcePath}/publication</arg>
|
|
<arg>--outputPath</arg><arg>${workingDir}/country/publication</arg>
|
|
<arg>--workingPath</arg><arg>${workingDir}/country/workingP</arg>
|
|
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
|
|
<arg>--preparedInfoPath</arg><arg>${workingDir}/country/preparedInfo</arg>
|
|
</spark>
|
|
<ok to="wait_prepare"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
|
|
<action name="prepareresult_dataset">
|
|
<spark xmlns="uri:oozie:spark-action:0.2">
|
|
<master>yarn</master>
|
|
<mode>cluster</mode>
|
|
<name>prepareResultCountry-Dataset</name>
|
|
<class>eu.dnetlib.dhp.countrypropagation.PrepareResultCountrySet</class>
|
|
<jar>dhp-enrichment-${projectVersion}.jar</jar>
|
|
<spark-opts>
|
|
--executor-cores=${sparkExecutorCores}
|
|
--executor-memory=${sparkExecutorMemory}
|
|
--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.speculation=false
|
|
--conf spark.hadoop.mapreduce.map.speculative=false
|
|
--conf spark.hadoop.mapreduce.reduce.speculative=false
|
|
--conf spark.sql.shuffle.partitions=3840
|
|
</spark-opts>
|
|
<arg>--sourcePath</arg><arg>${sourcePath}/dataset</arg>
|
|
<arg>--outputPath</arg><arg>${workingDir}/country/dataset</arg>
|
|
<arg>--workingPath</arg><arg>${workingDir}/country/workingD</arg>
|
|
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
|
|
<arg>--preparedInfoPath</arg><arg>${workingDir}/country/preparedInfo</arg>
|
|
</spark>
|
|
<ok to="wait_prepare"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
|
|
<action name="prepareresult_otherresearchproduct">
|
|
<spark xmlns="uri:oozie:spark-action:0.2">
|
|
<master>yarn</master>
|
|
<mode>cluster</mode>
|
|
<name>prepareResultCountry-ORP</name>
|
|
<class>eu.dnetlib.dhp.countrypropagation.PrepareResultCountrySet</class>
|
|
<jar>dhp-enrichment-${projectVersion}.jar</jar>
|
|
<spark-opts>
|
|
--executor-cores=${sparkExecutorCores}
|
|
--executor-memory=${sparkExecutorMemory}
|
|
--driver-memory=${sparkDriverMemory}
|
|
--conf spark.extraListeners=${spark2ExtraListeners}
|
|
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
|
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
|
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
|
--conf spark.speculation=false
|
|
--conf spark.hadoop.mapreduce.map.speculative=false
|
|
--conf spark.hadoop.mapreduce.reduce.speculative=false
|
|
--conf spark.sql.shuffle.partitions=3840
|
|
</spark-opts>
|
|
<arg>--sourcePath</arg><arg>${sourcePath}/otherresearchproduct</arg>
|
|
<arg>--outputPath</arg><arg>${workingDir}/country/otherresearchproduct</arg>
|
|
<arg>--workingPath</arg><arg>${workingDir}/country/workingO</arg>
|
|
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
|
|
<arg>--preparedInfoPath</arg><arg>${workingDir}/country/preparedInfo</arg>
|
|
</spark>
|
|
<ok to="wait_prepare"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
|
|
<action name="prepareresult_software">
|
|
<spark xmlns="uri:oozie:spark-action:0.2">
|
|
<master>yarn</master>
|
|
<mode>cluster</mode>
|
|
<name>prepareResultCountry-Software</name>
|
|
<class>eu.dnetlib.dhp.countrypropagation.PrepareResultCountrySet</class>
|
|
<jar>dhp-enrichment-${projectVersion}.jar</jar>
|
|
<spark-opts>
|
|
--executor-cores=${sparkExecutorCores}
|
|
--executor-memory=${sparkExecutorMemory}
|
|
--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.speculation=false
|
|
--conf spark.hadoop.mapreduce.map.speculative=false
|
|
--conf spark.hadoop.mapreduce.reduce.speculative=false
|
|
--conf spark.sql.shuffle.partitions=3840
|
|
</spark-opts>
|
|
<arg>--sourcePath</arg><arg>${sourcePath}/software</arg>
|
|
<arg>--outputPath</arg><arg>${workingDir}/country/software</arg>
|
|
<arg>--workingPath</arg><arg>${workingDir}/country/workingS</arg>
|
|
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
|
|
<arg>--preparedInfoPath</arg><arg>${workingDir}/country/preparedInfo</arg>
|
|
</spark>
|
|
<ok to="wait_prepare"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
|
|
<join name="wait_prepare" to="fork_apply_country_propagation"/>
|
|
|
|
<fork name="fork_apply_country_propagation">
|
|
<path start="propagation_publication"/>
|
|
<path start="propagation_dataset"/>
|
|
<path start="propagation_otherresearchproduct"/>
|
|
<path start="propagation_software"/>
|
|
</fork>
|
|
|
|
<action name="propagation_publication">
|
|
<spark xmlns="uri:oozie:spark-action:0.2">
|
|
<master>yarn</master>
|
|
<mode>cluster</mode>
|
|
<name>countryPropagationForPublications</name>
|
|
<class>eu.dnetlib.dhp.countrypropagation.SparkCountryPropagationJob</class>
|
|
<jar>dhp-enrichment-${projectVersion}.jar</jar>
|
|
<spark-opts>
|
|
--executor-cores=${sparkExecutorCores}
|
|
--executor-memory=${sparkExecutorMemory}
|
|
--driver-memory=${sparkDriverMemory}
|
|
--conf spark.extraListeners=${spark2ExtraListeners}
|
|
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
|
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
|
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
|
--conf spark.speculation=false
|
|
--conf spark.hadoop.mapreduce.map.speculative=false
|
|
--conf spark.hadoop.mapreduce.reduce.speculative=false
|
|
--conf spark.sql.shuffle.partitions=7680
|
|
</spark-opts>
|
|
<arg>--sourcePath</arg><arg>${sourcePath}/publication</arg>
|
|
<arg>--preparedInfoPath</arg><arg>${workingDir}/country/publication</arg>
|
|
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
|
|
<arg>--outputPath</arg><arg>${workingDir}/country/country/publication</arg>
|
|
</spark>
|
|
<ok to="wait"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
|
|
<action name="propagation_dataset">
|
|
<spark xmlns="uri:oozie:spark-action:0.2">
|
|
<master>yarn</master>
|
|
<mode>cluster</mode>
|
|
<name>countryPropagationForDataset</name>
|
|
<class>eu.dnetlib.dhp.countrypropagation.SparkCountryPropagationJob</class>
|
|
<jar>dhp-enrichment-${projectVersion}.jar</jar>
|
|
<spark-opts>
|
|
--executor-cores=${sparkExecutorCores}
|
|
--executor-memory=${sparkExecutorMemory}
|
|
--driver-memory=${sparkDriverMemory}
|
|
--conf spark.extraListeners=${spark2ExtraListeners}
|
|
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
|
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
|
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
|
--conf spark.speculation=false
|
|
--conf spark.hadoop.mapreduce.map.speculative=false
|
|
--conf spark.hadoop.mapreduce.reduce.speculative=false
|
|
--conf spark.sql.shuffle.partitions=3840
|
|
</spark-opts>
|
|
<arg>--sourcePath</arg><arg>${sourcePath}/dataset</arg>
|
|
<arg>--preparedInfoPath</arg><arg>${workingDir}/country/dataset</arg>
|
|
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
|
|
<arg>--outputPath</arg><arg>${workingDir}/country/country/dataset</arg>
|
|
</spark>
|
|
<ok to="wait"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
|
|
<action name="propagation_otherresearchproduct">
|
|
<spark xmlns="uri:oozie:spark-action:0.2">
|
|
<master>yarn</master>
|
|
<mode>cluster</mode>
|
|
<name>countryPropagationForORP</name>
|
|
<class>eu.dnetlib.dhp.countrypropagation.SparkCountryPropagationJob</class>
|
|
<jar>dhp-enrichment-${projectVersion}.jar</jar>
|
|
<spark-opts>
|
|
--executor-cores=${sparkExecutorCores}
|
|
--executor-memory=${sparkExecutorMemory}
|
|
--driver-memory=${sparkDriverMemory}
|
|
--conf spark.extraListeners=${spark2ExtraListeners}
|
|
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
|
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
|
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
|
--conf spark.speculation=false
|
|
--conf spark.hadoop.mapreduce.map.speculative=false
|
|
--conf spark.hadoop.mapreduce.reduce.speculative=false
|
|
--conf spark.sql.shuffle.partitions=3840
|
|
</spark-opts>
|
|
<arg>--sourcePath</arg><arg>${sourcePath}/otherresearchproduct</arg>
|
|
<arg>--preparedInfoPath</arg><arg>${workingDir}/country/otherresearchproduct</arg>
|
|
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
|
|
<arg>--outputPath</arg><arg>${workingDir}/country/country/otherresearchproduct</arg>
|
|
</spark>
|
|
<ok to="wait"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
|
|
<action name="propagation_software">
|
|
<spark xmlns="uri:oozie:spark-action:0.2">
|
|
<master>yarn</master>
|
|
<mode>cluster</mode>
|
|
<name>countryPropagationForSoftware</name>
|
|
<class>eu.dnetlib.dhp.countrypropagation.SparkCountryPropagationJob</class>
|
|
<jar>dhp-enrichment-${projectVersion}.jar</jar>
|
|
<spark-opts>
|
|
--executor-cores=${sparkExecutorCores}
|
|
--executor-memory=${sparkExecutorMemory}
|
|
--driver-memory=${sparkDriverMemory}
|
|
--conf spark.extraListeners=${spark2ExtraListeners}
|
|
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
|
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
|
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
|
--conf spark.speculation=false
|
|
--conf spark.hadoop.mapreduce.map.speculative=false
|
|
--conf spark.hadoop.mapreduce.reduce.speculative=false
|
|
--conf spark.sql.shuffle.partitions=3840
|
|
</spark-opts>
|
|
<arg>--sourcePath</arg><arg>${sourcePath}/software</arg>
|
|
<arg>--preparedInfoPath</arg><arg>${workingDir}/country/software</arg>
|
|
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
|
|
<arg>--outputPath</arg><arg>${workingDir}/country/country/software</arg>
|
|
</spark>
|
|
<ok to="wait"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
|
|
|
|
<join name="wait" to="move-results"/>
|
|
<action name="move-results">
|
|
<spark xmlns="uri:oozie:spark-action:0.2">
|
|
<master>yarn</master>
|
|
<mode>cluster</mode>
|
|
<name>community2resultfromorganization - move results</name>
|
|
<class>eu.dnetlib.dhp.MoveResult</class>
|
|
<jar>dhp-enrichment-${projectVersion}.jar</jar>
|
|
<spark-opts>
|
|
--executor-cores=6
|
|
--executor-memory=5G
|
|
--conf spark.executor.memoryOverhead=3g
|
|
--conf spark.sql.shuffle.partitions=3284
|
|
--driver-memory=${sparkDriverMemory}
|
|
--conf spark.extraListeners=${spark2ExtraListeners}
|
|
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
|
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
|
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
|
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
|
|
</spark-opts>
|
|
<arg>--sourcePath</arg><arg>${workingDir}/country/country/</arg>
|
|
<arg>--outputPath</arg><arg>${sourcePath}/</arg>
|
|
<!-- <arg>--outputPath</arg><arg>/tmp/miriam/rescomm/</arg>-->
|
|
</spark>
|
|
<ok to="deleteWD"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
<decision name="deleteWD">
|
|
<switch>
|
|
<case to="End">${wf:conf('startFrom') eq 'undelete'}</case>
|
|
<default to="reset_workingDir"/>
|
|
</switch>
|
|
</decision>
|
|
|
|
<action name="reset_workingDir">
|
|
<fs>
|
|
<delete path="${workingDir}"/>
|
|
<mkdir path="${workingDir}"/>
|
|
</fs>
|
|
<ok to="End"/>
|
|
<error to="Kill"/>
|
|
</action>
|
|
<end name="End"/>
|
|
|
|
</workflow-app> |