alessia.bardi
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

workflow to download the files

This commit is contained in:
Miriam Baglioni 2020-05-15 18:18:31 +02:00
parent 22cb9e0da7
commit 83c262a483
1 changed files with 57 additions and 88 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

145
dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionset/h2020programme/oozie_app/workflow.xml
View File

@ -1,112 +1,81 @@
<workflow-app name="CollectionWorkflow" xmlns="uri:oozie:workflow:0.5"> <workflow-app name="H2020Programme" xmlns="uri:oozie:workflow:0.5">
<parameters> <parameters>
<property> <property>
<name>sequenceFilePath</name> <name>projectFileURL</name>
<description>the path to store the sequence file of the native metadata collected</description> <description>the url where to get the projects file</description>
</property> </property>
<property> <property>
<name>mdStorePath</name> <name>programmeFileURL</name>
<description>the path of the native mdstore</description> <description>the url where to get the programme file</description>
</property> </property>
<property> <property>
<name>apiDescription</name> <name>outputPath</name>
<description>A json encoding of the API Description class</description> <description>path where to store the action set</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 idnentifier 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>
</parameters> </parameters>
<start to="DeleteMDStoresNative"/> <start to="deleteoutputpath"/>
<kill name="Kill"> <kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message> <message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill> </kill>
<action name="DeleteMDStoresNative"> <action name="deleteoutputpath">
<fs> <fs>
<mkdir path='${sequenceFilePath}'/> <delete path='${outputPath}'/>
<mkdir path='${mdStorePath}'/> <mkdir path='${outputPath}'/>
<delete path='${sequenceFilePath}'/>
<delete path='${mdStorePath}'/>
</fs> </fs>
<ok to="CollectionWorker"/> <ok to="get_project_file"/>
<error to="Kill"/> <error to="Kill"/>
</action> </action>
<action name="CollectionWorker">
<java>
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<main-class>eu.dnetlib.dhp.collection.worker.DnetCollectorWorker</main-class>
<java-opts>-p</java-opts><java-opts>${sequenceFilePath}</java-opts>
<java-opts>-a</java-opts><java-opts>${apiDescription}</java-opts>
<java-opts>-n</java-opts><java-opts>${nameNode}</java-opts>
<java-opts>-rh</java-opts><java-opts>${rmq_host}</java-opts>
<java-opts>-ru</java-opts><java-opts>${rmq_user}</java-opts>
<java-opts>-rp</java-opts><java-opts>${rmq_pwd}</java-opts>
<java-opts>-rr</java-opts><java-opts>${rmq_report}</java-opts>
<java-opts>-ro</java-opts><java-opts>${rmq_ongoing}</java-opts>
<java-opts>-u</java-opts><java-opts>sandro.labruzzo</java-opts>
<java-opts>-w</java-opts><java-opts>${workflowId}</java-opts>
</java>
<ok to="GenerateNativeStoreSparkJob"/>
<error to="Kill"/>
</action>
<action name="GenerateNativeStoreSparkJob">
<spark xmlns="uri:oozie:spark-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<master>yarn</master>
<mode>cluster</mode>
<name>GenerateNativeStoreSparkJob</name>
<class>eu.dnetlib.dhp.collection.GenerateNativeStoreSparkJob</class>
<jar>dhp-aggregations-1.0.0-SNAPSHOT.jar</jar>
<spark-opts>--num-executors 50 --conf spark.yarn.jars=&quot;hdfs://hadoop-rm1.garr-pa1.d4science.org:8020/user/oozie/share/lib/lib_20180405103059/spark2&quot;</spark-opts>
<arg>--encoding</arg> <arg>${metadataEncoding}</arg>
<arg>--dateOfCollection</arg> <arg>${timestamp}</arg>
<arg>--provenance</arg> <arg> ${dataSourceInfo}</arg>
<arg>--xpath</arg><arg>${identifierPath}</arg>
<arg>--input</arg><arg>${sequenceFilePath}</arg>
<arg>--output</arg><arg>${mdStorePath}</arg>
<arg>-rh</arg><arg>${rmq_host}</arg>
<arg>-ru</arg><arg>${rmq_user}</arg>
<arg>-rp</arg><arg>${rmq_pwd}</arg>
<arg>-rr</arg><arg>${rmq_report}</arg>
<arg>-ro</arg><arg>${rmq_ongoing}</arg>
<arg>-w</arg><arg>${workflowId}</arg>
</spark>
<ok to="End"/>
<error to="DropInvalidStore"/>
</action>
<action name="DropInvalidStore"> <action name="get_project_file">
<fs> <java>
<delete path='${mdStorePath}/../'/> <main-class>eu.dnetlib.dhp.actionset.h2020programme.GetFile</main-class>
</fs> <arg>--hdfsNameNode</arg><arg>${nameNode}</arg>
<ok to="Kill"/> <arg>--fileUrl</arg><arg>${projectFileURL}</arg>
<arg>--hdfsPath</arg><arg>${workingDir}/projects.csv</arg>
</java>
<ok to="shell_get_programme_file"/>
<error to="Kill"/> <error to="Kill"/>
</action> </action>
<action name="shell_get_programme_file">
<java>
<main-class>eu.dnetlib.dhp.actionset.h2020programme.GetFile</main-class>
<arg>--hdfsNameNode</arg><arg>${nameNode}</arg>
<arg>--fileUrl</arg><arg>${programmeFileURL}</arg>
<arg>--hdfsPath</arg><arg>${workingDir}/programme.csv</arg>
</java>
<ok to="End"/>
<error to="Kill"/>
</action>
<!-- <action name="create_actionset">-->
<!-- <spark xmlns="uri:oozie:spark-action:0.2">-->
<!-- <master>yarn</master>-->
<!-- <mode>cluster</mode>-->
<!-- <name>ProjectProgrammeAS</name>-->
<!-- <class>eu.dnetlib.dhp.actionset.h2020programme</class>-->
<!-- <jar>dhp-aggregation-${projectVersion}.jar</jar>-->
<!-- <spark-opts>-->
<!-- &#45;&#45;executor-cores=${sparkExecutorCores}-->
<!-- &#45;&#45;executor-memory=${sparkExecutorMemory}-->
<!-- &#45;&#45;driver-memory=${sparkDriverMemory}-->
<!-- &#45;&#45;conf spark.extraListeners=${spark2ExtraListeners}-->
<!-- &#45;&#45;conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}-->
<!-- &#45;&#45;conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}-->
<!-- &#45;&#45;conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}-->
<!-- &#45;&#45;conf spark.sql.shuffle.partitions=3840-->
<!-- </spark-opts>-->
<!-- <arg>&#45;&#45;sourcePath</arg><arg>${sourcePath}/relation</arg>-->
<!-- <arg>&#45;&#45;outputPath</arg><arg>${outputPath}/relation</arg>-->
<!-- <arg>&#45;&#45;hdfsPath</arg><arg>${workingDir}/blacklist</arg>-->
<!-- <arg>&#45;&#45;mergesPath</arg><arg>${workingDir}/mergesRelation</arg>-->
<!-- </spark>-->
<!-- <ok to="End"/>-->
<!-- <error to="Kill"/>-->
<!-- </action>-->
<end name="End"/> <end name="End"/>
</workflow-app> </workflow-app>