michele.artini
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

manually merged PR#139

This commit is contained in:
Claudio Atzori 2021-08-13 17:15:53 +02:00
parent d43667d857 5856ca8a7b
commit 2c0a05f11a
4 changed files with 6 additions and 224 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
dhp-workflows/dhp-doiboost/src/main/resources/eu/dnetlib/dhp/doiboost/crossref_dump_reader/oozie_app/config-default.xml
View File

@ -1,42 +0,0 @@
<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>

128
dhp-workflows/dhp-doiboost/src/main/resources/eu/dnetlib/dhp/doiboost/crossref_dump_reader/oozie_app/workflow.xml
View File

@ -1,128 +0,0 @@
<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>
<property>
<name>crossrefdumptoken</name>
<description>the token for the API 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="removeFiles">
<fs>
<delete path="${crossrefDumpPath}/${crossrefdumpfilename}"/>
<delete path="${crossrefDumpPath}/files"/>
<delete path="${crossrefDumpPath}/crossref_unpack"/>
</fs>
<ok to="DownloadDump"/>
<error to="Kill"/>
</action>
<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>
<argument>${crossrefdumptoken}</argument>
<env-var>HADOOP_USER_NAME=${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>
<end name="End"/>
</workflow-app>

57
dhp-workflows/dhp-doiboost/src/main/resources/eu/dnetlib/dhp/doiboost/preprocess/oozie_app/workflow.xml
View File

@ -1,4 +1,4 @@
<workflow-app name="Generate DOIBoost ActionSet for BETA - PREPROCESS" xmlns="uri:oozie:workflow:0.5"> <workflow-app name="Generate DOIBoost ActionSet - PREPROCESS" xmlns="uri:oozie:workflow:0.5">
<parameters> <parameters>
<property> <property>
<name>sparkDriverMemory</name> <name>sparkDriverMemory</name>
@ -63,12 +63,10 @@
<decision name="resume_from"> <decision name="resume_from">
<switch> <switch>
<case to="UnpackCrossrefEntries">${wf:conf('resumeFrom') eq 'UnpackCrossrefEntries'}</case>
<case to="GenerateCrossrefDataset">${wf:conf('resumeFrom') eq 'GenerateCrossrefDataset'}</case>
<case to="ResetMagWorkingPath">${wf:conf('resumeFrom') eq 'ResetMagWorkingPath'}</case> <case to="ResetMagWorkingPath">${wf:conf('resumeFrom') eq 'ResetMagWorkingPath'}</case>
<case to="ConvertMagToDataset">${wf:conf('resumeFrom') eq 'ConvertMagToDataset'}</case> <case to="ConvertMagToDataset">${wf:conf('resumeFrom') eq 'ConvertMagToDataset'}</case>
<case to="PreProcessORCID">${wf:conf('resumeFrom') eq 'PreProcessORCID'}</case> <case to="PreProcessORCID">${wf:conf('resumeFrom') eq 'PreProcessORCID'}</case>
<default to="ImportCrossRef"/> <default to="GenerateCrossrefDataset"/> <!-- first action to be done when downloadDump is to be performed -->
</switch> </switch>
</decision> </decision>
@ -77,46 +75,6 @@
</kill> </kill>
<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>${nameNode}</arg>
<arg>--crossrefFileNameTarGz</arg><arg>${crossrefDumpPath}/crossref.tar.gz</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>${crossrefDumpPath}/crossref_unpack/</arg>
</spark>
<ok to="GenerateCrossrefDataset"/>
<error to="Kill"/>
</action>
<action name="GenerateCrossrefDataset"> <action name="GenerateCrossrefDataset">
<spark xmlns="uri:oozie:spark-action:0.2"> <spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn-cluster</master> <master>yarn-cluster</master>
@ -139,18 +97,11 @@
<arg>--targetPath</arg><arg>${inputPathCrossref}/crossref_ds</arg> <arg>--targetPath</arg><arg>${inputPathCrossref}/crossref_ds</arg>
</spark> </spark>
<ok to="removeFiles"/> <ok to="ResetMagWorkingPath"/>
<error to="Kill"/> <error to="Kill"/>
</action> </action>
<action name="removeFiles">
<fs>
<!-- <delete path="${crossrefDumpPath}/files"/>-->
<delete path="${crossrefDumpPath}/crossref_unpack/"/>
</fs>
<ok to="ResetMagWorkingPath"/>
<error to="Kill"/>
</action>
<!-- MAG SECTION --> <!-- MAG SECTION -->
<action name="ResetMagWorkingPath"> <action name="ResetMagWorkingPath">

3
dhp-workflows/dhp-doiboost/src/main/resources/eu/dnetlib/dhp/doiboost/process/oozie_app/workflow.xml
View File

@ -1,4 +1,4 @@
<workflow-app name="Generate DOIBoost ActionSet for BETA - PROCESS" xmlns="uri:oozie:workflow:0.5"> <workflow-app name="Generate DOIBoost ActionSet - PROCESS" xmlns="uri:oozie:workflow:0.5">
<parameters> <parameters>
<property> <property>
<name>sparkDriverMemory</name> <name>sparkDriverMemory</name>
@ -75,6 +75,7 @@
<decision name="resume_from"> <decision name="resume_from">
<switch> <switch>
<case to="End">${wf:conf('resumeFrom') eq 'Skip'}</case>
<case to="ProcessMAG">${wf:conf('resumeFrom') eq 'PreprocessMag'}</case> <case to="ProcessMAG">${wf:conf('resumeFrom') eq 'PreprocessMag'}</case>
<case to="ProcessUW">${wf:conf('resumeFrom') eq 'PreprocessUW'}</case> <case to="ProcessUW">${wf:conf('resumeFrom') eq 'PreprocessUW'}</case>
<case to="ProcessORCID">${wf:conf('resumeFrom') eq 'ProcessORCID'}</case> <case to="ProcessORCID">${wf:conf('resumeFrom') eq 'ProcessORCID'}</case>