new workflow for downloading the dump of crossref and unpack it

This commit is contained in:
Miriam Baglioni 2021-08-04 18:29:03 +02:00
parent b4eb026c8b
commit 1965e4eece
5 changed files with 168 additions and 1 deletions

View File

@ -0,0 +1,42 @@
<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>
<property>
<name>oozie.launcher.mapreduce.user.classpath.first</name>
<value>true</value>
</property>
<property>
<name>hive_metastore_uris</name>
<value>thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083</value>
</property>
<property>
<name>spark2YarnHistoryServerAddress</name>
<value>http://iis-cdh5-test-gw.ocean.icm.edu.pl:18089</value>
</property>
<property>
<name>spark2EventLogDir</name>
<value>/user/spark/spark2ApplicationHistory</value>
</property>
<property>
<name>spark2ExtraListeners</name>
<value>"com.cloudera.spark.lineage.NavigatorAppListener"</value>
</property>
<property>
<name>spark2SqlQueryExecutionListeners</name>
<value>"com.cloudera.spark.lineage.NavigatorQueryListener"</value>
</property>
</configuration>

View File

@ -0,0 +1,2 @@
#!/bin/bash
curl -LSs -H "Crossref-Plus-API-Token: Bearer eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpc3MiOiJodHRwOi8vY3Jvc3NyZWYub3JnLyIsImF1ZCI6Im1kcGx1cyIsImp0aSI6Ijk3YTZkNGVkLTg5MjktNGQ2Yi05NWY1LTY2YmMyNDgzNTRjNCJ9.5DPM4gRibUBYBtrUSpRz3RGHYVB-8f61jQBW_q-r-hs" $1 | hdfs dfs -put - $2/$3

View File

@ -0,0 +1,2 @@
#!/bin/bash
curl -LSs $1 | hdfs dfs -put - $2/$3

View File

@ -0,0 +1,121 @@
<workflow-app name="CROSSREF DUMP - DOWNLOAD" xmlns="uri:oozie:workflow:0.5">
<parameters>
<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>
<!-- Crossref Parameters -->
<property>
<name>crossrefdumpfilename</name>
<description>the Crossref input path</description>
</property>
<property>
<name>crossrefDumpPath</name>
<description>the Crossref dump path</description>
</property>
</parameters>
<global>
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>oozie.action.sharelib.for.spark</name>
<value>${oozieActionShareLibForSpark2}</value>
</property>
</configuration>
</global>
<start to="removeFiles"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="DownloadDump">
<shell xmlns="uri:oozie:shell-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>mapred.job.queue.name</name>
<value>${queueName}</value>
</property>
</configuration>
<exec>download.sh</exec>
<argument>${url}</argument>
<argument>${crossrefDumpPath}</argument>
<argument>${crossrefdumpfilename}</argument>
<env-var>HADOOP_USER_NAME=${wf:user()}</env-var>
<file>download.sh</file>
<capture-output/>
</shell>
<ok to="ImportCrossRef"/>
<error to="Kill"/>
</action>
<action name="ImportCrossRef">
<java>
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<main-class>eu.dnetlib.doiboost.crossref.ExtractCrossrefRecords</main-class>
<arg>--hdfsServerUri</arg><arg>${nameNode}</arg>
<arg>--crossrefFileNameTarGz</arg><arg>${crossrefdumpfilename}</arg>
<arg>--workingPath</arg><arg>${crossrefDumpPath}</arg>
<arg>--outputPath</arg><arg>${crossrefDumpPath}/files/</arg>
</java>
<ok to="UnpackCrossrefEntries"/>
<error to="Kill"/>
</action>
<action name="UnpackCrossrefEntries">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>SparkUnpackCrossrefEntries</name>
<class>eu.dnetlib.doiboost.crossref.UnpackCrtossrefEntries</class>
<jar>dhp-doiboost-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.sql.shuffle.partitions=3840
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--master</arg><arg>yarn-cluster</arg>
<arg>--sourcePath</arg><arg>${crossrefDumpPath}/files</arg>
<arg>--targetPath</arg><arg>${crossrefDumpPath}/crossref_unpack/</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<action name="removeFiles">
<fs>
<delete path="${crossrefDumpPath}/files"/>
<delete path="${crossrefDumpPath}/crossref_unpack/"/>
</fs>
<ok to="DownloadDump"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>

View File

@ -1,2 +1,2 @@
#!bin/bash
#!/bin/bash
curl -LSs $1 | hdfs dfs -put - $2/$3